From f4c20290509d7ed3a8fd5304577e7a4cc0b9d974 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Tue, 3 Apr 2007 03:49:53 +0000 Subject: Ok, no code is left in src, it's all in src/old. We'll gradually move code back into src as it's fixed and re-org'd. This includes tests, which, I may write a unit test system into libbu++ just to make my life easier. --- src/tests/clistress.cpp | 20 --- src/tests/confpair.cpp | 19 --- src/tests/connect.cpp | 38 ----- src/tests/exception.cpp | 16 -- src/tests/formula.cpp | 13 -- src/tests/fstring.cpp | 48 ------ src/tests/hash.cpp | 116 -------------- src/tests/hashtest.cpp | 107 ------------- src/tests/hashtest2.cpp | 15 -- src/tests/httpsrv/httpconnectionmonitor.cpp | 88 ----------- src/tests/httpsrv/httpconnectionmonitor.h | 16 -- src/tests/httpsrv/main.cpp | 22 --- src/tests/log.cpp | 29 ---- src/tests/md5test.cpp | 19 --- src/tests/ordhash.cpp | 48 ------ src/tests/param.cpp | 46 ------ src/tests/param.h | 21 --- src/tests/plugin/main.cpp | 14 -- src/tests/plugin/plugin.cpp | 10 -- src/tests/plugin/plugin.h | 14 -- src/tests/qsort.cpp | 228 ---------------------------- src/tests/sbuffer.cpp | 27 ---- src/tests/serialize.cpp | 30 ---- src/tests/serializetext.cpp | 28 ---- src/tests/sha1.cpp | 44 ------ src/tests/sptr.cpp | 55 ------- src/tests/srvstress.cpp | 91 ----------- src/tests/strhash.cpp | 12 -- src/tests/teltest/main.cpp | 21 --- src/tests/teltest/telnetmonitor.cpp | 54 ------- src/tests/teltest/telnetmonitor.h | 26 ---- src/tests/xmlreadtest.cpp | 29 ---- src/tests/xmlrepltest.cpp | 31 ---- src/tests/xmlwritetest.cpp | 48 ------ 34 files changed, 1443 deletions(-) delete mode 100644 src/tests/clistress.cpp delete mode 100644 src/tests/confpair.cpp delete mode 100644 src/tests/connect.cpp delete mode 100644 src/tests/exception.cpp delete mode 100644 src/tests/formula.cpp delete mode 100644 src/tests/fstring.cpp delete mode 100644 src/tests/hash.cpp delete mode 100644 src/tests/hashtest.cpp delete mode 100644 src/tests/hashtest2.cpp delete mode 100644 src/tests/httpsrv/httpconnectionmonitor.cpp delete mode 100644 src/tests/httpsrv/httpconnectionmonitor.h delete mode 100644 src/tests/httpsrv/main.cpp delete mode 100644 src/tests/log.cpp delete mode 100644 src/tests/md5test.cpp delete mode 100644 src/tests/ordhash.cpp delete mode 100644 src/tests/param.cpp delete mode 100644 src/tests/param.h delete mode 100644 src/tests/plugin/main.cpp delete mode 100644 src/tests/plugin/plugin.cpp delete mode 100644 src/tests/plugin/plugin.h delete mode 100644 src/tests/qsort.cpp delete mode 100644 src/tests/sbuffer.cpp delete mode 100644 src/tests/serialize.cpp delete mode 100644 src/tests/serializetext.cpp delete mode 100644 src/tests/sha1.cpp delete mode 100644 src/tests/sptr.cpp delete mode 100644 src/tests/srvstress.cpp delete mode 100644 src/tests/strhash.cpp delete mode 100644 src/tests/teltest/main.cpp delete mode 100644 src/tests/teltest/telnetmonitor.cpp delete mode 100644 src/tests/teltest/telnetmonitor.h delete mode 100644 src/tests/xmlreadtest.cpp delete mode 100644 src/tests/xmlrepltest.cpp delete mode 100644 src/tests/xmlwritetest.cpp (limited to 'src/tests') diff --git a/src/tests/clistress.cpp b/src/tests/clistress.cpp deleted file mode 100644 index 6b0ac66..0000000 --- a/src/tests/clistress.cpp +++ /dev/null @@ -1,20 +0,0 @@ -#include "connection.h" - -int main() -{ - Connection c; - - c.open("localhost", 4001 ); - - c.appendOutput("w"); - c.writeOutput(); - - c.waitForInput( 6, 5, 0 ); - - printf("read: %s\n", c.getInput() ); - - c.close(); - - return 0; -} - diff --git a/src/tests/confpair.cpp b/src/tests/confpair.cpp deleted file mode 100644 index fb1b0d3..0000000 --- a/src/tests/confpair.cpp +++ /dev/null @@ -1,19 +0,0 @@ -#include "confpair.h" -#include - -using namespace std; - -int main() -{ - ConfPair p1("DebugMode"); - p1.value() = 12; - cout << p1.value() << "\n"; - p1.value() = 55; - cout << p1.value() << "\n"; - - ConfPairBase &p = p1; - - p = "33.12"; - cout << p.getAsString(); -} - diff --git a/src/tests/connect.cpp b/src/tests/connect.cpp deleted file mode 100644 index a9fca64..0000000 --- a/src/tests/connect.cpp +++ /dev/null @@ -1,38 +0,0 @@ -#include -#include -#include -#include -#include "connection.h" - -int main() -{ - Connection c; - c.open("127.0.0.1", 12457 ); - - { - int newSocket = c.getSocket(); - int flags; - - flags = fcntl(newSocket, F_GETFL, 0); - flags |= O_NONBLOCK; - if (fcntl(newSocket, F_SETFL, flags) < 0) - { - return false; - } - } - - for( int i = 0; i < 50; i++ ) - { - usleep( 100000 ); - int nbytes = c.readInput(); - if( nbytes == 0 ) - printf("0 bytes, EOF?\n"); - else - printf("Got %d bytes, whacky...\n", nbytes ); - } - - c.close(); - - return 0; -} - diff --git a/src/tests/exception.cpp b/src/tests/exception.cpp deleted file mode 100644 index 6417692..0000000 --- a/src/tests/exception.cpp +++ /dev/null @@ -1,16 +0,0 @@ -#include -#include "exceptions.h" - -int main() -{ - try - { - throw ExceptionBase( 42, "There was an error on line: %d", __LINE__ ); - } - catch( ExceptionBase &e ) - { - std::cout << "Error "<< e.getErrorCode() << ": " << e.what() << "\n"; - } - - throw ExceptionBase( 112, "This exception wasn't caught!"); -} diff --git a/src/tests/formula.cpp b/src/tests/formula.cpp deleted file mode 100644 index 976b039..0000000 --- a/src/tests/formula.cpp +++ /dev/null @@ -1,13 +0,0 @@ -#include "formula.h" - -int main( int argc, char *argv[] ) -{ - if( argc < 2 ) return 0; - - Formula f; - double dOut = f.run( argv[1] ); - printf("%s = %f\n", argv[1], dOut ); - - return 0; -} - diff --git a/src/tests/fstring.cpp b/src/tests/fstring.cpp deleted file mode 100644 index 271738c..0000000 --- a/src/tests/fstring.cpp +++ /dev/null @@ -1,48 +0,0 @@ -#include "hash.h" -#include "fstring.h" - -FString genThing() -{ - FString bob; - bob.append("ab "); - bob += "cd "; - bob += "efg"; - - printf("---bob------\n%08X: %s\n", (unsigned int)bob.c_str(), bob.c_str() ); - return bob; -} - -void thing( FString str ) -{ - printf("Hey: %s\n", str.c_str() ); -} - -#define pem printf("---------\n%08X: %s\n%08X: %s\n", (unsigned int)str.c_str(), str.c_str(), (unsigned int)str2.c_str(), str2.c_str() ); -int main( int argc, char *argv ) -{ - FString str("th"); - - str.prepend("Hello "); - str.append("ere."); - - FString str2( str ); - pem; - str += " What's up?"; - pem; - str2 += " How are you?"; - pem; - str = str2; - pem; - - str2 = genThing(); - pem; - - str = str2; - pem; - - thing( str2 ); - thing("test."); - - printf("%d == %d\n", __calcHashCode( str ), __calcHashCode( str.c_str() ) ); -} - diff --git a/src/tests/hash.cpp b/src/tests/hash.cpp deleted file mode 100644 index 2fc6968..0000000 --- a/src/tests/hash.cpp +++ /dev/null @@ -1,116 +0,0 @@ -#include "hash.h" -#include "staticstring.h" - -int main() -{ - const char *names[]={ - "Homer the Great", - "And Maggie Makes Three", - "Bart's Comet", - "Homie The Clown", - "Bart Vs Australia", - "Homer vs Patty and Selma", - "A star is burns", - "Lisa's Wedding", - "Two Dozen and One Greyhounds", - "The PTA Disbands", - "Round Springfield", - "The Springfield connection", - "Lemon of Troy", - "Who Shot Mr. Burns (Pt. 1)", - "Who Shot Mr. Burns (pt. 2)", - "Radioactive Man", - "Home Sweet Homediddly-dum-doodly", - "Bart Sells His Soul", - "Lisa the Vegetarian", - "Treehouse of horror VI", - "King Size Homer", - "Mother Simpson", - "Sideshow Bob's Last Gleaming", - "The Simpson's 138th Show Spectacular", - "Marge Be Not Proud", - "Team Homer", - "Two Bad Neighbors", - "Scenes From the Class Struggle in Springfield", - "Bart the Fink", - "Lisa the Iconoclast", - "Homer the Smithers", - "The Day the Violence Died", - "A Fish Called Selma", - "Bart on the road", - "22 Short Films about Springfield", - "The Curse of the Flying Hellfish", - "Much Apu about Nothing", - "Homerpalooza", - "The Summer of 4 Ft 2", - "Treehouse of Horror VII", - "You Only Move Twice", - "The Homer They Fall", - "Burns Baby Burns", - "Bart After Dark", - "A Millhouse Divided", - "Lisas Date With Destiny", - "Hurricane Neddy", - "The Mysterious Voyage of Our Homer", - "The Springfield Files", - "The Twisted World of Marge Simpson", - "Mountain of Madness", - NULL - }; - - Hash sTest; - - printf("Inserting\n-------------------\n\n"); - for( int j = 0; j < 33; j++ ) - { - sTest[names[j]] = j; - } - - printf("Test1: %d, Test2: %d\n", sTest.has("Lemon of Troy"), sTest.has(std::string("Lemon of Troy").c_str() ) ); - - sTest.has(std::string("Lemon of Troy").c_str() ); - - printf("Getting\n-------------------\n\n"); - - sTest.erase("Homer the Great"); - sTest["Bart's Comet"].erase(); - - for( Hash::iterator i = sTest.begin(); - i != sTest.end(); i++ ) - { - Hash::iterator j = i; - printf("%d: %s\n", (*j).second, (*j).first ); - } - - printf("Testing\n-------------------\n\n"); - for( int j = 0; j < 33; j++ ) - { - if( sTest.has(names[j]) ) - { - if( sTest[names[j]] != j ) - { - printf("'%s' should be %d, is %d\n", - names[j], j, - sTest[names[j]].value() - ); - } - } - else - { - printf("Missing element %d, '%s'\n", j, names[j] ); - } - } - - printf("Clearing\n-------------------\n\n"); - - sTest.clear(); - - for( Hash::iterator i = sTest.begin(); - i != sTest.end(); i++ ) - { - Hash::iterator j = i; - printf("%d: %s\n", (*j).second, (*j).first ); - } - -} - diff --git a/src/tests/hashtest.cpp b/src/tests/hashtest.cpp deleted file mode 100644 index eaa84a0..0000000 --- a/src/tests/hashtest.cpp +++ /dev/null @@ -1,107 +0,0 @@ -#include -#include -#include "hashtable.h" -#include "hashfunctioncasestring.h" - -int main() -{ - const char *names[]={ - "Homer the Great", - "And Maggie Makes Three", - "Bart's Comet", - "Homie The Clown", - "Bart Vs Australia", - "Homer vs Patty and Selma", - "A star is burns", - "Lisa's Wedding", - "Two Dozen and One Greyhounds", - "The PTA Disbands", - "Round Springfield", - "The Springfield connection", - "Lemon of Troy", - "Who Shot Mr. Burns (Pt. 1)", - "Who Shot Mr. Burns (pt. 2)", - "Radioactive Man", - "Home Sweet Homediddly-dum-doodly", - "Bart Sells His Soul", - "Lisa the Vegetarian", - "Treehouse of horror VI", - "King Size Homer", - "Mother Simpson", - "Sideshow Bob's Last Gleaming", - "The Simpson's 138th Show Spectacular", - "Marge Be Not Proud", - "Team Homer", - "Two Bad Neighbors", - "Scenes From the Class Struggle in Springfield", - "Bart the Fink", - "Lisa the Iconoclast", - "Homer the Smithers", - "The Day the Violence Died", - "A Fish Called Selma", - "Bart on the road", - "22 Short Films about Springfield", - "The Curse of the Flying Hellfish", - "Much Apu about Nothing", - "Homerpalooza", - "The Summer of 4 Ft 2", - "Treehouse of Horror VII", - "You Only Move Twice", - "The Homer They Fall", - "Burns Baby Burns", - "Bart After Dark", - "A Millhouse Divided", - "Lisas Date With Destiny", - "Hurricane Neddy", - "The Mysterious Voyage of Our Homer", - "The Springfield Files", - "The Twisted World of Marge Simpson", - "Mountain of Madness", - NULL - }; - - HashTable h( new HashFunctionCaseString(), 5, false ); - - int j; - printf("Inserting...\n"); - for( j = 0; j < 10; j++ ) - { - h.insert( names[j], (void *)(j+1) ); - h.insert( names[j], (void *)(j+1) ); - printf("Capacity: %lu, Size: %lu, Load: %f\n", - h.getCapacity(), - h.getSize(), - h.getLoad() - ); - } - - for( j = 0; j < 10; j++ ) - { - printf("\"%s\" = %d\n", names[j], (int)h[names[j]] ); - } - - printf("\nDeleting some...\n"); - - for( int k = 0; k < 7; k++ ) - { - h.del( names[k] ); - //h.insert( names[j], (void *)(j+1) ); - printf("Capacity: %lu, Size: %lu, Load: %f\n", - h.getCapacity(), - h.getSize(), - h.getLoad() - ); - } - - printf("\nInserting more...\n"); - - for( ; names[j] != NULL; j++ ) - { - h.insert( names[j], (void *)(j+1) ); - printf("Capacity: %lu, Size: %lu, Load: %f\n", - h.getCapacity(), - h.getSize(), - h.getLoad() - ); - } -} diff --git a/src/tests/hashtest2.cpp b/src/tests/hashtest2.cpp deleted file mode 100644 index 74700fd..0000000 --- a/src/tests/hashtest2.cpp +++ /dev/null @@ -1,15 +0,0 @@ -#include "hash.h" -#include - -int main() -{ - char *a, *b; - a = new char[10]; - b = new char[10]; - strcpy( a, "Hey there"); - strcpy( b, "Hey there"); - printf("Same: %s\n", __cmpHashKeys( a, b )?"yes":"no"); - - return 0; -} - diff --git a/src/tests/httpsrv/httpconnectionmonitor.cpp b/src/tests/httpsrv/httpconnectionmonitor.cpp deleted file mode 100644 index 51d82f3..0000000 --- a/src/tests/httpsrv/httpconnectionmonitor.cpp +++ /dev/null @@ -1,88 +0,0 @@ -#include "httpconnectionmonitor.h" -#include "http.h" -#include "exceptions.h" -#include - -HttpConnectionMonitor::HttpConnectionMonitor() -{ -} - -HttpConnectionMonitor::~HttpConnectionMonitor() -{ -} - -bool HttpConnectionMonitor::onNewConnection( Connection *pCon, int nPort ) -{ - printf("Got connection on port %d\n", nPort ); - - try - { - pCon->readInput( 60, 0 ); - printf("#######################\n%s\n#######################\n", pCon->getInput() ); - - Http hp( pCon ); - while( hp.parseRequest() == false ); - printf("Done parsing.\n\n"); - - if( hp.getRequestType() == Http::reqGet ) - { - printf("\"\"\"%s\"\"\"\n", hp.getRequestURI() ); - if( !strcmp( hp.getRequestURI(), "/" ) ) - { - std::string content("Server Test</test></head><body>This is a test of a new system where all the pages will be more or less dynamic...<br>If you want to try to login, you can do that here:<br><form method=\"post\" action=\"showvars\" enctype=\"multipart/form-data\">Name: <input type=\"text\" name=\"name\"><br>Password: <input type=\"password\" name=\"pass\"><br><input type=\"submit\" name=\"action\" value=\"login\"></form></body></html>"); - hp.buildResponse(); - hp.setResponseContent( - "text/html", - content.c_str(), - content.size() - ); - hp.sendResponse(); - } - else - { - std::string content("<html><head><title>URL Not Found</test></head><body>There is no content mapped to the URL you requested. Please try another one.</body></html>"); - hp.buildResponse( 404, "File not found."); - hp.setResponseContent( - "text/html", - content.c_str(), - content.size() - ); - hp.sendResponse(); - } - } - else - { - printf("Non get: %s\n", hp.getRequestTypeStr() ); - pCon->appendOutput("HTTP/1.1 100 Continue\r\n\r\n"); - } - pCon->writeOutput(); - //for( int j = 0; j < 50; j++ ) - { - pCon->readInput( 1, 0 ); - //printf("Size so far: %d\n", pCon->getInputAmnt() ); - } - - if( pCon->hasInput() ) - { - std::string s( pCon->getInput(), pCon->getInputAmnt() ); - - pCon->printInputDebug(); - //printf("Reamining data\n==============\n%s\n==============\n", - // s.c_str() ); - } - - pCon->disconnect(); - } - catch( ConnectionException &e ) - { - printf("Connection: %s\n", e.what() ); - } - - return true; -} - -bool HttpConnectionMonitor::onClosedConnection( Connection *pCon ) -{ - return true; -} - diff --git a/src/tests/httpsrv/httpconnectionmonitor.h b/src/tests/httpsrv/httpconnectionmonitor.h deleted file mode 100644 index 30c0afd..0000000 --- a/src/tests/httpsrv/httpconnectionmonitor.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef HTTPCONNECTIONMONITOR_H -#define HTTPCONNECTIONMONITOR_H - -#include "connectionmonitor.h" - -class HttpConnectionMonitor : public ConnectionMonitor -{ -public: - HttpConnectionMonitor(); - ~HttpConnectionMonitor(); - - bool onNewConnection( Connection *pCon, int nPort ); - bool onClosedConnection( Connection *pCon ); -}; - -#endif diff --git a/src/tests/httpsrv/main.cpp b/src/tests/httpsrv/main.cpp deleted file mode 100644 index 2f1563c..0000000 --- a/src/tests/httpsrv/main.cpp +++ /dev/null @@ -1,22 +0,0 @@ -#include "connectionmanager.h" -#include "httpconnectionmonitor.h" - -int main() -{ - printf("Starting server...\n"); - - ConnectionManager srv; - HttpConnectionMonitor http; - - srv.setConnectionMonitor( &http ); - - printf("Listening on port 7331\n"); - srv.startServer( 7331 ); - - for(;;) - { - srv.scanConnections( 5000, false ); - } - - return 0; -} diff --git a/src/tests/log.cpp b/src/tests/log.cpp deleted file mode 100644 index d7cfa0b..0000000 --- a/src/tests/log.cpp +++ /dev/null @@ -1,29 +0,0 @@ -#include <stdio.h> -#include <stdlib.h> -#include <iostream> -#include "multilog.h" -#include "multilogtext.h" - -class Test -{ -public: - Test() - { - MultiLineLog( 4, "Test init'd\n"); - } -}; - -int main() -{ - MultiLog &xLog = MultiLog::getInstance(); - - xLog.LineLog( 2, "Hello again"); - - MultiLog::getInstance().addChannel( - new MultiLogText( STDOUT_FILENO, "%02y-%02m-%02d %02h:%02M:%02s: %t" ) - ); - - MultiLineLog( MultiLog::LError, "Hi there!"); - Test t; -} - diff --git a/src/tests/md5test.cpp b/src/tests/md5test.cpp deleted file mode 100644 index 6f832df..0000000 --- a/src/tests/md5test.cpp +++ /dev/null @@ -1,19 +0,0 @@ -#include <stdio.h> -#include <string.h> -#include "md5.h" - -int main() -{ - md5 mproc; - md5sum sum; - char hexstr[33]; - - memset( hexstr, 0, 33 ); - - mproc.sumString( &sum, "qwertyuiopasdfgh" ); - mproc.sumToHex( &sum, hexstr ); - printf("sum: %s\n", hexstr ); - printf("chk: 1ebfc043d8880b758b13ddc8aa1638ef\n"); - - return 0; -} diff --git a/src/tests/ordhash.cpp b/src/tests/ordhash.cpp deleted file mode 100644 index f1d96ec..0000000 --- a/src/tests/ordhash.cpp +++ /dev/null @@ -1,48 +0,0 @@ -#include "ordhash.h" -#include <string> - -typedef struct eldef -{ - eldef( int a, int b, const std::string &c ) : - id( a ), nSequence( b ), sName( c ) {} - int id; - int nSequence; - std::string sName; -} eldef; - -struct seqcmp -{ - bool operator()( eldef **a, eldef **b ) - { - return (*a)->nSequence < (*b)->nSequence; - } -}; - -struct namcmp -{ - bool operator()( eldef **a, eldef **b ) - { - return (*a)->sName < (*b)->sName; - } -}; - -typedef OrdHash<int, eldef, seqcmp> AHash; -//typedef OrdHash<int, eldef, namcmp> AHash; - -int main() -{ - AHash hsh; - hsh[1] = eldef( 0, 43, "Bob"); - hsh[4] = eldef( 1, 443, "Abby"); - hsh[2] = eldef( 2, 1, "Name"); - hsh[5] = eldef( 3, 0, "Catagory"); - hsh[32] = eldef( 4, 12, "Epilogue"); - - for( AHash::iterator i = hsh.begin(); i != hsh.end(); i++ ) - { - eldef e = (*i).second; - printf("%d, %d, %s\n", e.id, e.nSequence, e.sName.c_str() ); - } - -} - diff --git a/src/tests/param.cpp b/src/tests/param.cpp deleted file mode 100644 index a4d2824..0000000 --- a/src/tests/param.cpp +++ /dev/null @@ -1,46 +0,0 @@ -#include "param.h" -#include <stdio.h> - -Param::Param() -{ - addHelpBanner("param - A test of the libbu++ parameter systems\n" - "Enjoy with care and caution\n\nTest stuff:\n"); - addParam( "name", 's', mkproc( Param::printStuff ), &str, "Test a param param" ); - //addParam( "name", &str ); - addParam( "job", 'U', mkproc( Param::printStuff ), "Test a paramless param" ); - - addHelpBanner("\nInformational:\n"); - addParam( "help", mkproc( ParamProc::help ), "Help!" ); - - addHelpBanner("\nThanks for trying my test!\n\n"); -} - -Param::~Param() -{ -} - -int Param::printStuff( int argc, char *argv[] ) -{ - printf("------------%02d-------------\n", argc ); - for( int j = 0; j < argc; j++ ) - { - printf("%d: %s\n", j, argv[j] ); - } - printf("---------------------------\n" ); - printf("SETVAR===\"%s\"\n", str.c_str() ); - - return 1; -} - -int main( int argc, char *argv[] ) -{ - if( argc == 1 ) - { - printf("You have to enter some parameter, try '--help'\n\n"); - return 0; - } - - Param p; - p.process( argc, argv ); -} - diff --git a/src/tests/param.h b/src/tests/param.h deleted file mode 100644 index 2756b69..0000000 --- a/src/tests/param.h +++ /dev/null @@ -1,21 +0,0 @@ -#ifndef PARAM_H -#define PARAM_H - -#include <stdint.h> - -#include "paramproc.h" - -class Param : public ParamProc -{ -public: - Param(); - virtual ~Param(); - -private: - int printStuff( int argc, char *argv[] ); - - std::string str; - uint32_t uint32; -}; - -#endif diff --git a/src/tests/plugin/main.cpp b/src/tests/plugin/main.cpp deleted file mode 100644 index 51c8390..0000000 --- a/src/tests/plugin/main.cpp +++ /dev/null @@ -1,14 +0,0 @@ -#include "plugger.h" -#include "plugin.h" - -int main() -{ - Plugger<Plugin> p; - - p.registerExternalPlugin( "./guy.so", "Guy" ); - - Plugin *t = p.instantiate( "Guy" ); - - p.destroy( t ); -} - diff --git a/src/tests/plugin/plugin.cpp b/src/tests/plugin/plugin.cpp deleted file mode 100644 index ea558fd..0000000 --- a/src/tests/plugin/plugin.cpp +++ /dev/null @@ -1,10 +0,0 @@ -#include "plugin.h" - -Plugin::Plugin() -{ -} - -Plugin::~Plugin() -{ -} - diff --git a/src/tests/plugin/plugin.h b/src/tests/plugin/plugin.h deleted file mode 100644 index f726867..0000000 --- a/src/tests/plugin/plugin.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef PLUGIN_H -#define PLUGIN_H - -class Plugin -{ -public: - Plugin(); - virtual ~Plugin(); - -private: - -}; - -#endif diff --git a/src/tests/qsort.cpp b/src/tests/qsort.cpp deleted file mode 100644 index 28c6f03..0000000 --- a/src/tests/qsort.cpp +++ /dev/null @@ -1,228 +0,0 @@ -#define _QSORT_SWAP(a, b, t) ((void)((t = *a), (*a = *b), (*b = t))) - -/* Discontinue quicksort algorithm when partition gets below this size. - This particular magic number was chosen to work best on a Sun 4/260. */ -#define _QSORT_MAX_THRESH 4 - -/* Stack node declarations used to store unfulfilled partition obligations - * (inlined in QSORT). -typedef struct { - QSORT_TYPE *_lo, *_hi; -} qsort_stack_node; - */ - -/* The next 4 #defines implement a very fast in-line stack abstraction. */ -/* The stack needs log (total_elements) entries (we could even subtract - log(MAX_THRESH)). Since total_elements has type unsigned, we get as - upper bound for log (total_elements): - bits per byte (CHAR_BIT) * sizeof(unsigned). */ -#define _QSORT_STACK_SIZE (8 * sizeof(unsigned)) -#define _QSORT_PUSH(top, low, high) \ - (((top->_lo = (low)), (top->_hi = (high)), ++top)) -#define _QSORT_POP(low, high, top) \ - ((--top, (low = top->_lo), (high = top->_hi))) -#define _QSORT_STACK_NOT_EMPTY (_stack < _top) - - -/* Order size using quicksort. This implementation incorporates - four optimizations discussed in Sedgewick: - - 1. Non-recursive, using an explicit stack of pointer that store the - next array partition to sort. To save time, this maximum amount - of space required to store an array of SIZE_MAX is allocated on the - stack. Assuming a 32-bit (64 bit) integer for size_t, this needs - only 32 * sizeof(stack_node) == 256 bytes (for 64 bit: 1024 bytes). - Pretty cheap, actually. - - 2. Chose the pivot element using a median-of-three decision tree. - This reduces the probability of selecting a bad pivot value and - eliminates certain extraneous comparisons. - - 3. Only quicksorts TOTAL_ELEMS / MAX_THRESH partitions, leaving - insertion sort to order the MAX_THRESH items within each partition. - This is a big win, since insertion sort is faster for small, mostly - sorted array segments. - - 4. The larger of the two sub-partitions is always pushed onto the - stack first, with the algorithm then concentrating on the - smaller partition. This *guarantees* no more than log (total_elems) - stack size is needed (actually O(1) in this case)! */ - -/* The main code starts here... */ - -template<typename QSORT_TYPE, typename QSORT_LTT> -void qsrt( QSORT_TYPE *QSORT_BASE, int QSORT_NELT ) -{ - QSORT_LTT QSORT_LT; - QSORT_TYPE *const _base = (QSORT_BASE); - const unsigned _elems = (QSORT_NELT); - QSORT_TYPE _hold; - - /* Don't declare two variables of type QSORT_TYPE in a single - * statement: eg `TYPE a, b;', in case if TYPE is a pointer, - * expands to `type* a, b;' wich isn't what we want. - */ - - if (_elems > _QSORT_MAX_THRESH) { - QSORT_TYPE *_lo = _base; - QSORT_TYPE *_hi = _lo + _elems - 1; - struct { - QSORT_TYPE *_hi; QSORT_TYPE *_lo; - } _stack[_QSORT_STACK_SIZE], *_top = _stack + 1; - - while (_QSORT_STACK_NOT_EMPTY) { - QSORT_TYPE *_left_ptr; QSORT_TYPE *_right_ptr; - - /* Select median value from among LO, MID, and HI. Rearrange - LO and HI so the three values are sorted. This lowers the - probability of picking a pathological pivot value and - skips a comparison for both the LEFT_PTR and RIGHT_PTR in - the while loops. */ - - QSORT_TYPE *_mid = _lo + ((_hi - _lo) >> 1); - - if (QSORT_LT (_mid, _lo)) - _QSORT_SWAP (_mid, _lo, _hold); - if (QSORT_LT (_hi, _mid)) - _QSORT_SWAP (_mid, _hi, _hold); - else - goto _jump_over; - if (QSORT_LT (_mid, _lo)) - _QSORT_SWAP (_mid, _lo, _hold); - _jump_over:; - - _left_ptr = _lo + 1; - _right_ptr = _hi - 1; - - /* Here's the famous ``collapse the walls'' section of quicksort. - Gotta like those tight inner loops! They are the main reason - that this algorithm runs much faster than others. */ - do { - while (QSORT_LT (_left_ptr, _mid)) - ++_left_ptr; - - while (QSORT_LT (_mid, _right_ptr)) - --_right_ptr; - - if (_left_ptr < _right_ptr) { - _QSORT_SWAP (_left_ptr, _right_ptr, _hold); - if (_mid == _left_ptr) - _mid = _right_ptr; - else if (_mid == _right_ptr) - _mid = _left_ptr; - ++_left_ptr; - --_right_ptr; - } - else if (_left_ptr == _right_ptr) { - ++_left_ptr; - --_right_ptr; - break; - } - } while (_left_ptr <= _right_ptr); - - /* Set up pointers for next iteration. First determine whether - left and right partitions are below the threshold size. If so, - ignore one or both. Otherwise, push the larger partition's - bounds on the stack and continue sorting the smaller one. */ - - if (_right_ptr - _lo <= _QSORT_MAX_THRESH) { - if (_hi - _left_ptr <= _QSORT_MAX_THRESH) - /* Ignore both small partitions. */ - _QSORT_POP (_lo, _hi, _top); - else - /* Ignore small left partition. */ - _lo = _left_ptr; - } - else if (_hi - _left_ptr <= _QSORT_MAX_THRESH) - /* Ignore small right partition. */ - _hi = _right_ptr; - else if (_right_ptr - _lo > _hi - _left_ptr) { - /* Push larger left partition indices. */ - _QSORT_PUSH (_top, _lo, _right_ptr); - _lo = _left_ptr; - } - else { - /* Push larger right partition indices. */ - _QSORT_PUSH (_top, _left_ptr, _hi); - _hi = _right_ptr; - } - } - } - - /* Once the BASE array is partially sorted by quicksort the rest - is completely sorted using insertion sort, since this is efficient - for partitions below MAX_THRESH size. BASE points to the - beginning of the array to sort, and END_PTR points at the very - last element in the array (*not* one beyond it!). */ - - { - QSORT_TYPE *const _end_ptr = _base + _elems - 1; - QSORT_TYPE *_tmp_ptr = _base; - register QSORT_TYPE *_run_ptr; - QSORT_TYPE *_thresh; - - _thresh = _base + _QSORT_MAX_THRESH; - if (_thresh > _end_ptr) - _thresh = _end_ptr; - - /* Find smallest element in first threshold and place it at the - array's beginning. This is the smallest array element, - and the operation speeds up insertion sort's inner loop. */ - - for (_run_ptr = _tmp_ptr + 1; _run_ptr <= _thresh; ++_run_ptr) - if (QSORT_LT (_run_ptr, _tmp_ptr)) - _tmp_ptr = _run_ptr; - - if (_tmp_ptr != _base) - _QSORT_SWAP (_tmp_ptr, _base, _hold); - - /* Insertion sort, running from left-hand-side - * up to right-hand-side. */ - - _run_ptr = _base + 1; - while (++_run_ptr <= _end_ptr) { - _tmp_ptr = _run_ptr - 1; - while (QSORT_LT (_run_ptr, _tmp_ptr)) - --_tmp_ptr; - - ++_tmp_ptr; - if (_tmp_ptr != _run_ptr) { - QSORT_TYPE *_trav = _run_ptr + 1; - while (--_trav >= _run_ptr) { - QSORT_TYPE *_hi; QSORT_TYPE *_lo; - _hold = *_trav; - - for (_hi = _lo = _trav; --_lo >= _tmp_ptr; _hi = _lo) - *_hi = *_lo; - *_hi = _hold; - } - } - } - } - -} - - -struct cc -{ - bool operator()( int *a, int *b ) - { - return *a < *b; - } -}; - -#include <stdio.h> - -int main() -{ - int lst[] = { 43, 1, 342, 12, 491, 32, 12321, 32, 3, -3 }; - - for( int j = 0; j < 10; j++ ) - printf("%s%d", (j>0)?", ":"", lst[j] ); - printf("\n"); - qsrt<int, cc>( lst, 10 ); - for( int j = 0; j < 10; j++ ) - printf("%s%d", (j>0)?", ":"", lst[j] ); - printf("\n"); -} - diff --git a/src/tests/sbuffer.cpp b/src/tests/sbuffer.cpp deleted file mode 100644 index 02798cb..0000000 --- a/src/tests/sbuffer.cpp +++ /dev/null @@ -1,27 +0,0 @@ -#include "sbuffer.h" - -int main() -{ - SBuffer buf; - - buf.write("abcdefg", 7 ); - - printf("tell: %ld\n", buf.tell() ); - - char abuf[6]; - int nRead; - nRead = buf.read( abuf, 5 ); - abuf[nRead] = '\0'; - printf("Read %d bytes \"%s\"\n", nRead, abuf ); - - buf.setPos( 0 ); - nRead = buf.read( abuf, 5 ); - abuf[nRead] = '\0'; - printf("Read %d bytes \"%s\"\n", nRead, abuf ); - - nRead = buf.read( abuf, 5 ); - abuf[nRead] = '\0'; - printf("Read %d bytes \"%s\"\n", nRead, abuf ); - -} - diff --git a/src/tests/serialize.cpp b/src/tests/serialize.cpp deleted file mode 100644 index e233704..0000000 --- a/src/tests/serialize.cpp +++ /dev/null @@ -1,30 +0,0 @@ -#include "serializerbinary.h" -#include "staticstring.h" -#include <stdio.h> -#include <string> - -int main() -{ - int32_t one; - double two; - bool three; - StaticString s("Test string!"); - std::string ss("Another test string"); - SerializerBinary ar("hello.dat", false); - ar << (int)85; - ar << (double)2.63434; - ar << false; - ar << ss; - ar.close(); - - one = 0; two = 0; three = true; s = "die"; - - SerializerBinary ar2("hello.dat", true); - ar2 >> one; - ar2 >> two; - ar2 >> three; - ar2 >> s; - - printf("we got %d - %f - %s - \"%s\"\n", one, two, (three ? "true":"false"), s.getString() ); - return 0; -} diff --git a/src/tests/serializetext.cpp b/src/tests/serializetext.cpp deleted file mode 100644 index f6be7d3..0000000 --- a/src/tests/serializetext.cpp +++ /dev/null @@ -1,28 +0,0 @@ -#include "serializertext.h" -#include "staticstring.h" -#include <iostream> - -int main() -{ - StaticString s("You're a dog!!"); - SerializerText ar("hello.dat", false); - - ar << 4 << 3.993 << true << s; - - ar.close(); - - int one=0;float two=0.0;bool three=false; s = ""; - - SerializerText ar2("hello.dat", true); - - ar2 >> one; - ar2 >> two; - ar2 >> three; - ar2 >> s; - - //printf("out: %d, %f, %s, \"%s\"\n", one, two, (three ? "true" : "false"), s.getString()); - std::cout << one << ", " << two << ", " << three << ", " << s.getString() << "\n"; - - return 0; -} - diff --git a/src/tests/sha1.cpp b/src/tests/sha1.cpp deleted file mode 100644 index df3113c..0000000 --- a/src/tests/sha1.cpp +++ /dev/null @@ -1,44 +0,0 @@ -#include "sha1.h" -#include "sfile.h" - -#define BS 1024 - -int main( int argc, char *argv[] ) -{ - argc--; argv++; - - if( argc == 0 ) - { - printf("Provide a filename.\n"); - return 0; - } - - char buf[BS]; - - Sha1 s; - SFile fin( *argv, "rb" ); - for(;;) - { - int nRead = fin.read( buf, BS ); - if( nRead == 0 ) - break; - - s.update( buf, nRead ); - if( nRead < BS ) - break; - } - - unsigned char *dig = s.getDigest(); - - char val[]={"0123456789ABCDEF"}; - - for( int j = 0; j < 20; j++ ) - { - putchar( val[dig[j]>>4] ); - putchar( val[dig[j]&0x0F] ); - } - putchar('\n'); - - delete[] dig; -} - diff --git a/src/tests/sptr.cpp b/src/tests/sptr.cpp deleted file mode 100644 index 38d3675..0000000 --- a/src/tests/sptr.cpp +++ /dev/null @@ -1,55 +0,0 @@ -#include <stdio.h> -#include "sptr.h" - -class Annoy -{ -public: - Annoy() : nCnt( 0 ) - { - printf("Created.\n"); - } - - ~Annoy() - { - printf("Destroyed.\n"); - } - - void go() - { - printf("%d: I'm annoying.\n", ++nCnt); - } - - int nCnt; -}; - -void beAnnoying( SPtr<Annoy> bob ) -{ - printf("bob-Count: %d\n", bob.count() ); - bob->go(); -} - -int main() -{ - SPtr<Annoy> pt( new Annoy ); - printf("Count: %d\n", pt.count() ); - pt->go(); - - { - SPtr<Annoy> pt2 = pt; - printf("Count: %d\n", pt2.count() ); - - pt2->go(); - - { - SPtr<Annoy> pt3( pt2 ); - printf("Count: %d\n", pt3.count() ); - - pt3->go(); - - beAnnoying( pt3 ); - } - printf("Count: %d\n", pt.count() ); - } - printf("Count: %d\n", pt.count() ); -} - diff --git a/src/tests/srvstress.cpp b/src/tests/srvstress.cpp deleted file mode 100644 index d9a9a1c..0000000 --- a/src/tests/srvstress.cpp +++ /dev/null @@ -1,91 +0,0 @@ -#include "connectionmanager.h" -#include "programlink.h" -#include "linkedlist.h" -#include "protocol.h" - -class StressProtocol : public Protocol -{ -public: - bool onNewData() - { - switch( getConnection()->getInput()[0] ) - { - case 'd': - throw "Hello"; - break; - - case 'w': - getConnection()->appendOutput("Hello"); - break; - }; - - return true; - } - - bool onNewConnection() - { - return true; - } -}; - -class StressMonitor : public ConnectionMonitor, public ProgramLink -{ -public: - bool init() - { - return true; - } - - bool deInit() - { - return true; - } - - bool timeSlice() - { - return true; - } - - bool onNewConnection( Connection *pCon, int nPort ) - { - StressProtocol *sp = new StressProtocol(); - pCon->setProtocol( sp ); - - printf(" sys: New connection: socket(%d), port(%d)\n", - pCon->getSocket(), nPort ); - - return true; - } - - bool onClosedConnection( Connection *pCon ) - { - printf(" sys: Closed connection: socket(%d)\n", - pCon->getSocket() ); - - return true; - } - - LinkMessage *processIRM( LinkMessage *pMsg ) - { - return NULL; - } -}; - -int main() -{ - printf("Starting server...\n"); - - ConnectionManager srv; - StressMonitor telnet; - - srv.setConnectionMonitor( &telnet ); - - srv.startServer( 4001 ); - - for(;;) - { - srv.scanConnections( 5000, false ); - } - - return 0; -} diff --git a/src/tests/strhash.cpp b/src/tests/strhash.cpp deleted file mode 100644 index f6528ca..0000000 --- a/src/tests/strhash.cpp +++ /dev/null @@ -1,12 +0,0 @@ -#include <stdio.h> -#include "hashfunctionstring.h" - -int main( int argc, char *argv[] ) -{ - HashFunctionString h; - - printf("\"%s\": %lu\n", argv[1], h.hash( argv[1] ) ); - - return 0; -} - diff --git a/src/tests/teltest/main.cpp b/src/tests/teltest/main.cpp deleted file mode 100644 index 5d3ec26..0000000 --- a/src/tests/teltest/main.cpp +++ /dev/null @@ -1,21 +0,0 @@ -#include "connectionmanager.h" -#include "telnetmonitor.h" - -int main() -{ - printf("Starting server...\n"); - - ConnectionManager srv; - TelnetMonitor telnet; - - srv.setConnectionMonitor( &telnet ); - - srv.startServer( 4001 ); - - for(;;) - { - srv.scanConnections( 5000, false ); - } - - return 0; -} diff --git a/src/tests/teltest/telnetmonitor.cpp b/src/tests/teltest/telnetmonitor.cpp deleted file mode 100644 index 65954eb..0000000 --- a/src/tests/teltest/telnetmonitor.cpp +++ /dev/null @@ -1,54 +0,0 @@ -#include "telnetmonitor.h" -#include "protocoltelnet.h" -#include <sys/stat.h> - -TelnetMonitor::TelnetMonitor() -{ -} - -TelnetMonitor::~TelnetMonitor() -{ -} - -bool TelnetMonitor::init() -{ - return true; -} - -bool TelnetMonitor::deInit() -{ - return true; -} - -bool TelnetMonitor::timeSlice() -{ - for( int j = 0; j < lCon.getSize(); j++ ) - { - if( ((Connection *)lCon[j])->hasInput() ) - { - printf("%s\n", ((Connection *)lCon[j])->getInput() ); - } - } - return true; -} - -LinkMessage* TelnetMonitor::processIRM( LinkMessage *pMsg ) -{ - return NULL; -} - -bool TelnetMonitor::onNewConnection( Connection *pCon, int nPort ) -{ - ProtocolTelnet *pt = new ProtocolTelnet(); - pCon->setProtocol( pt ); - - lCon.append( pt ); - - return true; -} - -bool TelnetMonitor::onClosedConnection( Connection *pCon ) -{ - return true; -} - diff --git a/src/tests/teltest/telnetmonitor.h b/src/tests/teltest/telnetmonitor.h deleted file mode 100644 index ba5761e..0000000 --- a/src/tests/teltest/telnetmonitor.h +++ /dev/null @@ -1,26 +0,0 @@ -#ifndef HTTPCONNECTIONMONITOR_H -#define HTTPCONNECTIONMONITOR_H - -#include "connectionmonitor.h" -#include "programlink.h" -#include "linkedlist.h" - -class TelnetMonitor : public ConnectionMonitor, public ProgramLink -{ -public: - TelnetMonitor(); - ~TelnetMonitor(); - - bool init(); - bool deInit(); - bool timeSlice(); - LinkMessage* processIRM( LinkMessage *pMsgIn ); - - bool onNewConnection( Connection *pCon, int nPort ); - bool onClosedConnection( Connection *pCon ); - -private: - LinkedList lCon; -}; - -#endif diff --git a/src/tests/xmlreadtest.cpp b/src/tests/xmlreadtest.cpp deleted file mode 100644 index d061810..0000000 --- a/src/tests/xmlreadtest.cpp +++ /dev/null @@ -1,29 +0,0 @@ -#include "xmlfilereader.h" -#include "xmlstringreader.h" -#include "xmlfilewriter.h" - -int main( int argc, char *argv[] ) -{ - if( argc < 4 ) - { - printf("Usage: %s f <file in> <file out>\n", argv[0] ); - printf(" %s s <xml string> <file out>\n\n", argv[0] ); - return 0; - } - - if( argv[1][0] == 'f' ) - { - XmlFileReader r( argv[2], true ); -// XmlFileWriter w( argv[3], "\t", r.detatchRoot() ); -// w.write(); - } - else if( argv[1][0] == 's' ) - { - XmlStringReader r( argv[2], true ); - XmlFileWriter w(stdout, "\t", r.detatchRoot() ); - w.write(); - } - - return 0; -} - diff --git a/src/tests/xmlrepltest.cpp b/src/tests/xmlrepltest.cpp deleted file mode 100644 index 9667705..0000000 --- a/src/tests/xmlrepltest.cpp +++ /dev/null @@ -1,31 +0,0 @@ -#include "xmlwriter.h" - -int main() -{ - printf("Testing Xml Replacement...\n"); - XmlDocument w; - - w.addNode("text"); - w.setContent("this text is before the node. "); - w.addNode("keepme", "This one we keep...", true ); - w.setContent("this text is after."); - w.addNode("deleteme", "This one we don't...", true ); - w.setContent("this is last..." ); - w.closeNode(); - - //XmlWriter::writeNode( stdout, w.getRoot(), 0, NULL ); - - printf("\n\n"); - - //XmlNode *xNode = w.getRoot()->detatchNode( 1 ); - - //XmlWriter::writeNode( stdout, w.getRoot(), 0, NULL ); - - printf("\n\n"); - - //XmlWriter::writeNode( stdout, xNode, 0, NULL ); - - printf("\n\n"); - - return 0; -} diff --git a/src/tests/xmlwritetest.cpp b/src/tests/xmlwritetest.cpp deleted file mode 100644 index a22d19d..0000000 --- a/src/tests/xmlwritetest.cpp +++ /dev/null @@ -1,48 +0,0 @@ -#include "xmlfilewriter.h" -#include "xmlstringwriter.h" -#include "xmlstringreader.h" - -void fillItIn( XmlWriter &w ) -{ - w.addNode("thinglist"); - - w.addNode("thing"); - w.addProperty("type", " ±î´<M-F6><M-F6>³¸®°êòì¯"); - - w.addNode("id", "Klophin²³±¹¸·µ´äêíëã Staff", true ); - w.addNode("name", "Klophin Staff", true ); - w.addNode("durability", "0.01", true ); - w.addNode("size", "0.1", true ); - - w.addNode("config"); - w.addNode("damage", "3d6+4", true ); - w.addNode("class", "melee", true ); - w.addNode("type", "bludgeon", true ); - w.addNode("damagedesc", "club/clubs", true ); - w.closeNode(); - - w.closeNode(); - - w.closeNode(); -} - -int main() -{ - printf("Testing XmlWriter...\n"); - - //XmlStringReader *xsr = new XmlStringReader("<stuff/>"); - - //printf("%08X\n%08X\n%08X\n", xsr, (XmlReader *)xsr, (XmlDocument *)xsr ); - - //delete (XmlDocument *)xsr; - XmlFileWriter wf("test.xml", "\t"); - - fillItIn( wf ); - - XmlStringWriter ws("\t"); - fillItIn( ws ); - - printf("Now the string version:\n\n%s\n", ws.getString().c_str() ); - - return 0; -} -- cgit v1.2.3 From da89e6d30e57bd6dbb10b4d36b093ce9bbf5c666 Mon Sep 17 00:00:00 2001 From: Mike Buland <eichlan@xagasoft.com> Date: Tue, 3 Apr 2007 04:50:36 +0000 Subject: The first batch seem to have made it alright. Unfortunately the Archive class isn't done yet, I'm going to make it rely on streams, so those will be next, then we can make it work all sortsa' well. --- src/archable.cpp | 10 + src/archable.h | 35 +++ src/archive.cpp | 337 +++++++++++++++++++++ src/archive.h | 93 ++++++ src/exceptionbase.cpp | 70 +++++ src/exceptionbase.h | 114 +++++++ src/exceptions.cpp | 10 + src/exceptions.h | 28 ++ src/fstring.cpp | 14 + src/fstring.h | 653 ++++++++++++++++++++++++++++++++++++++++ src/hash.cpp | 101 +++++++ src/hash.h | 745 ++++++++++++++++++++++++++++++++++++++++++++++ src/old/exceptionbase.cpp | 70 ----- src/old/exceptionbase.h | 105 ------- src/old/exceptions.cpp | 8 - src/old/exceptions.h | 25 -- src/old/fstring.cpp | 13 - src/old/fstring.h | 651 ---------------------------------------- src/old/hash.cpp | 113 ------- src/old/hash.h | 744 --------------------------------------------- src/old/hashable.cpp | 1 - src/old/hashable.h | 12 - src/old/serializable.cpp | 8 - src/old/serializable.h | 34 --- src/old/serializer.cpp | 338 --------------------- src/old/serializer.h | 80 ----- src/old/stream.cpp | 10 - src/old/stream.h | 27 -- src/stream.cpp | 10 + src/stream.h | 34 +++ src/tests/archive.cpp | 7 + tests/comments.xml | 12 - tests/guy.cpp | 22 -- tests/makeplugin.sh | 3 - 34 files changed, 2261 insertions(+), 2276 deletions(-) create mode 100644 src/archable.cpp create mode 100644 src/archable.h create mode 100644 src/archive.cpp create mode 100644 src/archive.h create mode 100644 src/exceptionbase.cpp create mode 100644 src/exceptionbase.h create mode 100644 src/exceptions.cpp create mode 100644 src/exceptions.h create mode 100644 src/fstring.cpp create mode 100644 src/fstring.h create mode 100644 src/hash.cpp create mode 100644 src/hash.h delete mode 100644 src/old/exceptionbase.cpp delete mode 100644 src/old/exceptionbase.h delete mode 100644 src/old/exceptions.cpp delete mode 100644 src/old/exceptions.h delete mode 100644 src/old/fstring.cpp delete mode 100644 src/old/fstring.h delete mode 100644 src/old/hash.cpp delete mode 100644 src/old/hash.h delete mode 100644 src/old/hashable.cpp delete mode 100644 src/old/hashable.h delete mode 100644 src/old/serializable.cpp delete mode 100644 src/old/serializable.h delete mode 100644 src/old/serializer.cpp delete mode 100644 src/old/serializer.h delete mode 100644 src/old/stream.cpp delete mode 100644 src/old/stream.h create mode 100644 src/stream.cpp create mode 100644 src/stream.h create mode 100644 src/tests/archive.cpp delete mode 100644 tests/comments.xml delete mode 100644 tests/guy.cpp delete mode 100755 tests/makeplugin.sh (limited to 'src/tests') diff --git a/src/archable.cpp b/src/archable.cpp new file mode 100644 index 0000000..38fc31f --- /dev/null +++ b/src/archable.cpp @@ -0,0 +1,10 @@ +#include "archable.h" + +Bu::Archable::Archable() +{ +} + +Bu::Archable::~Archable() +{ +} + diff --git a/src/archable.h b/src/archable.h new file mode 100644 index 0000000..ed05a78 --- /dev/null +++ b/src/archable.h @@ -0,0 +1,35 @@ +#ifndef ARCHABLE_H +#define ARCHABLE_H + +namespace Bu +{ + /** + * The base class for any class you want to archive. Simply include this as + * a base class, implement the purely virtual archive function and you've + * got an easily archiveable class. + */ + class Archable + { + public: + /** + * Does nothing, here for completeness. + */ + Archable(); + + /** + * Here to ensure the deconstructor is virtual. + */ + virtual ~Archable(); + + /** + * This is the main workhorse of the archive system, just override and + * you've got a archiveable class. A reference to the Archive + * used is passed in as your only parameter, query it to discover if + * you are loading or saving. + * @param ar A reference to the Archive object to use. + */ + virtual void archive( class Archive &ar )=0; + }; +} + +#endif diff --git a/src/archive.cpp b/src/archive.cpp new file mode 100644 index 0000000..5f5145c --- /dev/null +++ b/src/archive.cpp @@ -0,0 +1,337 @@ +#include "archive.h" + +Bu::Archive::Archive(bool bLoading): + bLoading(bLoading) +{ +} +Bu::Archive::~Archive() +{ +} + +bool Bu::Archive::isLoading() +{ + return bLoading; +} +Bu::Archive &Bu::Archive::operator<<(bool p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(int8_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(int16_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(int32_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(int64_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(uint8_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(uint16_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(uint32_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(uint64_t p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(long p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(float p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(double p) +{ + write( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator<<(long double p) +{ + write( &p, sizeof(p) ); + return *this; +} + +Bu::Archive &Bu::Archive::operator>>(bool &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(int8_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(int16_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(int32_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(int64_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(uint8_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(uint16_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(uint32_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(uint64_t &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(long &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(float &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(double &p) +{ + read( &p, sizeof(p) ); + return *this; +} +Bu::Archive &Bu::Archive::operator>>(long double &p) +{ + read( &p, sizeof(p) ); + return *this; +} + +Bu::Archive &Bu::Archive::operator&&(bool &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(int8_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(int16_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(int32_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(int64_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(uint8_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(uint16_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(uint32_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(uint64_t &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(float &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(double &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + +Bu::Archive &Bu::Archive::operator&&(long double &p) +{ + if (bLoading) + { + return *this >> p; + } + else + { + return *this << p; + } +} + + +Bu::Archive &Bu::operator<<(Bu::Archive &s, Bu::Archable &p) +{ + p.archive( s ); + return s; +} + +Bu::Archive &Bu::operator>>(Bu::Archive &s, Bu::Archable &p) +{ + p.archive( s ); + return s; +} + +/* +Bu::Archive &Bu::operator&&(Bu::Archive &s, Bu::Archable &p) +{ + if (s.isLoading()) + { + return s >> p; + } + else + { + return s << p; + } +}*/ + +Bu::Archive &Bu::operator<<( Bu::Archive &ar, std::string &s ) +{ + ar << (uint32_t)s.length(); + ar.write( s.c_str(), s.length() ); + + return ar; +} + +Bu::Archive &Bu::operator>>( Bu::Archive &ar, std::string &s ) +{ + uint32_t l; + ar >> l; + char *tmp = new char[l+1]; + tmp[l] = '\0'; + ar.read( tmp, l ); + s = tmp; + delete[] tmp; + + return ar; +} + diff --git a/src/archive.h b/src/archive.h new file mode 100644 index 0000000..7de9220 --- /dev/null +++ b/src/archive.h @@ -0,0 +1,93 @@ +#ifndef ARCHIVE_H +#define ARCHIVE_H + +#include <stdint.h> +#include <string> +#include "archable.h" + +namespace Bu +{ + class Archive + { + private: + bool bLoading; + public: + bool isLoading(); + + enum + { + load = true, + save = false + }; + + Archive( bool bLoading ); + virtual ~Archive(); + virtual void close()=0; + + virtual void write(const void *, int32_t)=0; + virtual void read(void *, int32_t)=0; + + virtual Archive &operator<<(bool); + virtual Archive &operator<<(int8_t); + virtual Archive &operator<<(int16_t); + virtual Archive &operator<<(int32_t); + virtual Archive &operator<<(int64_t); + virtual Archive &operator<<(uint8_t); + virtual Archive &operator<<(uint16_t); + virtual Archive &operator<<(uint32_t); + virtual Archive &operator<<(uint64_t); + virtual Archive &operator<<(long); + virtual Archive &operator<<(float); + virtual Archive &operator<<(double); + virtual Archive &operator<<(long double); + + virtual Archive &operator>>(bool &); + virtual Archive &operator>>(int8_t &); + virtual Archive &operator>>(int16_t &); + virtual Archive &operator>>(int32_t &); + virtual Archive &operator>>(int64_t &); + virtual Archive &operator>>(uint8_t &); + virtual Archive &operator>>(uint16_t &); + virtual Archive &operator>>(uint32_t &); + virtual Archive &operator>>(uint64_t &); + virtual Archive &operator>>(long &); + virtual Archive &operator>>(float &); + virtual Archive &operator>>(double &); + virtual Archive &operator>>(long double &); + + virtual Archive &operator&&(bool &); + virtual Archive &operator&&(int8_t &); + virtual Archive &operator&&(int16_t &); + virtual Archive &operator&&(int32_t &); + virtual Archive &operator&&(int64_t &); + virtual Archive &operator&&(uint8_t &); + virtual Archive &operator&&(uint16_t &); + virtual Archive &operator&&(uint32_t &); + virtual Archive &operator&&(uint64_t &); + virtual Archive &operator&&(float &); + virtual Archive &operator&&(double &); + virtual Archive &operator&&(long double &); + }; + + Archive &operator<<(Archive &, class Bu::Archable &); + Archive &operator>>(Archive &, class Bu::Archable &); + //Archive &operator&&(Archive &s, class Bu::Archable &p); + + Archive &operator<<(Archive &, std::string &); + Archive &operator>>(Archive &, std::string &); + //Archive &operator&&(Archive &, std::string &); + + template<typename T> Archive &operator&&( Archive &ar, T &dat ) + { + if( ar.isLoading() ) + { + return ar >> dat; + } + else + { + return ar << dat; + } + } +} + +#endif diff --git a/src/exceptionbase.cpp b/src/exceptionbase.cpp new file mode 100644 index 0000000..f6ec625 --- /dev/null +++ b/src/exceptionbase.cpp @@ -0,0 +1,70 @@ +#include "exceptionbase.h" +#include <stdarg.h> + +Bu::ExceptionBase::ExceptionBase( const char *lpFormat, ... ) throw() : + nErrorCode( 0 ), + sWhat( NULL ) +{ + va_list ap; + + va_start(ap, lpFormat); + setWhat( lpFormat, ap ); + va_end(ap); +} + +Bu::ExceptionBase::ExceptionBase( int nCode, const char *lpFormat, ... ) throw() : + nErrorCode( nCode ), + sWhat( NULL ) +{ + va_list ap; + + va_start(ap, lpFormat); + setWhat( lpFormat, ap ); + va_end(ap); +} + +Bu::ExceptionBase::ExceptionBase( int nCode ) throw() : + nErrorCode( nCode ), + sWhat( NULL ) +{ +} + +Bu::ExceptionBase::~ExceptionBase() throw() +{ + if( sWhat ) + { + delete[] sWhat; + sWhat = NULL; + } +} + +void Bu::ExceptionBase::setWhat( const char *lpFormat, va_list &vargs ) +{ + if( sWhat ) delete[] sWhat; + int nSize; + + nSize = vsnprintf( NULL, 0, lpFormat, vargs ); + sWhat = new char[nSize+1]; + vsnprintf( sWhat, nSize+1, lpFormat, vargs ); +} + +void Bu::ExceptionBase::setWhat( const char *lpText ) +{ + if( sWhat ) delete[] sWhat; + int nSize; + + nSize = strlen( lpText ); + sWhat = new char[nSize+1]; + strcpy( sWhat, lpText ); +} + +const char *Bu::ExceptionBase::what() const throw() +{ + return sWhat; +} + +int Bu::ExceptionBase::getErrorCode() +{ + return nErrorCode; +} + diff --git a/src/exceptionbase.h b/src/exceptionbase.h new file mode 100644 index 0000000..fd78089 --- /dev/null +++ b/src/exceptionbase.h @@ -0,0 +1,114 @@ +#ifndef EXCEPTION_BASE_H +#define EXCEPTION_BASE_H + +#include <string> +#include <exception> +#include <stdarg.h> + +namespace Bu +{ + /** + * A generalized Exception base class. This is nice for making general and + * flexible child classes that can create new error code classes. + * + * In order to create your own exception class use these two lines. + * + * in your header: subExceptionDecl( NewClassName ); + * + * in your source: subExcpetienDef( NewClassName ); + */ + class ExceptionBase : public std::exception + { + public: + /** + * Construct an exception with an error code of zero, but with a + * description. The use of this is not reccomended most of the time, + * it's generally best to include an error code with the exception so + * your program can handle the exception in a better way. + * @param sFormat The format of the text. See printf for more info. + */ + ExceptionBase( const char *sFormat, ... ) throw(); + + /** + * + * @param nCode + * @param sFormat + */ + ExceptionBase( int nCode, const char *sFormat, ... ) throw(); + + /** + * + * @param nCode + * @return + */ + ExceptionBase( int nCode=0 ) throw(); + + /** + * + * @return + */ + virtual ~ExceptionBase() throw(); + + /** + * + * @return + */ + virtual const char *what() const throw(); + + /** + * + * @return + */ + int getErrorCode(); + + /** + * + * @param lpFormat + * @param vargs + */ + void setWhat( const char *lpFormat, va_list &vargs ); + + /** + * + * @param lpText + */ + void setWhat( const char *lpText ); + + private: + int nErrorCode; /**< The code for the error that occured. */ + char *sWhat; /**< The text string telling people what went wrong. */ + }; +} + +#define subExceptionDecl( name ) \ +class name : public ExceptionBase \ +{ \ + public: \ + name( const char *sFormat, ... ) throw (); \ + name( int nCode, const char *sFormat, ... ) throw(); \ + name( int nCode=0 ) throw (); \ +}; + +#define subExceptionDef( name ) \ +name::name( const char *lpFormat, ... ) throw() : \ + ExceptionBase( 0 ) \ +{ \ + va_list ap; \ + va_start( ap, lpFormat ); \ + setWhat( lpFormat, ap ); \ + va_end( ap ); \ +} \ +name::name( int nCode, const char *lpFormat, ... ) throw() : \ + ExceptionBase( nCode ) \ +{ \ + va_list ap; \ + va_start( ap, lpFormat ); \ + setWhat( lpFormat, ap ); \ + va_end( ap ); \ +} \ +name::name( int nCode ) throw() : \ + ExceptionBase( nCode ) \ +{ \ +} + +#endif diff --git a/src/exceptions.cpp b/src/exceptions.cpp new file mode 100644 index 0000000..37f09a4 --- /dev/null +++ b/src/exceptions.cpp @@ -0,0 +1,10 @@ +#include "exceptions.h" +#include <stdarg.h> + +namespace Bu +{ + subExceptionDef( XmlException ) + subExceptionDef( FileException ) + subExceptionDef( ConnectionException ) + subExceptionDef( PluginException ) +} diff --git a/src/exceptions.h b/src/exceptions.h new file mode 100644 index 0000000..b28d292 --- /dev/null +++ b/src/exceptions.h @@ -0,0 +1,28 @@ +#ifndef EXCEPTIONS_H +#define EXCEPTIONS_H + +#include "exceptionbase.h" +#include <stdarg.h> + +namespace Bu +{ + subExceptionDecl( XmlException ) + subExceptionDecl( FileException ) + subExceptionDecl( ConnectionException ) + subExceptionDecl( PluginException ) + + enum eFileException + { + excodeEOF + }; + + enum eConnectionException + { + excodeReadError, + excodeBadReadError, + excodeConnectionClosed, + excodeSocketTimeout + }; +} + +#endif diff --git a/src/fstring.cpp b/src/fstring.cpp new file mode 100644 index 0000000..56d2173 --- /dev/null +++ b/src/fstring.cpp @@ -0,0 +1,14 @@ +#include "fstring.h" +#include "hash.h" + +template<> uint32_t Bu::__calcHashCode<Bu::FString>( const Bu::FString &k ) +{ + return __calcHashCode( k.c_str() ); +} + +template<> bool Bu::__cmpHashKeys<Bu::FString>( + const Bu::FString &a, const Bu::FString &b ) +{ + return a == b; +} + diff --git a/src/fstring.h b/src/fstring.h new file mode 100644 index 0000000..717068f --- /dev/null +++ b/src/fstring.h @@ -0,0 +1,653 @@ +#ifndef F_STRING_H +#define F_STRING_H + +#include <stdint.h> +#include <memory> +#include "archable.h" +#include "archive.h" +#include "hash.h" + +namespace Bu +{ + template< typename chr > + struct FStringChunk + { + long nLength; + chr *pData; + FStringChunk *pNext; + }; + + /** + * Flexible String class. This class was designed with string passing and + * generation in mind. Like the standard string class you can specify what + * datatype to use for each character. Unlike the standard string class, + * collection of appended and prepended terms is done lazily, making long + * operations that involve many appends very inexpensive. In addition internal + * ref-counting means that if you pass strings around between functions there's + * almost no overhead in time or memory since a reference is created and no + * data is actually copied. This also means that you never need to put any + * FBasicString into a ref-counting container class. + */ + template< typename chr, typename chralloc=std::allocator<chr>, typename chunkalloc=std::allocator<struct FStringChunk<chr> > > + class FBasicString : public Archable + { +#ifndef VALTEST +#define cpy( dest, src, size ) memcpy( dest, src, size*sizeof(chr) ) +#endif + private: + typedef struct FStringChunk<chr> Chunk; + typedef struct FBasicString<chr, chralloc, chunkalloc> MyType; + + public: + FBasicString() : + nLength( 0 ), + pnRefs( NULL ), + pFirst( NULL ), + pLast( NULL ) + { + } + + FBasicString( const chr *pData ) : + nLength( 0 ), + pnRefs( NULL ), + pFirst( NULL ), + pLast( NULL ) + { + append( pData ); + } + + FBasicString( const chr *pData, long nLength ) : + nLength( 0 ), + pnRefs( NULL ), + pFirst( NULL ), + pLast( NULL ) + { + append( pData, nLength ); + } + + FBasicString( const MyType &rSrc ) : + nLength( 0 ), + pnRefs( NULL ), + pFirst( NULL ), + pLast( NULL ) + { + // Here we have no choice but to copy, since the other guy is a const. + // In the case that the source were flat, we could get a reference, it + // would make some things faster, but not matter in many other cases. + + joinShare( rSrc ); + //copyFrom( rSrc ); + } + + FBasicString( const MyType &rSrc, long nLength ) : + nLength( 0 ), + pnRefs( NULL ), + pFirst( NULL ), + pLast( NULL ) + { + append( rSrc.pFirst->pData, nLength ); + } + + FBasicString( const MyType &rSrc, long nStart, long nLength ) : + nLength( 0 ), + pnRefs( NULL ), + pFirst( NULL ), + pLast( NULL ) + { + append( rSrc.pFirst->pData+nStart, nLength ); + } + + FBasicString( long nSize ) : + nLength( nSize ), + pnRefs( NULL ), + pFirst( NULL ), + pLast( NULL ) + { + pFirst = pLast = newChunk( nSize ); + } + + virtual ~FBasicString() + { + clear(); + } + + void append( const chr *pData ) + { + long nLen; + for( nLen = 0; pData[nLen] != (chr)0; nLen++ ); + + Chunk *pNew = newChunk( nLen ); + cpy( pNew->pData, pData, nLen ); + + appendChunk( pNew ); + } + + void append( const chr *pData, long nLen ) + { + Chunk *pNew = newChunk( nLen ); + + cpy( pNew->pData, pData, nLen ); + + appendChunk( pNew ); + } + + void prepend( const chr *pData ) + { + long nLen; + for( nLen = 0; pData[nLen] != (chr)0; nLen++ ); + + Chunk *pNew = newChunk( nLen ); + cpy( pNew->pData, pData, nLen ); + + prependChunk( pNew ); + } + + void prepend( const chr *pData, long nLen ) + { + Chunk *pNew = newChunk( nLen ); + + cpy( pNew->pData, pData, nLen ); + + prependChunk( pNew ); + } + + void clear() + { + realClear(); + } + + void resize( long nNewSize ) + { + if( nLength == nNewSize ) + return; + + flatten(); + + Chunk *pNew = newChunk( nNewSize ); + long nNewLen = (nNewSize<nLength)?(nNewSize):(nLength); + cpy( pNew->pData, pFirst->pData, nNewLen ); + pNew->pData[nNewLen] = (chr)0; + aChr.deallocate( pFirst->pData, pFirst->nLength+1 ); + aChunk.deallocate( pFirst, 1 ); + pFirst = pLast = pNew; + nLength = nNewSize; + } + + long getSize() const + { + return nLength; + } + + chr *getStr() + { + if( pFirst == NULL ) + return NULL; + + flatten(); + return pFirst->pData; + } + + const chr *getStr() const + { + if( pFirst == NULL ) + return NULL; + + flatten(); + return pFirst->pData; + } + + chr *c_str() + { + if( pFirst == NULL ) + return NULL; + + flatten(); + return pFirst->pData; + } + + const chr *c_str() const + { + if( pFirst == NULL ) + return NULL; + + flatten(); + return pFirst->pData; + } + + MyType &operator +=( const chr *pData ) + { + append( pData ); + + return (*this); + } + + MyType &operator +=( const MyType &rSrc ) + { + rSrc.flatten(); + append( rSrc.pFirst->pData, rSrc.nLength ); + + return (*this); + } + + MyType &operator +=( const chr pData ) + { + chr tmp[2] = { pData, (chr)0 }; + append( tmp ); + + return (*this); + } + + MyType &operator =( const chr *pData ) + { + clear(); + append( pData ); + + return (*this); + } + + MyType &operator =( const MyType &rSrc ) + { + //if( rSrc.isFlat() ) + //{ + joinShare( rSrc ); + //} + //else + //{ + // copyFrom( rSrc ); + //} + // + + return (*this); + } + + bool operator ==( const chr *pData ) const + { + if( pFirst == NULL ) { + if( pData == NULL ) + return true; + return false; + } + + flatten(); + const chr *a = pData; + chr *b = pFirst->pData; + for( ; *a!=(chr)0; a++, b++ ) + { + if( *a != *b ) + return false; + } + + return true; + } + + bool operator ==( const MyType &pData ) const + { + if( pFirst == pData.pFirst ) + return true; + if( pFirst == NULL ) + return false; + + flatten(); + pData.flatten(); + const chr *a = pData.pFirst->pData; + chr *b = pFirst->pData; + for( ; *a!=(chr)0; a++, b++ ) + { + if( *a != *b ) + return false; + } + + return true; + } + + bool operator !=(const chr *pData ) const + { + return !(*this == pData); + } + + bool operator !=(const MyType &pData ) const + { + return !