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/xmlwriter.cpp | 173 ------------------------------------------------------ 1 file changed, 173 deletions(-) delete mode 100644 src/xmlwriter.cpp (limited to 'src/xmlwriter.cpp') diff --git a/src/xmlwriter.cpp b/src/xmlwriter.cpp deleted file mode 100644 index 56880b6..0000000 --- a/src/xmlwriter.cpp +++ /dev/null @@ -1,173 +0,0 @@ -#include -#include -#include "xmlwriter.h" - -XmlWriter::XmlWriter( const char *sIndent, XmlNode *pRoot ) : - XmlDocument( pRoot ) -{ - if( sIndent == NULL ) - { - this->sIndent = ""; - } - else - { - this->sIndent = sIndent; - } -} - -XmlWriter::~XmlWriter() -{ -} - -void XmlWriter::write() -{ - write( getRoot(), sIndent.c_str() ); -} - -void XmlWriter::write( XmlNode *pRoot, const char *sIndent ) -{ - writeNode( pRoot, 0, sIndent ); -} - -void XmlWriter::closeNode() -{ - XmlDocument::closeNode(); - - if( isCompleted() ) - { - write( getRoot(), sIndent.c_str() ); - } -} - -void XmlWriter::writeIndent( int nIndent, const char *sIndent ) -{ - if( sIndent == NULL ) return; - for( int j = 0; j < nIndent; j++ ) - { - writeString( sIndent ); - } -} - -std::string XmlWriter::escape( std::string sIn ) -{ - std::string sOut; - - std::string::const_iterator i; - for( i = sIn.begin(); i != sIn.end(); i++ ) - { - if( ((*i >= ' ' && *i <= '9') || - (*i >= 'a' && *i <= 'z') || - (*i >= 'A' && *i <= 'Z') ) && - (*i != '\"' && *i != '\'' && *i != '&') - ) - { - sOut += *i; - } - else - { - sOut += "&#"; - char buf[4]; - sprintf( buf, "%u", (unsigned char)*i ); - sOut += buf; - sOut += ';'; - } - } - - return sOut; -} - -void XmlWriter::writeNodeProps( XmlNode *pNode, int nIndent, const char *sIndent ) -{ - for( int j = 0; j < pNode->getNumProperties(); j++ ) - { - writeString(" "); - writeString( pNode->getPropertyName( j ) ); - writeString("=\""); - writeString( escape( pNode->getProperty( j ) ).c_str() ); - writeString("\""); - } -} - -void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) -{ - if( pNode->hasChildren() ) - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent ) - writeString(">\n"); - else - writeString(">"); - - if( pNode->getContent( 0 ) ) - { - writeIndent( nIndent+1, sIndent ); - if( sIndent ) - { - writeString( pNode->getContent( 0 ) ); - writeString("\n"); - } - else - writeString( pNode->getContent( 0 ) ); - } - - int nNumChildren = pNode->getNumChildren(); - for( int j = 0; j < nNumChildren; j++ ) - { - writeNode( pNode->getChild( j ), nIndent+1, sIndent ); - if( pNode->getContent( j+1 ) ) - { - writeIndent( nIndent+1, sIndent ); - if( sIndent ) - { - writeString( pNode->getContent( j+1 ) ); - writeString("\n"); - } - else - writeString( pNode->getContent( j+1 ) ); - } - } - - writeIndent( nIndent, sIndent ); - if( sIndent ) - { - writeString("getName() ); - writeString(">\n"); - } - else - { - writeString("getName() ); - writeString(">"); - } - } - else if( pNode->getContent() ) - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - writeString(">"); - writeString( pNode->getContent() ); - writeString("getName() ); - writeString(">"); - if( sIndent ) - writeString("\n"); - } - else - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent ) - writeString("/>\n"); - else - writeString("/>"); - } -} - -- cgit v1.2.3 From c17c4ebbab022de80a9f893115f2fd41e6a07c44 Mon Sep 17 00:00:00 2001 From: Mike Buland 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/xmlwriter.cpp') 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 @@ +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.

Abstract

The Extensible Markup Language (XML) is a subset of SGML that is completely +described in this document. Its goal is to enable generic SGML to be served, +received, and processed on the Web in the way that is now possible with HTML. +XML has been designed for ease of implementation and for interoperability +with both SGML and HTML.

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 ad92dc50b7cdf7cfe086f21d19442d03a90fd05d Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Wed, 9 May 2007 15:04:31 +0000 Subject: Just a few things re-arranged, moved the new taf/xml systems to the inprogress directory, and moved the old xml system in, so it will require heavy changes. --- src/inprogress/tafdocument.cpp | 9 + src/inprogress/tafdocument.h | 22 ++ src/inprogress/tafnode.cpp | 9 + src/inprogress/tafnode.h | 21 ++ src/inprogress/tafreader.cpp | 11 + src/inprogress/tafreader.h | 25 ++ src/inprogress/tafwriter.cpp | 9 + src/inprogress/tafwriter.h | 22 ++ src/inprogress/xmldocument.cpp | 9 + src/inprogress/xmldocument.h | 22 ++ src/inprogress/xmlnode.cpp | 9 + src/inprogress/xmlnode.h | 22 ++ src/inprogress/xmlreader.cpp | 267 +++++++++++++++++ src/inprogress/xmlreader.h | 121 ++++++++ src/inprogress/xmlwriter.cpp | 9 + src/inprogress/xmlwriter.h | 22 ++ src/old/xmldocument.cpp | 149 --------- src/old/xmldocument.h | 171 ----------- src/old/xmlnode.cpp | 445 --------------------------- src/old/xmlnode.h | 236 --------------- src/old/xmlreader.cpp | 602 ------------------------------------- src/old/xmlreader.h | 141 --------- src/old/xmlwriter.cpp | 173 ----------- src/old/xmlwriter.h | 96 ------ src/tafdocument.cpp | 9 - src/tafdocument.h | 22 -- src/tafnode.cpp | 9 - src/tafnode.h | 21 -- src/tafreader.cpp | 11 - src/tafreader.h | 25 -- src/tafwriter.cpp | 9 - src/tafwriter.h | 22 -- src/xmldocument.cpp | 146 ++++++++- src/xmldocument.h | 175 ++++++++++- src/xmlnode.cpp | 440 ++++++++++++++++++++++++++- src/xmlnode.h | 240 ++++++++++++++- src/xmlreader.cpp | 665 +++++++++++++++++++++++++++++++---------- src/xmlreader.h | 252 +++++++++------- src/xmlwriter.cpp | 168 ++++++++++- src/xmlwriter.h | 100 ++++++- 40 files changed, 2468 insertions(+), 2468 deletions(-) create mode 100644 src/inprogress/tafdocument.cpp create mode 100644 src/inprogress/tafdocument.h create mode 100644 src/inprogress/tafnode.cpp create mode 100644 src/inprogress/tafnode.h create mode 100644 src/inprogress/tafreader.cpp create mode 100644 src/inprogress/tafreader.h create mode 100644 src/inprogress/tafwriter.cpp create mode 100644 src/inprogress/tafwriter.h create mode 100644 src/inprogress/xmldocument.cpp create mode 100644 src/inprogress/xmldocument.h create mode 100644 src/inprogress/xmlnode.cpp create mode 100644 src/inprogress/xmlnode.h create mode 100644 src/inprogress/xmlreader.cpp create mode 100644 src/inprogress/xmlreader.h create mode 100644 src/inprogress/xmlwriter.cpp create mode 100644 src/inprogress/xmlwriter.h delete mode 100644 src/old/xmldocument.cpp delete mode 100644 src/old/xmldocument.h delete mode 100644 src/old/xmlnode.cpp delete mode 100644 src/old/xmlnode.h delete mode 100644 src/old/xmlreader.cpp delete mode 100644 src/old/xmlreader.h delete mode 100644 src/old/xmlwriter.cpp delete mode 100644 src/old/xmlwriter.h delete mode 100644 src/tafdocument.cpp delete mode 100644 src/tafdocument.h delete mode 100644 src/tafnode.cpp delete mode 100644 src/tafnode.h delete mode 100644 src/tafreader.cpp delete mode 100644 src/tafreader.h delete mode 100644 src/tafwriter.cpp delete mode 100644 src/tafwriter.h (limited to 'src/xmlwriter.cpp') diff --git a/src/inprogress/tafdocument.cpp b/src/inprogress/tafdocument.cpp new file mode 100644 index 0000000..bd44dd5 --- /dev/null +++ b/src/inprogress/tafdocument.cpp @@ -0,0 +1,9 @@ +#include "tafdocument.h" + +Bu::TafDocument::TafDocument() +{ +} + +Bu::TafDocument::~TafDocument() +{ +} diff --git a/src/inprogress/tafdocument.h b/src/inprogress/tafdocument.h new file mode 100644 index 0000000..171f829 --- /dev/null +++ b/src/inprogress/tafdocument.h @@ -0,0 +1,22 @@ +#ifndef BU_TAF_DOCUMENT_H +#define BU_TAF_DOCUMENT_H + +#include + +namespace Bu +{ + /** + * + */ + class TafDocument + { + public: + TafDocument(); + virtual ~TafDocument(); + + private: + + }; +} + +#endif diff --git a/src/inprogress/tafnode.cpp b/src/inprogress/tafnode.cpp new file mode 100644 index 0000000..c9756ec --- /dev/null +++ b/src/inprogress/tafnode.cpp @@ -0,0 +1,9 @@ +#include "tafnode.h" + +Bu::TafNode::TafNode() +{ +} + +Bu::TafNode::~TafNode() +{ +} diff --git a/src/inprogress/tafnode.h b/src/inprogress/tafnode.h new file mode 100644 index 0000000..34f5289 --- /dev/null +++ b/src/inprogress/tafnode.h @@ -0,0 +1,21 @@ +#ifndef BU_TAF_NODE_H +#define BU_TAF_NODE_H + +#include + +namespace Bu +{ + /** + * + */ + class TafNode + { + public: + TafNode(); + virtual ~TafNode(); + + private: + + }; +} +#endif diff --git a/src/inprogress/tafreader.cpp b/src/inprogress/tafreader.cpp new file mode 100644 index 0000000..f94fe44 --- /dev/null +++ b/src/inprogress/tafreader.cpp @@ -0,0 +1,11 @@ +#include "tafreader.h" + +Bu::TafReader::TafReader( Bu::Stream &sIn ) : + sIn( sIn ) +{ +} + +Bu::TafReader::~TafReader() +{ +} + diff --git a/src/inprogress/tafreader.h b/src/inprogress/tafreader.h new file mode 100644 index 0000000..2dbb9ea --- /dev/null +++ b/src/inprogress/tafreader.h @@ -0,0 +1,25 @@ +#ifndef BU_TAF_READER_H +#define BU_TAF_READER_H + +#include +#include "bu/tafdocument.h" +#include "bu/stream.h" + +namespace Bu +{ + /** + * + */ + class TafReader : public Bu::TafDocument + { + public: + TafReader( Bu::Stream &sIn ); + virtual ~TafReader(); + + private: + Stream &sIn; + + }; +} + +#endif diff --git a/src/inprogress/tafwriter.cpp b/src/inprogress/tafwriter.cpp new file mode 100644 index 0000000..3e6c025 --- /dev/null +++ b/src/inprogress/tafwriter.cpp @@ -0,0 +1,9 @@ +#include "tafwriter.h" + +Bu::TafWriter::TafWriter() +{ +} + +Bu::TafWriter::~TafWriter() +{ +} diff --git a/src/inprogress/tafwriter.h b/src/inprogress/tafwriter.h new file mode 100644 index 0000000..7057d62 --- /dev/null +++ b/src/inprogress/tafwriter.h @@ -0,0 +1,22 @@ +#ifndef BU_TAF_WRITER_H +#define BU_TAF_WRITER_H + +#include + +namespace Bu +{ + /** + * + */ + class TafWriter + { + public: + TafWriter(); + virtual ~TafWriter(); + + private: + + }; +} + +#endif diff --git a/src/inprogress/xmldocument.cpp b/src/inprogress/xmldocument.cpp new file mode 100644 index 0000000..cb21826 --- /dev/null +++ b/src/inprogress/xmldocument.cpp @@ -0,0 +1,9 @@ +#include "xmldocument.h" + +Bu::XmlDocument::XmlDocument() +{ +} + +Bu::XmlDocument::~XmlDocument() +{ +} diff --git a/src/inprogress/xmldocument.h b/src/inprogress/xmldocument.h new file mode 100644 index 0000000..e16e3ea --- /dev/null +++ b/src/inprogress/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/inprogress/xmlnode.cpp b/src/inprogress/xmlnode.cpp new file mode 100644 index 0000000..58ef5c5 --- /dev/null +++ b/src/inprogress/xmlnode.cpp @@ -0,0 +1,9 @@ +#include "xmlnode.h" + +Bu::XmlNode::XmlNode() +{ +} + +Bu::XmlNode::~XmlNode() +{ +} diff --git a/src/inprogress/xmlnode.h b/src/inprogress/xmlnode.h new file mode 100644 index 0000000..cd9961a --- /dev/null +++ b/src/inprogress/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/inprogress/xmlreader.cpp b/src/inprogress/xmlreader.cpp new file mode 100644 index 0000000..bd241cf --- /dev/null +++ b/src/inprogress/xmlreader.cpp @@ -0,0 +1,267 @@ +#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::XmlReader::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("", 2 ); +} + +void Bu::XmlReader::Misc() +{ + for(;;) + { + S(); + if( !strncmp("", 3 ); + return; + } + } + burn( 1 ); + } +} + +void Bu::XmlReader::PI() +{ + checkString("", lookahead(j+2)+j, 2 ) ) + { + burn( j+2 ); + return; + } + } +} + +void Bu::XmlReader::S() +{ + for( int j = 0;; j++ ) + { + char c = *lookahead( 1 ); + if( c == 0x20 || c == 0x9 || c == 0xD || c == 0xA ) + continue; + if( j == 0 ) + throw ExceptionBase("Expected whitespace."); + return; + } +} + +void Bu::XmlReader::Sq() +{ + for(;;) + { + char c = *lookahead( 1 ); + if( c == 0x20 || c == 0x9 || c == 0xD || c == 0xA ) + continue; + return; + } +} + +void Bu::XmlReader::VersionInfo() +{ + try + { + S(); + checkString("version", 7 ); + } + catch( ExceptionBase &e ) + { + return; + } + Eq(); + Bu::FString ver = AttValue(); + if( ver != "1.1" ) + throw ExceptionBase("Currently we only support xml version 1.1\n"); +} + +void Bu::XmlReader::Eq() +{ + Sq(); + checkString("=", 1 ); + Sq(); +} + +void Bu::XmlReader::EncodingDecl() +{ + S(); + try + { + checkString("encoding", 8 ); + } + catch( ExceptionBase &e ) + { + return; + } + + Eq(); + AttValue(); +} + +void Bu::XmlReader::SDDecl() +{ + S(); + try + { + checkString("standalone", 10 ); + } + catch( ExceptionBase &e ) + { + return; + } + + Eq(); + AttValue(); +} + +Bu::FString Bu::XmlReader::AttValue() +{ + char q = *lookahead(1); + if( q == '\"' ) + { + for( int j = 2;; j++ ) + { + if( lookahead(j)[j-1] == '\"' ) + { + Bu::FString ret( lookahead(j)+1, j-2 ); + burn( j ); + return ret; + } + } + } + else if( q == '\'' ) + { + for( int j = 2;; j++ ) + { + if( lookahead(j)[j-1] == '\'' ) + { + Bu::FString ret( lookahead(j)+1, j-2 ); + burn( j ); + return ret; + } + } + } + + throw ExceptionBase("Excpected either \' or \".\n"); +} + +Bu::FString Bu::XmlReader::Name() +{ + unsigned char c = *lookahead( 1 ); + if( c != ':' && c != '_' && + (c < 'A' || c > 'Z') && + (c < 'a' || c > 'z') && + (c < 0xC0 || c > 0xD6 ) && + (c < 0xD8 || c > 0xF6 ) && + (c < 0xF8)) + { + throw ExceptionBase("Invalid entity name starting character."); + } + + for( int j = 1;; j++ ) + { + unsigned char c = lookahead(j+1)[j]; + if( isS( c ) ) + { + FString ret( lookahead(j+1), j+1 ); + burn( j+1 ); + return ret; + } + if( c != ':' && c != '_' && c != '-' && c != '.' && c != 0xB7 && + (c < 'A' || c > 'Z') && + (c < 'a' || c > 'z') && + (c < '0' || c > '9') && + (c < 0xC0 || c > 0xD6 ) && + (c < 0xD8 || c > 0xF6 ) && + (c < 0xF8)) + { + throw ExceptionBase("Invalid character in name."); + } + } +} + diff --git a/src/inprogress/xmlreader.h b/src/inprogress/xmlreader.h new file mode 100644 index 0000000..708a386 --- /dev/null +++ b/src/inprogress/xmlreader.h @@ -0,0 +1,121 @@ +#ifndef XML_READER_H +#define XML_READER_H + +#include +#include "bu/stream.h" +#include "bu/fstring.h" +#include "bu/xmlnode.h" + +namespace Bu +{ + /** + * An Xml 1.1 reader. I've decided to write this, this time, based on the + * official W3C reccomendation, now included with the source code. I've + * named the productions in the parser states the same as in that document, + * which may make them easier to find, etc, although possibly slightly less + * optimized than writing my own reduced grammer. + * + * Below I will list differences between my parser and the official standard + * as I come up with them. + * - Encoding and Standalone headings are ignored for the moment. (4.3.3, + * 2.9) + * - The standalone heading attribute can have any standard whitespace + * before it (the specs say only spaces, no newlines). (2.9) + * - Since standalone is ignored, it is currently allowed to have any + * value (should be restricted to "yes" or "no"). (2.9) + * - Currently only UTF-8 / ascii are parsed. + * - [optional] The content of comments is thrown away. (2.5) + * - The content of processing instruction blocks is parsed properly, but + * thrown away. (2.6) + */ + 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, Includes Comments and PIData (Processing Instructions). + */ + void Misc(); + + /** + * Comments + */ + void Comment(); + + /** + * Processing Instructions + */ + void PI(); + + /** + * Whitespace eater. + */ + void S(); + + /** + * Optional whitespace eater. + */ + void Sq(); + + /** + * XML Version spec + */ + void VersionInfo(); + + /** + * Your basic equals sign with surrounding whitespace. + */ + void Eq(); + + /** + * Read in an attribute value. + */ + FString AttValue(); + + /** + * Read in the name of something. + */ + FString Name(); + + /** + * Encoding decleration in the header + */ + void EncodingDecl(); + + /** + * Standalone decleration in the header + */ + void SDDecl(); + + bool isS( unsigned char c ) + { + return ( c == 0x20 || c == 0x9 || c == 0xD || c == 0xA ); + } + }; +} + +#endif diff --git a/src/inprogress/xmlwriter.cpp b/src/inprogress/xmlwriter.cpp new file mode 100644 index 0000000..23a5175 --- /dev/null +++ b/src/inprogress/xmlwriter.cpp @@ -0,0 +1,9 @@ +#include "xmlwriter.h" + +Bu::XmlWriter::XmlWriter() +{ +} + +Bu::XmlWriter::~XmlWriter() +{ +} diff --git a/src/inprogress/xmlwriter.h b/src/inprogress/xmlwriter.h new file mode 100644 index 0000000..796d6fb --- /dev/null +++ b/src/inprogress/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 diff --git a/src/old/xmldocument.cpp b/src/old/xmldocument.cpp deleted file mode 100644 index d7867d5..0000000 --- a/src/old/xmldocument.cpp +++ /dev/null @@ -1,149 +0,0 @@ -#include -#include -#include "xmlwriter.h" - -XmlDocument::XmlDocument( XmlNode *pRoot ) -{ - this->pRoot = pRoot; - pCurrent = NULL; - bCompleted = (pRoot!=NULL); -} - -XmlDocument::~XmlDocument() -{ - if( pRoot ) - { - delete pRoot; - } -} - -void XmlDocument::addNode( const char *sName, const char *sContent, bool bClose ) -{ - if( pRoot == NULL ) - { - // This is the first node, so ignore position and just insert it. - pCurrent = pRoot = new XmlNode( sName, NULL, sContent ); - } - else - { - pCurrent = pCurrent->addChild( sName, sContent ); - } - - if( bClose ) - { - closeNode(); - } -} - -void XmlDocument::setName( const char *sName ) -{ - pCurrent->setName( sName ); -} - -bool XmlDocument::isCompleted() -{ - return bCompleted; -} - -XmlNode *XmlDocument::getRoot() -{ - return pRoot; -} - -XmlNode *XmlDocument::detatchRoot() -{ - XmlNode *pTemp = pRoot; - pRoot = NULL; - return pTemp; -} - -XmlNode *XmlDocument::getCurrent() -{ - return pCurrent; -} - -void XmlDocument::closeNode() -{ - if( pCurrent != NULL ) - { - pCurrent = pCurrent->getParent(); - - if( pCurrent == NULL ) - { - bCompleted = true; - } - } -} - -void XmlDocument::addProperty( const char *sName, const char *sValue ) -{ - if( pCurrent ) - { - pCurrent->addProperty( sName, sValue ); - } -} - -void XmlDocument::addProperty( const char *sName, const unsigned char nValue ) -{ - char buf[12]; - sprintf( buf, "%hhi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const char nValue ) -{ - char buf[12]; - sprintf( buf, "%hhi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const unsigned short nValue ) -{ - char buf[12]; - sprintf( buf, "%hi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const short nValue ) -{ - char buf[12]; - sprintf( buf, "%hi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const int nValue ) -{ - char buf[12]; - sprintf( buf, "%d", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const unsigned long nValue ) -{ - char buf[12]; - sprintf( buf, "%li", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const long nValue ) -{ - char buf[12]; - sprintf( buf, "%li", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const double dValue ) -{ - char buf[40]; - sprintf( buf, "%f", dValue ); - addProperty( sName, buf ); -} - -void XmlDocument::setContent( const char *sContent ) -{ - if( pCurrent ) - { - pCurrent->setContent( sContent ); - } -} - diff --git a/src/old/xmldocument.h b/src/old/xmldocument.h deleted file mode 100644 index 6671c41..0000000 --- a/src/old/xmldocument.h +++ /dev/null @@ -1,171 +0,0 @@ -#ifndef XMLDOCUMENT -#define XMLDOCUMENT - -#include "xmlnode.h" - -/** - * Keeps track of an easily managed set of XmlNode information. Allows simple - * operations for logical writing to and reading from XML structures. Using - * already formed structures is simply done through the XmlNode structures, - * and the getRoot function here. Creation is performed through a simple set - * of operations that creates the data in a stream type format. - *@author Mike Buland - */ -class XmlDocument -{ -public: - /** - * Construct either a blank XmlDocuemnt or construct a document around an - * existing XmlNode. Be careful, once an XmlNode is passed into a document - * the document takes over ownership and will delete it when the XmlDocument - * is deleted. - *@param pRoot The XmlNode to use as the root of this document, or NULL if - * you want to start a new document. - */ - XmlDocument( XmlNode *pRoot=NULL ); - - /** - * Destroy all contained nodes. - */ - virtual ~XmlDocument(); - - /** - * Add a new node to the document. The new node is appended to the end of - * the current context, i.e. XmlNode, and the new node, provided it isn't - * close as part of this operation, will become the current context. - *@param sName The name of the new node to add. - *@param sContent A content string to be placed inside of the new node. - *@param bClose Set this to true to close the node immediately after adding - * 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 ); - - /** - * Close the current node context. This will move the current context to - * the parent node of the former current node. If the current node was the - * root then the "completed" flag is set and no more operations are allowed. - */ - void closeNode(); - - /** - * Change the content of the current node at the current position between - * nodes. - *@param sContent The new content of the current node. - */ - void setContent( const char *sContent ); - - /** - * Add a named property to the current context node. - *@param sName The name of the property to add. - *@param sValue The string value of the property. - */ - void addProperty( const char *sName, const char *sValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const unsigned char nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const char nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const unsigned short nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const short nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const unsigned long nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const long nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const int nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param dValue The numerical value to add. - */ - void addProperty( const char *sName, const double dValue ); - - /** - * The XmlDocuemnt is considered completed if the root node has been closed. - * Once an XmlDocument has been completed, you can no longer perform - * operations on it. - *@return True if completed, false if still in progress. - */ - bool isCompleted(); - - /** - * Get a pointer to the root object of this XmlDocument. - *@returns A pointer to an internally owned XmlNode. Do not delete this - * XmlNode. - */ - XmlNode *getRoot(); - - /** - * Get a pointer to the root object of this XmlDocument, and remove the - * ownership from this object. - *@returns A pointer to an internally owned XmlNode. Do not delete this - * XmlNode. - */ - XmlNode *detatchRoot(); - - /** - * Get the current context node, which could be the same as the root node. - *@returns A pointer to an internally owned XmlNode. Do not delete this - * XmlNode. - */ - XmlNode *getCurrent(); - -private: - XmlNode *pRoot; /**< The root node. */ - XmlNode *pCurrent; /**< The current node. */ - bool bCompleted; /**< Is it completed? */ -}; - -#endif diff --git a/src/old/xmlnode.cpp b/src/old/xmlnode.cpp deleted file mode 100644 index b1ed9a9..0000000 --- a/src/old/xmlnode.cpp +++ /dev/null @@ -1,445 +0,0 @@ -#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 ) -{ - 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 ) - { - if( this->sName.size() == 0 ) - { - // We're not in the hash yet, so add us - this->sName = sName; - pParent->hChildren.insert( this->sName.c_str(), this ); - } - else - { - // Slightly more tricky, delete us, then add us... - pParent->hChildren.del( this->sName.c_str() ); - this->sName = sName; - pParent->hChildren.insert( this->sName.c_str(), this ); - } - } - else - { - // If we have no parent, then just set the name string, we don't need - // to worry about hashing. - this->sName = sName; - } -} - -void XmlNode::setContent( const char *sContent, int nIndex ) -{ - if( nIndex == -1 ) - { - nIndex = nCurContent; - } - if( nIndex == 0 ) - { - if( this->sPreContent ) - { - delete this->sPreContent; - } - - this->sPreContent = new std::string( sContent ); - } - else - { - nIndex--; - if( lPostContent[nIndex] ) - { - delete (std::string *)lPostContent[nIndex]; - } - - lPostContent.setAt( nIndex, new std::string( sContent ) ); - } -} - -const char *XmlNode::getContent( int nIndex ) -{ - if( nIndex == 0 ) - { - if( sPreContent ) - { - return sPreContent->c_str(); - } - } - else - { - nIndex--; - if( lPostContent[nIndex] ) - { - return ((std::string *)lPostContent[nIndex])->c_str(); - } - } - - return NULL; -} - -XmlNode *XmlNode::addChild( const char *sName, const char *sContent ) -{ - return addChild( new XmlNode( sName, this, sContent ) ); -} - -XmlNode *XmlNode::addChild( XmlNode *pNode ) -{ - lChildren.append( pNode ); - lPostContent.append( NULL ); - nCurContent++; - pNode->pParent = this; - - return pNode; -} - -XmlNode *XmlNode::getParent() -{ - return pParent; -} - -void XmlNode::addProperty( const char *sName, const char *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 ); -} - -int XmlNode::getNumProperties() -{ - return lPropNames.getSize(); -} - -const char *XmlNode::getPropertyName( int nIndex ) -{ - std::string *tmp = ((std::string *)lPropNames[nIndex]); - if( tmp == NULL ) - return NULL; - return tmp->c_str(); -} - -const char *XmlNode::getProperty( int nIndex ) -{ - std::string *tmp = ((std::string *)lPropValues[nIndex]); - if( tmp == NULL ) - return NULL; - return tmp->c_str(); -} - -const char *XmlNode::getProperty( const char *sName ) -{ - const char *tmp = (const char *)hProperties[sName]; - if( tmp == NULL ) - return NULL; - return tmp; -} - -void XmlNode::deleteProperty( int nIndex ) -{ - hProperties.del( ((std::string *)lPropNames[nIndex])->c_str() ); - - delete (std::string *)lPropNames[nIndex]; - delete (std::string *)lPropValues[nIndex]; - - lPropNames.deleteAt( nIndex ); - lPropValues.deleteAt( nIndex ); -} - -bool XmlNode::hasChildren() -{ - return lChildren.