Adding new version of the SAX interface, it's not there yet, currently

* Makefile.am SAX2.c include/libxml/Makefile.am include/libxml/SAX2.h:
  Adding new version of the SAX interface, it's not there yet,
  currently just preparing the work
* globals.c parser.c SAX.c include/libxml/SAX.h
  include/libxml/globals.h include/libxml/parser.h: doing some
  refactoring of the SAXv1 interfaces, obsoleting a bunch of them
  while keeping functionalities, preparing SAX2 integration.
* dict.c: small cleanup.
Daniel

ChangeLog

@@ -1,3 +1,14 @@
+Thu Aug 21 00:50:32 CEST 2003 Daniel Veillard <daniel@veillard.com>
+
+	* Makefile.am SAX2.c include/libxml/Makefile.am include/libxml/SAX2.h:
+	  Adding new version of the SAX interface, it's not there yet,
+	  currently just preparing the work
+	* globals.c parser.c SAX.c include/libxml/SAX.h 
+	  include/libxml/globals.h include/libxml/parser.h: doing some
+	  refactoring of the SAXv1 interfaces, obsoleting a bunch of them
+	  while keeping functionalities, preparing SAX2 integration.
+	* dict.c: small cleanup.
+
 Wed Aug 20 00:20:01 CEST 2003 Daniel Veillard <daniel@veillard.com>
 
 	* tree.c: fixes a small bug introduced in last commit and detected

Makefile.am

@@ -26,7 +26,7 @@ libxml2_la_SOURCES = SAX.c entities.c encoding.c error.c parserInternals.c  \
 		xpointer.c xinclude.c nanohttp.c nanoftp.c DOCBparser.c \
 		catalog.c globals.c threads.c c14n.c \
 		xmlregexp.c xmlschemas.c xmlschemastypes.c xmlunicode.c \
-		triostr.c trio.c xmlreader.c relaxng.c dict.c
+		triostr.c trio.c xmlreader.c relaxng.c dict.c SAX2.c
 else
 libxml2_la_SOURCES = SAX.c entities.c encoding.c error.c parserInternals.c  \
 		parser.c tree.c hash.c list.c xmlIO.c xmlmemory.c uri.c  \
@@ -34,7 +34,7 @@ libxml2_la_SOURCES = SAX.c entities.c encoding.c error.c parserInternals.c  \
 		xpointer.c xinclude.c nanohttp.c nanoftp.c DOCBparser.c \
 		catalog.c globals.c threads.c c14n.c \
 		xmlregexp.c xmlschemas.c xmlschemastypes.c xmlunicode.c \
-		xmlreader.c relaxng.c dict.c
+		xmlreader.c relaxng.c dict.c SAX2.c
 endif
 
 DEPS = $(top_builddir)/libxml2.la

dict.c

@@ -61,8 +61,6 @@ struct _xmlDict {
 static unsigned long
 xmlDictComputeKey(xmlDictPtr dict, const xmlChar *name, int namelen) {
     unsigned long value = 0L;
-    char ch;
-    int len = 0;
     
     if (name == NULL) return(0);
     value += 30 * (*name);