(*this == pData); + } + + chr &operator[]( long nIndex ) + { + flatten(); + + return pFirst->pData[nIndex]; + } + + const chr &operator[]( long nIndex ) const + { + flatten(); + + return pFirst->pData[nIndex]; + } + + bool isWS( long nIndex ) const + { + flatten(); + + return pFirst->pData[nIndex]==' ' || pFirst->pData[nIndex]=='\t' + || pFirst->pData[nIndex]=='\r' || pFirst->pData[nIndex]=='\n'; + } + + bool isAlpha( long nIndex ) const + { + flatten(); + + return (pFirst->pData[nIndex] >= 'a' && pFirst->pData[nIndex] <= 'z') + || (pFirst->pData[nIndex] >= 'A' && pFirst->pData[nIndex] <= 'Z'); + } + + void toLower() + { + flatten(); + unShare(); + + for( long j = 0; j < nLength; j++ ) + { + if( pFirst->pData[j] >= 'A' && pFirst->pData[j] <= 'Z' ) + pFirst->pData[j] -= 'A'-'a'; + } + } + + void toUpper() + { + flatten(); + unShare(); + + for( long j = 0; j < nLength; j++ ) + { + if( pFirst->pData[j] >= 'a' && pFirst->pData[j] <= 'z' ) + pFirst->pData[j] += 'A'-'a'; + } + } + + void archive( class Archive &ar ) + { + if( ar.isLoading() ) + { + clear(); + long nLen; + ar >> nLen; + + Chunk *pNew = newChunk( nLen ); + ar.read( pNew->pData, nLen*sizeof(chr) ); + appendChunk( pNew ); + } + else + { + flatten(); + + ar << nLength; + ar.write( pFirst->pData, nLength*sizeof(chr) ); + } + } + + private: + void flatten() const + { + if( isFlat() ) + return; + + if( pFirst == NULL ) + return; + + unShare(); + + Chunk *pNew = newChunk( nLength ); + chr *pos = pNew->pData; + Chunk *i = pFirst; + for(;;) + { + cpy( pos, i->pData, i->nLength ); + pos += i->nLength; + i = i->pNext; + if( i == NULL ) + break; + } + realClear(); + + pLast = pFirst = pNew; + nLength = pNew->nLength; + } + + void realClear() const + { + if( pFirst == NULL ) + return; + + if( isShared() ) + { + decRefs(); + } + else + { + Chunk *i = pFirst; + for(;;) + { + Chunk *n = i->pNext; + aChr.deallocate( i->pData, i->nLength+1 ); + aChunk.deallocate( i, 1 ); + if( n == NULL ) + break; + i = n; + } + pFirst = pLast = NULL; + nLength = 0; + } + } + + void copyFrom( const FBasicString<chr, chralloc, chunkalloc> &rSrc ) + { + if( rSrc.pFirst == NULL ) + return; + + decRefs(); + + Chunk *pNew = newChunk( rSrc.nLength ); + chr *pos = pNew->pData; + Chunk *i = rSrc.pFirst; + for(;;) + { + cpy( pos, i->pData, i->nLength ); + pos += i->nLength; + i = i->pNext; + if( i == NULL ) + break; + } + clear(); + + appendChunk( pNew ); + } + + bool isFlat() const + { + return (pFirst == pLast); + } + + bool isShared() const + { + return (pnRefs != NULL); + } + + Chunk *newChunk() const + { + Chunk *pNew = aChunk.allocate( 1 ); + pNew->pNext = NULL; + return pNew; + } + + Chunk *newChunk( long nLen ) const + { + Chunk *pNew = aChunk.allocate( 1 ); + pNew->pNext = NULL; + pNew->nLength = nLen; + pNew->pData = aChr.allocate( nLen+1 ); + pNew->pData[nLen] = (chr)0; + return pNew; + } + + void appendChunk( Chunk *pNewChunk ) + { + unShare(); + + if( pFirst == NULL ) + pLast = pFirst = pNewChunk; + else + { + pLast->pNext = pNewChunk; + pLast = pNewChunk; + } + + nLength += pNewChunk->nLength; + } + + void prependChunk( Chunk *pNewChunk ) + { + unShare(); + + if( pFirst == NULL ) + pLast = pFirst = pNewChunk; + else + { + pNewChunk->pNext = pFirst; + pFirst = pNewChunk; + } + + nLength += pNewChunk->nLength; + } + + void joinShare( MyType &rSrc ) + { + clear(); + + if( !rSrc.isFlat() ) + rSrc.flatten(); + + rSrc.initCount(); + pnRefs = rSrc.pnRefs; + (*pnRefs)++; + nLength = rSrc.nLength; + pFirst = rSrc.pFirst; + pLast = rSrc.pLast; + } + + void joinShare( const MyType &rSrc ) + { + clear(); + + rSrc.flatten(); + + if( !rSrc.isShared() ) + { + rSrc.pnRefs = new uint32_t; + (*rSrc.pnRefs) = 1; + } + pnRefs = rSrc.pnRefs; + (*pnRefs)++; + nLength = rSrc.nLength; + pFirst = rSrc.pFirst; + pLast = rSrc.pLast; + } + + /** + * This takes an object that was shared and makes a copy of the base data + * that was being shared so that this copy can be changed. This should be + * added before any call that will change this object; + */ + void unShare() const + { + if( isShared() == false ) + return; + + Chunk *pNew = newChunk( nLength ); + chr *pos = pNew->pData; + Chunk *i = pFirst; + for(;;) + { + cpy( pos, i->pData, i->nLength ); + pos += i->nLength; + i = i->pNext; + if( i == NULL ) + break; + } + decRefs(); + pLast = pFirst = pNew; + nLength = pNew->nLength; + } + + /** + * This decrements our ref count and pulls us out of the share. If the ref + * count hits zero because of this, it destroys the share. This is not + * safe to call on it's own, it's much better to call unShare. + */ + void decRefs() const + { + if( isShared() ) + { + (*pnRefs)--; + if( (*pnRefs) == 0 ) + destroyShare(); + else + { + pnRefs = NULL; + pFirst = NULL; + pLast = NULL; + nLength = 0; + } + } + } + + /** + * While the unShare function removes an instance from a share, this + * function destroys the data that was in the share, removing the share + * itself. This should only be called when the refcount for the share has + * or is about to reach zero. + */ + void destroyShare() const + { + delete pnRefs; + pnRefs = NULL; + realClear(); + } + +#ifdef VALTEST + void cpy( chr *dest, const chr *src, long count ) const + { + for( int j = 0; j < count; j++ ) + { + *dest = *src; + dest++; + src++; + } + } +#endif + + void initCount() const + { + if( !isShared() ) + { + pnRefs = new uint32_t; + (*pnRefs) = 1; + } + } + + private: + mutable long nLength; + mutable uint32_t *pnRefs; + mutable Chunk *pFirst; + mutable Chunk *pLast; + + mutable chralloc aChr; + mutable chunkalloc aChunk; + }; + + typedef FBasicString<char> FString; + + template<> uint32_t __calcHashCode<FString>( const FString &k ); + template<> bool __cmpHashKeys<FString>( const FString &a, const FString &b ); +} + +#endif diff --git a/src/hash.cpp b/src/hash.cpp new file mode 100644 index 0000000..a207c29 --- /dev/null +++ b/src/hash.cpp @@ -0,0 +1,101 @@ +#include "hash.h" + +namespace Bu { subExceptionDef( HashException ) } + +template<> uint32_t Bu::__calcHashCode<int>( const int &k ) +{ + return k; +} + +template<> bool Bu::__cmpHashKeys<int>( const int &a, const int &b ) +{ + return a == b; +} + +template<> uint32_t Bu::__calcHashCode<unsigned int>( const unsigned int &k ) +{ + return k; +} + +template<> bool Bu::__cmpHashKeys<unsigned int>( const unsigned int &a, const unsigned int &b ) +{ + return a == b; +} + +template<> +uint32_t Bu::__calcHashCode<const char *>( const char * const &k ) +{ + if (k == NULL) + { + return 0; + } + + unsigned long int nPos = 0; + for( const char *s = k; *s; s++ ) + { + nPos = *s + (nPos << 6) + (nPos << 16) - nPos; + } + + return nPos; +} + +template<> bool Bu::__cmpHashKeys<const char *>( const char * const &a, const char * const &b ) +{ + if( a == b ) + return true; + + for(int j=0; a[j] == b[j]; j++ ) + if( a[j] == '\0' ) + return true; + + return false; +} + +template<> +uint32_t Bu::__calcHashCode<char *>( char * const &k ) +{ + if (k == NULL) + { + return 0; + } + + unsigned long int nPos = 0; + for( const char *s = k; *s; s++ ) + { + nPos = *s + (nPos << 6) + (nPos << 16) - nPos; + } + + return nPos; +} + +template<> bool Bu::__cmpHashKeys<char *>( char * const &a, char * const &b ) +{ + if( a == b ) + return true; + + for(int j=0; a[j] == b[j]; j++ ) + if( a[j] == '\0' ) + return true; + + return false; +} + +template<> uint32_t Bu::__calcHashCode<std::string>( const std::string &k ) +{ + std::string::size_type j, sz = k.size(); + const char *s = k.c_str(); + + unsigned long int nPos = 0; + for( j = 0; j < sz; j++, s++ ) + { + nPos = *s + (nPos << 6) + (nPos << 16) - nPos; + } + + return nPos; +} + +template<> bool Bu::__cmpHashKeys<std::string>( const std::string &a, const std::string &b ) +{ + return a == b; +} + diff --git a/src/hash.h b/src/hash.h new file mode 100644 index 0000000..9e498f1 --- /dev/null +++ b/src/hash.h @@ -0,0 +1,745 @@ +#ifndef HASH_H +#define HASH_H + +#include <stddef.h> +#include <string.h> +#include <memory> +#include <iostream> +#include <list> +#include <utility> +#include "exceptionbase.h" +#include "archable.h" +#include "archive.h" + +#define bitsToBytes( n ) (n/32+(n%32>0 ? 1 : 0)) + +namespace Bu +{ + subExceptionDecl( HashException ) + + enum eHashException + { + excodeNotFilled + }; + + template<typename T> + uint32_t __calcHashCode( const T &k ); + + template<typename T> + bool __cmpHashKeys( const T &a, const T &b ); + + struct __calcNextTSize_fast + { + uint32_t operator()( uint32_t nCapacity, uint32_t nFill, uint32_t nDeleted ) const + { + if( nDeleted >= nCapacity/2 ) + return nCapacity; + return nCapacity*2+1; + } + }; + + template<typename key, typename value, typename sizecalc = __calcNextTSize_fast, typename keyalloc = std::allocator<key>, typename valuealloc = std::allocator<value>, typename challoc = std::allocator<uint32_t> > + class Hash; + + template< typename key, typename _value, typename sizecalc = __calcNextTSize_fast, typename keyalloc = std::allocator<key>, typename valuealloc = std::allocator<_value>, typename challoc = std::allocator<uint32_t> > + struct HashProxy + { + friend class Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc>; + private: + HashProxy( Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc> &h, key *k, uint32_t nPos, uint32_t hash ) : + hsh( h ), + pKey( k ), + nPos( nPos ), + hash( hash ), + bFilled( false ) + { + } + + HashProxy( Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc> &h, uint32_t nPos, _value *pValue ) : + hsh( h ), + nPos( nPos ), + pValue( pValue ), + bFilled( true ) + { + } + + Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc> &hsh; + key *pKey; + uint32_t nPos; + _value *pValue; + uint32_t hash; + bool bFilled; + + public: + operator _value &() + { + if( bFilled == false ) + throw HashException( + excodeNotFilled, + "No data assosiated with that key." + ); + return *pValue; + } + + _value &value() + { + if( bFilled == false ) + throw HashException( + excodeNotFilled, + "No data assosiated with that key." + ); + return *pValue; + } + + bool isFilled() + { + return bFilled; + } + + void erase() + { + if( bFilled ) + { + hsh._erase( nPos ); + hsh.onDelete(); + } + } + + _value operator=( _value nval ) + { + if( bFilled ) + { + hsh.va.destroy( pValue ); + hsh.va.construct( pValue, nval ); + hsh.onUpdate(); + } + else + { + hsh.fill( nPos, *pKey, nval, hash ); + hsh.onInsert(); + } + + return nval; + } + + _value *operator->() + { + if( bFilled == false ) + throw HashException( + excodeNotFilled, + "No data assosiated with that key." + ); + return pValue; + } + }; + + template<typename key, typename value, typename sizecalc, typename keyalloc, typename valuealloc, typename challoc > + class Hash + { + friend struct HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc>; + public: + Hash() : + nCapacity( 11 ), + nFilled( 0 ), + nDeleted( 0 ), + bFilled( NULL ), + bDeleted( NULL ), + aKeys( NULL ), + aValues( NULL ), + aHashCodes( NULL ) + { + nKeysSize = bitsToBytes( nCapacity ); + bFilled = ca.allocate( nKeysSize ); + bDeleted = ca.allocate( nKeysSize ); + clearBits(); + + aHashCodes = ca.allocate( nCapacity ); + aKeys = ka.allocate( nCapacity ); + aValues = va.allocate( nCapacity ); + } + + Hash( const Hash &src ) : + nCapacity( src.nCapacity ), + nFilled( 0 ), + nDeleted( 0 ), + bFilled( NULL ), + bDeleted( NULL ), + aKeys( NULL ), + aValues( NULL ), + aHashCodes( NULL ) + { + nKeysSize = bitsToBytes( nCapacity ); + bFilled = ca.allocate( nKeysSize ); + bDeleted = ca.allocate( nKeysSize ); + clearBits(); + + aHashCodes = ca.allocate( nCapacity ); + aKeys = ka.allocate( nCapacity ); + aValues = va.allocate( nCapacity ); + + for( uint32_t j = 0; j < src.nCapacity; j++ ) + { + if( src.isFilled( j ) ) + { + insert( src.aKeys[j], src.aValues[j] ); + } + } + } + + Hash &operator=( const Hash &src ) + { + for( uint32_t j = 0; j < nCapacity; j++ ) + { + if( isFilled( j ) ) + if( !isDeleted( j ) ) + { + va.destroy( &aValues[j] ); + ka.destroy( &aKeys[j] ); + } + } + va.deallocate( aValues, nCapacity ); + ka.deallocate( aKeys, nCapacity ); + ca.deallocate( bFilled, nKeysSize ); + ca.deallocate( bDeleted, nKeysSize ); + ca.deallocate( aHashCodes, nCapacity ); + + nFilled = 0; + nDeleted = 0; + nCapacity = src.nCapacity; + nKeysSize = bitsToBytes( nCapacity ); + bFilled = ca.allocate( nKeysSize ); + bDeleted = ca.allocate( nKeysSize ); + clearBits(); + + aHashCodes = ca.allocate( nCapacity ); + aKeys = ka.allocate( nCapacity ); + aValues = va.allocate( nCapacity ); + + for( uint32_t j = 0; j < src.nCapacity; j++ ) + { + if( src.isFilled( j ) ) + { + insert( src.aKeys[j], src.aValues[j] ); + } + } + + return *this; + } + + virtual ~Hash() + { + for( uint32_t j = 0; j < nCapacity; j++ ) + { + if( isFilled( j ) ) + if( !isDeleted( j ) ) + { + va.destroy( &aValues[j] ); + ka.destroy( &aKeys[j] ); + } + } + va.deallocate( aValues, nCapacity ); + ka.deallocate( aKeys, nCapacity ); + ca.deallocate( bFilled, nKeysSize ); + ca.deallocate( bDeleted, nKeysSize ); + ca.deallocate( aHashCodes, nCapacity ); + } + + uint32_t getCapacity() + { + return nCapacity; + } + + uint32_t getFill() + { + return nFilled; + } + + uint32_t size() + { + return nFilled-nDeleted; + } + + uint32_t getDeleted() + { + return nDeleted; + } + + virtual HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc> operator[]( key k ) + { + uint32_t hash = __calcHashCode( k ); + bool bFill; + uint32_t nPos = probe( hash, k, bFill ); + + if( bFill ) + { + return HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc>( *this, nPos, &aValues[nPos] ); + } + else + { + return HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc>( *this, &k, nPos, hash ); + } + } + + virtual void insert( key k, value v ) + { + uint32_t hash = __calcHashCode( k ); + bool bFill; + uint32_t nPos = probe( hash, k, bFill ); + + if( bFill ) + { + va.destroy( &aValues[nPos] ); + va.construct( &aValues[nPos], v ); + onUpdate(); + } + else + { + fill( nPos, k, v, hash ); + onInsert(); + } + } + + virtual void erase( key k ) + { + uint32_t hash = __calcHashCode( k ); + bool bFill; + uint32_t nPos = probe( hash, k, bFill ); + + if( bFill ) + { + _erase( nPos ); + onDelete(); + } + } + + struct iterator; + virtual void erase( struct iterator &i ) + { + if( this != &i.hsh ) + throw HashException("This iterator didn't come from this Hash."); + if( isFilled( i.nPos ) && !isDeleted( i.nPos ) ) + { + _erase( i.nPos ); + onDelete(); + } + } + + virtual void clear() + { + for( uint32_t j = 0; j < nCapacity; j++ ) + { + if( isFilled( j ) ) + if( !isDeleted( j ) ) + { + va.destroy( &aValues[j] ); + ka.destroy( &aKeys[j] ); + onDelete(); + } + } + + clearBits(); + } + + virtual value &get( key k ) + { + uint32_t hash = __calcHashCode( k ); + bool bFill; + uint32_t nPos = probe( hash, k, bFill ); + + if( bFill ) + { + return aValues[nPos]; + } + else + { + throw HashException( + excodeNotFilled, + "No data assosiated with that key." + ); + } + } + + virtual bool has( key k ) + { + bool bFill; + probe( __calcHashCode( k ), k, bFill, false ); + + return bFill; + } + + typedef struct iterator + { + friend class Hash<key, value, sizecalc, keyalloc, valuealloc, challoc>; + private: + iterator( Hash<key, value, sizecalc, keyalloc, valuealloc, challoc> &hsh ) : + hsh( hsh ), + nPos( 0 ), + bFinished( false ) + { + nPos = hsh.getFirstPos( bFinished ); + } + + iterator( Hash<key, value, sizecalc, keyalloc, valuealloc, challoc> &hsh, bool bDone ) : + hsh( hsh ), + nPos( 0 ), + bFinished( bDone ) + { + } + + Hash<key, value, sizecalc, keyalloc, valuealloc, challoc> &hsh; + uint32_t nPos; + bool bFinished; + + public: + iterator operator++( int ) + { + if( bFinished == false ) + nPos = hsh.getNextPos( nPos, bFinished ); + + return *this; + } + + iterator operator++() + { + if( bFinished == false ) + nPos = hsh.getNextPos( nPos, bFinished ); + + return *this; + } + + bool operator==( const iterator &oth ) + { + if( bFinished != oth.bFinished ) + return false; + if( bFinished == true ) + { + return true; + } + else + { + if( oth.nPos == nPos ) + return true; + return false; + } + } + + bool operator!=( const iterator &oth ) + { + return !(*this == oth ); + } + + iterator operator=( const iterator &oth ) + { + if( &hsh != &oth.hsh ) + throw HashException( + "Cannot mix iterators from different hash objects."); + nPos = oth.nPos; + bFinished = oth.bFinished; + } + + std::pair<key,value> operator *() + { + return hsh.getAtPos( nPos ); + } + + key &getKey() + { + return hsh.getKeyAtPos( nPos ); + } + + value &getValue() + { + return hsh.getValueAtPos( nPos ); + } + }; + + iterator begin() + { + return iterator( *this ); + } + + iterator end() + { + return iterator( *this, true ); + } + + std::list<key> getKeys() + { + std::list<key> lKeys; + + for( uint32_t j = 0; j < nCapacity; j++ ) + { + if( isFilled( j ) ) + { + if( !isDeleted( j ) ) + { + lKeys.push_back( aKeys[j] ); + } + } + } + + return lKeys; + } + + protected: + virtual void onInsert() {} + virtual void onUpdate() {} + virtual void onDelete() {} + virtual void onReHash() {} + + virtual void clearBits() + { + for( uint32_t j = 0; j < nKeysSize; j++ ) + { + bFilled[j] = bDeleted[j] = 0; + } + } + + virtual void fill( uint32_t loc, key &k, value &v, uint32_t hash ) + { + bFilled[loc/32] |= (1<<(loc%32)); + va.construct( &aValues[loc], v ); + ka.construct( &aKeys[loc], k ); + aHashCodes[loc] = hash; + nFilled++; + //printf("Filled: %d, Deleted: %d, Capacity: %d\n", + // nFilled, nDeleted, nCapacity ); + } + + virtual void _erase( uint32_t loc ) + { + bDeleted[loc/32] |= (1<<(loc%32)); + va.destroy( &aValues[loc] ); + ka.destroy( &aKeys[loc] ); + nDeleted++; + //printf("Filled: %d, Deleted: %d, Capacity: %d\n", + // nFilled, nDeleted, nCapacity ); + } + + virtual std::pair<key,value> getAtPos( uint32_t nPos ) + { + return std::pair<key,value>(aKeys[nPos],aValues[nPos]); + } + + virtual key &getKeyAtPos( uint32_t nPos ) + { + return aKeys[nPos]; + } + + virtual value &getValueAtPos( uint32_t nPos ) + { + return aValues[nPos]; + } + + virtual uint32_t getFirstPos( bool &bFinished ) + { + for( uint32_t j = 0; j < nCapacity; j++ ) + { + if( isFilled( j ) ) + if( !isDeleted( j ) ) + return j; + } + + bFinished = true; + return 0; + } + + virtual uint32_t getNextPos( uint32_t nPos, bool &bFinished ) + { + for( uint32_t j = nPos+1; j < nCapacity; j++ ) + { + if( isFilled( j ) ) + if( !isDeleted( j ) ) + return j; + } + + bFinished = true; + return 0; + } + + uint32_t probe( uint32_t hash, key k, bool &bFill, bool rehash=true ) + { + uint32_t nCur = hash%nCapacity; + + // First we scan to see if the key is already there, abort if we + // run out of probing room, or we find a non-filled entry + for( int8_t j = 0; + isFilled( nCur ) && j < 32; + nCur = (nCur + (1<<j))%nCapacity, j++ + ) + { + // Is this the same hash code we were looking for? + if( hash == aHashCodes[nCur] ) + { + // Skip over deleted entries. Deleted entries are also filled, + // so we only have to do this check here. + if( isDeleted( nCur ) ) + continue; + + // Is it really the same key? (for safety) + if( __cmpHashKeys( aKeys[nCur], k ) == true ) + { + bFill = true; + return nCur; + } + } + } + + // This is our insurance, if the table is full, then go ahead and + // rehash, then try again. + if( isFilled( nCur ) && rehash == true ) + { + reHash( szCalc(getCapacity(), getFill(), getDeleted()) ); + + // This is potentially dangerous, and could cause an infinite loop. + // Be careful writing probe, eh? + return probe( hash, k, bFill ); + } + + bFill = false; + return nCur; + } + + void reHash( uint32_t nNewSize ) + { + //printf("---REHASH---"); + //printf("Filled: %d, Deleted: %d, Capacity: %d\n", + // nFilled, nDeleted, nCapacity ); + + // Save all the old data + uint32_t nOldCapacity = nCapacity; + uint32_t *bOldFilled = bFilled; + uint32_t *aOldHashCodes = aHashCodes; + uint32_t nOldKeysSize = nKeysSize; + uint32_t *bOldDeleted = bDeleted; + value *aOldValues = aValues; + key *aOldKeys = aKeys; + + // Calculate new sizes + nCapacity = nNewSize; + nKeysSize = bitsToBytes( nCapacity ); + + // Allocate new memory + prep + bFilled = ca.allocate( nKeysSize ); + bDeleted = ca.allocate( nKeysSize ); + clearBits(); + + aHashCodes = ca.allocate( nCapacity ); + aKeys = ka.allocate( nCapacity ); + aValues = va.allocate( nCapacity ); + + nDeleted = nFilled = 0; + + // Re-insert all of the old data (except deleted items) + for( uint32_t j = 0; j < nOldCapacity; j++ ) + { + if( (bOldFilled[j/32]&(1<<(j%32)))!=0 && + (bOldDeleted[j/32]&(1<<(j%32)))==0 ) + { + insert( aOldKeys[j], aOldValues[j] ); + } + } + + // Delete all of the old data + for( uint32_t j = 0; j < nOldCapacity; j++ ) + { + if( (bOldFilled[j/32]&(1<<(j%32)))!=0 ) + { + va.destroy( &aOldValues[j] ); + ka.destroy( &aOldKeys[j] ); + } + } + va.deallocate( aOldValues, nOldCapacity ); + ka.deallocate( aOldKeys, nOldCapacity ); + ca.deallocate( bOldFilled, nOldKeysSize ); + ca.deallocate( bOldDeleted, nOldKeysSize ); + ca.deallocate( aOldHashCodes, nOldCapacity ); + } + + virtual bool isFilled( uint32_t loc ) const + { + return (bFilled[loc/32]&(1<<(loc%32)))!=0; + } + + virtual bool isDeleted( uint32_t loc ) + { + return (bDeleted[loc/32]&(1<<(loc%32)))!=0; + } + + protected: + uint32_t nCapacity; + uint32_t nFilled; + uint32_t nDeleted; + uint32_t *bFilled; + uint32_t *bDeleted; + uint32_t nKeysSize; + key *aKeys; + value *aValues; + uint32_t *aHashCodes; + valuealloc va; + keyalloc ka; + challoc ca; + sizecalc szCalc; + }; + + template<> uint32_t __calcHashCode<int>( const int &k ); + template<> bool __cmpHashKeys<int>( const int &a, const int &b ); + + template<> uint32_t __calcHashCode<unsigned int>( const unsigned int &k ); + template<> bool __cmpHashKeys<unsigned int>( const unsigned int &a, const unsigned int &b ); + + template<> uint32_t __calcHashCode<const char *>( const char * const &k ); + template<> bool __cmpHashKeys<const char *>( const char * const &a, const char * const &b ); + + template<> uint32_t __calcHashCode<char *>( char * const &k ); + template<> bool __cmpHashKeys<char *>( char * const &a, char * const &b ); + + template<> uint32_t __calcHashCode<std::string>( const std::string &k ); + template<> bool __cmpHashKeys<std::string>( const std::string &a, const std::string &b ); + + template<typename key, typename value> + Archive &operator<<( Archive &ar, Hash<key,value> &h ) + { + ar << h.size(); + for( typename Hash<key,value>::iterator i = h.begin(); i != h.end(); i++ ) + { + std::pair<key,value> p = *i; + ar << p.first << p.second; + } + + return ar; + } + + template<typename key, typename value> + Archive &operator>>( Archive &ar, Hash<key,value> &h ) + { + h.clear(); + uint32_t nSize; + ar >> nSize; + + for( uint32_t j = 0; j < nSize; j++ ) + { + key k; value v; + ar >> k >> v; + h.insert( k, v ); + } + + return ar; + } + + /* + template<typename key, typename value> + Serializer &operator&&( Serializer &ar, Hash<key,value> &h ) + { + if( ar.isLoading() ) + { + return ar >> h; + } + else + { + return ar << h; + } + }*/ +} + +#endif diff --git a/src/old/exceptionbase.cpp b/src/old/exceptionbase.cpp deleted file mode 100644 index f3d22da..0000000 --- a/src/old/exceptionbase.cpp +++ /dev/null @@ -1,70 +0,0 @@ -#include "exceptionbase.h" -#include <stdarg.h> - -ExceptionBase::ExceptionBase( const char *lpFormat, ... ) throw() : - nErrorCode( 0 ), - sWhat( NULL ) -{ - va_list ap; - - va_start(ap, lpFormat); - setWhat( lpFormat, ap ); - va_end(ap); -} - -ExceptionBase::ExceptionBase( int nCode, const char *lpFormat, ... ) throw() : - nErrorCode( nCode ), - sWhat( NULL ) -{ - va_list ap; - - va_start(ap, lpFormat); - setWhat( lpFormat, ap ); - va_end(ap); -} - -ExceptionBase::ExceptionBase( int nCode ) throw() : - nErrorCode( nCode ), - sWhat( NULL ) -{ -} - -ExceptionBase::~ExceptionBase() throw() -{ - if( sWhat ) - { - delete[] sWhat; - sWhat = NULL; - } -} - -void ExceptionBase::setWhat( const char *lpFormat, va_list &vargs ) -{ - if( sWhat ) delete[] sWhat; - int nSize; - - nSize = vsnprintf( NULL, 0, lpFormat, vargs ); - sWhat = new char[nSize+1]; - vsnprintf( sWhat, nSize+1, lpFormat, vargs ); -} - -void ExceptionBase::setWhat( const char *lpText ) -{ - if( sWhat ) delete[] sWhat; - int nSize; - - nSize = strlen( lpText ); - sWhat = new char[nSize+1]; - strcpy( sWhat, lpText ); -} - -const char *ExceptionBase::what() const throw() -{ - return sWhat; -} - -int ExceptionBase::getErrorCode() -{ - return nErrorCode; -} - diff --git a/src/old/exceptionbase.h b/src/old/exceptionbase.h deleted file mode 100644 index 6f1eca7..0000000 --- a/src/old/exceptionbase.h +++ /dev/null @@ -1,105 +0,0 @@ -#ifndef EXCEPTION_BASE_H -#define EXCEPTION_BASE_H - -#include <string> -#include <exception> -#include <stdarg.h> - -/** - * A generalized Exception base class. This is nice for making general and - * flexible child classes that can create new error code classes. - */ -class ExceptionBase : public std::exception -{ -public: - /** - * Construct an exception with an error code of zero, but with a - * description. The use of this is not reccomended most of the time, it's - * generally best to include an error code with the exception so your - * program can handle the exception in a better way. - * @param sFormat The format of the text. See printf for more info. - */ - ExceptionBase( const char *sFormat, ... ) throw(); - - /** - * - * @param nCode - * @param sFormat - */ - ExceptionBase( int nCode, const char *sFormat, ... ) throw(); - - /** - * - * @param nCode - * @return - */ - ExceptionBase( int nCode=0 ) throw(); - - /** - * - * @return - */ - virtual ~ExceptionBase() throw(); - - /** - * - * @return - */ - virtual const char *what() const throw(); - - /** - * - * @return - */ - int getErrorCode(); - - /** - * - * @param lpFormat - * @param vargs - */ - void setWhat( const char *lpFormat, va_list &vargs ); - - /** - * - * @param lpText - */ - void setWhat( const char *lpText ); - -private: - int nErrorCode; /**< The code for the error that occured. */ - char *sWhat; /**< The text string telling people what went wrong. */ -}; - -#define subExceptionDecl( name ) \ -class name : public ExceptionBase \ -{ \ - public: \ - name( const char *sFormat, ... ) throw (); \ - name( int nCode, const char *sFormat, ... ) throw(); \ - name( int nCode=0 ) throw (); \ -}; - -#define subExceptionDef( name ) \ -name::name( const char *lpFormat, ... ) throw() : \ - ExceptionBase( 0 ) \ -{ \ - va_list ap; \ - va_start( ap, lpFormat ); \ - setWhat( lpFormat, ap ); \ - va_end( ap ); \ -} \ -name::name( int nCode, const char *lpFormat, ... ) throw() : \ - ExceptionBase( nCode ) \ -{ \ - va_list ap; \ - va_start( ap, lpFormat ); \ - setWhat( lpFormat, ap ); \ - va_end( ap ); \ -} \ -name::name( int nCode ) throw() : \ - ExceptionBase( nCode ) \ -{ \ -} - -#endif diff --git a/src/old/exceptions.cpp b/src/old/exceptions.cpp deleted file mode 100644 index ce79a5e..0000000 --- a/src/old/exceptions.cpp +++ /dev/null @@ -1,8 +0,0 @@ -#include "exceptions.h" -#include <stdarg.h> - -subExceptionDef( XmlException ) -subExceptionDef( FileException ) -subExceptionDef( ConnectionException ) -subExceptionDef( PluginException ) - diff --git a/src/old/exceptions.h b/src/old/exceptions.h deleted file mode 100644 index 0ab2b15..0000000 --- a/src/old/exceptions.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef EXCEPTIONS_H -#define EXCEPTIONS_H - -#include "exceptionbase.h" -#include <stdarg.h> - -subExceptionDecl( XmlException ) -subExceptionDecl( FileException ) -subExceptionDecl( ConnectionException ) -subExceptionDecl( PluginException ) - -enum eFileException -{ - excodeEOF -}; - -enum eConnectionException -{ - excodeReadError, - excodeBadReadError, - excodeConnectionClosed, - excodeSocketTimeout -}; - -#endif diff --git a/src/old/fstring.cpp b/src/old/fstring.cpp deleted file mode 100644 index 82d024d..0000000 --- a/src/old/fstring.cpp +++ /dev/null @@ -1,13 +0,0 @@ -#include "fstring.h" -#include "hash.h" - -template<> uint32_t __calcHashCode<FString>( const FString &k ) -{ - return __calcHashCode( k.c_str() ); -} - -template<> bool __cmpHashKeys<FString>( const FString &a, const FString &b ) -{ - return a == b; -} - diff --git a/src/old/fstring.h b/src/old/fstring.h deleted file mode 100644 index c5397cc..0000000 --- a/src/old/fstring.h +++ /dev/null @@ -1,651 +0,0 @@ -#ifndef F_STRING_H -#define F_STRING_H - -#include <stdint.h> -#include <memory> -#include "serializable.h" -#include "serializer.h" - -template< typename chr > -struct FStringChunk -{ - long nLength; - chr *pData; - FStringChunk *pNext; -}; - -/** - * Flexible String class. This class was designed with string passing and - * generation in mind. Like the standard string class you can specify what - * datatype to use for each character. Unlike the standard string class, - * collection of appended and prepended terms is done lazily, making long - * operations that involve many appends very inexpensive. In addition internal - * ref-counting means that if you pass strings around between functions there's - * almost no overhead in time or memory since a reference is created and no - * data is actually copied. This also means that you never need to put any - * FBasicString into a ref-counting container class. - */ -template< typename chr, typename chralloc=std::allocator<chr>, typename chunkalloc=std::allocator<struct FStringChunk<chr> > > -class FBasicString : public Serializable -{ -#ifndef VALTEST -#define cpy( dest, src, size ) memcpy( dest, src, size*sizeof(chr) ) -#endif -private: - typedef struct FStringChunk<chr> Chunk; - typedef struct FBasicString<chr, chralloc, chunkalloc> MyType; - -public: - FBasicString() : - nLength( 0 ), - pnRefs( NULL ), - pFirst( NULL ), - pLast( NULL ) - { - } - - FBasicString( const chr *pData ) : - nLength( 0 ), - pnRefs( NULL ), - pFirst( NULL ), - pLast( NULL ) - { - append( pData ); - } - - FBasicString( const chr *pData, long nLength ) : - nLength( 0 ), - pnRefs( NULL ), - pFirst( NULL ), - pLast( NULL ) - { - append( pData, nLength ); - } - - FBasicString( const MyType &rSrc ) : - nLength( 0 ), - pnRefs( NULL ), - pFirst( NULL ), - pLast( NULL ) - { - // Here we have no choice but to copy, since the other guy is a const. - // In the case that the source were flat, we could get a reference, it - // would make some things faster, but not matter in many other cases. - - joinShare( rSrc ); - //copyFrom( rSrc ); - } - - FBasicString( const MyType &rSrc, long nLength ) : - nLength( 0 ), - pnRefs( NULL ), - pFirst( NULL ), - pLast( NULL ) - { - append( rSrc.pFirst->pData, nLength ); - } - - FBasicString( const MyType &rSrc, long nStart, long nLength ) : - nLength( 0 ), - pnRefs( NULL ), - pFirst( NULL ), - pLast( NULL ) - { - append( rSrc.pFirst->pData+nStart, nLength ); - } - - FBasicString( long nSize ) : - nLength( nSize ), - pnRefs( NULL ), - pFirst( NULL ), - pLast( NULL ) - { - pFirst = pLast = newChunk( nSize ); - } - - virtual ~FBasicString() - { - clear(); - } - - void append( const chr *pData ) - { - long nLen; - for( nLen = 0; pData[nLen] != (chr)0; nLen++ ); - - Chunk *pNew = newChunk( nLen ); - cpy( pNew->pData, pData, nLen ); - - appendChunk( pNew ); - } - - void append( const chr *pData, long nLen ) - { - Chunk *pNew = newChunk( nLen ); - - cpy( pNew->pData, pData, nLen ); - - appendChunk( pNew ); - } - - void prepend( const chr *pData ) - { - long nLen; - for( nLen = 0; pData[nLen] != (chr)0; nLen++ ); - - Chunk *pNew = newChunk( nLen ); - cpy( pNew->pData, pData, nLen ); - - prependChunk( pNew ); - } - - void prepend( const chr *pData, long nLen ) - { - Chunk *pNew = newChunk( nLen ); - - cpy( pNew->pData, pData, nLen ); - - prependChunk( pNew ); - } - - void clear() - { - realClear(); - } - - void resize( long nNewSize ) - { - if( nLength == nNewSize ) - return; - - flatten(); - - Chunk *pNew = newChunk( nNewSize ); - long nNewLen = (nNewSize<nLength)?(nNewSize):(nLength); - cpy( pNew->pData, pFirst->pData, nNewLen ); - pNew->pData[nNewLen] = (chr)0; - aChr.deallocate( pFirst->pData, pFirst->nLength+1 ); - aChunk.deallocate( pFirst, 1 ); - pFirst = pLast = pNew; - nLength = nNewSize; - } - - long getSize() const - { - return nLength; - } - - chr *getStr() - { - if( pFirst == NULL ) - return NULL; - - flatten(); - return pFirst->pData; - } - - const chr *getStr() const - { - if( pFirst == NULL ) - return NULL; - - flatten(); - return pFirst->pData; - } - - chr *c_str() - { - if( pFirst == NULL ) - return NULL; - - flatten(); - return pFirst->pData; - } - - const chr *c_str() const - { - if( pFirst == NULL ) - return NULL; - - flatten(); - return pFirst->pData; - } - - MyType &operator +=( const chr *pData ) - { - append( pData ); - - return (*this); - } - - MyType &operator +=( const MyType &rSrc ) - { - rSrc.flatten(); - append( rSrc.pFirst->pData, rSrc.nLength ); - - return (*this); - } - - MyType &operator +=( const chr pData ) - { - chr tmp[2] = { pData, (chr)0 }; - append( tmp ); - - return (*this); - } - - MyType &operator =( const chr *pData ) - { - clear(); - append( pData ); - - return (*this); - } - - MyType &operator =( const MyType &rSrc ) - { - //if( rSrc.isFlat() ) - //{ - joinShare( rSrc ); - //} - //else - //{ - // copyFrom( rSrc ); - //} - // - - return (*this); - } - - bool operator ==( const chr *pData ) const - { - if( pFirst == NULL ) { - if( pData == NULL ) - return true; - return false; - } - - flatten(); - const chr *a = pData; - chr *b = pFirst->pData; - for( ; *a!=(chr)0; a++, b++ ) - { - if( *a != *b ) - return false; - } - - return true; - } - - bool operator ==( const MyType &pData ) const - { - if( pFirst == pData.pFirst ) - return true; - if( pFirst == NULL ) - return false; - - flatten(); - pData.flatten(); - const chr *a = pData.pFirst->pData; - chr *b = pFirst->pData; - for( ; *a!=(chr)0; a++, b++ ) - { - if( *a != *b ) - return false; - } - - return true; - } - - bool operator !=(const chr *pData ) const - { - return !(*this == pData); - } - - bool operator !=(const MyType &pData ) const - { - return !(*this == pData); - } - - chr &operator[]( long nIndex ) - { - flatten(); - - return pFirst->pData[nIndex]; - } - - const chr &operator[]( long nIndex ) const - { - flatten(); - - return pFirst->pData[nIndex]; - } - - bool isWS( long nIndex ) const - { - flatten(); - - return pFirst->pData[nIndex]==' ' || pFirst->pData[nIndex]=='\t' - || pFirst->pData[nIndex]=='\r' || pFirst->pData[nIndex]=='\n'; - } - - bool isAlpha( long nIndex ) const - { - flatten(); - - return (pFirst->pData[nIndex] >= 'a' && pFirst->pData[nIndex] <= 'z') - || (pFirst->pData[nIndex] >= 'A' && pFirst->pData[nIndex] <= 'Z'); - } - - void toLower() - { - flatten(); - unShare(); - - for( long j = 0; j < nLength; j++ ) - { - if( pFirst->pData[j] >= 'A' && pFirst->pData[j] <= 'Z' ) - pFirst->pData[j] -= 'A'-'a'; - } - } - - void toUpper() - { - flatten(); - unShare(); - - for( long j = 0; j < nLength; j++ ) - { - if( pFirst->pData[j] >= 'a' && pFirst->pData[j] <= 'z' ) - pFirst->pData[j] += 'A'-'a'; - } - } - - void serialize( class Serializer &ar ) - { - if( ar.isLoading() ) - { - clear(); - long nLen; - ar >> nLen; - - Chunk *pNew = newChunk( nLen ); - ar.read( pNew->pData, nLen*sizeof(chr) ); - appendChunk( pNew ); - } - else - { - flatten(); - - ar << nLength; - ar.write( pFirst->pData, nLength*sizeof(chr) ); - } - } - -private: - void flatten() const - { - if( isFlat() ) - return; - - if( pFirst == NULL ) - return; - - unShare(); - - Chunk *pNew = newChunk( nLength ); - chr *pos = pNew->pData; - Chunk *i = pFirst; - for(;;) - { - cpy( pos, i->pData, i->nLength ); - pos += i->nLength; - i = i->pNext; - if( i == NULL ) - break; - } - realClear(); - - pLast = pFirst = pNew; - nLength = pNew->nLength; - } - - void realClear() const - { - if( pFirst == NULL ) - return; - - if( isShared() ) - { - decRefs(); - } - else - { - Chunk *i = pFirst; - for(;;) - { - Chunk *n = i->pNext; - aChr.deallocate( i->pData, i->nLength+1 ); - aChunk.deallocate( i, 1 ); - if( n == NULL ) - break; - i = n; - } - pFirst = pLast = NULL; - nLength = 0; - } - } - - void copyFrom( const FBasicString<chr, chralloc, chunkalloc> &rSrc ) - { - if( rSrc.pFirst == NULL ) - return; - - decRefs(); - - Chunk *pNew = newChunk( rSrc.nLength ); - chr *pos = pNew->pData; - Chunk *i = rSrc.pFirst; - for(;;) - { - cpy( pos, i->pData, i->nLength ); - pos += i->nLength; - i = i->pNext; - if( i == NULL ) - break; - } - clear(); - - appendChunk( pNew ); - } - - bool isFlat() const - { - return (pFirst == pLast); - } - - bool isShared() const - { - return (pnRefs != NULL); - } - - Chunk *newChunk() const - { - Chunk *pNew = aChunk.allocate( 1 ); - pNew->pNext = NULL; - return pNew; - } - - Chunk *newChunk( long nLen ) const - { - Chunk *pNew = aChunk.allocate( 1 ); - pNew->pNext = NULL; - pNew->nLength = nLen; - pNew->pData = aChr.allocate( nLen+1 ); - pNew->pData[nLen] = (chr)0; - return pNew; - } - - void appendChunk( Chunk *pNewChunk ) - { - unShare(); - - if( pFirst == NULL ) - pLast = pFirst = pNewChunk; - else - { - pLast->pNext = pNewChunk; - pLast = pNewChunk; - } - - nLength += pNewChunk->nLength; - } - - void prependChunk( Chunk *pNewChunk ) - { - unShare(); - - if( pFirst == NULL ) - pLast = pFirst = pNewChunk; - else - { - pNewChunk->pNext = pFirst; - pFirst = pNewChunk; - } - - nLength += pNewChunk->nLength; - } - - void joinShare( MyType &rSrc ) - { - clear(); - - if( !rSrc.isFlat() ) - rSrc.flatten(); - - rSrc.initCount(); - pnRefs = rSrc.pnRefs; - (*pnRefs)++; - nLength = rSrc.nLength; - pFirst = rSrc.pFirst; - pLast = rSrc.pLast; - } - - void joinShare( const MyType &rSrc ) - { - clear(); - - rSrc.flatten(); - - if( !rSrc.isShared() ) - { - rSrc.pnRefs = new uint32_t; - (*rSrc.pnRefs) = 1; - } - pnRefs = rSrc.pnRefs; - (*pnRefs)++; - nLength = rSrc.nLength; - pFirst = rSrc.pFirst; - pLast = rSrc.pLast; - } - - /** - * This takes an object that was shared and makes a copy of the base data - * that was being shared so that this copy can be changed. This should be - * added before any call that will change this object; - */ - void unShare() const - { - if( isShared() == false ) - return; - - Chunk *pNew = newChunk( nLength ); - chr *pos = pNew->pData; - Chunk *i = pFirst; - for(;;) - { - cpy( pos, i->pData, i->nLength ); - pos += i->nLength; - i = i->pNext; - if( i == NULL ) - break; - } - decRefs(); - pLast = pFirst = pNew; - nLength = pNew->nLength; - } - - /** - * This decrements our ref count and pulls us out of the share. If the ref - * count hits zero because of this, it destroys the share. This is not - * safe to call on it's own, it's much better to call unShare. - */ - void decRefs() const - { - if( isShared() ) - { - (*pnRefs)--; - if( (*pnRefs) == 0 ) - destroyShare(); - else - { - pnRefs = NULL; - pFirst = NULL; - pLast = NULL; - nLength = 0; - } - } - } - - /** - * While the unShare function removes an instance from a share, this - * function destroys the data that was in the share, removing the share - * itself. This should only be called when the refcount for the share has - * or is about to reach zero. - */ - void destroyShare() const - { - delete pnRefs; - pnRefs = NULL; - realClear(); - } - -#ifdef VALTEST - void cpy( chr *dest, const chr *src, long count ) const - { - for( int j = 0; j < count; j++ ) - { - *dest = *src; - dest++; - src++; - } - } -#endif - - void initCount() const - { - if( !isShared() ) - { - pnRefs = new uint32_t; - (*pnRefs) = 1; - } - } - -private: - mutable long nLength; - mutable uint32_t *pnRefs; - mutable Chunk *pFirst; - mutable Chunk *pLast; - - mutable chralloc aChr; - mutable chunkalloc aChunk; -}; - -typedef FBasicString<char> FString; - -#include "hash.h" -template<> uint32_t __calcHashCode<FString>( const FString &k ); -template<> bool __cmpHashKeys<FString>( const FString &a, const FString &b ); - - -#endif diff --git a/src/old/hash.cpp b/src/old/hash.cpp deleted file mode 100644 index c52e6b1..0000000 --- a/src/old/hash.cpp +++ /dev/null @@ -1,113 +0,0 @@ -#include "hash.h" - -subExceptionDef( HashException ) - -template<> uint32_t __calcHashCode<int>( const int &k ) -{ - return k; -} - -template<> bool __cmpHashKeys<int>( const int &a, const int &b ) -{ - return a == b; -} - -template<> uint32_t __calcHashCode<unsigned int>( const unsigned int &k ) -{ - return k; -} - -template<> bool __cmpHashKeys<unsigned int>( const unsigned int &a, const unsigned int &b ) -{ - return a == b; -} - -template<> -uint32_t __calcHashCode<const char *>( const char * const &k ) -{ - if (k == NULL) - { - return 0; - } - - unsigned long int nPos = 0; - for( const char *s = k; *s; s++ ) - { - nPos = *s + (nPos << 6) + (nPos << 16) - nPos; - } - - return nPos; -} - -template<> bool __cmpHashKeys<const char *>( const char * const &a, const char * const &b ) -{ - if( a == b ) - return true; - - for(int j=0; a[j] == b[j]; j++ ) - if( a[j] == '\0' ) - return true; - - return false; -} - -template<> -uint32_t __calcHashCode<char *>( char * const &k ) -{ - if (k == NULL) - { - return 0; - } - - unsigned long int nPos = 0; - for( const char *s = k; *s; s++ ) - { - nPos = *s + (nPos << 6) + (nPos << 16) - nPos; - } - - return nPos; -} - -template<> bool __cmpHashKeys<char *>( char * const &a, char * const &b ) -{ - if( a == b ) - return true; - - for(int j=0; a[j] == b[j]; j++ ) - if( a[j] == '\0' ) - return true; - - return false; -} - -template<> uint32_t __calcHashCode<std::string>( const std::string &k ) -{ - std::string::size_type j, sz = k.size(); - const char *s = k.c_str(); - - unsigned long int nPos = 0; - for( j = 0; j < sz; j++, s++ ) - { - nPos = *s + (nPos << 6) + (nPos << 16) - nPos; - } - - return nPos; -} - -template<> bool __cmpHashKeys<std::string>( const std::string &a, const std::string &b ) -{ - return a == b; -} - -template<> uint32_t __calcHashCode<Hashable>( const Hashable &k ) -{ - return 0; - //return k.getHashCode(); -} - -template<> bool __cmpHashKeys<Hashable>( const Hashable &a, const Hashable &b ) -{ - return false; - //return a.compareForHash( b ); -} - diff --git a/src/old/hash.h b/src/old/hash.h deleted file mode 100644 index e819379..0000000 --- a/src/old/hash.h +++ /dev/null @@ -1,744 +0,0 @@ -#ifndef HASH_H -#define HASH_H - -#include <stddef.h> -#include <string.h> -#include <memory> -#include <iostream> -#include <list> -#include "exceptionbase.h" -#include "hashable.h" -#include "serializable.h" -#include "serializer.h" - -#define bitsToBytes( n ) (n/32+(n%32>0 ? 1 : 0)) - -subExceptionDecl( HashException ) - -enum eHashException -{ - excodeNotFilled -}; - -template<typename T> -uint32_t __calcHashCode( const T &k ); - -template<typename T> -bool __cmpHashKeys( const T &a, const T &b ); - -struct __calcNextTSize_fast -{ - uint32_t operator()( uint32_t nCapacity, uint32_t nFill, uint32_t nDeleted ) const - { - if( nDeleted >= nCapacity/2 ) - return nCapacity; - return nCapacity*2+1; - } -}; - -template<typename key, typename value, typename sizecalc = __calcNextTSize_fast, typename keyalloc = std::allocator<key>, typename valuealloc = std::allocator<value>, typename challoc = std::allocator<uint32_t> > -class Hash; - -template< typename key, typename _value, typename sizecalc = __calcNextTSize_fast, typename keyalloc = std::allocator<key>, typename valuealloc = std::allocator<_value>, typename challoc = std::allocator<uint32_t> > -struct HashProxy -{ - friend class Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc>; -private: - HashProxy( Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc> &h, key *k, uint32_t nPos, uint32_t hash ) : - hsh( h ), - pKey( k ), - nPos( nPos ), - hash( hash ), - bFilled( false ) - { - } - - HashProxy( Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc> &h, uint32_t nPos, _value *pValue ) : - hsh( h ), - nPos( nPos ), - pValue( pValue ), - bFilled( true ) - { - } - - Hash<key, _value, sizecalc, keyalloc, valuealloc, challoc> &hsh; - key *pKey; - uint32_t nPos; - _value *pValue; - uint32_t hash; - bool bFilled; - -public: - operator _value &() - { - if( bFilled == false ) - throw HashException( - excodeNotFilled, - "No data assosiated with that key." - ); - return *pValue; - } - - _value &value() - { - if( bFilled == false ) - throw HashException( - excodeNotFilled, - "No data assosiated with that key." - ); - return *pValue; - } - - bool isFilled() - { - return bFilled; - } - - void erase() - { - if( bFilled ) - { - hsh._erase( nPos ); - hsh.onDelete(); - } - } - - _value operator=( _value nval ) - { - if( bFilled ) - { - hsh.va.destroy( pValue ); - hsh.va.construct( pValue, nval ); - hsh.onUpdate(); - } - else - { - hsh.fill( nPos, *pKey, nval, hash ); - hsh.onInsert(); - } - - return nval; - } - - _value *operator->() - { - if( bFilled == false ) - throw HashException( - excodeNotFilled, - "No data assosiated with that key." - ); - return pValue; - } -}; - -template<typename key, typename value, typename sizecalc, typename keyalloc, typename valuealloc, typename challoc > -class Hash -{ - friend struct HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc>; -public: - Hash() : - nCapacity( 11 ), - nFilled( 0 ), - nDeleted( 0 ), - bFilled( NULL ), - bDeleted( NULL ), - aKeys( NULL ), - aValues( NULL ), - aHashCodes( NULL ) - { - nKeysSize = bitsToBytes( nCapacity ); - bFilled = ca.allocate( nKeysSize ); - bDeleted = ca.allocate( nKeysSize ); - clearBits(); - - aHashCodes = ca.allocate( nCapacity ); - aKeys = ka.allocate( nCapacity ); - aValues = va.allocate( nCapacity ); - } - - Hash( const Hash &src ) : - nCapacity( src.nCapacity ), - nFilled( 0 ), - nDeleted( 0 ), - bFilled( NULL ), - bDeleted( NULL ), - aKeys( NULL ), - aValues( NULL ), - aHashCodes( NULL ) - { - nKeysSize = bitsToBytes( nCapacity ); - bFilled = ca.allocate( nKeysSize ); - bDeleted = ca.allocate( nKeysSize ); - clearBits(); - - aHashCodes = ca.allocate( nCapacity ); - aKeys = ka.allocate( nCapacity ); - aValues = va.allocate( nCapacity ); - - for( uint32_t j = 0; j < src.nCapacity; j++ ) - { - if( src.isFilled( j ) ) - { - insert( src.aKeys[j], src.aValues[j] ); - } - } - } - - Hash &operator=( const Hash &src ) - { - for( uint32_t j = 0; j < nCapacity; j++ ) - { - if( isFilled( j ) ) - if( !isDeleted( j ) ) - { - va.destroy( &aValues[j] ); - ka.destroy( &aKeys[j] ); - } - } - va.deallocate( aValues, nCapacity ); - ka.deallocate( aKeys, nCapacity ); - ca.deallocate( bFilled, nKeysSize ); - ca.deallocate( bDeleted, nKeysSize ); - ca.deallocate( aHashCodes, nCapacity ); - - nFilled = 0; - nDeleted = 0; - nCapacity = src.nCapacity; - nKeysSize = bitsToBytes( nCapacity ); - bFilled = ca.allocate( nKeysSize ); - bDeleted = ca.allocate( nKeysSize ); - clearBits(); - - aHashCodes = ca.allocate( nCapacity ); - aKeys = ka.allocate( nCapacity ); - aValues = va.allocate( nCapacity ); - - for( uint32_t j = 0; j < src.nCapacity; j++ ) - { - if( src.isFilled( j ) ) - { - insert( src.aKeys[j], src.aValues[j] ); - } - } - - return *this; - } - - virtual ~Hash() - { - for( uint32_t j = 0; j < nCapacity; j++ ) - { - if( isFilled( j ) ) - if( !isDeleted( j ) ) - { - va.destroy( &aValues[j] ); - ka.destroy( &aKeys[j] ); - } - } - va.deallocate( aValues, nCapacity ); - ka.deallocate( aKeys, nCapacity ); - ca.deallocate( bFilled, nKeysSize ); - ca.deallocate( bDeleted, nKeysSize ); - ca.deallocate( aHashCodes, nCapacity ); - } - - uint32_t getCapacity() - { - return nCapacity; - } - - uint32_t getFill() - { - return nFilled; - } - - uint32_t size() - { - return nFilled-nDeleted; - } - - uint32_t getDeleted() - { - return nDeleted; - } - - virtual HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc> operator[]( key k ) - { - uint32_t hash = __calcHashCode( k ); - bool bFill; - uint32_t nPos = probe( hash, k, bFill ); - - if( bFill ) - { - return HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc>( *this, nPos, &aValues[nPos] ); - } - else - { - return HashProxy<key, value, sizecalc, keyalloc, valuealloc, challoc>( *this, &k, nPos, hash ); - } - } - - virtual void insert( key k, value v ) - { - uint32_t hash = __calcHashCode( k ); - bool bFill; - uint32_t nPos = probe( hash, k, bFill ); - - if( bFill ) - { - va.destroy( &aValues[nPos] ); - va.construct( &aValues[nPos], v ); - onUpdate(); - } - else - { - fill( nPos, k, v, hash ); - onInsert(); - } - } - - virtual void erase( key k ) - { - uint32_t hash = __calcHashCode( k ); - bool bFill; - uint32_t nPos = probe( hash, k, bFill ); - - if( bFill ) - { - _erase( nPos ); - onDelete(); - } - } - - struct iterator; - virtual void erase( struct iterator &i ) - { - if( this != &i.hsh ) - throw HashException("This iterator didn't come from this Hash."); - if( isFilled( i.nPos ) && !isDeleted( i.nPos ) ) - { - _erase( i.nPos ); - onDelete(); - } - } - - virtual void clear() - { - for( uint32_t j = 0; j < nCapacity; j++ ) - { - if( isFilled( j ) ) - if( !isDeleted( j ) ) - { - va.destroy( &aValues[j] ); - ka.destroy( &aKeys[j] ); - onDelete(); - } - } - - clearBits(); - } - - virtual value &get( key k ) - { - uint32_t hash = __calcHashCode( k ); - bool bFill; - uint32_t nPos = probe( hash, k, bFill ); - - if( bFill ) - { - return aValues[nPos]; - } - else - { - throw HashException( - excodeNotFilled, - "No data assosiated with that key." - ); - } - } - - virtual bool has( key k ) - { - bool bFill; - probe( __calcHashCode( k ), k, bFill, false ); - - return bFill; - } - - typedef struct iterator - { - friend class Hash<key, value, sizecalc, keyalloc, valuealloc, challoc>; - private: - iterator( Hash<key, value, sizecalc, keyalloc, valuealloc, challoc> &hsh ) : - hsh( hsh ), - nPos( 0 ), - bFinished( false ) - { - nPos = hsh.getFirstPos( bFinished ); - } - - iterator( Hash<key, value, sizecalc, keyalloc, valuealloc, challoc> &hsh, bool bDone ) : - hsh( hsh ), - nPos( 0 ), - bFinished( bDone ) - { - } - - Hash<key, value, sizecalc, keyalloc, valuealloc, challoc> &hsh; - uint32_t nPos; - bool bFinished; - - public: - iterator operator++( int ) - { - if( bFinished == false ) - nPos = hsh.getNextPos( nPos, bFinished ); - - return *this; - } - - iterator operator++() - { - if( bFinished == false ) - nPos = hsh.getNextPos( nPos, bFinished ); - - return *this; - } - - bool operator==( const iterator &oth ) - { - if( bFinished != oth.bFinished ) - return false; - if( bFinished == true ) - { - return true; - } - else - { - if( oth.nPos == nPos ) - return true; - return false; - } - } - - bool operator!=( const iterator &oth ) - { - return !(*this == oth ); - } - - iterator operator=( const iterator &oth ) - { - if( &hsh != &oth.hsh ) - throw HashException( - "Cannot mix iterators from different hash objects."); - nPos = oth.nPos; - bFinished = oth.bFinished; - } - - std::pair<key,value> operator *() - { - return hsh.getAtPos( nPos ); - } - - key &getKey() - { - return hsh.getKeyAtPos( nPos ); - } - - value &getValue() - { - return hsh.getValueAtPos( nPos ); - } - }; - - iterator begin() - { - return iterator( *this ); - } - - iterator end() - { - return iterator( *this, true ); - } - - std::list<key> getKeys() - { - std::list<key> lKeys; - - for( uint32_t j = 0; j < nCapacity; j++ ) - { - if( isFilled( j ) ) - { - if( !isDeleted( j ) ) - { - lKeys.push_back( aKeys[j] ); - } - } - } - - return lKeys; - } - -protected: - virtual void onInsert() {} - virtual void onUpdate() {} - virtual void onDelete() {} - virtual void onReHash() {} - - virtual void clearBits() - { - for( uint32_t j = 0; j < nKeysSize; j++ ) - { - bFilled[j] = bDeleted[j] = 0; - } - } - - virtual void fill( uint32_t loc, key &k, value &v, uint32_t hash ) - { - bFilled[loc/32] |= (1<<(loc%32)); - va.construct( &aValues[loc], v ); - ka.construct( &aKeys[loc], k ); - aHashCodes[loc] = hash; - nFilled++; - //printf("Filled: %d, Deleted: %d, Capacity: %d\n", - // nFilled, nDeleted, nCapacity ); - } - - virtual void _erase( uint32_t loc ) - { - bDeleted[loc/32] |= (1<<(loc%32)); - va.destroy( &aValues[loc] ); - ka.destroy( &aKeys[loc] ); - nDeleted++; - //printf("Filled: %d, Deleted: %d, Capacity: %d\n", - // nFilled, nDeleted, nCapacity ); - } - - virtual std::pair<key,value> getAtPos( uint32_t nPos ) - { - return std::pair<key,value>(aKeys[nPos],aValues[nPos]); - } - - virtual key &getKeyAtPos( uint32_t nPos ) - { - return aKeys[nPos]; - } - - virtual value &getValueAtPos( uint32_t nPos ) - { - return aValues[nPos]; - } - - virtual uint32_t getFirstPos( bool &bFinished ) - { - for( uint32_t j = 0; j < nCapacity; j++ ) - { - if( isFilled( j ) ) - if( !isDeleted( j ) ) - return j; - } - - bFinished = true; - return 0; - } - - virtual uint32_t getNextPos( uint32_t nPos, bool &bFinished ) - { - for( uint32_t j = nPos+1; j < nCapacity; j++ ) - { - if( isFilled( j ) ) - if( !isDeleted( j ) ) - return j; - } - - bFinished = true; - return 0; - } - - uint32_t probe( uint32_t hash, key k, bool &bFill, bool rehash=true ) - { - uint32_t nCur = hash%nCapacity; - - // First we scan to see if the key is already there, abort if we - // run out of probing room, or we find a non-filled entry - for( int8_t j = 0; - isFilled( nCur ) && j < 32; - nCur = (nCur + (1<<j))%nCapacity, j++ - ) - { - // Is this the same hash code we were looking for? - if( hash == aHashCodes[nCur] ) - { - // Skip over deleted entries. Deleted entries are also filled, - // so we only have to do this check here. - if( isDeleted( nCur ) ) - continue; - - // Is it really the same key? (for safety) - if( __cmpHashKeys( aKeys[nCur], k ) == true ) - { - bFill = true; - return nCur; - } - } - } - - // This is our insurance, if the table is full, then go ahead and - // rehash, then try again. - if( isFilled( nCur ) && rehash == true ) - { - reHash( szCalc(getCapacity(), getFill(), getDeleted()) ); - - // This is potentially dangerous, and could cause an infinite loop. - // Be careful writing probe, eh? - return probe( hash, k, bFill ); - } - - bFill = false; - return nCur; - } - - void reHash( uint32_t nNewSize ) - { - //printf("---REHASH---"); - //printf("Filled: %d, Deleted: %d, Capacity: %d\n", - // nFilled, nDeleted, nCapacity ); - - // Save all the old data - uint32_t nOldCapacity = nCapacity; - uint32_t *bOldFilled = bFilled; - uint32_t *aOldHashCodes = aHashCodes; - uint32_t nOldKeysSize = nKeysSize; - uint32_t *bOldDeleted = bDeleted; - value *aOldValues = aValues; - key *aOldKeys = aKeys; - - // Calculate new sizes - nCapacity = nNewSize; - nKeysSize = bitsToBytes( nCapacity ); - - // Allocate new memory + prep - bFilled = ca.allocate( nKeysSize ); - bDeleted = ca.allocate( nKeysSize ); - clearBits(); - - aHashCodes = ca.allocate( nCapacity ); - aKeys = ka.allocate( nCapacity ); - aValues = va.allocate( nCapacity ); - - nDeleted = nFilled = 0; - - // Re-insert all of the old data (except deleted items) - for( uint32_t j = 0; j < nOldCapacity; j++ ) - { - if( (bOldFilled[j/32]&(1<<(j%32)))!=0 && - (bOldDeleted[j/32]&(1<<(j%32)))==0 ) - { - insert( aOldKeys[j], aOldValues[j] ); - } - } - - // Delete all of the old data - for( uint32_t j = 0; j < nOldCapacity; j++ ) - { - if( (bOldFilled[j/32]&(1<<(j%32)))!=0 ) - { - va.destroy( &aOldValues[j] ); - ka.destroy( &aOldKeys[j] ); - } - } - va.deallocate( aOldValues, nOldCapacity ); - ka.deallocate( aOldKeys, nOldCapacity ); - ca.deallocate( bOldFilled, nOldKeysSize ); - ca.deallocate( bOldDeleted, nOldKeysSize ); - ca.deallocate( aOldHashCodes, nOldCapacity ); - } - - virtual bool isFilled( uint32_t loc ) const - { - return (bFilled[loc/32]&(1<<(loc%32)))!=0; - } - - virtual bool isDeleted( uint32_t loc ) - { - return (bDeleted[loc/32]&(1<<(loc%32)))!=0; - } - -protected: - uint32_t nCapacity; - uint32_t nFilled; - uint32_t nDeleted; - uint32_t *bFilled; - uint32_t *bDeleted; - uint32_t nKeysSize; - key *aKeys; - value *aValues; - uint32_t *aHashCodes; - valuealloc va; - keyalloc ka; - challoc ca; - sizecalc szCalc; -}; - -template<> uint32_t __calcHashCode<int>( const int &k ); -template<> bool __cmpHashKeys<int>( const int &a, const int &b ); - -template<> uint32_t __calcHashCode<unsigned int>( const unsigned int &k ); -template<> bool __cmpHashKeys<unsigned int>( const unsigned int &a, const unsigned int &b ); - -template<> uint32_t __calcHashCode<const char *>( const char * const &k ); -template<> bool __cmpHashKeys<const char *>( const char * const &a, const char * const &b ); - -template<> uint32_t __calcHashCode<char *>( char * const &k ); -template<> bool __cmpHashKeys<char *>( char * const &a, char * const &b ); - -template<> uint32_t __calcHashCode<std::string>( const std::string &k ); -template<> bool __cmpHashKeys<std::string>( const std::string &a, const std::string &b ); - -template<> uint32_t __calcHashCode<Hashable>( const Hashable &k ); -template<> bool __cmpHashKeys<Hashable>( const Hashable &a, const Hashable &b ); - -template<typename key, typename value> -Serializer &operator<<( Serializer &ar, Hash<key,value> &h ) -{ - ar << h.size(); - for( typename Hash<key,value>::iterator i = h.begin(); i != h.end(); i++ ) - { - std::pair<key,value> p = *i; - ar << p.first << p.second; - } - - return ar; -} - -template<typename key, typename value> -Serializer &operator>>( Serializer &ar, Hash<key,value> &h ) -{ - h.clear(); - uint32_t nSize; - ar >> nSize; - - for( uint32_t j = 0; j < nSize; j++ ) - { - key k; value v; - ar >> k >> v; - h.insert( k, v ); - } - - return ar; -} - -template<typename key, typename value> -Serializer &operator&&( Serializer &ar, Hash<key,value> &h ) -{ - if( ar.isLoading() ) - { - return ar >> h; - } - else - { - return ar << h; - } -} - -#endif diff --git a/src/old/hashable.cpp b/src/old/hashable.cpp deleted file mode 100644 index 8565956..0000000 --- a/src/old/hashable.cpp +++ /dev/null @@ -1 +0,0 @@ -#include "hashable.h" diff --git a/src/old/hashable.h b/src/old/hashable.h deleted file mode 100644 index 98643d5..0000000 --- a/src/old/hashable.