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 ) -{ - return (XmlNode *)hChildren.get( sName, nSkip ); -} - -const char *XmlNode::getName() -{ - return sName.c_str(); -} - -void XmlNode::deleteNode( int nIndex, const char *sReplacementText ) -{ - XmlNode *xRet = detatchNode( nIndex, sReplacementText ); - - if( xRet != NULL ) - { - delete xRet; - } -} - -XmlNode *XmlNode::detatchNode( int nIndex, const char *sReplacementText ) -{ - if( nIndex < 0 || nIndex >= lChildren.getSize() ) - return NULL; - - // The real trick when deleteing a node isn't actually deleting it, it's - // reforming the content around the node that's now missing...hmmm... - - if( nIndex == 0 ) - { - // If the index is zero we have to deal with the pre-content - if( sReplacementText ) - { - if( sPreContent == NULL ) - { - sPreContent = new std::string( sReplacementText ); - } - else - { - *sPreContent += sReplacementText; - } - } - if( lPostContent.getSize() > 0 ) - { - if( lPostContent[0] != NULL ) - { - if( sPreContent == NULL ) - { - sPreContent = new std::string( - ((std::string *)lPostContent[0])->c_str() - ); - } - else - { - *sPreContent += - ((std::string *)lPostContent[0])->c_str(); - } - } - delete (std::string *)lPostContent[0]; - lPostContent.deleteAt( 0 ); - } - } - else - { - int nCont = nIndex-1; - // If it's above zero we deal with the post-content only - if( sReplacementText ) - { - if( lPostContent[nCont] == NULL ) - { - lPostContent.setAt( nCont, new std::string( sReplacementText ) ); - } - else - { - *((std::string *)lPostContent[nCont]) += sReplacementText; - } - } - if( lPostContent.getSize() > nIndex ) - { - if( lPostContent[nIndex] != NULL ) - { - if( lPostContent[nCont] == NULL ) - { - lPostContent.setAt( nCont, new std::string( - ((std::string *)lPostContent[nIndex])->c_str() - ) ); - } - else - { - *((std::string *)lPostContent[nCont]) += - ((std::string *)lPostContent[nIndex])->c_str(); - } - } - delete (std::string *)lPostContent[nIndex]; - lPostContent.deleteAt( nIndex ); - } - } - - XmlNode *xRet = (XmlNode *)lChildren[nIndex]; - hChildren.del( ((XmlNode *)lChildren[nIndex])->getName() ); - lChildren.deleteAt( nIndex ); - - return xRet; -} - -void XmlNode::replaceNode( int nIndex, XmlNode *pNewNode ) -{ - if( nIndex < 0 || nIndex >= lChildren.getSize() ) - return; //TODO: throw an exception - - delete (XmlNode *)lChildren[nIndex]; - lChildren.setAt( nIndex, pNewNode ); - pNewNode->pParent = this; -} - -XmlNode *XmlNode::getCopy() -{ - XmlNode *pNew = new XmlNode(); - - pNew->sName = sName; - if( sPreContent ) - { - pNew->sPreContent = new std::string( sPreContent->c_str() ); - } - else - { - pNew->sPreContent = NULL; - } - pNew->nCurContent = 0; - - int nSize = lPostContent.getSize(); - pNew->lPostContent.setSize( nSize ); - for( int j = 0; j < nSize; j++ ) - { - if( lPostContent[j] ) - { - pNew->lPostContent.setAt( - j, new std::string( - ((std::string *)lPostContent[j])->c_str() - ) - ); - } - else - { - pNew->lPostContent.setAt( j, NULL ); - } - } - - nSize = lChildren.getSize(); - pNew->lChildren.setSize( nSize ); - for( int j = 0; j < nSize; j++ ) - { - XmlNode *pChild = ((XmlNode *)lChildren[j])->getCopy(); - pNew->lChildren.setAt( j, pChild ); - pChild->pParent = pNew; - pNew->hChildren.insert( pChild->getName(), pChild ); - } - - nSize = lPropNames.getSize(); - pNew->lPropNames.setSize( nSize ); - pNew->lPropValues.setSize( nSize ); - for( int j = 0; j < nSize; j++ ) - { - std::string *pProp = new std::string( ((std::string *)lPropNames[j])->c_str() ); - std::string *pVal = new std::string( ((std::string *)lPropValues[j])->c_str() ); - pNew->lPropNames.setAt( j, pProp ); - pNew->lPropValues.setAt( j, pVal ); - pNew->hProperties.insert( pProp->c_str(), pVal->c_str() ); - pNew->nCurContent++; - } - - return pNew; -} - -void XmlNode::deleteNodeKeepChildren( int nIndex ) -{ - // This is a tricky one...we need to do some patching to keep things all - // even... - XmlNode *xRet = (XmlNode *)lChildren[nIndex]; - - if( xRet == NULL ) - { - return; - } - else - { - if( getContent( nIndex ) ) - { - std::string sBuf( getContent( nIndex ) ); - sBuf += xRet->getContent( 0 ); - setContent( sBuf.c_str(), nIndex ); - } - else - { - setContent( xRet->getContent( 0 ), nIndex ); - } - - int nSize = xRet->lChildren.getSize(); - for( int j = 0; j < nSize; j++ ) - { - XmlNode *pCopy = ((XmlNode *)xRet->lChildren[j])->getCopy(); - pCopy->pParent = this; - lChildren.insertBefore( pCopy, nIndex+j ); - - if( xRet->lPostContent[j] ) - { - lPostContent.insertBefore( - new std::string( ((std::string *)xRet->lPostContent[j])->c_str() ), - nIndex+j - ); - } - else - { - lPostContent.insertBefore( NULL, nIndex+j ); - } - } - - if( getContent( nIndex+nSize ) ) - { - //SString sBuf( getContent( nIndex+nSize ) ); - //sBuf.catfrom( xRet->getContent( nSize ) ); - //setContent( sBuf, nIndex+nSize ); - } - else - { - setContent( xRet->getContent( nSize ), nIndex+nSize ); - } - - deleteNode( nIndex+nSize ); - } -} - -void XmlNode::replaceNodeWithChildren( int nIndex, XmlNode *pNewNode ) -{ -} - diff --git a/src/old/xmlnode.h b/src/old/xmlnode.h deleted file mode 100644 index 7525306..0000000 --- a/src/old/xmlnode.h +++ /dev/null @@ -1,236 +0,0 @@ -#ifndef XMLNODE -#define XMLNODE - -#include -#include "linkedlist.h" -#include "hashtable.h" - -/** - * Maintains all data pertient to an XML node, including sub-nodes and content. - * All child nodes can be accessed through index and through name via a hash - * table. This makes it very easy to gain simple and fast access to all of - * your data. For most applications, the memory footprint is also rather - * small. While XmlNode objects can be used directly to create XML structures - * it is highly reccomended that all operations be performed through the - * XmlDocument class. - *@author Mike Buland - */ -class XmlNode -{ -public: - /** - * Construct a new XmlNode. - *@param sName The name of the node. - *@param pParent The parent node. - *@param sContent The initial content string. - */ - XmlNode( - const char *sName=NULL, - XmlNode *pParent = NULL, - const char *sContent=NULL - ); - - /** - * Delete the node and cleanup all memory. - */ - virtual ~XmlNode(); - - /** - * Change the name of the node. - *@param sName The new name of the node. - */ - void setName( const char *sName ); - - /** - * Construct a new node and add it as a child to this node, also return a - * pointer to the newly constructed node. - *@param sName The name of the new node. - *@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 ); - - /** - * Add an already created XmlNode as a child to this node. The new child - * XmlNode's parent will be changed appropriately and the parent XmlNode - * will take ownership of the child. - *@param pChild The child XmlNode to add to this XmlNode. - *@returns A pointer to the child node that was just added. - */ - XmlNode *addChild( XmlNode *pChild ); - - /** - * Add a new property to the XmlNode. Properties are name/value pairs. - *@param sName The name of the property. Specifying a name that's already - * in use will overwrite that property. - *@param sValue The textual value of the property. - */ - void addProperty( const char *sName, const char *sValue ); - - /** - * Get a pointer to the parent node, if any. - *@returns A pointer to the node's parent, or NULL if there isn't one. - */ - XmlNode *getParent(); - - /** - * Tells you if this node has children. - *@returns True if this node has at least one child, false otherwise. - */ - bool hasChildren(); - - /** - * Tells you how many children this node has. - *@returns The number of children this node has. - */ - 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. - *@param sName The name of the child to find. - *@param nSkip The number of nodes with that name to skip. - *@returns A pointer to the child, or NULL if no child with that name was - * found. - */ - XmlNode *getChild( const char *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(); - - /** - * Set the content of this node, optionally at a specific index. Using the - * default of -1 will set the content after the last added node. - *@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 ); - - /** - * Get the number of properties in this node. - *@returns The number of properties in this node. - */ - 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 ); - - /** - * Delete a child node, possibly replacing it with some text. This actually - * fixes all content strings around the newly deleted child node. - *@param nIndex The index of the node to delete. - *@param sReplacementText The optional text to replace the node with. - *@returns True of the node was found, and deleted, false if it wasn't - * found. - */ - void deleteNode( int nIndex, const char *sReplacementText = NULL ); - - /** - * Delete a given node, but move all of it's children and content up to - * replace the deleted node. All of the content of the child node is - * spliced seamlessly into place with the parent node's content. - *@param nIndex The node to delete. - *@returns True if the node was found and deleted, false if it wasn't. - */ - void deleteNodeKeepChildren( int nIndex ); - - /** - * Detatch a given child node from this node. This effectively works just - * like a deleteNode, except that instead of deleting the node it is removed - * and returned, and all ownership is given up. - *@param nIndex The index of the node to detatch. - *@param sReplacementText The optional text to replace the detatched node - * with. - *@returns A pointer to the newly detatched node, which then passes - * ownership to the caller. - */ - XmlNode *detatchNode( int nIndex, const char *sReplacementText = NULL ); - - /** - * Replace a given node with a different node that is not currently owned by - * this XmlNode or any ancestor. - *@param nIndex The index of the node to replace. - *@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 ); - - /** - * Replace a given node with the children and content of a given node. - *@param nIndex The index of the node to replace. - *@param pNewNode The node that contains the children and content that will - * 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 ); - - /** - * 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(); - -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. */ - XmlNode *pParent; /**< A pointer to the parent of this node. */ - int nCurContent; /**< The current content we're on, for using the -1 on - setContent. */ -}; - -#endif diff --git a/src/old/xmlreader.cpp b/src/old/xmlreader.cpp deleted file mode 100644 index 18df69c..0000000 --- a/src/old/xmlreader.cpp +++ /dev/null @@ -1,602 +0,0 @@ -#include "xmlreader.h" -#include "exceptions.h" -#include -#include "hashfunctionstring.h" - -XmlReader::XmlReader( bool bStrip ) : - bStrip( bStrip ), - htEntity( new HashFunctionString(), 11 ) -{ -} - -XmlReader::~XmlReader() -{ - void *i = htEntity.getFirstItemPos(); - while( (i = htEntity.getNextItemPos( i ) ) ) - { - free( (char *)(htEntity.getItemID( i )) ); - delete (StaticString *)htEntity.getItemData( i ); - } -} - -void XmlReader::addEntity( const char *name, const char *value ) -{ - if( htEntity[name] ) return; - - char *sName = strdup( name ); - StaticString *sValue = new StaticString( value ); - - htEntity.insert( sName, sValue ); -} - -#define gcall( x ) if( x == false ) return false; - -bool XmlReader::isws( char chr ) -{ - return ( chr == ' ' || chr == '\t' || chr == '\n' || chr == '\r' ); -} - -bool XmlReader::ws() -{ - while( true ) - { - char chr = getChar(); - if( isws( chr ) ) - { - usedChar(); - } - else - { - return true; - } - } - return true; -} - -bool XmlReader::buildDoc() -{ - // take care of initial whitespace - gcall( ws() ); - textDecl(); - entity(); - addEntity("gt", ">"); - addEntity("lt", "<"); - addEntity("amp", "&"); - addEntity("apos", "\'"); - addEntity("quot", "\""); - gcall( node() ); - - return true; -} - -void XmlReader::textDecl() -{ - if( getChar() == '<' && getChar( 1 ) == '?' ) - { - usedChar( 2 ); - for(;;) - { - if( getChar() == '?' ) - { - if( getChar( 1 ) == '>' ) - { - usedChar( 2 ); - return; - } - } - usedChar(); - } - } -} - -void XmlReader::entity() -{ - for(;;) - { - ws(); - - if( getChar() == '<' && getChar( 1 ) == '!' ) - { - usedChar( 2 ); - ws(); - std::string buf; - for(;;) - { - char chr = getChar(); - usedChar(); - if( isws( chr ) ) break; - buf += chr; - } - - if( strcmp( buf.c_str(), "ENTITY") == 0 ) - { - ws(); - std::string name; - for(;;) - { - char chr = getChar(); - usedChar(); - if( isws( chr ) ) break; - name += chr; - } - ws(); - char quot = getChar(); - usedChar(); - if( quot != '\'' && quot != '\"' ) - { - throw XmlException( - "Only quoted entity values are supported." - ); - } - std::string value; - for(;;) - { - char chr = getChar(); - usedChar(); - if( chr == '&' ) - { - StaticString *tmp = getEscape(); - if( tmp == NULL ) throw XmlException("Entity thing"); - value += tmp->getString(); - delete tmp; - } - else if( chr == quot ) - { - break; - } - else - { - value += chr; - } - } - ws(); - if( getChar() == '>' ) - { - usedChar(); - - addEntity( name.c_str(), value.c_str() ); - } - else - { - throw XmlException( - "Malformed ENTITY: unexpected '%c' found.", - getChar() - ); - } - } - else - { - throw XmlException( - "Unsupported header symbol: %s", - buf.c_str() - ); - } - } - else - { - return; - } - } -} - -bool XmlReader::node() -{ - gcall( startNode() ) - - // At this point, we are closing the startNode - char chr = getChar(); - if( chr == '>' ) - { - usedChar(); - - // Now we process the guts of the node. - gcall( content() ); - } - else if( chr == '/' ) - { - // This is the tricky one, one more validation, then we close the node. - usedChar(); - if( getChar() == '>' ) - { - closeNode(); - usedChar(); - } - else - { - throw XmlException("Close node in singleNode malformed!"); - } - } - else - { - throw XmlException("Close node expected, but not found."); - return false; - } - - return true; -} - -bool XmlReader::startNode() -{ - if( getChar() == '<' ) - { - usedChar(); - - if( getChar() == '/' ) - { - // Heh, it's actually a close node, go figure - FlexBuf fbName; - usedChar(); - gcall( ws() ); - - while( true ) - { - char chr = getChar(); - if( isws( chr ) || chr == '>' ) - { - // 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() ) ) - { - closeNode(); - break; - } - else - { - throw XmlException("Got a mismatched node close tag."); - } - } - else - { - fbName.appendData( chr ); - usedChar(); - } - } - - gcall( ws() ); - if( getChar() == '>' ) - { - // Everything is cool. - usedChar(); - } - else - { - throw XmlException("Got extra junk data instead of node close tag."); - } - } - else - { - // We're good, format is consistant - addNode(); - - // Skip extra whitespace - gcall( ws() ); - gcall( name() ); - gcall( ws() ); - gcall( paramlist() ); - gcall( ws() ); - } - } - else - { - throw XmlException("Expected to find node opening char, '<'."); - } - - return true; -} - -bool XmlReader::name() -{ - FlexBuf fbName; - - while( true ) - { - char chr = getChar(); - if( isws( chr ) || chr == '>' || chr == '/' ) - { - setName( fbName.getData() ); - return true; - } - else - { - fbName.appendData( chr ); - usedChar(); - } - } - - return true; -} - -bool XmlReader::paramlist() -{ - while( true ) - { - char chr = getChar(); - if( chr == '/' || chr == '>' ) - { - return true; - } - else - { - gcall( param() ); - gcall( ws() ); - } - } - - return true; -} - -StaticString *XmlReader::getEscape() -{ - if( getChar( 1 ) == '#' ) - { - // If the entity starts with a # it's a character escape code - int base = 10; - usedChar( 2 ); - if( getChar() == 'x' ) - { - base = 16; - usedChar(); - } - char buf[4]; - int j = 0; - for( j = 0; getChar() != ';'; j++ ) - { - buf[j] = getChar(); - usedChar(); - } - usedChar(); - buf[j] = '\0'; - buf[0] = (char)strtol( buf, (char **)NULL, base ); - buf[1] = '\0'; - - return new StaticString( buf ); - } - else - { - // ...otherwise replace with the appropriate string... - std::string buf; - usedChar(); - for(;;) - { - char cbuf = getChar(); - usedChar(); - if( cbuf == ';' ) break; - buf += cbuf; - } - - StaticString *tmp = (StaticString *)htEntity[buf.c_str()]; - if( tmp == NULL ) return NULL; - - StaticString *ret = new StaticString( *tmp ); - return ret; - } -} - -bool XmlReader::param() -{ - FlexBuf fbName; - FlexBuf fbValue; - - while( true ) - { - char chr = getChar(); - if( isws( chr ) || chr == '=' ) - { - break; - } - else - { - fbName.appendData( chr ); - usedChar(); - } - } - - gcall( ws() ); - - if( getChar() == '=' ) - { - usedChar(); - - gcall( ws() ); - - char chr = getChar(); - if( chr == '"' ) - { - // Better quoted rhs - usedChar(); - - while( true ) - { - chr = getChar(); - if( chr == '"' ) - { - usedChar(); - addProperty( fbName.getData(), fbValue.getData() ); - return true; - } - else - { - if( chr == '&' ) - { - StaticString *tmp = getEscape(); - if( tmp == NULL ) return false; - fbValue.appendData( tmp->getString() ); - delete tmp; - } - else - { - fbValue.appendData( chr ); - usedChar(); - } - } - } - } - else - { - // Simple one-word rhs - while( true ) - { - chr = getChar(); - if( isws( chr ) || chr == '/' || chr == '>' ) - { - addProperty( fbName.getData(), fbValue.getData() ); - return true; - } - else - { - if( chr == '&' ) - { - StaticString *tmp = getEscape(); - if( tmp == NULL ) return false; - fbValue.appendData( tmp->getString() ); - delete tmp; - } - else - { - fbValue.appendData( chr ); - usedChar(); - } - } - } - } - } - else - { - throw XmlException("Expected an equals to seperate the params."); - return false; - } - - return true; -} - -bool XmlReader::content() -{ - FlexBuf fbContent; - - if( bStrip ) gcall( ws() ); - - while( true ) - { - char chr = getChar(); - if( chr == '<' ) - { - if( getChar(1) == '/' ) - { - if( fbContent.getLength() > 0 ) - { - if( bStrip ) - { - int j; - for( j = fbContent.getLength()-1; isws(fbContent.getData()[j]); j-- ); - ((char *)fbContent.getData())[j+1] = '\0'; - } - setContent( fbContent.getData() ); - } - usedChar( 2 ); - gcall( ws() ); - FlexBuf fbName; - while( true ) - { - chr = getChar(); - if( isws( chr ) || chr == '>' ) - { - if( !strcasecmp( getCurrent()->getName(), fbName.getData() ) ) - { - closeNode(); - break; - } - else - { - throw XmlException("Mismatched close tag found: <%s> to <%s>.", getCurrent()->getName(), fbName.getData() ); - } - } - else - { - fbName.appendData( chr ); - usedChar(); - } - } - gcall( ws() ); - if( getChar() == '>' ) - { - usedChar(); - return true; - } - else - { - throw XmlException("Malformed close tag."); - } - } - else if( getChar(1) == '!' ) - { - // We know it's a comment, let's see if it's proper - if( getChar(2) != '-' || - getChar(3) != '-' ) - { - // Not a valid XML comment - throw XmlException("Malformed comment start tag found."); - } - - usedChar( 4 ); - - // Now burn text until we find the close tag - for(;;) - { - if( getChar() == '-' ) - { - if( getChar( 1 ) == '-' ) - { - // 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."); - } - usedChar( 3 ); - break; - } - else - { - // Found a dash followed by a non dash, that's ok... - usedChar( 2 ); - } - } - else - { - // Burn comment chars - usedChar(); - } - } - } - else - { - if( fbContent.getLength() > 0 ) - { - if( bStrip ) - { - int j; - for( j = fbContent.getLength()-1; isws(fbContent.getData()[j]); j-- ); - ((char *)fbContent.getData())[j+1] = '\0'; - } - setContent( fbContent.getData() ); - fbContent.clearData(); - } - gcall( node() ); - } - - if( bStrip ) gcall( ws() ); - } - else if( chr == '&' ) - { - StaticString *tmp = getEscape(); - if( tmp == NULL ) return false; - fbContent.appendData( tmp->getString() ); - delete tmp; - } - else - { - fbContent.appendData( chr ); - usedChar(); - } - } -} - diff --git a/src/old/xmlreader.h b/src/old/xmlreader.h deleted file mode 100644 index c8f7202..0000000 --- a/src/old/xmlreader.h +++ /dev/null @@ -1,141 +0,0 @@ -#ifndef XMLREADER -#define XMLREADER - -#include -#include "xmldocument.h" -#include "flexbuf.h" -#include "hashtable.h" -#include "staticstring.h" - -/** - * Takes care of reading in xml formatted data from a file. This could/should - * be made more arbitrary in the future so that we can read the data from any - * source. This is actually made quite simple already since all data read in - * is handled by one single helper function and then palced into a FlexBuf for - * easy access by the other functions. The FlexBuf also allows for block - * reading from disk, which improves speed by a noticable amount. - *
