lib/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2025-07-30 22:43:14 +03:00
Code Activity

- added xmlRemoveProp

Browse Source 
- changed the way Windows socket stuff get included
- removed an indetermination xmLDecl/PI(xml...)
- xmlNewNs wasn't checking for double definition
- fixed a problem with dist-hook duplicates
- fixed the loading of external entities APIs, now xmlLoadExternalEntity()
  is used everywhere
- now the xhtml spec validates with the xhtml DTD.
- error.c: fixed crashes in case of no input stream
- added the xhtml spec and dtds to the validation tests and results
Daniel
This commit is contained in:
Daniel Veillard
2000-01-03 11:08:02 +00:00
parent 5e5c62351f
commit 686d6b6ab1
27 changed files with 7186 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
ChangeLog
View File

@ -1,3 +1,22 @@
Mon Jan 3 11:58:05 CET 2000 Daniel Veillard <Daniel.Veillard@w3.org>
* tree.[ch]: added xmlRemoveProp
* win32config.h.in nanohttp.c: avoid including the Windows
socket stuff in every C files
* parser.c: removed an indetermination xmLDecl/PI(xml...) in
the XmL parser(s)
* test/ns4 result/ns4 etc...: added test case for previous prob
* tree.c: xmlNewNs wasn't checking for double definition
* Makefile.in: fixed a problem with dist-hook duplicates
* parser.[hc], xmlIO.c: fixed the loading of external entities
APIs, now xmlLoadExternalEntity() is used everywhere and
setting up an app specific front-end using the
* SAX.c parser.c: some fixes, now the xhtml spec validates
with the xhtml DTD.
* error.c: fixed crashes in case of no input stream
* test/valid/[dtds/]/xhtml* : added the xhtml spec and dtds
to the validation tests and results
Wed Dec 29 15:29:52 CET 1999 Daniel Veillard <Daniel.Veillard@w3.org> Wed Dec 29 15:29:52 CET 1999 Daniel Veillard <Daniel.Veillard@w3.org>
* HTMLparser.[ch] testHTML.c: added push mode for the HTML parser * HTMLparser.[ch] testHTML.c: added push mode for the HTML parser

19
SAX.c
View File

@ -22,6 +22,7 @@
#include "entities.h" #include "entities.h"
#include "xml-error.h" #include "xml-error.h"
#include "debugXML.h" #include "debugXML.h"
#include "xmlIO.h"
#include "SAX.h" #include "SAX.h"
/* #define DEBUG_SAX */ /* #define DEBUG_SAX */
@ -145,7 +146,7 @@ hasExternalSubset(void *ctx)
* internalSubset: * internalSubset:
* @ctx: the user data (XML parser context) * @ctx: the user data (XML parser context)
* *
* Does this document has an internal subset * Callback on internal subset declaration.
*/ */
void void
internalSubset(void *ctx, const xmlChar *name, internalSubset(void *ctx, const xmlChar *name,
@ -226,11 +227,11 @@ internalSubset(void *ctx, const xmlChar *name,
* @publicId: The public ID of the entity * @publicId: The public ID of the entity
* @systemId: The system ID of the entity * @systemId: The system ID of the entity
* *
* Special entity resolver, better left to the parser, it has * The entity loader, to control the loading of external entities,
* more context than the application layer. * the application can either:
* The default behaviour is to NOT resolve the entities, in that case * - override this resolveEntity() callback in the SAX block
* the ENTITY_REF nodes are built in the structure (and the parameter * - or better use the xmlSetExternalEntityLoader() function to
* values). * set up it's own entity resolution routine
* *
* Returns the xmlParserInputPtr if inlined or NULL for DOM behaviour. * Returns the xmlParserInputPtr if inlined or NULL for DOM behaviour.
*/ */
@ -243,10 +244,8 @@ resolveEntity(void *ctx, const xmlChar *publicId, const xmlChar *systemId)
fprintf(stderr, "SAX.resolveEntity(%s, %s)\n", publicId, systemId); fprintf(stderr, "SAX.resolveEntity(%s, %s)\n", publicId, systemId);
#endif #endif
if (systemId != NULL) { return(xmlLoadExternalEntity((const char *) systemId,
return(xmlNewInputFromFile(ctxt, (char *) systemId)); (const char *) publicId, ctxt));
}
return(NULL);
} }
/** /**

59
SAXresult/ns4
View File

@ -1,5 +1,60 @@
SAX.setDocumentLocator() SAX.setDocumentLocator()
SAX.startDocument() SAX.startDocument()
SAX.startElement(diagram, testattr='test', xml:lang='en', xml:link='simple', xml:space='preserve') SAX.processingInstruction(xml-stylesheet, type="text/xml"
SAX.endElement(diagram) href="#style1")
SAX.internalSubset(doc, (null), doc.dtd)
SAX.startElement(doc)
SAX.characters(
, 1)
SAX.startElement(head)
SAX.characters(
, 1)
SAX.startElement(xsl:stylesheet, id='style1', version='1.0', xmlns:xsl='http://www.w3.org/1999/XSL/Transform', xmlns:fo='http://www.w3.org/1999/XSL/Format')
SAX.characters(
, 1)
SAX.startElement(xsl:import, href='doc.xsl')
SAX.endElement(xsl:import)
SAX.characters(
, 1)
SAX.startElement(xsl:template, match='id('foo')')
SAX.characters(
, 1)
SAX.startElement(fo:block, font-weight='bold')
SAX.startElement(xsl:apply-templates)
SAX.endElement(xsl:apply-templates)
SAX.endElement(fo:block)
SAX.characters(
, 1)
SAX.endElement(xsl:template)
SAX.characters(
, 1)
SAX.startElement(xsl:template, match='xsl:stylesheet')
SAX.characters(
, 1)
SAX.comment( ignore )
SAX.characters(
, 1)
SAX.endElement(xsl:template)
SAX.characters(
, 1)
SAX.endElement(xsl:stylesheet)
SAX.characters(
, 1)
SAX.endElement(head)
SAX.characters(
, 1)
SAX.startElement(body)
SAX.characters(
, 1)
SAX.startElement(para, id='foo')
SAX.characters(
...
, 5)
SAX.endElement(para)
SAX.characters(
, 1)
SAX.endElement(body)
SAX.characters(
, 1)
SAX.endElement(doc)
SAX.endDocument() SAX.endDocument()

5
error.c
View File

@ -46,6 +46,7 @@ xmlParserPrintFileContext(xmlParserInputPtr input) {
const xmlChar *cur, *base; const xmlChar *cur, *base;
int n; int n;
if (input == NULL) return;
cur = input->cur; cur = input->cur;
base = input->base; base = input->base;
while ((cur > base) && ((*cur == '\n') || (*cur == '\r'))) { while ((cur > base) && ((*cur == '\n') || (*cur == '\r'))) {
@ -91,7 +92,7 @@ xmlParserError(void *ctx, const char *msg, ...)
va_list args; va_list args;
input = ctxt->input; input = ctxt->input;
if ((input->filename == NULL) && (ctxt->inputNr > 1)) { if ((input != NULL) && (input->filename == NULL) && (ctxt->inputNr > 1)) {
cur = input; cur = input;
input = ctxt->inputTab[ctxt->inputNr - 2]; input = ctxt->inputTab[ctxt->inputNr - 2];
} }
@ -129,7 +130,7 @@ xmlParserWarning(void *ctx, const char *msg, ...)
va_list args; va_list args;
input = ctxt->input; input = ctxt->input;
if ((input->filename == NULL) && (ctxt->inputNr > 1)) { if ((input != NULL) && (input->filename == NULL) && (ctxt->inputNr > 1)) {
cur = input; cur = input;
input = ctxt->inputTab[ctxt->inputNr - 2]; input = ctxt->inputTab[ctxt->inputNr - 2];
} }

13
include/libxml/parser.h
View File

@ -50,10 +50,6 @@ typedef struct xmlParserInput {
} xmlParserInput; } xmlParserInput;
typedef xmlParserInput *xmlParserInputPtr; typedef xmlParserInput *xmlParserInputPtr;
typedef xmlParserInputPtr (*xmlExternalEntityLoader)(const char *URL,
const char *ID,
xmlParserInputPtr context);
/** /**
* the parser can be asked to collect Node informations, i.e. at what * the parser can be asked to collect Node informations, i.e. at what
* place in the file they were detected. * place in the file they were detected.
@ -255,6 +251,13 @@ typedef struct xmlSAXHandler {
} xmlSAXHandler; } xmlSAXHandler;
typedef xmlSAXHandler *xmlSAXHandlerPtr; typedef xmlSAXHandler *xmlSAXHandlerPtr;
/**
* External entity loaders types
*/
typedef xmlParserInputPtr (*xmlExternalEntityLoader)(const char *URL,
const char *ID,
xmlParserCtxtPtr context);
/** /**
* Global variables: just the default SAX interface tables and XML * Global variables: just the default SAX interface tables and XML
* version infos. * version infos.
@ -407,7 +410,7 @@ xmlExternalEntityLoader
xmlParserInputPtr xmlParserInputPtr
xmlLoadExternalEntity (const char *URL, xmlLoadExternalEntity (const char *URL,
const char *ID, const char *ID,
xmlParserInputPtr context); xmlParserCtxtPtr context);
#ifdef __cplusplus #ifdef __cplusplus
} }

1
include/libxml/tree.h
View File

@ -449,6 +449,7 @@ void xmlTextConcat (xmlNodePtr node,
int len); int len);
void xmlFreeNodeList (xmlNodePtr cur); void xmlFreeNodeList (xmlNodePtr cur);
void xmlFreeNode (xmlNodePtr cur); void xmlFreeNode (xmlNodePtr cur);
int xmlRemoveProp (xmlAttrPtr cur);
/* /*
* Namespaces * Namespaces

1
nanohttp.c
View File

@ -15,6 +15,7 @@
fly with ZLIB if found at compile-time */ fly with ZLIB if found at compile-time */
#ifdef WIN32 #ifdef WIN32
#define INCLUDE_WINSOCKS
#include "win32config.h" #include "win32config.h"
#else #else
#include "config.h" #include "config.h"