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef HASHABLE_H -#define HASHABLE_H - -class Hashable -{ -public: - virtual ~Hashable() {}; - virtual unsigned long int getHashCode() = 0; - virtual bool compareForHash( Hashable &other ) = 0; -}; - -#endif diff --git a/src/old/serializable.cpp b/src/old/serializable.cpp deleted file mode 100644 index fd50943..0000000 --- a/src/old/serializable.cpp +++ /dev/null @@ -1,8 +0,0 @@ -#include "serializable.h" - -Serializable::Serializable() -{ -} -Serializable::~Serializable() -{ -} diff --git a/src/old/serializable.h b/src/old/serializable.h deleted file mode 100644 index 06def29..0000000 --- a/src/old/serializable.h +++ /dev/null @@ -1,34 +0,0 @@ -#ifndef SERIALIZER_H -#define SERIALIZER_H - -//#include "serializer.h" - -/** - * The base class for any class you want to serialize. Simply include this as - * a base class, implement the purely virtual serialize function and you've got - * an easily serializable class. - */ -class Serializable -{ -public: - /** - * Does nothing, here for completeness. - */ - Serializable(); - - /** - * Here to ensure the deconstructor is virtual. - */ - virtual ~Serializable(); - - /** - * This is the main workhorse of the serialization system, just override and - * you've got a serializable class. A reference to the Serializer archive - * used is passed in as your only parameter, query it to discover if you are - * loading or saving. - * @param ar A reference to the Serializer object to use. - */ - virtual void serialize( class Serializer &ar )=0; -}; - -#endif diff --git a/src/old/serializer.cpp b/src/old/serializer.cpp deleted file mode 100644 index 636224e..0000000 --- a/src/old/serializer.cpp +++ /dev/null @@ -1,338 +0,0 @@ -#include "serializer.h" -#include "serializable.h" -#include <list> - -Serializer::Serializer(bool bLoading): - bLoading(bLoading) -{ -} -Serializer::~Serializer() -{ -} - -bool Serializer::isLoading() -{ - return bLoading; -} -Serializer &Serializer::operator<<(bool p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(int8_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(int16_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(int32_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(int64_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(uint8_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(uint16_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(uint32_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(uint64_t p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(long p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(float p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(double p) -{ - write( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator<<(long double p) -{ - write( &p, sizeof(p) ); - return *this; -} - -Serializer &Serializer::operator>>(bool &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(int8_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(int16_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(int32_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(int64_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(uint8_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(uint16_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(uint32_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(uint64_t &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(long &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(float &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(double &p) -{ - read( &p, sizeof(p) ); - return *this; -} -Serializer &Serializer::operator>>(long double &p) -{ - read( &p, sizeof(p) ); - return *this; -} - -Serializer &Serializer::operator&&(bool &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(int8_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(int16_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(int32_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(int64_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(uint8_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(uint16_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(uint32_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(uint64_t &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(float &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(double &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - -Serializer &Serializer::operator&&(long double &p) -{ - if (bLoading) - { - return *this >> p; - } - else - { - return *this << p; - } -} - - -Serializer &operator<<(Serializer &s, Serializable &p) -{ - p.serialize( s ); - return s; -} - -Serializer &operator>>(Serializer &s, Serializable &p) -{ - p.serialize( s ); - return s; -} - -Serializer &operator&&(Serializer &s, Serializable &p) -{ - if (s.isLoading()) - { - return s >> p; - } - else - { - return s << p; - } -} - -Serializer &operator<<( Serializer &ar, std::string &s ) -{ - ar << (uint32_t)s.length(); - ar.write( s.c_str(), s.length() ); - - return ar; -} - -Serializer &operator>>( Serializer &ar, std::string &s ) -{ - uint32_t l; - ar >> l; - char *tmp = new char[l+1]; - tmp[l] = '\0'; - ar.read( tmp, l ); - s = tmp; - delete[] tmp; - - return ar; -} - diff --git a/src/old/serializer.h b/src/old/serializer.h deleted file mode 100644 index 3af489c..0000000 --- a/src/old/serializer.h +++ /dev/null @@ -1,80 +0,0 @@ -#ifndef SERIALIZABLE_H -#define SERIALIZABLE_H - -#include <stdint.h> -#include <string> -#include <list> -//#include "serializable.h" - -class Serializer -{ -private: - bool bLoading; -public: - bool isLoading(); - - enum - { - load = true, - save = false - }; - - Serializer(bool bLoading); - virtual ~Serializer(); - virtual void close()=0; - - virtual void write(const void *, int32_t)=0; - virtual void read(void *, int32_t)=0; - - virtual Serializer &operator<<(bool); - virtual Serializer &operator<<(int8_t); - virtual Serializer &operator<<(int16_t); - virtual Serializer &operator<<(int32_t); - virtual Serializer &operator<<(int64_t); - virtual Serializer &operator<<(uint8_t); - virtual Serializer &operator<<(uint16_t); - virtual Serializer &operator<<(uint32_t); - virtual Serializer &operator<<(uint64_t); - virtual Serializer &operator<<(long); - virtual Serializer &operator<<(float); - virtual Serializer &operator<<(double); - virtual Serializer &operator<<(long double); - - virtual Serializer &operator>>(bool &); - virtual Serializer &operator>>(int8_t &); - virtual Serializer &operator>>(int16_t &); - virtual Serializer &operator>>(int32_t &); - virtual Serializer &operator>>(int64_t &); - virtual Serializer &operator>>(uint8_t &); - virtual Serializer &operator>>(uint16_t &); - virtual Serializer &operator>>(uint32_t &); - virtual Serializer &operator>>(uint64_t &); - virtual Serializer &operator>>(long &); - virtual Serializer &operator>>(float &); - virtual Serializer &operator>>(double &); - virtual Serializer &operator>>(long double &); - - virtual Serializer &operator&&(bool &); - virtual Serializer &operator&&(int8_t &); - virtual Serializer &operator&&(int16_t &); - virtual Serializer &operator&&(int32_t &); - virtual Serializer &operator&&(int64_t &); - virtual Serializer &operator&&(uint8_t &); - virtual Serializer &operator&&(uint16_t &); - virtual Serializer &operator&&(uint32_t &); - virtual Serializer &operator&&(uint64_t &); - virtual Serializer &operator&&(float &); - virtual Serializer &operator&&(double &); - virtual Serializer &operator&&(long double &); - - //virtual Serializer &operator&(Serializable &); -}; - -Serializer &operator<<(Serializer &, class Serializable &); -Serializer &operator>>(Serializer &, class Serializable &); -Serializer &operator&&(Serializer &s, class Serializable &p); - -Serializer &operator<<(Serializer &, std::string &); -Serializer &operator>>(Serializer &, std::string &); - -#endif diff --git a/src/old/stream.cpp b/src/old/stream.cpp deleted file mode 100644 index 856a58d..0000000 --- a/src/old/stream.cpp +++ /dev/null @@ -1,10 +0,0 @@ -#include "stream.h" - -Stream::Stream() -{ -} - -Stream::~Stream() -{ -} - diff --git a/src/old/stream.h b/src/old/stream.h deleted file mode 100644 index e086e28..0000000 --- a/src/old/stream.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef STREAM_H -#define STREAM_H - -#include <stdint.h> -#include <stdio.h> - -class Stream -{ -public: - Stream(); - virtual ~Stream(); - - virtual void close() = 0; - virtual size_t read( char *pBuf, size_t nBytes ) = 0; - virtual size_t write( const char *pBuf, size_t nBytes ) = 0; - - virtual long tell() = 0; - virtual void seek( long offset ) = 0; - virtual void setPos( long pos ) = 0; - virtual void setPosEnd( long pos ) = 0; - virtual bool isEOS() = 0; - -private: - -}; - -#endif diff --git a/src/stream.cpp b/src/stream.cpp new file mode 100644 index 0000000..267a7d1 --- /dev/null +++ b/src/stream.cpp @@ -0,0 +1,10 @@ +#include "stream.h" + +Bu::Stream::Stream() +{ +} + +Bu::Stream::~Stream() +{ +} + diff --git a/src/stream.h b/src/stream.h new file mode 100644 index 0000000..274f4fd --- /dev/null +++ b/src/stream.h @@ -0,0 +1,34 @@ +#ifndef STREAM_H +#define STREAM_H + +#include <stdint.h> +#include <stdio.h> + +namespace Bu +{ + class Stream + { + public: + Stream(); + virtual ~Stream(); + + virtual void close() = 0; + virtual size_t read( char *pBuf, size_t nBytes ) = 0; + virtual size_t write( const char *pBuf, size_t nBytes ) = 0; + + virtual long tell() = 0; + virtual void seek( long offset ) = 0; + virtual void setPos( long pos ) = 0; + virtual void setPosEnd( long pos ) = 0; + virtual bool isEOS() = 0; + + virtual bool canRead() = 0; + virtual bool canWrite() = 0; + virtual bool canSeek() = 0; + + private: + + }; +} + +#endif diff --git a/src/tests/archive.cpp b/src/tests/archive.cpp new file mode 100644 index 0000000..fb0d97c --- /dev/null +++ b/src/tests/archive.cpp @@ -0,0 +1,7 @@ +#include "archive.h" + +int main() +{ + //Archive +} + diff --git a/tests/comments.xml b/tests/comments.xml deleted file mode 100644 index df05b3b..0000000 --- a/tests/comments.xml +++ /dev/null @@ -1,12 +0,0 @@ -<?xml version="1.0"?> -<test> - <!----><stuff/><guy> - <!-- euntaho esutnaho .rucaho. u - ao.rcuh aor uasrcoh - rohaor - c.uha - orchu - aroch.ua. - -->Aaaugh! - </guy> -</test> diff --git a/tests/guy.cpp b/tests/guy.cpp deleted file mode 100644 index 6510771..0000000 --- a/tests/guy.cpp +++ /dev/null @@ -1,22 +0,0 @@ -#include "stdio.h" -#include "plugin.h" -#include "plugger.h" - -class Guy : public Plugin -{ -public: - Guy() - { - printf("I'm guy!\n"); - } - - virtual ~Guy() - { - printf("Guy is dead...\n"); - } - -private: -}; - -PluginInterface( Guy, Plugin, "Mike", 0, 1 ) - diff --git a/tests/makeplugin.sh b/tests/makeplugin.sh deleted file mode 100755 index 086fefd..0000000 --- a/tests/makeplugin.sh +++ /dev/null @@ -1,3 +0,0 @@ -#!/bin/sh - -g++ -fPIC -shared -Wl,-soname,guy.so -o guy.so -I../src -I../src/test/plugin guy.cpp ../src/test/plugin/plugin.cpp -- cgit v1.2.3 From c884da672645231b5ec47706c886381dab1b391a Mon Sep 17 00:00:00 2001 From: Mike Buland <eichlan@xagasoft.com> Date: Tue, 3 Apr 2007 05:09:12 +0000 Subject: The file stream is imported and works, as does our first test, and the new tweaks to archive. The && operator is now a template function, and as such requires no special handling. It could be worth it to check this out for other types, yet dangerous, since it would let you archive anything, even a class, without writing the proper functions for it...we shall see what happens... --- src/archive.cpp | 27 ++++++++++++++-- src/archive.h | 12 ++++--- src/old/sfile.cpp | 74 ------------------------------------------ src/old/sfile.h | 29 ----------------- src/sfile.cpp | 90 +++++++++++++++++++++++++++++++++++++++++++++++++++ src/sfile.h | 36 +++++++++++++++++++++ src/tests/archive.cpp | 11 ++++++- 7 files changed, 169 insertions(+), 110 deletions(-) delete mode 100644 src/old/sfile.cpp delete mode 100644 src/old/sfile.h create mode 100644 src/sfile.cpp create mode 100644 src/sfile.h (limited to 'src/tests') diff --git a/src/archive.cpp b/src/archive.cpp index 5f5145c..be06c0e 100644 --- a/src/archive.cpp +++ b/src/archive.cpp @@ -1,13 +1,36 @@ #include "archive.h" -Bu::Archive::Archive(bool bLoading): - bLoading(bLoading) +Bu::Archive::Archive( Stream &rStream, bool bLoading ) : + bLoading( bLoading ), + rStream( rStream ) { } + Bu::Archive::~Archive() { } +void Bu::Archive::write( const void *pData, int32_t nSize ) +{ + if( nSize == 0 || pData == NULL ) + return; + + rStream.write( (const char *)pData, nSize ); +} + +void Bu::Archive::read( void *pData, int32_t nSize ) +{ + if( nSize == 0 || pData == NULL ) + return; + + rStream.read( (char *)pData, nSize ); +} + +void Bu::Archive::close() +{ + rStream.close(); +} + bool Bu::Archive::isLoading() { return bLoading; diff --git a/src/archive.h b/src/archive.h index 7de9220..26e430b 100644 --- a/src/archive.h +++ b/src/archive.h @@ -4,6 +4,7 @@ #include <stdint.h> #include <string> #include "archable.h" +#include "stream.h" namespace Bu { @@ -20,12 +21,12 @@ namespace Bu save = false }; - Archive( bool bLoading ); + Archive( Stream &rStream, bool bLoading ); virtual ~Archive(); - virtual void close()=0; + virtual void close(); - virtual void write(const void *, int32_t)=0; - virtual void read(void *, int32_t)=0; + virtual void write(const void *, int32_t); + virtual void read(void *, int32_t); virtual Archive &operator<<(bool); virtual Archive &operator<<(int8_t); @@ -67,6 +68,9 @@ namespace Bu virtual Archive &operator&&(float &); virtual Archive &operator&&(double &); virtual Archive &operator&&(long double &); + + private: + Stream &rStream; }; Archive &operator<<(Archive &, class Bu::Archable &); diff --git a/src/old/sfile.cpp b/src/old/sfile.cpp deleted file mode 100644 index f1de03c..0000000 --- a/src/old/sfile.cpp +++ /dev/null @@ -1,74 +0,0 @@ -#include "sfile.h" -#include "exceptions.h" - -SFile::SFile( const char *sName, const char *sFlags ) -{ - fh = fopen( sName, sFlags ); -} - -SFile::~SFile() -{ -} - -void SFile::close() -{ - if( fh ) - { - fclose( fh ); - fh = NULL; - } -} - -size_t SFile::read( char *pBuf, size_t nBytes ) -{ - if( !fh ) - throw FileException("File not open."); - - return fread( pBuf, 1, nBytes, fh ); -} - -size_t SFile::write( const char *pBuf, size_t nBytes ) -{ - if( !fh ) - throw FileException("File not open."); - - return fwrite( pBuf, 1, nBytes, fh ); -} - -long SFile::tell() -{ - if( !fh ) - throw FileException("File not open."); - - return ftell( fh ); -} - -void SFile::seek( long offset ) -{ - if( !fh ) - throw FileException("File not open."); - - fseek( fh, offset, SEEK_CUR ); -} - -void SFile::setPos( long pos ) -{ - if( !fh ) - throw FileException("File not open."); - - fseek( fh, pos, SEEK_SET ); -} - -void SFile::setPosEnd( long pos ) -{ - if( !fh ) - throw FileException("File not open."); - - fseek( fh, pos, SEEK_END ); -} - -bool SFile::isEOS() -{ - return feof( fh ); -} - diff --git a/src/old/sfile.h b/src/old/sfile.h deleted file mode 100644 index b51e5bc..0000000 --- a/src/old/sfile.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef SFILE_H -#define SFILE_H - -#include <stdint.h> - -#include "stream.h" - -class SFile : public Stream -{ -public: - SFile( const char *sName, const char *sFlags ); - virtual ~SFile(); - - virtual void close(); - virtual size_t read( char *pBuf, size_t nBytes ); - virtual size_t write( const char *pBuf, size_t nBytes ); - - virtual long tell(); - virtual void seek( long offset ); - virtual void setPos( long pos ); - virtual void setPosEnd( long pos ); - virtual bool isEOS(); - -private: - FILE *fh; - -}; - -#endif diff --git a/src/sfile.cpp b/src/sfile.cpp new file mode 100644 index 0000000..d7c5c83 --- /dev/null +++ b/src/sfile.cpp @@ -0,0 +1,90 @@ +#include "sfile.h" +#include "exceptions.h" + +Bu::SFile::SFile( const char *sName, const char *sFlags ) +{ + fh = fopen( sName, sFlags ); +} + +Bu::SFile::~SFile() +{ + close(); +} + +void Bu::SFile::close() +{ + if( fh ) + { + fclose( fh ); + fh = NULL; + } +} + +size_t Bu::SFile::read( char *pBuf, size_t nBytes ) +{ + if( !fh ) + throw FileException("File not open."); + + return fread( pBuf, 1, nBytes, fh ); +} + +size_t Bu::SFile::write( const char *pBuf, size_t nBytes ) +{ + if( !fh ) + throw FileException("File not open."); + + return fwrite( pBuf, 1, nBytes, fh ); +} + +long Bu::SFile::tell() +{ + if( !fh ) + throw FileException("File not open."); + + return ftell( fh ); +} + +void Bu::SFile::seek( long offset ) +{ + if( !fh ) + throw FileException("File not open."); + + fseek( fh, offset, SEEK_CUR ); +} + +void Bu::SFile::setPos( long pos ) +{ + if( !fh ) + throw FileException("File not open."); + + fseek( fh, pos, SEEK_SET ); +} + +void Bu::SFile::setPosEnd( long pos ) +{ + if( !fh ) + throw FileException("File not open."); + + fseek( fh, pos, SEEK_END ); +} + +bool Bu::SFile::isEOS() +{ + return feof( fh ); +} + +bool Bu::SFile::canRead() +{ + return true; +} + +bool Bu::SFile::canWrite() +{ + return true; +} + +bool Bu::SFile::canSeek() +{ + return true; +} + diff --git a/src/sfile.h b/src/sfile.h new file mode 100644 index 0000000..304f6b7 --- /dev/null +++ b/src/sfile.h @@ -0,0 +1,36 @@ +#ifndef SFILE_H +#define SFILE_H + +#include <stdint.h> + +#include "stream.h" + +namespace Bu +{ + class SFile : public Bu::Stream + { + public: + SFile( const char *sName, const char *sFlags ); + virtual ~SFile(); + + virtual void close(); + virtual size_t read( char *pBuf, size_t nBytes ); + virtual size_t write( const char *pBuf, size_t nBytes ); + + virtual long tell(); + virtual void seek( long offset ); + virtual void setPos( long pos ); + virtual void setPosEnd( long pos ); + virtual bool isEOS(); + + virtual bool canRead(); + virtual bool canWrite(); + virtual bool canSeek(); + + private: + FILE *fh; + + }; +} + +#endif diff --git a/src/tests/archive.cpp b/src/tests/archive.cpp index fb0d97c..5b7e285 100644 --- a/src/tests/archive.cpp +++ b/src/tests/archive.cpp @@ -1,7 +1,16 @@ #include "archive.h" +#include "sfile.h" + +using namespace Bu; int main() { - //Archive + SFile f("test.dat", "wb"); + Archive ar( f, Archive::save ); + + std::string s("Hello there"); + ar << s; + + return 0; } -- cgit v1.2.3 From 070374dde0f53bff26078550997f7682e84412e5 Mon Sep 17 00:00:00 2001 From: Mike Buland <eichlan@xagasoft.com> Date: Tue, 10 Apr 2007 20:16:19 +0000 Subject: I did it, the streams don't start with an S now. --- src/file.cpp | 100 +++++++++++++++++++++++++++++++++++++++++++++++ src/file.h | 36 +++++++++++++++++ src/sfile.cpp | 100 ----------------------------------------------- src/sfile.h | 36 ----------------- src/socket.cpp | 10 +++++ src/socket.h | 24 ++++++++++++ src/ssocket.cpp | 9 ----- src/ssocket.h | 24 ------------ src/tests/archive.cpp | 4 +- src/unit/file.cpp | 105 ++++++++++++++++++++++++++++++++++++++++++++++++++ src/unit/sfile.cpp | 105 -------------------------------------------------- src/unitsuite.h | 35 +++++++++++++++++ 12 files changed, 312 insertions(+), 276 deletions(-) create mode 100644 src/file.cpp create mode 100644 src/file.h delete mode 100644 src/sfile.cpp delete mode 100644 src/sfile.h create mode 100644 src/socket.cpp create mode 100644 src/socket.h delete mode 100644 src/ssocket.cpp delete mode 100644 src/ssocket.h create mode 100644 src/unit/file.cpp delete mode 100644 src/unit/sfile.cpp (limited to 'src/tests') diff --git a/src/file.cpp b/src/file.cpp new file mode 100644 index 0000000..5de5f6c --- /dev/null +++ b/src/file.cpp @@ -0,0 +1,100 @@ +#include "file.h" +#include "exceptions.h" +#include <errno.h> + +Bu::File::File( const char *sName, const char *sFlags ) +{ + fh = fopen( sName, sFlags ); + if( fh == NULL ) + { + throw Bu::FileException( errno, strerror(errno) ); + } +} + +Bu::File::~File() +{ + close(); +} + +void Bu::File::close() +{ + if( fh ) + { + fclose( fh ); + fh = NULL; + } +} + +size_t Bu::File::read( void *pBuf, size_t nBytes ) +{ + if( !fh ) + throw FileException("File not open."); + + int nAmnt = fread( pBuf, 1, nBytes, fh ); + + if( nAmnt == 0 ) + throw FileException("End of file."); + + return nAmnt; +} + +size_t Bu::File::write( const void *pBuf, size_t nBytes ) +{ + if( !fh ) + throw FileException("File not open."); + + return fwrite( pBuf, 1, nBytes, fh ); +} + +long Bu::File::tell() +{ + if( !fh ) + throw FileException("File not open."); + + return ftell( fh ); +} + +void Bu::File::seek( long offset ) +{ + if( !fh ) + throw FileException("File not open."); + + fseek( fh, offset, SEEK_CUR ); +} + +void Bu::File::setPos( long pos ) +{ + if( !fh ) + throw FileException("File not open."); + + fseek( fh, pos, SEEK_SET ); +} + +void Bu::File::setPosEnd( long pos ) +{ + if( !fh ) + throw FileException("File not open."); + + fseek( fh, pos, SEEK_END ); +} + +bool Bu::File::isEOS() +{ + return feof( fh ); +} + +bool Bu::File::canRead() +{ + return true; +} + +bool Bu::File::canWrite() +{ + return true; +} + +bool Bu::File::canSeek() +{ + return true; +} + diff --git a/src/file.h b/src/file.h new file mode 100644 index 0000000..bbc620c --- /dev/null +++ b/src/file.h @@ -0,0 +1,36 @@ +#ifndef FILE_H +#define FILE_H + +#include <stdint.h> + +#include "stream.h" + +namespace Bu +{ + class File : public Bu::Stream + { + public: + File( const char *sName, const char *sFlags ); + virtual ~File(); + + virtual void close(); + virtual size_t read( void *pBuf, size_t nBytes ); + virtual size_t write( const void *pBuf, size_t nBytes ); + + virtual long tell(); + virtual void seek( long offset ); + virtual void setPos( long pos ); + virtual void setPosEnd( long pos ); + virtual bool isEOS(); + + virtual bool canRead(); + virtual bool canWrite(); + virtual bool canSeek(); + + private: + FILE *fh; + + }; +} + +#endif diff --git a/src/sfile.cpp b/src/sfile.cpp deleted file mode 100644 index 529d8cd..0000000 --- a/src/sfile.cpp +++ /dev/null @@ -1,100 +0,0 @@ -#include "sfile.h" -#include "exceptions.h" -#include <errno.h> - -Bu::SFile::SFile( const char *sName, const char *sFlags ) -{ - fh = fopen( sName, sFlags ); - if( fh == NULL ) - { - throw Bu::FileException( errno, strerror(errno) ); - } -} - -Bu::SFile::~SFile() -{ - close(); -} - -void Bu::SFile::close() -{ - if( fh ) - { - fclose( fh ); - fh = NULL; - } -} - -size_t Bu::SFile::read( void *pBuf, size_t nBytes ) -{ - if( !fh ) - throw FileException("File not open."); - - int nAmnt = fread( pBuf, 1, nBytes, fh ); - - if( nAmnt == 0 ) - throw FileException("End of file."); - - return nAmnt; -} - -size_t Bu::SFile::write( const void *pBuf, size_t nBytes ) -{ - if( !fh ) - throw FileException("File not open."); - - return fwrite( pBuf, 1, nBytes, fh ); -} - -long Bu::SFile::tell() -{ - if( !fh ) - throw FileException("File not open."); - - return ftell( fh ); -} - -void Bu::SFile::seek( long offset ) -{ - if( !fh ) - throw FileException("File not open."); - - fseek( fh, offset, SEEK_CUR ); -} - -void Bu::SFile::setPos( long pos ) -{ - if( !fh ) - throw FileException("File not open."); - - fseek( fh, pos, SEEK_SET ); -} - -void Bu::SFile::setPosEnd( long pos ) -{ - if( !fh ) - throw FileException("File not open."); - - fseek( fh, pos, SEEK_END ); -} - -bool Bu::SFile::isEOS() -{ - return feof( fh ); -} - -bool Bu::SFile::canRead() -{ - return true; -} - -bool Bu::SFile::canWrite() -{ - return true; -} - -bool Bu::SFile::canSeek() -{ - return true; -} - diff --git a/src/sfile.h b/src/sfile.h deleted file mode 100644 index f63b812..0000000 --- a/src/sfile.h +++ /dev/null @@ -1,36 +0,0 @@ -#ifndef SFILE_H -#define SFILE_H - -#include <stdint.h> - -#include "stream.h" - -namespace Bu -{ - class SFile : public Bu::Stream - { - public: - SFile( const char *sName, const char *sFlags ); - virtual ~SFile(); - - virtual void close(); - virtual size_t read( void *pBuf, size_t nBytes ); - virtual size_t write( const void *pBuf, size_t nBytes ); - - virtual long tell(); - virtual void seek( long offset ); - virtual void setPos( long pos ); - virtual void setPosEnd( long pos ); - virtual bool isEOS(); - - virtual bool canRead(); - virtual bool canWrite(); - virtual bool canSeek(); - - private: - FILE *fh; - - }; -} - -#endif diff --git a/src/socket.cpp b/src/socket.cpp new file mode 100644 index 0000000..c5c592b --- /dev/null +++ b/src/socket.cpp @@ -0,0 +1,10 @@ +#include "socket.h" + +Bu::Socket::Socket() +{ +} + +Bu::Socket::~Socket() +{ +} + diff --git a/src/socket.h b/src/socket.h new file mode 100644 index 0000000..8ccde71 --- /dev/null +++ b/src/socket.h @@ -0,0 +1,24 @@ +#ifndef SOCKET_H +#define SOCKET_H + +#include <stdint.h> + +#include "stream.h" + +namespace Bu +{ + /** + * + */ + class Socket : public Stream + { + public: + Socket(); + virtual ~Socket(); + + private: + + }; +} + +#endif diff --git a/src/ssocket.cpp b/src/ssocket.cpp deleted file mode 100644 index 85a2da0..0000000 --- a/src/ssocket.cpp +++ /dev/null @@ -1,9 +0,0 @@ -#include "ssocket.h" - -Bu::SSocket::SSocket() -{ -} - -Bu::SSocket::~SSocket() -{ -} diff --git a/src/ssocket.h b/src/ssocket.h deleted file mode 100644 index ce02091..0000000 --- a/src/ssocket.h +++ /dev/null @@ -1,24 +0,0 @@ -#ifndef S_SOCKET_H -#define S_SOCKET_H - -#include <stdint.h> - -#include "stream.h" - -namespace Bu -{ - /** - * - */ - class SSocket : public Stream - { - public: - SSocket(); - virtual ~SSocket(); - - private: - - }; -} - -#endif diff --git a/src/tests/archive.cpp b/src/tests/archive.cpp index 5b7e285..2035aa6 100644 --- a/src/tests/archive.cpp +++ b/src/tests/archive.cpp @@ -1,11 +1,11 @@ #include "archive.h" -#include "sfile.h" +#include "file.h" using namespace Bu; int main() { - SFile f("test.dat", "wb"); + File f("test.dat", "wb"); Archive ar( f, Archive::save ); std::string s("Hello there"); diff --git a/src/unit/file.cpp b/src/unit/file.cpp new file mode 100644 index 0000000..a45b8d7 --- /dev/null +++ b/src/unit/file.cpp @@ -0,0 +1,105 @@ +#include "unitsuite.h" +#include "file.h" +#include "exceptions.h" + +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +class Unit : public Bu::UnitSuite +{ +public: + Unit() + { + setName("File"); + addTest( Unit::writeFull ); + addTest( Unit::readBlocks ); + addTest( Unit::readError1 ); + addTest( Unit::readError2 ); + } + + virtual ~Unit() { } + + // + // Tests go here + // + void writeFull() + { + Bu::File sf("testfile1", "wb"); + for( int c = 0; c < 256; c++ ) + { + unsigned char ch = (unsigned char)c; + sf.write( &ch, 1 ); + unitTest( sf.tell() == c+1 ); + } + //unitTest( sf.canRead() == false ); + //unitTest( sf.canWrite() == true ); + //unitTest( sf.canSeek() == true ); + sf.close(); + struct stat sdat; + stat("testfile1", &sdat ); + unitTest( sdat.st_size == 256 ); + } + + void readBlocks() + { + Bu::File sf("testfile1", "rb"); + unsigned char buf[50]; + size_t total = 0; + for(;;) + { + size_t s = sf.read( buf, 50 ); + for( size_t c = 0; c < s; c++ ) + { + unitTest( buf[c] == (unsigned char)(c+total) ); + } + total += s; + if( s < 50 ) + { + unitTest( total == 256 ); + unitTest( sf.isEOS() == true ); + break; + } + } + sf.close(); + } + + void readError1() + { + try + { + Bu::File sf("doesn'texist", "rb"); + unitFailed("No exception thrown"); + } + catch( Bu::FileException &e ) + { + return; + } + } + + void readError2() + { + Bu::File sf("testfile1", "rb"); + char buf[256]; + int r = sf.read( buf, 256 ); + unitTest( r == 256 ); + // You have to read past the end to set the EOS flag. + unitTest( sf.isEOS() == false ); + try + { + sf.read( buf, 5 ); + unitFailed("No exception thrown"); + } + catch( Bu::FileException &e ) + { + sf.close(); + return; + } + } +}; + +int main( int argc, char *argv[] ) +{ + return Unit().run( argc, argv ); +} + diff --git a/src/unit/sfile.cpp b/src/unit/sfile.cpp deleted file mode 100644 index 2aff312..0000000 --- a/src/unit/sfile.cpp +++ /dev/null @@ -1,105 +0,0 @@ -#include "unitsuite.h" -#include "sfile.h" -#include "exceptions.h" - -#include <sys/types.h> -#include <sys/stat.h> -#include <unistd.h> - -class Unit : public Bu::UnitSuite -{ -public: - Unit() - { - setName("SFile"); - addTest( Unit::writeFull ); - addTest( Unit::readBlocks ); - addTest( Unit::readError1 ); - addTest( Unit::readError2 ); - } - - virtual ~Unit() { } - - // - // Tests go here - // - void writeFull() - { - Bu::SFile sf("testfile1", "wb"); - for( int c = 0; c < 256; c++ ) - { - unsigned char ch = (unsigned char)c; - sf.write( &ch, 1 ); - unitTest( sf.tell() == c+1 ); - } - //unitTest( sf.canRead() == false ); - //unitTest( sf.canWrite() == true ); - //unitTest( sf.canSeek() == true ); - sf.close(); - struct stat sdat; - stat("testfile1", &sdat ); - unitTest( sdat.st_size == 256 ); - } - - void readBlocks() - { - Bu::SFile sf("testfile1", "rb"); - unsigned char buf[50]; - size_t total = 0; - for(;;) - { - size_t s = sf.read( buf, 50 ); - for( size_t c = 0; c < s; c++ ) - { - unitTest( buf[c] == (unsigned char)(c+total) ); - } - total += s; - if( s < 50 ) - { - unitTest( total == 256 ); - unitTest( sf.isEOS() == true ); - break; - } - } - sf.close(); - } - - void readError1() - { - try - { - Bu::SFile sf("doesn'texist", "rb"); - unitFailed("No exception thrown"); - } - catch( Bu::FileException &e ) - { - return; - } - } - - void readError2() - { - Bu::SFile sf("testfile1", "rb"); - char buf[256]; - int r = sf.read( buf, 256 ); - unitTest( r == 256 ); - // You have to read past the end to set the EOS flag. - unitTest( sf.isEOS() == false ); - try - { - sf.read( buf, 5 ); - unitFailed("No exception thrown"); - } - catch( Bu::FileException &e ) - { - sf.close(); - return; - } - } -}; - -int main( int argc, char *argv[] ) -{ - return Unit().run( argc, argv ); -} - diff --git a/src/unitsuite.h b/src/unitsuite.h index db249b2..6e9270a 100644 --- a/src/unitsuite.h +++ b/src/unitsuite.h @@ -8,7 +8,42 @@ namespace Bu { /** + * Provides a unit testing framework. This is pretty easy to use, probably + * the best way to get started is to use ch to generate a template, or use + * the code below with appropriate tweaks: + *@code + * #include "unitsuite.h" + * + * class Unit : public Bu::UnitSuite + * { + * public: + * Unit() + * { + * setName("Example"); + * addTest( Unit::test ); + * } + * + * virtual ~Unit() { } + * + * // + * // Tests go here + * // + * void test() + * { + * unitTest( 1 == 1 ); + * } + * }; + * + * int main( int argc, char *argv[] ) + * { + * return Unit().run( argc, argv ); + * } * + @endcode + * The main function can contain other things, but using this one exactly + * makes all of the test suites work exactly the same. Using the optional + * setName at the top of the constructor replaces the class name with the + * chosen name when printing out stats and info. */ class UnitSuite { -- cgit v1.2.3 From 530014a3cce53e86dce8917e98a4e86d02f176aa Mon Sep 17 00:00:00 2001 From: Mike Buland <eichlan@xagasoft.com> Date: Thu, 26 Apr 2007 15:06:49 +0000 Subject: Merged Ito and put it in the BU namespace. I should probably clean up the formatting on the comments, some of the lines wrap, but I'm not too worried about it right now. I also fixed up the doxygen config and build.conf files so that everything is building nice and smooth now. --- Doxyfile | 4 +- build.conf | 26 ++++-- mkincs.sh | 5 ++ src/exceptions.cpp | 1 + src/exceptions.h | 1 + src/ito.cpp | 40 +++++++++ src/ito.h | 98 ++++++++++++++++++++ src/itoatom.h | 56 ++++++++++++ src/itocondition.cpp | 42 +++++++++ src/itocondition.h | 81 +++++++++++++++++ src/itomutex.cpp | 27 ++++++ src/itomutex.h | 61 +++++++++++++ src/itoqueue.h | 231 ++++++++++++++++++++++++++++++++++++++++++++++++ src/main.dox | 14 +++ src/serversocket.cpp | 148 +++++++++++++++++++++++++++++++ src/serversocket.h | 31 +++++++ src/socket.cpp | 16 +--- src/socket.h | 4 +- src/tests/itoqueue1.cpp | 110 +++++++++++++++++++++++ src/tests/itoqueue2.cpp | 83 +++++++++++++++++ 20 files changed, 1059 insertions(+), 20 deletions(-) create mode 100755 mkincs.sh create mode 100644 src/ito.cpp create mode 100644 src/ito.h create mode 100644 src/itoatom.h create mode 100644 src/itocondition.cpp create mode 100644 src/itocondition.h create mode 100644 src/itomutex.cpp create mode 100644 src/itomutex.h create mode 100644 src/itoqueue.h create mode 100644 src/main.dox create mode 100644 src/serversocket.cpp create mode 100644 src/serversocket.h create mode 100644 src/tests/itoqueue1.cpp create mode 100644 src/tests/itoqueue2.cpp (limited to 'src/tests') diff --git a/Doxyfile b/Doxyfile index 6c7412e..c3168fa 100644 --- a/Doxyfile +++ b/Doxyfile @@ -74,9 +74,9 @@ QUIET = NO WARNINGS = YES WARN_IF_UNDOCUMENTED = YES WARN_IF_DOC_ERROR = YES -WARN_NO_PARAMDOC = NO +WARN_NO_PARAMDOC = YES WARN_FORMAT = "$file:$line: $text" -WARN_LOGFILE = +WARN_LOGFILE = Doxywarn #--------------------------------------------------------------------------- # configuration options related to the input files #--------------------------------------------------------------------------- diff --git a/build.conf b/build.conf index bc186f9..c289205 100644 --- a/build.conf +++ b/build.conf @@ -1,13 +1,17 @@ # This is a build file for libbu++ -default action: check "libbu++.a" -"clean" action: clean targets() -"tests" action: check targets() filter regexp("^tests/.*$") -"all" action: check targets() -"fstring" action: check "tests/fstring" +default action: check group "lnhdrs", check "libbu++.a" +"tests" action: check group "lnhdrs", check group "tests" +"all" action: check group "lnhdrs", check targets() set "CXXFLAGS" += "-ggdb -Wall" +filesIn("src") filter regexp("^src/(.*)\\.h$", "src/bu/{re:1}.h"): + rule "hln", + group "lnhdrs", + target file, + input "src/{re:1}.h" + "libbu++.a": rule "lib", target file, @@ -17,6 +21,7 @@ set "CXXFLAGS" += "-ggdb -Wall" directoriesIn("src/tests","tests/"): rule "exe", target file, + group "tests", requires "libbu++.a", set "CXXFLAGS" += "-Isrc", set "LDFLAGS" += "-L. -lbu++", @@ -25,14 +30,18 @@ directoriesIn("src/tests","tests/"): filesIn("src/tests") filter regexp("^src/tests/(.*)\\.cpp$", "tests/{re:1}"): rule "exe", target file, + group "tests", requires "libbu++.a", set "CXXFLAGS" += "-Isrc", set "LDFLAGS" += "-L. -lbu++", input "src/{target}.cpp" +["tests/itoqueue1", "tests/itoqueue2"]: set "LDFLAGS" += "-lpthread" + directoriesIn("src/unit","unit/"): rule "exe", target file, + group "tests", requires "libbu++.a", set "CXXFLAGS" += "-Isrc", set "LDFLAGS" += "-L. -lbu++", @@ -41,6 +50,7 @@ directoriesIn("src/unit","unit/"): filesIn("src/unit") filter regexp("^src/unit/(.*)\\.cpp$", "unit/{re:1}"): rule "exe", target file, + group "tests", requires "libbu++.a", set "CXXFLAGS" += "-Isrc", set "LDFLAGS" += "-L. -lbu++", @@ -63,3 +73,9 @@ rule "cpp": produces "{re:1}.o", requires commandToList("g++ -M {CXXFLAGS} {match}", "make"), perform command("g++ {CXXFLAGS} -c -o {target} {match}") + +rule "hln": + matches regexp("src/(.*)\\.h"), + produces "src/bu/{re:1}.h", + perform command("ln -s ../{re:1}.h {target}") + diff --git a/mkincs.sh b/mkincs.sh new file mode 100755 index 0000000..6f72f89 --- /dev/null +++ b/mkincs.sh @@ -0,0 +1,5 @@ +#!/bin/bash + +cd src/bu +rm * +for i in ../*.h; do ln -s $i; done diff --git a/src/exceptions.cpp b/src/exceptions.cpp index a512105..d9f4e70 100644 --- a/src/exceptions.cpp +++ b/src/exceptions.cpp @@ -5,6 +5,7 @@ namespace Bu { subExceptionDef( XmlException ) subExceptionDef( FileException ) + subExceptionDef( SocketException ) subExceptionDef( ConnectionException ) subExceptionDef( PluginException ) subExceptionDef( UnsupportedException ) diff --git a/src/exceptions.h b/src/exceptions.h index 3efa19f..f146b73 100644 --- a/src/exceptions.h +++ b/src/exceptions.h @@ -8,6 +8,7 @@ namespace Bu { subExceptionDecl( XmlException ) subExceptionDecl( FileException ) + subExceptionDecl( SocketException ) subExceptionDecl( ConnectionException ) subExceptionDecl( PluginException ) subExceptionDecl( UnsupportedException ) diff --git a/src/ito.cpp b/src/ito.cpp new file mode 100644 index 0000000..001ca06 --- /dev/null +++ b/src/ito.cpp @@ -0,0 +1,40 @@ +#include "ito.h" + +Bu::Ito::Ito() +{ +} + +Bu::Ito::~Ito() +{ +} + +bool Bu::Ito::start() +{ + nHandle = pthread_create( &ptHandle, NULL, threadRunner, this ); + + return true; +} + +bool Bu::Ito::stop() +{ + pthread_exit( &ptHandle ); + + return true; +} + +void *Bu::Ito::threadRunner( void *pThread ) +{ + return ((Ito *)pThread)->run(); +} + +bool Bu::Ito::join() +{ + pthread_join( ptHandle, NULL ); + return true; +} + +void Bu::Ito::yield() +{ + pthread_yield(); +} + diff --git a/src/ito.h b/src/ito.h new file mode 100644 index 0000000..01253f5 --- /dev/null +++ b/src/ito.h @@ -0,0 +1,98 @@ +#ifndef ITO_H +#define ITO_H + +#include <pthread.h> + +namespace Bu +{ + /** + * Simple thread class. This wraps the basic pthread (posix threads) system in + * an object oriented sort of way. It allows you to create a class with + * standard member variables and callable functions that can be run in it's own + * thread, one per class instance. + *@author Mike Buland + */ + class Ito + { + public: + /** + * Construct an Ito thread. + */ + Ito(); + + /** + * Destroy an Ito thread. + */ + virtual ~Ito(); + + /** + * Begin thread execution. This will call the overridden run function, + * which will simply execute in it's own thread until the function exits, + * the thread is killed, or the thread is cancelled (optionally). The + * thread started in this manner has access to all of it's class variables, + * but be sure to protect possible multiple-access with ItoMutex objects. + *@returns True if starting the thread was successful. False if something + * went wrong and the thread has not started. + */ + bool start(); + + /** + * Forcibly kill a thread. This is not generally considered a good thing to + * do, but in those rare cases you need it, it's invaluable. The problem + * with stopping (or killing) a thread is that it stops it the moment you + * call stop, no matter what it's doing. The object oriented approach to + * this will help clean up any class variables that were used, but anything + * not managed as a member variable will probably create a memory leak type + * of situation. Instead of stop, consider using cancel, which can be + * handled by the running thread in a graceful manner. + *@returns True if the thread was stopped, false otherwise. When this + * function returns the thread may not have stopped, to ensure that the + * thread has really stopped, call join. + */ + bool stop(); + + /** + * The workhorse of the Ito class. This is the function that will run in + * the thread, when this function exits the thread dies and is cleaned up + * by the system. Make sure to read up on ItoMutex, ItoCondition, and + * cancel to see how to control and protect everything you do in a safe way + * within this function. + *@returns I'm not sure right now, but this is the posix standard form. + */ + virtual void *run()=0; + + /** + * Join the thread in action. This function performs what is commonly + * called a thread join. That is that it effectively makes the calling + * thread an the Ito thread contained in the called object one in the same, + * and pauses the calling thread until the called thread exits. That is, + * when called from, say, your main(), mythread.join() will not return until + * the thread mythread has exited. This is very handy at the end of + * programs to ensure all of your data was cleaned up. + *@returns True if the thread was joined, false if the thread couldn't be + * joined, usually because it isn't running to begin with. + */ + bool join(); + + private: + pthread_t ptHandle; /**< Internal handle to the posix thread. */ + int nHandle; /**< Numeric handle to the posix thread. */ + + protected: + /** + * This is the hidden-heard of the thread system. While run is what the + * user gets to override, and everything said about it is true, this is + * the function that actually makes up the thread, it simply calls the + * run member function in an OO-friendly way. This is what allows us to + * use member variables from within the thread itself. + *@param Should always be this. + *@returns This is specified by posix, I'm not sure yet. + */ + static void *threadRunner( void *pThread ); + + void yield(); + + }; +} + +#endif diff --git a/src/itoatom.h b/src/itoatom.h new file mode 100644 index 0000000..96090f2 --- /dev/null +++ b/src/itoatom.h @@ -0,0 +1,56 @@ +#ifndef ITO_QUEUE_H +#define ITO_QUEUE_H + +#include <pthread.h> + +#include "itomutex.h" +#include "itocondition.h" + +/** + * A thread-safe wrapper class. + *@author Mike Buland + */ +template <class T> +class ItoAtom +{ +public: + /** + * Construct an empty queue. + */ + ItoAtom() + { + } + + ItoAtom( const T &src ) : + data( src ) + { + } + + ~ItoQueue() + { + } + + T get() + { + mOperate.lock(); + mOperate.unlock(); + return data; + } + + void set( const T &val ) + { + mOperate.lock(); + data = val; + cBlock.signal(); + mOperate.unlock(); + } + +private: + Item *pStart; /**< The start of the queue, the next element to dequeue. */ + Item *pEnd; /**< The end of the queue, the last element to dequeue. */ + + ItoMutex mOperate; /**< The master mutex, used on all operations. */ + ItoCondition cBlock; /**< The condition for blocking dequeues. */ +}; + +#endif diff --git a/src/itocondition.cpp b/src/itocondition.cpp new file mode 100644 index 0000000..d8f5375 --- /dev/null +++ b/src/itocondition.cpp @@ -0,0 +1,42 @@ +#include <sys/time.h> + +#include "itocondition.h" + +Bu::ItoCondition::ItoCondition() +{ + pthread_cond_init( &cond, NULL ); +} + +Bu::ItoCondition::~ItoCondition() +{ + pthread_cond_destroy( &cond ); +} + +int Bu::ItoCondition::wait() +{ + return pthread_cond_wait( &cond, &mutex ); +} + +int Bu::ItoCondition::wait( int nSec, int nUSec ) +{ + struct timeval now; + struct timespec timeout; + struct timezone tz; + + gettimeofday( &now, &tz ); + timeout.tv_sec = now.tv_sec + nSec + ((now.tv_usec + nUSec)/1000000); + timeout.tv_nsec = ((now.tv_usec + nUSec)%1000000)*1000; + + return pthread_cond_timedwait( &cond, &mutex, &timeout ); +} + +int Bu::ItoCondition::signal() +{ + return pthread_cond_signal( &cond ); +} + +int Bu::ItoCondition::broadcast() +{ + return pthread_cond_broadcast( &cond ); +} + diff --git a/src/itocondition.h b/src/itocondition.h new file mode 100644 index 0000000..4771b22 --- /dev/null +++ b/src/itocondition.h @@ -0,0 +1,81 @@ +#ifndef ITO_CONDITION_H +#define ITO_CONDITION_H + +#include <pthread.h> + +#include "itomutex.h" + +namespace Bu +{ + /** + * Ito condition. This is a fairly simple condition mechanism. As you may + * notice this class inherits from the ItoMutex class, this is because all + * conditions must be within a locked block. The standard usage of a condition + * is to pause one thread, perhaps indefinately, until another thread signals + * that it is alright to procede. + * <br> + * Standard usage for the thread that wants to wait is as follows: + * <pre> + * ItoCondition cond; + * ... // Perform setup and enter your run loop + * cond.lock(); + * while( !isFinished() ) // Could be anything you're waiting for + * cond.wait(); + * ... // Take care of what you have to. + * cond.unlock(); + * </pre> + * The usage for the triggering thread is much simpler, when it needs to tell + * the others that it's time to grab some data it calls either signal or + * broadcast. See both of those functions for the difference. + *@author Mike Buland + */ + class ItoCondition : public ItoMutex + { + public: + /** + * Create a condition. + */ + ItoCondition(); + + /** + * Destroy a condition. + */ + ~ItoCondition(); + + /** + * Wait forever, or until signalled. This has to be called from within a + * locked section, i.e. before calling this this object's lock function + * should be called. + */ + int wait(); + + /** + * Wait for a maximum of nSec seconds and nUSec micro-seconds or until + * signalled. This is a little more friendly function if you want to + * perform other operations in the thrad loop that calls this function. + * Like the other wait function, this must be inside a locked section. + *@param nSec The seconds to wait. + *@param nUSec the micro-seconds to wait. + */ + int wait( int nSec, int nUSec ); + + /** + * Notify the next thread waiting on this condition that they can go ahead. + * This only signals one thread, the next one in the condition queue, that + * it is safe to procede with whatever operation was being waited on. + */ + int signal(); + + /** + * Notify all threads waiting on this condition that they can go ahead now. + * This function is slower than signal, but more effective in certain + * situations where you may not know how many threads should be activated. + */ + int broadcast(); + + private: + pthread_cond_t cond; /**< Internal condition reference. */ + }; +} + +#endif diff --git a/src/itomutex.cpp b/src/itomutex.cpp new file mode 100644 index 0000000..dc51af9 --- /dev/null +++ b/src/itomutex.cpp @@ -0,0 +1,27 @@ +#include "itomutex.h" + +Bu::ItoMutex::ItoMutex() +{ + pthread_mutex_init( &mutex, NULL ); +} + +Bu::ItoMutex::~ItoMutex() +{ + pthread_mutex_destroy( &mutex ); +} + +int Bu::ItoMutex::lock() +{ + return pthread_mutex_lock( &mutex ); +} + +int Bu::ItoMutex::unlock() +{ + return pthread_mutex_unlock( &mutex ); +} + +int Bu::ItoMutex::trylock() +{ + return pthread_mutex_trylock( &mutex ); +} + diff --git a/src/itomutex.h b/src/itomutex.h new file mode 100644 index 0000000..80956b8 --- /dev/null +++ b/src/itomutex.h @@ -0,0 +1,61 @@ +#ifndef ITO_MUTEX_H +#define ITO_MUTEX_H + +#include <pthread.h> + +namespace Bu +{ + /** + * Simple mutex wrapper. Currently this doesn't do anything extra for you + * except keep all of the functionality together in an OO sorta' way and keep + * you from having to worry about cleaning up your mutexes properly, or initing + * them. + *@author Mike Buland + */ + class ItoMutex + { + public: + /** + * Create an unlocked mutex. + */ + ItoMutex(); + + /** + * Destroy a mutex. This can only be done when a mutex is unlocked. + * Failure to unlock before destroying a mutex object could cause it to + * wait for the mutex to unlock, the odds of which are usually farily low + * at deconstruction time. + */ + ~ItoMutex(); + + /** + * Lock the mutex. This causes all future calls to lock on this instance + * of mutex to block until the first thread that called mutex unlocks it. + * At that point the next thread that called lock will get a chance to go + * to work. Because of the nature of a mutex lock it is a very bad idea to + * do any kind of serious or rather time consuming computation within a + * locked section. This can cause thread-deadlock and your program may + * hang. + */ + int lock(); + + /** + * Unlock the mutex. This allows the next thread that asked for a lock to + * lock the mutex and continue with execution. + */ + int unlock(); + + /** + * Try to lock the mutex. This is the option to go with if you cannot avoid + * putting lengthy operations within a locked section. trylock will attempt + * to lock the mutex, if the mutex is already locked this function returns + * immediately with an error code. + */ + int trylock(); + + protected: + pthread_mutex_t mutex; /**< The internal mutex reference. */ + }; +} + +#endif diff --git a/src/itoqueue.h b/src/itoqueue.h new file mode 100644 index 0000000..322698d --- /dev/null +++ b/src/itoqueue.h @@ -0,0 +1,231 @@ +#ifndef ITO_QUEUE_H +#define ITO_QUEUE_H + +#include <pthread.h> + +#include "itomutex.h" +#include "itocondition.h" + +namespace Bu +{ + /** + * A thread-safe queue class. This class is a very simple queue with some cool + * extra functionality for use with the Ito system. The main extra that it + * provides is the option to either dequeue without blocking, with infinite + * blocking, or with timed blocking, which will return a value if something is + * enqueued within the specified time limit, or NULL if the time limit is + * exceded. + *@author Mike Buland + */ + template <class T> + class ItoQueue + { + private: + /** + * Helper struct. Keeps track of linked-list items for the queue data. + */ + typedef struct Item + { + T pData; + Item *pNext; + } Item; + + public: + /** + * Construct an empty queue. + */ + ItoQueue() : + pStart( NULL ), + pEnd( NULL ), + nSize( 0 ) + { + } + + /** + * Destroy the queue. This function will simply free all contained + * structures. If you stored pointers in the queue, this will lose the + * pointers without cleaning up the memory they pointed to. Make sure + * you're queue is empty before allowing it to be destroyed! + */ + ~ItoQueue() + { + Item *pCur = pStart; + while( pCur ) + { + Item *pTmp = pCur->pNext; + delete pCur; + pCur = pTmp; + } + } + + /** + * Enqueue a pieces of data. The new data will go at the end of the queue, + * and unless another piece of data is enqueued, will be the last piece of + * data to be dequeued. + *@param pData The data to enqueue. If this is not a primitive data type + * it's probably best to use a pointer type. + */ + void enqueue( T pData ) + { + mOperate.lock(); + + if( pStart == NULL ) + { + pStart = pEnd = new Item; + pStart->pData = pData; + pStart->pNext = NULL; + nSize++; + } + else + { + pEnd->pNext = new Item; + pEnd = pEnd->pNext; + pEnd->pData = pData; + pEnd->pNext = NULL; + nSize++; + } + + cBlock.signal(); + + mOperate.unlock(); + } + + /** + * Dequeue the first item from the queue. This function can operate in two + * different modes, blocking and non-blocking. In non-blocking mode it will + * return immediately weather there was data in the queue or not. If there + * was data it will remove it from the queue and return it to the caller. + * In blocking mode it will block forever wating for data to be enqueued. + * When data finally is enqueued this function will return immediately with + * the new data. The only way this function should ever return a null in + * blocking mode is if the calling thread was cancelled. It's probably a + * good idea to check for NULL return values even if you use blocking, just + * to be on the safe side. + *@param bBlock Set to true to enable blocking, leave as false to work in + * non-blocking mode. + *@returns The next piece of data in the queue, or NULL if no data was in + * the queue. + */ + T dequeue( bool bBlock=false ) + { + mOperate.lock(); + if( pStart == NULL ) + { + mOperate.unlock(); + + if( bBlock ) + { + cBlock.lock(); + + while( pStart == NULL ) + cBlock.wait(); + + T tmp = dequeue( false ); + + cBlock.unlock(); + return tmp; + + } + + return NULL; + } + else + { + T pTmp = pStart->pData; + Item *pDel = pStart; + pStart = pStart->pNext; + delete pDel; + nSize--; + + mOperate.unlock(); + return pTmp; + } + } + + /** + * Operates just like the other dequeue function in blocking mode with one + * twist. This function will block for at most nSec seconds and nUSec + * micro-seconds. If the timer is up and no data is available, this will + * just return NULL. If data is enqueued before the timeout expires, it + * will dequeue and exit immediately. + *@param nSec The number of seconds to wait, max. + *@param nUSec The number of micro-seconds to wait, max. + *@returns The next piece of data in the queue, or NULL if the timeout was + * exceeded. + */ + T dequeue( int nSec, int nUSec ) + { + mOperate.lock(); + if( pStart == NULL ) + { + mOperate.unlock(); + + cBlock.lock(); + + cBlock.wait( nSec, nUSec ); + + if( pStart == NULL ) + { + cBlock.unlock(); + return NULL; + } + + mOperate.lock(); + T pTmp = pStart->pData; + Item *pDel = pStart; + pStart = pStart->pNext; + delete pDel; + nSize--; + mOperate.unlock(); + + cBlock.unlock(); + return pTmp; + } + else + { + T pTmp = pStart->pData; + Item *pDel = pStart; + pStart = pStart->pNext; + delete pDel; + nSize--; + + mOperate.unlock(); + return pTmp; + } + } + + /** + * Checks to see if the queue has data in it or not. Note that there is no + * function to determine the length of the queue. This data isn't kept + * track of. If you really need to know, fix this. + *@returns True if the queue is empty, false if it has data in it. + */ + bool isEmpty() + { + mOperate.lock(); + bool bEmpty = (pStart == NULL ); + mOperate.unlock(); + + return bEmpty; + } + + long getSize() + { + mOperate.lock(); + long nRet = nSize; + mOperate.unlock(); + + return nRet; + } + + private: + Item *pStart; /**< The start of the queue, the next element to dequeue. */ + Item *pEnd; /**< The end of the queue, the last element to dequeue. */ + long nSize; /**< The number of items in the queue. */ + + ItoMutex mOperate; /**< The master mutex, used on all operations. */ + ItoCondition cBlock; /**< The condition for blocking dequeues. */ + }; +} + +#endif diff --git a/src/main.dox b/src/main.dox new file mode 100644 index 0000000..668d2e3 --- /dev/null +++ b/src/main.dox @@ -0,0 +1,14 @@ +/** + *@mainpage libbu++ utility library + * + *@section secIntro Introduction + * + * Libbu++ is a C++ library of general utility classes and functions. They + * cover a wide range of topics from streams and sockets to data structures to + * data serialization and xml handling to threading. + * + */ + +/** + *@namespace Bu The core libbu++ namespace, to ensure things don't get muddied. + */ diff --git a/src/serversocket.cpp b/src/serversocket.cpp new file mode 100644 index 0000000..c53c80d --- /dev/null +++ b/src/serversocket.cpp @@ -0,0 +1,148 @@ +#include <time.h> +#include <string.h> +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <termios.h> +#include <netinet/in.h> +#include <netdb.h> +#include <arpa/inet.h> +#include <fcntl.h> +#include "serversocket.h" +#include "exceptions.h" + +Bu::ServerSocket::ServerSocket( int nPort, int nPoolSize ) : + nPort( nPort ) +{ + /* Create the socket and set it up to accept connections. */ + struct sockaddr_in name; + + /* Give the socket a name. */ + name.sin_family = AF_INET; + name.sin_port = htons( nPort ); + + // I think this specifies who we will accept connections from, + // a good thing to make configurable later on + name.sin_addr.s_addr = htonl( INADDR_ANY ); + + startServer( name, nPoolSize ); +} + +Bu::ServerSocket::ServerSocket(const FString &sAddr,int nPort, int nPoolSize) : + nPort( nPort ) +{ + /* Create the socket and set it up to accept connections. */ + struct sockaddr_in name; + + /* Give the socket a name. */ + name.sin_family = AF_INET; + name.sin_port = htons( nPort ); + + inet_aton( sAddr.getStr(), &name.sin_addr ); + + startServer( name, nPoolSize ); +} + +Bu::ServerSocket::~ServerSocket() +{ +} + +void Bu::ServerSocket::startServer( struct sockaddr_in &name, int nPoolSize ) +{ + /* Create the socket. */ + nServer = socket( PF_INET, SOCK_STREAM, 0 ); + if( nServer < 0 ) + { + throw Bu::SocketException("Couldn't create a listen socket."); + } + + int opt = 1; + setsockopt( + nServer, + SOL_SOCKET, + SO_REUSEADDR, + (char *)&opt, + sizeof( opt ) + ); + + if( bind( nServer, (struct sockaddr *) &name, sizeof(name) ) < 0 ) + { + throw Bu::SocketException("Couldn't bind to the listen socket."); + } + + if( listen( nServer, nPoolSize ) < 0 ) + { + throw Bu::SocketException( + "Couldn't begin listening to the server socket." + ); + } + + FD_ZERO( &fdActive ); + /* Initialize the set of active sockets. */ + FD_SET( nServer, &fdActive ); +} + +int Bu::ServerSocket::accept( int nTimeoutSec, int nTimeoutUSec ) +{ + fd_set fdRead = fdActive; + + struct timeval xT; + + xT.tv_sec = nTimeoutSec; + xT.tv_usec = nTimeoutUSec; + + if( TEMP_FAILURE_RETRY(select( nServer+1, &fdRead, NULL, NULL, &xT )) < 0 ) + { + throw SocketException( + "Error scanning for new connections: %s", strerror( errno ) + ); + } + + if( FD_ISSET( nServer, &fdRead ) ) + { + struct sockaddr_in clientname; + size_t size; + int nClient; + + size = sizeof( clientname ); +#ifdef __CYGWIN__ + nClient = ::accept( nServer, (struct sockaddr *)&clientname, + (int *)&size + ); +#else + nClient = ::accept( nServer, (struct sockaddr *)&clientname, &size ); +#endif + if( nClient < 0 ) + { + throw SocketException( + "Error accepting a new connection: %s", strerror( errno ) + ); + } + char tmpa[20]; + inet_ntop( AF_INET, (void *)&clientname.sin_addr, tmpa, 20 ); + //"New connection from host %s, port %hd.", + // tmpa, ntohs (clientname.sin_port) ); + + { + int flags; + + flags = fcntl( nClient, F_GETFL, 0 ); + flags |= O_NONBLOCK; + if( fcntl( nClient, F_SETFL, flags ) < 0) + { + throw SocketException( + "Error setting option on client socket: %s", + strerror( errno ) + ); + } + } + + return nClient; + } + + return -1; +} + diff --git a/src/serversocket.h b/src/serversocket.h new file mode 100644 index 0000000..9a26e2d --- /dev/null +++ b/src/serversocket.h @@ -0,0 +1,31 @@ +#ifndef SERVER_SOCKET_H +#define SERVER_SOCKET_H + +#include <stdint.h> +#include "fstring.h" +#include "socket.h" + +namespace Bu +{ + /** + * + */ + class ServerSocket + { + public: + ServerSocket( int nPort, int nPoolSize=40 ); + ServerSocket( const FString &sAddr, int nPort, int nPoolSize=40 ); + virtual ~ServerSocket(); + + int accept( int nTimeoutSec, int nTimeoutUSec ); + + private: + void startServer( struct sockaddr_in &name, int nPoolSize ); + + fd_set fdActive; + int nServer; + int nPort; + }; +} + +#endif diff --git a/src/socket.cpp b/src/socket.cpp index c4f914b..455b5c8 100644 --- a/src/socket.cpp +++ b/src/socket.cpp @@ -118,6 +118,7 @@ void Bu::Socket::close() //} } +/* void Bu::Socket::read() { char buffer[RBS]; @@ -132,7 +133,6 @@ void Bu::Socket::read() if( nbytes < 0 && errno != 0 && errno != EAGAIN ) { //printf("errno: %d, %s\n", errno, strerror( errno ) ); - /* Read error. */ //perror("readInput"); throw ConnectionException( excodeReadError, @@ -146,15 +146,13 @@ void Bu::Socket::read() break; nTotalRead += nbytes; sReadBuf.append( buffer, nbytes ); - /* Data read. */ if( nbytes < RBS ) { break; } - /* New test, if data is divisible by RBS bytes on some libs the - * read could block, this keeps it from happening. - */ + // New test, if data is divisible by RBS bytes on some libs the + // read could block, this keeps it from happening. { fd_set rfds; FD_ZERO(&rfds); @@ -171,13 +169,7 @@ void Bu::Socket::read() } } } - - /* - if( pProtocol != NULL && nTotalRead > 0 ) - { - pProtocol->onNewData(); - }*/ -} +}*/ size_t Bu::Socket::read( void *pBuf, size_t nBytes ) { diff --git a/src/socket.h b/src/socket.h index 3d0125d..568cad6 100644 --- a/src/socket.h +++ b/src/socket.h @@ -19,7 +19,7 @@ namespace Bu virtual ~Socket(); virtual void close(); - virtual void read(); + //virtual void read(); virtual size_t read( void *pBuf, size_t nBytes ); virtual size_t write( const void *pBuf, size_t nBytes ); @@ -33,6 +33,8 @@ namespace Bu virtual bool canWrite(); virtual bool canSeek(); + + private: int nSocket; bool bActive; diff --git a/src/tests/itoqueue1.cpp b/src/tests/itoqueue1.cpp new file mode 100644 index 0000000..f73f4d3 --- /dev/null +++ b/src/tests/itoqueue1.cpp @@ -0,0 +1,110 @@ +#include <string> +#include "bu/ito.h" +#include "bu/itoqueue.h" + +class Reader : public Bu::Ito +{ +public: + Reader( Bu::ItoQueue<std::string *> &q, int id ) : + q( q ), + id( id ) + { + } + + void *run() + { + for( int i = 0; i < 10; i++ ) + { + std::string *pStr = q.dequeue( true ); + if( pStr == NULL ) + { + printf("Null received...\n"); + } + else + { + printf("[%d] read: %s\n", id, pStr->c_str() ); + delete pStr; + } + usleep( (int)(((double)rand())/((double)RAND_MAX)*2000000.0) ); + } + + return NULL; + } + +private: + Bu::ItoQueue<std::string *> &q; + int id; +}; + +class Writer : public Bu::Ito +{ +public: + Writer( Bu::ItoQueue<std::string *> &q, int id, const char *strbase ) : + q( q ), + strbase( strbase ), + id( id ) + { + } + + void *run() + { + for( int i = 0; i < 11; i++ ) + { + usleep( (int)(((double)rand())/((double)RAND_MAX)*2000000.0) ); + q.enqueue( new std::string( strbase ) ); + printf("[%d] write: %s\n", id, strbase ); + } + + return NULL; + } + +private: + Bu::ItoQueue<std::string *> &q; + const char *strbase; + int id; +}; + +int main() +{ + Writer *wr[5]; + Reader *rd[5]; + const char bob[][7]={ + {"Test 1"}, + {"Test 2"}, + {"Test 3"}, + {"Test 4"}, + {"Test 5"} + }; + + Bu::ItoQueue<std::string *> q; + + for( int j = 0; j < 5; j++ ) + { + wr[j] = new Writer( q, j, bob[j] ); + rd[j] = new Reader( q, j ); + } + + for( int j = 0; j < 5; j++ ) + { + rd[j]->start(); + } + + for( int j = 0; j < 5; j++ ) + { + wr[j]->start(); + } + + for( int j = 0; j < 5; j++ ) + { + rd[j]->join(); + } + + for( int j = 0; j < 5; j++ ) + { + delete wr[j]; + delete rd[j]; + } + + return 0; +} + diff --git a/src/tests/itoqueue2.cpp b/src/tests/itoqueue2.cpp new file mode 100644 index 0000000..f4b5e19 --- /dev/null +++ b/src/tests/itoqueue2.cpp @@ -0,0 +1,83 @@ +#include <string> +#include "bu/ito.h" +#include "bu/itoqueue.h" +#include <errno.h> + +class Reader : public Bu::Ito +{ +public: + Reader( Bu::ItoQueue<std::string *> &q, int id ) : + q( q ), + id( id ) + { + } + + void *run() + { + for( int i = 0; i < 10; i++ ) + { + std::string *pStr = q.dequeue( 0, 500000 ); + if( pStr == NULL ) + { + printf("Null received...\n"); + i--; + } + else + { + printf("[%d] read: %s\n", id, pStr->c_str() ); + delete pStr; + } + } + + return NULL; + } + +private: + Bu::ItoQueue<std::string *> &q; + int id; +}; + +class Writer : public Bu::Ito +{ +public: + Writer( Bu::ItoQueue<std::string *> &q, int id, const char *strbase ) : + q( q ), + strbase( strbase ), + id( id ) + { + } + + void *run() + { + for( int i = 0; i < 11; i++ ) + { + sleep( 2 ); + printf("[%d] write: %s\n", id, strbase ); + q.enqueue( new std::string( strbase ) ); + } + + return NULL; + } + +private: + Bu::ItoQueue<std::string *> &q; + const char *strbase; + int id; +}; + +int main() +{ + printf("ETIMEDOUT: %d\n", ETIMEDOUT ); + Bu::ItoQueue<std::string *> q; + Writer wr( q, 0, "writer" ); + Reader rd( q, 0 ); + + rd.start(); + wr.start(); + + rd.join(); + wr.join(); + + return 0; +} + -- cgit v1.2.3 From c17c4ebbab022de80a9f893115f2fd41e6a07c44 Mon Sep 17 00:00:00 2001 From: Mike Buland <eichlan@xagasoft.com> Date: Tue, 8 May 2007 06:31:33 +0000 Subject: Added the TAF format structures and XML format structures, I'm making up TAF (textual archive format), but named it wrong, this seemed easier than redoing it all. --- misc/w3c-xml-1.1.html | 1598 +++++++++++++++++++++++++++++++++++++++++++++++++ src/tests/xml.cpp | 15 + src/tsfdocument.cpp | 9 + src/tsfdocument.h | 22 + src/tsfnode.cpp | 9 + src/tsfnode.h | 21 + src/tsfreader.cpp | 9 + src/tsfreader.h | 22 + src/tsfwriter.cpp | 9 + src/tsfwriter.h | 22 + src/xmldocument.cpp | 9 + src/xmldocument.h | 22 + src/xmlnode.cpp | 9 + src/xmlnode.h | 22 + src/xmlreader.cpp | 108 ++++ src/xmlreader.h | 70 +++ src/xmlwriter.cpp | 9 + src/xmlwriter.h | 22 + 18 files changed, 2007 insertions(+) create mode 100644 misc/w3c-xml-1.1.html create mode 100644 src/tests/xml.cpp create mode 100644 src/tsfdocument.cpp create mode 100644 src/tsfdocument.h create mode 100644 src/tsfnode.cpp create mode 100644 src/tsfnode.h create mode 100644 src/tsfreader.cpp create mode 100644 src/tsfreader.h create mode 100644 src/tsfwriter.cpp create mode 100644 src/tsfwriter.h create mode 100644 src/xmldocument.cpp create mode 100644 src/xmldocument.h create mode 100644 src/xmlnode.cpp create mode 100644 src/xmlnode.h create mode 100644 src/xmlreader.cpp create mode 100644 src/xmlreader.h create mode 100644 src/xmlwriter.cpp create mode 100644 src/xmlwriter.h (limited to 'src/tests') diff --git a/misc/w3c-xml-1.1.html b/misc/w3c-xml-1.1.html new file mode 100644 index 0000000..6a9211a --- /dev/null +++ b/misc/w3c-xml-1.1.html @@ -0,0 +1,1598 @@ +<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"><html lang="EN" xmlns="http://www.w3.org/1999/xhtml"><head><meta http-equiv="Content-Type" content="text/html;charset=UTF-8" /><title>Extensible Markup Language (XML) 1.1