- * There are also some extra features implemented that allow you to break the - * standard XML reader specs and eliminate leading and trailing whitespace in - * all read content. This is useful in situations where you allow additional - * whitespace in the files to make them easily human readable. The resturned - * content will be NULL in sitautions where all content between nodes was - * stripped. - *@author Mike Buland - */ -class XmlReader : public XmlDocument -{ -public: - /** - * Create a standard XmlReader. The optional parameter bStrip allows you to - * create a reader that will strip out all leading and trailing whitespace - * in content, a-la html. - *@param bStrip Strip out leading and trailing whitespace? - */ - XmlReader( bool bStrip=false ); - - /** - * Destroy this XmlReader. - */ - virtual ~XmlReader(); - - /** - * Build a document based on some kind of input. This is called - * automatically by the constructor. - */ - bool buildDoc(); - -private: - /** - * This is called by the low level automoton in order to get the next - * character. This function should return a character at the current - * position plus nIndex, but does not increment the current character. - *@param nIndex The index of the character from the current stream position. - *@returns A single character at the requested position, or 0 for end of - * stream. - */ - virtual char getChar( int nIndex = 0 ) = 0; - - /** - * Called to increment the current stream position by a single character. - */ - virtual void usedChar( int nAmnt = 1) = 0; - - /** - * Automoton function: is whitespace. - *@param chr A character - *@returns True if chr is whitespace, false otherwise. - */ - bool isws( char chr ); - - /** - * Automoton function: ws. Skips sections of whitespace. - *@returns True if everything was ok, False for end of stream. - */ - bool ws(); - - /** - * Automoton function: node. Processes an XmlNode - *@returns True if everything was ok, False for end of stream. - */ - bool node(); - - /** - * Automoton function: startNode. Processes the begining of a node. - *@returns True if everything was ok, False for end of stream. - */ - bool startNode(); - - /** - * Automoton function: name. Processes the name of a node. - *@returns True if everything was ok, False for end of stream. - */ - bool name(); - - /** - * Automoton function: textDecl. Processes the xml text decleration, if - * there is one. - */ - void textDecl(); - - /** - * Automoton function: entity. Processes an entity from the header. - */ - void entity(); - - /** - * Adds an entity to the list, if it doesn't already exist. - *@param name The name of the entity - *@param value The value of the entity - */ - void addEntity( const char *name, const char *value ); - - StaticString *getEscape(); - - /** - * Automoton function: paramlist. Processes a list of node params. - *@returns True if everything was ok, False for end of stream. - */ - bool paramlist(); - - /** - * Automoton function: param. Processes a single parameter. - *@returns True if everything was ok, False for end of stream. - */ - bool param(); - - /** - * Automoton function: content. Processes node content. - *@returns True if everything was ok, False for end of stream. - */ - 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? */ - - HashTable htEntity; /**< Entity type definitions. */ -}; - -#endif diff --git a/src/old/xmlwriter.cpp b/src/old/xmlwriter.cpp deleted file mode 100644 index 56880b6..0000000 --- a/src/old/xmlwriter.cpp +++ /dev/null @@ -1,173 +0,0 @@ -#include -#include -#include "xmlwriter.h" - -XmlWriter::XmlWriter( const char *sIndent, XmlNode *pRoot ) : - XmlDocument( pRoot ) -{ - if( sIndent == NULL ) - { - this->sIndent = ""; - } - else - { - this->sIndent = sIndent; - } -} - -XmlWriter::~XmlWriter() -{ -} - -void XmlWriter::write() -{ - write( getRoot(), sIndent.c_str() ); -} - -void XmlWriter::write( XmlNode *pRoot, const char *sIndent ) -{ - writeNode( pRoot, 0, sIndent ); -} - -void XmlWriter::closeNode() -{ - XmlDocument::closeNode(); - - if( isCompleted() ) - { - write( getRoot(), sIndent.c_str() ); - } -} - -void XmlWriter::writeIndent( int nIndent, const char *sIndent ) -{ - if( sIndent == NULL ) return; - for( int j = 0; j < nIndent; j++ ) - { - writeString( sIndent ); - } -} - -std::string XmlWriter::escape( std::string sIn ) -{ - std::string sOut; - - std::string::const_iterator i; - for( i = sIn.begin(); i != sIn.end(); i++ ) - { - if( ((*i >= ' ' && *i <= '9') || - (*i >= 'a' && *i <= 'z') || - (*i >= 'A' && *i <= 'Z') ) && - (*i != '\"' && *i != '\'' && *i != '&') - ) - { - sOut += *i; - } - else - { - sOut += "&#"; - char buf[4]; - sprintf( buf, "%u", (unsigned char)*i ); - sOut += buf; - sOut += ';'; - } - } - - return sOut; -} - -void XmlWriter::writeNodeProps( XmlNode *pNode, int nIndent, const char *sIndent ) -{ - for( int j = 0; j < pNode->getNumProperties(); j++ ) - { - writeString(" "); - writeString( pNode->getPropertyName( j ) ); - writeString("=\""); - writeString( escape( pNode->getProperty( j ) ).c_str() ); - writeString("\""); - } -} - -void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) -{ - if( pNode->hasChildren() ) - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent ) - writeString(">\n"); - else - writeString(">"); - - if( pNode->getContent( 0 ) ) - { - writeIndent( nIndent+1, sIndent ); - if( sIndent ) - { - writeString( pNode->getContent( 0 ) ); - writeString("\n"); - } - else - writeString( pNode->getContent( 0 ) ); - } - - int nNumChildren = pNode->getNumChildren(); - for( int j = 0; j < nNumChildren; j++ ) - { - writeNode( pNode->getChild( j ), nIndent+1, sIndent ); - if( pNode->getContent( j+1 ) ) - { - writeIndent( nIndent+1, sIndent ); - if( sIndent ) - { - writeString( pNode->getContent( j+1 ) ); - writeString("\n"); - } - else - writeString( pNode->getContent( j+1 ) ); - } - } - - writeIndent( nIndent, sIndent ); - if( sIndent ) - { - writeString("getName() ); - writeString(">\n"); - } - else - { - writeString("getName() ); - writeString(">"); - } - } - else if( pNode->getContent() ) - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - writeString(">"); - writeString( pNode->getContent() ); - writeString("getName() ); - writeString(">"); - if( sIndent ) - writeString("\n"); - } - else - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent ) - writeString("/>\n"); - else - writeString("/>"); - } -} - diff --git a/src/old/xmlwriter.h b/src/old/xmlwriter.h deleted file mode 100644 index c48e810..0000000 --- a/src/old/xmlwriter.h +++ /dev/null @@ -1,96 +0,0 @@ -#ifndef XMLWRITER -#define XMLWRITER - -#include "xmlnode.h" -#include "xmldocument.h" - -/** - * Implements xml writing in the XML standard format. Also allows you to - * break that format and auto-indent your exported xml data for ease of - * reading. The auto-indenting will only be applied to sections that - * have no content of their own already. This means that except for - * whitespace all of your data will be preserved perfectly. - * You can create an XmlWriter object around a file, or access the static - * write function directly and just hand it a filename and a root XmlNode. - * When using an XmlWriter object the interface is identicle to that of - * the XmlDocument class, so reference that class for API info. However - * when the initial (or root) node is closed, and the document is finished - * the file will be created and written to automatically. The user can - * check to see if this is actually true by calling the isFinished - * function in the XmlDocument class. - *@author Mike Buland - */ -class XmlWriter : public XmlDocument -{ -public: - /** - * Construct a standard XmlWriter. - *@param sIndent Set this to something other than NULL to include it as an - * indent before each node in the output that doesn't already have content. - * If you are using the whitespace stripping option in the XmlReader and set - * this to a tab or some spaces it will never effect the content of your - * file. - */ - XmlWriter( const char *sIndent=NULL, XmlNode *pRoot=NULL ); - - /** - * Destroy the writer. - */ - virtual ~XmlWriter(); - - /** - * This override of the parent class closeNode function calls the parent - * class, but also triggers a write operation when the final node is closed. - * This means that by checking the isCompleted() function the user may also - * check to see if their file has been written or not. - */ - void closeNode(); - - void write(); - -private: - std::string sIndent; /**< The indent string */ - - std::string escape( std::string sIn ); - - /** - * Write the file. - *@param pNode The root node - *@param sIndent The indent text. - */ - void write( XmlNode *pNode, const char *sIndent=NULL ); - - /** - * Write a node in the file, including children. - *@param pNode The node to write. - *@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 ); - - /** - * Write the properties of a node. - *@param pNode The node who's properties to write. - *@param nIndent The indent level of the containing node - *@param sIndent The indent text. - */ - void writeNodeProps( XmlNode *pNode, int nIndent, const char *sIndent ); - - /** - * Called to write the actual indent. - *@param nIndent The indent level. - *@param sIndent The indent text. - */ - void writeIndent( int nIndent, const char *sIndent ); - - /** - * This is the function that must be overridden in order to use this class. - * It must write the null-terminated string sString, minus the mull, - * verbatum to it's output device. Adding extra characters for any reason - * will break the XML formatting. - *@param sString The string data to write to the output. - */ - virtual void writeString( const char *sString ) = 0; -}; - -#endif diff --git a/src/tafdocument.cpp b/src/tafdocument.cpp deleted file mode 100644 index bd44dd5..0000000 --- a/src/tafdocument.cpp +++ /dev/null @@ -1,9 +0,0 @@ -#include "tafdocument.h" - -Bu::TafDocument::TafDocument() -{ -} - -Bu::TafDocument::~TafDocument() -{ -} diff --git a/src/tafdocument.h b/src/tafdocument.h deleted file mode 100644 index 171f829..0000000 --- a/src/tafdocument.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef BU_TAF_DOCUMENT_H -#define BU_TAF_DOCUMENT_H - -#include - -namespace Bu -{ - /** - * - */ - class TafDocument - { - public: - TafDocument(); - virtual ~TafDocument(); - - private: - - }; -} - -#endif diff --git a/src/tafnode.cpp b/src/tafnode.cpp deleted file mode 100644 index c9756ec..0000000 --- a/src/tafnode.cpp +++ /dev/null @@ -1,9 +0,0 @@ -#include "tafnode.h" - -Bu::TafNode::TafNode() -{ -} - -Bu::TafNode::~TafNode() -{ -} diff --git a/src/tafnode.h b/src/tafnode.h deleted file mode 100644 index 34f5289..0000000 --- a/src/tafnode.h +++ /dev/null @@ -1,21 +0,0 @@ -#ifndef BU_TAF_NODE_H -#define BU_TAF_NODE_H - -#include - -namespace Bu -{ - /** - * - */ - class TafNode - { - public: - TafNode(); - virtual ~TafNode(); - - private: - - }; -} -#endif diff --git a/src/tafreader.cpp b/src/tafreader.cpp deleted file mode 100644 index f94fe44..0000000 --- a/src/tafreader.cpp +++ /dev/null @@ -1,11 +0,0 @@ -#include "tafreader.h" - -Bu::TafReader::TafReader( Bu::Stream &sIn ) : - sIn( sIn ) -{ -} - -Bu::TafReader::~TafReader() -{ -} - diff --git a/src/tafreader.h b/src/tafreader.h deleted file mode 100644 index 2dbb9ea..0000000 --- a/src/tafreader.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef BU_TAF_READER_H -#define BU_TAF_READER_H - -#include -#include "bu/tafdocument.h" -#include "bu/stream.h" - -namespace Bu -{ - /** - * - */ - class TafReader : public Bu::TafDocument - { - public: - TafReader( Bu::Stream &sIn ); - virtual ~TafReader(); - - private: - Stream &sIn; - - }; -} - -#endif diff --git a/src/tafwriter.cpp b/src/tafwriter.cpp deleted file mode 100644 index 3e6c025..0000000 --- a/src/tafwriter.cpp +++ /dev/null @@ -1,9 +0,0 @@ -#include "tafwriter.h" - -Bu::TafWriter::TafWriter() -{ -} - -Bu::TafWriter::~TafWriter() -{ -} diff --git a/src/tafwriter.h b/src/tafwriter.h deleted file mode 100644 index 7057d62..0000000 --- a/src/tafwriter.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef BU_TAF_WRITER_H -#define BU_TAF_WRITER_H - -#include - -namespace Bu -{ - /** - * - */ - class TafWriter - { - public: - TafWriter(); - virtual ~TafWriter(); - - private: - - }; -} - -#endif diff --git a/src/xmldocument.cpp b/src/xmldocument.cpp index cb21826..d7867d5 100644 --- a/src/xmldocument.cpp +++ b/src/xmldocument.cpp @@ -1,9 +1,149 @@ -#include "xmldocument.h" +#include +#include +#include "xmlwriter.h" -Bu::XmlDocument::XmlDocument() +XmlDocument::XmlDocument( XmlNode *pRoot ) { + this->pRoot = pRoot; + pCurrent = NULL; + bCompleted = (pRoot!=NULL); } -Bu::XmlDocument::~XmlDocument() +XmlDocument::~XmlDocument() { + if( pRoot ) + { + delete pRoot; + } } + +void XmlDocument::addNode( const char *sName, const char *sContent, bool bClose ) +{ + if( pRoot == NULL ) + { + // This is the first node, so ignore position and just insert it. + pCurrent = pRoot = new XmlNode( sName, NULL, sContent ); + } + else + { + pCurrent = pCurrent->addChild( sName, sContent ); + } + + if( bClose ) + { + closeNode(); + } +} + +void XmlDocument::setName( const char *sName ) +{ + pCurrent->setName( sName ); +} + +bool XmlDocument::isCompleted() +{ + return bCompleted; +} + +XmlNode *XmlDocument::getRoot() +{ + return pRoot; +} + +XmlNode *XmlDocument::detatchRoot() +{ + XmlNode *pTemp = pRoot; + pRoot = NULL; + return pTemp; +} + +XmlNode *XmlDocument::getCurrent() +{ + return pCurrent; +} + +void XmlDocument::closeNode() +{ + if( pCurrent != NULL ) + { + pCurrent = pCurrent->getParent(); + + if( pCurrent == NULL ) + { + bCompleted = true; + } + } +} + +void XmlDocument::addProperty( const char *sName, const char *sValue ) +{ + if( pCurrent ) + { + pCurrent->addProperty( sName, sValue ); + } +} + +void XmlDocument::addProperty( const char *sName, const unsigned char nValue ) +{ + char buf[12]; + sprintf( buf, "%hhi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const char nValue ) +{ + char buf[12]; + sprintf( buf, "%hhi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const unsigned short nValue ) +{ + char buf[12]; + sprintf( buf, "%hi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const short nValue ) +{ + char buf[12]; + sprintf( buf, "%hi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const int nValue ) +{ + char buf[12]; + sprintf( buf, "%d", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const unsigned long nValue ) +{ + char buf[12]; + sprintf( buf, "%li", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const long nValue ) +{ + char buf[12]; + sprintf( buf, "%li", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const double dValue ) +{ + char buf[40]; + sprintf( buf, "%f", dValue ); + addProperty( sName, buf ); +} + +void XmlDocument::setContent( const char *sContent ) +{ + if( pCurrent ) + { + pCurrent->setContent( sContent ); + } +} + diff --git a/src/xmldocument.h b/src/xmldocument.h index e16e3ea..6671c41 100644 --- a/src/xmldocument.h +++ b/src/xmldocument.h @@ -1,22 +1,171 @@ -#ifndef XML_DOCUMENT_H -#define XML_DOCUMENT_H +#ifndef XMLDOCUMENT +#define XMLDOCUMENT -#include +#include "xmlnode.h" -namespace Bu +/** + * Keeps track of an easily managed set of XmlNode information. Allows simple + * operations for logical writing to and reading from XML structures. Using + * already formed structures is simply done through the XmlNode structures, + * and the getRoot function here. Creation is performed through a simple set + * of operations that creates the data in a stream type format. + *@author Mike Buland + */ +class XmlDocument { +public: /** - * + * Construct either a blank XmlDocuemnt or construct a document around an + * existing XmlNode. Be careful, once an XmlNode is passed into a document + * the document takes over ownership and will delete it when the XmlDocument + * is deleted. + *@param pRoot The XmlNode to use as the root of this document, or NULL if + * you want to start a new document. */ - class XmlDocument - { - public: - XmlDocument(); - virtual ~XmlDocument(); + XmlDocument( XmlNode *pRoot=NULL ); - private: + /** + * Destroy all contained nodes. + */ + virtual ~XmlDocument(); + + /** + * Add a new node to the document. The new node is appended to the end of + * the current context, i.e. XmlNode, and the new node, provided it isn't + * close as part of this operation, will become the current context. + *@param sName The name of the new node to add. + *@param sContent A content string to be placed inside of the new node. + *@param bClose Set this to true to close the node immediately after adding + * 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 ); + + /** + * Close the current node context. This will move the current context to + * the parent node of the former current node. If the current node was the + * root then the "completed" flag is set and no more operations are allowed. + */ + void closeNode(); + + /** + * Change the content of the current node at the current position between + * nodes. + *@param sContent The new content of the current node. + */ + void setContent( const char *sContent ); + + /** + * Add a named property to the current context node. + *@param sName The name of the property to add. + *@param sValue The string value of the property. + */ + void addProperty( const char *sName, const char *sValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const unsigned char nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const char nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const unsigned short nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const short nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const unsigned long nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const long nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const int nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param dValue The numerical value to add. + */ + void addProperty( const char *sName, const double dValue ); + + /** + * The XmlDocuemnt is considered completed if the root node has been closed. + * Once an XmlDocument has been completed, you can no longer perform + * operations on it. + *@return True if completed, false if still in progress. + */ + bool isCompleted(); + + /** + * Get a pointer to the root object of this XmlDocument. + *@returns A pointer to an internally owned XmlNode. Do not delete this + * XmlNode. + */ + XmlNode *getRoot(); + + /** + * Get a pointer to the root object of this XmlDocument, and remove the + * ownership from this object. + *@returns A pointer to an internally owned XmlNode. Do not delete this + * XmlNode. + */ + XmlNode *detatchRoot(); + + /** + * Get the current context node, which could be the same as the root node. + *@returns A pointer to an internally owned XmlNode. Do not delete this + * XmlNode. + */ + XmlNode *getCurrent(); - }; -} +private: + XmlNode *pRoot; /**< The root node. */ + XmlNode *pCurrent; /**< The current node. */ + bool bCompleted; /**< Is it completed? */ +}; #endif diff --git a/src/xmlnode.cpp b/src/xmlnode.cpp index 58ef5c5..b1ed9a9 100644 --- a/src/xmlnode.cpp +++ b/src/xmlnode.cpp @@ -1,9 +1,445 @@ #include "xmlnode.h" +#include "hashfunctionstring.h" -Bu::XmlNode::XmlNode() +XmlNode::XmlNode( const char *sName, XmlNode *pParent, const char *sContent ) : + hProperties( new HashFunctionString(), 53, false ), + hChildren( new HashFunctionString(), 53, true ) { + this->pParent = pParent; + if( sName != NULL ) + { + setName( sName ); + } + if( sContent != NULL ) + { + this->sPreContent = new std::string( sContent ); + } + else + { + this->sPreContent = NULL; + } + nCurContent = 0; } -Bu::XmlNode::~XmlNode() +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 ) + { + if( this->sName.size() == 0 ) + { + // We're not in the hash yet, so add us + this->sName = sName; + pParent->hChildren.insert( this->sName.c_str(), this ); + } + else + { + // Slightly more tricky, delete us, then add us... + pParent->hChildren.del( this->sName.c_str() ); + this->sName = sName; + pParent->hChildren.insert( this->sName.c_str(), this ); + } + } + else + { + // If we have no parent, then just set the name string, we don't need + // to worry about hashing. + this->sName = sName; + } +} + +void XmlNode::setContent( const char *sContent, int nIndex ) +{ + if( nIndex == -1 ) + { + nIndex = nCurContent; + } + if( nIndex == 0 ) + { + if( this->sPreContent ) + { + delete this->sPreContent; + } + + this->sPreContent = new std::string( sContent ); + } + else + { + nIndex--; + if( lPostContent[nIndex] ) + { + delete (std::string *)lPostContent[nIndex]; + } + + lPostContent.setAt( nIndex, new std::string( sContent ) ); + } +} + +const char *XmlNode::getContent( int nIndex ) +{ + if( nIndex == 0 ) + { + if( sPreContent ) + { + return sPreContent->c_str(); + } + } + else + { + nIndex--; + if( lPostContent[nIndex] ) + { + return ((std::string *)lPostContent[nIndex])->c_str(); + } + } + + return NULL; +} + +XmlNode *XmlNode::addChild( const char *sName, const char *sContent ) +{ + return addChild( new XmlNode( sName, this, sContent ) ); +} + +XmlNode *XmlNode::addChild( XmlNode *pNode ) +{ + lChildren.append( pNode ); + lPostContent.append( NULL ); + nCurContent++; + pNode->pParent = this; + + return pNode; +} + +XmlNode *XmlNode::getParent() +{ + return pParent; +} + +void XmlNode::addProperty( const char *sName, const char *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 ); +} + +int XmlNode::getNumProperties() +{ + return lPropNames.getSize(); +} + +const char *XmlNode::getPropertyName( int nIndex ) +{ + std::string *tmp = ((std::string *)lPropNames[nIndex]); + if( tmp == NULL ) + return NULL; + return tmp->c_str(); +} + +const char *XmlNode::getProperty( int nIndex ) +{ + std::string *tmp = ((std::string *)lPropValues[nIndex]); + if( tmp == NULL ) + return NULL; + return tmp->c_str(); +} + +const char *XmlNode::getProperty( const char *sName ) +{ + const char *tmp = (const char *)hProperties[sName]; + if( tmp == NULL ) + return NULL; + return tmp; +} + +void XmlNode::deleteProperty( int nIndex ) +{ + hProperties.del( ((std::string *)lPropNames[nIndex])->c_str() ); + + delete (std::string *)lPropNames[nIndex]; + delete (std::string *)lPropValues[nIndex]; + + lPropNames.deleteAt( nIndex ); + lPropValues.deleteAt( nIndex ); +} + +bool XmlNode::hasChildren() +{ + return lChildren.