25
parser.c
View File

@ -344,6 +344,8 @@ PUSH_AND_POP(extern, xmlChar*, name)
#define SKIP_BLANKS \ #define SKIP_BLANKS \
do { \ do { \
while (IS_BLANK(CUR)) NEXT; \ while (IS_BLANK(CUR)) NEXT; \
while ((CUR == 0) && (ctxt->inputNr > 1)) \
xmlPopInput(ctxt); \
if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \ if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \
if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); \ if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); \
} while (IS_BLANK(CUR)); } while (IS_BLANK(CUR));
@ -494,7 +496,7 @@ xmlNewEntityInputStream(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) {
case XML_EXTERNAL_GENERAL_PARSED_ENTITY: case XML_EXTERNAL_GENERAL_PARSED_ENTITY:
case XML_EXTERNAL_PARAMETER_ENTITY: case XML_EXTERNAL_PARAMETER_ENTITY:
return(xmlLoadExternalEntity((char *) entity->SystemID, return(xmlLoadExternalEntity((char *) entity->SystemID,
(char *) entity->ExternalID, ctxt->input)); (char *) entity->ExternalID, ctxt));
case XML_INTERNAL_GENERAL_ENTITY: case XML_INTERNAL_GENERAL_ENTITY:
if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
ctxt->sax->error(ctxt->userData, ctxt->sax->error(ctxt->userData,
@ -584,7 +586,7 @@ xmlNewInputFromFile(xmlParserCtxtPtr ctxt, const char *filename) {
buf = xmlParserInputBufferCreateFilename(name, buf = xmlParserInputBufferCreateFilename(name,
XML_CHAR_ENCODING_NONE); XML_CHAR_ENCODING_NONE);
if (buf != NULL) if (buf != NULL)
directory = xmlMemStrdup(ctxt->input->directory); directory = xmlParserGetDirectory(name);
} }
if ((buf == NULL) && (ctxt->directory != NULL)) { if ((buf == NULL) && (ctxt->directory != NULL)) {
#ifdef WIN32 #ifdef WIN32
@ -595,7 +597,7 @@ xmlNewInputFromFile(xmlParserCtxtPtr ctxt, const char *filename) {
buf = xmlParserInputBufferCreateFilename(name, buf = xmlParserInputBufferCreateFilename(name,
XML_CHAR_ENCODING_NONE); XML_CHAR_ENCODING_NONE);
if (buf != NULL) if (buf != NULL)
directory = xmlMemStrdup(ctxt->directory); directory = xmlParserGetDirectory(name);
} }
if (buf == NULL) if (buf == NULL)
return(NULL); return(NULL);
@ -4665,7 +4667,15 @@ xmlParseElementDecl(xmlParserCtxtPtr ctxt) {
if (name != NULL) xmlFree(name); if (name != NULL) xmlFree(name);
return(-1); return(-1);
} }
SKIP_BLANKS; SKIP_BLANKS;
/*
* Pop-up of finished entities.
*/
while ((CUR == 0) && (ctxt->inputNr > 1))
xmlPopInput(ctxt);
SKIP_BLANKS;
if (CUR != '>') { if (CUR != '>') {
if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
ctxt->sax->error(ctxt->userData, ctxt->sax->error(ctxt->userData,
@ -6838,19 +6848,17 @@ xmlParseDocument(xmlParserCtxtPtr ctxt) {
GROW; GROW;
if ((CUR == '<') && (NXT(1) == '?') && if ((CUR == '<') && (NXT(1) == '?') &&
(NXT(2) == 'x') && (NXT(3) == 'm') && (NXT(2) == 'x') && (NXT(3) == 'm') &&
(NXT(4) == 'l')) { (NXT(4) == 'l') && (IS_BLANK(NXT(5)))) {
xmlParseXMLDecl(ctxt); xmlParseXMLDecl(ctxt);
/* SKIP_EOL(cur); */
SKIP_BLANKS; SKIP_BLANKS;
} else if ((CUR == '<') && (NXT(1) == '?') && } else if ((CUR == '<') && (NXT(1) == '?') &&
(NXT(2) == 'X') && (NXT(3) == 'M') && (NXT(2) == 'X') && (NXT(3) == 'M') &&
(NXT(4) == 'L')) { (NXT(4) == 'L') && (IS_BLANK(NXT(5)))) {
/* /*
* The first drafts were using <?XML and the final W3C REC * The first drafts were using <?XML and the final W3C REC
* now use <?xml ... * now use <?xml ...
*/ */
xmlParseXMLDecl(ctxt); xmlParseXMLDecl(ctxt);
/* SKIP_EOL(cur); */
SKIP_BLANKS; SKIP_BLANKS;
} else { } else {
ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION); ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION);
@ -7127,7 +7135,8 @@ xmlParseTry(xmlParserCtxtPtr ctxt) {
&xmlDefaultSAXLocator); &xmlDefaultSAXLocator);
if ((in->cur[2] == 'x') && if ((in->cur[2] == 'x') &&
(in->cur[3] == 'm') && (in->cur[3] == 'm') &&
(in->cur[4] == 'l')) { (in->cur[4] == 'l') &&
(IS_BLANK(in->cur[5]))) {
ret += 5; ret += 5;
#ifdef DEBUG_PUSH #ifdef DEBUG_PUSH
fprintf(stderr, "PP: Parsing XML Decl\n"); fprintf(stderr, "PP: Parsing XML Decl\n");

13
parser.h
View File

@ -50,10 +50,6 @@ typedef struct xmlParserInput {
} xmlParserInput; } xmlParserInput;
typedef xmlParserInput *xmlParserInputPtr; typedef xmlParserInput *xmlParserInputPtr;
typedef xmlParserInputPtr (*xmlExternalEntityLoader)(const char *URL,
const char *ID,
xmlParserInputPtr context);
/** /**
* the parser can be asked to collect Node informations, i.e. at what * the parser can be asked to collect Node informations, i.e. at what
* place in the file they were detected. * place in the file they were detected.
@ -255,6 +251,13 @@ typedef struct xmlSAXHandler {
} xmlSAXHandler; } xmlSAXHandler;
typedef xmlSAXHandler *xmlSAXHandlerPtr; typedef xmlSAXHandler *xmlSAXHandlerPtr;
/**
* External entity loaders types
*/
typedef xmlParserInputPtr (*xmlExternalEntityLoader)(const char *URL,
const char *ID,
xmlParserCtxtPtr context);
/** /**
* Global variables: just the default SAX interface tables and XML * Global variables: just the default SAX interface tables and XML
* version infos. * version infos.
@ -407,7 +410,7 @@ xmlExternalEntityLoader
xmlParserInputPtr xmlParserInputPtr
xmlLoadExternalEntity (const char *URL, xmlLoadExternalEntity (const char *URL,
const char *ID, const char *ID,
xmlParserInputPtr context); xmlParserCtxtPtr context);
#ifdef __cplusplus #ifdef __cplusplus
} }

24
result/noent/ns4
View File

@ -1,2 +1,24 @@
<?xml version="1.0"?> <?xml version="1.0"?>
<diagram xml:lang="en" xml:link="simple" xml:space="preserve" testattr="test"/> <!DOCTYPE doc SYSTEM "doc.dtd">
<?xml-stylesheet type="text/xml"
href="#style1"?>
<doc>
<head>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:fo="http://www.w3.org/1999/XSL/Format" id="style1" version="1.0">
<xsl:import href="doc.xsl"/>
<xsl:template match="id(&apos;foo&apos;)">
<fo:block font-weight="bold">
<xsl:apply-templates/>
</fo:block>
</xsl:template>
<xsl:template match="xsl:stylesheet">
<!-- ignore -->
</xsl:template>
</xsl:stylesheet>
</head>
<body>
<para id="foo">
...
</para>
</body>
</doc>

24
result/ns4
View File

@ -1,2 +1,24 @@
<?xml version="1.0"?> <?xml version="1.0"?>
<diagram xml:lang="en" xml:link="simple" xml:space="preserve" testattr="test"/> <!DOCTYPE doc SYSTEM "doc.dtd">
<?xml-stylesheet type="text/xml"
href="#style1"?>
<doc>
<head>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:fo="http://www.w3.org/1999/XSL/Format" id="style1" version="1.0">
<xsl:import href="doc.xsl"/>
<xsl:template match="id(&apos;foo&apos;)">
<fo:block font-weight="bold">
<xsl:apply-templates/>
</fo:block>
</xsl:template>
<xsl:template match="xsl:stylesheet">
<!-- ignore -->
</xsl:template>
</xsl:stylesheet>
</head>
<body>
<para id="foo">
...
</para>
</body>
</doc>

1287
result/valid/xhtml1.xhtml Normal file
View File

File diff suppressed because it is too large Load Diff

0
result/valid/xhtml1.xhtml.err Normal file
View File

26
test/ns4
View File

@ -1,2 +1,24 @@
<?xml version="1.0"?> <?xml-stylesheet type="text/xml"
<diagram testattr="test" xml:lang="en" xml:link="simple" xml:space="preserve"/> href="#style1"?>
<!DOCTYPE doc SYSTEM "doc.dtd">
<doc>
<head>
<xsl:stylesheet id="style1"
version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:fo="http://www.w3.org/1999/XSL/Format">
<xsl:import href="doc.xsl"/>
<xsl:template match="id('foo')">
<fo:block font-weight="bold"><xsl:apply-templates/></fo:block>
</xsl:template>
<xsl:template match="xsl:stylesheet">
<!-- ignore -->
</xsl:template>
</xsl:stylesheet>
</head>
<body>
<para id="foo">
...
</para>
</body>
</doc>