W3C

+

Extensible Markup Language (XML) 1.1

+

W3C Recommendation 04 + February 2004, edited in place 15 April 2004

This version:
http://www.w3.org/TR/2004/REC-xml11-20040204/
Latest version:
http://www.w3.org/TR/xml11
Previous version:
http://www.w3.org/TR/2003/PR-xml11-20031105/
Editors:
Tim Bray, Textuality and Netscape <tbray@textuality.com>
Jean Paoli, Microsoft <jeanpa@microsoft.com>
C. M. Sperberg-McQueen, W3C <cmsmcq@w3.org>
Eve Maler, Sun Microsystems, Inc. <eve.maler@east.sun.com>
François Yergeau <fyergeau@alis.com>
John Cowan <cowan@ccil.org>

Please refer to the errata for this document, which may include some normative corrections.

This document is also available in these non-normative formats: XML and XHTML with color-coded revision indicators.

See also translations.

Copyright © 2004 W3C® (MIT, ERCIM, Keio), All Rights Reserved. W3C liability, trademark, document use and software licensing rules apply.

Status of this Document

This section describes the status of this document at the time of its publication. Other documents may supersede this document. A list of current W3C publications and the latest revision of this technical report can be found in the W3C technical reports index at http://www.w3.org/TR/.

This document is a Recommendation of the W3C. +It has been reviewed by W3C Members and other interested parties, and has +been endorsed by the Director as a W3C Recommendation. It is a stable document and may be used as reference material or cited as a normative reference from another document. W3C's role in making the +Recommendation is to draw attention to the specification and to promote its widespread deployment. +This enhances the functionality and interoperability of the Web.

This document specifies a syntax created by subsetting an existing, widely +used international text processing standard (Standard Generalized Markup Language, +ISO 8879:1986(E) as amended and corrected) for use on the World Wide Web. +It is a product of the W3C XML + Activity.

+ +

On 15 April 2004, this document was edited in place to add two +missing spaces to production +[1] in section 2.1

+ +

The English version of this specification is the only normative version. However, +for translations of this document, see http://www.w3.org/2003/03/Translations/byTechnology?technology=xml11. +

Documentation of intellectual property possibly relevant to this recommendation +may be found at the Working Group's public +IPR disclosure page.

An implementation report for XML 1.1 is available at http://www.w3.org/XML/2002/09/xml11-implementation.html.

Please report errors in this document to xml-editor@w3.org; archives are available. The errata list for this edition is available +at http://www.w3.org/XML/xml-V11-1e-errata.

A Test Suite is maintained to help assessing conformance to this specification.

Table of Contents

1 Introduction
    1.1 Origin and Goals
    1.2 Terminology
    1.3 Rationale and list of changes for XML 1.1
2 Documents
    2.1 Well-Formed XML Documents
    2.2 Characters
    2.3 Common Syntactic Constructs
    2.4 Character Data and Markup
    2.5 Comments
    2.6 Processing Instructions
    2.7 CDATA Sections
    2.8 Prolog and Document Type Declaration
    2.9 Standalone Document Declaration
    2.10 White Space Handling
    2.11 End-of-Line Handling
    2.12 Language Identification
    2.13 Normalization Checking
3 Logical Structures
    3.1 Start-Tags, End-Tags, and Empty-Element Tags
    3.2 Element Type Declarations
        3.2.1 Element Content
        3.2.2 Mixed Content
    3.3 Attribute-List Declarations
        3.3.1 Attribute Types
        3.3.2 Attribute Defaults
        3.3.3 Attribute-Value Normalization
    3.4 Conditional Sections
4 Physical Structures
    4.1 Character and Entity References
    4.2 Entity Declarations
        4.2.1 Internal Entities
        4.2.2 External Entities
    4.3 Parsed Entities
        4.3.1 The Text Declaration
        4.3.2 Well-Formed Parsed Entities
        4.3.3 Character Encoding in Entities
        4.3.4 Version Information in Entities
    4.4 XML Processor Treatment of Entities and References
        4.4.1 Not Recognized
        4.4.2 Included
        4.4.3 Included If Validating
        4.4.4 Forbidden
        4.4.5 Included in Literal
        4.4.6 Notify
        4.4.7 Bypassed
        4.4.8 Included as PE
        4.4.9 Error
    4.5 Construction of Entity Replacement Text
    4.6 Predefined Entities
    4.7 Notation Declarations
    4.8 Document Entity
5 Conformance
    5.1 Validating and Non-Validating Processors
    5.2 Using XML Processors
6 Notation

Appendices

A References
    A.1 Normative References
    A.2 Other References
B Definitions for Character Normalization
C Expansion of Entity and Character References (Non-Normative)
D Deterministic Content Models (Non-Normative)
E Autodetection of Character Encodings (Non-Normative)
    E.1 Detection Without External Encoding Information
    E.2 Priorities in the Presence of External Encoding Information
F W3C XML Working Group (Non-Normative)
G W3C XML Core Working Group (Non-Normative)
H Production Notes (Non-Normative)
I Suggestions for XML Names (Non-Normative)

1 Introduction

Extensible Markup Language, abbreviated XML, describes a class of data +objects called XML documents and partially +describes the behavior of computer programs which process them. XML is an +application profile or restricted form of SGML, the Standard Generalized Markup +Language [ISO 8879]. By construction, XML documents are conforming +SGML documents.

XML documents are made up of storage units called entities, +which contain either parsed or unparsed data. Parsed data is made up of characters, some of which form character +data, and some of which form markup. +Markup encodes a description of the document's storage layout and logical +structure. XML provides a mechanism to impose constraints on the storage layout +and logical structure.

[Definition: A software module called +an XML processor is used to read XML documents and provide access +to their content and structure.] [Definition: It +is assumed that an XML processor is doing its work on behalf of another module, +called the application.] This specification describes +the required behavior of an XML processor in terms of how it must read XML +data and the information it must provide to the application.

1.1 Origin and Goals

XML was developed by an XML Working Group (originally known as the SGML +Editorial Review Board) formed under the auspices of the World Wide Web Consortium +(W3C) in 1996. It was chaired by Jon Bosak of Sun Microsystems with the active +participation of an XML Special Interest Group (previously known as the SGML +Working Group) also organized by the W3C. The membership of the XML Working +Group is given in an appendix. Dan Connolly served as the Working Group's contact with +the W3C.

The design goals for XML are:

  1. XML shall be straightforwardly usable over the Internet.

  2. XML shall support a wide variety of applications.

  3. XML shall be compatible with SGML.

  4. It shall be easy to write programs which process XML documents.

  5. The number of optional features in XML is to be kept to the absolute +minimum, ideally zero.

  6. XML documents should be human-legible and reasonably clear.

  7. The XML design should be prepared quickly.

  8. The design of XML shall be formal and concise.

  9. XML documents shall be easy to create.

  10. Terseness in XML markup is of minimal importance.

This specification, together with associated standards (Unicode +[Unicode] and ISO/IEC 10646 [ISO/IEC 10646] +for characters, Internet RFC 3066 [IETF RFC 3066] for +language identification tags, ISO 639 [ISO 639] +for language name codes, and ISO 3166 [ISO 3166] for +country name codes), provides all the information necessary to +understand XML Version 1.1 and construct computer +programs to process it.

This version of the XML specification may be distributed freely, as long as +all text and legal notices remain intact.

1.2 Terminology

The terminology used to describe XML documents is defined in the body of +this specification. The key words MUST, MUST NOT, REQUIRED, SHALL, SHALL NOT, SHOULD, SHOULD NOT, RECOMMENDED, MAY, and OPTIONAL, when EMPHASIZED, are to be interpreted as described in [IETF RFC 2119]. In addition, the terms defined in the following list are used in building +those definitions and in describing the actions of an XML processor:

error

[Definition: A violation of the rules of this specification; +results are undefined. Unless otherwise specified, failure to observe a prescription of this specification indicated by one of the keywords MUST, REQUIRED, MUST NOT, SHALL and SHALL NOT is an error. Conforming software MAY detect and report an error +and MAY recover from it.]

fatal error

[Definition: An error which a conforming XML processor MUST detect and report to the application. +After encountering a fatal error, the processor MAY continue processing the +data to search for further errors and MAY report such errors to the application. +In order to support correction of errors, the processor MAY make unprocessed +data from the document (with intermingled character data and markup) available +to the application. Once a fatal error is detected, however, the processor +MUST NOT continue normal processing (i.e., it MUST NOT continue to pass character +data and information about the document's logical structure to the application +in the normal way).]

at user option

[Definition: Conforming software +MAY or MUST (depending on the modal verb in the sentence) behave as described; +if it does, it MUST provide users a means to enable or disable the behavior +described.]

validity constraint

[Definition: A rule which applies to +all valid XML documents. Violations of validity +constraints are errors; they MUST, at user option, be reported by validating XML processors.]

well-formedness constraint

[Definition: A rule which applies +to all well-formed XML documents. Violations +of well-formedness constraints are fatal errors.]

match

[Definition: (Of strings or names:) Two strings +or names being compared MUST be identical. Characters with multiple possible +representations in Unicode (e.g. characters with both precomposed and +base+diacritic forms) match only if they have the same representation in both +strings. No +case folding is performed. (Of strings and rules in the grammar:) A string +matches a grammatical production if it belongs to the language generated by +that production. (Of content and content models:) An element matches its declaration +when it conforms in the fashion described in the constraint [VC: Element Valid].]

for compatibility

[Definition: Marks +a sentence describing a feature of XML included solely to ensure +that XML remains compatible with SGML.]

for interoperability

[Definition: Marks +a sentence describing a non-binding recommendation included to increase +the chances that XML documents can be processed by the existing installed +base of SGML processors which predate the WebSGML Adaptations Annex to ISO 8879.]

1.3 Rationale and list of changes for XML 1.1

The W3C's XML 1.0 Recommendation was first issued in 1998, and +despite the issuance of many errata culminating in a Third Edition +of 2004, has remained (by intention) unchanged with respect to what +is well-formed XML and what is not. This stability has been +extremely useful for interoperability. However, the Unicode +Standard on which XML 1.0 relies for character specifications has +not remained static, evolving from version 2.0 to version 4.0 and +beyond. Characters not present in Unicode 2.0 may already be used +in XML 1.0 character data. However, they are not allowed in XML +names such as element type names, attribute names, enumerated +attribute values, processing instruction targets, and so on. In +addition, some characters that should have been permitted in XML +names were not, due to oversights and inconsistencies in Unicode +2.0.

The overall philosophy of names has changed since XML 1.0. +Whereas XML 1.0 provided a rigid definition of names, wherein +everything that was not permitted was forbidden, XML 1.1 names are +designed so that everything that is not forbidden (for a specific +reason) is permitted. Since Unicode will continue to grow past +version 4.0, further changes to XML can be avoided by allowing +almost any character, including those not yet assigned, in +names.

In addition, XML 1.0 attempts to adapt to the line-end +conventions of various modern operating systems, but discriminates +against the conventions used on IBM and IBM-compatible mainframes. +As a result, XML documents on mainframes are not plain text files +according to the local conventions. XML 1.0 documents generated on +mainframes must either violate the local line-end conventions, or +employ otherwise unnecessary translation phases before parsing and +after generation. Allowing straightforward interoperability is +particularly important when data stores are shared between +mainframe and non-mainframe systems (as opposed to being copied +from one to the other). Therefore XML 1.1 adds NEL (#x85) to the +list of line-end characters. For completeness, the Unicode line +separator character, #x2028, is also supported. +

Finally, there is considerable demand to define a standard representation +of arbitrary Unicode characters in XML documents. Therefore, XML 1.1 +allows the use of character references to the control characters #x1 through +#x1F, most of which are forbidden in XML 1.0. For reasons of robustness, +however, these characters still cannot be used directly in documents. In +order to improve the robustness of character encoding detection, the additional +control characters #x7F through #x9F, which were freely allowed in XML 1.0 +documents, now must also appear only as character references. (Whitespace +characters are of course exempt.) The minor sacrifice of backward compatibility +is considered not significant. Due to potential problems with APIs, +#x0 is still forbidden both directly and as a character reference. +

Finally, XML 1.1 defines a set of constraints called "full +normalization" on XML documents, which document creators +SHOULD adhere to, and document processors +SHOULD verify. Using fully normalized documents +ensures that identity comparisons of names, attribute values, and +character content can be made correctly by simple binary comparison of +Unicode strings.

A new XML version, rather than a set of errata to XML 1.0, is +being created because the changes affect the definition of +well-formed documents. XML 1.0 processors must continue to reject +documents that contain new characters in XML names, new line-end +conventions, and references to control characters. The distinction between XML 1.0 and XML 1.1 documents +is indicated by the version number information in the XML +declaration at the start of each document. +

2 Documents

[Definition: A data object is an XML +document if it is well-formed, +as defined in this specification. A well-formed XML document MAY in addition +be valid if it meets certain further constraints.]

Each XML document has both a logical and a physical structure. Physically, +the document is composed of units called entities. +An entity MAY refer to other entities to +cause their inclusion in the document. A document begins in a "root" +or document entity. Logically, the document +is composed of declarations, elements, comments, character references, and +processing instructions, all of which are indicated in the document by explicit +markup. The logical and physical structures MUST nest properly, as described +in 4.3.2 Well-Formed Parsed Entities.

2.1 Well-Formed XML Documents

[Definition: A textual object is a well-formed +XML document if:]

  1. Taken as a whole, it matches the production labeled document.

  2. It meets all the well-formedness constraints given in this specification.

  3. Each of the parsed entities +which is referenced directly or indirectly within the document is well-formed.

Document
[1]   document   ::=   prolog element Misc* - Char* RestrictedChar Char*

Matching the document production implies that:

  1. It contains one or more elements.

  2. [Definition: There is exactly one element, +called the root, or document element, no part of which appears +in the content of any other element.] For +all other elements, if the start-tag is in +the content of another element, the end-tag +is in the content of the same element. More simply stated, the elements, +delimited by start- and end-tags, nest properly within each other.

[Definition: As a consequence of this, +for each non-root element C in the document, there is one other element P +in the document such that C is in the content of P, but +is not in the content of any other element that is in the content of P. P +is referred to as the parent of C, and C as +a child of P.]

2.2 Characters

[Definition: A parsed entity contains text, +a sequence of characters, which may +represent markup or character data.] [Definition: A character +is an atomic unit of text as specified by ISO/IEC 10646 [ISO/IEC 10646]. Legal characters are tab, carriage +return, line feed, and the legal characters +of Unicode and ISO/IEC 10646. The +versions of these standards cited in A.1 Normative References were +current at the time this document was prepared. New characters may be added +to these standards by amendments or new editions. Consequently, XML processors +MUST accept any character in the range specified for Char.]

Character Range
[2]   Char   ::=   [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]/* any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. */
[2a]   RestrictedChar   ::=   [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]

The mechanism for encoding character code points into bit patterns MAY +vary from entity to entity. All XML processors MUST accept the UTF-8 and UTF-16 +encodings of Unicode +[Unicode]; +the mechanisms for signaling which of the two is in use, +or for bringing other encodings into play, are discussed later, in 4.3.3 Character Encoding in Entities.

Note:

Document authors are encouraged to avoid +"compatibility characters", as defined +in Unicode [Unicode]. +The characters defined in the following ranges are also +discouraged. They are either control characters or permanently undefined Unicode +characters:

+[#x7F-#x84], [#x86-#x9F], [#xFDD0-#xFDDF],
+[#1FFFE-#x1FFFF], [#2FFFE-#x2FFFF], [#3FFFE-#x3FFFF],
+[#4FFFE-#x4FFFF], [#5FFFE-#x5FFFF], [#6FFFE-#x6FFFF],
+[#7FFFE-#x7FFFF], [#8FFFE-#x8FFFF], [#9FFFE-#x9FFFF],
+[#AFFFE-#xAFFFF], [#BFFFE-#xBFFFF], [#CFFFE-#xCFFFF],
+[#DFFFE-#xDFFFF], [#EFFFE-#xEFFFF], [#FFFFE-#xFFFFF],
+[#10FFFE-#x10FFFF].

2.3 Common Syntactic Constructs

This section defines some symbols used widely in the grammar.

S (white space) consists of one or more space (#x20) +characters, carriage returns, line feeds, or tabs.

White Space
[3]   S   ::=   (#x20 | #x9 | #xD | #xA)+

Note:

The presence of #xD in the above production is +maintained purely for backward compatibility with the +First Edition. +As explained in 2.11 End-of-Line Handling, +all #xD characters literally present in an XML document +are either removed or replaced by #xA characters before +any other processing is done. The only way to get a #xD character to match this production is to +use a character reference in an entity value literal.

[Definition: A Name is a token beginning +with a letter or one of a few punctuation characters, and continuing with +letters, digits, hyphens, underscores, colons, or full stops, together known +as name characters.] Names beginning with the string "xml", +or with any string which would match (('X'|'x') ('M'|'m') ('L'|'l')), +are reserved for standardization in this or future versions of this specification.

Note:

The +Namespaces in XML Recommendation [XML Names] assigns a meaning +to names containing colon characters. Therefore, authors should not use the +colon in XML names except for namespace purposes, but XML processors must +accept the colon as a name character.

An Nmtoken (name token) is any mixture of name +characters.

The first character of a Name MUST be a NameStartChar, and any +other characters MUST be NameChars; this mechanism is used to +prevent names from beginning with European (ASCII) digits or with +basic combining characters. Almost all characters are permitted in +names, except those which either are or reasonably could be used as +delimiters. The intention is to be inclusive rather than exclusive, +so that writing systems not yet encoded in Unicode can be used in +XML names. See I Suggestions for XML Names for suggestions on the creation of +names.

Document authors are encouraged to use names which are +meaningful words or combinations of words in natural languages, and +to avoid symbolic or white space characters in names. Note that +COLON, HYPHEN-MINUS, FULL STOP (period), LOW LINE (underscore), and +MIDDLE DOT are explicitly permitted.

The ASCII symbols and punctuation marks, along with a fairly +large group of Unicode symbol characters, are excluded from names +because they are more useful as delimiters in contexts where XML +names are used outside XML documents; providing this group gives +those contexts hard guarantees about what cannot be part of +an XML name. The character #x037E, GREEK QUESTION MARK, is excluded +because when normalized it becomes a semicolon, which could change +the meaning of entity references.

Names and Tokens
[4]   NameStartChar   ::=   ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] | [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] | [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] | [#x10000-#xEFFFF]
[4a]   NameChar   ::=   NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040]
[5]   Name   ::=   NameStartChar (NameChar)*
[6]   Names   ::=   Name (#x20 Name)*
[7]   Nmtoken   ::=   (NameChar)+
[8]   Nmtokens   ::=   Nmtoken (#x20 Nmtoken)*

Note:

The Names +and Nmtokens productions are used to define the validity +of tokenized attribute values after normalization (see 3.3.1 Attribute Types).

Literal data is any quoted string not containing the quotation mark used +as a delimiter for that string. Literals are used for specifying the content +of internal entities (EntityValue), the values +of attributes (AttValue), and external identifiers +(SystemLiteral). Note that a SystemLiteral +can be parsed without scanning for markup.

Literals
[9]   EntityValue   ::=   '"' ([^%&"] | PEReference +| Reference)* '"'
|  "'" ([^%&'] | PEReference | Reference)* "'"
[10]   AttValue   ::=   '"' ([^<&"] | Reference)* +'"'
|  "'" ([^<&'] | Reference)* +"'"
[11]   SystemLiteral   ::=   ('"' [^"]* '"') | ("'" [^']* "'")
[12]   PubidLiteral   ::=   '"' PubidChar* '"' +| "'" (PubidChar - "'")* "'"
[13]   PubidChar   ::=   #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]

Note:

Although +the EntityValue production allows the definition +of a general entity consisting of a single explicit < in the literal +(e.g., <!ENTITY mylt "<">), it is strongly advised to avoid +this practice since any reference to that entity will cause a well-formedness +error.

2.4 Character Data and Markup

Text consists of intermingled character data and markup. [Definition: Markup takes the form of start-tags, end-tags, empty-element tags, entity references, character +references, comments, CDATA section delimiters, document +type declarations, processing instructions, XML declarations, text declarations, +and any white space that is at the top level of the document entity (that +is, outside the document element and not inside any other markup).]

[Definition: All text that is not markup +constitutes the character data of the document.]

The ampersand character (&) and the left angle bracket (<) MUST NOT appear +in their literal form, except when used as markup delimiters, or +within a comment, a processing +instruction, or a CDATA section. + +If they are needed elsewhere, they MUST be escaped +using either numeric character references +or the strings "&amp;" and "&lt;" +respectively. The right angle bracket (>) MAY be represented using the string "&gt;", +and MUST, for compatibility, be escaped +using either "&gt;" or a character reference when it +appears in the string "]]>" in content, when +that string is not marking the end of a CDATA +section.

In the content of elements, character data is any string of characters +which does not contain the start-delimiter of any markup or the +CDATA-section-close delimiter, +"]]>". +In a CDATA section, +character data is any string of characters not including the CDATA-section-close +delimiter.

To allow attribute values to contain both single and double quotes, the +apostrophe or single-quote character (') MAY be represented as "&apos;", +and the double-quote character (") as "&quot;".

Character Data
[14]   CharData   ::=   [^<&]* - ([^<&]* ']]>' [^<&]*)

2.5 Comments

[Definition: Comments MAY appear +anywhere in a document outside other markup; +in addition, they MAY appear within the document type declaration at places +allowed by the grammar. They are not part of the document's character +data; an XML processor MAY, but need not, make it possible for an +application to retrieve the text of comments. For +compatibility, the string "--" (double-hyphen) +MUST NOT occur within comments.] Parameter +entity references MUST NOT be recognized within comments.

Comments
[15]   Comment   ::=   '<!--' ((Char - '-') | ('-' +(Char - '-')))* '-->'

An example of a comment:

<!-- declarations for <head> & <body> -->

Note +that the grammar does not allow a comment ending in --->. The +following example is not well-formed.

<!-- B+, B, or B--->

2.6 Processing Instructions

[Definition: Processing instructions +(PIs) allow documents to contain instructions for applications.]

Processing Instructions
[16]   PI   ::=   '<?' PITarget (S +(Char* - (Char* '?>' Char*)))? '?>'
[17]   PITarget   ::=   Name - (('X' | 'x') ('M' | +'m') ('L' | 'l'))

PIs are not part of the document's character +data, but MUST be passed through to the application. The PI begins +with a target (PITarget) used to identify the application +to which the instruction is directed. The target names "XML", "xml", +and so on are reserved for standardization in this or future versions of this +specification. The XML Notation mechanism +MAY be used for formal declaration of PI targets. Parameter +entity references MUST NOT be recognized within processing instructions.

2.7 CDATA Sections

[Definition: CDATA sections MAY occur anywhere character data may occur; they are used to escape blocks +of text containing characters which would otherwise be recognized as markup. +CDATA sections begin with the string "<![CDATA[" +and end with the string "]]>":]

CDATA Sections
[18]   CDSect   ::=   CDStart CData CDEnd
[19]   CDStart   ::=   '<![CDATA['
[20]   CData   ::=   (Char* - (Char* +']]>' Char*))
[21]   CDEnd   ::=   ']]>'

Within a CDATA section, only the CDEnd string is +recognized as markup, so that left angle brackets and ampersands may occur +in their literal form; they need not (and cannot) be escaped using "&lt;" +and "&amp;". CDATA sections cannot nest.

An example of a CDATA section, in which "<greeting>" +and "</greeting>" are recognized as character data, not markup:

<![CDATA[<greeting>Hello, world!</greeting>]]>

2.8 Prolog and Document Type Declaration

[Definition: XML 1.1 documents MUST +begin with an XML declaration which specifies the version of +XML being used.] For example, the following is a complete XML 1.1 document, well-formed but not valid:

<?xml version="1.1"?>
+<greeting>Hello, world!</greeting>

but the following is an XML 1.0 document because it +does not have an XML declaration:

<greeting>Hello, world!</greeting>

The function of the markup in an XML document is to describe its storage and +logical structure and to associate attribute +name-value pairs with its logical structures. XML provides a mechanism, the +document +type declaration, to define constraints on the logical structure +and to support the use of predefined storage units. [Definition: An XML document is valid if it has an associated +document type declaration and if the document complies with the constraints +expressed in it.]

The document type declaration MUST appear before the first element +in the document.

Prolog
[22]   prolog   ::=   XMLDecl Misc* +(doctypedecl Misc*)?
[23]   XMLDecl   ::=   '<?xml' VersionInfo EncodingDecl? SDDecl? S?'?>'
[24]   VersionInfo   ::=   S 'version' Eq +("'" VersionNum "'" | '"' VersionNum +'"')
[25]   Eq   ::=   S? '=' S?
[26]   VersionNum   ::=   '1.1'
[27]   Misc   ::=   Comment | PI +| S

[Definition: The XML document +type declaration contains or points to markup +declarations that provide a grammar for a class of documents. This +grammar is known as a document type definition, or DTD. The document +type declaration can point to an external subset (a special kind of external entity) containing markup declarations, +or can contain the markup declarations directly in an internal subset, or +can do both. The DTD for a document consists of both subsets taken together.]

[Definition: A markup declaration +is an element type declaration, an attribute-list declaration, an entity +declaration, or a notation declaration.] +These declarations MAY be contained in whole or in part within parameter +entities, as described in the well-formedness and validity constraints +below. For further +information, see 4 Physical Structures.

Document Type Definition
[28]   doctypedecl   ::=   '<!DOCTYPE' S Name +(S ExternalID)? S? +('[' intSubset ']' S?)? '>'[VC: Root Element Type]
[WFC: External Subset]
[28a]   DeclSep   ::=   PEReference | S[WFC: PE Between Declarations]
[28b]   intSubset   ::=   (markupdecl | DeclSep)*
[29]   markupdecl   ::=   elementdecl | AttlistDecl | EntityDecl +| NotationDecl | PI | Comment[VC: Proper Declaration/PE Nesting]
[WFC: PEs in Internal Subset]

Note +that it is possible to construct a well-formed document containing a doctypedecl +that neither points to an external subset nor contains an internal subset.

The markup declarations MAY be made up in whole or in part of the replacement text of parameter +entities. The productions later in this specification for individual +nonterminals (elementdecl, AttlistDecl, +and so on) describe the declarations after all the parameter +entities have been included.

Parameter +entity references are recognized anywhere in the DTD (internal and external +subsets and external parameter entities), except in literals, processing instructions, +comments, and the contents of ignored conditional sections (see 3.4 Conditional Sections). +They are also recognized in entity value literals. The use of parameter entities +in the internal subset is restricted as described below.

Validity constraint: Root Element Type

The Name +in the document type declaration MUST match the element type of the root element.

Validity constraint: Proper Declaration/PE Nesting

Parameter-entity replacement text MUST be properly nested with markup declarations. That is to say, if either +the first character or the last character of a markup declaration (markupdecl +above) is contained in the replacement text for a parameter-entity +reference, both MUST be contained in the same replacement text.

Well-formedness constraint: PEs in Internal Subset

In +the internal DTD subset, parameter-entity references MUST NOT occur within markup declarations; they MAY occur where markup declarations can occur. +(This does not apply to references that occur in external parameter entities +or to the external subset.)

Well-formedness constraint: External Subset

The external subset, if any, MUST match the production for extSubset.

Well-formedness constraint: PE Between Declarations

The replacement text of a parameter entity reference +in a DeclSep MUST match the production extSubsetDecl.

Like the internal subset, the external subset and any external parameter +entities referenced +in a DeclSep MUST consist of a series of +complete markup declarations of the types allowed by the non-terminal symbol markupdecl, interspersed with white space or parameter-entity references. However, portions of +the contents of the external subset or of these +external parameter entities MAY conditionally be ignored by using the conditional section construct; this is not +allowed in the internal subset but is +allowed in external parameter entities referenced in the internal subset.

External Subset
[30]   extSubset   ::=   TextDecl? extSubsetDecl
[31]   extSubsetDecl   ::=   ( markupdecl | conditionalSect | DeclSep)*

The external subset and external parameter entities also differ from the +internal subset in that in them, parameter-entity +references are permitted within markup declarations, +not only between markup declarations.

An example of an XML document with a document type declaration:

<?xml version="1.1"?>
+<!DOCTYPE greeting SYSTEM "hello.dtd">
+<greeting>Hello, world!</greeting>

The system identifier "hello.dtd" +gives the address (a URI reference) of a DTD for the document.

The declarations can also be given locally, as in this example:

<?xml version="1.1" encoding="UTF-8" ?>
+<!DOCTYPE greeting [
+<!ELEMENT greeting (#PCDATA)>
+]>
+<greeting>Hello, world!</greeting>

If both the external and internal subsets are used, the internal subset +MUST be considered to occur before the external subset. +This has the effect that entity and attribute-list declarations in the internal +subset take precedence over those in the external subset.

XML 1.1 processors SHOULD accept XML 1.0 +documents as well. If a document is well-formed or valid XML 1.0, and provided it +does not contain any control characters +in the range [#x7F-#x9F] other than as character escapes, it may be +made well-formed or valid XML 1.1 respectively simply by changing the +version number.

2.9 Standalone Document Declaration

Markup declarations can affect the content of the document, as passed from +an XML processor to an application; examples +are attribute defaults and entity declarations. The standalone document declaration, +which MAY appear as a component of the XML declaration, signals whether or +not there are such declarations which appear external to the document +entity +or in parameter entities. [Definition: An external +markup declaration is defined as a markup declaration occurring in +the external subset or in a parameter entity (external or internal, the latter +being included because non-validating processors are not required to read +them).]

Standalone Document Declaration
[32]   SDDecl   ::=   #x20+ 'standalone' Eq +(("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"')) [VC: Standalone Document Declaration]

In a standalone document declaration, the value "yes" indicates +that there are no external markup declarations which +affect the information passed from the XML processor to the application. The +value "no" indicates that there are or may be such external +markup declarations. Note that the standalone document declaration only denotes +the presence of external declarations; the presence, in a document, +of references to external entities, when those entities are internally +declared, does not change its standalone status.

If there are no external markup declarations, the standalone document declaration +has no meaning. If there are external markup declarations but there is no +standalone document declaration, the value "no" is assumed.

Any XML document for which standalone="no" holds can be converted +algorithmically to a standalone document, which may be desirable for some +network delivery applications.

Validity constraint: Standalone Document Declaration

The +standalone document declaration MUST have the value "no" if +any external markup declarations contain declarations of:

  • attributes with default values, +if elements to which these attributes apply appear in the document without +specifications of values for these attributes, or

  • entities (other than amp, +lt, +gt, +apos, +quot), if references +to those entities appear in the document, or

  • attributes with +tokenized types, where the +attribute appears in the document with a value such that +normalization +will produce a different value from that which would be produced +in the absence of the declaration, or

  • element types with element content, +if white space occurs directly within any instance of those types.

An example XML declaration with a standalone document declaration:

<?xml version="1.1" standalone='yes'?>

2.10 White Space Handling

In editing XML documents, it is often convenient to use "white space" +(spaces, tabs, and blank lines) +to set apart the markup for greater readability. Such white space is typically +not intended for inclusion in the delivered version of the document. On the +other hand, "significant" white space that should be preserved +in the delivered version is common, for example in poetry and source code.

An XML processor MUST always pass +all characters in a document that are not markup through to the application. +A validating XML processor MUST also +inform the application which of these characters constitute white space appearing +in element content.

A special attribute named xml:space MAY be attached to an element to signal an intention that in that element, +white space should be preserved by applications. In valid documents, this +attribute, like any other, MUST be declared +if it is used. When declared, it MUST be given as an enumerated +type whose values +are one or both of "default" and "preserve". +For example:

<!ATTLIST poem  xml:space (default|preserve) 'preserve'>
+<!ATTLIST pre xml:space (preserve) #FIXED 'preserve'>

The value "default" signals that applications' default white-space +processing modes are acceptable for this element; the value "preserve" +indicates the intent that applications preserve all the white space. This +declared intent is considered to apply to all elements within the content +of the element where it is specified, unless overridden with +another instance of the xml:space attribute. This specification does not give meaning to any value of xml:space other than "default" and "preserve". It is an error for other values to be specified; the XML processor MAY report the error or MAY recover by ignoring the attribute specification or by reporting the (erroneous) value to the application. Applications may ignore or reject erroneous values.

The root element of any document is considered +to have signaled no intentions as regards application space handling, unless +it provides a value for this attribute or the attribute is declared with a +default value.

2.11 End-of-Line Handling

XML parsed entities are often stored +in computer files which, for editing convenience, are organized into lines. +These lines are typically separated by some combination of the characters +CARRIAGE RETURN (#xD) and LINE FEED (#xA).

To +simplify the tasks of applications, the +XML +processor MUST behave as if it normalized all line breaks in external parsed +entities (including the document entity) on input, before parsing, by translating + +all of the following to a single #xA character:

  1. the two-character sequence #xD #xA

  2. the two-character sequence #xD #x85

  3. the single character #x85

  4. the single character #x2028

  5. any #xD character that is not immediately followed by #xA or #x85.

The characters #x85 and #x2028 cannot be reliably recognized and +translated until an entity's encoding declaration (if present) has +been read. Therefore, it is a fatal error to use them within the XML +declaration or text declaration. +

2.12 Language Identification

In document processing, it is often useful to identify the natural or formal +language in which the content is written. A special attribute +named xml:lang MAY be inserted in documents to specify the language +used in the contents and attribute values of any element in an XML document. +In valid documents, this attribute, like any other, MUST be declared +if it is used. The +values of the attribute are language identifiers as defined by [IETF RFC 3066], Tags +for the Identification of Languages, or its successor; in addition, the empty string MAY be specified.

(Productions 33 through 38 have been removed.)

For example:

<p xml:lang="en">The quick brown fox jumps over the lazy dog.</p>
+<p xml:lang="en-GB">What colour is it?</p>
+<p xml:lang="en-US">What color is it?</p>
+<sp who="Faust" desc='leise' xml:lang="de">
+<l>Habe nun, ach! Philosophie,</l>
+<l>Juristerei, und Medizin</l>
+<l>und leider auch Theologie</l>
+<l>durchaus studiert mit hei&#xDF;em Bem&#xFC;h'n.</l>
+</sp>

The intent declared with xml:lang is considered to apply to +all attributes and content of the element where it is specified, unless overridden +with an instance of xml:lang on another element within that content. In particular, the empty value of xml:lang is used on an element B to override a specification of xml:lang on an enclosing element A, without specifying another language. Within B, it is considered that there is no language information available, just as if xml:lang had not been specified on B or any of its ancestors.

Note:

Language information may also be provided by external transport protocols (e.g. HTTP or +MIME). When available, this information may be used by XML applications, but the more local +information provided by xml:lang should be considered to override it. +

A simple declaration for xml:lang might take the form

xml:lang CDATA #IMPLIED

but specific default values MAY also be given, if appropriate. In a collection +of French poems for English students, with glosses and notes in English, the xml:lang +attribute might be declared this way:

<!ATTLIST poem   xml:lang CDATA 'fr'>
+<!ATTLIST gloss  xml:lang CDATA 'en'>
+<!ATTLIST note   xml:lang CDATA 'en'>

2.13 Normalization Checking

All XML parsed +entities (including document +entities) SHOULD be fully +normalized as per the definition of +B Definitions for Character Normalization supplemented by the following definitions of +relevant constructs for XML:

  1. The +replacement text of all parsed +entities

  2. All text matching, in context, one of the following +productions:

    1. +CData

    2. +CharData

    3. +content

    4. Name

    5. +Nmtoken

However, a document is still well-formed even if it is not +fully normalized. +XML processors SHOULD provide a user option to verify that the document being +processed is in fully normalized form, and report to the application whether +it is or not. The option to not verify SHOULD be chosen only when the +input text is certified, +as defined by B Definitions for Character Normalization.

The verification of full normalization MUST be carried out as if by +first verifying that the entity is in include-normalized +form as defined by B Definitions for Character Normalization and by then verifying that none of the relevant +constructs listed above begins (after character references are +expanded) with a composing character as defined by +B Definitions for Character Normalization. +Non-validating processors MUST ignore possible +denormalizations that would be caused by inclusion of external +entities that they do not read.

Note:

The composing character are all +Unicode characters of non-zero combining class, plus a small number +of class-zero characters that nevertheless take part as a +non-initial character in certain Unicode canonical +decompositions. Since these characters are meant to follow +base characters, restricting relevant constructs (including +content) from beginning with a composing character does not +meaningfully diminish the expressiveness of XML.

If, while verifying full normalization, a processor encounters +characters for which it cannot determine the normalization +properties (i.e., characters introduced in a version of Unicode [Unicode] +later than the one used in the implementation of the processor), +then the processor MAY, at user option, ignore any possible +denormalizations caused by these characters. The option to ignore +those denormalizations SHOULD NOT be chosen by applications when +reliability or security are critical.

XML processors MUST NOT transform the input to be in +fully normalized form. +XML applications that create XML 1.1 output +from either XML 1.1 or XML 1.0 input SHOULD ensure that the output +is fully normalized; it is not necessary for internal processing +forms to be fully normalized.

The purpose of this section is to strongly encourage XML +processors to ensure that the creators of XML documents have +properly normalized them, so that XML applications can make tests +such as identity comparisons of strings without having to worry +about the different possible "spellings" of strings which +Unicode allows. +

When entities are in a non-Unicode encoding, if the processor +transcodes them to Unicode, it SHOULD use a normalizing transcoder. +

3 Logical Structures

[Definition: Each XML +document contains one or more elements, the boundaries +of which are either delimited by start-tags +and end-tags, or, for empty +elements, by an empty-element tag. Each +element has a type, identified by name, sometimes called its "generic +identifier" (GI), and MAY have a set of attribute specifications.] +Each attribute specification has a name +and a value.

Element
[39]   element   ::=   EmptyElemTag
| STag content ETag[WFC: Element Type Match]
[VC: Element Valid]

This specification does not constrain the semantics, use, or (beyond syntax) +names of the element types and attributes, except that names beginning with +a match to (('X'|'x')('M'|'m')('L'|'l')) are reserved for standardization +in this or future versions of this specification.

Well-formedness constraint: Element Type Match

The Name +in an element's end-tag MUST match the element type in the start-tag.

Validity constraint: Element Valid

An element is valid +if there is a declaration matching elementdecl +where the Name matches the element type, and one of +the following holds:

  1. The declaration matches EMPTY and the element has no content (not even entity +references, comments, PIs or white space).

  2. The declaration matches children and the +sequence of child elements belongs +to the language generated by the regular expression in the content model, +with optional white space, comments and +PIs (i.e. markup matching production [27] Misc) between the +start-tag and the first child element, between child elements, or between +the last child element and the end-tag. Note that a CDATA section containing +only white space or a reference +to an entity whose replacement text is character references expanding to white +space do not +match the nonterminal S, and +hence cannot appear in these positions; however, a +reference to an internal entity with a literal value consisting of character +references expanding to white space does match S, since its +replacement text is the white space resulting from expansion of the character +references.

  3. The declaration matches Mixed and the content +(after replacing +any entity references with their replacement text) consists of +character data, +comments, PIs and child elements whose types match names in the +content model.

  4. The declaration matches ANY, and the +content +(after replacing +any entity references with their replacement text) +consists of character data and child elements +whose types +have been declared.

3.1 Start-Tags, End-Tags, and Empty-Element Tags

[Definition: The beginning of every non-empty +XML element is marked by a start-tag.]

Start-tag
[40]   STag   ::=   '<' Name (S Attribute)* S? '>'[WFC: Unique Att Spec]
[41]   Attribute   ::=   Name Eq AttValue[VC: Attribute Value Type]
[WFC: No External Entity References]
[WFC: No < in Attribute Values]

The Name in the start- and end-tags gives the element's type. [Definition: The Name-AttValue +pairs are referred to as the attribute specifications of the +element], [Definition: with the Name in each pair referred to as the attribute name] +and [Definition: the content of the AttValue (the text between the ' or " +delimiters) as the attribute value.] Note +that the order of attribute specifications in a start-tag or empty-element +tag is not significant.

Well-formedness constraint: Unique Att Spec

An attribute name +MUST NOT appear more than once in the same start-tag or empty-element tag.

Validity constraint: Attribute Value Type

The attribute MUST +have been declared; the value MUST be of the type declared for it. (For attribute +types, see 3.3 Attribute-List Declarations.)

Well-formedness constraint: No External Entity References

Attribute +values MUST NOT contain direct or indirect entity references to external entities.

Well-formedness constraint: No < in Attribute Values

The replacement text of any entity +referred to directly or indirectly in an attribute value MUST NOT contain a <.

An example of a start-tag:

<termdef id="dt-dog" term="dog">

[Definition: The end of every element that begins +with a start-tag MUST be marked by an end-tag containing a name +that echoes the element's type as given in the start-tag:]

End-tag
[42]   ETag   ::=   '</' Name S? +'>'

An example of an end-tag:

</termdef>

[Definition: The text +between the start-tag and end-tag is called the element's content:]

Content of Elements
[43]   content   ::=   CharData? ((element +| Reference | CDSect +| PI | Comment) CharData?)*

[Definition: An element +with no content is said to be empty.] The representation +of an empty element is either a start-tag immediately followed by an end-tag, +or an empty-element tag. [Definition: An empty-element +tag takes a special form:]

Tags for Empty Elements
[44]   EmptyElemTag   ::=   '<' Name (S Attribute)* S? '/>'[WFC: Unique Att Spec]

Empty-element tags MAY be used for any element which has no content, whether +or not it is declared using the keyword EMPTY. For +interoperability, the empty-element tag SHOULD +be used, and SHOULD only be used, for elements which are declared +EMPTY.

Examples of empty elements:

<IMG align="left"
+src="http://www.w3.org/Icons/WWW/w3c_home" />
+<br></br>
+<br/>

3.2 Element Type Declarations

The element structure of an XML document MAY, for validation +purposes, be constrained using element type and attribute-list declarations. +An element type declaration constrains the element's content.

Element type declarations often constrain which element types can appear +as children of the element. At user +option, an XML processor MAY issue a warning when a declaration mentions an +element type for which no declaration is provided, but this is not an error.

[Definition: An element +type declaration takes the form:]

Element Type Declaration
[45]   elementdecl   ::=   '<!ELEMENT' S Name S contentspec S? +'>'[VC: Unique Element Type Declaration]
[46]   contentspec   ::=   'EMPTY' | 'ANY' | Mixed +| children

where the Name gives the element type being declared.

Validity constraint: Unique Element Type Declaration

An element +type MUST NOT be declared more than once.

Examples of element type declarations:

<!ELEMENT br EMPTY>
+<!ELEMENT p (#PCDATA|emph)* >
+<!ELEMENT %name.para; %content.para; >
+<!ELEMENT container ANY>

3.2.1 Element Content

[Definition: An element type has element content when elements +of that type MUST contain only child +elements (no character data), optionally separated by white space (characters +matching the nonterminal S).] [Definition: In this case, the constraint includes a content +model, a simple grammar governing the allowed types of the +child elements and the order in which they are allowed to appear.] +The grammar is built on content particles (cps), which +consist of names, choice lists of content particles, or sequence lists of +content particles:

Element-content Models
[47]   children   ::=   (choice | seq) +('?' | '*' | '+')?
[48]   cp   ::=   (Name | choice +| seq) ('?' | '*' | '+')?
[49]   choice   ::=   '(' S? cp ( S? '|' S? cp )+ S? ')'[VC: Proper Group/PE Nesting]
[50]   seq   ::=   '(' S? cp ( S? ',' S? cp )* S? ')'[VC: Proper Group/PE Nesting]

where each Name is the type of an element which +MAY appear as a child. Any content +particle in a choice list MAY appear in the element +content at the location where the choice list appears in the grammar; +content particles occurring in a sequence list MUST each appear in the element content in the order given in the list. +The optional character following a name or list governs whether the element +or the content particles in the list may occur one or more (+), +zero or more (*), or zero or one times (?). The +absence of such an operator means that the element or content particle MUST +appear exactly once. This syntax and meaning are identical to those used in +the productions in this specification.

The content of an element matches a content model if and only if it is +possible to trace out a path through the content model, obeying the sequence, +choice, and repetition operators and matching each element in the content +against an element type in the content model. For +compatibility, it is an error if the content model +allows an element to match more than one occurrence of an element type in the +content model. For more information, see D Deterministic Content Models.

Validity constraint: Proper Group/PE Nesting

Parameter-entity replacement text MUST be properly nested with parenthesized +groups. That is to say, if either of the opening or closing parentheses in +a choice, seq, or Mixed +construct is contained in the replacement text for a parameter +entity, both MUST be contained in the same replacement text.

For interoperability, if a parameter-entity reference +appears in a choice, seq, or Mixed construct, its replacement text SHOULD contain at +least one non-blank character, and neither the first nor last non-blank character +of the replacement text SHOULD be a connector (| or ,).

Examples of element-content models:

<!ELEMENT spec (front, body, back?)>
+<!ELEMENT div1 (head, (p | list | note)*, div2*)>
+<!ELEMENT dictionary-body (%div.mix; | %dict.mix;)*>

3.2.2 Mixed Content

[Definition: An element type +has mixed content when elements of that type MAY contain character +data, optionally interspersed with child +elements.] In this case, the types of the child elements MAY be constrained, +but not their order or their number of occurrences:

Mixed-content Declaration
[51]   Mixed   ::=   '(' S? '#PCDATA' (S? +'|' S? Name)* S? +')*'
| '(' S? '#PCDATA' S? ')' [VC: Proper Group/PE Nesting]
[VC: No Duplicate Types]

where the Names give the types of elements that +may appear as children. The +keyword #PCDATA derives historically from the term "parsed +character data."

Validity constraint: No Duplicate Types

The +same name MUST NOT appear more than once in a single mixed-content declaration.

Examples of mixed content declarations:

<!ELEMENT p (#PCDATA|a|ul|b|i|em)*>
+<!ELEMENT p (#PCDATA | %font; | %phrase; | %special; | %form;)* >
+<!ELEMENT b (#PCDATA)>

3.3 Attribute-List Declarations

Attributes are used to associate name-value +pairs with elements. Attribute specifications +MUST NOT appear outside of start-tags and empty-element tags; thus, the productions used to +recognize them appear in 3.1 Start-Tags, End-Tags, and Empty-Element Tags. Attribute-list declarations +MAY be used:

  • To define the set of attributes pertaining to a given element type.

  • To establish type constraints for these attributes.

  • To provide default values for +attributes.

[Definition: Attribute-list +declarations specify the name, data type, and default value (if any) +of each attribute associated with a given element type:]

Attribute-list Declaration
[52]   AttlistDecl   ::=   '<!ATTLIST' S Name AttDef* S? '>'
[53]   AttDef   ::=   S Name S AttType S DefaultDecl

The Name in the AttlistDecl +rule is the type of an element. At user option, an XML processor MAY issue +a warning if attributes are declared for an element type not itself declared, +but this is not an error. The Name in the AttDef +rule is the name of the attribute.

When more than one AttlistDecl is provided +for a given element type, the contents of all those provided are merged. When +more than one definition is provided for the same attribute of a given element +type, the first declaration is binding and later declarations are ignored. For interoperability, writers of DTDs MAY choose +to provide at most one attribute-list declaration for a given element type, +at most one attribute definition for a given attribute name in an attribute-list +declaration, and at least one attribute definition in each attribute-list +declaration. For interoperability, an XML processor MAY at user option +issue a warning when more than one attribute-list declaration is provided +for a given element type, or more than one attribute definition is provided +for a given attribute, but this is not an error.

3.3.1 Attribute Types

XML attribute types are of three kinds: a string type, a set of tokenized +types, and enumerated types. The string type may take any literal string as +a value; the tokenized types have varying lexical and semantic constraints. +The validity constraints noted in the grammar are applied after the attribute +value has been normalized as described in 3.3.3 Attribute-Value Normalization.

Attribute Types
[54]   AttType   ::=   StringType | TokenizedType +| EnumeratedType
[55]   StringType   ::=   'CDATA'
[56]   TokenizedType   ::=   'ID'[VC: ID]
[VC: One ID per Element Type]
[VC: ID Attribute Default]
| 'IDREF'[VC: IDREF]
| 'IDREFS'[VC: IDREF]
| 'ENTITY'[VC: Entity Name]
| 'ENTITIES'[VC: Entity Name]
| 'NMTOKEN'[VC: Name Token]
| 'NMTOKENS'[VC: Name Token]

Validity constraint: ID

Values of type ID MUST match the Name production. A name MUST NOT appear more than once +in an XML document as a value of this type; i.e., ID values MUST uniquely +identify the elements which bear them.

Validity constraint: One ID per Element Type

An element +type MUST NOT have more than one ID attribute specified.

Validity constraint: ID Attribute Default

An ID attribute +MUST have a declared default of #IMPLIED or #REQUIRED.

Validity constraint: IDREF

Values of type IDREF MUST +match the Name production, and values of type IDREFS MUST match Names; each Name MUST match the value of an ID attribute on some element in the XML document; +i.e. IDREF values MUST match the value of some ID attribute.

Validity constraint: Entity Name

Values of type ENTITY MUST match the Name production, values of type ENTITIES MUST match Names; each Name MUST match the name of an unparsed entity +declared in the DTD.