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 ) +{ + return (XmlNode *)hChildren.get( sName, nSkip ); +} + +const char *XmlNode::getName() +{ + return sName.c_str(); +} + +void XmlNode::deleteNode( int nIndex, const char *sReplacementText ) +{ + XmlNode *xRet = detatchNode( nIndex, sReplacementText ); + + if( xRet != NULL ) + { + delete xRet; + } +} + +XmlNode *XmlNode::detatchNode( int nIndex, const char *sReplacementText ) +{ + if( nIndex < 0 || nIndex >= lChildren.getSize() ) + return NULL; + + // The real trick when deleteing a node isn't actually deleting it, it's + // reforming the content around the node that's now missing...hmmm... + + if( nIndex == 0 ) + { + // If the index is zero we have to deal with the pre-content + if( sReplacementText ) + { + if( sPreContent == NULL ) + { + sPreContent = new std::string( sReplacementText ); + } + else + { + *sPreContent += sReplacementText; + } + } + if( lPostContent.getSize() > 0 ) + { + if( lPostContent[0] != NULL ) + { + if( sPreContent == NULL ) + { + sPreContent = new std::string( + ((std::string *)lPostContent[0])->c_str() + ); + } + else + { + *sPreContent += + ((std::string *)lPostContent[0])->c_str(); + } + } + delete (std::string *)lPostContent[0]; + lPostContent.deleteAt( 0 ); + } + } + else + { + int nCont = nIndex-1; + // If it's above zero we deal with the post-content only + if( sReplacementText ) + { + if( lPostContent[nCont] == NULL ) + { + lPostContent.setAt( nCont, new std::string( sReplacementText ) ); + } + else + { + *((std::string *)lPostContent[nCont]) += sReplacementText; + } + } + if( lPostContent.getSize() > nIndex ) + { + if( lPostContent[nIndex] != NULL ) + { + if( lPostContent[nCont] == NULL ) + { + lPostContent.setAt( nCont, new std::string( + ((std::string *)lPostContent[nIndex])->c_str() + ) ); + } + else + { + *((std::string *)lPostContent[nCont]) += + ((std::string *)lPostContent[nIndex])->c_str(); + } + } + delete (std::string *)lPostContent[nIndex]; + lPostContent.deleteAt( nIndex ); + } + } + + XmlNode *xRet = (XmlNode *)lChildren[nIndex]; + hChildren.del( ((XmlNode *)lChildren[nIndex])->getName() ); + lChildren.deleteAt( nIndex ); + + return xRet; +} + +void XmlNode::replaceNode( int nIndex, XmlNode *pNewNode ) +{ + if( nIndex < 0 || nIndex >= lChildren.getSize() ) + return; //TODO: throw an exception + + delete (XmlNode *)lChildren[nIndex]; + lChildren.setAt( nIndex, pNewNode ); + pNewNode->pParent = this; +} + +XmlNode *XmlNode::getCopy() +{ + XmlNode *pNew = new XmlNode(); + + pNew->sName = sName; + if( sPreContent ) + { + pNew->sPreContent = new std::string( sPreContent->c_str() ); + } + else + { + pNew->sPreContent = NULL; + } + pNew->nCurContent = 0; + + int nSize = lPostContent.getSize(); + pNew->lPostContent.setSize( nSize ); + for( int j = 0; j < nSize; j++ ) + { + if( lPostContent[j] ) + { + pNew->lPostContent.setAt( + j, new std::string( + ((std::string *)lPostContent[j])->c_str() + ) + ); + } + else + { + pNew->lPostContent.setAt( j, NULL ); + } + } + + nSize = lChildren.getSize(); + pNew->lChildren.setSize( nSize ); + for( int j = 0; j < nSize; j++ ) + { + XmlNode *pChild = ((XmlNode *)lChildren[j])->getCopy(); + pNew->lChildren.setAt( j, pChild ); + pChild->pParent = pNew; + pNew->hChildren.insert( pChild->getName(), pChild ); + } + + nSize = lPropNames.getSize(); + pNew->lPropNames.setSize( nSize ); + pNew->lPropValues.setSize( nSize ); + for( int j = 0; j < nSize; j++ ) + { + std::string *pProp = new std::string( ((std::string *)lPropNames[j])->c_str() ); + std::string *pVal = new std::string( ((std::string *)lPropValues[j])->c_str() ); + pNew->lPropNames.setAt( j, pProp ); + pNew->lPropValues.setAt( j, pVal ); + pNew->hProperties.insert( pProp->c_str(), pVal->c_str() ); + pNew->nCurContent++; + } + + return pNew; +} + +void XmlNode::deleteNodeKeepChildren( int nIndex ) +{ + // This is a tricky one...we need to do some patching to keep things all + // even... + XmlNode *xRet = (XmlNode *)lChildren[nIndex]; + + if( xRet == NULL ) + { + return; + } + else + { + if( getContent( nIndex ) ) + { + std::string sBuf( getContent( nIndex ) ); + sBuf += xRet->getContent( 0 ); + setContent( sBuf.c_str(), nIndex ); + } + else + { + setContent( xRet->getContent( 0 ), nIndex ); + } + + int nSize = xRet->lChildren.getSize(); + for( int j = 0; j < nSize; j++ ) + { + XmlNode *pCopy = ((XmlNode *)xRet->lChildren[j])->getCopy(); + pCopy->pParent = this; + lChildren.insertBefore( pCopy, nIndex+j ); + + if( xRet->lPostContent[j] ) + { + lPostContent.insertBefore( + new std::string( ((std::string *)xRet->lPostContent[j])->c_str() ), + nIndex+j + ); + } + else + { + lPostContent.insertBefore( NULL, nIndex+j ); + } + } + + if( getContent( nIndex+nSize ) ) + { + //SString sBuf( getContent( nIndex+nSize ) ); + //sBuf.catfrom( xRet->getContent( nSize ) ); + //setContent( sBuf, nIndex+nSize ); + } + else + { + setContent( xRet->getContent( nSize ), nIndex+nSize ); + } + + deleteNode( nIndex+nSize ); + } +} + +void XmlNode::replaceNodeWithChildren( int nIndex, XmlNode *pNewNode ) +{ +} + diff --git a/src/xmlnode.h b/src/xmlnode.h index cd9961a..7525306 100644 --- a/src/xmlnode.h +++ b/src/xmlnode.h @@ -1,22 +1,236 @@ -#ifndef XML_NODE_H -#define XML_NODE_H +#ifndef XMLNODE +#define XMLNODE -#include +#include +#include "linkedlist.h" +#include "hashtable.h" -namespace Bu +/** + * Maintains all data pertient to an XML node, including sub-nodes and content. + * All child nodes can be accessed through index and through name via a hash + * table. This makes it very easy to gain simple and fast access to all of + * your data. For most applications, the memory footprint is also rather + * small. While XmlNode objects can be used directly to create XML structures + * it is highly reccomended that all operations be performed through the + * XmlDocument class. + *@author Mike Buland + */ +class XmlNode { +public: /** - * + * Construct a new XmlNode. + *@param sName The name of the node. + *@param pParent The parent node. + *@param sContent The initial content string. */ - class XmlNode - { - public: - XmlNode(); - virtual ~XmlNode(); + XmlNode( + const char *sName=NULL, + XmlNode *pParent = NULL, + const char *sContent=NULL + ); + + /** + * Delete the node and cleanup all memory. + */ + virtual ~XmlNode(); + + /** + * Change the name of the node. + *@param sName The new name of the node. + */ + void setName( const char *sName ); + + /** + * Construct a new node and add it as a child to this node, also return a + * pointer to the newly constructed node. + *@param sName The name of the new node. + *@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 ); + + /** + * Add an already created XmlNode as a child to this node. The new child + * XmlNode's parent will be changed appropriately and the parent XmlNode + * will take ownership of the child. + *@param pChild The child XmlNode to add to this XmlNode. + *@returns A pointer to the child node that was just added. + */ + XmlNode *addChild( XmlNode *pChild ); + + /** + * Add a new property to the XmlNode. Properties are name/value pairs. + *@param sName The name of the property. Specifying a name that's already + * in use will overwrite that property. + *@param sValue The textual value of the property. + */ + void addProperty( const char *sName, const char *sValue ); + + /** + * Get a pointer to the parent node, if any. + *@returns A pointer to the node's parent, or NULL if there isn't one. + */ + XmlNode *getParent(); + + /** + * Tells you if this node has children. + *@returns True if this node has at least one child, false otherwise. + */ + bool hasChildren(); + + /** + * Tells you how many children this node has. + *@returns The number of children this node has. + */ + 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. + *@param sName The name of the child to find. + *@param nSkip The number of nodes with that name to skip. + *@returns A pointer to the child, or NULL if no child with that name was + * found. + */ + XmlNode *getChild( const char *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(); + + /** + * Set the content of this node, optionally at a specific index. Using the + * default of -1 will set the content after the last added node. + *@param sContent The content string to use. + *@param nIndex The index of the content. + */ + void setContent( const char *sContent, int nIndex=-1 ); - private: + /** + * 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 ); + + /** + * Get the number of properties in this node. + *@returns The number of properties in this node. + */ + 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 ); + + /** + * Delete a child node, possibly replacing it with some text. This actually + * fixes all content strings around the newly deleted child node. + *@param nIndex The index of the node to delete. + *@param sReplacementText The optional text to replace the node with. + *@returns True of the node was found, and deleted, false if it wasn't + * found. + */ + void deleteNode( int nIndex, const char *sReplacementText = NULL ); + + /** + * Delete a given node, but move all of it's children and content up to + * replace the deleted node. All of the content of the child node is + * spliced seamlessly into place with the parent node's content. + *@param nIndex The node to delete. + *@returns True if the node was found and deleted, false if it wasn't. + */ + void deleteNodeKeepChildren( int nIndex ); + + /** + * Detatch a given child node from this node. This effectively works just + * like a deleteNode, except that instead of deleting the node it is removed + * and returned, and all ownership is given up. + *@param nIndex The index of the node to detatch. + *@param sReplacementText The optional text to replace the detatched node + * with. + *@returns A pointer to the newly detatched node, which then passes + * ownership to the caller. + */ + XmlNode *detatchNode( int nIndex, const char *sReplacementText = NULL ); + + /** + * Replace a given node with a different node that is not currently owned by + * this XmlNode or any ancestor. + *@param nIndex The index of the node to replace. + *@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 ); + + /** + * Replace a given node with the children and content of a given node. + *@param nIndex The index of the node to replace. + *@param pNewNode The node that contains the children and content that will + * 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 ); + + /** + * 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(); - }; -} +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. */ + XmlNode *pParent; /**< A pointer to the parent of this node. */ + int nCurContent; /**< The current content we're on, for using the -1 on + setContent. */ +}; #endif diff --git a/src/xmlreader.cpp b/src/xmlreader.cpp index bd241cf..18df69c 100644 --- a/src/xmlreader.cpp +++ b/src/xmlreader.cpp @@ -1,82 +1,176 @@ #include "xmlreader.h" +#include "exceptions.h" +#include +#include "hashfunctionstring.h" -Bu::XmlReader::XmlReader( Bu::Stream &sIn ) : - sIn( sIn ) +XmlReader::XmlReader( bool bStrip ) : + bStrip( bStrip ), + htEntity( new HashFunctionString(), 11 ) { } -Bu::XmlReader::~XmlReader() +XmlReader::~XmlReader() { + void *i = htEntity.getFirstItemPos(); + while( (i = htEntity.getNextItemPos( i ) ) ) + { + free( (char *)(htEntity.getItemID( i )) ); + delete (StaticString *)htEntity.getItemData( i ); + } } -const char *Bu::XmlReader::lookahead( int nAmnt ) +void XmlReader::addEntity( const char *name, const char *value ) { - if( sBuf.getSize() >= nAmnt ) - return sBuf.getStr(); + if( htEntity[name] ) return; - int nNew = nAmnt - sBuf.getSize(); - char *buf = new char[nNew]; - sIn.read( buf, nNew ); - sBuf.append( buf ); + char *sName = strdup( name ); + StaticString *sValue = new StaticString( value ); - return sBuf.getStr(); + htEntity.insert( sName, sValue ); } -void Bu::XmlReader::burn( int nAmnt ) -{ - if( sBuf.getSize() < nAmnt ) - { - lookahead( nAmnt ); - } +#define gcall( x ) if( x == false ) return false; - //sBuf.remove( nAmnt ); +bool XmlReader::isws( char chr ) +{ + return ( chr == ' ' || chr == '\t' || chr == '\n' || chr == '\r' ); } -void Bu::XmlReader::checkString( const char *str, int nLen ) +bool XmlReader::ws() { - if( !strncmp( str, lookahead( nLen ), nLen ) ) + while( true ) { - burn( nLen ); - return; + char chr = getChar(); + if( isws( chr ) ) + { + usedChar(); + } + else + { + return true; + } } - - throw Bu::ExceptionBase("Expected string '%s'", str ); + return true; } -Bu::XmlNode *Bu::XmlReader::read() +bool XmlReader::buildDoc() { - prolog(); -} + // take care of initial whitespace + gcall( ws() ); + textDecl(); + entity(); + addEntity("gt", ">"); + addEntity("lt", "<"); + addEntity("amp", "&"); + addEntity("apos", "\'"); + addEntity("quot", "\""); + gcall( node() ); -void Bu::XmlReader::prolog() -{ - XMLDecl(); - Misc(); + return true; } -void Bu::XmlReader::XMLDecl() +void XmlReader::textDecl() { - checkString("", 2 ); + if( getChar() == '<' && getChar( 1 ) == '?' ) + { + usedChar( 2 ); + for(;;) + { + if( getChar() == '?' ) + { + if( getChar( 1 ) == '>' ) + { + usedChar( 2 ); + return; + } + } + usedChar(); + } + } } -void Bu::XmlReader::Misc() +void XmlReader::entity() { for(;;) { - S(); - if( !strncmp("", 3 ); - return; - } + closeNode(); + usedChar(); + } + else + { + throw XmlException("Close node in singleNode malformed!"); } - burn( 1 ); } + else + { + throw XmlException("Close node expected, but not found."); + return false; + } + + return true; } -void Bu::XmlReader::PI() +bool XmlReader::startNode() { - checkString("", lookahead(j+2)+j, 2 ) ) + usedChar(); + + if( getChar() == '/' ) { - burn( j+2 ); - return; + // Heh, it's actually a close node, go figure + FlexBuf fbName; + usedChar(); + gcall( ws() ); + + while( true ) + { + char chr = getChar(); + if( isws( chr ) || chr == '>' ) + { + // 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() ) ) + { + closeNode(); + break; + } + else + { + throw XmlException("Got a mismatched node close tag."); + } + } + else + { + fbName.appendData( chr ); + usedChar(); + } + } + + gcall( ws() ); + if( getChar() == '>' ) + { + // Everything is cool. + usedChar(); + } + else + { + throw XmlException("Got extra junk data instead of node close tag."); + } } + else + { + // We're good, format is consistant + addNode(); + + // Skip extra whitespace + gcall( ws() ); + gcall( name() ); + gcall( ws() ); + gcall( paramlist() ); + gcall( ws() ); + } + } + else + { + throw XmlException("Expected to find node opening char, '<'."); } + + return true; } -void Bu::XmlReader::S() +bool XmlReader::name() { - for( int j = 0;; j++ ) + FlexBuf fbName; + + while( true ) { - char c = *lookahead( 1 ); - if( c == 0x20 || c == 0x9 || c == 0xD || c == 0xA ) - continue; - if( j == 0 ) - throw ExceptionBase("Expected whitespace."); - return; + char chr = getChar(); + if( isws( chr ) || chr == '>' || chr == '/' ) + { + setName( fbName.getData() ); + return true; + } + else + { + fbName.appendData( chr ); + usedChar(); + } } + + return true; } -void Bu::XmlReader::Sq() +bool XmlReader::paramlist() { - for(;;) + while( true ) { - char c = *lookahead( 1 ); - if( c == 0x20 || c == 0x9 || c == 0xD || c == 0xA ) - continue; - return; + char chr = getChar(); + if( chr == '/' || chr == '>' ) + { + return true; + } + else + { + gcall( param() ); + gcall( ws() ); + } } + + return true; } -void Bu::XmlReader::VersionInfo() +StaticString *XmlReader::getEscape() { - try + if( getChar( 1 ) == '#' ) { - S(); - checkString("version", 7 ); + // If the entity starts with a # it's a character escape code + int base = 10; + usedChar( 2 ); + if( getChar() == 'x' ) + { + base = 16; + usedChar(); + } + char buf[4]; + int j = 0; + for( j = 0; getChar() != ';'; j++ ) + { + buf[j] = getChar(); + usedChar(); + } + usedChar(); + buf[j] = '\0'; + buf[0] = (char)strtol( buf, (char **)NULL, base ); + buf[1] = '\0'; + + return new StaticString( buf ); } - catch( ExceptionBase &e ) + else { - return; + // ...otherwise replace with the appropriate string... + std::string buf; + usedChar(); + for(;;) + { + char cbuf = getChar(); + usedChar(); + if( cbuf == ';' ) break; + buf += cbuf; + } + + StaticString *tmp = (StaticString *)htEntity[buf.c_str()]; + if( tmp == NULL ) return NULL; + + StaticString *ret = new StaticString( *tmp ); + return ret; } - Eq(); - Bu::FString ver = AttValue(); - if( ver != "1.1" ) - throw ExceptionBase("Currently we only support xml version 1.1\n"); } -void Bu::XmlReader::Eq() +bool XmlReader::param() { - Sq(); - checkString("=", 1 ); - Sq(); -} + FlexBuf fbName; + FlexBuf fbValue; -void Bu::XmlReader::EncodingDecl() -{ - S(); - try - { - checkString("encoding", 8 ); - } - catch( ExceptionBase &e ) + while( true ) { - return; + char chr = getChar(); + if( isws( chr ) || chr == '=' ) + { + break; + } + else + { + fbName.appendData( chr ); + usedChar(); + } } - Eq(); - AttValue(); -} + gcall( ws() ); -void Bu::XmlReader::SDDecl() -{ - S(); - try - { - checkString("standalone", 10 ); - } - catch( ExceptionBase &e ) + if( getChar() == '=' ) { - return; - } + usedChar(); - Eq(); - AttValue(); -} + gcall( ws() ); -Bu::FString Bu::XmlReader::AttValue() -{ - char q = *lookahead(1); - if( q == '\"' ) - { - for( int j = 2;; j++ ) + char chr = getChar(); + if( chr == '"' ) { - if( lookahead(j)[j-1] == '\"' ) + // Better quoted rhs + usedChar(); + + while( true ) { - Bu::FString ret( lookahead(j)+1, j-2 ); - burn( j ); - return ret; + chr = getChar(); + if( chr == '"' ) + { + usedChar(); + addProperty( fbName.getData(), fbValue.getData() ); + return true; + } + else + { + if( chr == '&' ) + { + StaticString *tmp = getEscape(); + if( tmp == NULL ) return false; + fbValue.appendData( tmp->getString() ); + delete tmp; + } + else + { + fbValue.appendData( chr ); + usedChar(); + } + } } } - } - else if( q == '\'' ) - { - for( int j = 2;; j++ ) + else { - if( lookahead(j)[j-1] == '\'' ) + // Simple one-word rhs + while( true ) { - Bu::FString ret( lookahead(j)+1, j-2 ); - burn( j ); - return ret; + chr = getChar(); + if( isws( chr ) || chr == '/' || chr == '>' ) + { + addProperty( fbName.getData(), fbValue.getData() ); + return true; + } + else + { + if( chr == '&' ) + { + StaticString *tmp = getEscape(); + if( tmp == NULL ) return false; + fbValue.appendData( tmp->getString() ); + delete tmp; + } + else + { + fbValue.appendData( chr ); + usedChar(); + } + } } } } + else + { + throw XmlException("Expected an equals to seperate the params."); + return false; + } - throw ExceptionBase("Excpected either \' or \".\n"); + return true; } -Bu::FString Bu::XmlReader::Name() +bool XmlReader::content() { - unsigned char c = *lookahead( 1 ); - if( c != ':' && c != '_' && - (c < 'A' || c > 'Z') && - (c < 'a' || c > 'z') && - (c < 0xC0 || c > 0xD6 ) && - (c < 0xD8 || c > 0xF6 ) && - (c < 0xF8)) - { - throw ExceptionBase("Invalid entity name starting character."); - } + FlexBuf fbContent; - for( int j = 1;; j++ ) + if( bStrip ) gcall( ws() ); + + while( true ) { - unsigned char c = lookahead(j+1)[j]; - if( isS( c ) ) + char chr = getChar(); + if( chr == '<' ) + { + if( getChar(1) == '/' ) + { + if( fbContent.getLength() > 0 ) + { + if( bStrip ) + { + int j; + for( j = fbContent.getLength()-1; isws(fbContent.getData()[j]); j-- ); + ((char *)fbContent.getData())[j+1] = '\0'; + } + setContent( fbContent.getData() ); + } + usedChar( 2 ); + gcall( ws() ); + FlexBuf fbName; + while( true ) + { + chr = getChar(); + if( isws( chr ) || chr == '>' ) + { + if( !strcasecmp( getCurrent()->getName(), fbName.getData() ) ) + { + closeNode(); + break; + } + else + { + throw XmlException("Mismatched close tag found: <%s> to <%s>.", getCurrent()->getName(), fbName.getData() ); + } + } + else + { + fbName.appendData( chr ); + usedChar(); + } + } + gcall( ws() ); + if( getChar() == '>' ) + { + usedChar(); + return true; + } + else + { + throw XmlException("Malformed close tag."); + } + } + else if( getChar(1) == '!' ) + { + // We know it's a comment, let's see if it's proper + if( getChar(2) != '-' || + getChar(3) != '-' ) + { + // Not a valid XML comment + throw XmlException("Malformed comment start tag found."); + } + + usedChar( 4 ); + + // Now burn text until we find the close tag + for(;;) + { + if( getChar() == '-' ) + { + if( getChar( 1 ) == '-' ) + { + // 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."); + } + usedChar( 3 ); + break; + } + else + { + // Found a dash followed by a non dash, that's ok... + usedChar( 2 ); + } + } + else + { + // Burn comment chars + usedChar(); + } + } + } + else + { + if( fbContent.getLength() > 0 ) + { + if( bStrip ) + { + int j; + for( j = fbContent.getLength()-1; isws(fbContent.getData()[j]); j-- ); + ((char *)fbContent.getData())[j+1] = '\0'; + } + setContent( fbContent.getData() ); + fbContent.clearData(); + } + gcall( node() ); + } + + if( bStrip ) gcall( ws() ); + } + else if( chr == '&' ) { - FString ret( lookahead(j+1), j+1 ); - burn( j+1 ); - return ret; + StaticString *tmp = getEscape(); + if( tmp == NULL ) return false; + fbContent.appendData( tmp->getString() ); + delete tmp; } - if( c != ':' && c != '_' && c != '-' && c != '.' && c != 0xB7 && - (c < 'A' || c > 'Z') && - (c < 'a' || c > 'z') && - (c < '0' || c > '9') && - (c < 0xC0 || c > 0xD6 ) && - (c < 0xD8 || c > 0xF6 ) && - (c < 0xF8)) + else { - throw ExceptionBase("Invalid character in name."); + fbContent.appendData( chr ); + usedChar(); } } } diff --git a/src/xmlreader.h b/src/xmlreader.h index 708a386..c8f7202 100644 --- a/src/xmlreader.h +++ b/src/xmlreader.h @@ -1,121 +1,141 @@ -#ifndef XML_READER_H -#define XML_READER_H +#ifndef XMLREADER +#define XMLREADER + +#include +#include "xmldocument.h" +#include "flexbuf.h" +#include "hashtable.h" +#include "staticstring.h" + +/** + * Takes care of reading in xml formatted data from a file. This could/should + * be made more arbitrary in the future so that we can read the data from any + * source. This is actually made quite simple already since all data read in + * is handled by one single helper function and then palced into a FlexBuf for + * easy access by the other functions. The FlexBuf also allows for block + * reading from disk, which improves speed by a noticable amount. + *