196
test/valid/dtds/xhtml-lat1.ent Normal file
View File

@ -0,0 +1,196 @@
<!-- Portions (C) International Organization for Standardization 1986
Permission to copy in any form is granted for use with
conforming SGML systems and applications as defined in
ISO 8879, provided this notice is included in all copies.
-->
<!-- Character entity set. Typical invocation:
<!ENTITY % HTMLlat1 PUBLIC
"-//W3C//ENTITIES Latin 1 for XHTML//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml-lat1.ent">
%HTMLlat1;
-->
<!ENTITY nbsp "&#160;"> <!-- no-break space = non-breaking space,
U+00A0 ISOnum -->
<!ENTITY iexcl "&#161;"> <!-- inverted exclamation mark, U+00A1 ISOnum -->
<!ENTITY cent "&#162;"> <!-- cent sign, U+00A2 ISOnum -->
<!ENTITY pound "&#163;"> <!-- pound sign, U+00A3 ISOnum -->
<!ENTITY curren "&#164;"> <!-- currency sign, U+00A4 ISOnum -->
<!ENTITY yen "&#165;"> <!-- yen sign = yuan sign, U+00A5 ISOnum -->
<!ENTITY brvbar "&#166;"> <!-- broken bar = broken vertical bar,
U+00A6 ISOnum -->
<!ENTITY sect "&#167;"> <!-- section sign, U+00A7 ISOnum -->
<!ENTITY uml "&#168;"> <!-- diaeresis = spacing diaeresis,
U+00A8 ISOdia -->
<!ENTITY copy "&#169;"> <!-- copyright sign, U+00A9 ISOnum -->
<!ENTITY ordf "&#170;"> <!-- feminine ordinal indicator, U+00AA ISOnum -->
<!ENTITY laquo "&#171;"> <!-- left-pointing double angle quotation mark
= left pointing guillemet, U+00AB ISOnum -->
<!ENTITY not "&#172;"> <!-- not sign = discretionary hyphen,
U+00AC ISOnum -->
<!ENTITY shy "&#173;"> <!-- soft hyphen = discretionary hyphen,
U+00AD ISOnum -->
<!ENTITY reg "&#174;"> <!-- registered sign = registered trade mark sign,
U+00AE ISOnum -->
<!ENTITY macr "&#175;"> <!-- macron = spacing macron = overline
= APL overbar, U+00AF ISOdia -->
<!ENTITY deg "&#176;"> <!-- degree sign, U+00B0 ISOnum -->
<!ENTITY plusmn "&#177;"> <!-- plus-minus sign = plus-or-minus sign,
U+00B1 ISOnum -->
<!ENTITY sup2 "&#178;"> <!-- superscript two = superscript digit two
= squared, U+00B2 ISOnum -->
<!ENTITY sup3 "&#179;"> <!-- superscript three = superscript digit three
= cubed, U+00B3 ISOnum -->
<!ENTITY acute "&#180;"> <!-- acute accent = spacing acute,
U+00B4 ISOdia -->
<!ENTITY micro "&#181;"> <!-- micro sign, U+00B5 ISOnum -->
<!ENTITY para "&#182;"> <!-- pilcrow sign = paragraph sign,
U+00B6 ISOnum -->
<!ENTITY middot "&#183;"> <!-- middle dot = Georgian comma
= Greek middle dot, U+00B7 ISOnum -->
<!ENTITY cedil "&#184;"> <!-- cedilla = spacing cedilla, U+00B8 ISOdia -->
<!ENTITY sup1 "&#185;"> <!-- superscript one = superscript digit one,
U+00B9 ISOnum -->
<!ENTITY ordm "&#186;"> <!-- masculine ordinal indicator,
U+00BA ISOnum -->
<!ENTITY raquo "&#187;"> <!-- right-pointing double angle quotation mark
= right pointing guillemet, U+00BB ISOnum -->
<!ENTITY frac14 "&#188;"> <!-- vulgar fraction one quarter
= fraction one quarter, U+00BC ISOnum -->
<!ENTITY frac12 "&#189;"> <!-- vulgar fraction one half
= fraction one half, U+00BD ISOnum -->
<!ENTITY frac34 "&#190;"> <!-- vulgar fraction three quarters
= fraction three quarters, U+00BE ISOnum -->
<!ENTITY iquest "&#191;"> <!-- inverted question mark
= turned question mark, U+00BF ISOnum -->
<!ENTITY Agrave "&#192;"> <!-- latin capital letter A with grave
= latin capital letter A grave,
U+00C0 ISOlat1 -->
<!ENTITY Aacute "&#193;"> <!-- latin capital letter A with acute,
U+00C1 ISOlat1 -->
<!ENTITY Acirc "&#194;"> <!-- latin capital letter A with circumflex,
U+00C2 ISOlat1 -->
<!ENTITY Atilde "&#195;"> <!-- latin capital letter A with tilde,
U+00C3 ISOlat1 -->
<!ENTITY Auml "&#196;"> <!-- latin capital letter A with diaeresis,
U+00C4 ISOlat1 -->
<!ENTITY Aring "&#197;"> <!-- latin capital letter A with ring above
= latin capital letter A ring,
U+00C5 ISOlat1 -->
<!ENTITY AElig "&#198;"> <!-- latin capital letter AE
= latin capital ligature AE,
U+00C6 ISOlat1 -->
<!ENTITY Ccedil "&#199;"> <!-- latin capital letter C with cedilla,
U+00C7 ISOlat1 -->
<!ENTITY Egrave "&#200;"> <!-- latin capital letter E with grave,
U+00C8 ISOlat1 -->
<!ENTITY Eacute "&#201;"> <!-- latin capital letter E with acute,
U+00C9 ISOlat1 -->
<!ENTITY Ecirc "&#202;"> <!-- latin capital letter E with circumflex,
U+00CA ISOlat1 -->
<!ENTITY Euml "&#203;"> <!-- latin capital letter E with diaeresis,
U+00CB ISOlat1 -->
<!ENTITY Igrave "&#204;"> <!-- latin capital letter I with grave,
U+00CC ISOlat1 -->
<!ENTITY Iacute "&#205;"> <!-- latin capital letter I with acute,
U+00CD ISOlat1 -->
<!ENTITY Icirc "&#206;"> <!-- latin capital letter I with circumflex,
U+00CE ISOlat1 -->
<!ENTITY Iuml "&#207;"> <!-- latin capital letter I with diaeresis,
U+00CF ISOlat1 -->
<!ENTITY ETH "&#208;"> <!-- latin capital letter ETH, U+00D0 ISOlat1 -->
<!ENTITY Ntilde "&#209;"> <!-- latin capital letter N with tilde,
U+00D1 ISOlat1 -->
<!ENTITY Ograve "&#210;"> <!-- latin capital letter O with grave,
U+00D2 ISOlat1 -->
<!ENTITY Oacute "&#211;"> <!-- latin capital letter O with acute,
U+00D3 ISOlat1 -->
<!ENTITY Ocirc "&#212;"> <!-- latin capital letter O with circumflex,
U+00D4 ISOlat1 -->
<!ENTITY Otilde "&#213;"> <!-- latin capital letter O with tilde,
U+00D5 ISOlat1 -->
<!ENTITY Ouml "&#214;"> <!-- latin capital letter O with diaeresis,
U+00D6 ISOlat1 -->
<!ENTITY times "&#215;"> <!-- multiplication sign, U+00D7 ISOnum -->
<!ENTITY Oslash "&#216;"> <!-- latin capital letter O with stroke
= latin capital letter O slash,
U+00D8 ISOlat1 -->
<!ENTITY Ugrave "&#217;"> <!-- latin capital letter U with grave,
U+00D9 ISOlat1 -->
<!ENTITY Uacute "&#218;"> <!-- latin capital letter U with acute,
U+00DA ISOlat1 -->
<!ENTITY Ucirc "&#219;"> <!-- latin capital letter U with circumflex,
U+00DB ISOlat1 -->
<!ENTITY Uuml "&#220;"> <!-- latin capital letter U with diaeresis,
U+00DC ISOlat1 -->
<!ENTITY Yacute "&#221;"> <!-- latin capital letter Y with acute,
U+00DD ISOlat1 -->
<!ENTITY THORN "&#222;"> <!-- latin capital letter THORN,
U+00DE ISOlat1 -->
<!ENTITY szlig "&#223;"> <!-- latin small letter sharp s = ess-zed,
U+00DF ISOlat1 -->
<!ENTITY agrave "&#224;"> <!-- latin small letter a with grave
= latin small letter a grave,
U+00E0 ISOlat1 -->
<!ENTITY aacute "&#225;"> <!-- latin small letter a with acute,
U+00E1 ISOlat1 -->
<!ENTITY acirc "&#226;"> <!-- latin small letter a with circumflex,
U+00E2 ISOlat1 -->
<!ENTITY atilde "&#227;"> <!-- latin small letter a with tilde,
U+00E3 ISOlat1 -->
<!ENTITY auml "&#228;"> <!-- latin small letter a with diaeresis,
U+00E4 ISOlat1 -->
<!ENTITY aring "&#229;"> <!-- latin small letter a with ring above
= latin small letter a ring,
U+00E5 ISOlat1 -->
<!ENTITY aelig "&#230;"> <!-- latin small letter ae
= latin small ligature ae, U+00E6 ISOlat1 -->
<!ENTITY ccedil "&#231;"> <!-- latin small letter c with cedilla,
U+00E7 ISOlat1 -->
<!ENTITY egrave "&#232;"> <!-- latin small letter e with grave,
U+00E8 ISOlat1 -->
<!ENTITY eacute "&#233;"> <!-- latin small letter e with acute,
U+00E9 ISOlat1 -->
<!ENTITY ecirc "&#234;"> <!-- latin small letter e with circumflex,
U+00EA ISOlat1 -->
<!ENTITY euml "&#235;"> <!-- latin small letter e with diaeresis,
U+00EB ISOlat1 -->
<!ENTITY igrave "&#236;"> <!-- latin small letter i with grave,
U+00EC ISOlat1 -->
<!ENTITY iacute "&#237;"> <!-- latin small letter i with acute,
U+00ED ISOlat1 -->
<!ENTITY icirc "&#238;"> <!-- latin small letter i with circumflex,
U+00EE ISOlat1 -->
<!ENTITY iuml "&#239;"> <!-- latin small letter i with diaeresis,
U+00EF ISOlat1 -->
<!ENTITY eth "&#240;"> <!-- latin small letter eth, U+00F0 ISOlat1 -->
<!ENTITY ntilde "&#241;"> <!-- latin small letter n with tilde,
U+00F1 ISOlat1 -->
<!ENTITY ograve "&#242;"> <!-- latin small letter o with grave,
U+00F2 ISOlat1 -->
<!ENTITY oacute "&#243;"> <!-- latin small letter o with acute,
U+00F3 ISOlat1 -->
<!ENTITY ocirc "&#244;"> <!-- latin small letter o with circumflex,
U+00F4 ISOlat1 -->
<!ENTITY otilde "&#245;"> <!-- latin small letter o with tilde,
U+00F5 ISOlat1 -->
<!ENTITY ouml "&#246;"> <!-- latin small letter o with diaeresis,
U+00F6 ISOlat1 -->
<!ENTITY divide "&#247;"> <!-- division sign, U+00F7 ISOnum -->
<!ENTITY oslash "&#248;"> <!-- latin small letter o with stroke,
= latin small letter o slash,
U+00F8 ISOlat1 -->
<!ENTITY ugrave "&#249;"> <!-- latin small letter u with grave,
U+00F9 ISOlat1 -->
<!ENTITY uacute "&#250;"> <!-- latin small letter u with acute,
U+00FA ISOlat1 -->
<!ENTITY ucirc "&#251;"> <!-- latin small letter u with circumflex,
U+00FB ISOlat1 -->
<!ENTITY uuml "&#252;"> <!-- latin small letter u with diaeresis,
U+00FC ISOlat1 -->
<!ENTITY yacute "&#253;"> <!-- latin small letter y with acute,
U+00FD ISOlat1 -->
<!ENTITY thorn "&#254;"> <!-- latin small letter thorn with,
U+00FE ISOlat1 -->
<!ENTITY yuml "&#255;"> <!-- latin small letter y with diaeresis,
U+00FF ISOlat1 -->

79
test/valid/dtds/xhtml-special.ent Normal file
View File

@ -0,0 +1,79 @@
<!-- Special characters for HTML -->
<!-- Character entity set. Typical invocation:
<!ENTITY % HTMLspecial PUBLIC
"-//W3C//ENTITIES Special for XHTML//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml-special.ent">
%HTMLspecial;
-->
<!-- Portions (C) International Organization for Standardization 1986:
Permission to copy in any form is granted for use with
conforming SGML systems and applications as defined in
ISO 8879, provided this notice is included in all copies.
-->
<!-- Relevant ISO entity set is given unless names are newly introduced.
New names (i.e., not in ISO 8879 list) do not clash with any
existing ISO 8879 entity names. ISO 10646 character numbers
are given for each character, in hex. values are decimal
conversions of the ISO 10646 values and refer to the document
character set. Names are Unicode names.
-->
<!-- C0 Controls and Basic Latin -->
<!ENTITY quot "&#34;"> <!-- quotation mark = APL quote,
U+0022 ISOnum -->
<!ENTITY amp "&#38;#38;"> <!-- ampersand, U+0026 ISOnum -->
<!ENTITY lt "&#38;#60;"> <!-- less-than sign, U+003C ISOnum -->
<!ENTITY gt "&#62;"> <!-- greater-than sign, U+003E ISOnum -->
<!ENTITY apos "&#39;"> <!-- apostrophe mark, U+0027 ISOnum -->
<!-- Latin Extended-A -->
<!ENTITY OElig "&#338;"> <!-- latin capital ligature OE,
U+0152 ISOlat2 -->
<!ENTITY oelig "&#339;"> <!-- latin small ligature oe, U+0153 ISOlat2 -->
<!-- ligature is a misnomer, this is a separate character in some languages -->
<!ENTITY Scaron "&#352;"> <!-- latin capital letter S with caron,
U+0160 ISOlat2 -->
<!ENTITY scaron "&#353;"> <!-- latin small letter s with caron,
U+0161 ISOlat2 -->
<!ENTITY Yuml "&#376;"> <!-- latin capital letter Y with diaeresis,
U+0178 ISOlat2 -->
<!-- Spacing Modifier Letters -->
<!ENTITY circ "&#710;"> <!-- modifier letter circumflex accent,
U+02C6 ISOpub -->
<!ENTITY tilde "&#732;"> <!-- small tilde, U+02DC ISOdia -->
<!-- General Punctuation -->
<!ENTITY ensp "&#8194;"> <!-- en space, U+2002 ISOpub -->
<!ENTITY emsp "&#8195;"> <!-- em space, U+2003 ISOpub -->
<!ENTITY thinsp "&#8201;"> <!-- thin space, U+2009 ISOpub -->
<!ENTITY zwnj "&#8204;"> <!-- zero width non-joiner,
U+200C NEW RFC 2070 -->
<!ENTITY zwj "&#8205;"> <!-- zero width joiner, U+200D NEW RFC 2070 -->
<!ENTITY lrm "&#8206;"> <!-- left-to-right mark, U+200E NEW RFC 2070 -->
<!ENTITY rlm "&#8207;"> <!-- right-to-left mark, U+200F NEW RFC 2070 -->
<!ENTITY ndash "&#8211;"> <!-- en dash, U+2013 ISOpub -->
<!ENTITY mdash "&#8212;"> <!-- em dash, U+2014 ISOpub -->
<!ENTITY lsquo "&#8216;"> <!-- left single quotation mark,
U+2018 ISOnum -->
<!ENTITY rsquo "&#8217;"> <!-- right single quotation mark,
U+2019 ISOnum -->
<!ENTITY sbquo "&#8218;"> <!-- single low-9 quotation mark, U+201A NEW -->
<!ENTITY ldquo "&#8220;"> <!-- left double quotation mark,
U+201C ISOnum -->
<!ENTITY rdquo "&#8221;"> <!-- right double quotation mark,
U+201D ISOnum -->
<!ENTITY bdquo "&#8222;"> <!-- double low-9 quotation mark, U+201E NEW -->
<!ENTITY dagger "&#8224;"> <!-- dagger, U+2020 ISOpub -->
<!ENTITY Dagger "&#8225;"> <!-- double dagger, U+2021 ISOpub -->
<!ENTITY permil "&#8240;"> <!-- per mille sign, U+2030 ISOtech -->
<!ENTITY lsaquo "&#8249;"> <!-- single left-pointing angle quotation mark,
U+2039 ISO proposed -->
<!-- lsaquo is proposed but not yet ISO standardized -->
<!ENTITY rsaquo "&#8250;"> <!-- single right-pointing angle quotation mark,
U+203A ISO proposed -->
<!-- rsaquo is proposed but not yet ISO standardized -->
<!ENTITY euro "&#8364;"> <!-- euro sign, U+20AC NEW -->