Validity constraint: Name Token

Values of type NMTOKEN MUST match the Nmtoken production; values of type NMTOKENS MUST match Nmtokens.

[Definition: Enumerated attributes MUST take one of a list of values +provided in the declaration]. There are two kinds of enumerated types:

Enumerated Attribute Types
[57]   EnumeratedType   ::=   NotationType +| Enumeration
[58]   NotationType   ::=   'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')' [VC: Notation Attributes]
[VC: One Notation Per Element Type]
[VC: No Notation on Empty Element]
[VC: No Duplicate +Tokens]
[59]   Enumeration   ::=   '(' S? Nmtoken +(S? '|' S? Nmtoken)* S? ')'[VC: Enumeration]
[VC: No Duplicate +Tokens]

A NOTATION attribute identifies a notation, +declared in the DTD with associated system and/or public identifiers, to be +used in interpreting the element to which the attribute is attached.

Validity constraint: Notation Attributes

Values of this type +MUST match one of the notation names +included in the declaration; all notation names in the declaration MUST be +declared.

Validity constraint: One Notation Per Element Type

An element type MUST NOT have more than one NOTATION +attribute specified.

Validity constraint: No Notation on Empty Element

For compatibility, +an attribute of type NOTATION MUST NOT be declared on an element +declared EMPTY.

Validity constraint: No Duplicate +Tokens

The notation names in a single NotationType +attribute declaration, as well as the NmTokens in a single +Enumeration attribute declaration, MUST all be distinct.

Validity constraint: Enumeration

Values of this type MUST match +one of the Nmtoken tokens in the declaration.

For interoperability, the same Nmtoken SHOULD NOT occur more than once in the enumerated +attribute types of a single element type.

3.3.2 Attribute Defaults

An attribute declaration provides information +on whether the attribute's presence is REQUIRED, and if not, how an XML processor +is +to react if a declared attribute is absent in a document.

Attribute Defaults
[60]   DefaultDecl   ::=   '#REQUIRED' | '#IMPLIED'
| (('#FIXED' S)? AttValue)[VC: Required Attribute]
[VC: Attribute +Default Value Syntactically Correct]
[WFC: No < in Attribute Values]
[VC: Fixed Attribute Default]

In an attribute declaration, #REQUIRED means that the attribute +MUST always be provided, #IMPLIED that no default value is provided. +[Definition: If +the declaration is neither #REQUIRED nor #IMPLIED, then +the AttValue value contains the declared default +value; the #FIXED keyword states that the attribute MUST always have +the default value. +When an XML processor encounters +an element +without a specification for an attribute for which it has read a default +value declaration, it MUST report the attribute with the declared default +value to the application.]

Validity constraint: Required Attribute

If the default +declaration is the keyword #REQUIRED, then the attribute MUST be +specified for all elements of the type in the attribute-list declaration.

Validity constraint: Attribute +Default Value Syntactically Correct

The declared default value MUST meet the syntactic +constraints of the declared attribute type.

Note that only the +syntactic constraints of the type are required here; other constraints (e.g. +that the value be the name of a declared unparsed entity, for an attribute of +type ENTITY) may come into play if the declared default value is actually used +(an element without a specification for this attribute occurs).

Validity constraint: Fixed Attribute Default

If an attribute +has a default value declared with the #FIXED keyword, instances of +that attribute MUST match the default value.

Examples of attribute-list declarations:

<!ATTLIST termdef
+id      ID      #REQUIRED
+name    CDATA   #IMPLIED>
+<!ATTLIST list
+type    (bullets|ordered|glossary)  "ordered">
+<!ATTLIST form
+method  CDATA   #FIXED "POST">

3.3.3 Attribute-Value Normalization

Before the value of an attribute is passed to the application or checked +for validity, the XML processor MUST normalize the attribute value by applying +the algorithm below, or by using some other method such that the value passed +to the application is the same as that produced by the algorithm.

  1. All line breaks MUST have been normalized on input to #xA as described +in 2.11 End-of-Line Handling, so the rest of this algorithm operates +on text normalized in this way.

  2. Begin with a normalized value consisting of the empty string.

  3. For each character, entity reference, or character reference in the +unnormalized attribute value, beginning with the first and continuing to the +last, do the following:

    • For a character reference, append the referenced character to the +normalized value.

    • For an entity reference, recursively apply step 3 of this algorithm +to the replacement text of the entity.

    • For a white space character (#x20, #xD, #xA, #x9), append a space +character (#x20) to the normalized value.

    • For another character, append the character to the normalized value.

If the attribute type is not CDATA, then the XML processor MUST further +process the normalized attribute value by discarding any leading and trailing +space (#x20) characters, and by replacing sequences of space (#x20) characters +by a single space (#x20) character.

Note that if the unnormalized attribute value contains a character reference +to a white space character other than space (#x20), the normalized value contains +the referenced character itself (#xD, #xA or #x9). This contrasts with the +case where the unnormalized value contains a white space character (not a +reference), which is replaced with a space character (#x20) in the normalized +value and also contrasts with the case where the unnormalized value contains +an entity reference whose replacement text contains a white space character; +being recursively processed, the white space character is replaced with a +space character (#x20) in the normalized value.

All attributes for which no declaration has been read SHOULD be treated +by a non-validating processor as if declared CDATA.

It +is an error if an +attribute +value contains a reference to an +entity for which no declaration has been read.

Following are examples of attribute normalization. Given the following +declarations:

<!ENTITY d "&#xD;">
+<!ENTITY a "&#xA;">
+<!ENTITY da "&#xD;&#xA;">

the attribute specifications in the left column below would be normalized +to the character sequences of the middle column if the attribute a +is declared NMTOKENS and to those of the right columns if a +is declared CDATA.

Attribute specificationa is NMTOKENSa is CDATA
a="
+xyz"
x y z
#x20 #x20 x y z
a="&d;&d;A&a;&#x20;&a;B&da;"
A #x20 B
#x20 #x20 A #x20 #x20 #x20 B #x20 #x20
a=
+"&#xd;&#xd;A&#xa;&#xa;B&#xd;&#xa;"
#xD #xD A #xA #xA B #xD #xA
#xD #xD A #xA #xA B #xD #xA

Note that the last example is invalid (but well-formed) if a +is declared to be of type NMTOKENS.

3.4 Conditional Sections

[Definition: Conditional +sections are portions of the document type +declaration external subset or +of external parameter entities which are included in, or excluded from, +the logical structure of the DTD based on the keyword which governs them.]

Conditional Section
[61]   conditionalSect   ::=   includeSect | ignoreSect
[62]   includeSect   ::=   '<![' S? 'INCLUDE' S? '[' extSubsetDecl +']]>' [VC: Proper Conditional Section/PE Nesting]
[63]   ignoreSect   ::=   '<![' S? 'IGNORE' S? '[' ignoreSectContents* +']]>'[VC: Proper Conditional Section/PE Nesting]
[64]   ignoreSectContents   ::=   Ignore ('<![' ignoreSectContents ']]>' Ignore)*
[65]   Ignore   ::=   Char* - (Char* +('<![' | ']]>') Char*)

Validity constraint: Proper Conditional Section/PE Nesting

If any of the "<![", +"[", or "]]>" of a conditional section is contained +in the replacement text for a parameter-entity reference, all of them MUST +be contained in the same replacement text.

Like the internal and external DTD subsets, a conditional section may contain +one or more complete declarations, comments, processing instructions, or nested +conditional sections, intermingled with white space.

If the keyword of the conditional section is INCLUDE, then the +contents of the conditional section MUST be considered part of the DTD. If the keyword of +the conditional section is IGNORE, then the contents of the conditional +section MUST be considered as not logically part of the DTD. +If a conditional section with a keyword of INCLUDE occurs within +a larger conditional section with a keyword of IGNORE, both the outer +and the inner conditional sections MUST be ignored. The contents +of an ignored conditional section MUST be parsed by ignoring all characters after +the "[" following the keyword, except conditional section starts +"<![" and ends "]]>", until the matching conditional +section end is found. Parameter entity references MUST NOT be recognized in this +process.

If the keyword of the conditional section is a parameter-entity reference, +the parameter entity MUST be replaced by its content before the processor +decides whether to include or ignore the conditional section.

An example:

<!ENTITY % draft 'INCLUDE' >
+<!ENTITY % final 'IGNORE' >
+<![%draft;[
+<!ELEMENT book (comments*, title, body, supplements?)>
+]]>
+<![%final;[
+<!ELEMENT book (title, body, supplements?)>
+]]>

4 Physical Structures

[Definition: An XML document may consist of one +or many storage units. These +are called entities; they all have content and are +all (except for the document entity and +the external DTD subset) identified by +entity name.] Each XML document has one entity +called the document entity, which serves +as the starting point for the XML processor +and may contain the whole document.

Entities may be either parsed or unparsed. [Definition: The contents of a parsed +entity are referred to as its replacement +text; this text is considered an +integral part of the document.]

[Definition: An unparsed entity +is a resource whose contents may or may not be text, +and if text, may +be other than XML. Each unparsed entity has an associated notation, identified by name. Beyond a requirement +that an XML processor make the identifiers for the entity and notation available +to the application, XML places no constraints on the contents of unparsed +entities.]

Parsed entities are invoked by name using entity references; unparsed entities +by name, given in the value of ENTITY or ENTITIES attributes.

[Definition: General entities +are entities for use within the document content. In this specification, general +entities are sometimes referred to with the unqualified term entity +when this leads to no ambiguity.] [Definition: Parameter +entities are parsed entities for use within the DTD.] +These two types of entities use different forms of reference and are recognized +in different contexts. Furthermore, they occupy different namespaces; a parameter +entity and a general entity with the same name are two distinct entities.

4.1 Character and Entity References

[Definition: A character +reference refers to a specific character in the ISO/IEC 10646 character +set, for example one not directly accessible from available input devices.]

Character Reference
[66]   CharRef   ::=   '&#' [0-9]+ ';'
| '&#x' [0-9a-fA-F]+ ';'[WFC: Legal Character]

Well-formedness constraint: Legal Character

Characters referred +to using character references MUST match the production for Char.

If the character reference begins with "&#x", +the digits and letters up to the terminating ; provide a hexadecimal +representation of the character's code point in ISO/IEC 10646. If it begins +just with "&#", the digits up to the terminating ; +provide a decimal representation of the character's code point.

[Definition: An entity reference +refers to the content of a named entity.] [Definition: References to parsed general entities use +ampersand (&) and semicolon (;) as delimiters.] [Definition: Parameter-entity references +use percent-sign (%) and semicolon (;) as delimiters.]

Entity Reference
[67]   Reference   ::=   EntityRef | CharRef
[68]   EntityRef   ::=   '&' Name ';'[WFC: Entity Declared]
[VC: Entity Declared]
[WFC: Parsed Entity]
[WFC: No Recursion]
[69]   PEReference   ::=   '%' Name ';'[VC: Entity Declared]
[WFC: No Recursion]
[WFC: In DTD]

Well-formedness constraint: Entity Declared

In a document +without any DTD, a document with only an internal DTD subset which contains +no parameter entity references, or a document with "standalone='yes'", for +an entity reference that does not occur within the external subset or a parameter +entity, the Name given in the entity reference MUST match that in an entity +declaration that does not occur within the external subset or a +parameter entity, except that well-formed documents need not declare +any of the following entities: amp, +lt, +gt, +apos, +quot. The +declaration of a general entity MUST precede any reference to it which appears +in a default value in an attribute-list declaration.

Note +that non-validating processors are not +obligated to to read and process entity declarations occurring in parameter entities or in +the external subset; for such documents, +the rule that an entity must be declared is a well-formedness constraint only +if standalone='yes'.

Validity constraint: Entity Declared

In a document with +an external subset or external parameter entities with "standalone='no'", +the Name given in the entity reference MUST match that in an entity +declaration. For interoperability, valid documents SHOULD declare +the entities amp, +lt, +gt, +apos, +quot, in the form specified in 4.6 Predefined Entities. +The declaration of a parameter entity MUST precede any reference to it. Similarly, +the declaration of a general entity MUST precede any attribute-list +declaration containing a default value with a direct or indirect reference +to that general entity.

Well-formedness constraint: Parsed Entity

An entity reference MUST +NOT contain the name of an unparsed entity. +Unparsed entities may be referred to only in attribute +values declared to be of type ENTITY or ENTITIES.

Well-formedness constraint: No Recursion

A parsed entity MUST NOT contain a recursive reference to itself, either directly or indirectly.

Well-formedness constraint: In DTD

Parameter-entity references MUST NOT appear outside +the DTD.

Examples of character and entity references:

Type <key>less-than</key> (&#x3C;) to save options.
+This document was prepared on &docdate; and
+is classified &security-level;.

Example of a parameter-entity reference:

<!-- declare the parameter entity "ISOLat2"... -->
+<!ENTITY % ISOLat2
+SYSTEM "http://www.xml.com/iso/isolat2-xml.entities" >
+<!-- ... now reference it. -->
+%ISOLat2;

4.2 Entity Declarations

[Definition: Entities are declared +thus:]

Entity Declaration
[70]   EntityDecl   ::=   GEDecl | PEDecl
[71]   GEDecl   ::=   '<!ENTITY' S Name S EntityDef S? +'>'
[72]   PEDecl   ::=   '<!ENTITY' S '%' S Name S PEDef S? '>'
[73]   EntityDef   ::=   EntityValue| (ExternalID NDataDecl?)
[74]   PEDef   ::=   EntityValue | ExternalID

The Name identifies the entity in an entity +reference or, in the case of an unparsed entity, in the value of +an ENTITY or ENTITIES attribute. If the same entity is declared +more than once, the first declaration encountered is binding; at user option, +an XML processor MAY issue a warning if entities are declared multiple times.

4.2.1 Internal Entities

[Definition: If the +entity definition is an EntityValue, the defined +entity is called an internal entity. There is no separate physical +storage object, and the content of the entity is given in the declaration.] +Note that some processing of entity and character references in the literal entity value may be required to produce +the correct replacement text: see 4.5 Construction of Entity Replacement Text.

An internal entity is a parsed entity.

Example of an internal entity declaration:

<!ENTITY Pub-Status "This is a pre-release of the
+specification.">

4.2.2 External Entities

[Definition: If the entity is not internal, +it is an external entity, declared as follows:]

External Entity Declaration
[75]   ExternalID   ::=   'SYSTEM' S SystemLiteral
| 'PUBLIC' S PubidLiteral S SystemLiteral
[76]   NDataDecl   ::=   S 'NDATA' S Name[VC: Notation Declared]

If the NDataDecl is present, this is a general unparsed entity; otherwise it is a parsed entity.

Validity constraint: Notation Declared

The Name MUST match the declared name of a notation.

[Definition: The SystemLiteral is called the entity's system +identifier. It is meant to be +converted to a URI reference +(as defined in [IETF RFC 2396], updated by [IETF RFC 2732]), +as part of the +process of dereferencing it to obtain input for the XML processor to construct the +entity's replacement text.] It is an error for a fragment identifier +(beginning with a # character) to be part of a system identifier. +Unless otherwise provided by information outside the scope of this specification +(e.g. a special XML element type defined by a particular DTD, or a processing +instruction defined by a particular application specification), relative URIs +are relative to the location of the resource within which the entity declaration +occurs. This is defined to +be the external entity containing the '<' which starts the declaration, at the +point when it is parsed as a declaration. +A URI might thus be relative to the document +entity, to the entity containing the external +DTD subset, or to some other external parameter +entity. Attempts to +retrieve the resource identified by a URI MAY be redirected at the parser +level (for example, in an entity resolver) or below (at the protocol level, +for example, via an HTTP Location: header). In the absence of additional +information outside the scope of this specification within the resource, +the base URI of a resource is always the URI of the actual resource returned. +In other words, it is the URI of the resource retrieved after all redirection +has occurred.

System +identifiers (and other XML strings meant to be used as URI references) MAY contain +characters that, according to [IETF RFC 2396] and [IETF RFC 2732], +must be escaped before a URI can be used to retrieve the referenced resource. The +characters to be escaped are the control characters #x0 to #x1F and #x7F (most of +which cannot appear in XML), space #x20, the delimiters '<' #x3C, '>' #x3E and +'"' #x22, the unwise characters '{' #x7B, '}' #x7D, '|' #x7C, '\' #x5C, '^' #x5E and +'`' #x60, as well as all characters above #x7F. Since escaping is not always a fully +reversible process, it MUST be performed only when absolutely necessary and as late +as possible in a processing chain. In particular, neither the process of converting +a relative URI to an absolute one nor the process of passing a URI reference to a +process or software component responsible for dereferencing it SHOULD trigger escaping. +When escaping does occur, it MUST be performed as follows:

  1. Each +character to be escaped +is represented in +UTF-8 [Unicode] +as one or more bytes.

  2. The resulting bytes +are escaped with +the URI escaping mechanism (that is, converted to %HH, +where HH is the hexadecimal notation of the byte value).

  3. The original character is replaced by the resulting character sequence.

[Definition: In addition to a system +identifier, an external identifier MAY include a public identifier.] +An XML processor attempting to retrieve the entity's content MAY use +any combination of +the public and system identifiers as well as additional information outside the +scope of this specification to try to generate an alternative URI reference. +If the processor is unable to do so, it MUST use the URI +reference specified in the system literal. Before a match is attempted, +all strings of white space in the public identifier MUST be normalized to +single space characters (#x20), and leading and trailing white space MUST +be removed.

Examples of external entity declarations:

<!ENTITY open-hatch
+SYSTEM "http://www.textuality.com/boilerplate/OpenHatch.xml">
+<!ENTITY open-hatch
+PUBLIC "-//Textuality//TEXT Standard open-hatch boilerplate//EN"
+"http://www.textuality.com/boilerplate/OpenHatch.xml">
+<!ENTITY hatch-pic
+SYSTEM "../grafix/OpenHatch.gif"
+NDATA gif >

4.3 Parsed Entities

4.3.1 The Text Declaration

External parsed entities SHOULD each begin with a text declaration.

Text Declaration
[77]   TextDecl   ::=   '<?xml' VersionInfo? EncodingDecl S? '?>'

The text declaration MUST be provided literally, not by reference +to a parsed entity. The text declaration +MUST NOT appear at any +position other than the beginning of an external parsed entity. The text declaration +in an external parsed entity is not considered part of its replacement text.

4.3.2 Well-Formed Parsed Entities

The document entity is well-formed if it matches the production labeled document. An external general parsed entity is well-formed +if it matches the production labeled extParsedEnt. All +external parameter entities are well-formed by definition.

Well-Formed External Parsed Entity
[78]   extParsedEnt   ::=   TextDecl? content - Char* RestrictedChar Char*

An internal general parsed entity is well-formed if its replacement text +matches the production labeled content. All internal +parameter entities are well-formed by definition.

A consequence of well-formedness in general +entities is that the logical and physical +structures in an XML document are properly nested; no start-tag, end-tag, empty-element tag, element, comment, processing instruction, character +reference, or entity reference +can begin in one entity and end in another.

4.3.3 Character Encoding in Entities

Each external parsed entity in an XML document MAY use a different encoding +for its characters. All XML processors MUST be able to read entities in both +the UTF-8 and UTF-16 encodings. The terms "UTF-8" +and "UTF-16" in this specification do not apply to character +encodings with any other labels, even if the encodings or labels are very +similar to UTF-8 or UTF-16.

Entities encoded in UTF-16 MUST and entities +encoded in UTF-8 MAY begin with the Byte Order Mark described in +ISO/IEC 10646 [ISO/IEC 10646] or Unicode [Unicode] +(the ZERO WIDTH NO-BREAK SPACE character, #xFEFF). This is an encoding signature, +not part of either the markup or the character data of the XML document. XML +processors MUST be able to use this character to differentiate between UTF-8 +and UTF-16 encoded documents.

Although an XML processor is required to read only entities in the UTF-8 +and UTF-16 encodings, it is recognized that other encodings are used around +the world, and it may be desired for XML processors to read entities that +use them. In +the absence of external character encoding information (such as MIME headers), +parsed entities which are stored in an encoding other than UTF-8 or UTF-16 +MUST begin with a text declaration (see 4.3.1 The Text Declaration) containing +an encoding declaration:

Encoding Declaration
[80]   EncodingDecl   ::=   S 'encoding' Eq +('"' EncName '"' | "'" EncName +"'" )
[81]   EncName   ::=   [A-Za-z] ([A-Za-z0-9._] | '-')*/* Encoding +name contains only Latin characters */

In the document entity, the encoding +declaration is part of the XML declaration. +The EncName is the name of the encoding used.

In an encoding declaration, the values "UTF-8", "UTF-16", +"ISO-10646-UCS-2", and "ISO-10646-UCS-4" SHOULD be used +for the various encodings and transformations of Unicode / ISO/IEC 10646, +the values "ISO-8859-1", "ISO-8859-2", +... "ISO-8859-n" (where n +is the part number) SHOULD be used for the parts of ISO 8859, and +the values "ISO-2022-JP", "Shift_JIS", +and "EUC-JP" SHOULD be used for the various encoded +forms of JIS X-0208-1997. It +is RECOMMENDED that character encodings registered (as charsets) +with the Internet Assigned Numbers Authority [IANA-CHARSETS], +other than those just listed, be referred to using their registered names; +other encodings SHOULD use names starting with an "x-" prefix. +XML processors SHOULD match character encoding names in a case-insensitive +way and SHOULD either interpret an IANA-registered name as the encoding registered +at IANA for that name or treat it as unknown (processors are, of course, not +required to support all IANA-registered encodings).

In the absence of information provided by an external transport protocol +(e.g. HTTP or MIME), it is a fatal error for +an entity including an encoding declaration to be presented to the XML processor +in an encoding other than that named in the declaration, or for an entity which +begins with neither a Byte Order Mark +nor an encoding declaration to use an encoding other than UTF-8. Note that +since ASCII is a subset of UTF-8, ordinary ASCII entities do not strictly +need an encoding declaration.

It is a fatal error for a TextDecl to occur other +than at the beginning of an external entity.

It is a fatal error when an XML processor +encounters an entity with an encoding that it is unable to process. It +is a fatal error if an XML entity is determined (via default, encoding declaration, +or higher-level protocol) to be in a certain encoding but contains byte +sequences that are not legal in that encoding. Specifically, it is a +fatal error if an entity encoded in UTF-8 contains any irregular code unit sequences, +as defined in Unicode [Unicode]. Unless an encoding +is determined by a higher-level protocol, it is also a fatal error if an XML entity +contains no encoding declaration and its content is not legal UTF-8 or UTF-16.

Examples of text declarations containing encoding declarations:

<?xml encoding='UTF-8'?>
+<?xml encoding='EUC-JP'?>

4.3.4 Version Information in Entities

Each entity, including the document entity, +can be separately +declared as XML 1.0 or XML 1.1. The version declaration appearing +in the document entity determines the version of the document as a +whole. An XML 1.1 document may invoke XML 1.0 external entities, so +that otherwise duplicated versions of external entities, +particularly DTD external subsets, need not be maintained. However, +in such a case the rules of XML 1.1 are applied to the entire +document.

If an entity (including the document entity) is not labeled +with a version number, it is treated as if labeled as version +1.0.

4.4 XML Processor Treatment of Entities and References

The table below summarizes the contexts in which character references, +entity references, and invocations of unparsed entities might appear and the +REQUIRED behavior of an XML processor +in each case. The labels in the leftmost column describe the recognition context:

Reference in Content

as a reference anywhere after the start-tag +and before the end-tag of an element; corresponds +to the nonterminal content.

Reference in Attribute Value

as a reference within either the value of an attribute in a start-tag, +or a default value in an attribute declaration; +corresponds to the nonterminal AttValue.

Occurs as Attribute Value

as a Name, not a reference, appearing either as +the value of an attribute which has been declared as type ENTITY, +or as one of the space-separated tokens in the value of an attribute which +has been declared as type ENTITIES.

Reference in Entity Value

as a reference within a parameter or internal entity's literal +entity value in the entity's declaration; corresponds to the nonterminal EntityValue.

Reference in DTD

as a reference within either the internal or external subsets of the DTD, but outside of an EntityValue, AttValue, PI, Comment, SystemLiteral, PubidLiteral, +or the contents of an ignored conditional section (see 3.4 Conditional Sections).

.

Entity +TypeCharacter
ParameterInternal GeneralExternal Parsed +GeneralUnparsed
Reference +in ContentNot recognizedIncludedIncluded +if validatingForbiddenIncluded
Reference in Attribute ValueNot recognizedIncluded +in literalForbiddenForbiddenIncluded
Occurs as Attribute +ValueNot recognizedForbiddenForbiddenNotifyNot recognized
Reference in EntityValueIncluded in literalBypassedBypassedErrorIncluded
Reference in DTDIncluded as PEForbiddenForbiddenForbiddenForbidden

4.4.1 Not Recognized

Outside the DTD, the % character has no special significance; +thus, what would be parameter entity references in the DTD are not recognized +as markup in content. Similarly, the names of unparsed +entities are not recognized except when they appear in the value of an appropriately +declared attribute.

4.4.2 Included

[Definition: An entity is included +when its replacement text is retrieved +and processed, in place of the reference itself, as though it were part of +the document at the location the reference was recognized.] The replacement +text MAY contain both character data +and (except for parameter entities) markup, +which MUST be recognized in the usual way. (The string "AT&amp;T;" +expands to "AT&T;" and the remaining ampersand +is not recognized as an entity-reference delimiter.) A character reference +is included when the indicated character is processed in place +of the reference itself.

4.4.3 Included If Validating

When an XML processor recognizes a reference to a parsed entity, in order +to validate the document, the processor +MUST include its replacement text. If +the entity is external, and the processor is not attempting to validate the +XML document, the processor MAY, but need +not, include the entity's replacement text. If a non-validating processor +does not include the replacement text, it MUST inform the application that +it recognized, but did not read, the entity.

This rule is based on the recognition that the automatic inclusion provided +by the SGML and XML entity mechanism, primarily designed to support modularity +in authoring, is not necessarily appropriate for other applications, in particular +document browsing. Browsers, for example, when encountering an external parsed +entity reference, might choose to provide a visual indication of the entity's +presence and retrieve it for display only on demand.

4.4.4 Forbidden

The following are forbidden, and constitute fatal +errors:

  • the appearance of a reference to an unparsed +entity, except in the +EntityValue in an entity declaration.

  • the appearance of any character or general-entity reference in the +DTD except within an EntityValue or AttValue.

  • a reference to an external entity in an attribute value.

4.4.5 Included in Literal

When an entity reference appears in +an attribute value, or a parameter entity reference appears in a literal entity +value, its replacement text MUST be processed +in place of the reference itself as though it were part of the document at +the location the reference was recognized, except that a single or double +quote character in the replacement text MUST always be treated as a normal data +character and MUST NOT terminate the literal. For example, this is well-formed:

<!ENTITY % YN '"Yes"' >
+<!ENTITY WhatHeSaid "He said %YN;" >

while this is not:

<!ENTITY EndAttr "27'" >
+<element attribute='a-&EndAttr;>

4.4.6 Notify

When the name of an unparsed entity +appears as a token in the value of an attribute of declared type ENTITY +or ENTITIES, a validating processor MUST inform the application of +the system and public +(if any) identifiers for both the entity and its associated notation.

4.4.7 Bypassed

When a general entity reference appears in the EntityValue +in an entity declaration, it MUST be bypassed and left as is.

4.4.8 Included as PE

Just as with external parsed entities, parameter entities need only be included if validating. When a parameter-entity +reference is recognized in the DTD and included, its replacement +text MUST be enlarged by the attachment of one leading and one following +space (#x20) character; the intent is to constrain the replacement text of +parameter entities to contain an integral number of grammatical tokens in +the DTD. This +behavior MUST NOT apply to parameter entity references within entity values; +these are described in 4.4.5 Included in Literal.

4.4.9 Error

It is an error for a reference to +an unparsed entity to appear in the EntityValue in an +entity declaration.

4.5 Construction of Entity Replacement Text

In discussing the treatment of entities, it is useful to distinguish +two forms of the entity's value. +[Definition: For an +internal entity, the literal +entity value is the quoted string actually present in the entity declaration, +corresponding to the non-terminal EntityValue.] [Definition: For an external entity, the literal +entity value is the exact text contained in the entity.] [Definition: For an +internal entity, the replacement text +is the content of the entity, after replacement of character references and +parameter-entity references.] [Definition: For +an external entity, the replacement text is the content of the entity, +after stripping the text declaration (leaving any surrounding white space) if there +is one but without any replacement of character references or parameter-entity +references.]

The literal entity value as given in an internal entity declaration (EntityValue) MAY contain character, parameter-entity, +and general-entity references. Such references MUST be contained entirely +within the literal entity value. The actual replacement text that is included (or included in literal) as described above +MUST contain the replacement +text of any parameter entities referred to, and MUST contain the character +referred to, in place of any character references in the literal entity value; +however, general-entity references MUST be left as-is, unexpanded. For example, +given the following declarations:

<!ENTITY % pub    "&#xc9;ditions Gallimard" >
+<!ENTITY   rights "All rights reserved" >
+<!ENTITY   book   "La Peste: Albert Camus,
+&#xA9; 1947 %pub;. &rights;" >

then the replacement text for the entity "book" +is:

La Peste: Albert Camus,
+© 1947 Éditions Gallimard. &rights;

The general-entity reference "&rights;" would +be expanded should the reference "&book;" appear +in the document's content or an attribute value.

These simple rules may have complex interactions; for a detailed discussion +of a difficult example, see C Expansion of Entity and Character References.

4.6 Predefined Entities

[Definition: Entity and character references MAY +both be used to escape the left angle bracket, ampersand, and +other delimiters. A set of general entities (amp, +lt, +gt, +apos, +quot) is specified for +this purpose. Numeric character references MAY also be used; they are expanded +immediately when recognized and MUST be treated as character data, so the +numeric character references "&#60;" and "&#38;" MAY be used to escape < and & when they occur +in character data.]

All XML processors MUST recognize these entities whether they are declared +or not. For interoperability, valid XML +documents SHOULD declare these entities, like any others, before using them. If +the entities lt or amp are declared, they MUST be +declared as internal entities whose replacement text is a character reference +to the respective +character (less-than sign or ampersand) being escaped; the double +escaping is REQUIRED for these entities so that references to them produce +a well-formed result. If the entities gt, apos, +or quot are declared, they MUST be declared as internal entities +whose replacement text is the single character being escaped (or a character +reference to that character; the double escaping here is OPTIONAL but harmless). +For example:

<!ENTITY lt     "&#38;#60;">
+<!ENTITY gt     "&#62;">
+<!ENTITY amp    "&#38;#38;">
+<!ENTITY apos   "&#39;">
+<!ENTITY quot   "&#34;">

4.7 Notation Declarations

[Definition: Notations identify +by name the format of unparsed entities, +the format of elements which bear a notation attribute, or the application +to which a processing instruction is addressed.]

[Definition: Notation declarations +provide a name for the notation, for use in entity and attribute-list declarations +and in attribute specifications, and an external identifier for the notation +which may allow an XML processor or its client application to locate a helper +application capable of processing data in the given notation.]

Notation Declarations
[82]   NotationDecl   ::=   '<!NOTATION' S Name S (ExternalID | PublicID) S? '>'[VC: Unique Notation Name]
[83]   PublicID   ::=   'PUBLIC' S PubidLiteral

Validity constraint: Unique Notation Name

A given Name MUST NOT be declared in more than one notation declaration.

XML processors MUST provide applications with the name and external identifier(s) +of any notation declared and referred to in an attribute value, attribute +definition, or entity declaration. They MAY additionally resolve the external +identifier into the system identifier, file +name, or other information needed to allow the application to call a processor +for data in the notation described. (It is not an error, however, for XML +documents to declare and refer to notations for which notation-specific applications +are not available on the system where the XML processor or application is +running.)

4.8 Document Entity

[Definition: The document entity +serves as the root of the entity tree and a starting-point for an XML processor.] This specification does +not specify how the document entity is to be located by an XML processor; +unlike other entities, the document entity has no name and might well appear +on a processor input stream without any identification at all.

5 Conformance

5.1 Validating and Non-Validating Processors

Conforming XML processors fall into +two classes: validating and non-validating.

Validating and non-validating processors alike MUST report violations of +this specification's well-formedness constraints in the content of the document entity and any other parsed +entities that they read.

[Definition: Validating +processors MUST, +at user option, report violations of the constraints expressed by +the declarations in the DTD, and failures +to fulfill the validity constraints given in this specification.] +To accomplish this, validating XML processors MUST read and process the entire +DTD and all external parsed entities referenced in the document.

Non-validating processors are REQUIRED to check only the document +entity, including the entire internal DTD subset, for well-formedness. [Definition: While they are not required +to check the document for validity, they are REQUIRED to process +all the declarations they read in the internal DTD subset and in any parameter +entity that they read, up to the first reference to a parameter entity that +they do not read; that is to say, they MUST use the information +in those declarations to normalize +attribute values, include the replacement +text of internal entities, and supply default +attribute values.] Except when standalone="yes", they +MUST NOT process entity +declarations or attribute-list declarations +encountered after a reference to a parameter entity that is not read, since +the entity may have contained overriding declarations; when standalone="yes", processors MUST +process these declarations.

Note +that when processing invalid documents with a non-validating +processor the application may not be presented with consistent +information. For example, several requirements for uniqueness +within the document may not be met, including more than one element +with the same id, duplicate declarations of elements or notations +with the same name, etc. In these cases the behavior of the parser +with respect to reporting such information to the application is +undefined.

XML 1.1 processors MUST be able to process both XML 1.0 +and XML 1.1 documents. Programs which generate XML SHOULD +generate XML 1.0, unless one of the specific features of XML 1.1 is required.

5.2 Using XML Processors

The behavior of a validating XML processor is highly predictable; it must +read every piece of a document and report all well-formedness and validity +violations. Less is required of a non-validating processor; it need not read +any part of the document other than the document entity. This has two effects +that may be important to users of XML processors:

For maximum reliability in interoperating between different XML processors, +applications which use non-validating processors SHOULD NOT rely on any behaviors +not required of such processors. Applications which require DTD facilities +not related to validation (such +as the declaration of default attributes and internal entities that are +or may be specified in +external entities SHOULD use validating XML processors.

6 Notation

The formal grammar of XML is given in this specification using a simple +Extended Backus-Naur Form (EBNF) notation. Each rule in the grammar defines +one symbol, in the form

symbol ::= expression

Symbols are written with an initial capital letter if they are the +start symbol of a regular language, otherwise with an initial lowercase +letter. Literal strings are quoted.

Within the expression on the right-hand side of a rule, the following expressions +are used to match strings of one or more characters:

#xN

where N is a hexadecimal integer, the expression matches the character +whose number +(code point) in ISO/IEC 10646 is N. The number of leading zeros in the #xN +form is insignificant.

[a-zA-Z], [#xN-#xN]

matches any Char with a value in the range(s) indicated (inclusive).

[abc], [#xN#xN#xN]

matches any Char with a value among the characters +enumerated. Enumerations and ranges can be mixed in one set of brackets.

[^a-z], [^#xN-#xN]

matches any Char with a value outside the range +indicated.

[^abc], [^#xN#xN#xN]

matches any Char with a value not among the characters given. Enumerations +and ranges of forbidden values can be mixed in one set of brackets.

"string"

matches a literal string matching that +given inside the double quotes.

'string'

matches a literal string matching that +given inside the single quotes.

These symbols may be combined to match more complex patterns as follows, +where A and B represent simple expressions:

(expression)

expression is treated as a unit and may be combined as described +in this list.

A?

matches A or nothing; optional A.

A B

matches A followed by B. This +operator has higher precedence than alternation; thus A B | C D +is identical to (A B) | (C D).

A | B

matches A or B.

A - B

matches any string that matches A but does not match B.

A+

matches one or more occurrences of A. Concatenation +has higher precedence than alternation; thus A+ | B+ is identical +to (A+) | (B+).

A*

matches zero or more occurrences of A. Concatenation +has higher precedence than alternation; thus A* | B* is identical +to (A*) | (B*).

Other notations used in the productions are:

/* ... */

comment.

[ wfc: ... ]

well-formedness constraint; this identifies by name a constraint on well-formed documents associated with a production.

[ vc: ... ]

validity constraint; this identifies by name a constraint on valid +documents associated with a production.

A References

A.1 Normative References

IANA-CHARSETS
(Internet +Assigned Numbers Authority) Official Names for Character Sets, +ed. Keld Simonsen et al. (See http://www.iana.org/assignments/character-sets.)
IETF RFC 2119
IETF +(Internet Engineering Task Force). RFC 2119: Key words for use in RFCs to Indicate Requirement Levels. +Scott Bradner, 1997. (See http://www.ietf.org/rfc/rfc2119.txt.)
IETF RFC 2396
IETF +(Internet Engineering Task Force). RFC 2396: Uniform Resource Identifiers +(URI): Generic Syntax. T. Berners-Lee, R. Fielding, L. Masinter. +1998. (See http://www.ietf.org/rfc/rfc2396.txt.)
IETF RFC 2732
IETF +(Internet Engineering Task Force). RFC 2732: Format for Literal +IPv6 Addresses in URL's. R. Hinden, B. Carpenter, L. Masinter. +1999. (See http://www.ietf.org/rfc/rfc2732.txt.)
IETF RFC 3066
IETF +(Internet Engineering Task Force). RFC 3066: Tags for the Identification +of Languages, ed. H. Alvestrand. 2001. (See http://www.ietf.org/rfc/rfc3066.txt.)
ISO/IEC 10646
ISO (International +Organization for Standardization). ISO/IEC 10646-1:2000. Information +technology — Universal Multiple-Octet Coded Character Set (UCS) — +Part 1: Architecture and Basic Multilingual Plane and ISO/IEC 10646-2:2001. +Information technology — Universal Multiple-Octet Coded Character Set (UCS) — Part 2: +Supplementary Planes, as, from time to time, amended, replaced by a new edition or +expanded by the addition of new parts. [Geneva]: International Organization for Standardization. +(See http://www.iso.ch for the latest version.)
Unicode
The Unicode Consortium. The Unicode +Standard, Version 4.0. Reading, Mass.: Addison-Wesley, +2003, +as updated from time to time by the publication of new versions. (See + +http://www.unicode.org/unicode/standard/versions for the latest version +and additional information on versions of the standard and of the Unicode +Character Database).
XML-1.0
W3C. Extensible Markup Language (XML) 1.0 (Third +Edition). Tim Bray, Jean Paoli, C.M. Sperberg-McQueen, Eve Maler, François Yergeau +(editors) (See http://www.w3.org/TR/REC-xml.)

A.2 Other References

Aho/Ullman
Aho, Alfred V., Ravi Sethi, and Jeffrey D. +Ullman. Compilers: Principles, Techniques, and Tools. +Reading: Addison-Wesley, 1986, rpt. corr. 1988.
Brüggemann-Klein
Brüggemann-Klein, +Anne. Formal Models in Document Processing. Habilitationsschrift. Faculty +of Mathematics at the University of Freiburg, 1993. (See ftp://ftp.informatik.uni-freiburg.de/documents/papers/brueggem/habil.ps.)
Brüggemann-Klein and Wood
Brüggemann-Klein, +Anne, and Derick Wood. Deterministic Regular Languages. +Universität Freiburg, Institut für Informatik, Bericht 38, Oktober 1991. Extended +abstract in A. Finkel, M. Jantzen, Hrsg., STACS 1992, S. 173-184. Springer-Verlag, +Berlin 1992. Lecture Notes in Computer Science 577. Full version titled One-Unambiguous +Regular Languages in Information and Computation 140 (2): 229-253, +February 1998.
Charmod
W3C Working Draft. + +Character Model for the World Wide Web 1.0. + +Martin J. Dürst, François Yergeau, Richard Ishida, Misha Wolf, Tex Texin. (See http://www.w3.org/TR/2003/WD-charmod-20030822/.)
Clark
James Clark. +Comparison of SGML and XML. (See http://www.w3.org/TR/NOTE-sgml-xml-971215.)
IANA-LANGCODES
(Internet +Assigned Numbers Authority) Registry of Language Tags, +ed. Keld Simonsen et al. (See http://www.iana.org/assignments/language-tags.)
IETF RFC 2141
IETF +(Internet Engineering Task Force). RFC 2141: URN Syntax, ed. +R. Moats. 1997. (See http://www.ietf.org/rfc/rfc2141.txt.)
IETF RFC 3023
IETF +(Internet Engineering Task Force). RFC 3023: XML Media Types. +eds. M. Murata, S. St.Laurent, D. Kohn. 2001. (See http://www.ietf.org/rfc/rfc3023.txt.)
IETF RFC 2781
IETF +(Internet Engineering Task Force). RFC 2781: UTF-16, an encoding +of ISO 10646, ed. P. Hoffman, F. Yergeau. 2000. (See http://www.ietf.org/rfc/rfc2781.txt.)
ISO 639
(International Organization for Standardization). +ISO 639:1988 (E). +Code for the representation of names of languages. [Geneva]: International +Organization for Standardization, 1988.
ISO 3166
(International Organization for Standardization). +ISO 3166-1:1997 +(E). Codes for the representation of names of countries and their subdivisions — +Part 1: Country codes [Geneva]: International Organization for +Standardization, 1997.
ISO 8879
ISO (International Organization for Standardization). ISO +8879:1986(E). Information processing — Text and Office Systems — +Standard Generalized Markup Language (SGML). First edition — +1986-10-15. [Geneva]: International Organization for Standardization, 1986.
ISO/IEC 10744
ISO (International Organization for +Standardization). ISO/IEC 10744-1992 (E). Information technology — +Hypermedia/Time-based Structuring Language (HyTime). [Geneva]: +International Organization for Standardization, 1992. Extended Facilities +Annexe. [Geneva]: International Organization for Standardization, 1996.
WEBSGML
ISO +(International Organization for Standardization). ISO 8879:1986 +TC2. Information technology — Document Description and Processing Languages. +[Geneva]: International Organization for Standardization, 1998. (See http://www.sgmlsource.com/8879/n0029.htm.)
XML Names
Tim Bray, +Dave Hollander, and Andrew Layman, editors. Namespaces in XML. +Textuality, Hewlett-Packard, and Microsoft. World Wide Web Consortium, 1999. (See http://www.w3.org/TR/REC-xml-names/.)

B Definitions for Character Normalization

This appendix contains the necessary definitions for character normalization. +For additional background information and examples, see [Charmod].

+[Definition: Text is said to be +in a Unicode encoding form if it is encoded in +UTF-8, UTF-16 or UTF-32.]

+[Definition: Legacy encoding +is taken to mean any character encoding not based on Unicode.]

+[Definition: A +normalizing transcoder is a transcoder that converts from a +legacy encoding to a +Unicode encoding form and +ensures that the result is in Unicode Normalization Form C +(see UAX #15 [Unicode]).]

[Definition: A character escape +is a syntactic device defined in a markup or programming language that allows +one or more of:]

  1. expressing syntax-significant characters while disregarding +their significance in the syntax of the language, or

  2. expressing characters not representable in the character encoding +chosen for an instance of the language, or

  3. expressing characters in general, without use of the corresponding +character codes.

+[Definition: Certified text +is text which satisfies at least one of the following conditions:]

  1. it has been confirmed through inspection that the text +is in normalized form

  2. the source text-processing component is identified +and is known to produce only normalized text.

+[Definition: Text is, for the purposes of +this specification, Unicode-normalized if it is in a +Unicode encoding form and is in +Unicode Normalization Form C, according to a version of Unicode Standard Annex #15: +Unicode Normalization Forms [Unicode] at least as recent as the +oldest version of the Unicode Standard that contains all the characters +actually present in the text, but no earlier +than version 3.2.]

+[Definition: Text is +include-normalized if:]

  1. the text is Unicode-normalized +and does not contain any character escapes +or includes whose expansion would +cause the text to become no longer Unicode-normalized; +or

  2. the text is in a legacy encoding and, if it were transcoded +to a Unicode encoding form by a +normalizing transcoder, the resulting +text would satisfy clause 1 above.

+[Definition: A composing character +is a character that is one or both of the following:]

  1. the second character in the canonical decomposition mapping of +some primary composite (as defined in D3 of UAX #15 [Unicode]), or

  2. of non-zero canonical combining class (as defined in Unicode +[Unicode]).

+[Definition: Text is +fully-normalized if:]

  1. the text is in a Unicode encoding +form, is include-normalized and +none of the relevant +constructs comprising the text begin with a +composing character or a +character escape representing a +composing character; or

  2. the text is in a legacy encoding and, +if it were transcoded to a Unicode encoding form +by a normalizing transcoder, the resulting text +would satisfy clause 1 above.

C Expansion of Entity and Character References (Non-Normative)

This appendix contains some examples illustrating the sequence of entity- +and character-reference recognition and expansion, as specified in 4.4 XML Processor Treatment of Entities and References.

If the DTD contains the declaration

<!ENTITY example "<p>An ampersand (&#38;#38;) may be escaped
+numerically (&#38;#38;#38;) or with a general entity
+(&amp;amp;).</p>" >

then the XML processor will recognize the character references when it +parses the entity declaration, and resolve them before storing the following +string as the value of the entity "example":

<p>An ampersand (&#38;) may be escaped
+numerically (&#38;#38;) or with a general entity
+(&amp;amp;).</p>

A reference in the document to "&example;" +will cause the text to be reparsed, at which time the start- and end-tags +of the p element will be recognized and the three references will +be recognized and expanded, resulting in a p element with the following +content (all data, no delimiters or markup):

An ampersand (&) may be escaped
+numerically (&#38;) or with a general entity
+(&amp;).

A more complex example will illustrate the rules and their effects fully. +In the following example, the line numbers are solely for reference.

1 <?xml version='1.0'?>
+2 <!DOCTYPE test [
+3 <!ELEMENT test (#PCDATA) >
+4 <!ENTITY % xx '&#37;zz;'>
+5 <!ENTITY % zz '&#60;!ENTITY tricky "error-prone" >' >
+6 %xx;
+7 ]>
+8 <test>This sample shows a &tricky; method.</test>

This produces the following:

  • in line 4, the reference to character 37 is expanded immediately, +and the parameter entity "xx" is stored in the symbol +table with the value "%zz;". Since the replacement +text is not rescanned, the reference to parameter entity "zz" +is not recognized. (And it would be an error if it were, since "zz" +is not yet declared.)

  • in line 5, the character reference "&#60;" +is expanded immediately and the parameter entity "zz" +is stored with the replacement text "<!ENTITY tricky "error-prone" +>", which is a well-formed entity declaration.

  • in line 6, the reference to "xx" is recognized, +and the replacement text of "xx" (namely "%zz;") +is parsed. The reference to "zz" is recognized in +its turn, and its replacement text ("<!ENTITY tricky "error-prone" +>") is parsed. The general entity "tricky" +has now been declared, with the replacement text "error-prone".

  • in line 8, the reference to the general entity "tricky" +is recognized, and it is expanded, so the full content of the test +element is the self-describing (and ungrammatical) string This sample +shows a error-prone method.

D Deterministic Content Models (Non-Normative)

As +noted in 3.2.1 Element Content, it is required that content +models in element type declarations be deterministic. This requirement is for compatibility with SGML (which calls deterministic +content models "unambiguous"); XML processors built +using SGML systems may flag non-deterministic content models as errors.

For example, the content model ((b, c) | (b, d)) is non-deterministic, +because given an initial b the XML processor +cannot know which b in the model is being matched without looking +ahead to see which element follows the b. In this case, the two references +to b can be collapsed into a single reference, making the model read (b, +(c | d)). An initial b now clearly matches only a single name +in the content model. The processor doesn't need to look ahead to see what follows; either c or d +would be accepted.

More formally: a finite state automaton may be constructed from the content +model using the standard algorithms, e.g. algorithm 3.5 in section 3.9 of +Aho, Sethi, and Ullman [Aho/Ullman]. In many such algorithms, a follow +set is constructed for each position in the regular expression (i.e., each +leaf node in the syntax tree for the regular expression); if any position +has a follow set in which more than one following position is labeled with +the same element type name, then the content model is in error and may be +reported as an error.

Algorithms exist which allow many but not all non-deterministic content +models to be reduced automatically to equivalent deterministic models; see +Brüggemann-Klein 1991 [Brüggemann-Klein].

E Autodetection of Character Encodings (Non-Normative)

The XML encoding declaration functions as an internal label on each entity, +indicating which character encoding is in use. Before an XML processor can +read the internal label, however, it apparently has to know what character +encoding is in use — which is what the internal label is trying to indicate. +In the general case, this is a hopeless situation. It is not entirely hopeless +in XML, however, because XML limits the general case in two ways: each implementation +is assumed to support only a finite set of character encodings, and the XML +encoding declaration is restricted in position and content in order to make +it feasible to autodetect the character encoding in use in each entity in +normal cases. Also, in many cases other sources of information are available +in addition to the XML data stream itself. Two cases may be distinguished, +depending on whether the XML entity is presented to the processor without, +or with, any accompanying (external) information. We consider the first case +first.

E.1 Detection Without External Encoding Information

Because each XML entity not accompanied by external +encoding information and not in UTF-8 or UTF-16 encoding must +begin with an XML encoding declaration, in which the first characters must +be '<?xml', any conforming processor can detect, after two +to four octets of input, which of the following cases apply. In reading this +list, it may help to know that in UCS-4, '<' is "#x0000003C" +and '?' is "#x0000003F", and the Byte Order Mark +required of UTF-16 data streams is "#xFEFF". The notation +## is used to denote any byte value except that two consecutive +##s cannot be both 00.

With a Byte Order Mark:

00 00 FE +FFUCS-4, big-endian machine (1234 order)
FF +FE 00 00UCS-4, little-endian machine (4321 order)
00 00 FF FEUCS-4, unusual octet order (2143)
FE FF 00 00UCS-4, unusual octet order (3412)
FE FF ## ##UTF-16, big-endian
FF FE ## ##UTF-16, little-endian
EF BB BFUTF-8

Without a Byte Order Mark:

00 00 00 3CUCS-4 or other encoding with a 32-bit code unit and ASCII +characters encoded as ASCII values, in respectively big-endian (1234), little-endian +(4321) and two unusual byte orders (2143 and 3412). The encoding declaration +must be read to determine which of UCS-4 or other supported 32-bit encodings +applies.
3C 00 00 00
00 00 3C 00
00 3C 00 00
00 3C 00 3FUTF-16BE or big-endian ISO-10646-UCS-2 +or other encoding with a 16-bit code unit in big-endian order and ASCII characters +encoded as ASCII values (the encoding declaration must be read to determine +which)
3C 00 3F 00UTF-16LE or little-endian +ISO-10646-UCS-2 or other encoding with a 16-bit code unit in little-endian +order and ASCII characters encoded as ASCII values (the encoding declaration +must be read to determine which)
3C 3F 78 6DUTF-8, ISO 646, ASCII, some part of ISO 8859, Shift-JIS, EUC, or any other +7-bit, 8-bit, or mixed-width encoding which ensures that the characters of +ASCII have their normal positions, width, and values; the actual encoding +declaration must be read to detect which of these applies, but since all of +these encodings use the same bit patterns for the relevant ASCII characters, +the encoding declaration itself may be read reliably
4C +6F A7 94EBCDIC (in some flavor; the full encoding declaration +must be read to tell which code page is in use)
OtherUTF-8 without an encoding declaration, or else the data stream is mislabeled +(lacking a required encoding declaration), corrupt, fragmentary, or enclosed +in a wrapper of some kind

Note:

In cases above which do not require reading the encoding declaration to +determine the encoding, section 4.3.3 still requires that the encoding declaration, +if present, be read and that the encoding name be checked to match the actual +encoding of the entity. Also, it is possible that new character encodings +will be invented that will make it necessary to use the encoding declaration +to determine the encoding, in cases where this is not required at present.

This level of autodetection is enough to read the XML encoding declaration +and parse the character-encoding identifier, which is still necessary to distinguish +the individual members of each family of encodings (e.g. to tell UTF-8 from +8859, and the parts of 8859 from each other, or to distinguish the specific +EBCDIC code page in use, and so on).

Because the contents of the encoding declaration are restricted to characters +from the ASCII repertoire (however encoded), +a processor can reliably read the entire encoding declaration as soon as it +has detected which family of encodings is in use. Since in practice, all widely +used character encodings fall into one of the categories above, the XML encoding +declaration allows reasonably reliable in-band labeling of character encodings, +even when external sources of information at the operating-system or transport-protocol +level are unreliable. Character encodings such as UTF-7 +that make overloaded usage of ASCII-valued bytes may fail to be reliably detected.

Once the processor has detected the character encoding in use, it can act +appropriately, whether by invoking a separate input routine for each case, +or by calling the proper conversion function on each character of input.

Like any self-labeling system, the XML encoding declaration will not work +if any software changes the entity's character set or encoding without updating +the encoding declaration. Implementors of character-encoding routines should +be careful to ensure the accuracy of the internal and external information +used to label the entity.

E.2 Priorities in the Presence of External Encoding Information

The second possible case occurs when the XML entity is accompanied by encoding +information, as in some file systems and some network protocols. When multiple +sources of information are available, their relative priority and the preferred +method of handling conflict should be specified as part of the higher-level +protocol used to deliver XML. In particular, please refer +to [IETF RFC 3023] or its successor, which defines the text/xml +and application/xml MIME types and provides some useful guidance. +In the interests of interoperability, however, the following rule is recommended.

  • If an XML entity is in a file, the Byte-Order Mark and encoding declaration are used +(if present) to determine the character encoding.

F W3C XML Working Group (Non-Normative)

This specification was prepared and approved for publication by the W3C +XML Working Group (WG). WG approval of this specification does not necessarily +imply that all WG participants voted for its approval. The current and former members +in the XML WG are:

G W3C XML Core Working Group (Non-Normative)

The present edition of this specification was prepared by the W3C XML Core +Working Group (WG). The participants in the WG at the time of publication of this +edition were:

H Production Notes (Non-Normative)

This edition was encoded in a +slightly modified version of the +XMLspec DTD, 2.5. +The XHTML versions were produced with a combination of the +xmlspec.xsl, +diffspec.xsl, +and REC-xml-3e.xsl +XSLT stylesheets.

I Suggestions for XML Names (Non-Normative)

The following suggestions define what is believed to be best +practice in the construction of XML names used as element names, +attribute names, processing instruction targets, entity names, +notation names, and the values of attributes of type ID, and are +intended as guidance for document authors and schema designers. +All references to Unicode are understood with respect to +a particular version of the Unicode Standard greater than or equal +to 3.0; which version should be used is left to the discretion of +the document author or schema designer.

The first two suggestions are directly derived from the rules +given for identifiers in the Unicode Standard, version 3.0, and +exclude all control characters, enclosing nonspacing marks, +non-decimal numbers, private-use characters, punctuation characters +(with the noted exceptions), symbol characters, unassigned +codepoints, and white space characters. The other suggestions +are mostly derived from [XML-1.0] Appendix B.

  1. The first character of any name should have a Unicode General +Category of Ll, Lu, Lo, Lm, Lt, or Nl, or else be '_' #x5F.

  2. Characters other than the first should have a Unicode General +Category of Ll, Lu, Lo, Lm, Lt, Mc, Mn, Nl, Nd, Pc, or Cf, or else +be one of the following: '-' #x2D, '.' #x2E, ':' #x3A or +'·' #xB7 (middle dot). Since Cf characters are not +directly visible, they should be employed with caution and only +when necessary, to avoid creating names which are distinct to XML +processors but look the same to human beings.

  3. Ideographic characters which have a canonical decomposition +(including those in the ranges [#xF900-#xFAFF] and +[#x2F800-#x2FFFD], with 12 exceptions) should not be used in names. +

  4. Characters which have a compatibility decomposition (those with +a "compatibility formatting tag" in field 5 of the Unicode +Character Database -- marked by field 5 beginning with a "<") +should not be used in names. This suggestion does not apply +to #x0E33 THAI CHARACTER SARA AM or #x0EB3 LAO CHARACTER AM, which +despite their compatibility decompositions are in regular use in +those scripts.

  5. Combining characters meant for use with symbols only (including +those in the ranges [#x20D0-#x20EF] and [#x1D165-#x1D1AD]) should +not be used in names.