+ * There are also some extra features implemented that allow you to break the + * standard XML reader specs and eliminate leading and trailing whitespace in + * all read content. This is useful in situations where you allow additional + * whitespace in the files to make them easily human readable. The resturned + * content will be NULL in sitautions where all content between nodes was + * stripped. + *@author Mike Buland + */ +class XmlReader : public XmlDocument +{ +public: + /** + * Create a standard XmlReader. The optional parameter bStrip allows you to + * create a reader that will strip out all leading and trailing whitespace + * in content, a-la html. + *@param bStrip Strip out leading and trailing whitespace? + */ + XmlReader( bool bStrip=false ); -#include -#include "bu/stream.h" -#include "bu/fstring.h" -#include "bu/xmlnode.h" + /** + * Destroy this XmlReader. + */ + virtual ~XmlReader(); + + /** + * Build a document based on some kind of input. This is called + * automatically by the constructor. + */ + bool buildDoc(); + +private: + /** + * This is called by the low level automoton in order to get the next + * character. This function should return a character at the current + * position plus nIndex, but does not increment the current character. + *@param nIndex The index of the character from the current stream position. + *@returns A single character at the requested position, or 0 for end of + * stream. + */ + virtual char getChar( int nIndex = 0 ) = 0; + + /** + * Called to increment the current stream position by a single character. + */ + virtual void usedChar( int nAmnt = 1) = 0; + + /** + * Automoton function: is whitespace. + *@param chr A character + *@returns True if chr is whitespace, false otherwise. + */ + bool isws( char chr ); + + /** + * Automoton function: ws. Skips sections of whitespace. + *@returns True if everything was ok, False for end of stream. + */ + bool ws(); + + /** + * Automoton function: node. Processes an XmlNode + *@returns True if everything was ok, False for end of stream. + */ + bool node(); -namespace Bu -{ /** - * An Xml 1.1 reader. I've decided to write this, this time, based on the - * official W3C reccomendation, now included with the source code. I've - * named the productions in the parser states the same as in that document, - * which may make them easier to find, etc, although possibly slightly less - * optimized than writing my own reduced grammer. - * - * Below I will list differences between my parser and the official standard - * as I come up with them. - * - Encoding and Standalone headings are ignored for the moment. (4.3.3, - * 2.9) - * - The standalone heading attribute can have any standard whitespace - * before it (the specs say only spaces, no newlines). (2.9) - * - Since standalone is ignored, it is currently allowed to have any - * value (should be restricted to "yes" or "no"). (2.9) - * - Currently only UTF-8 / ascii are parsed. - * - [optional] The content of comments is thrown away. (2.5) - * - The content of processing instruction blocks is parsed properly, but - * thrown away. (2.6) - */ - 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, Includes Comments and PIData (Processing Instructions). - */ - void Misc(); - - /** - * Comments - */ - void Comment(); - - /** - * Processing Instructions - */ - void PI(); - - /** - * Whitespace eater. - */ - void S(); - - /** - * Optional whitespace eater. - */ - void Sq(); - - /** - * XML Version spec - */ - void VersionInfo(); - - /** - * Your basic equals sign with surrounding whitespace. - */ - void Eq(); - - /** - * Read in an attribute value. - */ - FString AttValue(); - - /** - * Read in the name of something. - */ - FString Name(); - - /** - * Encoding decleration in the header - */ - void EncodingDecl(); - - /** - * Standalone decleration in the header - */ - void SDDecl(); - - bool isS( unsigned char c ) - { - return ( c == 0x20 || c == 0x9 || c == 0xD || c == 0xA ); - } - }; -} + * Automoton function: startNode. Processes the begining of a node. + *@returns True if everything was ok, False for end of stream. + */ + bool startNode(); + + /** + * Automoton function: name. Processes the name of a node. + *@returns True if everything was ok, False for end of stream. + */ + bool name(); + + /** + * Automoton function: textDecl. Processes the xml text decleration, if + * there is one. + */ + void textDecl(); + + /** + * Automoton function: entity. Processes an entity from the header. + */ + void entity(); + + /** + * Adds an entity to the list, if it doesn't already exist. + *@param name The name of the entity + *@param value The value of the entity + */ + void addEntity( const char *name, const char *value ); + + StaticString *getEscape(); + + /** + * Automoton function: paramlist. Processes a list of node params. + *@returns True if everything was ok, False for end of stream. + */ + bool paramlist(); + + /** + * Automoton function: param. Processes a single parameter. + *@returns True if everything was ok, False for end of stream. + */ + bool param(); + + /** + * Automoton function: content. Processes node content. + *@returns True if everything was ok, False for end of stream. + */ + 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? */ + + HashTable htEntity; /**< Entity type definitions. */ +}; #endif diff --git a/src/xmlwriter.cpp b/src/xmlwriter.cpp index 23a5175..56880b6 100644 --- a/src/xmlwriter.cpp +++ b/src/xmlwriter.cpp @@ -1,9 +1,173 @@ +#include +#include #include "xmlwriter.h" -Bu::XmlWriter::XmlWriter() +XmlWriter::XmlWriter( const char *sIndent, XmlNode *pRoot ) : + XmlDocument( pRoot ) { + if( sIndent == NULL ) + { + this->sIndent = ""; + } + else + { + this->sIndent = sIndent; + } } -Bu::XmlWriter::~XmlWriter() +XmlWriter::~XmlWriter() { } + +void XmlWriter::write() +{ + write( getRoot(), sIndent.c_str() ); +} + +void XmlWriter::write( XmlNode *pRoot, const char *sIndent ) +{ + writeNode( pRoot, 0, sIndent ); +} + +void XmlWriter::closeNode() +{ + XmlDocument::closeNode(); + + if( isCompleted() ) + { + write( getRoot(), sIndent.c_str() ); + } +} + +void XmlWriter::writeIndent( int nIndent, const char *sIndent ) +{ + if( sIndent == NULL ) return; + for( int j = 0; j < nIndent; j++ ) + { + writeString( sIndent ); + } +} + +std::string XmlWriter::escape( std::string sIn ) +{ + std::string sOut; + + std::string::const_iterator i; + for( i = sIn.begin(); i != sIn.end(); i++ ) + { + if( ((*i >= ' ' && *i <= '9') || + (*i >= 'a' && *i <= 'z') || + (*i >= 'A' && *i <= 'Z') ) && + (*i != '\"' && *i != '\'' && *i != '&') + ) + { + sOut += *i; + } + else + { + sOut += "&#"; + char buf[4]; + sprintf( buf, "%u", (unsigned char)*i ); + sOut += buf; + sOut += ';'; + } + } + + return sOut; +} + +void XmlWriter::writeNodeProps( XmlNode *pNode, int nIndent, const char *sIndent ) +{ + for( int j = 0; j < pNode->getNumProperties(); j++ ) + { + writeString(" "); + writeString( pNode->getPropertyName( j ) ); + writeString("=\""); + writeString( escape( pNode->getProperty( j ) ).c_str() ); + writeString("\""); + } +} + +void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const char *sIndent ) +{ + if( pNode->hasChildren() ) + { + writeIndent( nIndent, sIndent ); + writeString("<"); + writeString( pNode->getName() ); + writeNodeProps( pNode, nIndent, sIndent ); + if( sIndent ) + writeString(">\n"); + else + writeString(">"); + + if( pNode->getContent( 0 ) ) + { + writeIndent( nIndent+1, sIndent ); + if( sIndent ) + { + writeString( pNode->getContent( 0 ) ); + writeString("\n"); + } + else + writeString( pNode->getContent( 0 ) ); + } + + int nNumChildren = pNode->getNumChildren(); + for( int j = 0; j < nNumChildren; j++ ) + { + writeNode( pNode->getChild( j ), nIndent+1, sIndent ); + if( pNode->getContent( j+1 ) ) + { + writeIndent( nIndent+1, sIndent ); + if( sIndent ) + { + writeString( pNode->getContent( j+1 ) ); + writeString("\n"); + } + else + writeString( pNode->getContent( j+1 ) ); + } + } + + writeIndent( nIndent, sIndent ); + if( sIndent ) + { + writeString("getName() ); + writeString(">\n"); + } + else + { + writeString("getName() ); + writeString(">"); + } + } + else if( pNode->getContent() ) + { + writeIndent( nIndent, sIndent ); + writeString("<"); + writeString( pNode->getName() ); + writeNodeProps( pNode, nIndent, sIndent ); + writeString(">"); + writeString( pNode->getContent() ); + writeString("getName() ); + writeString(">"); + if( sIndent ) + writeString("\n"); + } + else + { + writeIndent( nIndent, sIndent ); + writeString("<"); + writeString( pNode->getName() ); + writeNodeProps( pNode, nIndent, sIndent ); + if( sIndent ) + writeString("/>\n"); + else + writeString("/>"); + } +} + diff --git a/src/xmlwriter.h b/src/xmlwriter.h index 796d6fb..c48e810 100644 --- a/src/xmlwriter.h +++ b/src/xmlwriter.h @@ -1,22 +1,96 @@ -#ifndef XML_WRITER_H -#define XML_WRITER_H +#ifndef XMLWRITER +#define XMLWRITER -#include +#include "xmlnode.h" +#include "xmldocument.h" -namespace Bu +/** + * Implements xml writing in the XML standard format. Also allows you to + * break that format and auto-indent your exported xml data for ease of + * reading. The auto-indenting will only be applied to sections that + * have no content of their own already. This means that except for + * whitespace all of your data will be preserved perfectly. + * You can create an XmlWriter object around a file, or access the static + * write function directly and just hand it a filename and a root XmlNode. + * When using an XmlWriter object the interface is identicle to that of + * the XmlDocument class, so reference that class for API info. However + * when the initial (or root) node is closed, and the document is finished + * the file will be created and written to automatically. The user can + * check to see if this is actually true by calling the isFinished + * function in the XmlDocument class. + *@author Mike Buland + */ +class XmlWriter : public XmlDocument { +public: /** - * + * Construct a standard XmlWriter. + *@param sIndent Set this to something other than NULL to include it as an + * indent before each node in the output that doesn't already have content. + * If you are using the whitespace stripping option in the XmlReader and set + * this to a tab or some spaces it will never effect the content of your + * file. */ - class XmlWriter - { - public: - XmlWriter(); - virtual ~XmlWriter(); + XmlWriter( const char *sIndent=NULL, XmlNode *pRoot=NULL ); - private: + /** + * Destroy the writer. + */ + virtual ~XmlWriter(); + + /** + * This override of the parent class closeNode function calls the parent + * class, but also triggers a write operation when the final node is closed. + * This means that by checking the isCompleted() function the user may also + * check to see if their file has been written or not. + */ + void closeNode(); + + void write(); - }; -} +private: + std::string sIndent; /**< The indent string */ + + std::string escape( std::string sIn ); + + /** + * Write the file. + *@param pNode The root node + *@param sIndent The indent text. + */ + void write( XmlNode *pNode, const char *sIndent=NULL ); + + /** + * Write a node in the file, including children. + *@param pNode The node to write. + *@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 ); + + /** + * Write the properties of a node. + *@param pNode The node who's properties to write. + *@param nIndent The indent level of the containing node + *@param sIndent The indent text. + */ + void writeNodeProps( XmlNode *pNode, int nIndent, const char *sIndent ); + + /** + * Called to write the actual indent. + *@param nIndent The indent level. + *@param sIndent The indent text. + */ + void writeIndent( int nIndent, const char *sIndent ); + + /** + * This is the function that must be overridden in order to use this class. + * It must write the null-terminated string sString, minus the mull, + * verbatum to it's output device. Adding extra characters for any reason + * will break the XML formatting. + *@param sString The string data to write to the output. + */ + virtual void writeString( const char *sString ) = 0; +}; #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/xmlwriter.cpp') 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 4cb166570a8e2e97216bf6c7aeb99b971ff58ad7 Mon Sep 17 00:00:00 2001 From: Mike Buland Date: Tue, 12 Jun 2007 01:28:27 +0000 Subject: Moved out the xml system again. I think that if I am going to do it again, I'm going to do it over from scratch, that was just painful. Also, started in again on the server system, it's looking pretty good, already got connections working, next up is managing data flow through clients and protocols! --- src/client.cpp | 1 + src/file.cpp | 4 +- src/old/xmldocument.cpp | 145 ++++++++++++ src/old/xmldocument.h | 165 +++++++++++++ src/old/xmlnode.cpp | 403 ++++++++++++++++++++++++++++++++ src/old/xmlnode.h | 207 +++++++++++++++++ src/old/xmlreader.cpp | 604 ++++++++++++++++++++++++++++++++++++++++++++++++ src/old/xmlreader.h | 144 ++++++++++++ src/old/xmlwriter.cpp | 167 +++++++++++++ src/old/xmlwriter.h | 96 ++++++++ src/server.cpp | 7 +- src/server.h | 9 +- src/serversocket.cpp | 5 + src/serversocket.h | 1 + src/xmldocument.cpp | 145 ------------ src/xmldocument.h | 165 ------------- src/xmlnode.cpp | 403 -------------------------------- src/xmlnode.h | 207 ----------------- src/xmlreader.cpp | 604 ------------------------------------------------ src/xmlreader.h | 144 ------------ src/xmlwriter.cpp | 167 ------------- src/xmlwriter.h | 96 -------- 22 files changed, 1953 insertions(+), 1936 deletions(-) create mode 100644 src/old/xmldocument.cpp create mode 100644 src/old/xmldocument.h create mode 100644 src/old/xmlnode.cpp create mode 100644 src/old/xmlnode.h create mode 100644 src/old/xmlreader.cpp create mode 100644 src/old/xmlreader.h create mode 100644 src/old/xmlwriter.cpp create mode 100644 src/old/xmlwriter.h delete mode 100644 src/xmldocument.cpp delete mode 100644 src/xmldocument.h delete mode 100644 src/xmlnode.cpp delete mode 100644 src/xmlnode.h delete mode 100644 src/xmlreader.cpp delete mode 100644 src/xmlreader.h delete mode 100644 src/xmlwriter.cpp delete mode 100644 src/xmlwriter.h (limited to 'src/xmlwriter.cpp') diff --git a/src/client.cpp b/src/client.cpp index a048ca3..a33cdc3 100644 --- a/src/client.cpp +++ b/src/client.cpp @@ -7,3 +7,4 @@ Bu::Client::Client() Bu::Client::~Client() { } + diff --git a/src/file.cpp b/src/file.cpp index 14b6e54..2965afa 100644 --- a/src/file.cpp +++ b/src/file.cpp @@ -48,8 +48,8 @@ size_t Bu::File::read( void *pBuf, size_t nBytes ) int nAmnt = fread( pBuf, 1, nBytes, fh ); - if( nAmnt == 0 ) - throw FileException("End of file."); + //if( nAmnt == 0 ) + // throw FileException("End of file."); return nAmnt; } diff --git a/src/old/xmldocument.cpp b/src/old/xmldocument.cpp new file mode 100644 index 0000000..95b9788 --- /dev/null +++ b/src/old/xmldocument.cpp @@ -0,0 +1,145 @@ +#include +#include +#include "xmldocument.h" + +XmlDocument::XmlDocument( XmlNode *pRoot ) +{ + this->pRoot = pRoot; + pCurrent = NULL; + bCompleted = (pRoot!=NULL); +} + +XmlDocument::~XmlDocument() +{ + if( pRoot ) + { + delete pRoot; + } +} + +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 ); + } + else + { + pCurrent = pCurrent->addChild( sName ); + } +} +/* +void XmlDocument::setName( const char *sName ) +{ + pCurrent->setName( sName ); +}*/ + +bool XmlDocument::isCompleted() +{ + return bCompleted; +} + +XmlNode *XmlDocument::getRoot() +{ + return pRoot; +} + +XmlNode *XmlDocument::detatchRoot() +{ + XmlNode *pTemp = pRoot; + pRoot = NULL; + return pTemp; +} + +XmlNode *XmlDocument::getCurrent() +{ + return pCurrent; +} + +void XmlDocument::closeNode() +{ + if( pCurrent != NULL ) + { + pCurrent = pCurrent->getParent(); + + if( pCurrent == NULL ) + { + bCompleted = true; + } + } +} + +void XmlDocument::addProperty( const char *sName, const char *sValue ) +{ + if( pCurrent ) + { + pCurrent->addProperty( sName, sValue ); + } +} + +void XmlDocument::addProperty( const char *sName, const unsigned char nValue ) +{ + char buf[12]; + sprintf( buf, "%hhi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const char nValue ) +{ + char buf[12]; + sprintf( buf, "%hhi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const unsigned short nValue ) +{ + char buf[12]; + sprintf( buf, "%hi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const short nValue ) +{ + char buf[12]; + sprintf( buf, "%hi", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const int nValue ) +{ + char buf[12]; + sprintf( buf, "%d", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const unsigned long nValue ) +{ + char buf[12]; + sprintf( buf, "%li", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const long nValue ) +{ + char buf[12]; + sprintf( buf, "%li", nValue ); + addProperty( sName, buf ); +} + +void XmlDocument::addProperty( const char *sName, const double dValue ) +{ + char buf[40]; + sprintf( buf, "%f", dValue ); + addProperty( sName, buf ); +} + +void XmlDocument::setContent( const char *sContent ) +{ + if( pCurrent ) + { + printf("XmlDocument::setContent: not yet implemented.\n"); + //pCurrent->setContent( sContent ); + } +} + diff --git a/src/old/xmldocument.h b/src/old/xmldocument.h new file mode 100644 index 0000000..e0c36eb --- /dev/null +++ b/src/old/xmldocument.h @@ -0,0 +1,165 @@ +#ifndef XMLDOCUMENT +#define XMLDOCUMENT + +#include "xmlnode.h" + +/** + * Keeps track of an easily managed set of XmlNode information. Allows simple + * operations for logical writing to and reading from XML structures. Using + * already formed structures is simply done through the XmlNode structures, + * and the getRoot function here. Creation is performed through a simple set + * of operations that creates the data in a stream type format. + *@author Mike Buland + */ +class XmlDocument +{ +public: + /** + * Construct either a blank XmlDocuemnt or construct a document around an + * existing XmlNode. Be careful, once an XmlNode is passed into a document + * the document takes over ownership and will delete it when the XmlDocument + * is deleted. + *@param pRoot The XmlNode to use as the root of this document, or NULL if + * you want to start a new document. + */ + XmlDocument( XmlNode *pRoot=NULL ); + + /** + * Destroy all contained nodes. + */ + virtual ~XmlDocument(); + + /** + * Add a new node to the document. The new node is appended to the end of + * the current context, i.e. XmlNode, and the new node, provided it isn't + * close as part of this operation, will become the current context. + *@param sName The name of the new node to add. + *@param sContent A content string to be placed inside of the new node. + *@param bClose Set this to true to close the node immediately after adding + * 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 Bu::FString &sName ); + + /** + * Close the current node context. This will move the current context to + * the parent node of the former current node. If the current node was the + * root then the "completed" flag is set and no more operations are allowed. + */ + void closeNode(); + + /** + * Change the content of the current node at the current position between + * nodes. + *@param sContent The new content of the current node. + */ + void setContent( const char *sContent ); + + /** + * Add a named property to the current context node. + *@param sName The name of the property to add. + *@param sValue The string value of the property. + */ + void addProperty( const char *sName, const char *sValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const unsigned char nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const char nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const unsigned short nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const short nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const unsigned long nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const long nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param nValue The numerical value to add. + */ + void addProperty( const char *sName, const int nValue ); + + /** + * Add a named property to the current context node, converting the + * numerical parameter to text using standrd printf style conversion. + *@param sName The name of the property to add. + *@param dValue The numerical value to add. + */ + void addProperty( const char *sName, const double dValue ); + + /** + * The XmlDocuemnt is considered completed if the root node has been closed. + * Once an XmlDocument has been completed, you can no longer perform + * operations on it. + *@return True if completed, false if still in progress. + */ + bool isCompleted(); + + /** + * Get a pointer to the root object of this XmlDocument. + *@returns A pointer to an internally owned XmlNode. Do not delete this + * XmlNode. + */ + XmlNode *getRoot(); + + /** + * Get a pointer to the root object of this XmlDocument, and remove the + * ownership from this object. + *@returns A pointer to an internally owned XmlNode. Do not delete this + * XmlNode. + */ + XmlNode *detatchRoot(); + + /** + * Get the current context node, which could be the same as the root node. + *@returns A pointer to an internally owned XmlNode. Do not delete this + * XmlNode. + */ + XmlNode *getCurrent(); + +private: + XmlNode *pRoot; /**< The root node. */ + XmlNode *pCurrent; /**< The current node. */ + bool bCompleted; /**< Is it completed? */ +}; + +#endif diff --git a/src/old/xmlnode.cpp b/src/old/xmlnode.cpp new file mode 100644 index 0000000..96d5850 --- /dev/null +++ b/src/old/xmlnode.cpp @@ -0,0 +1,403 @@ +#include "xmlnode.h" + +XmlNode::XmlNode( const Bu::FString &sName, XmlNode *pParent ) : + sName( sName ), + pParent( pParent ) +{ +} + +XmlNode::~XmlNode() +{ +} +/* +void XmlNode::setName( const char *sName ) +{ + if( pParent ) + { + if( this->sName.size() == 0 ) + { + // We're not in the hash yet, so add us + this->sName = sName; + pParent->hChildren.insert( this->sName.c_str(), this ); + } + else + { + // Slightly more tricky, delete us, then add us... + pParent->hChildren.del( this->sName.c_str() ); + this->sName = sName; + pParent->hChildren.insert( this->sName.c_str(), this ); + } + } + else + { + // If we have no parent, then just set the name string, we don't need + // to worry about hashing. + this->sName = sName; + } +} + +void XmlNode::setContent( const char *sContent, int nIndex ) +{ + if( nIndex == -1 ) + { + nIndex = nCurContent; + } + if( nIndex == 0 ) + { + if( this->sPreContent ) + { + delete this->sPreContent; + } + + this->sPreContent = new std::string( sContent ); + } + else + { + nIndex--; + if( lPostContent[nIndex] ) + { + delete (std::string *)lPostContent[nIndex]; + } + + lPostContent.setAt( nIndex, new std::string( sContent ) ); + } +} + +const char *XmlNode::getContent( int nIndex ) +{ + if( nIndex == 0 ) + { + if( sPreContent ) + { + return sPreContent->c_str(); + } + } + else + { + nIndex--; + if( lPostContent[nIndex] ) + { + return ((std::string *)lPostContent[nIndex])->c_str(); + } + } + + return NULL; +}*/ + +XmlNode *XmlNode::addChild( const Bu::FString &sName ) +{ + return addChild( new XmlNode( sName, this ) ); +} + +XmlNode *XmlNode::addChild( XmlNode *pNode ) +{ + Child c = { typeNode }; + c.pNode = pNode; + lChildren.append( c ); + pNode->pParent = this; + + return pNode; +} + +XmlNode *XmlNode::getParent() +{ + return pParent; +} + +void XmlNode::addProperty( const Bu::FString &sName, const Bu::FString &sValue ) +{ + hProperties.insert( sName, sValue ); +} + +int XmlNode::getNumProperties() +{ + return hProperties.size(); +} +/* +const char *XmlNode::getPropertyName( int nIndex ) +{ + std::string *tmp = ((std::string *)lPropNames[nIndex]); + if( tmp == NULL ) + return NULL; + return tmp->c_str(); +} + +const char *XmlNode::getProperty( int nIndex ) +{ + std::string *tmp = ((std::string *)lPropValues[nIndex]); + if( tmp == NULL ) + return NULL; + return tmp->c_str(); +} +*/ +Bu::FString XmlNode::getProperty( const Bu::FString &sName ) +{ + return hProperties[sName]; +} +/* +void XmlNode::deleteProperty( int nIndex ) +{ + hProperties.del( ((std::string *)lPropNames[nIndex])->c_str() ); + + delete (std::string *)lPropNames[nIndex]; + delete (std::string *)lPropValues[nIndex]; + + lPropNames.deleteAt( nIndex ); + lPropValues.deleteAt( nIndex ); +} + +bool XmlNode::hasChildren() +{ + return hChildren.getSize()>0; +}*/ + +int XmlNode::getNumChildren() +{ + return lChildren.getSize(); +} +/* +XmlNode *XmlNode::getChild( int nIndex ) +{ + return (XmlNode *)lChildren[nIndex]; +} +*/ +XmlNode *XmlNode::getChild( const Bu::FString &sName, int nSkip ) +{ + if( !hChildren.has( sName ) ) + return NULL; + + Bu::List::iterator i = hChildren[sName]->begin(); + return *i; +} + +Bu::FString XmlNode::getName() +{ + return sName; +} +/* +void XmlNode::deleteNode( int nIndex, const char *sReplacementText ) +{ + XmlNode *xRet = detatchNode( nIndex, sReplacementText ); + + if( xRet != NULL ) + { + delete xRet; + } +} + +XmlNode *XmlNode::detatchNode( int nIndex, const char *sReplacementText ) +{ + if( nIndex < 0 || nIndex >= lChildren.getSize() ) + return NULL; + + // The real trick when deleteing a node isn't actually deleting it, it's + // reforming the content around the node that's now missing...hmmm... + + if( nIndex == 0 ) + { + // If the index is zero we have to deal with the pre-content + if( sReplacementText ) + { + if( sPreContent == NULL ) + { + sPreContent = new std::string( sReplacementText ); + } + else + { + *sPreContent += sReplacementText; + } + } + if( lPostContent.getSize() > 0 ) + { + if( lPostContent[0] != NULL ) + { + if( sPreContent == NULL ) + { + sPreContent = new std::string( + ((std::string *)lPostContent[0])->c_str() + ); + } + else + { + *sPreContent += + ((std::string *)lPostContent[0])->c_str(); + } + } + delete (std::string *)lPostContent[0]; + lPostContent.deleteAt( 0 ); + } + } + else + { + int nCont = nIndex-1; + // If it's