242
test/valid/dtds/xhtml-symbol.ent Normal file
View File

@ -0,0 +1,242 @@
<!-- Mathematical, Greek and Symbolic characters for HTML -->
<!-- Character entity set. Typical invocation:
<!ENTITY % HTMLsymbol PUBLIC
"-//W3C//ENTITIES Symbols for XHTML//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml-symbol.ent">
%HTMLsymbol;
-->
<!-- Portions (C) International Organization for Standardization 1986:
Permission to copy in any form is granted for use with
conforming SGML systems and applications as defined in
ISO 8879, provided this notice is included in all copies.
-->
<!-- Relevant ISO entity set is given unless names are newly introduced.
New names (i.e., not in ISO 8879 list) do not clash with any
existing ISO 8879 entity names. ISO 10646 character numbers
are given for each character, in hex. values are decimal
conversions of the ISO 10646 values and refer to the document
character set. Names are Unicode names.
-->
<!-- Latin Extended-B -->
<!ENTITY fnof "&#402;"> <!-- latin small f with hook = function
= florin, U+0192 ISOtech -->
<!-- Greek -->
<!ENTITY Alpha "&#913;"> <!-- greek capital letter alpha, U+0391 -->
<!ENTITY Beta "&#914;"> <!-- greek capital letter beta, U+0392 -->
<!ENTITY Gamma "&#915;"> <!-- greek capital letter gamma,
U+0393 ISOgrk3 -->
<!ENTITY Delta "&#916;"> <!-- greek capital letter delta,
U+0394 ISOgrk3 -->
<!ENTITY Epsilon "&#917;"> <!-- greek capital letter epsilon, U+0395 -->
<!ENTITY Zeta "&#918;"> <!-- greek capital letter zeta, U+0396 -->
<!ENTITY Eta "&#919;"> <!-- greek capital letter eta, U+0397 -->
<!ENTITY Theta "&#920;"> <!-- greek capital letter theta,
U+0398 ISOgrk3 -->
<!ENTITY Iota "&#921;"> <!-- greek capital letter iota, U+0399 -->
<!ENTITY Kappa "&#922;"> <!-- greek capital letter kappa, U+039A -->
<!ENTITY Lambda "&#923;"> <!-- greek capital letter lambda,
U+039B ISOgrk3 -->
<!ENTITY Mu "&#924;"> <!-- greek capital letter mu, U+039C -->
<!ENTITY Nu "&#925;"> <!-- greek capital letter nu, U+039D -->
<!ENTITY Xi "&#926;"> <!-- greek capital letter xi, U+039E ISOgrk3 -->
<!ENTITY Omicron "&#927;"> <!-- greek capital letter omicron, U+039F -->
<!ENTITY Pi "&#928;"> <!-- greek capital letter pi, U+03A0 ISOgrk3 -->
<!ENTITY Rho "&#929;"> <!-- greek capital letter rho, U+03A1 -->
<!-- there is no Sigmaf, and no U+03A2 character either -->
<!ENTITY Sigma "&#931;"> <!-- greek capital letter sigma,
U+03A3 ISOgrk3 -->
<!ENTITY Tau "&#932;"> <!-- greek capital letter tau, U+03A4 -->
<!ENTITY Upsilon "&#933;"> <!-- greek capital letter upsilon,
U+03A5 ISOgrk3 -->
<!ENTITY Phi "&#934;"> <!-- greek capital letter phi,
U+03A6 ISOgrk3 -->
<!ENTITY Chi "&#935;"> <!-- greek capital letter chi, U+03A7 -->
<!ENTITY Psi "&#936;"> <!-- greek capital letter psi,
U+03A8 ISOgrk3 -->
<!ENTITY Omega "&#937;"> <!-- greek capital letter omega,
U+03A9 ISOgrk3 -->
<!ENTITY alpha "&#945;"> <!-- greek small letter alpha,
U+03B1 ISOgrk3 -->
<!ENTITY beta "&#946;"> <!-- greek small letter beta, U+03B2 ISOgrk3 -->
<!ENTITY gamma "&#947;"> <!-- greek small letter gamma,
U+03B3 ISOgrk3 -->
<!ENTITY delta "&#948;"> <!-- greek small letter delta,
U+03B4 ISOgrk3 -->
<!ENTITY epsilon "&#949;"> <!-- greek small letter epsilon,
U+03B5 ISOgrk3 -->
<!ENTITY zeta "&#950;"> <!-- greek small letter zeta, U+03B6 ISOgrk3 -->
<!ENTITY eta "&#951;"> <!-- greek small letter eta, U+03B7 ISOgrk3 -->
<!ENTITY theta "&#952;"> <!-- greek small letter theta,
U+03B8 ISOgrk3 -->
<!ENTITY iota "&#953;"> <!-- greek small letter iota, U+03B9 ISOgrk3 -->
<!ENTITY kappa "&#954;"> <!-- greek small letter kappa,
U+03BA ISOgrk3 -->
<!ENTITY lambda "&#955;"> <!-- greek small letter lambda,
U+03BB ISOgrk3 -->
<!ENTITY mu "&#956;"> <!-- greek small letter mu, U+03BC ISOgrk3 -->
<!ENTITY nu "&#957;"> <!-- greek small letter nu, U+03BD ISOgrk3 -->
<!ENTITY xi "&#958;"> <!-- greek small letter xi, U+03BE ISOgrk3 -->
<!ENTITY omicron "&#959;"> <!-- greek small letter omicron, U+03BF NEW -->
<!ENTITY pi "&#960;"> <!-- greek small letter pi, U+03C0 ISOgrk3 -->
<!ENTITY rho "&#961;"> <!-- greek small letter rho, U+03C1 ISOgrk3 -->
<!ENTITY sigmaf "&#962;"> <!-- greek small letter final sigma,
U+03C2 ISOgrk3 -->
<!ENTITY sigma "&#963;"> <!-- greek small letter sigma,
U+03C3 ISOgrk3 -->
<!ENTITY tau "&#964;"> <!-- greek small letter tau, U+03C4 ISOgrk3 -->
<!ENTITY upsilon "&#965;"> <!-- greek small letter upsilon,
U+03C5 ISOgrk3 -->
<!ENTITY phi "&#966;"> <!-- greek small letter phi, U+03C6 ISOgrk3 -->
<!ENTITY chi "&#967;"> <!-- greek small letter chi, U+03C7 ISOgrk3 -->
<!ENTITY psi "&#968;"> <!-- greek small letter psi, U+03C8 ISOgrk3 -->
<!ENTITY omega "&#969;"> <!-- greek small letter omega,
U+03C9 ISOgrk3 -->
<!ENTITY thetasym "&#977;"> <!-- greek small letter theta symbol,
U+03D1 NEW -->
<!ENTITY upsih "&#978;"> <!-- greek upsilon with hook symbol,
U+03D2 NEW -->
<!ENTITY piv "&#982;"> <!-- greek pi symbol, U+03D6 ISOgrk3 -->
<!-- General Punctuation -->
<!ENTITY bull "&#8226;"> <!-- bullet = black small circle,
U+2022 ISOpub -->
<!-- bullet is NOT the same as bullet operator, U+2219 -->
<!ENTITY hellip "&#8230;"> <!-- horizontal ellipsis = three dot leader,
U+2026 ISOpub -->
<!ENTITY prime "&#8242;"> <!-- prime = minutes = feet, U+2032 ISOtech -->
<!ENTITY Prime "&#8243;"> <!-- double prime = seconds = inches,
U+2033 ISOtech -->
<!ENTITY oline "&#8254;"> <!-- overline = spacing overscore,
U+203E NEW -->
<!ENTITY frasl "&#8260;"> <!-- fraction slash, U+2044 NEW -->
<!-- Letterlike Symbols -->
<!ENTITY weierp "&#8472;"> <!-- script capital P = power set
= Weierstrass p, U+2118 ISOamso -->
<!ENTITY image "&#8465;"> <!-- blackletter capital I = imaginary part,
U+2111 ISOamso -->
<!ENTITY real "&#8476;"> <!-- blackletter capital R = real part symbol,
U+211C ISOamso -->
<!ENTITY trade "&#8482;"> <!-- trade mark sign, U+2122 ISOnum -->
<!ENTITY alefsym "&#8501;"> <!-- alef symbol = first transfinite cardinal,
U+2135 NEW -->
<!-- alef symbol is NOT the same as hebrew letter alef,
U+05D0 although the same glyph could be used to depict both characters -->
<!-- Arrows -->
<!ENTITY larr "&#8592;"> <!-- leftwards arrow, U+2190 ISOnum -->
<!ENTITY uarr "&#8593;"> <!-- upwards arrow, U+2191 ISOnum-->
<!ENTITY rarr "&#8594;"> <!-- rightwards arrow, U+2192 ISOnum -->
<!ENTITY darr "&#8595;"> <!-- downwards arrow, U+2193 ISOnum -->
<!ENTITY harr "&#8596;"> <!-- left right arrow, U+2194 ISOamsa -->
<!ENTITY crarr "&#8629;"> <!-- downwards arrow with corner leftwards
= carriage return, U+21B5 NEW -->
<!ENTITY lArr "&#8656;"> <!-- leftwards double arrow, U+21D0 ISOtech -->
<!-- Unicode does not say that lArr is the same as the 'is implied by' arrow
but also does not have any other character for that function. So ? lArr can
be used for 'is implied by' as ISOtech suggests -->
<!ENTITY uArr "&#8657;"> <!-- upwards double arrow, U+21D1 ISOamsa -->
<!ENTITY rArr "&#8658;"> <!-- rightwards double arrow,
U+21D2 ISOtech -->
<!-- Unicode does not say this is the 'implies' character but does not have
another character with this function so ?
rArr can be used for 'implies' as ISOtech suggests -->
<!ENTITY dArr "&#8659;"> <!-- downwards double arrow, U+21D3 ISOamsa -->
<!ENTITY hArr "&#8660;"> <!-- left right double arrow,
U+21D4 ISOamsa -->
<!-- Mathematical Operators -->
<!ENTITY forall "&#8704;"> <!-- for all, U+2200 ISOtech -->
<!ENTITY part "&#8706;"> <!-- partial differential, U+2202 ISOtech -->
<!ENTITY exist "&#8707;"> <!-- there exists, U+2203 ISOtech -->
<!ENTITY empty "&#8709;"> <!-- empty set = null set = diameter,
U+2205 ISOamso -->
<!ENTITY nabla "&#8711;"> <!-- nabla = backward difference,
U+2207 ISOtech -->
<!ENTITY isin "&#8712;"> <!-- element of, U+2208 ISOtech -->
<!ENTITY notin "&#8713;"> <!-- not an element of, U+2209 ISOtech -->
<!ENTITY ni "&#8715;"> <!-- contains as member, U+220B ISOtech -->
<!-- should there be a more memorable name than 'ni'? -->
<!ENTITY prod "&#8719;"> <!-- n-ary product = product sign,
U+220F ISOamsb -->
<!-- prod is NOT the same character as U+03A0 'greek capital letter pi' though
the same glyph might be used for both -->
<!ENTITY sum "&#8721;"> <!-- n-ary sumation, U+2211 ISOamsb -->
<!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'
though the same glyph might be used for both -->
<!ENTITY minus "&#8722;"> <!-- minus sign, U+2212 ISOtech -->
<!ENTITY lowast "&#8727;"> <!-- asterisk operator, U+2217 ISOtech -->
<!ENTITY radic "&#8730;"> <!-- square root = radical sign,
U+221A ISOtech -->
<!ENTITY prop "&#8733;"> <!-- proportional to, U+221D ISOtech -->
<!ENTITY infin "&#8734;"> <!-- infinity, U+221E ISOtech -->
<!ENTITY ang "&#8736;"> <!-- angle, U+2220 ISOamso -->
<!ENTITY and "&#8743;"> <!-- logical and = wedge, U+2227 ISOtech -->
<!ENTITY or "&#8744;"> <!-- logical or = vee, U+2228 ISOtech -->
<!ENTITY cap "&#8745;"> <!-- intersection = cap, U+2229 ISOtech -->
<!ENTITY cup "&#8746;"> <!-- union = cup, U+222A ISOtech -->
<!ENTITY int "&#8747;"> <!-- integral, U+222B ISOtech -->
<!ENTITY there4 "&#8756;"> <!-- therefore, U+2234 ISOtech -->
<!ENTITY sim "&#8764;"> <!-- tilde operator = varies with = similar to,
U+223C ISOtech -->
<!-- tilde operator is NOT the same character as the tilde, U+007E,
although the same glyph might be used to represent both -->
<!ENTITY cong "&#8773;"> <!-- approximately equal to, U+2245 ISOtech -->
<!ENTITY asymp "&#8776;"> <!-- almost equal to = asymptotic to,
U+2248 ISOamsr -->
<!ENTITY ne "&#8800;"> <!-- not equal to, U+2260 ISOtech -->
<!ENTITY equiv "&#8801;"> <!-- identical to, U+2261 ISOtech -->
<!ENTITY le "&#8804;"> <!-- less-than or equal to, U+2264 ISOtech -->
<!ENTITY ge "&#8805;"> <!-- greater-than or equal to,
U+2265 ISOtech -->
<!ENTITY sub "&#8834;"> <!-- subset of, U+2282 ISOtech -->
<!ENTITY sup "&#8835;"> <!-- superset of, U+2283 ISOtech -->
<!-- note that nsup, 'not a superset of, U+2283' is not covered by the Symbol
font encoding and is not included. Should it be, for symmetry?
It is in ISOamsn -->
<!ENTITY nsub "&#8836;"> <!-- not a subset of, U+2284 ISOamsn -->
<!ENTITY sube "&#8838;"> <!-- subset of or equal to, U+2286 ISOtech -->
<!ENTITY supe "&#8839;"> <!-- superset of or equal to,
U+2287 ISOtech -->
<!ENTITY oplus "&#8853;"> <!-- circled plus = direct sum,
U+2295 ISOamsb -->
<!ENTITY otimes "&#8855;"> <!-- circled times = vector product,
U+2297 ISOamsb -->
<!ENTITY perp "&#8869;"> <!-- up tack = orthogonal to = perpendicular,
U+22A5 ISOtech -->
<!ENTITY sdot "&#8901;"> <!-- dot operator, U+22C5 ISOamsb -->
<!-- dot operator is NOT the same character as U+00B7 middle dot -->
<!-- Miscellaneous Technical -->
<!ENTITY lceil "&#8968;"> <!-- left ceiling = apl upstile,
U+2308 ISOamsc -->
<!ENTITY rceil "&#8969;"> <!-- right ceiling, U+2309 ISOamsc -->
<!ENTITY lfloor "&#8970;"> <!-- left floor = apl downstile,
U+230A ISOamsc -->
<!ENTITY rfloor "&#8971;"> <!-- right floor, U+230B ISOamsc -->
<!ENTITY lang "&#9001;"> <!-- left-pointing angle bracket = bra,
U+2329 ISOtech -->
<!-- lang is NOT the same character as U+003C 'less than'
or U+2039 'single left-pointing angle quotation mark' -->
<!ENTITY rang "&#9002;"> <!-- right-pointing angle bracket = ket,
U+232A ISOtech -->
<!-- rang is NOT the same character as U+003E 'greater than'
or U+203A 'single right-pointing angle quotation mark' -->
<!-- Geometric Shapes -->
<!ENTITY loz "&#9674;"> <!-- lozenge, U+25CA ISOpub -->
<!-- Miscellaneous Symbols -->
<!ENTITY spades "&#9824;"> <!-- black spade suit, U+2660 ISOpub -->
<!-- black here seems to mean filled as opposed to hollow -->
<!ENTITY clubs "&#9827;"> <!-- black club suit = shamrock,
U+2663 ISOpub -->
<!ENTITY hearts "&#9829;"> <!-- black heart suit = valentine,
U+2665 ISOpub -->
<!ENTITY diams "&#9830;"> <!-- black diamond suit, U+2666 ISOpub -->