globals.c

@@ -331,34 +331,38 @@ int xmlSaveNoEmptyTagsThrDef = 0;
  * Default handler for XML, builds the DOM tree
  */
 xmlSAXHandler xmlDefaultSAXHandler = {
-    internalSubset,
+    xmlSAX2InternalSubset,
-    isStandalone,
+    xmlSAX2IsStandalone,
-    hasInternalSubset,
+    xmlSAX2HasInternalSubset,
-    hasExternalSubset,
+    xmlSAX2HasExternalSubset,
-    resolveEntity,
+    xmlSAX2ResolveEntity,
-    getEntity,
+    xmlSAX2GetEntity,
-    entityDecl,
+    xmlSAX2EntityDecl,
-    notationDecl,
+    xmlSAX2NotationDecl,
-    attributeDecl,
+    xmlSAX2AttributeDecl,
-    elementDecl,
+    xmlSAX2ElementDecl,
-    unparsedEntityDecl,
+    xmlSAX2UnparsedEntityDecl,
-    setDocumentLocator,
+    xmlSAX2SetDocumentLocator,
-    startDocument,
+    xmlSAX2StartDocument,
-    endDocument,
+    xmlSAX2EndDocument,
-    startElement,
+    xmlSAX2StartElement,
-    endElement,
+    xmlSAX2EndElement,
-    reference,
+    xmlSAX2Reference,
-    characters,
+    xmlSAX2Characters,
-    characters,
+    xmlSAX2Characters,
-    processingInstruction,
+    xmlSAX2ProcessingInstruction,
-    comment,
+    xmlSAX2Comment,
     xmlParserWarning,
     xmlParserError,
     xmlParserError,
-    getParameterEntity,
+    xmlSAX2GetParameterEntity,
-    cdataBlock,
+    xmlSAX2CDataBlock,
-    externalSubset,
+    xmlSAX2ExternalSubset,
-    0
+    0,
+    NULL,
+    NULL,
+    NULL,
+    NULL
 };
 
 /**
@@ -368,7 +372,10 @@ xmlSAXHandler xmlDefaultSAXHandler = {
  * { getPublicId, getSystemId, getLineNumber, getColumnNumber}
  */
 xmlSAXLocator xmlDefaultSAXLocator = {
-    getPublicId, getSystemId, getLineNumber, getColumnNumber
+    xmlSAX2GetPublicId,
+    xmlSAX2GetSystemId,
+    xmlSAX2GetLineNumber,
+    xmlSAX2GetColumnNumber
 };
 
 #ifdef LIBXML_HTML_ENABLED
@@ -378,34 +385,38 @@ xmlSAXLocator xmlDefaultSAXLocator = {
  * Default handler for HTML, builds the DOM tree
  */
 xmlSAXHandler htmlDefaultSAXHandler = {
-    internalSubset,
+    xmlSAX2InternalSubset,
     NULL,
     NULL,
     NULL,
     NULL,
-    getEntity,
+    xmlSAX2GetEntity,
     NULL,
     NULL,
     NULL,
     NULL,
     NULL,
-    setDocumentLocator,
+    xmlSAX2SetDocumentLocator,
-    startDocument,
+    xmlSAX2StartDocument,
-    endDocument,
+    xmlSAX2EndDocument,
-    startElement,
+    xmlSAX2StartElement,
-    endElement,
+    xmlSAX2EndElement,
     NULL,
-    characters,
+    xmlSAX2Characters,
-    ignorableWhitespace,
+    xmlSAX2IgnorableWhitespace,
     NULL,
-    comment,
+    xmlSAX2Comment,
     xmlParserWarning,
     xmlParserError,
     xmlParserError,
-    getParameterEntity,
+    xmlSAX2GetParameterEntity,
-    cdataBlock,
+    xmlSAX2CDataBlock,
     NULL,
-    0
+    0,
+    NULL,
+    NULL,
+    NULL,
+    NULL
 };
 #endif /* LIBXML_HTML_ENABLED */
 