  6. The interlinear annotation characters ([#xFFF9-#xFFFB) should +not be used in names.

  7. Variation selector characters should not be used in names.

  8. Names which are nonsensical, unpronounceable, hard to read, or +easily confusable with other names should not be employed.

diff --git a/src/tests/xml.cpp b/src/tests/xml.cpp new file mode 100644 index 0000000..9ef6a7e --- /dev/null +++ b/src/tests/xml.cpp @@ -0,0 +1,15 @@ +#include "bu/xmlreader.h" +#include "bu/xmlnode.h" +#include "bu/xmldocument.h" +#include "bu/file.h" + +int main() +{ + Bu::File f("test.xml", "r"); + Bu::XmlReader xr( f ); + + xr.read(); + + return 0; +} + diff --git a/src/tsfdocument.cpp b/src/tsfdocument.cpp new file mode 100644 index 0000000..582f1b1 --- /dev/null +++ b/src/tsfdocument.cpp @@ -0,0 +1,9 @@ +#include "tsfdocument.h" + +Bu::TsfDocument::TsfDocument() +{ +} + +Bu::TsfDocument::~TsfDocument() +{ +} diff --git a/src/tsfdocument.h b/src/tsfdocument.h new file mode 100644 index 0000000..e324459 --- /dev/null +++ b/src/tsfdocument.h @@ -0,0 +1,22 @@ +#ifndef TSF_DOCUMENT_H +#define TSF_DOCUMENT_H + +#include + +namespace Bu +{ + /** + * + */ + class TsfDocument + { + public: + TsfDocument(); + virtual ~TsfDocument(); + + private: + + }; +} + +#endif diff --git a/src/tsfnode.cpp b/src/tsfnode.cpp new file mode 100644 index 0000000..19df4ed --- /dev/null +++ b/src/tsfnode.cpp @@ -0,0 +1,9 @@ +#include "tsfnode.h" + +Bu::TsfNode::TsfNode() +{ +} + +Bu::TsfNode::~TsfNode() +{ +} diff --git a/src/tsfnode.h b/src/tsfnode.h new file mode 100644 index 0000000..f58b825 --- /dev/null +++ b/src/tsfnode.h @@ -0,0 +1,21 @@ +#ifndef TSF_NODE_H +#define TSF_NODE_H + +#include + +namespace Bu +{ + /** + * + */ + class TsfNode + { + public: + TsfNode(); + virtual ~TsfNode(); + + private: + + }; +} +#endif diff --git a/src/tsfreader.cpp b/src/tsfreader.cpp new file mode 100644 index 0000000..58f4f78 --- /dev/null +++ b/src/tsfreader.cpp @@ -0,0 +1,9 @@ +#include "tsfreader.h" + +Bu::TsfReader::TsfReader() +{ +} + +Bu::TsfReader::~TsfReader() +{ +} diff --git a/src/tsfreader.h b/src/tsfreader.h new file mode 100644 index 0000000..cc8400a --- /dev/null +++ b/src/tsfreader.h @@ -0,0 +1,22 @@ +#ifndef TSF_READER_H +#define TSF_READER_H + +#include + +namespace Bu +{ + /** + * + */ + class TsfReader + { + public: + TsfReader(); + virtual ~TsfReader(); + + private: + + }; +} + +#endif diff --git a/src/tsfwriter.cpp b/src/tsfwriter.cpp new file mode 100644 index 0000000..6592996 --- /dev/null +++ b/src/tsfwriter.cpp @@ -0,0 +1,9 @@ +#include "tsfwriter.h" + +Bu::TsfWriter::TsfWriter() +{ +} + +Bu::TsfWriter::~TsfWriter() +{ +} diff --git a/src/tsfwriter.h b/src/tsfwriter.h new file mode 100644 index 0000000..18f19d6 --- /dev/null +++ b/src/tsfwriter.h @@ -0,0 +1,22 @@ +#ifndef TSF_WRITER_H +#define TSF_WRITER_H + +#include + +namespace Bu +{ + /** + * + */ + class TsfWriter + { + public: + TsfWriter(); + virtual ~TsfWriter(); + + private: + + }; +} + +#endif diff --git a/src/xmldocument.cpp b/src/xmldocument.cpp new file mode 100644 index 0000000..cb21826 --- /dev/null +++ b/src/xmldocument.cpp @@ -0,0 +1,9 @@ +#include "xmldocument.h" + +Bu::XmlDocument::XmlDocument() +{ +} + +Bu::XmlDocument::~XmlDocument() +{ +} diff --git a/src/xmldocument.h b/src/xmldocument.h new file mode 100644 index 0000000..e16e3ea --- /dev/null +++ b/src/xmldocument.h @@ -0,0 +1,22 @@ +#ifndef XML_DOCUMENT_H +#define XML_DOCUMENT_H + +#include + +namespace Bu +{ + /** + * + */ + class XmlDocument + { + public: + XmlDocument(); + virtual ~XmlDocument(); + + private: + + }; +} + +#endif diff --git a/src/xmlnode.cpp b/src/xmlnode.cpp new file mode 100644 index 0000000..58ef5c5 --- /dev/null +++ b/src/xmlnode.cpp @@ -0,0 +1,9 @@ +#include "xmlnode.h" + +Bu::XmlNode::XmlNode() +{ +} + +Bu::XmlNode::~XmlNode() +{ +} diff --git a/src/xmlnode.h b/src/xmlnode.h new file mode 100644 index 0000000..cd9961a --- /dev/null +++ b/src/xmlnode.h @@ -0,0 +1,22 @@ +#ifndef XML_NODE_H +#define XML_NODE_H + +#include + +namespace Bu +{ + /** + * + */ + class XmlNode + { + public: + XmlNode(); + virtual ~XmlNode(); + + private: + + }; +} + +#endif diff --git a/src/xmlreader.cpp b/src/xmlreader.cpp new file mode 100644 index 0000000..432ecc1 --- /dev/null +++ b/src/xmlreader.cpp @@ -0,0 +1,108 @@ +#include "xmlreader.h" + +Bu::XmlReader::XmlReader( Bu::Stream &sIn ) : + sIn( sIn ) +{ +} + +Bu::XmlReader::~XmlReader() +{ +} + +const char *Bu::XmlReader::lookahead( int nAmnt ) +{ + if( sBuf.getSize() >= nAmnt ) + return sBuf.getStr(); + + int nNew = nAmnt - sBuf.getSize(); + char *buf = new char[nNew]; + sIn.read( buf, nNew ); + sBuf.append( buf ); + + return sBuf.getStr(); +} + +void Bu::XmlReader::burn( int nAmnt ) +{ + if( sBuf.getSize() < nAmnt ) + { + lookahead( nAmnt ); + } + + sBuf.remove( nAmnt ); +} + +void Bu::XmlNode::checkString( const char *str, int nLen ) +{ + if( !strncmp( str, lookahead( nLen ), nLen ) ) + { + burn( nLen ); + return; + } + + throw Bu::ExceptionBase("Expected string '%s'", str ); +} + +Bu::XmlNode *Bu::XmlReader::read() +{ + prolog(); +} + +void Bu::XmlReader::prolog() +{ + XMLDecl(); + Misc(); +} + +void Bu::XmlReader::XMLDecl() +{ + checkString(" +#include "bu/stream.h" +#include "bu/fstring.h" +#include "bu/xmlnode.h" + +namespace Bu +{ + /** + * + */ + class XmlReader + { + public: + XmlReader( Bu::Stream &sIn ); + virtual ~XmlReader(); + + XmlNode *read(); + + private: + Bu::Stream &sIn; + Bu::FString sBuf; + + private: // Helpers + const char *lookahead( int nAmnt ); + void burn( int nAmnt ); + void checkString( const char *str, int nLen ); + + private: // States + /** + * The headers, etc. + */ + void prolog(); + + /** + * The xml decleration (version, encoding, etc). + */ + void XMLDecl(); + + /** + * Misc things...? + */ + void Misc(); + + /** + * Whitespace eater. + */ + void S(); + + /** + * Optional whitespace eater. + */ + void Sq(); + + /** + * XML Version spec + */ + void VersionInfo(); + + /** + * Your basic equals sign with surrounding whitespace. + */ + void Eq(); + + }; +} + +#endif diff --git a/src/xmlwriter.cpp b/src/xmlwriter.cpp new file mode 100644 index 0000000..23a5175 --- /dev/null +++ b/src/xmlwriter.cpp @@ -0,0 +1,9 @@ +#include "xmlwriter.h" + +Bu::XmlWriter::XmlWriter() +{ +} + +Bu::XmlWriter::~XmlWriter() +{ +} diff --git a/src/xmlwriter.h b/src/xmlwriter.h new file mode 100644 index 0000000..796d6fb --- /dev/null +++ b/src/xmlwriter.h @@ -0,0 +1,22 @@ +#ifndef XML_WRITER_H +#define XML_WRITER_H + +#include + +namespace Bu +{ + /** + * + */ + class XmlWriter + { + public: + XmlWriter(); + virtual ~XmlWriter(); + + private: + + }; +} + +#endif -- cgit v1.2.3 From 033c41ed57348abb3a418166b1fb39bfad3312de Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Fri, 11 May 2007 07:51:40 +0000 Subject: Added a list template class, seems to work pretty well for now, I may have forgotten proper cleanup in the deconstructor, but besides that you can do almost everything you need. I'll make a slist/stack next, probably with the same basic code, just a different structure (not doubley-linked). The xml system from old-libbu++ is almost completely converted, I was going to re-write it, but this seemed easier at first, it may not have been, we'll see. It almost parses everything again, and almost outputs again, and it does use streams now. The FString is partway to doing minimum chunk allocations, so that adding single-characters will be really fast up to the minimum chunk size. I also figured out how to add this optimization without any extra variables taking up space, and it's optional in the template, which is cool. You can specify the size of the blocks (default 256 bytes), if it's 0 then they'll be like the old FString, 1 chunk per operation. The next FString update should be allowing efficient removal from the begining of the string by faking it, and simply moving a secondary base pointer ahead, and then optimizing appends after that fact to simply move the existing data around if you shouldn't have to re-allocate (alla FlexBuf). The final fun addition that I'm planning is a simple switch in the template (boolean) that will switch an FString into a thread-safe mode without changing the interface or anything that you can do with them at all. It may increasing memory usage, but they should still be better than std::strings, and totally thread-safe. The best part of that is that if it's done with a boolean template parameter and if statements that only test that parameter controlling flow, the code that you don't want (threadsafe/non-threadsafe) won't be included at all post-optimization. --- src/fstring.h | 14 +++-- src/list.cpp | 2 + src/list.h | 176 ++++++++++++++++++++++++++++++++++++++++++++++++++++ src/tests/list.cpp | 22 +++++++ src/tests/xml.cpp | 6 +- src/xmldocument.cpp | 20 +++--- src/xmldocument.h | 8 +-- src/xmlnode.cpp | 106 ++++++++++--------------------- src/xmlnode.h | 101 +++++++++++------------------- src/xmlreader.cpp | 170 +++++++++++++++++++++++++------------------------- src/xmlreader.h | 31 ++++----- src/xmlwriter.cpp | 62 +++++++++--------- src/xmlwriter.h | 16 ++--- 13 files changed, 428 insertions(+), 306 deletions(-) create mode 100644 src/list.cpp create mode 100644 src/list.h create mode 100644 src/tests/list.cpp (limited to 'src/tests') diff --git a/src/fstring.h b/src/fstring.h index 877e5a7..f738f63 100644 --- a/src/fstring.h +++ b/src/fstring.h @@ -28,7 +28,7 @@ namespace Bu * data is actually copied. This also means that you never need to put any * FBasicString into a ref-counting container class. */ - template< typename chr, typename chralloc=std::allocator, typename chunkalloc=std::allocator > > + template< typename chr, int nMinSize=256, typename chralloc=std::allocator, typename chunkalloc=std::allocator > > class FBasicString : public Archival { #ifndef VALTEST @@ -36,7 +36,7 @@ namespace Bu #endif private: typedef struct FStringChunk Chunk; - typedef struct FBasicString MyType; + typedef struct FBasicString MyType; public: FBasicString() : @@ -131,6 +131,11 @@ namespace Bu appendChunk( pNew ); } + void append( const chr cData ) + { + append( &cData, 1 ); + } + void prepend( const chr *pData ) { long nLen; @@ -231,8 +236,7 @@ namespace Bu MyType &operator +=( const chr pData ) { - chr tmp[2] = { pData, (chr)0 }; - append( tmp ); + append( &pData, 1 ); return (*this); } @@ -475,7 +479,7 @@ namespace Bu } } - void copyFrom( const FBasicString &rSrc ) + void copyFrom( const FBasicString &rSrc ) { if( rSrc.pFirst == NULL ) return; diff --git a/src/list.cpp b/src/list.cpp new file mode 100644 index 0000000..abe92ad --- /dev/null +++ b/src/list.cpp @@ -0,0 +1,2 @@ +#include "bu/list.h" + diff --git a/src/list.h b/src/list.h new file mode 100644 index 0000000..ec63496 --- /dev/null +++ b/src/list.h @@ -0,0 +1,176 @@ +#ifndef LIST_H +#define LIST_H + +#include +#include "bu/exceptionbase.h" + +namespace Bu +{ + template + struct ListLink + { + value *pValue; + ListLink *pNext; + ListLink *pPrev; + }; + template, typename linkalloc=std::allocator > > + class List + { + private: + typedef struct ListLink Link; + typedef class List MyType; + + public: + List() : + pFirst( NULL ), + pLast( NULL ) + { + } + + void append( value v ) + { + Link *pNew = la.allocate( sizeof( Link ) ); + pNew->pValue = va.allocate( sizeof( value ) ); + va.construct( pNew->pValue, v ); + if( pFirst == NULL ) + { + // Empty list + pFirst = pLast = pNew; + pNew->pNext = pNew->pPrev = NULL; + } + else + { + pNew->pNext = NULL; + pNew->pPrev = pLast; + pLast->pNext = pNew; + pLast = pNew; + } + } + + void prepend( value v ) + { + Link *pNew = la.allocate( sizeof( Link ) ); + pNew->pValue = va.allocate( sizeof( value ) ); + va.construct( pNew->pValue, v ); + if( pFirst == NULL ) + { + // Empty list + pFirst = pLast = pNew; + pNew->pNext = pNew->pPrev = NULL; + } + else + { + pNew->pNext = pFirst; + pNew->pPrev = NULL; + pFirst->pPrev = pNew; + pFirst = pNew; + } + } + + typedef struct iterator + { + friend class List; + private: + Link *pLink; + iterator() : + pLink( NULL ) + { + } + + iterator( Link *pLink ) : + pLink( pLink ) + { + } + + public: + bool operator==( const iterator &oth ) + { + return ( pLink == oth.pLink ); + } + + bool operator==( const Link *pOth ) + { + return ( pLink == pOth ); + } + + bool operator!=( const iterator &oth ) + { + return ( pLink != oth.pLink ); + } + + bool operator!=( const Link *pOth ) + { + return ( pLink != pOth ); + } + + value &operator*() + { + return *(pLink->pValue); + } + + value *operator->() + { + return pLink->pValue(); + } + + iterator operator++() + { + if( pLink != NULL ) + pLink = pLink->pNext; + return *this; + } + + iterator operator--() + { + if( pLink != NULL ) + pLink = pLink->pPrev; + return *this; + } + + iterator operator++( int ) + { + if( pLink != NULL ) + pLink = pLink->pNext; + return *this; + } + + iterator operator--( int ) + { + if( pLink != NULL ) + pLink = pLink->pPrev; + return *this; + } + + iterator operator=( const iterator &oth ) + { + pLink = oth.pLink; + } + }; + + iterator begin() + { + return iterator( pFirst ); + } + + const Link *end() + { + return NULL; + } + + int getSize() + { + int j = 0; + for( Link *pCur = pFirst; pCur; pCur = pCur->pNext ) + j++; + return j; + } + + private: + Link *pFirst; + Link *pLast; + linkalloc la; + valuealloc va; + }; +} + +#endif diff --git a/src/tests/list.cpp b/src/tests/list.cpp new file mode 100644 index 0000000..34ab656 --- /dev/null +++ b/src/tests/list.cpp @@ -0,0 +1,22 @@ +#include "bu/list.h" + +int main() +{ + Bu::List l; + + l.append( 0 ); + + for( int j = 3; j <= 21; j += 3 ) + { + l.append( j ); + l.prepend( -j ); + } + + for( Bu::List::iterator i = l.begin(); i != l.end(); i++ ) + { + printf("%d ", *i ); + } + + printf("\n\n"); +} + diff --git a/src/tests/xml.cpp b/src/tests/xml.cpp index 9ef6a7e..9689a28 100644 --- a/src/tests/xml.cpp +++ b/src/tests/xml.cpp @@ -6,9 +6,9 @@ int main() { Bu::File f("test.xml", "r"); - Bu::XmlReader xr( f ); - - xr.read(); + XmlReader xr( f ); + + //xr.read(); return 0; } diff --git a/src/xmldocument.cpp b/src/xmldocument.cpp index d7867d5..95b9788 100644 --- a/src/xmldocument.cpp +++ b/src/xmldocument.cpp @@ -1,6 +1,6 @@ #include #include -#include "xmlwriter.h" +#include "xmldocument.h" XmlDocument::XmlDocument( XmlNode *pRoot ) { @@ -17,28 +17,23 @@ XmlDocument::~XmlDocument() } } -void XmlDocument::addNode( const char *sName, const char *sContent, bool bClose ) +void XmlDocument::addNode( const Bu::FString &sName ) { if( pRoot == NULL ) { // This is the first node, so ignore position and just insert it. - pCurrent = pRoot = new XmlNode( sName, NULL, sContent ); + pCurrent = pRoot = new XmlNode( sName ); } else { - pCurrent = pCurrent->addChild( sName, sContent ); - } - - if( bClose ) - { - closeNode(); + pCurrent = pCurrent->addChild( sName ); } } - +/* void XmlDocument::setName( const char *sName ) { pCurrent->setName( sName ); -} +}*/ bool XmlDocument::isCompleted() { @@ -143,7 +138,8 @@ void XmlDocument::setContent( const char *sContent ) { if( pCurrent ) { - pCurrent->setContent( sContent ); + printf("XmlDocument::setContent: not yet implemented.\n"); + //pCurrent->setContent( sContent ); } } diff --git a/src/xmldocument.h b/src/xmldocument.h index 6671c41..e0c36eb 100644 --- a/src/xmldocument.h +++ b/src/xmldocument.h @@ -39,13 +39,7 @@ public: * the node and setting the content and name. If this is set to true the * node is appended, but the context node doesn't change. */ - void addNode( const char *sName=NULL, const char *sContent=NULL, bool bClose=false ); - - /** - * Set the name of the current node context. - *@param sName The new name of the node. - */ - void setName( const char *sName ); + void addNode( const Bu::FString &sName ); /** * Close the current node context. This will move the current context to diff --git a/src/xmlnode.cpp b/src/xmlnode.cpp index b1ed9a9..96d5850 100644 --- a/src/xmlnode.cpp +++ b/src/xmlnode.cpp @@ -1,53 +1,15 @@ #include "xmlnode.h" -#include "hashfunctionstring.h" -XmlNode::XmlNode( const char *sName, XmlNode *pParent, const char *sContent ) : - hProperties( new HashFunctionString(), 53, false ), - hChildren( new HashFunctionString(), 53, true ) +XmlNode::XmlNode( const Bu::FString &sName, XmlNode *pParent ) : + sName( sName ), + pParent( pParent ) { - this->pParent = pParent; - if( sName != NULL ) - { - setName( sName ); - } - if( sContent != NULL ) - { - this->sPreContent = new std::string( sContent ); - } - else - { - this->sPreContent = NULL; - } - nCurContent = 0; } XmlNode::~XmlNode() { - for( int j = 0; j < lChildren.getSize(); j++ ) - { - delete (XmlNode *)lChildren[j]; - } - for( int j = 0; j < lPropNames.getSize(); j++ ) - { - delete (std::string *)lPropNames[j]; - } - for( int j = 0; j < lPropValues.getSize(); j++ ) - { - delete (std::string *)lPropValues[j]; - } - for( int j = 0; j < lPostContent.getSize(); j++ ) - { - if( lPostContent[j] != NULL ) - { - delete (std::string *)lPostContent[j]; - } - } - if( sPreContent ) - { - delete sPreContent; - } } - +/* void XmlNode::setName( const char *sName ) { if( pParent ) @@ -120,18 +82,18 @@ const char *XmlNode::getContent( int nIndex ) } return NULL; -} +}*/ -XmlNode *XmlNode::addChild( const char *sName, const char *sContent ) +XmlNode *XmlNode::addChild( const Bu::FString &sName ) { - return addChild( new XmlNode( sName, this, sContent ) ); + return addChild( new XmlNode( sName, this ) ); } XmlNode *XmlNode::addChild( XmlNode *pNode ) { - lChildren.append( pNode ); - lPostContent.append( NULL ); - nCurContent++; + Child c = { typeNode }; + c.pNode = pNode; + lChildren.append( c ); pNode->pParent = this; return pNode; @@ -142,21 +104,16 @@ XmlNode *XmlNode::getParent() return pParent; } -void XmlNode::addProperty( const char *sName, const char *sValue ) +void XmlNode::addProperty( const Bu::FString &sName, const Bu::FString &sValue ) { - std::string *pName = new std::string( sName ); - std::string *pValue = new std::string( sValue ); - - hProperties.insert( pName->c_str(), pValue->c_str() ); - lPropNames.append( pName ); - lPropValues.append( pValue ); + hProperties.insert( sName, sValue ); } int XmlNode::getNumProperties() { - return lPropNames.getSize(); + return hProperties.size(); } - +/* const char *XmlNode::getPropertyName( int nIndex ) { std::string *tmp = ((std::string *)lPropNames[nIndex]); @@ -172,15 +129,12 @@ const char *XmlNode::getProperty( int nIndex ) return NULL; return tmp->c_str(); } - -const char *XmlNode::getProperty( const char *sName ) +*/ +Bu::FString XmlNode::getProperty( const Bu::FString &sName ) { - const char *tmp = (const char *)hProperties[sName]; - if( tmp == NULL ) - return NULL; - return tmp; + return hProperties[sName]; } - +/* void XmlNode::deleteProperty( int nIndex ) { hProperties.del( ((std::string *)lPropNames[nIndex])->c_str() ); @@ -194,29 +148,33 @@ void XmlNode::deleteProperty( int nIndex ) bool XmlNode::hasChildren() { - return lChildren.getSize()>0; -} + return hChildren.getSize()>0; +}*/ int XmlNode::getNumChildren() { return lChildren.getSize(); } - +/* XmlNode *XmlNode::getChild( int nIndex ) { return (XmlNode *)lChildren[nIndex]; } - -XmlNode *XmlNode::getChild( const char *sName, int nSkip ) +*/ +XmlNode *XmlNode::getChild( const Bu::FString &sName, int nSkip ) { - return (XmlNode *)hChildren.get( sName, nSkip ); + if( !hChildren.has( sName ) ) + return NULL; + + Bu::List::iterator i = hChildren[sName]->begin(); + return *i; } -const char *XmlNode::getName() +Bu::FString XmlNode::getName() { - return sName.c_str(); + return sName; } - +/* void XmlNode::deleteNode( int nIndex, const char *sReplacementText ) { XmlNode *xRet = detatchNode( nIndex, sReplacementText ); @@ -442,4 +400,4 @@ void XmlNode::deleteNodeKeepChildren( int nIndex ) void XmlNode::replaceNodeWithChildren( int nIndex, XmlNode *pNewNode ) { } - +*/ diff --git a/src/xmlnode.h b/src/xmlnode.h index 7525306..c895cd8 100644 --- a/src/xmlnode.h +++ b/src/xmlnode.h @@ -2,8 +2,9 @@ #define XMLNODE #include -#include "linkedlist.h" -#include "hashtable.h" +#include "bu/list.h" +#include "bu/hash.h" +#include "bu/fstring.h" /** * Maintains all data pertient to an XML node, including sub-nodes and content. @@ -25,9 +26,8 @@ public: *@param sContent The initial content string. */ XmlNode( - const char *sName=NULL, - XmlNode *pParent = NULL, - const char *sContent=NULL + const Bu::FString &sName, + XmlNode *pParent=NULL ); /** @@ -39,7 +39,7 @@ public: * Change the name of the node. *@param sName The new name of the node. */ - void setName( const char *sName ); + //void setName( const char *sName ); /** * Construct a new node and add it as a child to this node, also return a @@ -48,7 +48,7 @@ public: *@param sContent The initial content of the new node. *@returns A pointer to the newly created child node. */ - XmlNode *addChild( const char *sName, const char *sContent=NULL ); + XmlNode *addChild( const Bu::FString &sName ); /** * Add an already created XmlNode as a child to this node. The new child @@ -65,7 +65,7 @@ public: * in use will overwrite that property. *@param sValue The textual value of the property. */ - void addProperty( const char *sName, const char *sValue ); + void addProperty( const Bu::FString &sName, const Bu::FString &sValue ); /** * Get a pointer to the parent node, if any. @@ -85,14 +85,6 @@ public: */ int getNumChildren(); - /** - * Get a child node at a specific index. - *@param nIndex The zero-based index of the child to retreive. - *@returns A pointer to the child, or NULL if you requested an invalid - * index. - */ - XmlNode *getChild( int nIndex ); - /** * Get a child with the specified name, and possibly skip value. For an * explination of skip values see the HashTable. @@ -101,14 +93,14 @@ public: *@returns A pointer to the child, or NULL if no child with that name was * found. */ - XmlNode *getChild( const char *sName, int nSkip=0 ); + XmlNode *getChild( const Bu::FString &sName, int nSkip=0 ); /** * Get a pointer to the name of this node. Do not change this, use setName * instead. *@returns A pointer to the name of this node. */ - const char *getName(); + Bu::FString getName(); /** * Set the content of this node, optionally at a specific index. Using the @@ -116,14 +108,7 @@ public: *@param sContent The content string to use. *@param nIndex The index of the content. */ - void setContent( const char *sContent, int nIndex=-1 ); - - /** - * Get the content string at a given index, or zero for initial content. - *@param nIndex The index of the content. - *@returns A pointer to the content at that location. - */ - const char *getContent( int nIndex = 0 ); + //void setContent( const char *sContent, int nIndex=-1 ); /** * Get the number of properties in this node. @@ -131,37 +116,13 @@ public: */ int getNumProperties(); - /** - * Get a property's name by index. - *@param nIndex The index of the property to examine. - *@returns A pointer to the name of the property specified, or NULL if none - * found. - */ - const char *getPropertyName( int nIndex ); - - /** - * Get a proprty's value by index. - *@param nIndex The index of the property to examine. - *@returns A pointer to the value of the property specified, or NULL if none - * found. - */ - const char *getProperty( int nIndex ); - /** * Get a propery's value by name. *@param sName The name of the property to examine. *@returns A pointer to the value of the property specified, or NULL if none * found. */ - const char *getProperty( const char *sName ); - - /** - * Delete a property by index. - *@param nIndex The index of the property to delete. - *@returns True if the property was found and deleted, false if it wasn't - * found. - */ - void deleteProperty( int nIndex ); + Bu::FString getProperty( const Bu::FString &sName ); /** * Delete a child node, possibly replacing it with some text. This actually @@ -171,7 +132,7 @@ public: *@returns True of the node was found, and deleted, false if it wasn't * found. */ - void deleteNode( int nIndex, const char *sReplacementText = NULL ); + //void deleteNode( int nIndex, const char *sReplacementText = NULL ); /** * Delete a given node, but move all of it's children and content up to @@ -180,7 +141,7 @@ public: *@param nIndex The node to delete. *@returns True if the node was found and deleted, false if it wasn't. */ - void deleteNodeKeepChildren( int nIndex ); + //void deleteNodeKeepChildren( int nIndex ); /** * Detatch a given child node from this node. This effectively works just @@ -192,7 +153,7 @@ public: *@returns A pointer to the newly detatched node, which then passes * ownership to the caller. */ - XmlNode *detatchNode( int nIndex, const char *sReplacementText = NULL ); + //XmlNode *detatchNode( int nIndex, const char *sReplacementText = NULL ); /** * Replace a given node with a different node that is not currently owned by @@ -201,7 +162,7 @@ public: *@param pNewNode The new node to replace the old node with. *@returns True if the node was found and replaced, false if it wasn't. */ - void replaceNode( int nIndex, XmlNode *pNewNode ); + //void replaceNode( int nIndex, XmlNode *pNewNode ); /** * Replace a given node with the children and content of a given node. @@ -210,24 +171,34 @@ public: * replace the node specified by nIndex. *@returns True if the node was found and replaced, false if it wasn't. */ - void replaceNodeWithChildren( int nIndex, XmlNode *pNewNode ); + //void replaceNodeWithChildren( int nIndex, XmlNode *pNewNode ); /** * Get a copy of this node and all children. getCopy is recursive, so * beware copying large trees of xml. *@returns A newly created copy of this node and all of it's children. */ - XmlNode *getCopy(); + //XmlNode *getCopy(); + + enum ChildType + { + typeNode, + typeContent + }; private: - std::string sName; /**< The name of the node. */ - std::string *sPreContent; /**< The content that goes before any node. */ - LinkedList lChildren; /**< The children. */ - LinkedList lPostContent; /**< The content that comes after children. */ - HashTable hProperties; /**< Property hashtable. */ - HashTable hChildren; /**< Children hashtable. */ - LinkedList lPropNames; /**< List of property names. */ - LinkedList lPropValues; /**< List of property values. */ + typedef struct + { + uint8_t nType; + union { + XmlNode *pNode; + Bu::FString *pContent; + }; + } Child; + Bu::FString sName; /**< The name of the node. */ + Bu::List lChildren; /**< The children. */ + Bu::Hash hProperties; /**< Property hashtable. */ + Bu::Hash > hChildren; /**< Children hashtable. */ XmlNode *pParent; /**< A pointer to the parent of this node. */ int nCurContent; /**< The current content we're on, for using the -1 on setContent. */ diff --git a/src/xmlreader.cpp b/src/xmlreader.cpp index 18df69c..38cad5f 100644 --- a/src/xmlreader.cpp +++ b/src/xmlreader.cpp @@ -1,32 +1,49 @@ -#include "xmlreader.h" -#include "exceptions.h" +#include "bu/xmlreader.h" +#include "bu/exceptions.h" #include -#include "hashfunctionstring.h" -XmlReader::XmlReader( bool bStrip ) : - bStrip( bStrip ), - htEntity( new HashFunctionString(), 11 ) +XmlReader::XmlReader( Bu::Stream &sIn, bool bStrip ) : + sIn( sIn ), + bStrip( bStrip ) { + buildDoc(); } XmlReader::~XmlReader() { - void *i = htEntity.getFirstItemPos(); - while( (i = htEntity.getNextItemPos( i ) ) ) +} + +char XmlReader::getChar( int nIndex ) +{ + if( sBuf.getSize() <= nIndex ) { - free( (char *)(htEntity.getItemID( i )) ); - delete (StaticString *)htEntity.getItemData( i ); + int nInc = nIndex-sBuf.getSize()+1; + char *buf = new char[nInc]; + sIn.read( buf, nInc ); + sBuf.append( buf, nInc ); + delete[] buf; } + + return sBuf[nIndex]; } -void XmlReader::addEntity( const char *name, const char *value ) +void XmlReader::usedChar( int nAmnt ) { - if( htEntity[name] ) return; - - char *sName = strdup( name ); - StaticString *sValue = new StaticString( value ); + if( nAmnt >= sBuf.getSize() ) + { + sBuf.clear(); + } + else + { + char *s = sBuf.getStr(); + memcpy( s, s+nAmnt, sBuf.getSize()-nAmnt ); + sBuf.resize( sBuf.getSize()-nAmnt ); + } +} - htEntity.insert( sName, sValue ); +void XmlReader::addEntity( const Bu::FString &name, const Bu::FString &value ) +{ + htEntity[name] = value; } #define gcall( x ) if( x == false ) return false; @@ -99,7 +116,7 @@ void XmlReader::entity() { usedChar( 2 ); ws(); - std::string buf; + Bu::FString buf; for(;;) { char chr = getChar(); @@ -111,7 +128,7 @@ void XmlReader::entity() if( strcmp( buf.c_str(), "ENTITY") == 0 ) { ws(); - std::string name; + Bu::FString name; for(;;) { char chr = getChar(); @@ -124,21 +141,19 @@ void XmlReader::entity() usedChar(); if( quot != '\'' && quot != '\"' ) { - throw XmlException( + throw Bu::XmlException( "Only quoted entity values are supported." ); } - std::string value; + Bu::FString value; for(;;) { char chr = getChar(); usedChar(); if( chr == '&' ) { - StaticString *tmp = getEscape(); - if( tmp == NULL ) throw XmlException("Entity thing"); - value += tmp->getString(); - delete tmp; + Bu::FString tmp = getEscape(); + value += tmp; } else if( chr == quot ) { @@ -158,7 +173,7 @@ void XmlReader::entity() } else { - throw XmlException( + throw Bu::XmlException( "Malformed ENTITY: unexpected '%c' found.", getChar() ); @@ -166,7 +181,7 @@ void XmlReader::entity() } else { - throw XmlException( + throw Bu::XmlException( "Unsupported header symbol: %s", buf.c_str() ); @@ -203,12 +218,12 @@ bool XmlReader::node() } else { - throw XmlException("Close node in singleNode malformed!"); + throw Bu::XmlException("Close node in singleNode malformed!"); } } else { - throw XmlException("Close node expected, but not found."); + throw Bu::XmlException("Close node expected, but not found."); return false; } @@ -224,7 +239,7 @@ bool XmlReader::startNode() if( getChar() == '/' ) { // Heh, it's actually a close node, go figure - FlexBuf fbName; + Bu::FString sName; usedChar(); gcall( ws() ); @@ -235,19 +250,19 @@ bool XmlReader::startNode() { // Here we actually compare the name we got to the name // we already set, they have to match exactly. - if( !strcasecmp( getCurrent()->getName(), fbName.getData() ) ) + if( getCurrent()->getName() == sName ) { closeNode(); break; } else { - throw XmlException("Got a mismatched node close tag."); + throw Bu::XmlException("Got a mismatched node close tag."); } } else { - fbName.appendData( chr ); + sName += chr; usedChar(); } } @@ -260,13 +275,13 @@ bool XmlReader::startNode() } else { - throw XmlException("Got extra junk data instead of node close tag."); + throw Bu::XmlException("Got extra junk data instead of node close tag."); } } else { // We're good, format is consistant - addNode(); + //addNode(); // Skip extra whitespace gcall( ws() ); @@ -278,7 +293,7 @@ bool XmlReader::startNode() } else { - throw XmlException("Expected to find node opening char, '<'."); + throw Bu::XmlException("Expected to find node opening char, '<'."); } return true; @@ -286,19 +301,19 @@ bool XmlReader::startNode() bool XmlReader::name() { - FlexBuf fbName; + Bu::FString sName; while( true ) { char chr = getChar(); if( isws( chr ) || chr == '>' || chr == '/' ) { - setName( fbName.getData() ); + addNode( sName ); return true; } else { - fbName.appendData( chr ); + sName += chr; usedChar(); } } @@ -325,7 +340,7 @@ bool XmlReader::paramlist() return true; } -StaticString *XmlReader::getEscape() +Bu::FString XmlReader::getEscape() { if( getChar( 1 ) == '#' ) { @@ -349,12 +364,12 @@ StaticString *XmlReader::getEscape() buf[0] = (char)strtol( buf, (char **)NULL, base ); buf[1] = '\0'; - return new StaticString( buf ); + return buf; } else { // ...otherwise replace with the appropriate string... - std::string buf; + Bu::FString buf; usedChar(); for(;;) { @@ -364,18 +379,14 @@ StaticString *XmlReader::getEscape() buf += cbuf; } - StaticString *tmp = (StaticString *)htEntity[buf.c_str()]; - if( tmp == NULL ) return NULL; - - StaticString *ret = new StaticString( *tmp ); - return ret; + return htEntity[buf]; } } bool XmlReader::param() { - FlexBuf fbName; - FlexBuf fbValue; + Bu::FString sName; + Bu::FString sValue; while( true ) { @@ -386,7 +397,7 @@ bool XmlReader::param() } else { - fbName.appendData( chr ); + sName.append( chr ); usedChar(); } } @@ -411,21 +422,18 @@ bool XmlReader::param() if( chr == '"' ) { usedChar(); - addProperty( fbName.getData(), fbValue.getData() ); + addProperty( sName.getStr(), sValue.getStr() ); return true; } else { if( chr == '&' ) { - StaticString *tmp = getEscape(); - if( tmp == NULL ) return false; - fbValue.appendData( tmp->getString() ); - delete tmp; + sValue += getEscape(); } else { - fbValue.appendData( chr ); + sValue += chr; usedChar(); } } @@ -439,21 +447,18 @@ bool XmlReader::param() chr = getChar(); if( isws( chr ) || chr == '/' || chr == '>' ) { - addProperty( fbName.getData(), fbValue.getData() ); + addProperty( sName.getStr(), sValue.getStr() ); return true; } else { if( chr == '&' ) { - StaticString *tmp = getEscape(); - if( tmp == NULL ) return false; - fbValue.appendData( tmp->getString() ); - delete tmp; + sValue += getEscape(); } else { - fbValue.appendData( chr ); + sValue += chr; usedChar(); } } @@ -462,7 +467,7 @@ bool XmlReader::param() } else { - throw XmlException("Expected an equals to seperate the params."); + throw Bu::XmlException("Expected an equals to seperate the params."); return false; } @@ -471,7 +476,7 @@ bool XmlReader::param() bool XmlReader::content() { - FlexBuf fbContent; + Bu::FString sContent; if( bStrip ) gcall( ws() ); @@ -482,37 +487,37 @@ bool XmlReader::content() { if( getChar(1) == '/' ) { - if( fbContent.getLength() > 0 ) + if( sContent.getSize() > 0 ) { if( bStrip ) { int j; - for( j = fbContent.getLength()-1; isws(fbContent.getData()[j]); j-- ); - ((char *)fbContent.getData())[j+1] = '\0'; + for( j = sContent.getSize()-1; isws(sContent[j]); j-- ); + sContent[j+1] = '\0'; } - setContent( fbContent.getData() ); + setContent( sContent.getStr() ); } usedChar( 2 ); gcall( ws() ); - FlexBuf fbName; + Bu::FString sName; while( true ) { chr = getChar(); if( isws( chr ) || chr == '>' ) { - if( !strcasecmp( getCurrent()->getName(), fbName.getData() ) ) + if( !strcasecmp( getCurrent()->getName().getStr(), sName.getStr() ) ) { closeNode(); break; } else { - throw XmlException("Mismatched close tag found: <%s> to <%s>.", getCurrent()->getName(), fbName.getData() ); + throw Bu::XmlException("Mismatched close tag found: <%s> to <%s>.", getCurrent()->getName().getStr(), sName.getStr() ); } } else { - fbName.appendData( chr ); + sName += chr; usedChar(); } } @@ -524,7 +529,7 @@ bool XmlReader::content() } else { - throw XmlException("Malformed close tag."); + throw Bu::XmlException("Malformed close tag."); } } else if( getChar(1) == '!' ) @@ -534,7 +539,7 @@ bool XmlReader::content() getChar(3) != '-' ) { // Not a valid XML comment - throw XmlException("Malformed comment start tag found."); + throw Bu::XmlException("Malformed comment start tag found."); } usedChar( 4 ); @@ -549,7 +554,7 @@ bool XmlReader::content() // The next one has to be a '>' now if( getChar( 2 ) != '>' ) { - throw XmlException("Malformed comment close tag found. You cannot have a '--' that isn't followed by a '>' in a comment."); + throw Bu::XmlException("Malformed comment close tag found. You cannot have a '--' that isn't followed by a '>' in a comment."); } usedChar( 3 ); break; @@ -569,16 +574,16 @@ bool XmlReader::content() } else { - if( fbContent.getLength() > 0 ) + if( sContent.getSize() > 0 ) { if( bStrip ) { int j; - for( j = fbContent.getLength()-1; isws(fbContent.getData()[j]); j-- ); - ((char *)fbContent.getData())[j+1] = '\0'; + for( j = sContent.getSize()-1; isws(sContent[j]); j-- ); + sContent[j+1] = '\0'; } - setContent( fbContent.getData() ); - fbContent.clearData(); + setContent( sContent.getStr() ); + sContent.clear(); } gcall( node() ); } @@ -587,14 +592,11 @@ bool XmlReader::content() } else if( chr == '&' ) { - StaticString *tmp = getEscape(); - if( tmp == NULL ) return false; - fbContent.appendData( tmp->getString() ); - delete tmp; + sContent += getEscape(); } else { - fbContent.appendData( chr ); + sContent += chr; usedChar(); } } diff --git a/src/xmlreader.h b/src/xmlreader.h index c8f7202..7c85ddb 100644 --- a/src/xmlreader.h +++ b/src/xmlreader.h @@ -2,10 +2,10 @@ #define XMLREADER #include -#include "xmldocument.h" -#include "flexbuf.h" -#include "hashtable.h" -#include "staticstring.h" +#include "bu/xmldocument.h" +#include "bu/hash.h" +#include "bu/fstring.h" +#include "bu/stream.h" /** * Takes care of reading in xml formatted data from a file. This could/should @@ -32,7 +32,7 @@ public: * in content, a-la html. *@param bStrip Strip out leading and trailing whitespace? */ - XmlReader( bool bStrip=false ); + XmlReader( Bu::Stream &sIn, bool bStrip=false ); /** * Destroy this XmlReader. @@ -54,12 +54,12 @@ private: *@returns A single character at the requested position, or 0 for end of * stream. */ - virtual char getChar( int nIndex = 0 ) = 0; + virtual char getChar( int nIndex = 0 ); /** * Called to increment the current stream position by a single character. */ - virtual void usedChar( int nAmnt = 1) = 0; + virtual void usedChar( int nAmnt = 1 ); /** * Automoton function: is whitespace. @@ -108,9 +108,9 @@ private: *@param name The name of the entity *@param value The value of the entity */ - void addEntity( const char *name, const char *value ); + void addEntity( const Bu::FString &name, const Bu::FString &value ); - StaticString *getEscape(); + Bu::FString getEscape(); /** * Automoton function: paramlist. Processes a list of node params. @@ -130,12 +130,15 @@ private: */ bool content(); - FlexBuf fbContent; /**< buffer for the current node's content. */ - FlexBuf fbParamName; /**< buffer for the current param's name. */ - FlexBuf fbParamValue; /**< buffer for the current param's value. */ - bool bStrip; /**< Are we stripping whitespace? */ + Bu::FString sContent; /**< buffer for the current node's content. */ + Bu::FString sParamName; /**< buffer for the current param's name. */ + Bu::FString sParamValue; /**< buffer for the current param's value. */ + Bu::Stream &sIn; + bool bStrip; /**< Are we stripping whitespace? */ - HashTable htEntity; /**< Entity type definitions. */ + Bu::Hash htEntity; /**< Entity type definitions. */ + + Bu::FString sBuf; }; #endif diff --git a/src/xmlwriter.cpp b/src/xmlwriter.cpp index 56880b6..7dc6ca9 100644 --- a/src/xmlwriter.cpp +++ b/src/xmlwriter.cpp @@ -2,17 +2,10 @@ #include #include "xmlwriter.h" -XmlWriter::XmlWriter( const char *sIndent, XmlNode *pRoot ) : - XmlDocument( pRoot ) +XmlWriter::XmlWriter( const Bu::FString &sIndent, XmlNode *pRoot ) : + XmlDocument( pRoot ), + sIndent( sIndent ) { - if( sIndent == NULL ) - { - this->sIndent = ""; - } - else - { - this->sIndent = sIndent; - } } XmlWriter::~XmlWriter() @@ -24,7 +17,7 @@ void XmlWriter::write() write( getRoot(), sIndent.c_str() ); } -void XmlWriter::write( XmlNode *pRoot, const char *sIndent ) +void XmlWriter::write( XmlNode *pRoot, const Bu::FString &sIndent ) { writeNode( pRoot, 0, sIndent ); } @@ -39,7 +32,7 @@ void XmlWriter::closeNode() } } -void XmlWriter::writeIndent( int nIndent, const char *sIndent ) +void XmlWriter::writeIndent( int nIndent, const Bu::FString &sIndent ) { if( sIndent == NULL ) return; for( int j = 0; j < nIndent; j++ ) @@ -48,26 +41,27 @@ void XmlWriter::writeIndent( int nIndent, const char *sIndent ) } } -std::string XmlWriter::escape( std::string sIn ) +Bu::FString XmlWriter::escape( const Bu::FString &sIn ) { - std::string sOut; + Bu::FString sOut; - std::string::const_iterator i; - for( i = sIn.begin(); i != sIn.end(); i++ ) + int nMax = sIn.getSize(); + for( int j = 0; j < nMax; j++ ) { - if( ((*i >= ' ' && *i <= '9') || - (*i >= 'a' && *i <= 'z') || - (*i >= 'A' && *i <= 'Z') ) && - (*i != '\"' && *i != '\'' && *i != '&') + char c = sIn[j]; + if( ((c >= ' ' && c <= '9') || + (c >= 'a' && c <= 'z') || + (c >= 'A' && c <= 'Z') ) && + (c != '\"' && c != '\'' && c != '&') ) { - sOut += *i; + sOut += c; } else { sOut += "&#"; char buf[4]; - sprintf( buf, "%u", (unsigned char)*i ); + sprintf( buf, "%u", (unsigned char)c ); sOut += buf; sOut += ';'; } @@ -76,19 +70,19 @@ std::string XmlWriter::escape( std::string sIn ) return sOut; } -void XmlWriter::writeNodeProps( XmlNode *pNode, int nIndent, const char *sIndent ) +void XmlWriter::writeNodeProps( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ) { for( int j = 0; j < pNode->getNumProperties(); j++ ) { writeString(" "); - writeString( pNode->getPropertyName( j ) ); + //writeString( pNode->getPropertyName( j ) ); writeString("=\""); - writeString( escape( pNode->getProperty( j ) ).c_str() ); + //writeString( escape( pNode->getProperty( j ) ).c_str() ); writeString("\""); } } -void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) +void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ) { if( pNode->hasChildren() ) { @@ -96,15 +90,15 @@ void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) writeString("<"); writeString( pNode->getName() ); writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent ) + if( sIndent != "" ) writeString(">\n"); else writeString(">"); - +/* if( pNode->getContent( 0 ) ) { writeIndent( nIndent+1, sIndent ); - if( sIndent ) + if( sIndent != "" ) { writeString( pNode->getContent( 0 ) ); writeString("\n"); @@ -129,9 +123,9 @@ void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) writeString( pNode->getContent( j+1 ) ); } } - +*/ writeIndent( nIndent, sIndent ); - if( sIndent ) + if( sIndent != "" ) { writeString("getName() ); @@ -143,7 +137,7 @@ void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) writeString( pNode->getName() ); writeString(">"); } - } + }/* else if( pNode->getContent() ) { writeIndent( nIndent, sIndent ); @@ -157,14 +151,14 @@ void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) writeString(">"); if( sIndent ) writeString("\n"); - } + }*/ else { writeIndent( nIndent, sIndent ); writeString("<"); writeString( pNode->getName() ); writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent ) + if( sIndent != "" ) writeString("/>\n"); else writeString("/>"); diff --git a/src/xmlwriter.h b/src/xmlwriter.h index c48e810..7e3c876 100644 --- a/src/xmlwriter.h +++ b/src/xmlwriter.h @@ -31,7 +31,7 @@ public: * this to a tab or some spaces it will never effect the content of your * file. */ - XmlWriter( const char *sIndent=NULL, XmlNode *pRoot=NULL ); + XmlWriter( const Bu::FString &sIndent="", XmlNode *pRoot=NULL ); /** * Destroy the writer. @@ -49,16 +49,16 @@ public: void write(); private: - std::string sIndent; /**< The indent string */ + Bu::FString sIndent; /**< The indent string */ - std::string escape( std::string sIn ); + Bu::FString escape( const Bu::FString &sIn ); /** * Write the file. *@param pNode The root node *@param sIndent The indent text. */ - void write( XmlNode *pNode, const char *sIndent=NULL ); + void write( XmlNode *pNode, const Bu::FString &sIndent ); /** * Write a node in the file, including children. @@ -66,7 +66,7 @@ private: *@param nIndent The indent level (the number of times to include sIndent) *@param sIndent The indent text. */ - void writeNode( XmlNode *pNode, int nIndent, const char *sIndent ); + void writeNode( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ); /** * Write the properties of a node. @@ -74,14 +74,14 @@ private: *@param nIndent The indent level of the containing node *@param sIndent The indent text. */ - void writeNodeProps( XmlNode *pNode, int nIndent, const char *sIndent ); + void writeNodeProps( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ); /** * Called to write the actual indent. *@param nIndent The indent level. *@param sIndent The indent text. */ - void writeIndent( int nIndent, const char *sIndent ); + void writeIndent( int nIndent, const Bu::FString &sIndent ); /** * This is the function that must be overridden in order to use this class. @@ -90,7 +90,7 @@ private: * will break the XML formatting. *@param sString The string data to write to the output. */ - virtual void writeString( const char *sString ) = 0; + virtual void writeString( const Bu::FString &sString ) = 0; }; #endif -- cgit v1.2.3 From dda94f3b53e02e117e6eb5758afa1410e1664c9f Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Tue, 15 May 2007 05:25:19 +0000 Subject: SPtr is now Bu::ified, and the List class now acts the way we think const lists should act, you can't change anything in there. I'm still debating changing the const_iterator to a constIterator, or something else that's more Bu::worthy. Heh, the namespaces are funny...ok...I'm really tired. --- src/list.h | 214 ++++++++++++++++++++++++++++++++++++++++++++++++----- src/old/sptr.cpp | 1 - src/old/sptr.h | 99 ------------------------- src/serversocket.h | 10 ++- src/sptr.cpp | 1 + src/sptr.h | 147 ++++++++++++++++++++++++++++++++++++ src/tests/list.cpp | 31 ++++++++ 7 files changed, 382 insertions(+), 121 deletions(-) delete mode 100644 src/old/sptr.cpp delete mode 100644 src/old/sptr.h create mode 100644 src/sptr.cpp create mode 100644 src/sptr.h (limited to 'src/tests') diff --git a/src/list.h b/src/list.h index ec63496..4d16872 100644 --- a/src/list.h +++ b/src/list.h @@ -13,6 +13,15 @@ namespace Bu ListLink *pNext; ListLink *pPrev; }; + + /** + * Linked list template container. This class is similar to the stl list + * class except for a few minor changes. First, it doesn't mimic a stack or + * queue, use the Stack or Queue clasess for that. Second, when const, all + * members are only accessable const. Third, erasing a location does not + * invalidate the iterator, it simply points to the next valid location, or + * end() if there are no more. + */ template, typename linkalloc=std::allocator > > class List { @@ -23,15 +32,59 @@ namespace Bu public: List() : pFirst( NULL ), - pLast( NULL ) + pLast( NULL ), + nSize( 0 ) + { + } + + List( const MyType &src ) : + pFirst( NULL ), + pLast( NULL ), + nSize( 0 ) + { + for( Link *pCur = src.pFirst; pCur; pCur = pCur->pNext ) + { + append( *pCur->pValue ); + } + } + + ~List() + { + clear(); + } + + MyType &operator=( const MyType &src ) { + clear(); + for( Link *pCur = src.pFirst; pCur; pCur = pCur->pNext ) + { + append( *pCur->pValue ); + } + } + + void clear() + { + Link *pCur = pFirst; + for(;;) + { + if( pCur == NULL ) break; + va.destroy( pCur->pValue ); + va.deallocate( pCur->pValue, sizeof( value ) ); + Link *pTmp = pCur->pNext; + la.destroy( pCur ); + la.deallocate( pCur, sizeof( Link ) ); + pCur = pTmp; + } + pFirst = pLast = NULL; + nSize = 0; } - void append( value v ) + void append( const value &v ) { Link *pNew = la.allocate( sizeof( Link ) ); pNew->pValue = va.allocate( sizeof( value ) ); va.construct( pNew->pValue, v ); + nSize++; if( pFirst == NULL ) { // Empty list @@ -47,11 +100,12 @@ namespace Bu } } - void prepend( value v ) + void prepend( const value &v ) { Link *pNew = la.allocate( sizeof( Link ) ); pNew->pValue = va.allocate( sizeof( value ) ); va.construct( pNew->pValue, v ); + nSize++; if( pFirst == NULL ) { // Empty list @@ -83,22 +137,22 @@ namespace Bu } public: - bool operator==( const iterator &oth ) + bool operator==( const iterator &oth ) const { return ( pLink == oth.pLink ); } - bool operator==( const Link *pOth ) + bool operator==( const Link *pOth ) const { return ( pLink == pOth ); } - bool operator!=( const iterator &oth ) + bool operator!=( const iterator &oth ) const { return ( pLink != oth.pLink ); } - bool operator!=( const Link *pOth ) + bool operator!=( const Link *pOth ) const { return ( pLink != pOth ); } @@ -110,40 +164,128 @@ namespace Bu value *operator->() { - return pLink->pValue(); + return pLink->pValue; } - iterator operator++() + iterator &operator++() { if( pLink != NULL ) pLink = pLink->pNext; return *this; } - iterator operator--() + iterator &operator--() { if( pLink != NULL ) pLink = pLink->pPrev; return *this; } - iterator operator++( int ) + iterator &operator++( int ) { if( pLink != NULL ) pLink = pLink->pNext; return *this; } - iterator operator--( int ) + iterator &operator--( int ) { if( pLink != NULL ) pLink = pLink->pPrev; return *this; } - iterator operator=( const iterator &oth ) + iterator &operator=( const iterator &oth ) { pLink = oth.pLink; + return *this; + } + }; + + typedef struct const_iterator + { + friend class List; + private: + Link *pLink; + const_iterator() : + pLink( NULL ) + { + } + + const_iterator( Link *pLink ) : + pLink( pLink ) + { + } + + public: + bool operator==( const const_iterator &oth ) const + { + return ( pLink == oth.pLink ); + } + + bool operator==( const Link *pOth ) const + { + return ( pLink == pOth ); + } + + bool operator!=( const const_iterator &oth ) const + { + return ( pLink != oth.pLink ); + } + + bool operator!