14
test/valid/dtds/xhtml.cat Normal file
View File

@ -0,0 +1,14 @@
OVERRIDE YES
-- Oasis entity catalog for Extensible HTML 1.0 --
PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "xhtml1-strict.dtd"
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "xhtml1-transitional.dtd"
PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN" "xhtml1-frameset.dtd"
-- ISO latin 1 entity set for Extensible HTML (XML 1.0 format) --
PUBLIC "-//W3C//ENTITIES Latin 1 for XHTML//EN" "xhtml-lat1.ent"
PUBLIC "-//W3C//ENTITIES Symbols for XHTML//EN" "xhtml-symbol.ent"
PUBLIC "-//W3C//ENTITIES Special for XHTML//EN" "xhtml-special.ent"
SGMLDECL "xhtml1.dcl"

1225
test/valid/dtds/xhtml1-frameset.dtd Normal file
View File

File diff suppressed because it is too large Load Diff

988
test/valid/dtds/xhtml1-strict.dtd Normal file
View File

@ -0,0 +1,988 @@
<!--
Extensible HTML version 1.0 Strict DTD
This is the same as HTML 4.0 Strict except for
changes due to the differences between XML and SGML.
Namespace = http://www.w3.org/1999/xhtml
For further information, see: http://www.w3.org/TR/xhtml1
Copyright (c) 1998-1999 W3C (MIT, INRIA, Keio),
All Rights Reserved.
This DTD module is identified by the PUBLIC and SYSTEM identifiers:
PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"
$Revision: 1.12 $
$Date: 1999/11/17 23:36:32 $
-->
<!--================ Character mnemonic entities =========================-->
<!ENTITY % HTMLlat1 PUBLIC
"-//W3C//ENTITIES Latin 1 for XHTML//EN"
"xhtml-lat1.ent">
%HTMLlat1;
<!ENTITY % HTMLsymbol PUBLIC
"-//W3C//ENTITIES Symbols for XHTML//EN"
"xhtml-symbol.ent">
%HTMLsymbol;
<!ENTITY % HTMLspecial PUBLIC
"-//W3C//ENTITIES Special for XHTML//EN"
"xhtml-special.ent">
%HTMLspecial;
<!--================== Imported Names ====================================-->
<!ENTITY % ContentType "CDATA">
<!-- media type, as per [RFC2045] -->
<!ENTITY % ContentTypes "CDATA">
<!-- comma-separated list of media types, as per [RFC2045] -->
<!ENTITY % Charset "CDATA">
<!-- a character encoding, as per [RFC2045] -->
<!ENTITY % Charsets "CDATA">
<!-- a space separated list of character encodings, as per [RFC2045] -->
<!ENTITY % LanguageCode "NMTOKEN">
<!-- a language code, as per [RFC1766] -->
<!ENTITY % Character "CDATA">
<!-- a single character from [ISO10646] -->
<!ENTITY % Number "CDATA">
<!-- one or more digits -->
<!ENTITY % LinkTypes "CDATA">
<!-- space-separated list of link types -->
<!ENTITY % MediaDesc "CDATA">
<!-- single or comma-separated list of media descriptors -->
<!ENTITY % URI "CDATA">
<!-- a Uniform Resource Identifier, see [RFC2396] -->
<!ENTITY % UriList "CDATA">
<!-- a space separated list of Uniform Resource Identifiers -->
<!ENTITY % Datetime "CDATA">
<!-- date and time information. ISO date format -->
<!ENTITY % Script "CDATA">
<!-- script expression -->
<!ENTITY % StyleSheet "CDATA">
<!-- style sheet data -->
<!ENTITY % Text "CDATA">
<!-- used for titles etc. -->
<!ENTITY % FrameTarget "NMTOKEN">
<!-- render in this frame -->
<!ENTITY % Length "CDATA">
<!-- nn for pixels or nn% for percentage length -->
<!ENTITY % MultiLength "CDATA">
<!-- pixel, percentage, or relative -->
<!ENTITY % MultiLengths "CDATA">
<!-- comma-separated list of MultiLength -->
<!ENTITY % Pixels "CDATA">
<!-- integer representing length in pixels -->
<!-- these are used for image maps -->
<!ENTITY % Shape "(rect|circle|poly|default)">
<!ENTITY % Coords "CDATA">
<!-- comma separated list of lengths -->
<!--=================== Generic Attributes ===============================-->
<!-- core attributes common to most elements
id document-wide unique id
class space separated list of classes
style associated style info
title advisory title/amplification
-->
<!ENTITY % coreattrs
"id ID #IMPLIED
class CDATA #IMPLIED
style %StyleSheet; #IMPLIED
title %Text; #IMPLIED"
>
<!-- internationalization attributes
lang language code (backwards compatible)
xml:lang language code (as per XML 1.0 spec)
dir direction for weak/neutral text
-->
<!ENTITY % i18n
"lang %LanguageCode; #IMPLIED
xml:lang %LanguageCode; #IMPLIED
dir (ltr|rtl) #IMPLIED"
>
<!-- attributes for common UI events
onclick a pointer button was clicked
ondblclick a pointer button was double clicked
onmousedown a pointer button was pressed down
onmouseup a pointer button was released
onmousemove a pointer was moved onto the element
onmouseout a pointer was moved away from the element
onkeypress a key was pressed and released
onkeydown a key was pressed down
onkeyup a key was released
-->
<!ENTITY % events
"onclick %Script; #IMPLIED
ondblclick %Script; #IMPLIED
onmousedown %Script; #IMPLIED
onmouseup %Script; #IMPLIED
onmouseover %Script; #IMPLIED
onmousemove %Script; #IMPLIED
onmouseout %Script; #IMPLIED
onkeypress %Script; #IMPLIED
onkeydown %Script; #IMPLIED
onkeyup %Script; #IMPLIED"
>
<!-- attributes for elements that can get the focus
accesskey accessibility key character
tabindex position in tabbing order
onfocus the element got the focus
onblur the element lost the focus
-->
<!ENTITY % focus
"accesskey %Character; #IMPLIED
tabindex %Number; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED"
>
<!ENTITY % attrs "%coreattrs; %i18n; %events;">
<!--=================== Text Elements ====================================-->
<!ENTITY % special
"br | span | bdo | object | img | map">
<!ENTITY % fontstyle "tt | i | b | big | small">
<!ENTITY % phrase "em | strong | dfn | code | q | sub | sup |
samp | kbd | var | cite | abbr | acronym">
<!ENTITY % inline.forms "input | select | textarea | label | button">
<!-- these can occur at block or inline level -->
<!ENTITY % misc "ins | del | script | noscript">
<!ENTITY % inline "a | %special; | %fontstyle; | %phrase; | %inline.forms;">
<!-- %Inline; covers inline or "text-level" elements -->
<!ENTITY % Inline "(#PCDATA | %inline; | %misc;)*">
<!--================== Block level elements ==============================-->
<!ENTITY % heading "h1|h2|h3|h4|h5|h6">
<!ENTITY % lists "ul | ol | dl">
<!ENTITY % blocktext "pre | hr | blockquote | address">
<!ENTITY % block
"p | %heading; | div | %lists; | %blocktext; | fieldset | table">
<!ENTITY % Block "(%block; | form | %misc;)*">
<!-- %Flow; mixes Block and Inline and is used for list items etc. -->
<!ENTITY % Flow "(#PCDATA | %block; | form | %inline; | %misc;)*">
<!--================== Content models for exclusions =====================-->
<!-- a elements use %Inline; excluding a -->
<!ENTITY % a.content
"(#PCDATA | %special; | %fontstyle; | %phrase; | %inline.forms; | %misc;)*">
<!-- pre uses %Inline excluding img, object, big, small, sup or sup -->
<!ENTITY % pre.content
"(#PCDATA | a | br | span | bdo | map | tt | i | b |
%phrase; | %inline.forms;)*">
<!-- form uses %Block; excluding form -->
<!ENTITY % form.content "(%block; | %misc;)*">
<!-- button uses %Flow; but excludes a, form and form controls -->
<!ENTITY % button.content
"(#PCDATA | p | %heading; | div | %lists; | %blocktext; |
table | %special; | %fontstyle; | %phrase; | %misc;)*">
<!--================ Document Structure ==================================-->
<!-- the namespace URI designates the document profile -->
<!ELEMENT html (head, body)>
<!ATTLIST html
%i18n;
xmlns %URI; #FIXED 'http://www.w3.org/1999/xhtml'
>
<!--================ Document Head =======================================-->
<!ENTITY % head.misc "(script|style|meta|link|object)*">
<!-- content model is %head.misc; combined with a single
title and an optional base element in any order -->
<!ELEMENT head (%head.misc;,
((title, %head.misc;, (base, %head.misc;)?) |
(base, %head.misc;, (title, %head.misc;))))>
<!ATTLIST head
%i18n;
profile %URI; #IMPLIED
>
<!-- The title element is not considered part of the flow of text.
It should be displayed, for example as the page header or
window title. Exactly one title is required per document.
-->
<!ELEMENT title (#PCDATA)>
<!ATTLIST title %i18n;>
<!-- document base URI -->
<!ELEMENT base EMPTY>
<!ATTLIST base
href %URI; #IMPLIED
>
<!-- generic metainformation -->
<!ELEMENT meta EMPTY>
<!ATTLIST meta
%i18n;
http-equiv CDATA #IMPLIED
name CDATA #IMPLIED
content CDATA #REQUIRED
scheme CDATA #IMPLIED
>
<!--
Relationship values can be used in principle:
a) for document specific toolbars/menus when used
with the link element in document head e.g.
start, contents, previous, next, index, end, help
b) to link to a separate style sheet (rel="stylesheet")
c) to make a link to a script (rel="script")
d) by stylesheets to control how collections of
html nodes are rendered into printed documents
e) to make a link to a printable version of this document
e.g. a PostScript or PDF version (rel="alternate" media="print")
-->
<!ELEMENT link EMPTY>
<!ATTLIST link
%attrs;
charset %Charset; #IMPLIED
href %URI; #IMPLIED
hreflang %LanguageCode; #IMPLIED
type %ContentType; #IMPLIED
rel %LinkTypes; #IMPLIED
rev %LinkTypes; #IMPLIED
media %MediaDesc; #IMPLIED
>
<!-- style info, which may include CDATA sections -->
<!ELEMENT style (#PCDATA)>
<!ATTLIST style
%i18n;
type %ContentType; #REQUIRED
media %MediaDesc; #IMPLIED
title %Text; #IMPLIED
xml:space (preserve) #FIXED 'preserve'
>
<!-- script statements, which may include CDATA sections -->
<!ELEMENT script (#PCDATA)>
<!ATTLIST script
charset %Charset; #IMPLIED
type %ContentType; #REQUIRED
src %URI; #IMPLIED
defer (defer) #IMPLIED
xml:space (preserve) #FIXED 'preserve'
>
<!-- alternate content container for non script-based rendering -->
<!ELEMENT noscript %Block;>
<!ATTLIST noscript
%attrs;
>
<!--=================== Document Body ====================================-->
<!ELEMENT body %Block;>
<!ATTLIST body
%attrs;
onload %Script; #IMPLIED
onunload %Script; #IMPLIED
>
<!ELEMENT div %Flow;> <!-- generic language/style container -->
<!ATTLIST div
%attrs;
>
<!--=================== Paragraphs =======================================-->
<!ELEMENT p %Inline;>
<!ATTLIST p
%attrs;
>
<!--=================== Headings =========================================-->
<!--
There are six levels of headings from h1 (the most important)
to h6 (the least important).
-->
<!ELEMENT h1 %Inline;>
<!ATTLIST h1
%attrs;
>
<!ELEMENT h2 %Inline;>
<!ATTLIST h2
%attrs;
>
<!ELEMENT h3 %Inline;>
<!ATTLIST h3
%attrs;
>
<!ELEMENT h4 %Inline;>
<!ATTLIST h4
%attrs;
>
<!ELEMENT h5 %Inline;>
<!ATTLIST h5
%attrs;
>
<!ELEMENT h6 %Inline;>
<!ATTLIST h6
%attrs;
>
<!--=================== Lists ============================================-->
<!-- Unordered list -->
<!ELEMENT ul (li)+>
<!ATTLIST ul
%attrs;
>
<!-- Ordered (numbered) list -->
<!ELEMENT ol (li)+>
<!ATTLIST ol
%attrs;
>
<!-- list item -->
<!ELEMENT li %Flow;>
<!ATTLIST li
%attrs;
>
<!-- definition lists - dt for term, dd for its definition -->
<!ELEMENT dl (dt|dd)+>
<!ATTLIST dl
%attrs;
>
<!ELEMENT dt %Inline;>
<!ATTLIST dt
%attrs;
>
<!ELEMENT dd %Flow;>
<!ATTLIST dd
%attrs;
>
<!--=================== Address ==========================================-->
<!-- information on author -->
<!ELEMENT address %Inline;>
<!ATTLIST address
%attrs;
>
<!--=================== Horizontal Rule ==================================-->
<!ELEMENT hr EMPTY>
<!ATTLIST hr
%attrs;
>
<!--=================== Preformatted Text ================================-->
<!-- content is %Inline; excluding "img|object|big|small|sub|sup" -->
<!ELEMENT pre %pre.content;>
<!ATTLIST pre
%attrs;
xml:space (preserve) #FIXED 'preserve'
>
<!--=================== Block-like Quotes ================================-->
<!ELEMENT blockquote %Block;>
<!ATTLIST blockquote
%attrs;
cite %URI; #IMPLIED
>
<!--=================== Inserted/Deleted Text ============================-->
<!--
ins/del are allowed in block and inline content, but its