above zero we deal with the post-content only + if( sReplacementText ) + { + if( lPostContent[nCont] == NULL ) + { + lPostContent.setAt( nCont, new std::string( sReplacementText ) ); + } + else + { + *((std::string *)lPostContent[nCont]) += sReplacementText; + } + } + if( lPostContent.getSize() > nIndex ) + { + if( lPostContent[nIndex] != NULL ) + { + if( lPostContent[nCont] == NULL ) + { + lPostContent.setAt( nCont, new std::string( + ((std::string *)lPostContent[nIndex])->c_str() + ) ); + } + else + { + *((std::string *)lPostContent[nCont]) += + ((std::string *)lPostContent[nIndex])->c_str(); + } + } + delete (std::string *)lPostContent[nIndex]; + lPostContent.deleteAt( nIndex ); + } + } + + XmlNode *xRet = (XmlNode *)lChildren[nIndex]; + hChildren.del( ((XmlNode *)lChildren[nIndex])->getName() ); + lChildren.deleteAt( nIndex ); + + return xRet; +} + +void XmlNode::replaceNode( int nIndex, XmlNode *pNewNode ) +{ + if( nIndex < 0 || nIndex >= lChildren.getSize() ) + return; //TODO: throw an exception + + delete (XmlNode *)lChildren[nIndex]; + lChildren.setAt( nIndex, pNewNode ); + pNewNode->pParent = this; +} + +XmlNode *XmlNode::getCopy() +{ + XmlNode *pNew = new XmlNode(); + + pNew->sName = sName; + if( sPreContent ) + { + pNew->sPreContent = new std::string( sPreContent->c_str() ); + } + else + { + pNew->sPreContent = NULL; + } + pNew->nCurContent = 0; + + int nSize = lPostContent.getSize(); + pNew->lPostContent.setSize( nSize ); + for( int j = 0; j < nSize; j++ ) + { + if( lPostContent[j] ) + { + pNew->lPostContent.setAt( + j, new std::string( + ((std::string *)lPostContent[j])->c_str() + ) + ); + } + else + { + pNew->lPostContent.setAt( j, NULL ); + } + } + + nSize = lChildren.getSize(); + pNew->lChildren.setSize( nSize ); + for( int j = 0; j < nSize; j++ ) + { + XmlNode *pChild = ((XmlNode *)lChildren[j])->getCopy(); + pNew->lChildren.setAt( j, pChild ); + pChild->pParent = pNew; + pNew->hChildren.insert( pChild->getName(), pChild ); + } + + nSize = lPropNames.getSize(); + pNew->lPropNames.setSize( nSize ); + pNew->lPropValues.setSize( nSize ); + for( int j = 0; j < nSize; j++ ) + { + std::string *pProp = new std::string( ((std::string *)lPropNames[j])->c_str() ); + std::string *pVal = new std::string( ((std::string *)lPropValues[j])->c_str() ); + pNew->lPropNames.setAt( j, pProp ); + pNew->lPropValues.setAt( j, pVal ); + pNew->hProperties.insert( pProp->c_str(), pVal->c_str() ); + pNew->nCurContent++; + } + + return pNew; +} + +void XmlNode::deleteNodeKeepChildren( int nIndex ) +{ + // This is a tricky one...we need to do some patching to keep things all + // even... + XmlNode *xRet = (XmlNode *)lChildren[nIndex]; + + if( xRet == NULL ) + { + return; + } + else + { + if( getContent( nIndex ) ) + { + std::string sBuf( getContent( nIndex ) ); + sBuf += xRet->getContent( 0 ); + setContent( sBuf.c_str(), nIndex ); + } + else + { + setContent( xRet->getContent( 0 ), nIndex ); + } + + int nSize = xRet->lChildren.getSize(); + for( int j = 0; j < nSize; j++ ) + { + XmlNode *pCopy = ((XmlNode *)xRet->lChildren[j])->getCopy(); + pCopy->pParent = this; + lChildren.insertBefore( pCopy, nIndex+j ); + + if( xRet->lPostContent[j] ) + { + lPostContent.insertBefore( + new std::string( ((std::string *)xRet->lPostContent[j])->c_str() ), + nIndex+j + ); + } + else + { + lPostContent.insertBefore( NULL, nIndex+j ); + } + } + + if( getContent( nIndex+nSize ) ) + { + //SString sBuf( getContent( nIndex+nSize ) ); + //sBuf.catfrom( xRet->getContent( nSize ) ); + //setContent( sBuf, nIndex+nSize ); + } + else + { + setContent( xRet->getContent( nSize ), nIndex+nSize ); + } + + deleteNode( nIndex+nSize ); + } +} + +void XmlNode::replaceNodeWithChildren( int nIndex, XmlNode *pNewNode ) +{ +} +*/ diff --git a/src/old/xmlnode.h b/src/old/xmlnode.h new file mode 100644 index 0000000..c895cd8 --- /dev/null +++ b/src/old/xmlnode.h @@ -0,0 +1,207 @@ +#ifndef XMLNODE +#define XMLNODE + +#include +#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. + * All child nodes can be accessed through index and through name via a hash + * table. This makes it very easy to gain simple and fast access to all of + * your data. For most applications, the memory footprint is also rather + * small. While XmlNode objects can be used directly to create XML structures + * it is highly reccomended that all operations be performed through the + * XmlDocument class. + *@author Mike Buland + */ +class XmlNode +{ +public: + /** + * Construct a new XmlNode. + *@param sName The name of the node. + *@param pParent The parent node. + *@param sContent The initial content string. + */ + XmlNode( + const Bu::FString &sName, + XmlNode *pParent=NULL + ); + + /** + * Delete the node and cleanup all memory. + */ + virtual ~XmlNode(); + + /** + * Change the name of the node. + *@param sName The new name of the node. + */ + //void setName( const char *sName ); + + /** + * Construct a new node and add it as a child to this node, also return a + * pointer to the newly constructed node. + *@param sName The name of the new node. + *@param sContent The initial content of the new node. + *@returns A pointer to the newly created child node. + */ + XmlNode *addChild( const Bu::FString &sName ); + + /** + * Add an already created XmlNode as a child to this node. The new child + * XmlNode's parent will be changed appropriately and the parent XmlNode + * will take ownership of the child. + *@param pChild The child XmlNode to add to this XmlNode. + *@returns A pointer to the child node that was just added. + */ + XmlNode *addChild( XmlNode *pChild ); + + /** + * Add a new property to the XmlNode. Properties are name/value pairs. + *@param sName The name of the property. Specifying a name that's already + * in use will overwrite that property. + *@param sValue The textual value of the property. + */ + void addProperty( const Bu::FString &sName, const Bu::FString &sValue ); + + /** + * Get a pointer to the parent node, if any. + *@returns A pointer to the node's parent, or NULL if there isn't one. + */ + XmlNode *getParent(); + + /** + * Tells you if this node has children. + *@returns True if this node has at least one child, false otherwise. + */ + bool hasChildren(); + + /** + * Tells you how many children this node has. + *@returns The number of children this node has. + */ + int getNumChildren(); + + /** + * Get a child with the specified name, and possibly skip value. For an + * explination of skip values see the HashTable. + *@param sName The name of the child to find. + *@param nSkip The number of nodes with that name to skip. + *@returns A pointer to the child, or NULL if no child with that name was + * found. + */ + 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. + */ + Bu::FString getName(); + + /** + * Set the content of this node, optionally at a specific index. Using the + * default of -1 will set the content after the last added node. + *@param sContent The content string to use. + *@param nIndex The index of the content. + */ + //void setContent( const char *sContent, int nIndex=-1 ); + + /** + * Get the number of properties in this node. + *@returns The number of properties in this node. + */ + int getNumProperties(); + + /** + * 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. + */ + Bu::FString getProperty( const Bu::FString &sName ); + + /** + * Delete a child node, possibly replacing it with some text. This actually + * fixes all content strings around the newly deleted child node. + *@param nIndex The index of the node to delete. + *@param sReplacementText The optional text to replace the node with. + *@returns True of the node was found, and deleted, false if it wasn't + * found. + */ + //void deleteNode( int nIndex, const char *sReplacementText = NULL ); + + /** + * Delete a given node, but move all of it's children and content up to + * replace the deleted node. All of the content of the child node is + * spliced seamlessly into place with the parent node's content. + *@param nIndex The node to delete. + *@returns True if the node was found and deleted, false if it wasn't. + */ + //void deleteNodeKeepChildren( int nIndex ); + + /** + * Detatch a given child node from this node. This effectively works just + * like a deleteNode, except that instead of deleting the node it is removed + * and returned, and all ownership is given up. + *@param nIndex The index of the node to detatch. + *@param sReplacementText The optional text to replace the detatched node + * with. + *@returns A pointer to the newly detatched node, which then passes + * ownership to the caller. + */ + //XmlNode *detatchNode( int nIndex, const char *sReplacementText = NULL ); + + /** + * Replace a given node with a different node that is not currently owned by + * this XmlNode or any ancestor. + *@param nIndex The index of the node to replace. + *@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 ); + + /** + * Replace a given node with the children and content of a given node. + *@param nIndex The index of the node to replace. + *@param pNewNode The node that contains the children and content that will + * 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 ); + + /** + * 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(); + + enum ChildType + { + typeNode, + typeContent + }; + +private: + 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. */ +}; + +#endif diff --git a/src/old/xmlreader.cpp b/src/old/xmlreader.cpp new file mode 100644 index 0000000..38cad5f --- /dev/null +++ b/src/old/xmlreader.cpp @@ -0,0 +1,604 @@ +#include "bu/xmlreader.h" +#include "bu/exceptions.h" +#include + +XmlReader::XmlReader( Bu::Stream &sIn, bool bStrip ) : + sIn( sIn ), + bStrip( bStrip ) +{ + buildDoc(); +} + +XmlReader::~XmlReader() +{ +} + +char XmlReader::getChar( int nIndex ) +{ + if( sBuf.getSize() <= nIndex ) + { + 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::usedChar( int nAmnt ) +{ + if( nAmnt >= sBuf.getSize() ) + { + sBuf.clear(); + } + else + { + char *s = sBuf.getStr(); + memcpy( s, s+nAmnt, sBuf.getSize()-nAmnt ); + sBuf.resize( sBuf.getSize()-nAmnt ); + } +} + +void XmlReader::addEntity( const Bu::FString &name, const Bu::FString &value ) +{ + htEntity[name] = value; +} + +#define gcall( x ) if( x == false ) return false; + +bool XmlReader::isws( char chr ) +{ + return ( chr == ' ' || chr == '\t' || chr == '\n' || chr == '\r' ); +} + +bool XmlReader::ws() +{ + while( true ) + { + char chr = getChar(); + if( isws( chr ) ) + { + usedChar(); + } + else + { + return true; + } + } + return true; +} + +bool XmlReader::buildDoc() +{ + // take care of initial whitespace + gcall( ws() ); + textDecl(); + entity(); + addEntity("gt", ">"); + addEntity("lt", "<"); + addEntity("amp", "&"); + addEntity("apos", "\'"); + addEntity("quot", "\""); + gcall( node() ); + + return true; +} + +void XmlReader::textDecl() +{ + if( getChar() == '<' && getChar( 1 ) == '?' ) + { + usedChar( 2 ); + for(;;) + { + if( getChar() == '?' ) + { + if( getChar( 1 ) == '>' ) + { + usedChar( 2 ); + return; + } + } + usedChar(); + } + } +} + +void XmlReader::entity() +{ + for(;;) + { + ws(); + + if( getChar() == '<' && getChar( 1 ) == '!' ) + { + usedChar( 2 ); + ws(); + Bu::FString buf; + for(;;) + { + char chr = getChar(); + usedChar(); + if( isws( chr ) ) break; + buf += chr; + } + + if( strcmp( buf.c_str(), "ENTITY") == 0 ) + { + ws(); + Bu::FString name; + for(;;) + { + char chr = getChar(); + usedChar(); + if( isws( chr ) ) break; + name += chr; + } + ws(); + char quot = getChar(); + usedChar(); + if( quot != '\'' && quot != '\"' ) + { + throw Bu::XmlException( + "Only quoted entity values are supported." + ); + } + Bu::FString value; + for(;;) + { + char chr = getChar(); + usedChar(); + if( chr == '&' ) + { + Bu::FString tmp = getEscape(); + value += tmp; + } + else if( chr == quot ) + { + break; + } + else + { + value += chr; + } + } + ws(); + if( getChar() == '>' ) + { + usedChar(); + + addEntity( name.c_str(), value.c_str() ); + } + else + { + throw Bu::XmlException( + "Malformed ENTITY: unexpected '%c' found.", + getChar() + ); + } + } + else + { + throw Bu::XmlException( + "Unsupported header symbol: %s", + buf.c_str() + ); + } + } + else + { + return; + } + } +} + +bool XmlReader::node() +{ + gcall( startNode() ) + + // At this point, we are closing the startNode + char chr = getChar(); + if( chr == '>' ) + { + usedChar(); + + // Now we process the guts of the node. + gcall( content() ); + } + else if( chr == '/' ) + { + // This is the tricky one, one more validation, then we close the node. + usedChar(); + if( getChar() == '>' ) + { + closeNode(); + usedChar(); + } + else + { + throw Bu::XmlException("Close node in singleNode malformed!"); + } + } + else + { + throw Bu::XmlException("Close node expected, but not found."); + return false; + } + + return true; +} + +bool XmlReader::startNode() +{ + if( getChar() == '<' ) + { + usedChar(); + + if( getChar() == '/' ) + { + // Heh, it's actually a close node, go figure + Bu::FString sName; + usedChar(); + gcall( ws() ); + + while( true ) + { + char chr = getChar(); + if( isws( chr ) || chr == '>' ) + { + // Here we actually compare the name we got to the name + // we already set, they have to match exactly. + if( getCurrent()->getName() == sName ) + { + closeNode(); + break; + } + else + { + throw Bu::XmlException("Got a mismatched node close tag."); + } + } + else + { + sName += chr; + usedChar(); + } + } + + gcall( ws() ); + if( getChar() == '>' ) + { + // Everything is cool. + usedChar(); + } + else + { + throw Bu::XmlException("Got extra junk data instead of node close tag."); + } + } + else + { + // We're good, format is consistant + //addNode(); + + // Skip extra whitespace + gcall( ws() ); + gcall( name() ); + gcall( ws() ); + gcall( paramlist() ); + gcall( ws() ); + } + } + else + { + throw Bu::XmlException("Expected to find node opening char, '<'."); + } + + return true; +} + +bool XmlReader::name() +{ + Bu::FString sName; + + while( true ) + { + char chr = getChar(); + if( isws( chr ) || chr == '>' || chr == '/' ) + { + addNode( sName ); + return true; + } + else + { + sName += chr; + usedChar(); + } + } + + return true; +} + +bool XmlReader::paramlist() +{ + while( true ) + { + char chr = getChar(); + if( chr == '/' || chr == '>' ) + { + return true; + } + else + { + gcall( param() ); + gcall( ws() ); + } + } + + return true; +} + +Bu::FString XmlReader::getEscape() +{ + if( getChar( 1 ) == '#' ) + { + // If the entity starts with a # it's a character escape code + int base = 10; + usedChar( 2 ); + if( getChar() == 'x' ) + { + base = 16; + usedChar(); + } + char buf[4]; + int j = 0; + for( j = 0; getChar() != ';'; j++ ) + { + buf[j] = getChar(); + usedChar(); + } + usedChar(); + buf[j] = '\0'; + buf[0] = (char)strtol( buf, (char **)NULL, base ); + buf[1] = '\0'; + + return buf; + } + else + { + // ...otherwise replace with the appropriate string... + Bu::FString buf; + usedChar(); + for(;;) + { + char cbuf = getChar(); + usedChar(); + if( cbuf == ';' ) break; + buf += cbuf; + } + + return htEntity[buf]; + } +} + +bool XmlReader::param() +{ + Bu::FString sName; + Bu::FString sValue; + + while( true ) + { + char chr = getChar(); + if( isws( chr ) || chr == '=' ) + { + break; + } + else + { + sName.append( chr ); + usedChar(); + } + } + + gcall( ws() ); + + if( getChar() == '=' ) + { + usedChar(); + + gcall( ws() ); + + char chr = getChar(); + if( chr == '"' ) + { + // Better quoted rhs + usedChar(); + + while( true ) + { + chr = getChar(); + if( chr == '"' ) + { + usedChar(); + addProperty( sName.getStr(), sValue.getStr() ); + return true; + } + else + { + if( chr == '&' ) + { + sValue += getEscape(); + } + else + { + sValue += chr; + usedChar(); + } + } + } + } + else + { + // Simple one-word rhs + while( true ) + { + chr = getChar(); + if( isws( chr ) || chr == '/' || chr == '>' ) + { + addProperty( sName.getStr(), sValue.getStr() ); + return true; + } + else + { + if( chr == '&' ) + { + sValue += getEscape(); + } + else + { + sValue += chr; + usedChar(); + } + } + } + } + } + else + { + throw Bu::XmlException("Expected an equals to seperate the params."); + return false; + } + + return true; +} + +bool XmlReader::content() +{ + Bu::FString sContent; + + if( bStrip ) gcall( ws() ); + + while( true ) + { + char chr = getChar(); + if( chr == '<' ) + { + if( getChar(1) == '/' ) + { + if( sContent.getSize() > 0 ) + { + if( bStrip ) + { + int j; + for( j = sContent.getSize()-1; isws(sContent[j]); j-- ); + sContent[j+1] = '\0'; + } + setContent( sContent.getStr() ); + } + usedChar( 2 ); + gcall( ws() ); + Bu::FString sName; + while( true ) + { + chr = getChar(); + if( isws( chr ) || chr == '>' ) + { + if( !strcasecmp( getCurrent()->getName().getStr(), sName.getStr() ) ) + { + closeNode(); + break; + } + else + { + throw Bu::XmlException("Mismatched close tag found: <%s> to <%s>.", getCurrent()->getName().getStr(), sName.getStr() ); + } + } + else + { + sName += chr; + usedChar(); + } + } + gcall( ws() ); + if( getChar() == '>' ) + { + usedChar(); + return true; + } + else + { + throw Bu::XmlException("Malformed close tag."); + } + } + else if( getChar(1) == '!' ) + { + // We know it's a comment, let's see if it's proper + if( getChar(2) != '-' || + getChar(3) != '-' ) + { + // Not a valid XML comment + throw Bu::XmlException("Malformed comment start tag found."); + } + + usedChar( 4 ); + + // Now burn text until we find the close tag + for(;;) + { + if( getChar() == '-' ) + { + if( getChar( 1 ) == '-' ) + { + // The next one has to be a '>' now + if( getChar( 2 ) != '>' ) + { + throw Bu::XmlException("Malformed comment close tag found. You cannot have a '--' that isn't followed by a '>' in a comment."); + } + usedChar( 3 ); + break; + } + else + { + // Found a dash followed by a non dash, that's ok... + usedChar( 2 ); + } + } + else + { + // Burn comment chars + usedChar(); + } + } + } + else + { + if( sContent.getSize() > 0 ) + { + if( bStrip ) + { + int j; + for( j = sContent.getSize()-1; isws(sContent[j]); j-- ); + sContent[j+1] = '\0'; + } + setContent( sContent.getStr() ); + sContent.clear(); + } + gcall( node() ); + } + + if( bStrip ) gcall( ws() ); + } + else if( chr == '&' ) + { + sContent += getEscape(); + } + else + { + sContent += chr; + usedChar(); + } + } +} + diff --git a/src/old/xmlreader.h b/src/old/xmlreader.h new file mode 100644 index 0000000..7c85ddb --- /dev/null +++ b/src/old/xmlreader.h @@ -0,0 +1,144 @@ +#ifndef XMLREADER +#define XMLREADER + +#include +#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 + * be made more arbitrary in the future so that we can read the data from any + * source. This is actually made quite simple already since all data read in + * is handled by one single helper function and then palced into a FlexBuf for + * easy access by the other functions. The FlexBuf also allows for block + * reading from disk, which improves speed by a noticable amount. + *
+ * There are also some extra features implemented that allow you to break the + * standard XML reader specs and eliminate leading and trailing whitespace in + * all read content. This is useful in situations where you allow additional + * whitespace in the files to make them easily human readable. The resturned + * content will be NULL in sitautions where all content between nodes was + * stripped. + *@author Mike Buland + */ +class XmlReader : public XmlDocument +{ +public: + /** + * Create a standard XmlReader. The optional parameter bStrip allows you to + * create a reader that will strip out all leading and trailing whitespace + * in content, a-la html. + *@param bStrip Strip out leading and trailing whitespace? + */ + XmlReader( Bu::Stream &sIn, bool bStrip=false ); + + /** + * Destroy this XmlReader. + */ + virtual ~XmlReader(); + + /** + * Build a document based on some kind of input. This is called + * automatically by the constructor. + */ + bool buildDoc(); + +private: + /** + * This is called by the low level automoton in order to get the next + * character. This function should return a character at the current + * position plus nIndex, but does not increment the current character. + *@param nIndex The index of the character from the current stream position. + *@returns A single character at the requested position, or 0 for end of + * stream. + */ + virtual char getChar( int nIndex = 0 ); + + /** + * Called to increment the current stream position by a single character. + */ + virtual void usedChar( int nAmnt = 1 ); + + /** + * Automoton function: is whitespace. + *@param chr A character + *@returns True if chr is whitespace, false otherwise. + */ + bool isws( char chr ); + + /** + * Automoton function: ws. Skips sections of whitespace. + *@returns True if everything was ok, False for end of stream. + */ + bool ws(); + + /** + * Automoton function: node. Processes an XmlNode + *@returns True if everything was ok, False for end of stream. + */ + bool node(); + + /** + * Automoton function: startNode. Processes the begining of a node. + *@returns True if everything was ok, False for end of stream. + */ + bool startNode(); + + /** + * Automoton function: name. Processes the name of a node. + *@returns True if everything was ok, False for end of stream. + */ + bool name(); + + /** + * Automoton function: textDecl. Processes the xml text decleration, if + * there is one. + */ + void textDecl(); + + /** + * Automoton function: entity. Processes an entity from the header. + */ + void entity(); + + /** + * Adds an entity to the list, if it doesn't already exist. + *@param name The name of the entity + *@param value The value of the entity + */ + void addEntity( const Bu::FString &name, const Bu::FString &value ); + + Bu::FString getEscape(); + + /** + * Automoton function: paramlist. Processes a list of node params. + *@returns True if everything was ok, False for end of stream. + */ + bool paramlist(); + + /** + * Automoton function: param. Processes a single parameter. + *@returns True if everything was ok, False for end of stream. + */ + bool param(); + + /** + * Automoton function: content. Processes node content. + *@returns True if everything was ok, False for end of stream. + */ + bool content(); + + 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? */ + + Bu::Hash htEntity; /**< Entity type definitions. */ + + Bu::FString sBuf; +}; + +#endif diff --git a/src/old/xmlwriter.cpp b/src/old/xmlwriter.cpp new file mode 100644 index 0000000..7dc6ca9 --- /dev/null +++ b/src/old/xmlwriter.cpp @@ -0,0 +1,167 @@ +#include +#include +#include "xmlwriter.h" + +XmlWriter::XmlWriter( const Bu::FString &sIndent, XmlNode *pRoot ) : + XmlDocument( pRoot ), + sIndent( sIndent ) +{ +} + +XmlWriter::~XmlWriter() +{ +} + +void XmlWriter::write() +{ + write( getRoot(), sIndent.c_str() ); +} + +void XmlWriter::write( XmlNode *pRoot, const Bu::FString &sIndent ) +{ + writeNode( pRoot, 0, sIndent ); +} + +void XmlWriter::closeNode() +{ + XmlDocument::closeNode(); + + if( isCompleted() ) + { + write( getRoot(), sIndent.c_str() ); + } +} + +void XmlWriter::writeIndent( int nIndent, const Bu::FString &sIndent ) +{ + if( sIndent == NULL ) return; + for( int j = 0; j < nIndent; j++ ) + { + writeString( sIndent ); + } +} + +Bu::FString XmlWriter::escape( const Bu::FString &sIn ) +{ + Bu::FString sOut; + + int nMax = sIn.getSize(); + for( int j = 0; j < nMax; j++ ) + { + char c = sIn[j]; + if( ((c >= ' ' && c <= '9') || + (c >= 'a' && c <= 'z') || + (c >= 'A' && c <= 'Z') ) && + (c != '\"' && c != '\'' && c != '&') + ) + { + sOut += c; + } + else + { + sOut += "&#"; + char buf[4]; + sprintf( buf, "%u", (unsigned char)c ); + sOut += buf; + sOut += ';'; + } + } + + return sOut; +} + +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("=\""); + //writeString( escape( pNode->getProperty( j ) ).c_str() ); + writeString("\""); + } +} + +void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ) +{ + if( pNode->hasChildren() ) + { + writeIndent( nIndent, sIndent ); + writeString("<"); + writeString( pNode->getName() ); + writeNodeProps( pNode, nIndent, sIndent ); + if( sIndent != "" ) + writeString(">\n"); + else + writeString(">"); +/* + if( pNode->getContent( 0 ) ) + { + writeIndent( nIndent+1, sIndent ); + if( sIndent != "" ) + { + writeString( pNode->getContent( 0 ) ); + writeString("\n"); + } + else + writeString( pNode->getContent( 0 ) ); + } + + int nNumChildren = pNode->getNumChildren(); + for( int j = 0; j < nNumChildren; j++ ) + { + writeNode( pNode->getChild( j ), nIndent+1, sIndent ); + if( pNode->getContent( j+1 ) ) + { + writeIndent( nIndent+1, sIndent ); + if( sIndent ) + { + writeString( pNode->getContent( j+1 ) ); + writeString("\n"); + } + else + writeString( pNode->getContent( j+1 ) ); + } + } +*/ + writeIndent( nIndent, sIndent ); + if( sIndent != "" ) + { + writeString("getName() ); + writeString(">\n"); + } + else + { + writeString("getName() ); + writeString(">"); + } + }/* + else if( pNode->getContent() ) + { + writeIndent( nIndent, sIndent ); + writeString("<"); + writeString( pNode->getName() ); + writeNodeProps( pNode, nIndent, sIndent ); + writeString(">"); + writeString( pNode->getContent() ); + writeString("getName() ); + writeString(">"); + if( sIndent ) + writeString("\n"); + }*/ + else + { + writeIndent( nIndent, sIndent ); + writeString("<"); + writeString( pNode->getName() ); + writeNodeProps( pNode, nIndent, sIndent ); + if( sIndent != "" ) + writeString("/>\n"); + else + writeString("/>"); + } +} + diff --git a/src/old/xmlwriter.h b/src/old/xmlwriter.h new file mode 100644 index 0000000..7e3c876 --- /dev/null +++ b/src/old/xmlwriter.h @@ -0,0 +1,96 @@ +#ifndef XMLWRITER +#define XMLWRITER + +#include "xmlnode.h" +#include "xmldocument.h" + +/** + * Implements xml writing in the XML standard format. Also allows you to + * break that format and auto-indent your exported xml data for ease of + * reading. The auto-indenting will only be applied to sections that + * have no content of their own already. This means that except for + * whitespace all of your data will be preserved perfectly. + * You can create an XmlWriter object around a file, or access the static + * write function directly and just hand it a filename and a root XmlNode. + * When using an XmlWriter object the interface is identicle to that of + * the XmlDocument class, so reference that class for API info. However + * when the initial (or root) node is closed, and the document is finished + * the file will be created and written to automatically. The user can + * check to see if this is actually true by calling the isFinished + * function in the XmlDocument class. + *@author Mike Buland + */ +class XmlWriter : public XmlDocument +{ +public: + /** + * Construct a standard XmlWriter. + *@param sIndent Set this to something other than NULL to include it as an + * indent before each node in the output that doesn't already have content. + * If you are using the whitespace stripping option in the XmlReader and set + * this to a tab or some spaces it will never effect the content of your + * file. + */ + XmlWriter( const Bu::FString &sIndent="", XmlNode *pRoot=NULL ); + + /** + * Destroy the writer. + */ + virtual ~XmlWriter(); + + /** + * This override of the parent class closeNode function calls the parent + * class, but also triggers a write operation when the final node is closed. + * This means that by checking the isCompleted() function the user may also + * check to see if their file has been written or not. + */ + void closeNode(); + + void write(); + +private: + Bu::FString sIndent; /**< The indent string */ + + 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 Bu::FString &sIndent ); + + /** + * Write a node in the file, including children. + *@param pNode The node to write. + *@param nIndent The indent level (the number of times to include sIndent) + *@param sIndent The indent text. + */ + void writeNode( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ); + + /** + * Write the properties of a node. + *@param pNode The node who's properties to write. + *@param nIndent The indent level of the containing node + *@param sIndent The indent text. + */ + 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 Bu::FString &sIndent ); + + /** + * This is the function that must be overridden in order to use this class. + * It must write the null-terminated string sString, minus the mull, + * verbatum to it's output device. Adding extra characters for any reason + * will break the XML formatting. + *@param sString The string data to write to the output. + */ + virtual void writeString( const Bu::FString &sString ) = 0; +}; + +#endif diff --git a/src/server.cpp b/src/server.cpp index f93238c..abf4c5b 100644 --- a/src/server.cpp +++ b/src/server.cpp @@ -53,7 +53,8 @@ void Bu::Server::scan() { if( hServers.has( j ) ) { - addClient( hServers.get( j )->accept() ); + ServerSocket *pSrv = hServers.get( j ); + addClient( pSrv->accept(), pSrv->getPort() ); } else { @@ -63,11 +64,13 @@ void Bu::Server::scan() } } -void Bu::Server::addClient( int nSocket ) +void Bu::Server::addClient( int nSocket, int nPort ) { FD_SET( nSocket, &fdActive ); Client *c = new Client(); hClients.insert( nSocket, c ); + + onNewConnection( c, nPort ); } diff --git a/src/server.h b/src/server.h index 9f4f459..942eb32 100644 --- a/src/server.h +++ b/src/server.h @@ -22,6 +22,10 @@ namespace Bu * 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. + * + * In order to use a Server you must subclass it and implement the pure + * virtual functions. These allow you to receive notification of events + * happening within the server itself, and actually makes it useful. */ class Server { @@ -35,7 +39,10 @@ namespace Bu void scan(); void setTimeout( int nTimeoutSec, int nTimeoutUSec=0 ); - void addClient( int nSocket ); + void addClient( int nSocket, int nPort ); + + virtual void onNewConnection( Client *pClient, int nPort )=0; + virtual void onClosedConnection( Client *pClient )=0; private: int nTimeoutSec; diff --git a/src/serversocket.cpp b/src/serversocket.cpp index 9c8f743..1424630 100644 --- a/src/serversocket.cpp +++ b/src/serversocket.cpp @@ -151,3 +151,8 @@ int Bu::ServerSocket::accept( int nTimeoutSec, int nTimeoutUSec ) return -1; } +int Bu::ServerSocket::getPort() +{ + return nPort; +} + diff --git a/src/serversocket.h b/src/serversocket.h index d2601e4..cb86078 100644 --- a/src/serversocket.h +++ b/src/serversocket.h @@ -25,6 +25,7 @@ namespace Bu int accept( int nTimeoutSec=0, int nTimeoutUSec=0 ); int getSocket(); + int getPort(); private: void startServer( struct sockaddr_in &name, int nPoolSize ); diff --git a/src/xmldocument.cpp b/src/xmldocument.cpp deleted file mode 100644 index 95b9788..0000000 --- a/src/xmldocument.cpp +++ /dev/null @@ -1,145 +0,0 @@ -#include -#include -#include "xmldocument.h" - -XmlDocument::XmlDocument( XmlNode *pRoot ) -{ - this->pRoot = pRoot; - pCurrent = NULL; - bCompleted = (pRoot!=NULL); -} - -XmlDocument::~XmlDocument() -{ - if( pRoot ) - { - delete pRoot; - } -} - -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 ); - } - else - { - pCurrent = pCurrent->addChild( sName ); - } -} -/* -void XmlDocument::setName( const char *sName ) -{ - pCurrent->setName( sName ); -}*/ - -bool XmlDocument::isCompleted() -{ - return bCompleted; -} - -XmlNode *XmlDocument::getRoot() -{ - return pRoot; -} - -XmlNode *XmlDocument::detatchRoot() -{ - XmlNode *pTemp = pRoot; - pRoot = NULL; - return pTemp; -} - -XmlNode *XmlDocument::getCurrent() -{ - return pCurrent; -} - -void XmlDocument::closeNode() -{ - if( pCurrent != NULL ) - { - pCurrent = pCurrent->getParent(); - - if( pCurrent == NULL ) - { - bCompleted = true; - } - } -} - -void XmlDocument::addProperty( const char *sName, const char *sValue ) -{ - if( pCurrent ) - { - pCurrent->addProperty( sName, sValue ); - } -} - -void XmlDocument::addProperty( const char *sName, const unsigned char nValue ) -{ - char buf[12]; - sprintf( buf, "%hhi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const char nValue ) -{ - char buf[12]; - sprintf( buf, "%hhi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const unsigned short nValue ) -{ - char buf[12]; - sprintf( buf, "%hi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const short nValue ) -{ - char buf[12]; - sprintf( buf, "%hi", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const int nValue ) -{ - char buf[12]; - sprintf( buf, "%d", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const unsigned long nValue ) -{ - char buf[12]; - sprintf( buf, "%li", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const long nValue ) -{ - char buf[12]; - sprintf( buf, "%li", nValue ); - addProperty( sName, buf ); -} - -void XmlDocument::addProperty( const char *sName, const double dValue ) -{ - char buf[40]; - sprintf( buf, "%f", dValue ); - addProperty( sName, buf ); -} - -void XmlDocument::setContent( const char *sContent ) -{ - if( pCurrent ) - { - printf("XmlDocument::setContent: not yet implemented.\n"); - //pCurrent->setContent( sContent ); - } -} - diff --git a/src/xmldocument.h b/src/xmldocument.h deleted file mode 100644 index e0c36eb..0000000 --- a/src/xmldocument.h +++ /dev/null @@ -1,165 +0,0 @@ -#ifndef XMLDOCUMENT -#define XMLDOCUMENT - -#include "xmlnode.h" - -/** - * Keeps track of an easily managed set of XmlNode information. Allows simple - * operations for logical writing to and reading from XML structures. Using - * already formed structures is simply done through the XmlNode structures, - * and the getRoot function here. Creation is performed through a simple set - * of operations that creates the data in a stream type format. - *@author Mike Buland - */ -class XmlDocument -{ -public: - /** - * Construct either a blank XmlDocuemnt or construct a document around an - * existing XmlNode. Be careful, once an XmlNode is passed into a document - * the document takes over ownership and will delete it when the XmlDocument - * is deleted. - *@param pRoot The XmlNode to use as the root of this document, or NULL if - * you want to start a new document. - */ - XmlDocument( XmlNode *pRoot=NULL ); - - /** - * Destroy all contained nodes. - */ - virtual ~XmlDocument(); - - /** - * Add a new node to the document. The new node is appended to the end of - * the current context, i.e. XmlNode, and the new node, provided it isn't - * close as part of this operation, will become the current context. - *@param sName The name of the new node to add. - *@param sContent A content string to be placed inside of the new node. - *@param bClose Set this to true to close the node immediately after adding - * 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 Bu::FString &sName ); - - /** - * Close the current node context. This will move the current context to - * the parent node of the former current node. If the current node was the - * root then the "completed" flag is set and no more operations are allowed. - */ - void closeNode(); - - /** - * Change the content of the current node at the current position between - * nodes. - *@param sContent The new content of the current node. - */ - void setContent( const char *sContent ); - - /** - * Add a named property to the current context node. - *@param sName The name of the property to add. - *@param sValue The string value of the property. - */ - void addProperty( const char *sName, const char *sValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const unsigned char nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const char nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const unsigned short nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const short nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const unsigned long nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const long nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param nValue The numerical value to add. - */ - void addProperty( const char *sName, const int nValue ); - - /** - * Add a named property to the current context node, converting the - * numerical parameter to text using standrd printf style conversion. - *@param sName The name of the property to add. - *@param dValue The numerical value to add. - */ - void addProperty( const char *sName, const double dValue ); - - /** - * The XmlDocuemnt is considered completed if the root node has been closed. - * Once an XmlDocument has been completed, you can no longer perform - * operations on it. - *@return True if completed, false if still in progress. - */ - bool isCompleted(); - - /** - * Get a pointer to the root object of this XmlDocument. - *@returns A pointer to an internally owned XmlNode. Do not delete this - * XmlNode. - */ - XmlNode *getRoot(); - - /** - * Get a pointer to the root object of this XmlDocument, and remove the - * ownership from this object. - *@returns A pointer to an internally owned XmlNode. Do not delete this - * XmlNode. - */ - XmlNode *detatchRoot(); - - /** - * Get the current context node, which could be the same as the root node. - *@returns A pointer to an internally owned XmlNode. Do not delete this - * XmlNode. - */ - XmlNode *getCurrent(); - -private: - XmlNode *pRoot; /**< The root node. */ - XmlNode *pCurrent; /**< The current node. */ - bool bCompleted; /**< Is it completed? */ -}; - -#endif diff --git a/src/xmlnode.cpp b/src/xmlnode.cpp deleted file mode 100644 index 96d5850..0000000 --- a/src/xmlnode.cpp +++ /dev/null @@ -1,403 +0,0 @@ -#include "xmlnode.h" - -XmlNode::XmlNode( const Bu::FString &sName, XmlNode *pParent ) : - sName( sName ), - pParent( pParent ) -{ -} - -XmlNode::~XmlNode() -{ -} -/* -void XmlNode::setName( const char *sName ) -{ - if( pParent ) - { - if( this->sName.size() == 0 ) - { - // We're not in the hash yet, so add us - this->sName = sName; - pParent->hChildren.insert( this->sName.c_str(), this ); - } - else - { - // Slightly more tricky, delete us, then add us... - pParent->hChildren.del( this->sName.c_str() ); - this->sName = sName; - pParent->hChildren.insert( this->sName.c_str(), this ); - } - } - else - { - // If we have no parent, then just set the name string, we don't need - // to worry about hashing. - this->sName = sName; - } -} - -void XmlNode::setContent( const char *sContent, int nIndex ) -{ - if( nIndex == -1 ) - { - nIndex = nCurContent; - } - if( nIndex == 0 ) - { - if( this->sPreContent ) - { - delete this->sPreContent; - } - - this->sPreContent = new std::string( sContent ); - } - else - { - nIndex--; - if( lPostContent[nIndex] ) - { - delete (std::string *)lPostContent[nIndex]; - } - - lPostContent.setAt( nIndex, new std::string( sContent ) ); - } -} - -const char *XmlNode::getContent( int nIndex ) -{ - if( nIndex == 0 ) - { - if( sPreContent ) - { - return sPreContent->c_str(); - } - } - else - { - nIndex--; - if( lPostContent[nIndex] ) - { - return ((std::string *)lPostContent[nIndex])->c_str(); - } - } - - return NULL; -}*/ - -XmlNode *XmlNode::addChild( const Bu::FString &sName ) -{ - return addChild( new XmlNode( sName, this ) ); -} - -XmlNode *XmlNode::addChild( XmlNode *pNode ) -{ - Child c = { typeNode }; - c.pNode = pNode; - lChildren.append( c ); - pNode->pParent = this; - - return pNode; -} - -XmlNode *XmlNode::getParent() -{ - return pParent; -} - -void XmlNode::addProperty( const Bu::FString &sName, const Bu::FString &sValue ) -{ - hProperties.insert( sName, sValue ); -} - -int XmlNode::getNumProperties() -{ - return hProperties.size(); -} -/* -const char *XmlNode::getPropertyName( int nIndex ) -{ - std::string *tmp = ((std::string *)lPropNames[nIndex]); - if( tmp == NULL ) - return NULL; - return tmp->c_str(); -} - -const char *XmlNode::getProperty( int nIndex ) -{ - std::string *tmp = ((std::string *)lPropValues[nIndex]); - if( tmp == NULL ) - return NULL; - return tmp->c_str(); -} -*/ -Bu::FString XmlNode::getProperty( const Bu::FString &sName ) -{ - return hProperties[sName]; -} -/* -void XmlNode::deleteProperty( int nIndex ) -{ - hProperties.del( ((std::string *)lPropNames[nIndex])->c_str() ); - - delete (std::string *)lPropNames[nIndex]; - delete (std::string *)lPropValues[nIndex]; - - lPropNames.deleteAt( nIndex ); - lPropValues.deleteAt( nIndex ); -} - -bool XmlNode::hasChildren() -{ - return hChildren.getSize()>0; -}*/ - -int XmlNode::getNumChildren() -{ - return lChildren.getSize(); -} -/* -XmlNode *XmlNode::getChild( int nIndex ) -{ - return (XmlNode *)lChildren[nIndex]; -} -*/ -XmlNode *XmlNode::getChild( const Bu::FString &sName, int nSkip ) -{ - if( !hChildren.has( sName ) ) - return NULL; - - Bu::List::iterator i = hChildren[sName]->begin(); - return *i; -} - -Bu::FString XmlNode::getName() -{ - return sName; -} -/* -void XmlNode::deleteNode( int nIndex, const char *sReplacementText ) -{ - XmlNode *xRet = detatchNode( nIndex, sReplacementText ); - - if( xRet != NULL ) - { - delete xRet; - } -} - -XmlNode *XmlNode::detatchNode( int nIndex, const char *sReplacementText ) -{ - if( nIndex < 0 || nIndex >= lChildren.getSize() ) - return NULL; - - // The real trick when deleteing a node isn't actually deleting it, it's - // reforming the content around the node that's now missing...hmmm... - - if( nIndex == 0 ) - { - // If the index is zero we have to deal with the pre-content - if( sReplacementText ) - { - if( sPreContent == NULL ) - { - sPreContent = new std::string( sReplacementText ); - } - else - { - *sPreContent += sReplacementText; - } - } - if( lPostContent.getSize() > 0 ) - { - if( lPostContent[0] != NULL ) - { - if( sPreContent == NULL ) - { - sPreContent = new std::string( - ((std::string *)lPostContent[0])->c_str() - ); - } - else - { - *sPreContent += - ((std::string *)lPostContent[0])->c_str(); - } - } - delete (std::string *)lPostContent[0]; - lPostContent.deleteAt( 0 ); - } - } - else - { - int nCont = nIndex-1; - // If it's above zero we deal with the post-content only - if( sReplacementText ) - { - if( lPostContent[nCont] == NULL ) - { - lPostContent.setAt( nCont, new std::string( sReplacementText ) ); - } - else - { - *((std::string *)lPostContent[nCont]) += sReplacementText; - } - } - if( lPostContent.getSize() > nIndex ) - { - if( lPostContent[nIndex] != NULL ) - { - if( lPostContent[nCont] == NULL ) - { - lPostContent.setAt( nCont, new std::string( - ((std::string *)lPostContent[nIndex])->c_str() - ) ); - } - else - { - *((std::string *)lPostContent[nCont]) += - ((std::string *)lPostContent[nIndex])->c_str(); - } - } - delete (std::string *)lPostContent[nIndex]; - lPostContent.deleteAt( nIndex ); - } - } - - XmlNode *xRet = (XmlNode *)lChildren[nIndex]; - hChildren.del( ((XmlNode *)lChildren[nIndex])->getName() ); - lChildren.deleteAt( nIndex ); - - return xRet; -} - -void XmlNode::replaceNode( int nIndex, XmlNode *pNewNode ) -{ - if( nIndex < 0 || nIndex >= lChildren.getSize() ) - return; //TODO: throw an exception - - delete (XmlNode *)lChildren[nIndex]; - lChildren.setAt( nIndex, pNewNode ); - pNewNode->pParent = this; -} - -XmlNode *XmlNode::getCopy() -{ - XmlNode *pNew = new XmlNode(); - - pNew->sName = sName; - if( sPreContent ) - { - pNew->sPreContent = new std::string( sPreContent->c_str() ); - } - else - { - pNew->sPreContent = NULL; - } - pNew->nCurContent = 0; - - int nSize = lPostContent.getSize(); - pNew->lPostContent.setSize( nSize ); - for( int j = 0; j < nSize; j++ ) - { - if( lPostContent[j] ) - { - pNew->lPostContent.setAt( - j, new std::string( - ((std::string *)lPostContent[j])->c_str() - ) - ); - } - else - { - pNew->lPostContent.setAt( j, NULL ); - } - } - - nSize = lChildren.getSize(); - pNew->lChildren.setSize( nSize ); - for( int j = 0; j < nSize; j++ ) - { - XmlNode *pChild = ((XmlNode *)lChildren[j])->getCopy(); - pNew->lChildren.setAt( j, pChild ); - pChild->pParent = pNew; - pNew->hChildren.insert( pChild->getName(), pChild ); - } - - nSize = lPropNames.getSize(); - pNew->lPropNames.setSize( nSize ); - pNew->lPropValues.setSize( nSize ); - for( int j = 0; j < nSize; j++ ) - { - std::string *pProp = new std::string( ((std::string *)lPropNames[j])->c_str() ); - std::string *pVal = new std::string( ((std::string *)lPropValues[j])->c_str() ); - pNew->lPropNames.setAt( j, pProp ); - pNew->lPropValues.setAt( j, pVal ); - pNew->hProperties.insert( pProp->c_str(), pVal->c_str() ); - pNew->nCurContent++; - } - - return pNew; -} - -void XmlNode::deleteNodeKeepChildren( int nIndex ) -{ - // This is a tricky one...we need to do some patching to keep things all - // even... - XmlNode *xRet = (XmlNode *)lChildren[nIndex]; - - if( xRet == NULL ) - { - return; - } - else - { - if( getContent( nIndex ) ) - { - std::string sBuf( getContent( nIndex ) ); - sBuf += xRet->getContent( 0 ); - setContent( sBuf.c_str(), nIndex ); - } - else - { - setContent( xRet->getContent( 0 ), nIndex ); - } - - int nSize = xRet->lChildren.getSize(); - for( int j = 0; j < nSize; j++ ) - { - XmlNode *pCopy = ((XmlNode *)xRet->lChildren[j])->getCopy(); - pCopy->pParent = this; - lChildren.insertBefore( pCopy, nIndex+j ); - - if( xRet->lPostContent[j] ) - { - lPostContent.insertBefore( - new std::string( ((std::string *)xRet->lPostContent[j])->c_str() ), - nIndex+j - ); - } - else - { - lPostContent.insertBefore( NULL, nIndex+j ); - } - } - - if( getContent( nIndex+nSize ) ) - { - //SString sBuf( getContent( nIndex+nSize ) ); - //sBuf.catfrom( xRet->getContent( nSize ) ); - //setContent( sBuf, nIndex+nSize ); - } - else - { - setContent( xRet->getContent( nSize ), nIndex+nSize ); - } - - deleteNode( nIndex+nSize ); - } -} - -void XmlNode::replaceNodeWithChildren( int nIndex, XmlNode *pNewNode ) -{ -} -*/ diff --git a/src/xmlnode.h b/src/xmlnode.h deleted file mode 100644 index c895cd8..0000000 --- a/src/xmlnode.h +++ /dev/null @@ -1,207 +0,0 @@ -#ifndef XMLNODE -#define XMLNODE - -#include -#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. - * All child nodes can be accessed through index and through name via a hash - * table. This makes it very easy to gain simple and fast access to all of - * your data. For most applications, the memory footprint is also rather - * small. While XmlNode objects can be used directly to create XML structures - * it is highly reccomended that all operations be performed through the - * XmlDocument class. - *@author Mike Buland - */ -class XmlNode -{ -public: - /** - * Construct a new XmlNode. - *@param sName The name of the node. - *@param pParent The parent node. - *@param sContent The initial content string. - */ - XmlNode( - const Bu::FString &sName, - XmlNode *pParent=NULL - ); - - /** - * Delete the node and cleanup all memory. - */ - virtual ~XmlNode(); - - /** - * Change the name of the node. - *@param sName The new name of the node. - */ - //void setName( const char *sName ); - - /** - * Construct a new node and add it as a child to this node, also return a - * pointer to the newly constructed node. - *@param sName The name of the