=( const Link *pOth ) const + { + return ( pLink != pOth ); + } + + const value &operator*() + { + return *(pLink->pValue); + } + + const value *operator->() + { + return pLink->pValue; + } + + const_iterator &operator++() + { + if( pLink != NULL ) + pLink = pLink->pNext; + return *this; + } + + const_iterator &operator--() + { + if( pLink != NULL ) + pLink = pLink->pPrev; + return *this; + } + + const_iterator &operator++( int ) + { + if( pLink != NULL ) + pLink = pLink->pNext; + return *this; + } + + const_iterator &operator--( int ) + { + if( pLink != NULL ) + pLink = pLink->pPrev; + return *this; + } + + const_iterator &operator=( const iterator &oth ) + { + pLink = oth.pLink; + return *this; + } + + const_iterator &operator=( const const_iterator &oth ) + { + pLink = oth.pLink; + return *this; } }; @@ -152,17 +294,50 @@ namespace Bu return iterator( pFirst ); } - const Link *end() + const const_iterator begin() const + { + return const_iterator( pFirst ); + } + + const Link *end() const { return NULL; } - int getSize() + void erase( iterator &i ) + { + Link *pCur = i.pLink; + Link *pPrev = pCur->pPrev; + if( pPrev == NULL ) + { + va.destroy( pCur->pValue ); + va.deallocate( pCur->pValue, sizeof( value ) ); + pFirst = pCur->pNext; + la.destroy( pCur ); + la.deallocate( pCur, sizeof( Link ) ); + if( pFirst == NULL ) + pLast = NULL; + nSize--; + i.pLink = pFirst; + } + else + { + va.destroy( pCur->pValue ); + va.deallocate( pCur->pValue, sizeof( value ) ); + Link *pTmp = pCur->pNext; + la.destroy( pCur ); + la.deallocate( pCur, sizeof( Link ) ); + pPrev->pNext = pTmp; + if( pTmp != NULL ) + pTmp->pPrev = pPrev; + nSize--; + i.pLink = pTmp; + } + } + + int getSize() const { - int j = 0; - for( Link *pCur = pFirst; pCur; pCur = pCur->pNext ) - j++; - return j; + return nSize; } private: @@ -170,6 +345,7 @@ namespace Bu Link *pLast; linkalloc la; valuealloc va; + int nSize; }; } diff --git a/src/old/sptr.cpp b/src/old/sptr.cpp deleted file mode 100644 index 7f5e894..0000000 --- a/src/old/sptr.cpp +++ /dev/null @@ -1 +0,0 @@ -#include "sptr.h" diff --git a/src/old/sptr.h b/src/old/sptr.h deleted file mode 100644 index deae94d..0000000 --- a/src/old/sptr.h +++ /dev/null @@ -1,99 +0,0 @@ -#ifndef SPTR_H -#define SPTR_H - -#include -#include - -template -class SPtr -{ -public: - SPtr() : - pRefCnt( NULL ), - pData( NULL ) - { - } - - ~SPtr() - { - decCount(); - } - - SPtr( const SPtr &src ) : - pRefCnt( src.pRefCnt ), - pData( src.pData ) - { - if( pRefCnt ) - (*pRefCnt) += 1; - } - - SPtr( T *pSrc ) : - pRefCnt( NULL ), - pData( pSrc ) - { - pRefCnt = new int32_t; - (*pRefCnt) = 1; - } - - int32_t count() - { - return *pRefCnt; - } - - T *operator->() const - { - return pData; - } - - T *operator*() const - { - return pData; - } - - SPtr operator=( const SPtr &src ) - { - decCount(); - pRefCnt = src.pRefCnt; - pData = src.pData; - (*pRefCnt) += 1; - - return *this; - } - - bool operator==( const SPtr &src ) - { - return pData == src.pData; - } - - operator bool() - { - return pRefCnt != NULL; - } - - bool isSet() - { - return pRefCnt != NULL; - } - -private: - void decCount() - { - if( pRefCnt ) - { - (*pRefCnt) -= 1; - //printf("Decrementing ref-count to %d\n", *pRefCnt ); - if( (*pRefCnt) == 0 ) - { - delete pRefCnt; - delete pData; - pRefCnt = NULL; - pData = NULL; - } - } - } - - int32_t *pRefCnt; - T *pData; -}; - -#endif diff --git a/src/serversocket.h b/src/serversocket.h index 9a26e2d..f146d91 100644 --- a/src/serversocket.h +++ b/src/serversocket.h @@ -2,13 +2,19 @@ #define SERVER_SOCKET_H #include -#include "fstring.h" -#include "socket.h" +#include "bu/fstring.h" namespace Bu { /** + * A single tcp/ip server socket. When created the server socket will bind + * to the specified interface and port, and immediately begin listening for + * connections. When connections come in they are pooled by the networking + * drivers in the kernel until they are accepted, this means that failure + * to keep space in the connection pool will result in connection refusals. * + * Although the accept function returns an integral file descriptor, it is + * designed to be used with the Socket class. */ class ServerSocket { diff --git a/src/sptr.cpp b/src/sptr.cpp new file mode 100644 index 0000000..8ea7f8f --- /dev/null +++ b/src/sptr.cpp @@ -0,0 +1 @@ +#include "bu/sptr.h" diff --git a/src/sptr.h b/src/sptr.h new file mode 100644 index 0000000..faa8524 --- /dev/null +++ b/src/sptr.h @@ -0,0 +1,147 @@ +#ifndef SPTR_H +#define SPTR_H + +#include +#include + +namespace Bu +{ + template class SPtr; + template< typename Tb, typename Ta > SPtr SPtrCast( SPtr src ); + + template + class SPtr + { + template + friend SPtr SPtrCast( SPtr pt ); + public: + SPtr() : + pRefCnt( NULL ), + pData( NULL ) + { + } + + ~SPtr() + { + decCount(); + } + + SPtr( const SPtr &src ) : + pRefCnt( src.pRefCnt ), + pData( src.pData ) + { + if( pRefCnt ) + (*pRefCnt) += 1; + } + + SPtr( T *pSrc ) : + pRefCnt( NULL ), + pData( pSrc ) + { + if( pData ) + { + pRefCnt = new int32_t; + (*pRefCnt) = 1; + } + } + + int32_t count() const + { + return *pRefCnt; + } + + const T *operator->() const + { + return pData; + } + + const T &operator*() const + { + return *pData; + } + + T *operator->() + { + return pData; + } + + T &operator*() + { + return *pData; + } + + SPtr operator=( const SPtr &src ) + { + decCount(); + pRefCnt = src.pRefCnt; + pData = src.pData; + if( pRefCnt ) + (*pRefCnt) += 1; + + return *this; + } + + const SPtr operator=( const SPtr &src ) const + { + decCount(); + pRefCnt = src.pRefCnt; + pData = src.pData; + if( pRefCnt ) + (*pRefCnt) += 1; + + return *this; + } + + bool operator==( const SPtr &src ) const + { + return pData == src.pData; + } + + bool operator==( const T *src ) const + { + return pData == src; + } + + operator bool() const + { + return pRefCnt != NULL; + } + + bool isSet() const + { + return pRefCnt != NULL; + } + + private: + void decCount() const + { + if( pRefCnt ) + { + (*pRefCnt) -= 1; + //printf("Decrementing ref-count to %d\n", *pRefCnt ); + if( (*pRefCnt) == 0 ) + { + delete pRefCnt; + delete pData; + pRefCnt = NULL; + pData = NULL; + } + } + } + + mutable int32_t *pRefCnt; + mutable T *pData; + }; + + template< typename Tb, typename Ta > SPtr SPtrCast( SPtr src ) + { + SPtr ret; + ret.pRefCnt = src.pRefCnt; + ret.pData = dynamic_cast(src.pData); + if( ret.pRefCnt ) + (*(ret.pRefCnt)) += 1; + return ret; + } +} + +#endif diff --git a/src/tests/list.cpp b/src/tests/list.cpp index 34ab656..12807a5 100644 --- a/src/tests/list.cpp +++ b/src/tests/list.cpp @@ -1,4 +1,10 @@ #include "bu/list.h" +#include + +typedef struct Bob +{ + int nID; +} Bob; int main() { @@ -16,7 +22,32 @@ int main() { printf("%d ", *i ); } + printf("\n"); + for( Bu::List::iterator i = l.begin(); i != l.end(); i++ ) + { + l.erase( i ); + if( i != l.end() ) + printf("%d ", *i ); + } + + printf("\n\n"); + Bu::List lb; + for( int j = 0; j < 10; j++ ) + { + Bob b; + b.nID = j; + lb.append( b ); + } + + const Bu::List rb = lb; + + for( Bu::List::const_iterator i = rb.begin(); i != rb.end(); i++ ) + { + //i->nID += 2; + //(*i).nID = 4; + printf("%d ", i->nID ); + } printf("\n\n"); } -- cgit v1.2.3 From e0e7932a122614a0ff566fbfd8de5776de8b9f6d Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Thu, 17 May 2007 05:56:26 +0000 Subject: Lots of cool new stuff, the Server class actually works for everything except actually interacting with clients, and the Client class is almost there, except that it doesn't really do anything yet. --- src/client.cpp | 9 +++++++ src/client.h | 23 +++++++++++++++++ src/file.cpp | 10 +++++++ src/file.h | 3 +++ src/list.h | 5 ++++ src/old/singleton.h | 59 ------------------------------------------ src/server.cpp | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++++ src/server.h | 49 +++++++++++++++++++++++++++++++++++ src/serversocket.cpp | 5 ++++ src/serversocket.h | 3 ++- src/singleton.h | 62 ++++++++++++++++++++++++++++++++++++++++++++ src/socket.cpp | 9 +++++++ src/socket.h | 3 ++- src/stream.h | 3 +++ src/tests/hash.cpp | 24 +++++++++++++++++ 15 files changed, 279 insertions(+), 61 deletions(-) create mode 100644 src/client.cpp create mode 100644 src/client.h delete mode 100644 src/old/singleton.h create mode 100644 src/server.cpp create mode 100644 src/server.h create mode 100644 src/singleton.h create mode 100644 src/tests/hash.cpp (limited to 'src/tests') diff --git a/src/client.cpp b/src/client.cpp new file mode 100644 index 0000000..a048ca3 --- /dev/null +++ b/src/client.cpp @@ -0,0 +1,9 @@ +#include "client.h" + +Bu::Client::Client() +{ +} + +Bu::Client::~Client() +{ +} diff --git a/src/client.h b/src/client.h new file mode 100644 index 0000000..27fbad4 --- /dev/null +++ b/src/client.h @@ -0,0 +1,23 @@ +#ifndef CLIENT_H +#define CLIENT_H + +#include +#include "bu/socket.h" + +namespace Bu +{ + /** + * + */ + class Client + { + public: + Client(); + virtual ~Client(); + + private: + + }; +} + +#endif diff --git a/src/file.cpp b/src/file.cpp index 5de5f6c..26986a5 100644 --- a/src/file.cpp +++ b/src/file.cpp @@ -98,3 +98,13 @@ bool Bu::File::canSeek() return true; } +bool Bu::File::isBlocking() +{ + return true; +} + +void Bu::File::setBlocking( bool bBlocking ) +{ + return; +} + diff --git a/src/file.h b/src/file.h index bbc620c..ee3fdb3 100644 --- a/src/file.h +++ b/src/file.h @@ -27,6 +27,9 @@ namespace Bu virtual bool canWrite(); virtual bool canSeek(); + virtual bool isBlocking(); + virtual void setBlocking( bool bBlocking=true ); + private: FILE *fh; diff --git a/src/list.h b/src/list.h index 4d16872..6081ea5 100644 --- a/src/list.h +++ b/src/list.h @@ -217,6 +217,11 @@ namespace Bu { } + const_iterator( const iterator &i ) : + pLink( i.pLink ) + { + } + public: bool operator==( const const_iterator &oth ) const { diff --git a/src/old/singleton.h b/src/old/singleton.h deleted file mode 100644 index 47adbd5..0000000 --- a/src/old/singleton.h +++ /dev/null @@ -1,59 +0,0 @@ -#ifndef SINGLETON_H -#define SINGLETON_H - -#include - -/** - * Provides singleton functionality in a modular sort of way. Make this the - * base class of any other class and you immediately gain singleton - * functionality. Be sure to make your constructor and various functions use - * intellegent scoping. Cleanup and instantiation are performed automatically - * for you at first use and program exit. There are two things that you must - * do when using this template, first is to inherit from it with the name of - * your class filling in for T and then make this class a friend of your class. - *@code - * // Making the Single Singleton: - * class Single : public Singleton - * { - * friend class Singleton; - * protected: - * Single(); - * ... - * }; - @endcode - * You can still add public functions and variables to your new Singleton child - * class, but your constructor should be protected (hence the need for the - * friend decleration). - *@author Mike Buland - */ -template -class Singleton -{ -protected: - /** - * Private constructor. This constructor is empty but has a body so that - * you can make your own override of it. Be sure that you're override is - * also protected. - */ - Singleton() {}; - -private: - /** - * Copy constructor, defined so that you could write your own as well. - */ - Singleton( const Singleton& ); - -public: - /** - * Get a handle to the contained instance of the contained class. It is - * a reference. - *@returns A reference to the contained object. - */ - static T &getInstance() - { - static T i; - return i; - } -}; - -#endif diff --git a/src/server.cpp b/src/server.cpp new file mode 100644 index 0000000..f93238c --- /dev/null +++ b/src/server.cpp @@ -0,0 +1,73 @@ +#include "server.h" +#include + +Bu::Server::Server() : + nTimeoutSec( 0 ), + nTimeoutUSec( 0 ) +{ + FD_ZERO( &fdActive ); +} + +Bu::Server::~Server() +{ +} + +void Bu::Server::addPort( int nPort, int nPoolSize ) +{ + ServerSocket *s = new ServerSocket( nPort, nPoolSize ); + int nSocket = s->getSocket(); + FD_SET( nSocket, &fdActive ); + hServers.insert( nSocket, s ); +} + +void Bu::Server::addPort( const FString &sAddr, int nPort, int nPoolSize ) +{ + ServerSocket *s = new ServerSocket( sAddr, nPort, nPoolSize ); + int nSocket = s->getSocket(); + FD_SET( nSocket, &fdActive ); + hServers.insert( nSocket, s ); +} + +void Bu::Server::setTimeout( int nTimeoutSec, int nTimeoutUSec ) +{ + this->nTimeoutSec = nTimeoutSec; + this->nTimeoutUSec = nTimeoutUSec; +} + +void Bu::Server::scan() +{ + struct timeval xTimeout = { nTimeoutSec, nTimeoutUSec }; + + fd_set fdRead = fdActive; + fd_set fdWrite = fdActive; + fd_set fdException = fdActive; + + if( TEMP_FAILURE_RETRY( select( FD_SETSIZE, &fdRead, NULL, &fdException, &xTimeout ) ) < 0 ) + { + throw ExceptionBase("Error attempting to scan open connections."); + } + + for( int j = 0; j < FD_SETSIZE; j++ ) + { + if( FD_ISSET( j, &fdRead ) ) + { + if( hServers.has( j ) ) + { + addClient( hServers.get( j )->accept() ); + } + else + { + + } + } + } +} + +void Bu::Server::addClient( int nSocket ) +{ + FD_SET( nSocket, &fdActive ); + + Client *c = new Client(); + hClients.insert( nSocket, c ); +} + diff --git a/src/server.h b/src/server.h new file mode 100644 index 0000000..9f4f459 --- /dev/null +++ b/src/server.h @@ -0,0 +1,49 @@ +#ifndef SERVER_H +#define SERVER_H + +#include +#include "bu/serversocket.h" +#include "bu/list.h" +#include "bu/client.h" + +namespace Bu +{ + /** + * Core of a network server. This class is distinct from a ServerSocket in + * that a ServerSocket is one listening socket, nothing more. Socket will + * manage a pool of both ServerSockets and connected Sockets along with + * their protocols and buffers. + * + * To start serving on a new port, use the addPort functions. Each call to + * addPort creates a new ServerSocket, starts it listening, and adds it to + * the server pool. + * + * All of the real work is done by scan, which will wait for up + * to the timeout set by setTimeout before returning if there is no data + * pending. scan should probably be called in some sort of tight + * loop, possibly in it's own thread, or in the main control loop. + */ + class Server + { + public: + Server(); + virtual ~Server(); + + void addPort( int nPort, int nPoolSize=40 ); + void addPort( const FString &sAddr, int nPort, int nPoolSize=40 ); + + void scan(); + void setTimeout( int nTimeoutSec, int nTimeoutUSec=0 ); + + void addClient( int nSocket ); + + private: + int nTimeoutSec; + int nTimeoutUSec; + fd_set fdActive; + Hash hServers; + Hash hClients; + }; +} + +#endif diff --git a/src/serversocket.cpp b/src/serversocket.cpp index c53c80d..9c8f743 100644 --- a/src/serversocket.cpp +++ b/src/serversocket.cpp @@ -85,6 +85,11 @@ void Bu::ServerSocket::startServer( struct sockaddr_in &name, int nPoolSize ) FD_SET( nServer, &fdActive ); } +int Bu::ServerSocket::getSocket() +{ + return nServer; +} + int Bu::ServerSocket::accept( int nTimeoutSec, int nTimeoutUSec ) { fd_set fdRead = fdActive; diff --git a/src/serversocket.h b/src/serversocket.h index f146d91..d2601e4 100644 --- a/src/serversocket.h +++ b/src/serversocket.h @@ -23,7 +23,8 @@ namespace Bu ServerSocket( const FString &sAddr, int nPort, int nPoolSize=40 ); virtual ~ServerSocket(); - int accept( int nTimeoutSec, int nTimeoutUSec ); + int accept( int nTimeoutSec=0, int nTimeoutUSec=0 ); + int getSocket(); private: void startServer( struct sockaddr_in &name, int nPoolSize ); diff --git a/src/singleton.h b/src/singleton.h new file mode 100644 index 0000000..4976a61 --- /dev/null +++ b/src/singleton.h @@ -0,0 +1,62 @@ +#ifndef SINGLETON_H +#define SINGLETON_H + +#include + +namespace Bu +{ + /** + * Provides singleton functionality in a modular sort of way. Make this the + * base class of any other class and you immediately gain singleton + * functionality. Be sure to make your constructor and various functions use + * intellegent scoping. Cleanup and instantiation are performed automatically + * for you at first use and program exit. There are two things that you must + * do when using this template, first is to inherit from it with the name of + * your class filling in for T and then make this class a friend of your class. + *@code + * // Making the Single Singleton: + * class Single : public Singleton + * { + * friend class Singleton; + * protected: + * Single(); + * ... + * }; + @endcode + * You can still add public functions and variables to your new Singleton child + * class, but your constructor should be protected (hence the need for the + * friend decleration). + *@author Mike Buland + */ + template + class Singleton + { + protected: + /** + * Private constructor. This constructor is empty but has a body so that + * you can make your own override of it. Be sure that you're override is + * also protected. + */ + Singleton() {}; + + private: + /** + * Copy constructor, defined so that you could write your own as well. + */ + Singleton( const Singleton& ); + + public: + /** + * Get a handle to the contained instance of the contained class. It is + * a reference. + *@returns A reference to the contained object. + */ + static T &getInstance() + { + static T i; + return i; + } + }; +} + +#endif diff --git a/src/socket.cpp b/src/socket.cpp index 455b5c8..441678a 100644 --- a/src/socket.cpp +++ b/src/socket.cpp @@ -231,3 +231,12 @@ bool Bu::Socket::canSeek() return false; } +bool Bu::Socket::isBlocking() +{ + return false; +} + +void Bu::Socket::setBlocking( bool bBlocking ) +{ +} + diff --git a/src/socket.h b/src/socket.h index 568cad6..e65eb74 100644 --- a/src/socket.h +++ b/src/socket.h @@ -33,7 +33,8 @@ namespace Bu virtual bool canWrite(); virtual bool canSeek(); - + virtual bool isBlocking(); + virtual void setBlocking( bool bBlocking=true ); private: int nSocket; diff --git a/src/stream.h b/src/stream.h index e640959..5f586e6 100644 --- a/src/stream.h +++ b/src/stream.h @@ -36,6 +36,9 @@ namespace Bu virtual bool canWrite() = 0; virtual bool canSeek() = 0; + virtual bool isBlocking() = 0; + virtual void setBlocking( bool bBlocking=true ) = 0; + private: }; diff --git a/src/tests/hash.cpp b/src/tests/hash.cpp new file mode 100644 index 0000000..73cfb27 --- /dev/null +++ b/src/tests/hash.cpp @@ -0,0 +1,24 @@ +#include "bu/hash.h" +#include "bu/sptr.h" + +typedef struct Bob +{ + int nID; +} Bob; + +int main() +{ + Bu::Hash > lb; + for( int j = 0; j < 10; j++ ) + { + Bob *b = new Bob; + b->nID = j; + lb.insert( j, b ); + } + + for( int j = 0; j < 10; j++ ) + { + printf("%d\n", lb[j].value()->nID ); + } +} + -- cgit v1.2.3 From 326125aee0b8cd807a6a1d158398078ff6bfb1e1 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Thu, 17 May 2007 21:45:50 +0000 Subject: As evidenced by my latest test, the Bu::FString copy is actually slower than the std::string copy by a rather large margin. This seems very odd, so I'm going to do a few tests, the first one is stripping out the FString shared pointer stuff and seeing if that makes an appreciable difference. --- build.conf | 3 ++ src/fstring.h | 4 +- src/old/tests/fstring.cpp | 48 ----------------- src/tests/fstring.cpp | 130 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 136 insertions(+), 49 deletions(-) delete mode 100644 src/old/tests/fstring.cpp create mode 100644 src/tests/fstring.cpp (limited to 'src/tests') diff --git a/build.conf b/build.conf index c289205..35738e3 100644 --- a/build.conf +++ b/build.conf @@ -6,6 +6,9 @@ default action: check group "lnhdrs", check "libbu++.a" set "CXXFLAGS" += "-ggdb -Wall" +#set "CXXFLAGS" += "-pg" +#set "LDFLAGS" += "-pg" + filesIn("src") filter regexp("^src/(.*)\\.h$", "src/bu/{re:1}.h"): rule "hln", group "lnhdrs", diff --git a/src/fstring.h b/src/fstring.h index f738f63..43033b8 100644 --- a/src/fstring.h +++ b/src/fstring.h @@ -7,6 +7,8 @@ #include "archive.h" #include "hash.h" +#define min( a, b ) ((a @@ -131,7 +133,7 @@ namespace Bu appendChunk( pNew ); } - void append( const chr cData ) + void append( const chr &cData ) { append( &cData, 1 ); } diff --git a/src/old/tests/fstring.cpp b/src/old/tests/fstring.cpp deleted file mode 100644 index 271738c..0000000 --- a/src/old/tests/fstring.cpp +++ /dev/null @@ -1,48 +0,0 @@ -#include "hash.h" -#include "fstring.h" - -FString genThing() -{ - FString bob; - bob.append("ab "); - bob += "cd "; - bob += "efg"; - - printf("---bob------\n%08X: %s\n", (unsigned int)bob.c_str(), bob.c_str() ); - return bob; -} - -void thing( FString str ) -{ - printf("Hey: %s\n", str.c_str() ); -} - -#define pem printf("---------\n%08X: %s\n%08X: %s\n", (unsigned int)str.c_str(), str.c_str(), (unsigned int)str2.c_str(), str2.c_str() ); -int main( int argc, char *argv ) -{ - FString str("th"); - - str.prepend("Hello "); - str.append("ere."); - - FString str2( str ); - pem; - str += " What's up?"; - pem; - str2 += " How are you?"; - pem; - str = str2; - pem; - - str2 = genThing(); - pem; - - str = str2; - pem; - - thing( str2 ); - thing("test."); - - printf("%d == %d\n", __calcHashCode( str ), __calcHashCode( str.c_str() ) ); -} - diff --git a/src/tests/fstring.cpp b/src/tests/fstring.cpp new file mode 100644 index 0000000..d600be6 --- /dev/null +++ b/src/tests/fstring.cpp @@ -0,0 +1,130 @@ +#include "bu/hash.h" +#include "bu/fstring.h" +#include +#include + +inline double getTime() +{ + struct timeval tv; + gettimeofday( &tv, NULL ); + return ((double)tv.tv_sec) + ((double)tv.tv_usec/1000000.0); +} + +Bu::FString genThing() +{ + Bu::FString bob; + bob.append("ab "); + bob += "cd "; + bob += "efg"; + + printf("---bob------\n%08X: %s\n", (unsigned int)bob.c_str(), bob.c_str() ); + return bob; +} + +void thing( Bu::FString str ) +{ + printf("Hey: %s\n", str.c_str() ); +} + +void copyfunc( std::string temp ) +{ + temp += "Hi"; +} + +void copyfunc( Bu::FString temp ) +{ + temp += "Hi"; +} + +void doTimings() +{ + Bu::FString fs1, fs2; + std::string ss1, ss2; + double dStart, dEnd, tfs1, tfs2, tfs3, tss1, tss2, tss3; + int nChars = 500000, nChunks=5000, nCopies=5000000, nChunkSize=1024*4; + char *buf = new char[nChunkSize]; + memset( buf, '!', nChunkSize ); + + printf("Timing Bu::FString single chars...\n"); + dStart = getTime(); + for( int j = 0; j < nChars; j++ ) fs1 += (char)('a'+(j%26)); + fs1.getStr(); + dEnd = getTime(); + tfs1 = dEnd-dStart; + + printf("Timing std::string single chars...\n"); + dStart = getTime(); + for( int j = 0; j < nChars; j++ ) ss1 += (char)('a'+(j%26)); + ss1.c_str(); + dEnd = getTime(); + tss1 = dEnd-dStart; + + printf("Timing Bu::FString %d char chunks...\n", nChunkSize); + dStart = getTime(); + for( int j = 0; j < nChunks; j++ ) fs2.append(buf, nChunkSize); + fs2.getStr(); + dEnd = getTime(); + tfs2 = dEnd-dStart; + + printf("Timing std::string %d char chunks...\n", nChunkSize); + dStart = getTime(); + for( int j = 0; j < nChunks; j++ ) ss2.append(buf, nChunkSize); + ss2.c_str(); + dEnd = getTime(); + tss2 = dEnd-dStart; + + fs2 = "Hello there."; + ss2 = "Hello there."; + printf("Timing Bu::FString copies...\n"); + dStart = getTime(); + for( int j = 0; j < nCopies; j++ ) Bu::FString stmp = fs2; + dEnd = getTime(); + tfs3 = dEnd-dStart; + + printf("Timing std::string copies...\n"); + dStart = getTime(); + for( int j = 0; j < nCopies; j++ ) std::string stpm = ss2; + dEnd = getTime(); + tss3 = dEnd-dStart; + + printf( + "Results: singles: chunks: copies:\n" + "Bu::FString %10.2f/s %10.2f/s %10.2f/s\n" + "std::string %10.2f/s %10.2f/s %10.2f/s\n", + nChars/tfs1, nChunks/tfs2, nCopies/tfs3, + nChars/tss1, nChunks/tss2, nCopies/tss3 ); + + delete[] buf; +} + +#define pem printf("---------\n%08X: %s\n%08X: %s\n", (unsigned int)str.c_str(), str.c_str(), (unsigned int)str2.c_str(), str2.c_str() ); +int main( int argc, char *argv ) +{ + Bu::FString str("th"); + + str.prepend("Hello "); + str.append("ere."); + + Bu::FString str2( str ); + pem; + str += " What's up?"; + pem; + str2 += " How are you?"; + pem; + str = str2; + pem; + + str2 = genThing(); + pem; + + str = str2; + pem; + + thing( str2 ); + thing("test."); + + printf("%d == %d\n", Bu::__calcHashCode( str ), Bu::__calcHashCode( str.c_str() ) ); + + doTimings(); +} + -- cgit v1.2.3 From 8c2c728ce5aa1c1941426d0f8e9ab27762ef6754 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Tue, 5 Jun 2007 18:46:01 +0000 Subject: Added a basic ringbuffer, it should be nice and quick, but may be bad to use with objects at the moment, still contemplating that one... --- src/list.h | 20 +++++----- src/ringbuffer.cpp | 2 + src/ringbuffer.h | 100 +++++++++++++++++++++++++++++++++++++++++++++++ src/tests/ringbuffer.cpp | 29 ++++++++++++++ 4 files changed, 141 insertions(+), 10 deletions(-) create mode 100644 src/ringbuffer.cpp create mode 100644 src/ringbuffer.h create mode 100644 src/tests/ringbuffer.cpp (limited to 'src/tests') diff --git a/src/list.h b/src/list.h index 6081ea5..ea67f45 100644 --- a/src/list.h +++ b/src/list.h @@ -69,10 +69,10 @@ namespace Bu { if( pCur == NULL ) break; va.destroy( pCur->pValue ); - va.deallocate( pCur->pValue, sizeof( value ) ); + va.deallocate( pCur->pValue, 1 ); Link *pTmp = pCur->pNext; la.destroy( pCur ); - la.deallocate( pCur, sizeof( Link ) ); + la.deallocate( pCur, 1 ); pCur = pTmp; } pFirst = pLast = NULL; @@ -81,8 +81,8 @@ namespace Bu void append( const value &v ) { - Link *pNew = la.allocate( sizeof( Link ) ); - pNew->pValue = va.allocate( sizeof( value ) ); + Link *pNew = la.allocate( 1 ); + pNew->pValue = va.allocate( 1 ); va.construct( pNew->pValue, v ); nSize++; if( pFirst == NULL ) @@ -102,8 +102,8 @@ namespace Bu void prepend( const value &v ) { - Link *pNew = la.allocate( sizeof( Link ) ); - pNew->pValue = va.allocate( sizeof( value ) ); + Link *pNew = la.allocate( 1 ); + pNew->pValue = va.allocate( 1 ); va.construct( pNew->pValue, v ); nSize++; if( pFirst == NULL ) @@ -316,10 +316,10 @@ namespace Bu if( pPrev == NULL ) { va.destroy( pCur->pValue ); - va.deallocate( pCur->pValue, sizeof( value ) ); + va.deallocate( pCur->pValue, 1 ); pFirst = pCur->pNext; la.destroy( pCur ); - la.deallocate( pCur, sizeof( Link ) ); + la.deallocate( pCur, 1 ); if( pFirst == NULL ) pLast = NULL; nSize--; @@ -328,10 +328,10 @@ namespace Bu else { va.destroy( pCur->pValue ); - va.deallocate( pCur->pValue, sizeof( value ) ); + va.deallocate( pCur->pValue, 1 ); Link *pTmp = pCur->pNext; la.destroy( pCur ); - la.deallocate( pCur, sizeof( Link ) ); + la.deallocate( pCur, 1 ); pPrev->pNext = pTmp; if( pTmp != NULL ) pTmp->pPrev = pPrev; diff --git a/src/ringbuffer.cpp b/src/ringbuffer.cpp new file mode 100644 index 0000000..feb9bc7 --- /dev/null +++ b/src/ringbuffer.cpp @@ -0,0 +1,2 @@ +#include "bu/ringbuffer.h" + diff --git a/src/ringbuffer.h b/src/ringbuffer.h new file mode 100644 index 0000000..9480043 --- /dev/null +++ b/src/ringbuffer.h @@ -0,0 +1,100 @@ +#ifndef RING_BUFFER_H +#define RING_BUFFER_H + +#include +#include "bu/exceptionbase.h" + +namespace Bu +{ + template > + class RingBuffer + { + public: + RingBuffer( int nCapacity ) : + nCapacity( nCapacity ), + nStart( -1 ), + nEnd( -2 ) + { + aData = va.allocate( nCapacity ); + for( int j = 0; j < nCapacity; j++ ) + { + va.construct( &aData[j], value() ); + } + } + + virtual ~RingBuffer() + { + for( int j = 0; j < nCapacity; j++ ) + { + va.destroy( &aData[j] ); + } + va.deallocate( aData, nCapacity ); + } + + int getCapacity() + { + return nCapacity; + } + + bool isFilled() + { + return (nStart == nEnd); + } + + bool isEmpty() + { + return (nStart == -1); + } + + void enqueue( const value &v ) + { + if( nStart == -1 ) + { + nStart = 0; + nEnd = 1; + aData[0] = v; + } + else if( nStart == nEnd ) + { + throw ExceptionBase("Hey, it's full!"); + } + else + { + aData[nEnd] = v; + nEnd = (nEnd+1)%nCapacity; + } + } + + value dequeue() + { + if( nStart == -1 ) + { + throw ExceptionBase("No data"); + } + else + { + value &v = aData[nStart]; + nStart = (nStart+1)%nCapacity; + if( nStart == nEnd ) + { + nStart = -1; + nEnd = -2; + } + return v; + } + } + + value &operator[]( int nIndex ) + { + return aData[(nIndex+nStart)%nCapacity]; + } + + private: + int nCapacity; + value *aData; + valuealloc va; + int nStart, nEnd; + }; +} + +#endif diff --git a/src/tests/ringbuffer.cpp b/src/tests/ringbuffer.cpp new file mode 100644 index 0000000..259ec1f --- /dev/null +++ b/src/tests/ringbuffer.cpp @@ -0,0 +1,29 @@ +#include "bu/ringbuffer.h" +#include + +int main() +{ + Bu::RingBuffer ibuf( 10 ); + + for( int k = 0; k < 2; k++ ) + { + int j = 1; + for(; j < 7; j++ ) + { + ibuf.enqueue( j ); + } + + for(; j < 20; j++ ) + { + ibuf.enqueue( j ); + printf("- %d\n", ibuf.dequeue() ); + } + + for(;;) + { + if( ibuf.isEmpty() ) break; + printf(". %d\n", ibuf.dequeue() ); + } + } +} + -- cgit v1.2.3 From 3144bd7deb950de0cb80e2215c1545bdf8fc81e9 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Wed, 6 Jun 2007 18:48:07 +0000 Subject: Except for storing the data somewhere, the TafReader is more or less done. Some more generalizations are in order, then we'll stuff the data somewhere. --- misc/taf | 4 +- src/exceptions.cpp | 1 + src/exceptions.h | 1 + src/tafreader.cpp | 129 ++++++++++++++++++++++++++++++++++++++++++++++++++++- src/tafreader.h | 6 +++ src/tests/taf.cpp | 9 ++++ 6 files changed, 147 insertions(+), 3 deletions(-) create mode 100644 src/tests/taf.cpp (limited to 'src/tests') diff --git a/misc/taf b/misc/taf index 5ffcdcf..045b042 100644 --- a/misc/taf +++ b/misc/taf @@ -20,7 +20,7 @@ {: key="," value="yell"} {: key="li" value="lightning"} } - description = """They appear to be rather average looking, not particularly + description = "They appear to be rather average looking, not particularly tall or short, with facial features that are difficult to remember even - seconds after witnessing them.""" + seconds after witnessing them." } diff --git a/src/exceptions.cpp b/src/exceptions.cpp index d9f4e70..50b95c3 100644 --- a/src/exceptions.cpp +++ b/src/exceptions.cpp @@ -4,6 +4,7 @@ namespace Bu { subExceptionDef( XmlException ) + subExceptionDef( TafException ) subExceptionDef( FileException ) subExceptionDef( SocketException ) subExceptionDef( ConnectionException ) diff --git a/src/exceptions.h b/src/exceptions.h index f146b73..d5a9d39 100644 --- a/src/exceptions.h +++ b/src/exceptions.h @@ -7,6 +7,7 @@ namespace Bu { subExceptionDecl( XmlException ) + subExceptionDecl( TafException ) subExceptionDecl( FileException ) subExceptionDecl( SocketException ) subExceptionDecl( ConnectionException ) diff --git a/src/tafreader.cpp b/src/tafreader.cpp index 4d10b8d..91aa9f2 100644 --- a/src/tafreader.cpp +++ b/src/tafreader.cpp @@ -1,14 +1,141 @@ -#include "tafreader.h" +#include "bu/tafreader.h" +#include "bu/exceptions.h" +#include "bu/fstring.h" Bu::TafReader::TafReader( Bu::Stream &sIn ) : sIn( sIn ) { + next(); + node(); } Bu::TafReader::~TafReader() { } +void Bu::TafReader::node() +{ + ws(); + if( c != '{' ) + throw Bu::TafException("Expected '{'"); + next(); + ws(); + Bu::FString sName; + for(;;) + { + if( c == ':' ) + break; + else + sName += c; + next(); + } + next(); + printf("Node[%s]:\n", sName.getStr() ); + + nodeContent(); + + if( c != '}' ) + throw TafException("Expected '}'"); + + next(); +} + +void Bu::TafReader::nodeContent() +{ + for(;;) + { + ws(); + if( c == '{' ) + node(); + else if( c == '}' ) + return; + else + nodeProperty(); + } +} + +void Bu::TafReader::nodeProperty() +{ + Bu::FString sName; + for(;;) + { + if( isws() || c == '=' ) + break; + else + sName += c; + next(); + } + ws(); + if( c != '=' ) + { + printf(" %s (true)\n", sName.getStr() ); + return; + } + next(); + ws(); + Bu::FString sValue; + if( c == '"' ) + { + next(); + for(;;) + { + if( c == '\\' ) + { + next(); + if( c == 'x' ) + { + char code[3]={'\0','\0','\0'}; + next(); + code[0] = c; + next(); + code[1] = c; + c = (unsigned char)strtol( code, NULL, 16 ); + } + else if( c == '"' ) + c = '"'; + else + throw TafException("Invalid escape sequence."); + } + else if( c == '"' ) + break; + sValue += c; + next(); + } + next(); + } + else + { + for(;;) + { + if( isws() || c == '}' || c == '{' ) + break; + sValue += c; + next(); + } + } + printf(" %s = %s\n", sName.getStr(), sValue.getStr() ); +} + +FString Bu::TafReader::readStr() +{ +} + +void Bu::TafReader::ws() +{ + for(;;) + { + if( !isws() ) + return; + + next(); + } +} + +bool Bu::TafReader::isws() +{ + return (c == ' ' || c == '\t' || c == '\n' || c == '\r'); +} + void Bu::TafReader::next() { sIn.read( &c, 1 ); diff --git a/src/tafreader.h b/src/tafreader.h index b552f5d..127b571 100644 --- a/src/tafreader.h +++ b/src/tafreader.h @@ -17,7 +17,13 @@ namespace Bu virtual ~TafReader(); private: + void node(); + void nodeContent(); + void nodeProperty(); + void ws(); + bool isws(); void next(); + FString readStr(); char c; Stream &sIn; diff --git a/src/tests/taf.cpp b/src/tests/taf.cpp new file mode 100644 index 0000000..12c653e --- /dev/null +++ b/src/tests/taf.cpp @@ -0,0 +1,9 @@ +#include "bu/tafreader.h" +#include "bu/file.h" + +int main() +{ + Bu::File f("test.taf", "rb"); + Bu::TafReader tr( f ); +} + -- cgit v1.2.3 From 8b598e8436a7110abbd0a7566138bcaa952bb527 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Thu, 7 Jun 2007 03:26:43 +0000 Subject: Except for an excessive amount of debug info, I finally got the delete code working. Now you can load Taf structures and clean up, you just can't access all of the data inside 100%. --- src/tafnode.cpp | 39 ++++++++++++++++++++++++++++++++++++++- src/tafnode.h | 5 +++++ src/tafreader.cpp | 32 +++++++++++++++++--------------- src/tafreader.h | 7 +++---- src/tests/taf.cpp | 11 +++++++++++ 5 files changed, 74 insertions(+), 20 deletions(-) (limited to 'src/tests') diff --git a/src/tafnode.cpp b/src/tafnode.cpp index 01880d9..ed8adc0 100644 --- a/src/tafnode.cpp +++ b/src/tafnode.cpp @@ -6,11 +6,21 @@ Bu::TafNode::TafNode() Bu::TafNode::~TafNode() { + printf("Entering Bu::TafNode::~TafNode() \"%s\"\n", sName.getStr() ); + for( NodeHash::iterator i = hChildren.begin(); i != hChildren.end(); i++ ) + { + NodeList &l = i.getValue(); + for( NodeList::iterator k = l.begin(); k != l.end(); k++ ) + { + printf("deleting: [%08X] %s\n", *k, "" );//(*k)->getName().getStr() ); + delete (*k); + } + } } void Bu::TafNode::setProperty( Bu::FString sName, Bu::FString sValue ) { - if( hProp.has( sName ) ) + if( !hProp.has( sName ) ) { hProp.insert( sName, PropList() ); } @@ -18,8 +28,35 @@ void Bu::TafNode::setProperty( Bu::FString sName, Bu::FString sValue ) hProp.get( sName ).append( sValue ); } +void Bu::TafNode::addChild( TafNode *pNode ) +{ + if( !hChildren.has( pNode->getName() ) ) + { + hChildren.insert( pNode->getName(), NodeList() ); + } + + printf("Appending \"%s\"\n", pNode->getName().getStr() ); + hChildren.get( pNode->getName() ).append( pNode ); + printf("[%08X]\n", hChildren.get( pNode->getName() ).last() ); +} + const Bu::TafNode::PropList &Bu::TafNode::getProperty( const Bu::FString &sName ) { return hProp.get( sName ); } +const Bu::TafNode::NodeList &Bu::TafNode::getNode( const Bu::FString &sName ) +{ + return hChildren.get( sName ); +} + +void Bu::TafNode::setName( const Bu::FString &sName ) +{ + this->sName = sName; +} + +const Bu::FString &Bu::TafNode::getName() +{ + return sName; +} + diff --git a/src/tafnode.h b/src/tafnode.h index e962e88..a570d2d 100644 --- a/src/tafnode.h +++ b/src/tafnode.h @@ -23,8 +23,13 @@ namespace Bu TafNode(); virtual ~TafNode(); + void setName( const Bu::FString &sName ); + const Bu::FString &getName(); + void setProperty( Bu::FString sName, Bu::FString sValue ); const PropList &getProperty( const Bu::FString &sName ); + const NodeList &getNode( const Bu::FString &sName ); + void addChild( TafNode *pNode ); private: Bu::FString sName; diff --git a/src/tafreader.cpp b/src/tafreader.cpp index 5fe303b..1187176 100644 --- a/src/tafreader.cpp +++ b/src/tafreader.cpp @@ -5,10 +5,9 @@ using namespace Bu; Bu::TafReader::TafReader( Bu::Stream &sIn ) : + c( 0 ), sIn( sIn ) { - next(); - node(); } Bu::TafReader::~TafReader() @@ -16,55 +15,58 @@ Bu::TafReader::~TafReader() } -Bu::TafNode *Bu::TafReader::readNode() -{ -} - -void Bu::TafReader::node() +Bu::TafNode *Bu::TafReader::getNode() { + if( c == 0 ) next(); + TafNode *pNode = new TafNode(); ws(); if( c != '{' ) throw TafException("Expected '{'"); next(); ws(); FString sName = readStr(); + pNode->setName( sName ); next(); - printf("Node[%s]:\n", sName.getStr() ); + //printf("Node[%s]:\n", sName.getStr() ); - nodeContent(); + nodeContent( pNode ); if( c != '}' ) throw TafException("Expected '}'"); next(); + + return pNode; } -void Bu::TafReader::nodeContent() +void Bu::TafReader::nodeContent( Bu::TafNode *pNode ) { for(;;) { ws(); if( c == '{' ) - node(); + pNode->addChild( getNode() ); else if( c == '}' ) return; else - nodeProperty(); + nodeProperty( pNode ); } } -void Bu::TafReader::nodeProperty() +void Bu::TafReader::nodeProperty( Bu::TafNode *pNode ) { FString sName = readStr(); ws(); if( c != '=' ) { - printf(" %s (true)\n", sName.getStr() ); + //printf(" %s (true)\n", sName.getStr() ); + pNode->setProperty( sName, "" ); return; } next(); FString sValue = readStr(); - printf(" %s = %s\n", sName.getStr(), sValue.getStr() ); + pNode->setProperty( sName, sValue ); + //printf(" %s = %s\n", sName.getStr(), sValue.getStr() ); } Bu::FString Bu::TafReader::readStr() diff --git a/src/tafreader.h b/src/tafreader.h index 4da800c..47ae187 100644 --- a/src/tafreader.h +++ b/src/tafreader.h @@ -17,12 +17,11 @@ namespace Bu TafReader( Bu::Stream &sIn ); virtual ~TafReader(); - Bu::TafNode *readNode(); + Bu::TafNode *getNode(); private: - void node(); - void nodeContent(); - void nodeProperty(); + void nodeContent( Bu::TafNode *pNode ); + void nodeProperty( Bu::TafNode *pNode ); void ws(); bool isws(); void next(); diff --git a/src/tests/taf.cpp b/src/tests/taf.cpp index 12c653e..f7af2b2 100644 --- a/src/tests/taf.cpp +++ b/src/tests/taf.cpp @@ -5,5 +5,16 @@ int main() { Bu::File f("test.taf", "rb"); Bu::TafReader tr( f ); + + Bu::TafNode *pNode = tr.getNode(); + + const Bu::TafNode::NodeList &l = pNode->getNode("stats"); + for( Bu::TafNode::NodeList::const_iterator i = l.begin(); + i != l.end(); i++ ) + { + printf("%s\n", (*i)->getName().getStr() ); + } + + delete pNode; } -- cgit v1.2.3 From c2e3879b965d297604804f03271ac71c8c5c81f3 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Thu, 7 Jun 2007 04:55:29 +0000 Subject: The new taf interfaces seem to work just fine, except for saving and that loaded TafNode structures are immutable, it all looks really good. Saving should be a snap, and the immutable part I'm not sure is bad...we'll see what happens. Also, I'm contemplating looking into a way to add "named data structure" support to the Archive at a lower level, then allow it to use a nameing system to apply names to each data structure and then output to any backend that supports naming, like taf, xml, etc. --- src/hash.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++++- src/tafnode.cpp | 24 +++++++++++++++++------- src/tafnode.h | 8 +++++--- src/tests/taf.cpp | 9 +++------ 4 files changed, 77 insertions(+), 17 deletions(-) (limited to 'src/tests') diff --git a/src/hash.h b/src/hash.h index a81c355..f6c207f 100644 --- a/src/hash.h +++ b/src/hash.h @@ -358,6 +358,25 @@ namespace Bu ); } } + + virtual const value &get( key k ) const + { + uint32_t hash = __calcHashCode( k ); + bool bFill; + uint32_t nPos = probe( hash, k, bFill ); + + if( bFill ) + { + return aValues[nPos]; + } + else + { + throw HashException( + excodeNotFilled, + "No data assosiated with that key." + ); + } + } virtual bool has( key k ) { @@ -599,6 +618,38 @@ namespace Bu bFill = false; return nCur; } + + uint32_t probe( uint32_t hash, key k, bool &bFill, bool rehash=true ) const + { + uint32_t nCur = hash%nCapacity; + + // First we scan to see if the key is already there, abort if we + // run out of probing room, or we find a non-filled entry + for( int8_t j = 0; + isFilled( nCur ) && j < 32; + nCur = (nCur + (1<getName().getStr() ); + //printf("deleting: [%08X] %s\n", *k, "" );//(*k)->getName().getStr() ); delete (*k); } } @@ -35,27 +35,37 @@ void Bu::TafNode::addChild( TafNode *pNode ) hChildren.insert( pNode->getName(), NodeList() ); } - printf("Appending \"%s\"\n", pNode->getName().getStr() ); + //printf("Appending \"%s\"\n", pNode->getName().getStr() ); hChildren.get( pNode->getName() ).append( pNode ); - printf("[%08X]\n", hChildren.get( pNode->getName() ).last() ); + //printf("[%08X]\n", hChildren.get( pNode->getName() ).last() ); } -const Bu::TafNode::PropList &Bu::TafNode::getProperty( const Bu::FString &sName ) +const Bu::TafNode::PropList &Bu::TafNode::getProperties( const Bu::FString &sName ) const { return hProp.get( sName ); } -const Bu::TafNode::NodeList &Bu::TafNode::getNode( const Bu::FString &sName ) +const Bu::TafNode::NodeList &Bu::TafNode::getNodes( const Bu::FString &sName ) const { return hChildren.get( sName ); } +const Bu::FString &Bu::TafNode::getProperty( const Bu::FString &sName ) const +{ + return getProperties( sName ).first(); +} + +const Bu::TafNode *Bu::TafNode::getNode( const Bu::FString &sName ) const +{ + return getNodes( sName ).first(); +} + void Bu::TafNode::setName( const Bu::FString &sName ) { this->sName = sName; } -const Bu::FString &Bu::TafNode::getName() +const Bu::FString &Bu::TafNode::getName() const { return sName; } diff --git a/src/tafnode.h b/src/tafnode.h index a570d2d..10232d2 100644 --- a/src/tafnode.h +++ b/src/tafnode.h @@ -24,11 +24,13 @@ namespace Bu virtual ~TafNode(); void setName( const Bu::FString &sName ); - const Bu::FString &getName(); + const Bu::FString &getName() const; void setProperty( Bu::FString sName, Bu::FString sValue ); - const PropList &getProperty( const Bu::FString &sName ); - const NodeList &getNode( const Bu::FString &sName ); + const Bu::FString &getProperty( const Bu::FString &sName ) const; + const TafNode *getNode( const Bu::FString &sName ) const; + const PropList &getProperties( const Bu::FString &sName ) const; + const NodeList &getNodes( const Bu::FString &sName ) const; void addChild( TafNode *pNode ); private: diff --git a/src/tests/taf.cpp b/src/tests/taf.cpp index f7af2b2..e7bad52 100644 --- a/src/tests/taf.cpp +++ b/src/tests/taf.cpp @@ -8,12 +8,9 @@ int main() Bu::TafNode *pNode = tr.getNode(); - const Bu::TafNode::NodeList &l = pNode->getNode("stats"); - for( Bu::TafNode::NodeList::const_iterator i = l.begin(); - i != l.end(); i++ ) - { - printf("%s\n", (*i)->getName().getStr() ); - } + const Bu::TafNode *pStats = pNode->getNode("stats"); + printf("%s\n", pStats->getName().getStr() ); + printf(" str = %s\n", pStats->getProperty("str").getStr() ); delete pNode; } -- cgit v1.2.3 From 9e8a4944e50fab432012878c66e1bdac20649f76 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Thu, 7 Jun 2007 19:56:20 +0000 Subject: The Stream Filter archetecture is finished, it's actually much cooler than I had anticipated, and much cleaner. I'll have to add some documentation to it, because it's not really obvious how any of it fits together from the outset, although I have to say that the bzip2 test program is the easiest general bzip2 compression program I've ever made...it just goes :) Decompression in Bu::BZip2 isn't finished yet, but that's ok, it's coming soon. --- build.conf | 2 + src/bzip2.cpp | 123 ++++++++++++ src/bzip2.h | 35 ++++ src/entities/bu-class | 4 +- src/filter.cpp | 77 ++++++++ src/filter.h | 59 ++++++ src/fstring.h | 6 +- src/old/paramproc.cpp | 514 -------------------------------------------------- src/old/paramproc.h | 153 --------------- src/paramproc.cpp | 514 ++++++++++++++++++++++++++++++++++++++++++++++++++ src/paramproc.h | 156 +++++++++++++++ src/stream.h | 3 + src/tests/bzip2.cpp | 23 +++ 13 files changed, 998 insertions(+), 671 deletions(-) create mode 100644 src/bzip2.cpp create mode 100644 src/bzip2.h create mode 100644 src/filter.cpp create mode 100644 src/filter.h delete mode 100644 src/old/paramproc.cpp delete mode 100644 src/old/paramproc.h create mode 100644 src/paramproc.cpp create mode 100644 src/paramproc.h create mode 100644 src/tests/bzip2.cpp (limited to 'src/tests') diff --git a/build.conf b/build.conf index 35738e3..f493d67 100644 --- a/build.conf +++ b/build.conf @@ -61,6 +61,8 @@ filesIn("src/unit") filter regexp("^src/unit/(.*)\\.cpp$", "unit/{re:1}"): "tests/plugin": set "LDFLAGS" += "-ldl" +"tests/bzip2": set "LDFLAGS" += "-lbz2" + rule "exe": matches regexp("(.*)\\.o$"), aggregate toString(" "), diff --git a/src/bzip2.cpp b/src/bzip2.cpp new file mode 100644 index 0000000..b8c0f74 --- /dev/null +++ b/src/bzip2.cpp @@ -0,0 +1,123 @@ +#include "bu/bzip2.h" +#include "bu/exceptions.h" + +using namespace Bu; + +Bu::BZip2::BZip2( Bu::Stream &rNext, int nCompression ) : + Bu::Filter( rNext ), + nCompression( nCompression ) +{ + start(); +} + +Bu::BZip2::~BZip2() +{ + printf("-> Bu::BZip2::~BZip2()\n"); + stop(); +} + +void Bu::BZip2::start() +{ + printf("-> Bu::BZip2::start()\n"); + printf("Hey, it's starting...\n"); + bzState.state = NULL; + bzState.bzalloc = NULL; + bzState.bzfree = NULL; + bzState.opaque = NULL; + + nBufSize = 50000; + pBuf = new char[nBufSize]; +} + +void Bu::BZip2::stop() +{ + printf("-> Bu::BZip2::stop()\n"); + if( bzState.state ) + { + if( bReading ) + { + } + else + { + for(;;) + { + bzState.next_in = NULL; + bzState.avail_in = 0; + bzState.avail_out = nBufSize; + bzState.next_out = pBuf; + int res = BZ2_bzCompress( &bzState, BZ_FINISH ); + if( bzState.avail_out < nBufSize ) + { + rNext.write( pBuf, nBufSize-bzState.avail_out ); + } + if( res == BZ_STREAM_END ) + break; + } + BZ2_bzCompressEnd( &bzState ); + } + } +} + +void Bu::BZip2::bzError( int code ) +{ + switch( code ) + { + case BZ_OK: + return; + + case BZ_CONFIG_ERROR: + throw ExceptionBase("The bzip2 library has been miscompiled."); + + case BZ_PARAM_ERROR: + throw ExceptionBase("bzip2 parameter error."); + + case BZ_MEM_ERROR: + throw ExceptionBase("Not enough memory available for bzip2."); + } +} + +size_t Bu::BZip2::read( void *pData, size_t nBytes ) +{ + if( !bzState.state ) + { + bReading = true; + } + if( bReading == false ) + throw ExceptionBase("This bzip2 filter is in writing mode, you can't read."); + //bzState.next_in = pData; + //bzState.avail_in = nSizeIn; + + //printf("%db at [%08X] (%db)\n", bzState.avail_in, (uint32_t)bzState.next_in, bzState.total_in_lo32 ); + return 0; +} + +size_t Bu::BZip2::write( const void *pData, size_t nBytes ) +{ + if( !bzState.state ) + { + bReading = false; + BZ2_bzCompressInit( &bzState, nCompression, 0, 30 ); + } + if( bReading == true ) + throw ExceptionBase("This bzip2 filter is in reading mode, you can't write."); + + bzState.next_in = (char *)pData; + bzState.avail_in = nBytes; + for(;;) + { + bzState.avail_out = nBufSize; + bzState.next_out = pBuf; + + BZ2_bzCompress( &bzState, BZ_RUN ); + + if( bzState.avail_out < nBufSize ) + { + rNext.write( pBuf, nBufSize-bzState.avail_out ); + } + if( bzState.avail_in == 0 ) + break; + } + + return 0; +} + diff --git a/src/bzip2.h b/src/bzip2.h new file mode 100644 index 0000000..056f336 --- /dev/null +++ b/src/bzip2.h @@ -0,0 +1,35 @@ +#ifndef B_ZIP2_H +#define B_ZIP2_H + +#include +#include + +#include "bu/filter.h" + +namespace Bu +{ + /** + * + */ + class BZip2 : public Bu::Filter + { + public: + BZip2( Bu::Stream &rNext, int nCompression=9 ); + virtual ~BZip2(); + + virtual void start(); + virtual void stop(); + virtual size_t read( void *pBuf, size_t nBytes ); + virtual size_t write( const void *pBuf, size_t nBytes ); + + private: + void bzError( int code ); + bz_stream bzState; + bool bReading; + int nCompression; + char *pBuf; + uint32_t nBufSize; + }; +} + +#endif diff --git a/src/entities/bu-class b/src/entities/bu-class index 81e3d25..7b25291 100644 --- a/src/entities/bu-class +++ b/src/entities/bu-class @@ -10,7 +10,7 @@ #include <stdint.h> -{?parent:"#include \"{=parent:%tolower}.h\" +{?parent:"#include \"bu/{=parent:%tolower}.h\" "}namespace Bu { @@ -35,6 +35,8 @@ filename="{=name:%tolower}.cpp" >#include "bu/{=name:%tolower}.h" +using namespace Bu; + Bu::{=name}::{=name}() { } diff --git a/src/filter.cpp b/src/filter.cpp new file mode 100644 index 0000000..d3faa00 --- /dev/null +++ b/src/filter.cpp @@ -0,0 +1,77 @@ +#include "bu/filter.h" + +Bu::Filter::Filter( Bu::Stream &rNext ) : + rNext( rNext ) +{ +} + +Bu::Filter::~Filter() +{ + printf("-> Bu::Filter::~Filter()\n"); +} +/* +void Bu::Filter::start() +{ + printf("-> Bu::Filter::start()\n"); +} + +void Bu::Filter::stop() +{ +}*/ + +void Bu::Filter::close() +{ + stop(); + rNext.close(); +} + +long Bu::Filter::tell() +{ + return rNext.tell(); +} + +void Bu::Filter::seek( long offset ) +{ + rNext.seek( offset ); +} + +void Bu::Filter::setPos( long pos ) +{ + rNext.setPos( pos ); +} + +void Bu::Filter::setPosEnd( long pos ) +{ + rNext.setPosEnd( pos ); +} + +bool Bu::Filter::isEOS() +{ + return rNext.isEOS(); +} + +bool Bu::Filter::canRead() +{ + return rNext.canRead(); +} + +bool Bu::Filter::canWrite() +{ + return rNext.canWrite(); +} + +bool Bu::Filter::canSeek() +{ + return rNext.canSeek(); +} + +bool Bu::Filter::isBlocking() +{ + return rNext.isBlocking(); +} + +void Bu::Filter::setBlocking( bool bBlocking ) +{ + rNext.setBlocking( bBlocking ); +} + diff --git a/src/filter.h b/src/filter.h new file mode 100644 index 0000000..b068206 --- /dev/null +++ b/src/filter.h @@ -0,0 +1,59 @@ +#ifndef FILTER_H +#define FILTER_H + +#include + +#include "bu/stream.h" + +namespace Bu +{ + /** + * Data filter base class. Each data filter should contain a read and write + * section. Effectively, the write applies the filter, the read un-applies + * the filter, if possible. For example, BZip2 is a filter that compresses + * on write and decompresses on read. All bi-directional filters should + * follow: x == read( write( x ) ) (byte-for-byte comparison) + * + * Also, all returned buffers should be owned by the filter, and deleted + * when the filter is deleted. This means that the output of a read or + * write operation must be used before the next call to read or write or the + * data will be destroyed. Also, the internal buffer may be changed or + * recreated between calls, so always get a new pointer from a call to + * read or write. + * + * The close function can also return data, so make sure to check for it, + * many filters such as compression filters will buffer data until they have + * enough to create a compression block, in these cases the leftover data + * will be returned by close. + */ + class Filter : public Bu::Stream + { + public: + Filter( Bu::Stream &rNext ); + virtual ~Filter(); + + virtual void start()=0; + virtual void stop()=0; + virtual void close(); + virtual long tell(); + virtual void seek( long offset ); + virtual void setPos( long pos ); + virtual void setPosEnd( long pos ); + virtual bool isEOS(); + + virtual bool canRead(); + virtual bool canWrite(); + virtual bool canSeek(); + + virtual bool isBlocking(); + virtual void setBlocking( bool bBlocking=true ); + + protected: + Bu::Stream &rNext; + + private: + + }; +} + +#endif diff --git a/src/fstring.h b/src/fstring.h index 43033b8..d0307b5 100644 --- a/src/fstring.h +++ b/src/fstring.h @@ -3,9 +3,9 @@ #include #include -#include "archival.h" -#include "archive.h" -#include "hash.h" +#include "bu/archival.h" +#include "bu/archive.h" +#include "bu/hash.h" #define min( a, b ) ((a - -#define ptrtype( iitype, iiname ) \ - ParamProc::ParamPtr::ParamPtr( iitype *iiname ) : \ - type( vt ##iiname ) { val.iiname = iiname; } - -ParamProc::ParamPtr::ParamPtr() -{ - val.str = NULL; - type = vtunset; -} - -ptrtype( std::string, str ); -ptrtype( uint64_t, uint64 ); -ptrtype( uint32_t, uint32 ); -ptrtype( uint16_t, uint16 ); -ptrtype( uint8_t, uint8 ); -ptrtype( int64_t, int64 ); -ptrtype( int32_t, int32 ); -ptrtype( int16_t, int16 ); -ptrtype( int8_t, int8 ); -ptrtype( float, float32 ); -ptrtype( double, float64 ); -ptrtype( long double, float96 ); -ptrtype( bool, bln ); - -ParamProc::ParamPtr &ParamProc::ParamPtr::operator=( ParamProc::ParamPtr &ptr ) -{ - val = ptr.val; - type = ptr.type; - - return *this; -} - -bool ParamProc::ParamPtr::isSet() -{ - return type != vtunset; -} - -ParamProc::ParamPtr &ParamProc::ParamPtr::operator=( const char *str ) -{ - if( !isSet() ) return *this; - switch( type ) - { - case vtstr: - (*val.str) = str; - break; - - case vtuint64: - (*val.uint64) = strtoull( str, NULL, 10 ); - break; - - case vtuint32: - (*val.uint32) = strtoul( str, NULL, 10 ); - break; - - case vtuint16: - (*val.uint16) = (uint16_t)strtoul( str, NULL, 10 ); - break; - - case vtuint8: - (*val.uint8) = (uint8_t)strtoul( str, NULL, 10 ); - break; - - case vtint64: - (*val.int64) = strtoll( str, NULL, 10 ); - break; - - case vtint32: - (*val.int32) = strtol( str, NULL, 10 ); - break; - - case vtint16: - (*val.int16) = (int16_t)strtol( str, NULL, 10 ); - break; - - case vtint8: - (*val.int8) = (int8_t)strtol( str, NULL, 10 ); - break; - - case vtfloat32: - (*val.float32) = strtof( str, NULL ); - break; - - case vtfloat64: - (*val.float64) = strtod( str, NULL ); - break; - - case vtfloat96: - (*val.float96) = strtold( str, NULL ); - break; - - case vtbln: - if( strcasecmp("yes", str ) == 0 || - strcasecmp("true", str ) == 0 ) - { - (*val.bln) = true; - } - else - { - (*val.bln) = false; - } - break; - } - - return *this; -} - -ParamProc::ParamProc() -{ -} - -ParamProc::~ParamProc() -{ - for( std::list::iterator i = lArg.begin(); - i != lArg.end(); i++ ) - { - delete *i; - } - - for( std::list::iterator i = lBan.begin(); - i != lBan.end(); i++ ) - { - delete *i; - } - -} -/* -void ParamProc::addParam( const char *lpWord, char cChar, Proc proc, ParamPtr val ) -{ - printf("Calling callback...\n"); - val = "Hello there, this is set in the ParamProc"; - (this->*proc)(); -}*/ - -void ParamProc::addParam( const char *lpWord, char cChar, Proc proc, - ParamPtr val, const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - ArgSpec *as = new ArgSpec; - if( lpWord ) - as->sWord = lpWord; - - as->cChar = cChar; - as->proc = proc; - as->val = val; - if( lpDesc ) - as->sDesc = lpDesc; - if( lpExtra ) - as->sExtra = lpExtra; - if( lpValue ) - as->sValue = lpValue; - - lArg.push_back( as ); - - if( !lBan.empty() ) - { - if( lBan.back()->pBefore == NULL ) - lBan.back()->pBefore = as; - } -} - -void ParamProc::addParam( const char *lpWord, char cChar, Proc proc, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( lpWord, cChar, proc, ParamPtr(), lpDesc, lpExtra, lpValue ); -} - -void ParamProc::addParam( const char *lpWord, char cChar, ParamPtr val, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( lpWord, cChar, NULL, val, lpDesc, lpExtra, lpValue ); -} - -void ParamProc::addParam( const char *lpWord, Proc proc, ParamPtr val, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( lpWord, '\0', proc, val, lpDesc, lpExtra, lpValue ); -} - -void ParamProc::addParam( const char *lpWord, Proc proc, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( lpWord, '\0', proc, ParamPtr(), lpDesc, lpExtra, lpValue ); -} - -void ParamProc::addParam( const char *lpWord, ParamPtr val, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( lpWord, '\0', NULL, val, lpDesc, lpExtra, lpValue ); -} - -void ParamProc::addParam( char cChar, Proc proc, ParamPtr val, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( NULL, cChar, proc, val, lpDesc, lpExtra, lpValue ); -} - -void ParamProc::addParam( char cChar, Proc proc, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( NULL, cChar, proc, ParamPtr(), lpDesc, lpExtra, lpValue ); -} - -void ParamProc::addParam( char cChar, ParamPtr val, - const char *lpDesc, const char *lpExtra, - const char *lpValue ) -{ - addParam( NULL, cChar, NULL, val, lpDesc, lpExtra, lpValue ); -} - -void ParamProc::process( int argc, char *argv[] ) -{ - for( int arg = 1; arg < argc; arg++ ) - { - //printf(":::%d:::%s\n", arg, argv[arg] ); - if( argv[arg][0] == '-' ) - { - if( argv[arg][1] == '-' ) - { - ArgSpec *s = checkWord( argv[arg]+2 ); - if( s ) - { - if( argv[arg][s->sWord.getLength()+2] == '=' ) - { - if( s->val.isSet() ) - { - if( s->sValue.getString() == NULL ) - { - s->val = argv[arg]+s->sWord.getLength()+3; - } - else - { - s->val = s->sValue.getString(); - } - } - if( s->proc ) - { - char **tmp = new char*[argc-arg]; - tmp[0] = argv[arg]+s->sWord.getLength()+3; - for( int k = 1; k < argc-arg; k++ ) - tmp[k] = argv[arg+k]; - int ret = (this->*s->proc)( argc-arg, tmp ); - if( ret > 0 ) - { - arg += ret-1; - } - delete tmp; - } - } - else - { - int add = 0; - if( s->val.isSet() ) - { - if( s->sValue.getString() == NULL ) - { - if( arg+1 >= argc ) - { - return; - } - s->val = argv[arg+1]; - add++; - } - else - { - s->val = s->sValue.getString(); - } - } - if( s->proc ) - { - int ret = (this->*s->proc)( - argc-arg-1, argv+arg+1 ); - - if( ret > add ) - add = 0; - else - add -= ret; - arg += ret; - } - arg += add; - } - continue; - } - else - { - unknownParam( argc-arg, argv+arg ); - } - } - else - { - for( int chr = 1; argv[arg][chr]; chr++ ) - { - ArgSpec *s = checkLetr( argv[arg][chr] ); - if( s ) - { - if( argv[arg][chr+1] != '\0' ) - { - bool bUsed = false; - if( s->val.isSet() ) - { - if( s->sValue.getString() == NULL ) - { - s->val = argv[arg]+chr+1; - bUsed = true; - } - else - { - s->val = s->sValue.getString(); - } - } - if( s->proc ) - { - char **tmp = new char*[argc-arg]; - tmp[0] = argv[arg]+chr+1; - for( int k = 1; k < argc-arg; k++ ) - tmp[k] = argv[arg+k]; - int ret = (this->*s->proc)( argc-arg, tmp ); - if( ret > 0 ) - { - arg += ret - 1; - delete tmp; - break; - } - delete tmp; - } - if( bUsed ) - { - break; - } - } - else - { - bool bUsed = false; - if( s->val.isSet() ) - { - if( s->sValue.getString() == NULL ) - { - s->val = argv[arg+1]; - bUsed = true; - } - else - { - s->val = s->sValue.getString(); - } - } - if( s->proc ) - { - int ret = (this->*s->proc)( - argc-arg-1, argv+arg+1 - ); - if( ret > 0 ) - { - arg += ret; - break; - } - } - if( bUsed ) - { - arg++; - break; - } - } - } - else - { - unknownParam( argc-arg, argv+arg ); - } - } - } - } - else - { - cmdParam( argc-arg, argv+arg ); - } - } -} - -ParamProc::ArgSpec *ParamProc::checkWord( const char *arg ) -{ - //printf("Checking \"%s\"...\n", arg ); - std::list::const_iterator i; - for( i = lArg.begin(); i != lArg.end(); i++ ) - { - if( (*i)->sWord.getString() == NULL ) - continue; - - if( !strcmp( (*i)->sWord, arg ) ) - return *i; - - if( (*i)->val.isSet() ) - { - if( !strncmp( (*i)->sWord, arg, (*i)->sWord.getLength() ) && - arg[(*i)->sWord.getLength()] == '=' ) - { - return *i; - } - } - } - - return NULL; -} - -ParamProc::ArgSpec *ParamProc::checkLetr( const char arg ) -{ - //printf("Checking \'%c\'...\n", arg ); - std::list::const_iterator i; - for( i = lArg.begin(); i != lArg.end(); i++ ) - { - if( (*i)->cChar == '\0' ) - continue; - - if( (*i)->cChar == arg ) - { - return *i; - } - } - - return NULL; -} - -int ParamProc::cmdParam( int argc, char *argv[] ) -{ - printf("Unhandled command parameter \"%s\" found!\n", argv[0] ); - return 0; -} - -int ParamProc::unknownParam( int argc, char *argv[] ) -{ - printf("Unknown parameter \"%s\" found!\n", argv[0] ); - return 0; -} - -int ParamProc::help( int argc, char *argv[] ) -{ - std::list::const_iterator b = lBan.begin(); - std::list::const_iterator i; - int len=0; - for( i = lArg.begin(); i != lArg.end(); i++ ) - { - if( len < (*i)->sWord.getLength() + (*i)->sExtra.getLength() ) - len = (*i)->sWord.getLength() + (*i)->sExtra.getLength(); - } - char fmt[10]; - sprintf( fmt, "%%-%ds ", len ); - - for( i = lArg.begin(); i != lArg.end(); i++ ) - { - if( b != lBan.end() ) - { - if( (*b)->pBefore == (*i) ) - { - printf( (*b)->sBanner.getString() ); - b++; - } - } - printf(" "); - if( (*i)->cChar ) - { - if( (*i)->sWord.getString() ) - { - printf("-%c, ", (*i)->cChar ); - } - else - { - printf("-%c ", (*i)->cChar ); - } - } - else - { - printf(" "); - } - if( (*i)->sWord.getString() ) - { - printf("--"); - std::string sTmp = (*i)->sWord.getString(); - if( (*i)->sExtra.getString() ) - sTmp += (*i)->sExtra.getString(); - printf( fmt, sTmp.c_str() ); - } - else - { - printf(" "); - printf(fmt, "" ); - } - printf("%s\n", (*i)->sDesc.getString() ); - } - if( b != lBan.end() ) - { - if( (*b)->pBefore == NULL ) - { - printf( (*b)->sBanner.getString() ); - } - } - - exit( 0 ); -} - -void ParamProc::addHelpBanner( const char *sHelpBanner ) -{ - Banner *pBan = new Banner; - pBan->sBanner = sHelpBanner; - pBan->pBefore = NULL; - lBan.push_back( pBan ); -} - diff --git a/src/old/paramproc.h b/src/old/paramproc.h deleted file mode 100644 index d857193..0000000 --- a/src/old/paramproc.h +++ /dev/null @@ -1,153 +0,0 @@ -#ifndef PARAM_PROC_H -#define PARAM_PROC_H - -#include -#include -#include -#include "staticstring.h" - -class ParamProc -{ -public: - class ParamPtr - { - public: - ParamPtr(); - ParamPtr( std::string *str ); - ParamPtr( uint64_t *uint64 ); - ParamPtr( uint32_t *uint32 ); - ParamPtr( uint16_t *uint16 ); - ParamPtr( uint8_t *uint8 ); - ParamPtr( int64_t *int64 ); - ParamPtr( int32_t *int32 ); - ParamPtr( int16_t *int16 ); - ParamPtr( int8_t *int8 ); - ParamPtr( float *float32 ); - ParamPtr( double *float64 ); - ParamPtr( long double *float96 ); - ParamPtr( bool *bln ); - - enum - { - vtunset, - vtstr, - vtuint64, - vtuint32, - vtuint16, - vtuint8, - vtint64, - vtint32, - vtint16, - vtint8, - vtfloat32, - vtfloat64, - vtfloat96, - vtbln, - }; - ParamPtr &operator=( ParamPtr &ptr ); - ParamPtr &operator=( const char *str ); - - bool isSet(); - - private: - int type; - union - { - std::string *str; - uint64_t *uint64; - uint32_t *uint32; - uint16_t *uint16; - uint8_t *uint8; - int64_t *int64; - int32_t *int32; - int16_t *int16; - int8_t *int8; - float *float32; - double *float64; - long double *float96; - bool *bln; - } val; - }; - - typedef int (ParamProc::*Proc)( int, char *[] ); - - typedef struct ArgSpec - { - uint8_t nFlags; - StaticString sWord; - char cChar; - Proc proc; - ParamProc::ParamPtr val; - StaticString sExtra; - StaticString sDesc; - StaticString sValue; - } ArgSpec; - -public: - ParamProc(); - virtual ~ParamProc(); - - void addParam( const char *lpWord, char cChar, Proc proc, ParamPtr val, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - void addParam( const char *lpWord, char cChar, Proc proc, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - void addParam( const char *lpWord, char cChar, ParamPtr val, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - - void addParam( const char *lpWord, Proc proc, ParamPtr val, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - void addParam( const char *lpWord, Proc proc, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - void addParam( const char *lpWord, ParamPtr val, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - - void addParam( char cChar, Proc proc, ParamPtr val, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - void addParam( char cChar, Proc proc, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - void addParam( char cChar, ParamPtr val, - const char *lpDesc=NULL, const char *lpExtra=NULL, - const char *lpValue=NULL - ); - - void process( int argc, char *argv[] ); - void addHelpBanner( const char *sHelpBanner ); - -private: - ArgSpec *checkWord( const char *arg ); - ArgSpec *checkLetr( const char arg ); - -public: - virtual int cmdParam( int argc, char *argv[] ); - virtual int unknownParam( int argc, char *argv[] ); - virtual int help( int argc, char *argv[] ); - -private: - typedef struct Banner - { - StaticString sBanner; - ArgSpec *pBefore; - } Banner; - std::list lBan; - std::list lArg; -}; - -#define mkproc( cls ) static_cast(&cls) - -#endif diff --git a/src/paramproc.cpp b/src/paramproc.cpp new file mode 100644 index 0000000..34e973e --- /dev/null +++ b/src/paramproc.cpp @@ -0,0 +1,514 @@ +#include "paramproc.h" +#include + +#define ptrtype( iitype, iiname ) \ + Bu::ParamProc::ParamPtr::ParamPtr( iitype *iiname ) : \ + type( vt ##iiname ) { val.iiname = iiname; } + +Bu::ParamProc::ParamPtr::ParamPtr() +{ + val.str = NULL; + type = vtunset; +} + +ptrtype( std::string, str ); +ptrtype( uint64_t, uint64 ); +ptrtype( uint32_t, uint32 ); +ptrtype( uint16_t, uint16 ); +ptrtype( uint8_t, uint8 ); +ptrtype( int64_t, int64 ); +ptrtype( int32_t, int32 ); +ptrtype( int16_t, int16 ); +ptrtype( int8_t, int8 ); +ptrtype( float, float32 ); +ptrtype( double, float64 ); +ptrtype( long double, float96 ); +ptrtype( bool, bln ); + +Bu::ParamProc::ParamPtr &Bu::ParamProc::ParamPtr::operator=( ParamProc::ParamPtr &ptr ) +{ + val = ptr.val; + type = ptr.type; + + return *this; +} + +bool Bu::ParamProc::ParamPtr::isSet() +{ + return type != vtunset; +} + +Bu::ParamProc::ParamPtr &Bu::ParamProc::ParamPtr::operator=( const char *str ) +{ + if( !isSet() ) return *this; + switch( type ) + { + case vtstr: + (*val.str) = str; + break; + + case vtuint64: + (*val.uint64) = strtoull( str, NULL, 10 ); + break; + + case vtuint32: + (*val.uint32) = strtoul( str, NULL, 10 ); + break; + + case vtuint16: + (*val.uint16) = (uint16_t)strtoul( str, NULL, 10 ); + break; + + case vtuint8: + (*val.uint8) = (uint8_t)strtoul( str, NULL, 10 ); + break; + + case vtint64: + (*val.int64) = strtoll( str, NULL, 10 ); + break; + + case vtint32: + (*val.int32) = strtol( str, NULL, 10 ); + break; + + case vtint16: + (*val.int16) = (int16_t)strtol( str, NULL, 10 ); + break; + + case vtint8: + (*val.int8) = (int8_t)strtol( str, NULL, 10 ); + break; + + case vtfloat32: + (*val.float32) = strtof( str, NULL ); + break; + + case vtfloat64: + (*val.float64) = strtod( str, NULL ); + break; + + case vtfloat96: + (*val.float96) = strtold( str, NULL ); + break; + + case vtbln: + if( strcasecmp("yes", str ) == 0 || + strcasecmp("true", str ) == 0 ) + { + (*val.bln) = true; + } + else + { + (*val.bln) = false; + } + break; + } + + return *this; +} + +Bu::ParamProc::ParamProc() +{ +} + +Bu::ParamProc::~ParamProc() +{ + for( std::list::iterator i = lArg.begin(); + i != lArg.end(); i++ ) + { + delete *i; + } + + for( std::list::iterator i = lBan.begin(); + i != lBan.end(); i++ ) + { + delete *i; + } + +} +/* +void Bu::ParamProc::addParam( const char *lpWord, char cChar, Proc proc, ParamPtr val ) +{ + printf("Calling callback...