inappropriate to include block content within an ins element
occurring in inline content.
-->
<!ELEMENT ins %Flow;>
<!ATTLIST ins
%attrs;
cite %URI; #IMPLIED
datetime %Datetime; #IMPLIED
>
<!ELEMENT del %Flow;>
<!ATTLIST del
%attrs;
cite %URI; #IMPLIED
datetime %Datetime; #IMPLIED
>
<!--================== The Anchor Element ================================-->
<!-- content is %Inline; except that anchors shouldn't be nested -->
<!ELEMENT a %a.content;>
<!ATTLIST a
%attrs;
charset %Charset; #IMPLIED
type %ContentType; #IMPLIED
name NMTOKEN #IMPLIED
href %URI; #IMPLIED
hreflang %LanguageCode; #IMPLIED
rel %LinkTypes; #IMPLIED
rev %LinkTypes; #IMPLIED
accesskey %Character; #IMPLIED
shape %Shape; "rect"
coords %Coords; #IMPLIED
tabindex %Number; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED
>
<!--===================== Inline Elements ================================-->
<!ELEMENT span %Inline;> <!-- generic language/style container -->
<!ATTLIST span
%attrs;
>
<!ELEMENT bdo %Inline;> <!-- I18N BiDi over-ride -->
<!ATTLIST bdo
%coreattrs;
%events;
lang %LanguageCode; #IMPLIED
xml:lang %LanguageCode; #IMPLIED
dir (ltr|rtl) #REQUIRED
>
<!ELEMENT br EMPTY> <!-- forced line break -->
<!ATTLIST br
%coreattrs;
>
<!ELEMENT em %Inline;> <!-- emphasis -->
<!ATTLIST em %attrs;>
<!ELEMENT strong %Inline;> <!-- strong emphasis -->
<!ATTLIST strong %attrs;>
<!ELEMENT dfn %Inline;> <!-- definitional -->
<!ATTLIST dfn %attrs;>
<!ELEMENT code %Inline;> <!-- program code -->
<!ATTLIST code %attrs;>
<!ELEMENT samp %Inline;> <!-- sample -->
<!ATTLIST samp %attrs;>
<!ELEMENT kbd %Inline;> <!-- something user would type -->
<!ATTLIST kbd %attrs;>
<!ELEMENT var %Inline;> <!-- variable -->
<!ATTLIST var %attrs;>
<!ELEMENT cite %Inline;> <!-- citation -->
<!ATTLIST cite %attrs;>
<!ELEMENT abbr %Inline;> <!-- abbreviation -->
<!ATTLIST abbr %attrs;>
<!ELEMENT acronym %Inline;> <!-- acronym -->
<!ATTLIST acronym %attrs;>
<!ELEMENT q %Inline;> <!-- inlined quote -->
<!ATTLIST q
%attrs;
cite %URI; #IMPLIED
>
<!ELEMENT sub %Inline;> <!-- subscript -->
<!ATTLIST sub %attrs;>
<!ELEMENT sup %Inline;> <!-- superscript -->
<!ATTLIST sup %attrs;>
<!ELEMENT tt %Inline;> <!-- fixed pitch font -->
<!ATTLIST tt %attrs;>
<!ELEMENT i %Inline;> <!-- italic font -->
<!ATTLIST i %attrs;>
<!ELEMENT b %Inline;> <!-- bold font -->
<!ATTLIST b %attrs;>
<!ELEMENT big %Inline;> <!-- bigger font -->
<!ATTLIST big %attrs;>
<!ELEMENT small %Inline;> <!-- smaller font -->
<!ATTLIST small %attrs;>
<!--==================== Object ======================================-->
<!--
object is used to embed objects as part of HTML pages.
param elements should precede other content. Parameters
can also be expressed as attribute/value pairs on the
object element itself when brevity is desired.
-->
<!ELEMENT object (#PCDATA | param | %block; | form | %inline; | %misc;)*>
<!ATTLIST object
%attrs;
declare (declare) #IMPLIED
classid %URI; #IMPLIED
codebase %URI; #IMPLIED
data %URI; #IMPLIED
type %ContentType; #IMPLIED
codetype %ContentType; #IMPLIED
archive %UriList; #IMPLIED
standby %Text; #IMPLIED
height %Length; #IMPLIED
width %Length; #IMPLIED
usemap %URI; #IMPLIED
name NMTOKEN #IMPLIED
tabindex %Number; #IMPLIED
>
<!--
param is used to supply a named property value.
In XML it would seem natural to follow RDF and support an
abbreviated syntax where the param elements are replaced
by attribute value pairs on the object start tag.
-->
<!ELEMENT param EMPTY>
<!ATTLIST param
id ID #IMPLIED
name CDATA #IMPLIED
value CDATA #IMPLIED
valuetype (data|ref|object) "data"
type %ContentType; #IMPLIED
>
<!--=================== Images ===========================================-->
<!--
To avoid accessibility problems for people who aren't
able to see the image, you should provide a text
description using the alt and longdesc attributes.
In addition, avoid the use of server-side image maps.
Note that in this DTD there is no name attribute. That
is only available in the transitional and frameset DTD.
-->
<!ELEMENT img EMPTY>
<!ATTLIST img
%attrs;
src %URI; #REQUIRED
alt %Text; #REQUIRED
longdesc %URI; #IMPLIED
height %Length; #IMPLIED
width %Length; #IMPLIED
usemap %URI; #IMPLIED
ismap (ismap) #IMPLIED
>
<!-- usemap points to a map element which may be in this document
or an external document, although the latter is not widely supported -->
<!--================== Client-side image maps ============================-->
<!-- These can be placed in the same document or grouped in a
separate document although this isn't yet widely supported -->
<!ELEMENT map ((%block; | form | %misc;)+ | area+)>
<!ATTLIST map
%i18n;
%events;
id ID #REQUIRED
class CDATA #IMPLIED
style %StyleSheet; #IMPLIED
title %Text; #IMPLIED
name NMTOKEN #IMPLIED
>
<!ELEMENT area EMPTY>
<!ATTLIST area
%attrs;
shape %Shape; "rect"
coords %Coords; #IMPLIED
href %URI; #IMPLIED
nohref (nohref) #IMPLIED
alt %Text; #REQUIRED
tabindex %Number; #IMPLIED
accesskey %Character; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED
>
<!--================ Forms ===============================================-->
<!ELEMENT form %form.content;> <!-- forms shouldn't be nested -->
<!ATTLIST form
%attrs;
action %URI; #REQUIRED
method (get|post) "get"
enctype %ContentType; "application/x-www-form-urlencoded"
onsubmit %Script; #IMPLIED
onreset %Script; #IMPLIED
accept %ContentTypes; #IMPLIED
accept-charset %Charsets; #IMPLIED
>
<!--
Each label must not contain more than ONE field
Label elements shouldn't be nested.
-->
<!ELEMENT label %Inline;>
<!ATTLIST label
%attrs;
for IDREF #IMPLIED
accesskey %Character; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED
>
<!ENTITY % InputType
"(text | password | checkbox |
radio | submit | reset |
file | hidden | image | button)"
>
<!-- the name attribute is required for all but submit & reset -->
<!ELEMENT input EMPTY> <!-- form control -->
<!ATTLIST input
%attrs;
type %InputType; "text"
name CDATA #IMPLIED
value CDATA #IMPLIED
checked (checked) #IMPLIED
disabled (disabled) #IMPLIED
readonly (readonly) #IMPLIED
size CDATA #IMPLIED
maxlength %Number; #IMPLIED
src %URI; #IMPLIED
alt CDATA #IMPLIED
usemap %URI; #IMPLIED
tabindex %Number; #IMPLIED
accesskey %Character; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED
onselect %Script; #IMPLIED
onchange %Script; #IMPLIED
accept %ContentTypes; #IMPLIED
>
<!ELEMENT select (optgroup|option)+> <!-- option selector -->
<!ATTLIST select
%attrs;
name CDATA #IMPLIED
size %Number; #IMPLIED
multiple (multiple) #IMPLIED
disabled (disabled) #IMPLIED
tabindex %Number; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED
onchange %Script; #IMPLIED
>
<!ELEMENT optgroup (option)+> <!-- option group -->
<!ATTLIST optgroup
%attrs;
disabled (disabled) #IMPLIED
label %Text; #REQUIRED
>
<!ELEMENT option (#PCDATA)> <!-- selectable choice -->
<!ATTLIST option
%attrs;
selected (selected) #IMPLIED
disabled (disabled) #IMPLIED
label %Text; #IMPLIED
value CDATA #IMPLIED
>
<!ELEMENT textarea (#PCDATA)> <!-- multi-line text field -->
<!ATTLIST textarea
%attrs;
name CDATA #IMPLIED
rows %Number; #REQUIRED
cols %Number; #REQUIRED
disabled (disabled) #IMPLIED
readonly (readonly) #IMPLIED
tabindex %Number; #IMPLIED
accesskey %Character; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED
onselect %Script; #IMPLIED
onchange %Script; #IMPLIED
>
<!--
The fieldset element is used to group form fields.
Only one legend element should occur in the content
and if present should only be preceded by whitespace.
-->
<!ELEMENT fieldset (#PCDATA | legend | %block; | form | %inline; | %misc;)*>
<!ATTLIST fieldset
%attrs;
>
<!ELEMENT legend %Inline;> <!-- fieldset label -->
<!ATTLIST legend
%attrs;
accesskey %Character; #IMPLIED
>
<!--
Content is %Flow; excluding a, form and form controls
-->
<!ELEMENT button %button.content;> <!-- push button -->
<!ATTLIST button
%attrs;
name CDATA #IMPLIED
value CDATA #IMPLIED
type (button|submit|reset) "submit"
disabled (disabled) #IMPLIED
tabindex %Number; #IMPLIED
accesskey %Character; #IMPLIED
onfocus %Script; #IMPLIED
onblur %Script; #IMPLIED
>
<!--======================= Tables =======================================-->
<!-- Derived from IETF HTML table standard, see [RFC1942] -->
<!--
The border attribute sets the thickness of the frame around the
table. The default units are screen pixels.
The frame attribute specifies which parts of the frame around
the table should be rendered. The values are not the same as
CALS to avoid a name clash with the valign attribute.
-->
<!ENTITY % TFrame "(void|above|below|hsides|lhs|rhs|vsides|box|border)">
<!--
The rules attribute defines which rules to draw between cells:
If rules is absent then assume:
"none" if border is absent or border="0" otherwise "all"
-->
<!ENTITY % TRules "(none | groups | rows | cols | all)">
<!-- horizontal placement of table relative to document -->
<!ENTITY % TAlign "(left|center|right)">
<!-- horizontal alignment attributes for cell contents
char alignment char, e.g. char=':'
charoff offset for alignment char
-->
<!ENTITY % cellhalign
"align (left|center|right|justify|char) #IMPLIED
char %Character; #IMPLIED
charoff %Length; #IMPLIED"
>
<!-- vertical alignment attributes for cell contents -->
<!ENTITY % cellvalign
"valign (top|middle|bottom|baseline) #IMPLIED"
>
<!ELEMENT table
(caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))>
<!ELEMENT caption %Inline;>
<!ELEMENT thead (tr)+>
<!ELEMENT tfoot (tr)+>
<!ELEMENT tbody (tr)+>
<!ELEMENT colgroup (col)*>
<!ELEMENT col EMPTY>
<!ELEMENT tr (th|td)+>
<!ELEMENT th %Flow;>
<!ELEMENT td %Flow;>
<!ATTLIST table
%attrs;
summary %Text; #IMPLIED
width %Length; #IMPLIED
border %Pixels; #IMPLIED
frame %TFrame; #IMPLIED
rules %TRules; #IMPLIED
cellspacing %Length; #IMPLIED
cellpadding %Length; #IMPLIED
>
<!ENTITY % CAlign "(top|bottom|left|right)">
<!ATTLIST caption
%attrs;
>
<!--
colgroup groups a set of col elements. It allows you to group
several semantically related columns together.
-->
<!ATTLIST colgroup
%attrs;
span %Number; "1"
width %MultiLength; #IMPLIED
%cellhalign;
%cellvalign;
>
<!--
col elements define the alignment properties for cells in
one or more columns.
The width attribute specifies the width of the columns, e.g.
width=64 width in screen pixels
width=0.5* relative width of 0.5
The span attribute causes the attributes of one
col element to apply to more than one column.
-->
<!ATTLIST col
%attrs;
span %Number; "1"
width %MultiLength; #IMPLIED
%cellhalign;
%cellvalign;
>
<!--
Use thead to duplicate headers when breaking table
across page boundaries, or for static headers when
tbody sections are rendered in scrolling panel.
Use tfoot to duplicate footers when breaking table
across page boundaries, or for static footers when
tbody sections are rendered in scrolling panel.
Use multiple tbody sections when rules are needed
between groups of table rows.
-->
<!ATTLIST thead
%attrs;
%cellhalign;
%cellvalign;
>
<!ATTLIST tfoot
%attrs;
%cellhalign;
%cellvalign;
>
<!ATTLIST tbody
%attrs;
%cellhalign;
%cellvalign;
>
<!ATTLIST tr
%attrs;
%cellhalign;
%cellvalign;
>
<!-- Scope is simpler than headers attribute for common tables -->
<!ENTITY % Scope "(row|col|rowgroup|colgroup)">
<!-- th is for headers, td for data and for cells acting as both -->
<!ATTLIST th
%attrs;
abbr %Text; #IMPLIED
axis CDATA #IMPLIED
headers IDREFS #IMPLIED
scope %Scope; #IMPLIED
rowspan %Number; "1"
colspan %Number; "1"
%cellhalign;
%cellvalign;
>
<!ATTLIST td
%attrs;
abbr %Text; #IMPLIED
axis CDATA #IMPLIED
headers IDREFS #IMPLIED
scope %Scope; #IMPLIED
rowspan %Number; "1"
colspan %Number; "1"
%cellhalign;
%cellvalign;
>