@@ -416,34 +427,38 @@ xmlSAXHandler htmlDefaultSAXHandler = {
  * Default handler for SGML DocBook, builds the DOM tree
  */
 xmlSAXHandler docbDefaultSAXHandler = {
-    internalSubset,
+    xmlSAX2InternalSubset,
-    isStandalone,
+    xmlSAX2IsStandalone,
-    hasInternalSubset,
+    xmlSAX2HasInternalSubset,
-    hasExternalSubset,
+    xmlSAX2HasExternalSubset,
-    resolveEntity,
+    xmlSAX2ResolveEntity,
-    getEntity,
+    xmlSAX2GetEntity,
-    entityDecl,
+    xmlSAX2EntityDecl,
     NULL,
     NULL,
     NULL,
     NULL,
-    setDocumentLocator,
+    xmlSAX2SetDocumentLocator,
-    startDocument,
+    xmlSAX2StartDocument,
-    endDocument,
+    xmlSAX2EndDocument,
-    startElement,
+    xmlSAX2StartElement,
-    endElement,
+    xmlSAX2EndElement,
-    reference,
+    xmlSAX2Reference,
-    characters,
+    xmlSAX2Characters,
-    ignorableWhitespace,
+    xmlSAX2IgnorableWhitespace,
     NULL,
-    comment,
+    xmlSAX2Comment,
     xmlParserWarning,
     xmlParserError,
     xmlParserError,
-    getParameterEntity,
+    xmlSAX2GetParameterEntity,
     NULL,
     NULL,
-    0
+    0,
+    NULL,
+    NULL,
+    NULL,
+    NULL
 };
 #endif /* LIBXML_DOCB_ENABLED */
 

include/libxml/Makefile.am

@@ -40,7 +40,8 @@ xmlinc_HEADERS = \
 		xmlunicode.h \
 		xmlreader.h \
 		relaxng.h \
-		dict.h
+		dict.h \
+		SAX2.h
 
 install-exec-hook:
 	$(mkinstalldirs) $(DESTDIR)$(xmlincdir)

include/libxml/SAX.h

@@ -119,9 +119,6 @@ void		inithtmlDefaultSAXHandler	(xmlSAXHandler *hdlr);
 #ifdef LIBXML_DOCB_ENABLED
 void		initdocbDefaultSAXHandler	(xmlSAXHandler *hdlr);
 #endif
-void		xmlDefaultSAXHandlerInit	(void);
-void		htmlDefaultSAXHandlerInit	(void);
-void		docbDefaultSAXHandlerInit	(void);
 #ifdef __cplusplus
 }
 #endif