\n"); + val = "Hello there, this is set in the ParamProc"; + (this->*proc)(); +}*/ + +void Bu::ParamProc::addParam( const char *lpWord, char cChar, Proc proc, + ParamPtr val, const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + ArgSpec *as = new ArgSpec; + if( lpWord ) + as->sWord = lpWord; + + as->cChar = cChar; + as->proc = proc; + as->val = val; + if( lpDesc ) + as->sDesc = lpDesc; + if( lpExtra ) + as->sExtra = lpExtra; + if( lpValue ) + as->sValue = lpValue; + + lArg.push_back( as ); + + if( !lBan.empty() ) + { + if( lBan.back()->pBefore == NULL ) + lBan.back()->pBefore = as; + } +} + +void Bu::ParamProc::addParam( const char *lpWord, char cChar, Proc proc, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( lpWord, cChar, proc, ParamPtr(), lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::addParam( const char *lpWord, char cChar, ParamPtr val, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( lpWord, cChar, NULL, val, lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::addParam( const char *lpWord, Proc proc, ParamPtr val, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( lpWord, '\0', proc, val, lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::addParam( const char *lpWord, Proc proc, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( lpWord, '\0', proc, ParamPtr(), lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::addParam( const char *lpWord, ParamPtr val, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( lpWord, '\0', NULL, val, lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::addParam( char cChar, Proc proc, ParamPtr val, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( NULL, cChar, proc, val, lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::addParam( char cChar, Proc proc, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( NULL, cChar, proc, ParamPtr(), lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::addParam( char cChar, ParamPtr val, + const char *lpDesc, const char *lpExtra, + const char *lpValue ) +{ + addParam( NULL, cChar, NULL, val, lpDesc, lpExtra, lpValue ); +} + +void Bu::ParamProc::process( int argc, char *argv[] ) +{ + for( int arg = 1; arg < argc; arg++ ) + { + //printf(":::%d:::%s\n", arg, argv[arg] ); + if( argv[arg][0] == '-' ) + { + if( argv[arg][1] == '-' ) + { + ArgSpec *s = checkWord( argv[arg]+2 ); + if( s ) + { + if( argv[arg][s->sWord.getSize()+2] == '=' ) + { + if( s->val.isSet() ) + { + if( s->sValue.getStr() == NULL ) + { + s->val = argv[arg]+s->sWord.getSize()+3; + } + else + { + s->val = s->sValue.getStr(); + } + } + if( s->proc ) + { + char **tmp = new char*[argc-arg]; + tmp[0] = argv[arg]+s->sWord.getSize()+3; + for( int k = 1; k < argc-arg; k++ ) + tmp[k] = argv[arg+k]; + int ret = (this->*s->proc)( argc-arg, tmp ); + if( ret > 0 ) + { + arg += ret-1; + } + delete tmp; + } + } + else + { + int add = 0; + if( s->val.isSet() ) + { + if( s->sValue.getStr() == NULL ) + { + if( arg+1 >= argc ) + { + return; + } + s->val = argv[arg+1]; + add++; + } + else + { + s->val = s->sValue.getStr(); + } + } + if( s->proc ) + { + int ret = (this->*s->proc)( + argc-arg-1, argv+arg+1 ); + + if( ret > add ) + add = 0; + else + add -= ret; + arg += ret; + } + arg += add; + } + continue; + } + else + { + unknownParam( argc-arg, argv+arg ); + } + } + else + { + for( int chr = 1; argv[arg][chr]; chr++ ) + { + ArgSpec *s = checkLetr( argv[arg][chr] ); + if( s ) + { + if( argv[arg][chr+1] != '\0' ) + { + bool bUsed = false; + if( s->val.isSet() ) + { + if( s->sValue.getStr() == NULL ) + { + s->val = argv[arg]+chr+1; + bUsed = true; + } + else + { + s->val = s->sValue.getStr(); + } + } + if( s->proc ) + { + char **tmp = new char*[argc-arg]; + tmp[0] = argv[arg]+chr+1; + for( int k = 1; k < argc-arg; k++ ) + tmp[k] = argv[arg+k]; + int ret = (this->*s->proc)( argc-arg, tmp ); + if( ret > 0 ) + { + arg += ret - 1; + delete tmp; + break; + } + delete tmp; + } + if( bUsed ) + { + break; + } + } + else + { + bool bUsed = false; + if( s->val.isSet() ) + { + if( s->sValue.getStr() == NULL ) + { + s->val = argv[arg+1]; + bUsed = true; + } + else + { + s->val = s->sValue.getStr(); + } + } + if( s->proc ) + { + int ret = (this->*s->proc)( + argc-arg-1, argv+arg+1 + ); + if( ret > 0 ) + { + arg += ret; + break; + } + } + if( bUsed ) + { + arg++; + break; + } + } + } + else + { + unknownParam( argc-arg, argv+arg ); + } + } + } + } + else + { + cmdParam( argc-arg, argv+arg ); + } + } +} + +Bu::ParamProc::ArgSpec *Bu::ParamProc::checkWord( const char *arg ) +{ + //printf("Checking \"%s\"...\n", arg ); + std::list::const_iterator i; + for( i = lArg.begin(); i != lArg.end(); i++ ) + { + if( (*i)->sWord.getStr() == NULL ) + continue; + + if( !strcmp( (*i)->sWord.getStr(), arg ) ) + return *i; + + if( (*i)->val.isSet() ) + { + if( !strncmp( (*i)->sWord.getStr(), arg, (*i)->sWord.getSize() ) && + arg[(*i)->sWord.getSize()] == '=' ) + { + return *i; + } + } + } + + return NULL; +} + +Bu::ParamProc::ArgSpec *Bu::ParamProc::checkLetr( const char arg ) +{ + //printf("Checking \'%c\'...\n", arg ); + std::list::const_iterator i; + for( i = lArg.begin(); i != lArg.end(); i++ ) + { + if( (*i)->cChar == '\0' ) + continue; + + if( (*i)->cChar == arg ) + { + return *i; + } + } + + return NULL; +} + +int Bu::ParamProc::cmdParam( int argc, char *argv[] ) +{ + printf("Unhandled command parameter \"%s\" found!\n", argv[0] ); + return 0; +} + +int Bu::ParamProc::unknownParam( int argc, char *argv[] ) +{ + printf("Unknown parameter \"%s\" found!\n", argv[0] ); + return 0; +} + +int Bu::ParamProc::help( int argc, char *argv[] ) +{ + std::list::const_iterator b = lBan.begin(); + std::list::const_iterator i; + int len=0; + for( i = lArg.begin(); i != lArg.end(); i++ ) + { + if( len < (*i)->sWord.getSize() + (*i)->sExtra.getSize() ) + len = (*i)->sWord.getSize() + (*i)->sExtra.getSize(); + } + char fmt[10]; + sprintf( fmt, "%%-%ds ", len ); + + for( i = lArg.begin(); i != lArg.end(); i++ ) + { + if( b != lBan.end() ) + { + if( (*b)->pBefore == (*i) ) + { + printf( (*b)->sBanner.getStr() ); + b++; + } + } + printf(" "); + if( (*i)->cChar ) + { + if( (*i)->sWord.getStr() ) + { + printf("-%c, ", (*i)->cChar ); + } + else + { + printf("-%c ", (*i)->cChar ); + } + } + else + { + printf(" "); + } + if( (*i)->sWord.getStr() ) + { + printf("--"); + std::string sTmp = (*i)->sWord.getStr(); + if( (*i)->sExtra.getStr() ) + sTmp += (*i)->sExtra.getStr(); + printf( fmt, sTmp.c_str() ); + } + else + { + printf(" "); + printf(fmt, "" ); + } + printf("%s\n", (*i)->sDesc.getStr() ); + } + if( b != lBan.end() ) + { + if( (*b)->pBefore == NULL ) + { + printf( (*b)->sBanner.getStr() ); + } + } + + exit( 0 ); +} + +void Bu::ParamProc::addHelpBanner( const char *sHelpBanner ) +{ + Banner *pBan = new Banner; + pBan->sBanner = sHelpBanner; + pBan->pBefore = NULL; + lBan.push_back( pBan ); +} + diff --git a/src/paramproc.h b/src/paramproc.h new file mode 100644 index 0000000..beee4a0 --- /dev/null +++ b/src/paramproc.h @@ -0,0 +1,156 @@ +#ifndef PARAM_PROC_H +#define PARAM_PROC_H + +#include +#include +#include +#include "bu/fstring.h" + +namespace Bu +{ + class ParamProc + { + public: + class ParamPtr + { + public: + ParamPtr(); + ParamPtr( std::string *str ); + ParamPtr( uint64_t *uint64 ); + ParamPtr( uint32_t *uint32 ); + ParamPtr( uint16_t *uint16 ); + ParamPtr( uint8_t *uint8 ); + ParamPtr( int64_t *int64 ); + ParamPtr( int32_t *int32 ); + ParamPtr( int16_t *int16 ); + ParamPtr( int8_t *int8 ); + ParamPtr( float *float32 ); + ParamPtr( double *float64 ); + ParamPtr( long double *float96 ); + ParamPtr( bool *bln ); + + enum + { + vtunset, + vtstr, + vtuint64, + vtuint32, + vtuint16, + vtuint8, + vtint64, + vtint32, + vtint16, + vtint8, + vtfloat32, + vtfloat64, + vtfloat96, + vtbln, + }; + ParamPtr &operator=( ParamPtr &ptr ); + ParamPtr &operator=( const char *str ); + + bool isSet(); + + private: + int type; + union + { + std::string *str; + uint64_t *uint64; + uint32_t *uint32; + uint16_t *uint16; + uint8_t *uint8; + int64_t *int64; + int32_t *int32; + int16_t *int16; + int8_t *int8; + float *float32; + double *float64; + long double *float96; + bool *bln; + } val; + }; + + typedef int (ParamProc::*Proc)( int, char *[] ); + + typedef struct ArgSpec + { + uint8_t nFlags; + Bu::FString sWord; + char cChar; + Proc proc; + ParamProc::ParamPtr val; + Bu::FString sExtra; + Bu::FString sDesc; + Bu::FString sValue; + } ArgSpec; + + public: + ParamProc(); + virtual ~ParamProc(); + + void addParam( const char *lpWord, char cChar, Proc proc, ParamPtr val, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + void addParam( const char *lpWord, char cChar, Proc proc, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + void addParam( const char *lpWord, char cChar, ParamPtr val, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + + void addParam( const char *lpWord, Proc proc, ParamPtr val, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + void addParam( const char *lpWord, Proc proc, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + void addParam( const char *lpWord, ParamPtr val, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + + void addParam( char cChar, Proc proc, ParamPtr val, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + void addParam( char cChar, Proc proc, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + void addParam( char cChar, ParamPtr val, + const char *lpDesc=NULL, const char *lpExtra=NULL, + const char *lpValue=NULL + ); + + void process( int argc, char *argv[] ); + void addHelpBanner( const char *sHelpBanner ); + + private: + ArgSpec *checkWord( const char *arg ); + ArgSpec *checkLetr( const char arg ); + + public: + virtual int cmdParam( int argc, char *argv[] ); + virtual int unknownParam( int argc, char *argv[] ); + virtual int help( int argc, char *argv[] ); + + private: + typedef struct Banner + { + Bu::FString sBanner; + ArgSpec *pBefore; + } Banner; + std::list lBan; + std::list lArg; + }; +} + +#define mkproc( cls ) static_cast(&cls) + +#endif diff --git a/src/stream.h b/src/stream.h index 5f586e6..fa0a606 100644 --- a/src/stream.h +++ b/src/stream.h @@ -39,6 +39,9 @@ namespace Bu virtual bool isBlocking() = 0; virtual void setBlocking( bool bBlocking=true ) = 0; + public: // Filters + + private: }; diff --git a/src/tests/bzip2.cpp b/src/tests/bzip2.cpp new file mode 100644 index 0000000..683d3d7 --- /dev/null +++ b/src/tests/bzip2.cpp @@ -0,0 +1,23 @@ +#include "bu/bzip2.h" +#include "bu/file.h" + +int main( int argc, char *argv[] ) +{ + char buf[1024]; + size_t nRead; + + Bu::File f( "test.bz2", "wb" ); + Bu::BZip2 bz2( f ); + + Bu::File fin( argv[1], "rb"); + + for(;;) + { + nRead = fin.read( buf, 1024 ); + if( nRead > 0 ) + bz2.write( buf, nRead ); + if( fin.isEOS() ) + break; + } +} + -- cgit v1.2.3 From f5352edf3dc23c044a91f1d1537fa0dc0f0babc7 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Sat, 9 Jun 2007 05:43:04 +0000 Subject: Alright, looks like the bzip2 filter can decompress just fine. It won't try to compensate for overshooting the end of the compression block yet, which it won't be able to do on streams that don't support seeking...I think I'll make it only try on stop commands, and try to re-use the buffer otherwise...maybe...it's an interesting problem since it *always* overshoots (unless you're really, really lucky...) --- src/bzip2.cpp | 37 ++++++++++++++++++++++++++++++------- src/tests/bzip2.cpp | 10 +++++----- 2 files changed, 35 insertions(+), 12 deletions(-) (limited to 'src/tests') diff --git a/src/bzip2.cpp b/src/bzip2.cpp index b8c0f74..433fc91 100644 --- a/src/bzip2.cpp +++ b/src/bzip2.cpp @@ -12,14 +12,11 @@ Bu::BZip2::BZip2( Bu::Stream &rNext, int nCompression ) : Bu::BZip2::~BZip2() { - printf("-> Bu::BZip2::~BZip2()\n"); stop(); } void Bu::BZip2::start() { - printf("-> Bu::BZip2::start()\n"); - printf("Hey, it's starting...\n"); bzState.state = NULL; bzState.bzalloc = NULL; bzState.bzfree = NULL; @@ -31,11 +28,11 @@ void Bu::BZip2::start() void Bu::BZip2::stop() { - printf("-> Bu::BZip2::stop()\n"); if( bzState.state ) { if( bReading ) { + BZ2_bzDecompressEnd( &bzState ); } else { @@ -81,13 +78,39 @@ size_t Bu::BZip2::read( void *pData, size_t nBytes ) if( !bzState.state ) { bReading = true; + BZ2_bzDecompressInit( &bzState, 0, 0 ); + bzState.next_in = pBuf; + bzState.avail_in = 0; } if( bReading == false ) throw ExceptionBase("This bzip2 filter is in writing mode, you can't read."); - //bzState.next_in = pData; - //bzState.avail_in = nSizeIn; + + int nRead = 0; + int nReadTotal = bzState.total_out_lo32; + for(;;) + { + bzState.next_out = (char *)pData; + bzState.avail_out = nBytes; + int ret = BZ2_bzDecompress( &bzState ); - //printf("%db at [%08X] (%db)\n", bzState.avail_in, (uint32_t)bzState.next_in, bzState.total_in_lo32 ); + nReadTotal += nRead-bzState.avail_out; + + if( ret == BZ_STREAM_END ) + { + return nBytes-bzState.avail_out; + } + + if( bzState.avail_out ) + { + nRead = rNext.read( pBuf, nBufSize ); + bzState.next_in = pBuf; + bzState.avail_in = nRead; + } + else + { + return nBytes-bzState.avail_out; + } + } return 0; } diff --git a/src/tests/bzip2.cpp b/src/tests/bzip2.cpp index 683d3d7..ef9328f 100644 --- a/src/tests/bzip2.cpp +++ b/src/tests/bzip2.cpp @@ -6,17 +6,17 @@ int main( int argc, char *argv[] ) char buf[1024]; size_t nRead; - Bu::File f( "test.bz2", "wb" ); + Bu::File f( "test.bz2", "rb" ); Bu::BZip2 bz2( f ); - Bu::File fin( argv[1], "rb"); + Bu::File fin( argv[1], "wb"); for(;;) { - nRead = fin.read( buf, 1024 ); + nRead = bz2.read( buf, 1024 ); if( nRead > 0 ) - bz2.write( buf, nRead ); - if( fin.isEOS() ) + fin.write( buf, nRead ); + if( bz2.isEOS() ) break; } } -- cgit v1.2.3 From 5f39066a4f561e9a94a6cc9293ab9b978ebf1f81 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Sun, 10 Jun 2007 21:28:14 +0000 Subject: Bunch of maintenence type things. Minor tweaks and the like. The file class has a lot more helper functions and the like, the filters give more info back to the caller, minor updates to taf. --- src/bzip2.cpp | 41 ++++++++++++++++++++++++++++++++++------- src/bzip2.h | 2 +- src/file.cpp | 31 +++++++++++++++++++++++++++++++ src/file.h | 17 ++++++++++++++++- src/filter.cpp | 7 ++++++- src/filter.h | 4 +++- src/socket.cpp | 4 ++++ src/socket.h | 2 ++ src/stream.h | 2 ++ src/tafnode.cpp | 6 +++--- src/tafnode.h | 4 ++-- src/tests/taf.cpp | 2 +- 12 files changed, 105 insertions(+), 17 deletions(-) (limited to 'src/tests') diff --git a/src/bzip2.cpp b/src/bzip2.cpp index 433fc91..5423a10 100644 --- a/src/bzip2.cpp +++ b/src/bzip2.cpp @@ -26,16 +26,18 @@ void Bu::BZip2::start() pBuf = new char[nBufSize]; } -void Bu::BZip2::stop() +size_t Bu::BZip2::stop() { if( bzState.state ) { if( bReading ) { BZ2_bzDecompressEnd( &bzState ); + return 0; } else { + size_t sTotal = 0; for(;;) { bzState.next_in = NULL; @@ -45,14 +47,16 @@ void Bu::BZip2::stop() int res = BZ2_bzCompress( &bzState, BZ_FINISH ); if( bzState.avail_out < nBufSize ) { - rNext.write( pBuf, nBufSize-bzState.avail_out ); + sTotal += rNext.write( pBuf, nBufSize-bzState.avail_out ); } if( res == BZ_STREAM_END ) break; } BZ2_bzCompressEnd( &bzState ); + return sTotal; } } + return 0; } void Bu::BZip2::bzError( int code ) @@ -63,13 +67,35 @@ void Bu::BZip2::bzError( int code ) return; case BZ_CONFIG_ERROR: - throw ExceptionBase("The bzip2 library has been miscompiled."); + throw ExceptionBase("BZip2: Library configured improperly, reinstall."); + + case BZ_SEQUENCE_ERROR: + throw ExceptionBase("BZip2: Functions were called in an invalid sequence."); case BZ_PARAM_ERROR: - throw ExceptionBase("bzip2 parameter error."); + throw ExceptionBase("BZip2: Invalid parameter was passed into a function."); case BZ_MEM_ERROR: - throw ExceptionBase("Not enough memory available for bzip2."); + throw ExceptionBase("BZip2: Couldn't allocate sufficient memory."); + + case BZ_DATA_ERROR: + throw ExceptionBase("BZip2: Data was corrupted before decompression."); + + case BZ_DATA_ERROR_MAGIC: + throw ExceptionBase("BZip2: Stream does not appear to be bzip2 data."); + + case BZ_IO_ERROR: + throw ExceptionBase("BZip2: File couldn't be read from / written to."); + + case BZ_UNEXPECTED_EOF: + throw ExceptionBase("BZip2: End of file encountered before end of stream."); + + case BZ_OUTBUFF_FULL: + throw ExceptionBase("BZip2: Buffer not large enough to accomidate data."); + + default: + throw ExceptionBase("BZip2: Unknown error encountered."); + } } @@ -124,6 +150,7 @@ size_t Bu::BZip2::write( const void *pData, size_t nBytes ) if( bReading == true ) throw ExceptionBase("This bzip2 filter is in reading mode, you can't write."); + size_t sTotalOut = 0; bzState.next_in = (char *)pData; bzState.avail_in = nBytes; for(;;) @@ -135,12 +162,12 @@ size_t Bu::BZip2::write( const void *pData, size_t nBytes ) if( bzState.avail_out < nBufSize ) { - rNext.write( pBuf, nBufSize-bzState.avail_out ); + sTotalOut += rNext.write( pBuf, nBufSize-bzState.avail_out ); } if( bzState.avail_in == 0 ) break; } - return 0; + return sTotalOut; } diff --git a/src/bzip2.h b/src/bzip2.h index 056f336..a23f07a 100644 --- a/src/bzip2.h +++ b/src/bzip2.h @@ -18,7 +18,7 @@ namespace Bu virtual ~BZip2(); virtual void start(); - virtual void stop(); + virtual size_t stop(); virtual size_t read( void *pBuf, size_t nBytes ); virtual size_t write( const void *pBuf, size_t nBytes ); diff --git a/src/file.cpp b/src/file.cpp index 26986a5..14b6e54 100644 --- a/src/file.cpp +++ b/src/file.cpp @@ -1,6 +1,8 @@ #include "file.h" #include "exceptions.h" #include +#include +#include Bu::File::File( const char *sName, const char *sFlags ) { @@ -11,6 +13,20 @@ Bu::File::File( const char *sName, const char *sFlags ) } } +Bu::File::File( const Bu::FString &sName, const char *sFlags ) +{ + fh = fopen( sName.getStr(), sFlags ); + if( fh == NULL ) + { + throw Bu::FileException( errno, strerror(errno) ); + } +} + +Bu::File::File( int fd, const char *sFlags ) +{ + fh = fdopen( fd, sFlags ); +} + Bu::File::~File() { close(); @@ -108,3 +124,18 @@ void Bu::File::setBlocking( bool bBlocking ) return; } +void Bu::File::truncate( long nSize ) +{ + ftruncate( fileno( fh ), nSize ); +} + +void Bu::File::flush() +{ + fflush( fh ); +} + +void Bu::File::chmod( mode_t t ) +{ + fchmod( fileno( fh ), t ); +} + diff --git a/src/file.h b/src/file.h index ee3fdb3..8107a1b 100644 --- a/src/file.h +++ b/src/file.h @@ -3,7 +3,8 @@ #include -#include "stream.h" +#include "bu/stream.h" +#include "bu/fstring.h" namespace Bu { @@ -11,6 +12,8 @@ namespace Bu { public: File( const char *sName, const char *sFlags ); + File( const Bu::FString &sName, const char *sFlags ); + File( int fd, const char *sFlags ); virtual ~File(); virtual void close(); @@ -23,6 +26,8 @@ namespace Bu virtual void setPosEnd( long pos ); virtual bool isEOS(); + virtual void flush(); + virtual bool canRead(); virtual bool canWrite(); virtual bool canSeek(); @@ -30,6 +35,16 @@ namespace Bu virtual bool isBlocking(); virtual void setBlocking( bool bBlocking=true ); + inline static Bu::File tempFile( Bu::FString &sName, const char *sFlags ) + { + int afh_d = mkstemp( sName.getStr() ); + + return Bu::File( afh_d, sFlags ); + } + + void truncate( long nSize ); + void chmod( mode_t t ); + private: FILE *fh; diff --git a/src/filter.cpp b/src/filter.cpp index d3faa00..693fb9f 100644 --- a/src/filter.cpp +++ b/src/filter.cpp @@ -7,7 +7,7 @@ Bu::Filter::Filter( Bu::Stream &rNext ) : Bu::Filter::~Filter() { - printf("-> Bu::Filter::~Filter()\n"); + //printf("-> Bu::Filter::~Filter()\n"); } /* void Bu::Filter::start() @@ -75,3 +75,8 @@ void Bu::Filter::setBlocking( bool bBlocking ) rNext.setBlocking( bBlocking ); } +void Bu::Filter::flush() +{ + rNext.flush(); +} + diff --git a/src/filter.h b/src/filter.h index b068206..088d46e 100644 --- a/src/filter.h +++ b/src/filter.h @@ -33,7 +33,7 @@ namespace Bu virtual ~Filter(); virtual void start()=0; - virtual void stop()=0; + virtual size_t stop()=0; virtual void close(); virtual long tell(); virtual void seek( long offset ); @@ -41,6 +41,8 @@ namespace Bu virtual void setPosEnd( long pos ); virtual bool isEOS(); + virtual void flush(); + virtual bool canRead(); virtual bool canWrite(); virtual bool canSeek(); diff --git a/src/socket.cpp b/src/socket.cpp index 441678a..1832898 100644 --- a/src/socket.cpp +++ b/src/socket.cpp @@ -240,3 +240,7 @@ void Bu::Socket::setBlocking( bool bBlocking ) { } +void Bu::Socket::flush() +{ +} + diff --git a/src/socket.h b/src/socket.h index e65eb74..30a43fb 100644 --- a/src/socket.h +++ b/src/socket.h @@ -29,6 +29,8 @@ namespace Bu virtual void setPosEnd( long pos ); virtual bool isEOS(); + virtual void flush(); + virtual bool canRead(); virtual bool canWrite(); virtual bool canSeek(); diff --git a/src/stream.h b/src/stream.h index fa0a606..a80586b 100644 --- a/src/stream.h +++ b/src/stream.h @@ -32,6 +32,8 @@ namespace Bu virtual void setPosEnd( long pos ) = 0; virtual bool isEOS() = 0; + virtual void flush() = 0; + virtual bool canRead() = 0; virtual bool canWrite() = 0; virtual bool canSeek() = 0; diff --git a/src/tafnode.cpp b/src/tafnode.cpp index 3060606..b9a4a24 100644 --- a/src/tafnode.cpp +++ b/src/tafnode.cpp @@ -45,7 +45,7 @@ const Bu::TafNode::PropList &Bu::TafNode::getProperties( const Bu::FString &sNam return hProp.get( sName ); } -const Bu::TafNode::NodeList &Bu::TafNode::getNodes( const Bu::FString &sName ) const +const Bu::TafNode::NodeList &Bu::TafNode::getChildren( const Bu::FString &sName ) const { return hChildren.get( sName ); } @@ -55,9 +55,9 @@ const Bu::FString &Bu::TafNode::getProperty( const Bu::FString &sName ) const return getProperties( sName ).first(); } -const Bu::TafNode *Bu::TafNode::getNode( const Bu::FString &sName ) const +const Bu::TafNode *Bu::TafNode::getChild( const Bu::FString &sName ) const { - return getNodes( sName ).first(); + return getChildren( sName ).first(); } void Bu::TafNode::setName( const Bu::FString &sName ) diff --git a/src/tafnode.h b/src/tafnode.h index 10232d2..08f78e8 100644 --- a/src/tafnode.h +++ b/src/tafnode.h @@ -28,9 +28,9 @@ namespace Bu void setProperty( Bu::FString sName, Bu::FString sValue ); const Bu::FString &getProperty( const Bu::FString &sName ) const; - const TafNode *getNode( const Bu::FString &sName ) const; const PropList &getProperties( const Bu::FString &sName ) const; - const NodeList &getNodes( const Bu::FString &sName ) const; + const TafNode *getChild( const Bu::FString &sName ) const; + const NodeList &getChildren( const Bu::FString &sName ) const; void addChild( TafNode *pNode ); private: diff --git a/src/tests/taf.cpp b/src/tests/taf.cpp index e7bad52..d135e78 100644 --- a/src/tests/taf.cpp +++ b/src/tests/taf.cpp @@ -8,7 +8,7 @@ int main() Bu::TafNode *pNode = tr.getNode(); - const Bu::TafNode *pStats = pNode->getNode("stats"); + const Bu::TafNode *pStats = pNode->getChild("stats"); printf("%s\n", pStats->getName().getStr() ); printf(" str = %s\n", pStats->getProperty("str").getStr() ); -- cgit v1.2.3 From 408aca47fd423e7c4c38665b892a13c1c9fb1e9a Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Mon, 11 Jun 2007 07:31:52 +0000 Subject: Few minor tweaks to bzip2, it reports errors now...and there's a bug in odpm that could be in this, but it's going to be hard to tell... --- src/bzip2.cpp | 31 +++++++++++++++++++++++++++---- src/tests/bzip2.cpp | 10 +++++----- 2 files changed, 32 insertions(+), 9 deletions(-) (limited to 'src/tests') diff --git a/src/bzip2.cpp b/src/bzip2.cpp index 5423a10..6bb1429 100644 --- a/src/bzip2.cpp +++ b/src/bzip2.cpp @@ -64,6 +64,13 @@ void Bu::BZip2::bzError( int code ) switch( code ) { case BZ_OK: + printf("\n"); return; + case BZ_RUN_OK: + printf("\n"); return; + case BZ_FLUSH_OK: + printf("\n"); return; + case BZ_FINISH_OK: + printf("\n"); return; return; case BZ_CONFIG_ERROR: @@ -117,20 +124,36 @@ size_t Bu::BZip2::read( void *pData, size_t nBytes ) { bzState.next_out = (char *)pData; bzState.avail_out = nBytes; + printf(" (pre) in: %db, out: %db\n", bzState.avail_in, bzState.avail_out ); int ret = BZ2_bzDecompress( &bzState ); + printf("(post) in: %db, out: %db\n", bzState.avail_in, bzState.avail_out ); nReadTotal += nRead-bzState.avail_out; if( ret == BZ_STREAM_END ) { + printf("\n"); + if( bzState.avail_in > 0 ) + { + if( rNext.canSeek() ) + { + rNext.seek( -bzState.avail_in ); + } + } return nBytes-bzState.avail_out; } + bzError( ret ); if( bzState.avail_out ) { - nRead = rNext.read( pBuf, nBufSize ); - bzState.next_in = pBuf; - bzState.avail_in = nRead; + printf("Still more to fill, in: %db, out: %db\n", bzState.avail_in, bzState.avail_out ); + + if( bzState.avail_in == 0 ) + { + nRead = rNext.read( pBuf, nBufSize ); + bzState.next_in = pBuf; + bzState.avail_in = nRead; + } } else { @@ -158,7 +181,7 @@ size_t Bu::BZip2::write( const void *pData, size_t nBytes ) bzState.avail_out = nBufSize; bzState.next_out = pBuf; - BZ2_bzCompress( &bzState, BZ_RUN ); + bzError( BZ2_bzCompress( &bzState, BZ_RUN ) ); if( bzState.avail_out < nBufSize ) { diff --git a/src/tests/bzip2.cpp b/src/tests/bzip2.cpp index ef9328f..683d3d7 100644 --- a/src/tests/bzip2.cpp +++ b/src/tests/bzip2.cpp @@ -6,17 +6,17 @@ int main( int argc, char *argv[] ) char buf[1024]; size_t nRead; - Bu::File f( "test.bz2", "rb" ); + Bu::File f( "test.bz2", "wb" ); Bu::BZip2 bz2( f ); - Bu::File fin( argv[1], "wb"); + Bu::File fin( argv[1], "rb"); for(;;) { - nRead = bz2.read( buf, 1024 ); + nRead = fin.read( buf, 1024 ); if( nRead > 0 ) - fin.write( buf, nRead ); - if( bz2.isEOS() ) + bz2.write( buf, nRead ); + if( fin.isEOS() ) break; } } -- cgit v1.2.3 From 9f98bc834ce2ac524c47ef633be4b4fb9eb8a079 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Tue, 12 Jun 2007 20:41:00 +0000 Subject: Removed the xml test...the xml system is effectively gone. --- src/tests/xml.cpp | 15 --------------- 1 file changed, 15 deletions(-) delete mode 100644 src/tests/xml.cpp (limited to 'src/tests') diff --git a/src/tests/xml.cpp b/src/tests/xml.cpp deleted file mode 100644 index 9689a28..0000000 --- a/src/tests/xml.cpp +++ /dev/null @@ -1,15 +0,0 @@ -#include "bu/xmlreader.h" -#include "bu/xmlnode.h" -#include "bu/xmldocument.h" -#include "bu/file.h" - -int main() -{ - Bu::File f("test.xml", "r"); - XmlReader xr( f ); - - //xr.read(); - - return 0; -} - -- cgit v1.2.3 From f58a0b3a1f657124076b96ba092e1f69e88af263 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Mon, 18 Jun 2007 20:25:50 +0000 Subject: Added the atom class and did some more client work, it will close the socket now when the end has been reached. --- src/atom.cpp | 1 + src/atom.h | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ src/client.cpp | 5 +++ src/tests/atom.cpp | 17 ++++++++++ 4 files changed, 116 insertions(+) create mode 100644 src/atom.cpp create mode 100644 src/atom.h create mode 100644 src/tests/atom.cpp (limited to 'src/tests') diff --git a/src/atom.cpp b/src/atom.cpp new file mode 100644 index 0000000..f966bfc --- /dev/null +++ b/src/atom.cpp @@ -0,0 +1 @@ +#include "bu/atom.h" diff --git a/src/atom.h b/src/atom.h new file mode 100644 index 0000000..731e08b --- /dev/null +++ b/src/atom.h @@ -0,0 +1,93 @@ +#ifndef ATOM_H +#define ATOM_H + +#include +#include +#include "bu/exceptions.h" + +namespace Bu +{ + /** + * + */ + template > + class Atom + { + private: + typedef struct Atom MyType; + + public: + Atom() : + pData( NULL ) + { + } + + virtual ~Atom() + { + clear(); + } + + bool isSet() const + { + return (pData != NULL); + } + + void set( const t &val ) + { + clear(); + pData = ta.allocate( 1 ); + ta.construct( pData, val ); + } + + t &get() + { + if( !pData ) + throw Bu::ExceptionBase("Not set"); + return *pData; + } + + const t &get() const + { + if( !pData ) + throw Bu::ExceptionBase("Not set"); + return *pData; + } + + void clear() + { + if( pData ) + { + ta.destroy( pData ); + ta.deallocate( pData, 1 ); + pData = NULL; + } + } + + operator const t &() const + { + if( !pData ) + throw Bu::ExceptionBase("Not set"); + return *pData; + } + + operator t &() + { + if( !pData ) + throw Bu::ExceptionBase("Not set"); + return *pData; + } + + MyType &operator =( const t &oth ) + { + set( oth ); + + return *this; + } + + private: + t *pData; + talloc ta; + }; +} + +#endif diff --git a/src/client.cpp b/src/client.cpp index cf96424..6d7d81c 100644 --- a/src/client.cpp +++ b/src/client.cpp @@ -47,6 +47,11 @@ void Bu::Client::processInput() } } + if( nTotal == 0 ) + { + pSocket->close(); + } + if( pProto && nTotal ) { pProto->onNewData( this ); diff --git a/src/tests/atom.cpp b/src/tests/atom.cpp new file mode 100644 index 0000000..cf076b1 --- /dev/null +++ b/src/tests/atom.cpp @@ -0,0 +1,17 @@ +#include "bu/atom.h" +#include +#include + +int main() +{ + Bu::Atom aInt; + Bu::Atom aStr; + + aStr.set("Hey there, dude"); + aInt.set( 55 ); + int me = aInt; + aInt = 12; + printf("%d, %d\n", aInt.get(), me ); + printf("%s\n", aStr.get() ); +} + -- cgit v1.2.3 From 8a7fed8386c152023ddae611fe274b966287370a Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Mon, 18 Jun 2007 22:49:39 +0000 Subject: Added more helper guys to atom, it seems weird, but I think it's ok... --- src/atom.h | 14 ++++++++++++++ src/tests/atom.cpp | 8 ++++++++ 2 files changed, 22 insertions(+) (limited to 'src/tests') diff --git a/src/atom.h b/src/atom.h index f876274..a0469b6 100644 --- a/src/atom.h +++ b/src/atom.h @@ -84,6 +84,20 @@ namespace Bu return *this; } + t *operator ->() + { + if( !pData ) + throw Bu::ExceptionBase("Not set"); + return pData; + } + + t &operator *() + { + if( !pData ) + throw Bu::ExceptionBase("Not set"); + return *pData; + } + private: t *pData; talloc ta; diff --git a/src/tests/atom.cpp b/src/tests/atom.cpp index cf076b1..2077bfd 100644 --- a/src/tests/atom.cpp +++ b/src/tests/atom.cpp @@ -2,10 +2,18 @@ #include #include +typedef struct bob +{ + int a, b; +} bob; int main() { Bu::Atom aInt; Bu::Atom aStr; + Bu::Atom aBob; + + aBob = bob(); + aBob->a = 5; aStr.set("Hey there, dude"); aInt.set( 55 ); -- cgit v1.2.3 From 2b0fa89df615cb4789668014475ae64d99e773b5 Mon Sep 17 00:00:00 2001 From: David Date: Tue, 19 Jun 2007 06:05:55 +0000 Subject: david - got some things compiling on win32 (wine/devc++) --- fstringtest.dev | 59 ++++++++++++++ libbu++.dev | 209 ++++++++++++++++++++++++++++++++++++++++++++++++++ src/file.cpp | 10 ++- src/file.h | 2 + src/tests/fstring.cpp | 10 +++ 5 files changed, 286 insertions(+), 4 deletions(-) create mode 100644 fstringtest.dev create mode 100644 libbu++.dev (limited to 'src/tests') diff --git a/fstringtest.dev b/fstringtest.dev new file mode 100644 index 0000000..297242d --- /dev/null +++ b/fstringtest.dev @@ -0,0 +1,59 @@ +[Project] +FileName=fstringtest.dev +Name=fstringtest +UnitCount=1 +Type=1 +Ver=1 +ObjFiles= +Includes=z:\home\neonphog\wine_documents\libbu++\src\bu +Libs= +PrivateResource= +ResourceIncludes= +MakeIncludes= +Compiler= +CppCompiler=_@@_ +Linker=libbu++.a_@@_ +IsCpp=1 +Icon= +ExeOutput= +ObjectOutput= +OverrideOutput=0 +OverrideOutputName=fstringtest.exe +HostApplication= +Folders= +CommandLine= +UseCustomMakefile=0 +CustomMakefile= +IncludeVersionInfo=0 +SupportXPThemes=0 +CompilerSet=0 +CompilerSettings=0000000000000000000000 + +[VersionInfo] +Major=0 +Minor=1 +Release=1 +Build=1 +LanguageID=1033 +CharsetID=1252 +CompanyName= +FileVersion= +FileDescription=Developed using the Dev-C++ IDE +InternalName= +LegalCopyright= +LegalTrademarks= +OriginalFilename= +ProductName= +ProductVersion= +AutoIncBuildNr=0 + +[Unit1] +FileName=src\tests\fstring.cpp +CompileCpp=1 +Folder=fstringtest +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + diff --git a/libbu++.dev b/libbu++.dev new file mode 100644 index 0000000..2fb1ae9 --- /dev/null +++ b/libbu++.dev @@ -0,0 +1,209 @@ +[Project] +FileName=libbu++.dev +Name=libbu++ +UnitCount=16 +Type=2 +Ver=1 +ObjFiles= +Includes=z:\home\neonphog\wine_documents\libbu++\src\bu +Libs= +PrivateResource= +ResourceIncludes= +MakeIncludes= +Compiler= +CppCompiler= +Linker= +IsCpp=1 +Icon= +ExeOutput= +ObjectOutput= +OverrideOutput=0 +OverrideOutputName=libbu++.a +HostApplication= +Folders= +CommandLine= +UseCustomMakefile=0 +CustomMakefile= +IncludeVersionInfo=0 +SupportXPThemes=0 +CompilerSet=0 +CompilerSettings=0000000000000000000000 + +[Unit1] +FileName=src\stream.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[VersionInfo] +Major=0 +Minor=1 +Release=1 +Build=1 +LanguageID=1033 +CharsetID=1252 +CompanyName= +FileVersion= +FileDescription=Developed using the Dev-C++ IDE +InternalName= +LegalCopyright= +LegalTrademarks= +OriginalFilename= +ProductName= +ProductVersion= +AutoIncBuildNr=0 + +[Unit2] +FileName=src\stream.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit3] +FileName=src\file.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit4] +FileName=src\file.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit5] +FileName=src\fstring.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit6] +FileName=src\fstring.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit7] +FileName=src\archival.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit8] +FileName=src\archival.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit9] +FileName=src\archive.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit10] +FileName=src\archive.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit11] +FileName=src\hash.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit12] +FileName=src\hash.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit13] +FileName=src\exceptionbase.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit14] +FileName=src\exceptionbase.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit15] +FileName=src\list.cpp +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + +[Unit16] +FileName=src\list.h +CompileCpp=1 +Folder=libbu++ +Compile=1 +Link=1 +Priority=1000 +OverrideBuildCmd=0 +BuildCmd= + diff --git a/src/file.cpp b/src/file.cpp index 368b788..1a8bd08 100644 --- a/src/file.cpp +++ b/src/file.cpp @@ -134,19 +134,21 @@ void Bu::File::setBlocking( bool bBlocking ) return; } +#ifndef WIN32 void Bu::File::truncate( long nSize ) { ftruncate( fileno( fh ), nSize ); } -void Bu::File::flush() +void Bu::File::chmod( mode_t t ) { - fflush( fh ); + fchmod( fileno( fh ), t ); } +#endif -void Bu::File::chmod( mode_t t ) +void Bu::File::flush() { - fchmod( fileno( fh ), t ); + fflush( fh ); } bool Bu::File::isOpen() diff --git a/src/file.h b/src/file.h index 1a4421b..0f638a7 100644 --- a/src/file.h +++ b/src/file.h @@ -47,6 +47,7 @@ namespace Bu *@param sFlags (const char *) Standard file flags 'rb'... etc.. *@returns (Bu::File) A file object representing your temp file. */ +#ifndef WIN32 inline static Bu::File tempFile( Bu::FString &sName, const char *sFlags ) { int afh_d = mkstemp( sName.getStr() ); @@ -66,6 +67,7 @@ namespace Bu *@param t (mode_t) The new file access permissions. */ void chmod( mode_t t ); +#endif private: FILE *fh; diff --git a/src/tests/fstring.cpp b/src/tests/fstring.cpp index d600be6..48dfc5f 100644 --- a/src/tests/fstring.cpp +++ b/src/tests/fstring.cpp @@ -3,12 +3,22 @@ #include #include +#ifndef WIN32 inline double getTime() { struct timeval tv; gettimeofday( &tv, NULL ); return ((double)tv.tv_sec) + ((double)tv.tv_usec/1000000.0); } +#else +#include "windows.h" +#include "winbase.h" +inline double getTime() +{ + uint32_t t = (uint32_t) GetTickCount(); + return (double) t / 1000.0; +} +#endif Bu::FString genThing() { -- cgit v1.2.3 From aa82dc64b397b6ca0d336d91638d4f4b849e3667 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Tue, 26 Jun 2007 05:10:58 +0000 Subject: Fixed a minor bug in FString, and added the Logger and a test...it's cool, and a decent replacement for multilog now that we use runit. --- src/fstring.h | 1 + src/logger.cpp | 123 +++++++++++++++++++++++++++++++++++++++++++++++++++ src/logger.h | 112 ++++++++++++++++++++++++++++++++++++++++++++++ src/tests/logger.cpp | 28 ++++++++++++ 4 files changed, 264 insertions(+) create mode 100644 src/logger.cpp create mode 100644 src/logger.h create mode 100644 src/tests/logger.cpp (limited to 'src/tests') diff --git a/src/fstring.h b/src/fstring.h index 9d88bd4..fe34804 100644 --- a/src/fstring.h +++ b/src/fstring.h @@ -128,6 +128,7 @@ namespace Bu */ void append( const chr *pData ) { + if( !pData ) return; long nLen; for( nLen = 0; pData[nLen] != (chr)0; nLen++ ); if( nLen == 0 ) diff --git a/src/logger.cpp b/src/logger.cpp new file mode 100644 index 0000000..848dfb1 --- /dev/null +++ b/src/logger.cpp @@ -0,0 +1,123 @@ +#include "bu/logger.h" +#include +#include +#include + +Bu::Logger::Logger() +{ +} + +Bu::Logger::~Logger() +{ +} + +void Bu::Logger::log( int nLevel, const char *sFile, const char *sFunction, int nLine, const char *sFormat, ...) +{ + if( (nLevel&nLevelMask) == 0 ) + return; + + va_list ap; + va_start( ap, sFormat ); + char *text; + vasprintf( &text, sFormat, ap ); + va_end(ap); + + time_t t = time(NULL); + + char *line = NULL; + struct tm *pTime; + pTime = localtime( &t ); + asprintf( + &line, + sLogFormat.getStr(), + pTime->tm_year+1900, + pTime->tm_mon+1, + pTime->tm_mday, + pTime->tm_hour, + pTime->tm_min, + pTime->tm_sec, + nLevel, + sFile, + nLine, + text, + sFunction + ); + write( fileno(stdout), line, strlen(line) ); + free( text ); + free( line ); +} + +void Bu::Logger::setFormat( const Bu::FString &str ) +{ + sLogFormat = ""; + + static char fmts[][4]={ + {'y', 'd', '0', '1'}, + {'m', 'd', '0', '2'}, + {'d', 'd', '0', '3'}, + {'h', 'd', '0', '4'}, + {'M', 'd', '0', '5'}, + {'s', 'd', '0', '6'}, + {'L', 'd', '0', '7'}, + {'f', 's', '0', '8'}, + {'l', 'd', '0', '9'}, + {'t', 's', '1', '0'}, + {'F', 's', '1', '1'}, + {'\0', '\0', '\0', '\0'}, + }; + + for( const char *s = str.getStr(); *s; s++ ) + { + if( *s == '%' ) + { + sLogFormat += '%'; + s++; + for( int l = 0;; l++ ) + { + if( fmts[l][0] == '\0' ) + { + sLogFormat += *s; + break; + } + else if( *s == fmts[l][0] ) + { + sLogFormat += fmts[l][2]; + sLogFormat += fmts[l][3]; + sLogFormat += '$'; + sLogFormat += fmts[l][1]; + break; + } + } + } + else + { + sLogFormat += *s; + } + } + sLogFormat += '\n'; + + write( fileno(stdout), sLogFormat.getStr(), sLogFormat.getSize() ); +} + +void Bu::Logger::setMask( int n ) +{ + nLevelMask = n; +} + +void Bu::Logger::setLevel( int n ) +{ + int j; + for( j = 31; j > 0; j-- ) + { + if( (n&(1<= 0; j-- ) + { + n |= (1< + { + friend class Bu::Singleton; + private: + Logger(); + virtual ~Logger(); + + public: + void log( int nLevel, const char *sFile, const char *sFunction, int nLine, const char *sFormat, ...); + + void setFormat( const Bu::FString &str ); + void setMask( int n ); + void setLevel( int n ); + + private: + Bu::FString sLogFormat; + int nLevelMask; + }; +} + +/** + * Use Bu::Logger to log a message at the given level and with the given message + * using printf style formatting, and include extra data such as the current + * file, line number, and function. + */ +#define lineLog( nLevel, sFrmt, ...) \ + Bu::Logger::getInstance().log( nLevel, __FILE__, __PRETTY_FUNCTION__, __LINE__, sFrmt, ##__VA_ARGS__ ) + +/** + * Set the Bu::Logger logging mask directly. See Bu::Logger::setMask for + * details. + */ +#define setLogMask( nLevel ) \ + Bu::Logger::getInstance().setMask( nLevel ) + +/** + * Set the Bu::Logger format. See Bu::Logger::setFormat for details. + */ +#define setLogFormat( sFrmt ) \ + Bu::Logger::getInstance().setFormat( sFrmt ) + +/** + * Set the Bu::Logger logging mask simulating levels. See Bu::Logger::setLevel + * for details. + */ +#define setLogLevel( nLevel ) \ + Bu::Logger::getInstance().setLevel( nLevel ) + +#endif diff --git a/src/tests/logger.cpp b/src/tests/logger.cpp new file mode 100644 index 0000000..a271443 --- /dev/null +++ b/src/tests/logger.cpp @@ -0,0 +1,28 @@ +#include "bu/logger.h" +#include +#include + +class Thing +{ + public: + Thing() + { + lineLog( 2, "Want a thing?"); + } + + void go( int i ) + { + lineLog( 1, "GO!!!!"); + } +}; + +int main() +{ + setLogLevel( 4 ); + setLogFormat("%L: %y-%m-%d %h:%M:%s %f:%l:%F: %t"); + lineLog( 5, "Hey, error: %s", strerror( errno ) ); + + Thing gh; + gh.go( 6); +} + -- cgit v1.2.3 From c86c0cf088492e02431dffb1f860ff2f6faa492d Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Wed, 27 Jun 2007 18:11:13 +0000 Subject: The taf system is new and improved. The writer works, we added C++ style comment blocks, and it retains the order of all nodes. --- src/tafnode.cpp | 138 ++++++++++++++++++++++++++++++++++++++++++------------ src/tafnode.h | 68 +++++++++++++++++++++++---- src/tafreader.cpp | 44 +++++++++++------ src/tafreader.h | 9 ++-- src/tafwriter.cpp | 42 ++++++++++++++++- src/tafwriter.h | 4 +- src/tests/taf.cpp | 13 +++-- src/unit/taf.cpp | 2 +- test.taf | 31 +++--------- 9 files changed, 260 insertions(+), 91 deletions(-) (limited to 'src/tests') diff --git a/src/tafnode.cpp b/src/tafnode.cpp index b9a4a24..b7cf211 100644 --- a/src/tafnode.cpp +++ b/src/tafnode.cpp @@ -1,72 +1,148 @@ #include "tafnode.h" -Bu::TafNode::TafNode() +Bu::TafNode::TafNode( NodeType eType ) : + eType( eType ) { } Bu::TafNode::~TafNode() +{ +} + +const Bu::TafNode::NodeType Bu::TafNode::getType() const +{ + return eType; +} + +/* +const Bu::TafNode::PropList &Bu::TafNode::getProperties( const Bu::FString &sName ) const +{ + return hProp.get( sName ); +} + +const Bu::TafNode::NodeList &Bu::TafNode::getChildren( const Bu::FString &sName ) const +{ + return hChildren.get( sName ); +} + +const Bu::FString &Bu::TafNode::getProperty( const Bu::FString &sName ) const +{ + return getProperties( sName ).first(); +} + +const Bu::TafNode *Bu::TafNode::getChild( const Bu::FString &sName ) const +{ + return getChildren( sName ).first(); +} +*/ + +Bu::TafGroup::TafGroup( const Bu::FString &sName ) : + TafNode( typeGroup ), + sName( sName ) +{ +} + +Bu::TafGroup::~TafGroup() { //printf("Entering Bu::TafNode::~TafNode() \"%s\"\n", sName.getStr() ); - for( NodeHash::iterator i = hChildren.begin(); i != hChildren.end(); i++ ) + for( NodeList::iterator i = lChildren.begin(); i != lChildren.end(); i++ ) { - NodeList &l = i.getValue(); - for( NodeList::iterator k = l.begin(); k != l.end(); k++ ) - { - //printf("deleting: [%08X] %s\n", *k, "" );//(*k)->getName().getStr() ); - delete (*k); - } + delete (*i); } } -void Bu::TafNode::setProperty( Bu::FString sName, Bu::FString sValue ) +const Bu::FString &Bu::TafGroup::getName() const { - if( !hProp.has( sName ) ) + return sName; +} + +void Bu::TafGroup::addChild( Bu::TafNode *pNode ) +{ + switch( pNode->getType() ) { - hProp.insert( sName, PropList() ); + case typeGroup: + { + TafGroup *pGroup = (TafGroup *)pNode; + if( !hChildren.has( pGroup->getName() ) ) + hChildren.insert( pGroup->getName(), GroupList() ); + hChildren.get( pGroup->getName() ).append( pGroup ); + } + break; + + case typeProperty: + { + TafProperty *pProperty = (TafProperty *)pNode; + if( !hProp.has( pProperty->getName() ) ) + hProp.insert( pProperty->getName(), PropList() ); + hProp.get( pProperty->getName() ).append( pProperty->getValue() ); + } + break; + + case typeComment: + break; } - hProp.get( sName ).append( sValue ); + lChildren.append( pNode ); } -void Bu::TafNode::addChild( TafNode *pNode ) +const Bu::TafGroup::GroupList &Bu::TafGroup::getChildren( const Bu::FString &sName ) const { - if( !hChildren.has( pNode->getName() ) ) - { - hChildren.insert( pNode->getName(), NodeList() ); - } + return hChildren.get( sName ); +} - //printf("Appending \"%s\"\n", pNode->getName().getStr() ); - hChildren.get( pNode->getName() ).append( pNode ); - //printf("[%08X]\n", hChildren.get( pNode->getName() ).last() ); +const Bu::TafGroup::NodeList &Bu::TafGroup::getChildren() const +{ + return lChildren; } -const Bu::TafNode::PropList &Bu::TafNode::getProperties( const Bu::FString &sName ) const +const Bu::TafGroup *Bu::TafGroup::getChild( const Bu::FString &sName ) const { - return hProp.get( sName ); + return hChildren.get( sName ).first(); } -const Bu::TafNode::NodeList &Bu::TafNode::getChildren( const Bu::FString &sName ) const +const Bu::TafGroup::PropList &Bu::TafGroup::getProperties( const Bu::FString &sName ) const { - return hChildren.get( sName ); + return hProp.get( sName ); } -const Bu::FString &Bu::TafNode::getProperty( const Bu::FString &sName ) const +const Bu::FString &Bu::TafGroup::getProperty( const Bu::FString &sName ) const { - return getProperties( sName ).first(); + return hProp.get( sName ).first(); } -const Bu::TafNode *Bu::TafNode::getChild( const Bu::FString &sName ) const +Bu::TafProperty::TafProperty( const Bu::FString &sName, const Bu::FString &sValue ) : + TafNode( typeProperty ), + sName( sName ), + sValue( sValue ) { - return getChildren( sName ).first(); } -void Bu::TafNode::setName( const Bu::FString &sName ) +Bu::TafProperty::~TafProperty() { - this->sName = sName; } -const Bu::FString &Bu::TafNode::getName() const +const Bu::FString &Bu::TafProperty::getName() const { return sName; } +const Bu::FString &Bu::TafProperty::getValue() const +{ + return sValue; +} + +Bu::TafComment::TafComment( const Bu::FString &sText ) : + TafNode( typeComment ), + sText( sText ) +{ +} + +Bu::TafComment::~TafComment() +{ +} + +const Bu::FString &Bu::TafComment::getText() const +{ + return sText; +} + diff --git a/src/tafnode.h b/src/tafnode.h index 08f78e8..55a5123 100644 --- a/src/tafnode.h +++ b/src/tafnode.h @@ -14,29 +14,77 @@ namespace Bu class TafNode { public: - typedef Bu::List PropList; - typedef Bu::Hash PropHash; - typedef Bu::List NodeList; - typedef Bu::Hash NodeHash; + enum NodeType + { + typeGroup, + typeProperty, + typeComment + }; public: - TafNode(); + TafNode( NodeType eType ); virtual ~TafNode(); - void setName( const Bu::FString &sName ); + const NodeType getType() const; + + private: + NodeType eType; + }; + + class TafProperty; + class TafComment; + class TafGroup : public TafNode + { + public: + typedef Bu::List PropList; + typedef Bu::Hash PropHash; + typedef Bu::List GroupList; + typedef Bu::Hash GroupHash; + typedef Bu::List NodeList; + + TafGroup( const Bu::FString &sName ); + virtual ~TafGroup(); + const Bu::FString &getName() const; - void setProperty( Bu::FString sName, Bu::FString sValue ); const Bu::FString &getProperty( const Bu::FString &sName ) const; const PropList &getProperties( const Bu::FString &sName ) const; - const TafNode *getChild( const Bu::FString &sName ) const; - const NodeList &getChildren( const Bu::FString &sName ) const; + const TafGroup *getChild( const Bu::FString &sName ) const; + const GroupList &getChildren( const Bu::FString &sName ) const; void addChild( TafNode *pNode ); + const NodeList &getChildren() const; private: Bu::FString sName; PropHash hProp; - NodeHash hChildren; + GroupHash hChildren; + NodeList lChildren; + }; + + class TafProperty : public TafNode + { + public: + TafProperty( const Bu::FString &sName, const Bu::FString &sValue ); + virtual ~TafProperty(); + + const Bu::FString &getName() const; + const Bu::FString &getValue() const; + + private: + Bu::FString sName; + Bu::FString sValue; + }; + + class TafComment : public TafNode + { + public: + TafComment( const Bu::FString &sText ); + virtual ~TafComment(); + + const Bu::FString &getText() const; + + private: + Bu::FString sText; }; } diff --git a/src/tafreader.cpp b/src/tafreader.cpp index 1187176..db465e9 100644 --- a/src/tafreader.cpp +++ b/src/tafreader.cpp @@ -8,6 +8,7 @@ Bu::TafReader::TafReader( Bu::Stream &sIn ) : c( 0 ), sIn( sIn ) { + next(); next(); } Bu::TafReader::~TafReader() @@ -15,60 +16,74 @@ Bu::TafReader::~TafReader() } -Bu::TafNode *Bu::TafReader::getNode() +Bu::TafGroup *Bu::TafReader::readGroup() { - if( c == 0 ) next(); - TafNode *pNode = new TafNode(); ws(); if( c != '{' ) throw TafException("Expected '{'"); next(); ws(); FString sName = readStr(); - pNode->setName( sName ); + TafGroup *pGroup = new TafGroup( sName ); next(); //printf("Node[%s]:\n", sName.getStr() ); - nodeContent( pNode ); + groupContent( pGroup ); if( c != '}' ) throw TafException("Expected '}'"); next(); - return pNode; + return pGroup; } -void Bu::TafReader::nodeContent( Bu::TafNode *pNode ) +void Bu::TafReader::groupContent( Bu::TafGroup *pGroup ) { for(;;) { ws(); if( c == '{' ) - pNode->addChild( getNode() ); + pGroup->addChild( readGroup() ); else if( c == '}' ) return; + else if( c == '/' && la == '*' ) + pGroup->addChild( readComment() ); else - nodeProperty( pNode ); + pGroup->addChild( readProperty() ); } } -void Bu::TafReader::nodeProperty( Bu::TafNode *pNode ) +Bu::TafProperty *Bu::TafReader::readProperty() { FString sName = readStr(); ws(); if( c != '=' ) { //printf(" %s (true)\n", sName.getStr() ); - pNode->setProperty( sName, "" ); - return; + return new Bu::TafProperty( sName, "" ); } next(); FString sValue = readStr(); - pNode->setProperty( sName, sValue ); + return new Bu::TafProperty( sName, sValue ); //printf(" %s = %s\n", sName.getStr(), sValue.getStr() ); } +Bu::TafComment *Bu::TafReader::readComment() +{ + next(); + FString sCmnt; + for(;;) + { + next(); + if( c == '*' && la == '/' ) + break; + sCmnt += c; + } + + return new TafComment( sCmnt ); +} + Bu::FString Bu::TafReader::readStr() { ws(); @@ -134,6 +149,7 @@ bool Bu::TafReader::isws() void Bu::TafReader::next() { - sIn.read( &c, 1 ); + c = la; + sIn.read( &la, 1 ); } diff --git a/src/tafreader.h b/src/tafreader.h index 47ae187..eeaafb3 100644 --- a/src/tafreader.h +++ b/src/tafreader.h @@ -17,16 +17,17 @@ namespace Bu TafReader( Bu::Stream &sIn ); virtual ~TafReader(); - Bu::TafNode *getNode(); + Bu::TafGroup *readGroup(); private: - void nodeContent( Bu::TafNode *pNode ); - void nodeProperty( Bu::TafNode *pNode ); + void groupContent( Bu::TafGroup *pNode ); + Bu::TafProperty *readProperty(); + Bu::TafComment *readComment(); void ws(); bool isws(); void next(); Bu::FString readStr(); - char c; + char c, la; Bu::Stream &sIn; }; } diff --git a/src/tafwriter.cpp b/src/tafwriter.cpp index ac42d3d..6b505ef 100644 --- a/src/tafwriter.cpp +++ b/src/tafwriter.cpp @@ -9,16 +9,54 @@ Bu::TafWriter::~TafWriter() { } -void Bu::TafWriter::writeNode( Bu::TafNode *pRoot ) +void Bu::TafWriter::writeGroup( const Bu::TafGroup *pRoot ) { sOut.write("{", 1 ); - writeString( pRoot->getName().getStr() ); + writeString( pRoot->getName() ); sOut.write(": ", 2 ); + const Bu::TafGroup::NodeList &nl = pRoot->getChildren(); + for( Bu::TafGroup::NodeList::const_iterator i = nl.begin(); i != nl.end(); i++ ) + { + switch( (*i)->getType() ) + { + case Bu::TafNode::typeGroup: + writeGroup( (Bu::TafGroup *)(*i) ); + break; + + case Bu::TafNode::typeProperty: + writeProperty( (Bu::TafProperty *)(*i) ); + break; + + case Bu::TafNode::typeComment: + writeComment( (Bu::TafComment *)(*i) ); + break; + } + } sOut.write("}", 1 ); } +void Bu::TafWriter::writeProperty( const Bu::TafProperty *pProp ) +{ + writeString( pProp->getName() ); + if( pProp->getValue().getStr() != NULL ) + { + sOut.write("=", 1 ); + writeString( pProp->getValue() ); + } + sOut.write(" ", 1 ); +} + +void Bu::TafWriter::writeComment( const Bu::TafComment *pComment ) +{ + sOut.write("/*", 2 ); + sOut.write( pComment->getText().getStr(), pComment->getText().getSize() ); + sOut.write("*/ ", 3 ); +} + void Bu::TafWriter::writeString( const Bu::FString &str ) { + if( str.getStr() == NULL ) + return; sOut.write("\"", 1 ); for( const char *s = str.getStr(); *s; s++ ) { diff --git a/src/tafwriter.h b/src/tafwriter.h index 4310e62..5f80504 100644 --- a/src/tafwriter.h +++ b/src/tafwriter.h @@ -17,9 +17,11 @@ namespace Bu TafWriter( Bu::Stream &sOut ); virtual ~TafWriter(); - void writeNode( Bu::TafNode *pRoot ); + void writeGroup( const Bu::TafGroup *pRoot ); private: + void writeProperty( const Bu::TafProperty *pProp ); + void writeComment( const Bu::TafComment *pComment ); void writeString( const Bu::FString &str ); Bu::Stream &sOut; }; diff --git a/src/tests/taf.cpp b/src/tests/taf.cpp index d135e78..e3da120 100644 --- a/src/tests/taf.cpp +++ b/src/tests/taf.cpp @@ -1,4 +1,5 @@ #include "bu/tafreader.h" +#include "bu/tafwriter.h" #include "bu/file.h" int main() @@ -6,12 +7,18 @@ int main() Bu::File f("test.taf", "rb"); Bu::TafReader tr( f ); - Bu::TafNode *pNode = tr.getNode(); + Bu::TafGroup *pGroup = tr.readGroup(); - const Bu::TafNode *pStats = pNode->getChild("stats"); + const Bu::TafGroup *pStats = pGroup->getChild("stats"); printf("%s\n", pStats->getName().getStr() ); printf(" str = %s\n", pStats->getProperty("str").getStr() ); - delete pNode; + { + Bu::File fo("out.taf", "wb"); + Bu::TafWriter tw( fo ); + tw.writeGroup( pGroup ); + } + + delete pGroup; } diff --git a/src/unit/taf.cpp b/src/unit/taf.cpp index ab485d0..5e0e914 100644 --- a/src/unit/taf.cpp +++ b/src/unit/taf.cpp @@ -32,7 +32,7 @@ public: Bu::File fIn(sFnTmp.c_str(), "rb"); Bu::TafReader tr(fIn); - Bu::TafNode *tn = tr.getNode(); + Bu::TafGroup *tn = tr.readGroup(); unitTest( !strcmp("Bob", tn->getProperty("name").c_str()) ); delete tn; diff --git a/test.taf b/test.taf index 045b042..1d4e7d1 100644 --- a/test.taf +++ b/test.taf @@ -1,26 +1,7 @@ -{player: - password = "aoeuaoeuao" - userclass = "implementor" - species = "human" - sex = "male" - active - startroom = "Salourn::Xagafinelle's Room" - {stats: str=14 dex=12 spd=12 enr=7 rea=12 wil=10 int=13 cha=14} - {hp: cur = 100 max = 100} - {en: cur = 100 max = 100} - attackrate = 30 - gold = 0 - {inventory: - {: count=1 id="Salourn::Dark Blade"} - {: count=1 id="Salourn::Dark Suit"} - {: count=3 id="Salourn::Small Fig"} - } - {aliases: - {: key="." value="say"} - {: key="," value="yell"} - {: key="li" value="lightning"} - } - description = "They appear to be rather average looking, not particularly +{"player": "password"="aoeuaoeuao" "userclass"="implementor" "species"="human" "sex"="male" "active" "startroom"="Salourn::Xagafinelle's Room" {"stats": "str"="14" "dex"="12" "spd"="12" "enr"="7" "rea"="12" "wil"="10" "int"="13" "cha"="14" }{"hp": "cur"="100" "max"="100" }{"en": "cur"="100" "max"="100" }"attackrate"="30" "gold"="0" + + /* Hey, the inventory is next...isn't that cool? Oooooh yeah! */ + +{"inventory": {: "count"="1" "id"="Salourn::Dark Blade" }{: "count"="1" "id"="Salourn::Dark Suit" }{: "count"="3" "id"="Salourn::Small Fig" }}{"aliases": {: "key"="." "value"="say" }{: "key"="," "value"="yell" }{: "key"="li" "value"="lightning" }}"description"="They appear to be rather average looking, not particularly tall or short, with facial features that are difficult to remember even - seconds after witnessing them." -} + seconds after witnessing them." } -- cgit v1.2.3 From 60bac0c9f558ab34c70f099db923204a84d51ffc Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Fri, 29 Jun 2007 01:59:26 +0000 Subject: The plugger was dying on a HashException it should have caught, and the Logger now allows you to include extra printf formatting in your fields just like the docs say you can. --- src/logger.cpp | 32 ++++++++++++++++++++------------ src/plugger.h | 8 +++++--- src/tests/logger.cpp | 2 +- 3 files changed, 26 insertions(+), 16 deletions(-) (limited to 'src/tests') diff --git a/src/logger.cpp b/src/logger.cpp index 848dfb1..1fc2262 100644 --- a/src/logger.cpp +++ b/src/logger.cpp @@ -71,22 +71,30 @@ void Bu::Logger::setFormat( const Bu::FString &str ) if( *s == '%' ) { sLogFormat += '%'; - s++; - for( int l = 0;; l++ ) + Bu::FString sBuf; + for(;;) { - if( fmts[l][0] == '\0' ) + s++; + int l; + for( l = 0;; l++ ) { - sLogFormat += *s; - break; + if( fmts[l][0] == '\0' ) + { + sBuf += *s; + break; + } + else if( *s == fmts[l][0] ) + { + sLogFormat += fmts[l][2]; + sLogFormat += fmts[l][3]; + sLogFormat += '$'; + sLogFormat += sBuf; + sLogFormat += fmts[l][1]; + break; + } } - else if( *s == fmts[l][0] ) - { - sLogFormat += fmts[l][2]; - sLogFormat += fmts[l][3]; - sLogFormat += '$'; - sLogFormat += fmts[l][1]; + if( fmts[l][0] != '\0' ) break; - } } } else diff --git a/src/plugger.h b/src/plugger.h index 615a662..2124b7a 100644 --- a/src/plugger.h +++ b/src/plugger.h @@ -116,13 +116,15 @@ namespace Bu void registerExternalPlugin( const char *sFName, const char *sPluginName ) { - PluginReg *pReg = (PluginReg *)hPlugin[sPluginName]; - if( pReg != NULL ) - { + PluginReg *pReg; + try { + pReg = (PluginReg *)hPlugin[sPluginName]; hPlugin.erase( sPluginName ); dlclose( pReg->dlHandle ); delete pReg; pReg = NULL; + } catch( Bu::HashException &e ) + { } pReg = new PluginReg; diff --git a/src/tests/logger.cpp b/src/tests/logger.cpp index a271443..290f479 100644 --- a/src/tests/logger.cpp +++ b/src/tests/logger.cpp @@ -19,7 +19,7 @@ class Thing int main() { setLogLevel( 4 ); - setLogFormat("%L: %y-%m-%d %h:%M:%s %f:%l:%F: %t"); + setLogFormat("%L: %y-%02m-%02d %h:%02M:%02s %f:%l:%F: %t"); lineLog( 5, "Hey, error: %s", strerror( errno ) ); Thing gh; -- cgit v1.2.3