1196
test/valid/dtds/xhtml1-transitional.dtd Normal file
View File

File diff suppressed because it is too large Load Diff

179
test/valid/dtds/xhtml1.dcl Normal file
View File

@ -0,0 +1,179 @@
<!SGML -- SGML Declaration for valid XML documents --
"ISO 8879:1986 (WWW)"
CHARSET
BASESET
"ISO Registration Number 176//CHARSET
ISO/IEC 10646-1:1993 UCS-4 with implementation
level 3//ESC 2/5 2/15 4/6"
DESCSET
0 9 UNUSED
9 2 9
11 2 UNUSED
13 1 13
14 18 UNUSED
32 95 32
127 1 UNUSED
128 32 UNUSED
-- use this instead of the official declaration because SP only
supports 16-bit characters --
160 65374 160
65534 2 UNUSED
-- 55296 2048 UNUSED
57344 8190 57344
65534 2 UNUSED
65536 1048576 65536 --
CAPACITY NONE
SCOPE DOCUMENT
SYNTAX
SHUNCHAR NONE
BASESET "ISO Registration Number 176//CHARSET
ISO/IEC 10646-1:1993 UCS-4 with implementation
level 3//ESC 2/5 2/15 4/6"
DESCSET
0 1114112 0
FUNCTION
RE 13
RS 10
SPACE 32
TAB SEPCHAR 9
NAMING
LCNMSTRT ""
UCNMSTRT ""
NAMESTRT
58 95 192-214 216-246 248-305 308-318 321-328
330-382 384-451 461-496 500-501 506-535 592-680
699-705 902 904-906 908 910-929 931-974 976-982
986 988 990 992 994-1011 1025-1036 1038-1103
1105-1116 1118-1153 1168-1220 1223-1224
1227-1228 1232-1259 1262-1269 1272-1273
1329-1366 1369 1377-1414 1488-1514 1520-1522
1569-1594 1601-1610 1649-1719 1722-1726
1728-1742 1744-1747 1749 1765-1766 2309-2361
2365 2392-2401 2437-2444 2447-2448 2451-2472
2474-2480 2482 2486-2489 2524-2525 2527-2529
2544-2545 2565-2570 2575-2576 2579-2600
2602-2608 2610-2611 2613-2614 2616-2617
2649-2652 2654 2674-2676 2693-2699 2701
2703-2705 2707-2728 2730-2736 2738-2739
2741-2745 2749 2784 2821-2828 2831-2832
2835-2856 2858-2864 2866-2867 2870-2873 2877
2908-2909 2911-2913 2949-2954 2958-2960
2962-2965 2969-2970 2972 2974-2975 2979-2980
2984-2986 2990-2997 2999-3001 3077-3084
3086-3088 3090-3112 3114-3123 3125-3129
3168-3169 3205-3212 3214-3216 3218-3240
3242-3251 3253-3257 3294 3296-3297 3333-3340
3342-3344 3346-3368 3370-3385 3424-3425
3585-3630 3632 3634-3635 3648-3653 3713-3714
3716 3719-3720 3722 3725 3732-3735 3737-3743
3745-3747 3749 3751 3754-3755 3757-3758 3760
3762-3763 3773 3776-3780 3904-3911 3913-3945
4256-4293 4304-4342 4352 4354-4355 4357-4359
4361 4363-4364 4366-4370 4412 4414 4416 4428
4430 4432 4436-4437 4441 4447-4449 4451 4453
4455 4457 4461-4462 4466-4467 4469 4510 4520
4523 4526-4527 4535-4536 4538 4540-4546 4587
4592 4601 7680-7835 7840-7929 7936-7957
7960-7965 7968-8005 8008-8013 8016-8023 8025
8027 8029 8031-8061 8064-8116 8118-8124 8126
8130-8132 8134-8140 8144-8147 8150-8155
8160-8172 8178-8180 8182-8188 8486 8490-8491
8494 8576-8578 12295 12321-12329 12353-12436
12449-12538 12549-12588 19968-40869 44032-55203
LCNMCHAR ""
UCNMCHAR ""
NAMECHAR
45-46 183 720-721 768-837 864-865 903 1155-1158
1425-1441 1443-1465 1467-1469 1471 1473-1474
1476 1600 1611-1618 1632-1641 1648 1750-1764
1767-1768 1770-1773 1776-1785 2305-2307 2364
2366-2381 2385-2388 2402-2403 2406-2415
2433-2435 2492 2494-2500 2503-2504 2507-2509
2519 2530-2531 2534-2543 2562 2620 2622-2626
2631-2632 2635-2637 2662-2673 2689-2691 2748
2750-2757 2759-2761 2763-2765 2790-2799
2817-2819 2876 2878-2883 2887-2888 2891-2893
2902-2903 2918-2927 2946-2947 3006-3010
3014-3016 3018-3021 3031 3047-3055 3073-3075
3134-3140 3142-3144 3146-3149 3157-3158
3174-3183 3202-3203 3262-3268 3270-3272
3274-3277 3285-3286 3302-3311 3330-3331
3390-3395 3398-3400 3402-3405 3415 3430-3439
3633 3636-3642 3654-3662 3664-3673 3761
3764-3769 3771-3772 3782 3784-3789 3792-3801
3864-3865 3872-3881 3893 3895 3897 3902-3903
3953-3972 3974-3979 3984-3989 3991 3993-4013
4017-4023 4025 8400-8412 8417 12293 12330-12335
12337-12341 12441-12442 12445-12446 12540-12542
NAMECASE
GENERAL NO
ENTITY NO
DELIM
GENERAL SGMLREF
HCRO "&#38;#x" -- 38 is the number for ampersand --
NESTC "/"
NET ">"
PIC "?>"
SHORTREF NONE
NAMES
SGMLREF
QUANTITY NONE
ENTITIES
"amp" 38
"lt" 60
"gt" 62
"quot" 34
"apos" 39
FEATURES
MINIMIZE
DATATAG NO
OMITTAG NO
RANK NO
SHORTTAG
STARTTAG
EMPTY NO
UNCLOSED NO
NETENABL IMMEDNET
ENDTAG
EMPTY NO
UNCLOSED NO
ATTRIB
DEFAULT YES
OMITNAME NO
VALUE NO
EMPTYNRM YES
IMPLYDEF
ATTLIST NO
DOCTYPE NO
ELEMENT NO
ENTITY NO
NOTATION NO
LINK
SIMPLE NO
IMPLICIT NO
EXPLICIT NO
OTHER
CONCUR NO
SUBDOC NO
FORMAL NO
URN NO
KEEPRSRE YES
VALIDITY TYPE
ENTITIES
REF ANY
INTEGRAL YES
APPINFO NONE
SEEALSO "ISO 8879:1986//NOTATION
Extensible Markup Language (XML) 1.0//EN"
>