new node. - *@param sContent The initial content of the new node. - *@returns A pointer to the newly created child node. - */ - XmlNode *addChild( const Bu::FString &sName ); - - /** - * Add an already created XmlNode as a child to this node. The new child - * XmlNode's parent will be changed appropriately and the parent XmlNode - * will take ownership of the child. - *@param pChild The child XmlNode to add to this XmlNode. - *@returns A pointer to the child node that was just added. - */ - XmlNode *addChild( XmlNode *pChild ); - - /** - * Add a new property to the XmlNode. Properties are name/value pairs. - *@param sName The name of the property. Specifying a name that's already - * in use will overwrite that property. - *@param sValue The textual value of the property. - */ - void addProperty( const Bu::FString &sName, const Bu::FString &sValue ); - - /** - * Get a pointer to the parent node, if any. - *@returns A pointer to the node's parent, or NULL if there isn't one. - */ - XmlNode *getParent(); - - /** - * Tells you if this node has children. - *@returns True if this node has at least one child, false otherwise. - */ - bool hasChildren(); - - /** - * Tells you how many children this node has. - *@returns The number of children this node has. - */ - int getNumChildren(); - - /** - * Get a child with the specified name, and possibly skip value. For an - * explination of skip values see the HashTable. - *@param sName The name of the child to find. - *@param nSkip The number of nodes with that name to skip. - *@returns A pointer to the child, or NULL if no child with that name was - * found. - */ - 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. - */ - Bu::FString getName(); - - /** - * Set the content of this node, optionally at a specific index. Using the - * default of -1 will set the content after the last added node. - *@param sContent The content string to use. - *@param nIndex The index of the content. - */ - //void setContent( const char *sContent, int nIndex=-1 ); - - /** - * Get the number of properties in this node. - *@returns The number of properties in this node. - */ - int getNumProperties(); - - /** - * 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. - */ - Bu::FString getProperty( const Bu::FString &sName ); - - /** - * Delete a child node, possibly replacing it with some text. This actually - * fixes all content strings around the newly deleted child node. - *@param nIndex The index of the node to delete. - *@param sReplacementText The optional text to replace the node with. - *@returns True of the node was found, and deleted, false if it wasn't - * found. - */ - //void deleteNode( int nIndex, const char *sReplacementText = NULL ); - - /** - * Delete a given node, but move all of it's children and content up to - * replace the deleted node. All of the content of the child node is - * spliced seamlessly into place with the parent node's content. - *@param nIndex The node to delete. - *@returns True if the node was found and deleted, false if it wasn't. - */ - //void deleteNodeKeepChildren( int nIndex ); - - /** - * Detatch a given child node from this node. This effectively works just - * like a deleteNode, except that instead of deleting the node it is removed - * and returned, and all ownership is given up. - *@param nIndex The index of the node to detatch. - *@param sReplacementText The optional text to replace the detatched node - * with. - *@returns A pointer to the newly detatched node, which then passes - * ownership to the caller. - */ - //XmlNode *detatchNode( int nIndex, const char *sReplacementText = NULL ); - - /** - * Replace a given node with a different node that is not currently owned by - * this XmlNode or any ancestor. - *@param nIndex The index of the node to replace. - *@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 ); - - /** - * Replace a given node with the children and content of a given node. - *@param nIndex The index of the node to replace. - *@param pNewNode The node that contains the children and content that will - * 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 ); - - /** - * 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(); - - enum ChildType - { - typeNode, - typeContent - }; - -private: - 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. */ -}; - -#endif diff --git a/src/xmlreader.cpp b/src/xmlreader.cpp deleted file mode 100644 index 38cad5f..0000000 --- a/src/xmlreader.cpp +++ /dev/null @@ -1,604 +0,0 @@ -#include "bu/xmlreader.h" -#include "bu/exceptions.h" -#include - -XmlReader::XmlReader( Bu::Stream &sIn, bool bStrip ) : - sIn( sIn ), - bStrip( bStrip ) -{ - buildDoc(); -} - -XmlReader::~XmlReader() -{ -} - -char XmlReader::getChar( int nIndex ) -{ - if( sBuf.getSize() <= nIndex ) - { - 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::usedChar( int nAmnt ) -{ - if( nAmnt >= sBuf.getSize() ) - { - sBuf.clear(); - } - else - { - char *s = sBuf.getStr(); - memcpy( s, s+nAmnt, sBuf.getSize()-nAmnt ); - sBuf.resize( sBuf.getSize()-nAmnt ); - } -} - -void XmlReader::addEntity( const Bu::FString &name, const Bu::FString &value ) -{ - htEntity[name] = value; -} - -#define gcall( x ) if( x == false ) return false; - -bool XmlReader::isws( char chr ) -{ - return ( chr == ' ' || chr == '\t' || chr == '\n' || chr == '\r' ); -} - -bool XmlReader::ws() -{ - while( true ) - { - char chr = getChar(); - if( isws( chr ) ) - { - usedChar(); - } - else - { - return true; - } - } - return true; -} - -bool XmlReader::buildDoc() -{ - // take care of initial whitespace - gcall( ws() ); - textDecl(); - entity(); - addEntity("gt", ">"); - addEntity("lt", "<"); - addEntity("amp", "&"); - addEntity("apos", "\'"); - addEntity("quot", "\""); - gcall( node() ); - - return true; -} - -void XmlReader::textDecl() -{ - if( getChar() == '<' && getChar( 1 ) == '?' ) - { - usedChar( 2 ); - for(;;) - { - if( getChar() == '?' ) - { - if( getChar( 1 ) == '>' ) - { - usedChar( 2 ); - return; - } - } - usedChar(); - } - } -} - -void XmlReader::entity() -{ - for(;;) - { - ws(); - - if( getChar() == '<' && getChar( 1 ) == '!' ) - { - usedChar( 2 ); - ws(); - Bu::FString buf; - for(;;) - { - char chr = getChar(); - usedChar(); - if( isws( chr ) ) break; - buf += chr; - } - - if( strcmp( buf.c_str(), "ENTITY") == 0 ) - { - ws(); - Bu::FString name; - for(;;) - { - char chr = getChar(); - usedChar(); - if( isws( chr ) ) break; - name += chr; - } - ws(); - char quot = getChar(); - usedChar(); - if( quot != '\'' && quot != '\"' ) - { - throw Bu::XmlException( - "Only quoted entity values are supported." - ); - } - Bu::FString value; - for(;;) - { - char chr = getChar(); - usedChar(); - if( chr == '&' ) - { - Bu::FString tmp = getEscape(); - value += tmp; - } - else if( chr == quot ) - { - break; - } - else - { - value += chr; - } - } - ws(); - if( getChar() == '>' ) - { - usedChar(); - - addEntity( name.c_str(), value.c_str() ); - } - else - { - throw Bu::XmlException( - "Malformed ENTITY: unexpected '%c' found.", - getChar() - ); - } - } - else - { - throw Bu::XmlException( - "Unsupported header symbol: %s", - buf.c_str() - ); - } - } - else - { - return; - } - } -} - -bool XmlReader::node() -{ - gcall( startNode() ) - - // At this point, we are closing the startNode - char chr = getChar(); - if( chr == '>' ) - { - usedChar(); - - // Now we process the guts of the node. - gcall( content() ); - } - else if( chr == '/' ) - { - // This is the tricky one, one more validation, then we close the node. - usedChar(); - if( getChar() == '>' ) - { - closeNode(); - usedChar(); - } - else - { - throw Bu::XmlException("Close node in singleNode malformed!"); - } - } - else - { - throw Bu::XmlException("Close node expected, but not found."); - return false; - } - - return true; -} - -bool XmlReader::startNode() -{ - if( getChar() == '<' ) - { - usedChar(); - - if( getChar() == '/' ) - { - // Heh, it's actually a close node, go figure - Bu::FString sName; - usedChar(); - gcall( ws() ); - - while( true ) - { - char chr = getChar(); - if( isws( chr ) || chr == '>' ) - { - // Here we actually compare the name we got to the name - // we already set, they have to match exactly. - if( getCurrent()->getName() == sName ) - { - closeNode(); - break; - } - else - { - throw Bu::XmlException("Got a mismatched node close tag."); - } - } - else - { - sName += chr; - usedChar(); - } - } - - gcall( ws() ); - if( getChar() == '>' ) - { - // Everything is cool. - usedChar(); - } - else - { - throw Bu::XmlException("Got extra junk data instead of node close tag."); - } - } - else - { - // We're good, format is consistant - //addNode(); - - // Skip extra whitespace - gcall( ws() ); - gcall( name() ); - gcall( ws() ); - gcall( paramlist() ); - gcall( ws() ); - } - } - else - { - throw Bu::XmlException("Expected to find node opening char, '<'."); - } - - return true; -} - -bool XmlReader::name() -{ - Bu::FString sName; - - while( true ) - { - char chr = getChar(); - if( isws( chr ) || chr == '>' || chr == '/' ) - { - addNode( sName ); - return true; - } - else - { - sName += chr; - usedChar(); - } - } - - return true; -} - -bool XmlReader::paramlist() -{ - while( true ) - { - char chr = getChar(); - if( chr == '/' || chr == '>' ) - { - return true; - } - else - { - gcall( param() ); - gcall( ws() ); - } - } - - return true; -} - -Bu::FString XmlReader::getEscape() -{ - if( getChar( 1 ) == '#' ) - { - // If the entity starts with a # it's a character escape code - int base = 10; - usedChar( 2 ); - if( getChar() == 'x' ) - { - base = 16; - usedChar(); - } - char buf[4]; - int j = 0; - for( j = 0; getChar() != ';'; j++ ) - { - buf[j] = getChar(); - usedChar(); - } - usedChar(); - buf[j] = '\0'; - buf[0] = (char)strtol( buf, (char **)NULL, base ); - buf[1] = '\0'; - - return buf; - } - else - { - // ...otherwise replace with the appropriate string... - Bu::FString buf; - usedChar(); - for(;;) - { - char cbuf = getChar(); - usedChar(); - if( cbuf == ';' ) break; - buf += cbuf; - } - - return htEntity[buf]; - } -} - -bool XmlReader::param() -{ - Bu::FString sName; - Bu::FString sValue; - - while( true ) - { - char chr = getChar(); - if( isws( chr ) || chr == '=' ) - { - break; - } - else - { - sName.append( chr ); - usedChar(); - } - } - - gcall( ws() ); - - if( getChar() == '=' ) - { - usedChar(); - - gcall( ws() ); - - char chr = getChar(); - if( chr == '"' ) - { - // Better quoted rhs - usedChar(); - - while( true ) - { - chr = getChar(); - if( chr == '"' ) - { - usedChar(); - addProperty( sName.getStr(), sValue.getStr() ); - return true; - } - else - { - if( chr == '&' ) - { - sValue += getEscape(); - } - else - { - sValue += chr; - usedChar(); - } - } - } - } - else - { - // Simple one-word rhs - while( true ) - { - chr = getChar(); - if( isws( chr ) || chr == '/' || chr == '>' ) - { - addProperty( sName.getStr(), sValue.getStr() ); - return true; - } - else - { - if( chr == '&' ) - { - sValue += getEscape(); - } - else - { - sValue += chr; - usedChar(); - } - } - } - } - } - else - { - throw Bu::XmlException("Expected an equals to seperate the params."); - return false; - } - - return true; -} - -bool XmlReader::content() -{ - Bu::FString sContent; - - if( bStrip ) gcall( ws() ); - - while( true ) - { - char chr = getChar(); - if( chr == '<' ) - { - if( getChar(1) == '/' ) - { - if( sContent.getSize() > 0 ) - { - if( bStrip ) - { - int j; - for( j = sContent.getSize()-1; isws(sContent[j]); j-- ); - sContent[j+1] = '\0'; - } - setContent( sContent.getStr() ); - } - usedChar( 2 ); - gcall( ws() ); - Bu::FString sName; - while( true ) - { - chr = getChar(); - if( isws( chr ) || chr == '>' ) - { - if( !strcasecmp( getCurrent()->getName().getStr(), sName.getStr() ) ) - { - closeNode(); - break; - } - else - { - throw Bu::XmlException("Mismatched close tag found: <%s> to <%s>.", getCurrent()->getName().getStr(), sName.getStr() ); - } - } - else - { - sName += chr; - usedChar(); - } - } - gcall( ws() ); - if( getChar() == '>' ) - { - usedChar(); - return true; - } - else - { - throw Bu::XmlException("Malformed close tag."); - } - } - else if( getChar(1) == '!' ) - { - // We know it's a comment, let's see if it's proper - if( getChar(2) != '-' || - getChar(3) != '-' ) - { - // Not a valid XML comment - throw Bu::XmlException("Malformed comment start tag found."); - } - - usedChar( 4 ); - - // Now burn text until we find the close tag - for(;;) - { - if( getChar() == '-' ) - { - if( getChar( 1 ) == '-' ) - { - // The next one has to be a '>' now - if( getChar( 2 ) != '>' ) - { - throw Bu::XmlException("Malformed comment close tag found. You cannot have a '--' that isn't followed by a '>' in a comment."); - } - usedChar( 3 ); - break; - } - else - { - // Found a dash followed by a non dash, that's ok... - usedChar( 2 ); - } - } - else - { - // Burn comment chars - usedChar(); - } - } - } - else - { - if( sContent.getSize() > 0 ) - { - if( bStrip ) - { - int j; - for( j = sContent.getSize()-1; isws(sContent[j]); j-- ); - sContent[j+1] = '\0'; - } - setContent( sContent.getStr() ); - sContent.clear(); - } - gcall( node() ); - } - - if( bStrip ) gcall( ws() ); - } - else if( chr == '&' ) - { - sContent += getEscape(); - } - else - { - sContent += chr; - usedChar(); - } - } -} - diff --git a/src/xmlreader.h b/src/xmlreader.h deleted file mode 100644 index 7c85ddb..0000000 --- a/src/xmlreader.h +++ /dev/null @@ -1,144 +0,0 @@ -#ifndef XMLREADER -#define XMLREADER - -#include -#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 - * be made more arbitrary in the future so that we can read the data from any - * source. This is actually made quite simple already since all data read in - * is handled by one single helper function and then palced into a FlexBuf for - * easy access by the other functions. The FlexBuf also allows for block - * reading from disk, which improves speed by a noticable amount. - *
- * There are also some extra features implemented that allow you to break the - * standard XML reader specs and eliminate leading and trailing whitespace in - * all read content. This is useful in situations where you allow additional - * whitespace in the files to make them easily human readable. The resturned - * content will be NULL in sitautions where all content between nodes was - * stripped. - *@author Mike Buland - */ -class XmlReader : public XmlDocument -{ -public: - /** - * Create a standard XmlReader. The optional parameter bStrip allows you to - * create a reader that will strip out all leading and trailing whitespace - * in content, a-la html. - *@param bStrip Strip out leading and trailing whitespace? - */ - XmlReader( Bu::Stream &sIn, bool bStrip=false ); - - /** - * Destroy this XmlReader. - */ - virtual ~XmlReader(); - - /** - * Build a document based on some kind of input. This is called - * automatically by the constructor. - */ - bool buildDoc(); - -private: - /** - * This is called by the low level automoton in order to get the next - * character. This function should return a character at the current - * position plus nIndex, but does not increment the current character. - *@param nIndex The index of the character from the current stream position. - *@returns A single character at the requested position, or 0 for end of - * stream. - */ - virtual char getChar( int nIndex = 0 ); - - /** - * Called to increment the current stream position by a single character. - */ - virtual void usedChar( int nAmnt = 1 ); - - /** - * Automoton function: is whitespace. - *@param chr A character - *@returns True if chr is whitespace, false otherwise. - */ - bool isws( char chr ); - - /** - * Automoton function: ws. Skips sections of whitespace. - *@returns True if everything was ok, False for end of stream. - */ - bool ws(); - - /** - * Automoton function: node. Processes an XmlNode - *@returns True if everything was ok, False for end of stream. - */ - bool node(); - - /** - * Automoton function: startNode. Processes the begining of a node. - *@returns True if everything was ok, False for end of stream. - */ - bool startNode(); - - /** - * Automoton function: name. Processes the name of a node. - *@returns True if everything was ok, False for end of stream. - */ - bool name(); - - /** - * Automoton function: textDecl. Processes the xml text decleration, if - * there is one. - */ - void textDecl(); - - /** - * Automoton function: entity. Processes an entity from the header. - */ - void entity(); - - /** - * Adds an entity to the list, if it doesn't already exist. - *@param name The name of the entity - *@param value The value of the entity - */ - void addEntity( const Bu::FString &name, const Bu::FString &value ); - - Bu::FString getEscape(); - - /** - * Automoton function: paramlist. Processes a list of node params. - *@returns True if everything was ok, False for end of stream. - */ - bool paramlist(); - - /** - * Automoton function: param. Processes a single parameter. - *@returns True if everything was ok, False for end of stream. - */ - bool param(); - - /** - * Automoton function: content. Processes node content. - *@returns True if everything was ok, False for end of stream. - */ - bool content(); - - 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? */ - - Bu::Hash htEntity; /**< Entity type definitions. */ - - Bu::FString sBuf; -}; - -#endif diff --git a/src/xmlwriter.cpp b/src/xmlwriter.cpp deleted file mode 100644 index 7dc6ca9..0000000 --- a/src/xmlwriter.cpp +++ /dev/null @@ -1,167 +0,0 @@ -#include -#include -#include "xmlwriter.h" - -XmlWriter::XmlWriter( const Bu::FString &sIndent, XmlNode *pRoot ) : - XmlDocument( pRoot ), - sIndent( sIndent ) -{ -} - -XmlWriter::~XmlWriter() -{ -} - -void XmlWriter::write() -{ - write( getRoot(), sIndent.c_str() ); -} - -void XmlWriter::write( XmlNode *pRoot, const Bu::FString &sIndent ) -{ - writeNode( pRoot, 0, sIndent ); -} - -void XmlWriter::closeNode() -{ - XmlDocument::closeNode(); - - if( isCompleted() ) - { - write( getRoot(), sIndent.c_str() ); - } -} - -void XmlWriter::writeIndent( int nIndent, const Bu::FString &sIndent ) -{ - if( sIndent == NULL ) return; - for( int j = 0; j < nIndent; j++ ) - { - writeString( sIndent ); - } -} - -Bu::FString XmlWriter::escape( const Bu::FString &sIn ) -{ - Bu::FString sOut; - - int nMax = sIn.getSize(); - for( int j = 0; j < nMax; j++ ) - { - char c = sIn[j]; - if( ((c >= ' ' && c <= '9') || - (c >= 'a' && c <= 'z') || - (c >= 'A' && c <= 'Z') ) && - (c != '\"' && c != '\'' && c != '&') - ) - { - sOut += c; - } - else - { - sOut += "&#"; - char buf[4]; - sprintf( buf, "%u", (unsigned char)c ); - sOut += buf; - sOut += ';'; - } - } - - return sOut; -} - -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("=\""); - //writeString( escape( pNode->getProperty( j ) ).c_str() ); - writeString("\""); - } -} - -void XmlWriter::writeNode( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ) -{ - if( pNode->hasChildren() ) - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent != "" ) - writeString(">\n"); - else - writeString(">"); -/* - if( pNode->getContent( 0 ) ) - { - writeIndent( nIndent+1, sIndent ); - if( sIndent != "" ) - { - writeString( pNode->getContent( 0 ) ); - writeString("\n"); - } - else - writeString( pNode->getContent( 0 ) ); - } - - int nNumChildren = pNode->getNumChildren(); - for( int j = 0; j < nNumChildren; j++ ) - { - writeNode( pNode->getChild( j ), nIndent+1, sIndent ); - if( pNode->getContent( j+1 ) ) - { - writeIndent( nIndent+1, sIndent ); - if( sIndent ) - { - writeString( pNode->getContent( j+1 ) ); - writeString("\n"); - } - else - writeString( pNode->getContent( j+1 ) ); - } - } -*/ - writeIndent( nIndent, sIndent ); - if( sIndent != "" ) - { - writeString("getName() ); - writeString(">\n"); - } - else - { - writeString("getName() ); - writeString(">"); - } - }/* - else if( pNode->getContent() ) - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - writeString(">"); - writeString( pNode->getContent() ); - writeString("getName() ); - writeString(">"); - if( sIndent ) - writeString("\n"); - }*/ - else - { - writeIndent( nIndent, sIndent ); - writeString("<"); - writeString( pNode->getName() ); - writeNodeProps( pNode, nIndent, sIndent ); - if( sIndent != "" ) - writeString("/>\n"); - else - writeString("/>"); - } -} - diff --git a/src/xmlwriter.h b/src/xmlwriter.h deleted file mode 100644 index 7e3c876..0000000 --- a/src/xmlwriter.h +++ /dev/null @@ -1,96 +0,0 @@ -#ifndef XMLWRITER -#define XMLWRITER - -#include "xmlnode.h" -#include "xmldocument.h" - -/** - * Implements xml writing in the XML standard format. Also allows you to - * break that format and auto-indent your exported xml data for ease of - * reading. The auto-indenting will only be applied to sections that - * have no content of their own already. This means that except for - * whitespace all of your data will be preserved perfectly. - * You can create an XmlWriter object around a file, or access the static - * write function directly and just hand it a filename and a root XmlNode. - * When using an XmlWriter object the interface is identicle to that of - * the XmlDocument class, so reference that class for API info. However - * when the initial (or root) node is closed, and the document is finished - * the file will be created and written to automatically. The user can - * check to see if this is actually true by calling the isFinished - * function in the XmlDocument class. - *@author Mike Buland - */ -class XmlWriter : public XmlDocument -{ -public: - /** - * Construct a standard XmlWriter. - *@param sIndent Set this to something other than NULL to include it as an - * indent before each node in the output that doesn't already have content. - * If you are using the whitespace stripping option in the XmlReader and set - * this to a tab or some spaces it will never effect the content of your - * file. - */ - XmlWriter( const Bu::FString &sIndent="", XmlNode *pRoot=NULL ); - - /** - * Destroy the writer. - */ - virtual ~XmlWriter(); - - /** - * This override of the parent class closeNode function calls the parent - * class, but also triggers a write operation when the final node is closed. - * This means that by checking the isCompleted() function the user may also - * check to see if their file has been written or not. - */ - void closeNode(); - - void write(); - -private: - Bu::FString sIndent; /**< The indent string */ - - 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 Bu::FString &sIndent ); - - /** - * Write a node in the file, including children. - *@param pNode The node to write. - *@param nIndent The indent level (the number of times to include sIndent) - *@param sIndent The indent text. - */ - void writeNode( XmlNode *pNode, int nIndent, const Bu::FString &sIndent ); - - /** - * Write the properties of a node. - *@param pNode The node who's properties to write. - *@param nIndent The indent level of the containing node - *@param sIndent The indent text. - */ - 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 Bu::FString &sIndent ); - - /** - * This is the function that must be overridden in order to use this class. - * It must write the null-terminated string sString, minus the mull, - * verbatum to it's output device. Adding extra characters for any reason - * will break the XML formatting. - *@param sString The string data to write to the output. - */ - virtual void writeString( const Bu::FString &sString ) = 0; -}; - -#endif -- cgit v1.2.3