1505
test/valid/xhtml1.xhtml Normal file
View File

File diff suppressed because it is too large Load Diff

103
tree.c
View File

@ -116,8 +116,10 @@ xmlUpgradeOldNs(xmlDocPtr doc) {
* @href: the URI associated * @href: the URI associated
* @prefix: the prefix for the namespace * @prefix: the prefix for the namespace
* *
* Creation of a new Namespace. * Creation of a new Namespace. This function will refuse to create
* Returns returns a new namespace pointer * a namespace with a similar prefix than an existing one present on this
* node.
* Returns returns a new namespace pointer or NULL
*/ */
xmlNsPtr xmlNsPtr
xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) { xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) {
@ -149,6 +151,7 @@ xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) {
/* /*
* Add it at the end to preserve parsing order ... * Add it at the end to preserve parsing order ...
* and checks for existing use of the prefix
*/ */
cur->next = NULL; cur->next = NULL;
if (node != NULL) { if (node != NULL) {
@ -157,11 +160,17 @@ xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) {
} else { } else {
xmlNsPtr prev = node->nsDef; xmlNsPtr prev = node->nsDef;
while (prev->next != NULL) prev = prev->next; while (prev->next != NULL) {
if (((prev->prefix == NULL) && (cur->prefix == NULL)) ||
(!xmlStrcmp(prev->prefix, cur->prefix))) {
xmlFreeNs(cur);
return(NULL);
}
prev = prev->next;
}
prev->next = cur; prev->next = cur;
} }
} }
return(cur); return(cur);
} }
@ -171,48 +180,14 @@ xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) {
* @href: the URI associated * @href: the URI associated
* @prefix: the prefix for the namespace * @prefix: the prefix for the namespace
* *
* Creation of a Namespace, the old way using PI and without scoping, to AVOID. * Creation of a Namespace, the old way using PI and without scoping
* Returns returns a new namespace pointer * DEPRECATED !!!
* Will be removed at next major release !
* Returns NULL this functionnality had been removed
*/ */
xmlNsPtr xmlNsPtr
xmlNewGlobalNs(xmlDocPtr doc, const xmlChar *href, const xmlChar *prefix) { xmlNewGlobalNs(xmlDocPtr doc, const xmlChar *href, const xmlChar *prefix) {
xmlNsPtr cur; return(NULL);
/*
* Allocate a new DTD and fill the fields.
*/
cur = (xmlNsPtr) xmlMalloc(sizeof(xmlNs));
if (cur == NULL) {
fprintf(stderr, "xmlNewGlobalNs : malloc failed\n");
return(NULL);
}
cur->type = XML_GLOBAL_NAMESPACE;
if (href != NULL)
cur->href = xmlStrdup(href);
else
cur->href = NULL;
if (prefix != NULL)
cur->prefix = xmlStrdup(prefix);
else
cur->prefix = NULL;
/*
* Add it at the end to preserve parsing order ...
*/
cur->next = NULL;
if (doc != NULL) {
if (doc->oldNs == NULL) {
doc->oldNs = cur;
} else {
xmlNsPtr prev = doc->oldNs;
while (prev->next != NULL) prev = prev->next;
prev->next = cur;
}
}
return(cur);
} }
/** /**
@ -956,9 +931,9 @@ xmlFreePropList(xmlAttrPtr cur) {
/** /**
* xmlFreeProp: * xmlFreeProp:
* @cur: the first property in the list * @cur: an attribute
* *
* Free one property, all the childs are freed too. * Free one attribute, all the content is freed too
*/ */
void void
xmlFreeProp(xmlAttrPtr cur) { xmlFreeProp(xmlAttrPtr cur) {
@ -972,6 +947,44 @@ xmlFreeProp(xmlAttrPtr cur) {
xmlFree(cur); xmlFree(cur);
} }
/**
* xmlRemoveProp:
* @cur: an attribute
*
* Unlink and free one attribute, all the content is freed too
* Note this doesn't work for namespace definition attributes
*
* Returns 0 if success and -1 in case of error.
*/
int
xmlRemoveProp(xmlAttrPtr cur) {
xmlAttrPtr tmp;
if (cur == NULL) {
fprintf(stderr, "xmlRemoveProp : cur == NULL\n");
return(-1);
}
if (cur->node == NULL) {
fprintf(stderr, "xmlRemoveProp : cur->node == NULL\n");
return(-1);
}
tmp = cur->node->properties;
if (tmp == cur) {
cur->node->properties = cur->next;
xmlFreeProp(cur);
return(0);
}
while (tmp != NULL) {
if (tmp->next == cur) {
tmp->next = cur->next;
xmlFreeProp(cur);
return(0);
}
tmp = tmp->next;
}
fprintf(stderr, "xmlRemoveProp : attribute not owned by its node\n");
return(-1);
}
/** /**
* xmlNewPI: * xmlNewPI:
* @name: the processing instruction name * @name: the processing instruction name

1
tree.h
View File

@ -449,6 +449,7 @@ void xmlTextConcat (xmlNodePtr node,
int len); int len);
void xmlFreeNodeList (xmlNodePtr cur); void xmlFreeNodeList (xmlNodePtr cur);
void xmlFreeNode (xmlNodePtr cur); void xmlFreeNode (xmlNodePtr cur);
int xmlRemoveProp (xmlAttrPtr cur);
/* /*
* Namespaces * Namespaces

3
win32config.h.in
View File

@ -7,6 +7,8 @@
#define LIBXML_VERSION "@LIBXML_VERSION@" #define LIBXML_VERSION "@LIBXML_VERSION@"
#include <io.h> #include <io.h>
#ifdef INCLUDE_WINSOCK
#include <winsock2.h> #include <winsock2.h>
#define EWOULDBLOCK WSAEWOULDBLOCK #define EWOULDBLOCK WSAEWOULDBLOCK
@ -46,6 +48,7 @@
#define EDQUOT WSAEDQUOT #define EDQUOT WSAEDQUOT
#define ESTALE WSAESTALE #define ESTALE WSAESTALE
#define EREMOTE WSAEREMOTE #define EREMOTE WSAEREMOTE
#endif /* INCLUDE_WINSOCK */
#include <math.h> #include <math.h>
static int isinf (double d) { static int isinf (double d) {

28
xmlIO.c
View File

@ -36,6 +36,7 @@
#include "xmlmemory.h" #include "xmlmemory.h"
#include "parser.h" #include "parser.h"
#include "parserInternals.h"
#include "xmlIO.h" #include "xmlIO.h"
#include "nanohttp.h" #include "nanohttp.h"
@ -464,22 +465,33 @@ xmlParserGetDirectory(const char *filename) {
* xmlDefaultExternalEntityLoader: * xmlDefaultExternalEntityLoader:
* @URL: the URL for the entity to load * @URL: the URL for the entity to load
* @ID: the System ID for the entity to load * @ID: the System ID for the entity to load
* @context: the context in which the entity is called or NULL * @ctxt: the context in which the entity is called or NULL
* *
* By default we don't load external entitites, yet. * By default we don't load external entitites, yet.
* TODO: get a sample http implementation and scan for existing one
* at compile time.
* *
* Returns a new allocated xmlParserInputPtr, or NULL. * Returns a new allocated xmlParserInputPtr, or NULL.
*/ */
static static
xmlParserInputPtr xmlParserInputPtr
xmlDefaultExternalEntityLoader(const char *URL, const char *ID, xmlDefaultExternalEntityLoader(const char *URL, const char *ID,
xmlParserInputPtr context) { xmlParserCtxtPtr ctxt) {
xmlParserInputPtr ret = NULL;
#ifdef DEBUG_EXTERNAL_ENTITIES #ifdef DEBUG_EXTERNAL_ENTITIES
fprintf(stderr, "xmlDefaultExternalEntityLoader(%s, xxx)\n", URL); fprintf(stderr, "xmlDefaultExternalEntityLoader(%s, xxx)\n", URL);
#endif #endif
return(NULL); if (URL == NULL) {
if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
ctxt->sax->warning(ctxt, "failed to load external entity \"%s\"\n",
ID);
return(NULL);
}
ret = xmlNewInputFromFile(ctxt, URL);
if (ret == NULL) {
if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
ctxt->sax->warning(ctxt, "failed to load external entity \"%s\"\n",
URL);
}
return(ret);
} }
static xmlExternalEntityLoader xmlCurrentExternalEntityLoader = static xmlExternalEntityLoader xmlCurrentExternalEntityLoader =
@ -512,7 +524,7 @@ xmlGetExternalEntityLoader(void) {
* xmlLoadExternalEntity: * xmlLoadExternalEntity:
* @URL: the URL for the entity to load * @URL: the URL for the entity to load
* @ID: the System ID for the entity to load * @ID: the System ID for the entity to load
* @context: the context in which the entity is called or NULL * @ctxt: the context in which the entity is called or NULL
* *
* Load an external entity, note that the use of this function for * Load an external entity, note that the use of this function for
* unparsed entities may generate problems * unparsed entities may generate problems
@ -522,7 +534,7 @@ xmlGetExternalEntityLoader(void) {
*/ */
xmlParserInputPtr xmlParserInputPtr
xmlLoadExternalEntity(const char *URL, const char *ID, xmlLoadExternalEntity(const char *URL, const char *ID,
xmlParserInputPtr context) { xmlParserCtxtPtr ctxt) {
return(xmlCurrentExternalEntityLoader(URL, ID, context)); return(xmlCurrentExternalEntityLoader(URL, ID, ctxt));
} }