include/libxml/SAX2.h

@@ -0,0 +1,125 @@
+/*
+ * SAX.h : Default SAX2 handler interfaces to build a tree.
+ *
+ * See Copyright for the status of this software.
+ *
+ * Daniel Veillard <daniel@veillard.com>
+ */
+
+
+#ifndef __XML_SAX2_H__
+#define __XML_SAX2_H__
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <libxml/parser.h>
+#include <libxml/xlink.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+const xmlChar *	xmlSAX2GetPublicId		(void *ctx);
+const xmlChar *	xmlSAX2GetSystemId		(void *ctx);
+void		xmlSAX2SetDocumentLocator	(void *ctx,
+						 xmlSAXLocatorPtr loc);
+    
+int		xmlSAX2GetLineNumber		(void *ctx);
+int		xmlSAX2GetColumnNumber		(void *ctx);
+
+int		xmlSAX2IsStandalone		(void *ctx);
+int		xmlSAX2HasInternalSubset	(void *ctx);
+int		xmlSAX2HasExternalSubset	(void *ctx);
+
+void		xmlSAX2InternalSubset		(void *ctx,
+						 const xmlChar *name,
+						 const xmlChar *ExternalID,
+						 const xmlChar *SystemID);
+void		xmlSAX2ExternalSubset		(void *ctx,
+						 const xmlChar *name,
+						 const xmlChar *ExternalID,
+						 const xmlChar *SystemID);
+xmlEntityPtr	xmlSAX2GetEntity		(void *ctx,
+						 const xmlChar *name);
+xmlEntityPtr	xmlSAX2GetParameterEntity	(void *ctx,
+						 const xmlChar *name);
+xmlParserInputPtr xmlSAX2ResolveEntity		(void *ctx,
+						 const xmlChar *publicId,
+						 const xmlChar *systemId);
+
+void		xmlSAX2EntityDecl		(void *ctx,
+						 const xmlChar *name,
+						 int type,
+						 const xmlChar *publicId,
+						 const xmlChar *systemId,
+						 xmlChar *content);
+void		xmlSAX2AttributeDecl		(void *ctx,
+						 const xmlChar *elem,
+						 const xmlChar *fullname,
+						 int type,
+						 int def,
+						 const xmlChar *defaultValue,
+						 xmlEnumerationPtr tree);
+void		xmlSAX2ElementDecl		(void *ctx,
+						 const xmlChar *name,
+						 int type,
+						 xmlElementContentPtr content);
+void		xmlSAX2NotationDecl		(void *ctx,
+						 const xmlChar *name,
+						 const xmlChar *publicId,
+						 const xmlChar *systemId);
+void		xmlSAX2UnparsedEntityDecl	(void *ctx,
+						 const xmlChar *name,
+						 const xmlChar *publicId,
+						 const xmlChar *systemId,
+						 const xmlChar *notationName);
+
+void		xmlSAX2StartDocument		(void *ctx);
+void		xmlSAX2EndDocument		(void *ctx);
+void		xmlSAX2StartElement		(void *ctx,
+						 const xmlChar *fullname,
+						 const xmlChar **atts);
+void		xmlSAX2EndElement		(void *ctx,
+						 const xmlChar *name);
+void		xmlSAX2Reference		(void *ctx,
+						 const xmlChar *name);
+void		xmlSAX2Characters		(void *ctx,
+						 const xmlChar *ch,
+						 int len);
+void		xmlSAX2IgnorableWhitespace	(void *ctx,
+						 const xmlChar *ch,
+						 int len);
+void		xmlSAX2ProcessingInstruction	(void *ctx,
+						 const xmlChar *target,
+						 const xmlChar *data);
+void		xmlSAX2GlobalNamespace		(void *ctx,
+						 const xmlChar *href,
+						 const xmlChar *prefix);
+void		xmlSAX2SetNamespace		(void *ctx,
+						 const xmlChar *name);
+xmlNsPtr	xmlSAX2GetNamespace		(void *ctx);
+int		xmlSAX2CheckNamespace		(void *ctx,
+						 xmlChar *nameSpace);
+void		xmlSAX2NamespaceDecl		(void *ctx,
+						 const xmlChar *href,
+						 const xmlChar *prefix);
+void		xmlSAX2Comment			(void *ctx,
+						 const xmlChar *value);
+void		xmlSAX2CDataBlock		(void *ctx,
+						 const xmlChar *value,
+						 int len);
+
+void		xmlSAX2InitDefaultSAXHandler    (xmlSAXHandler *hdlr,
+						 int warning);
+#ifdef LIBXML_HTML_ENABLED
+void		xmlSAX2InitHtmlDefaultSAXHandler(xmlSAXHandler *hdlr);
+#endif
+#ifdef LIBXML_DOCB_ENABLED
+void		xmlSAX2InitDocbDefaultSAXHandler(xmlSAXHandler *hdlr);
+#endif
+void		xmlDefaultSAXHandlerInit	(void);
+void		htmlDefaultSAXHandlerInit	(void);
+void		docbDefaultSAXHandlerInit	(void);
+#ifdef __cplusplus
+}
+#endif
+#endif /* __XML_SAX2_H__ */

include/libxml/globals.h

@@ -15,7 +15,7 @@
 
 #include <libxml/parser.h>
 #include <libxml/xmlerror.h>
-#include <libxml/SAX.h>
+#include <libxml/SAX2.h>
 #include <libxml/xmlmemory.h>
 
 #ifdef __cplusplus

include/libxml/parser.h

@@ -574,6 +574,7 @@ typedef int (*isStandaloneSAXFunc) (void *ctx);
  * Returns 1 if true
  */
 typedef int (*hasInternalSubsetSAXFunc) (void *ctx);
+
 /**
  * hasExternalSubsetSAXFunc:
  * @ctx:  the user data (XML parser context)
@@ -584,6 +585,80 @@ typedef int (*hasInternalSubsetSAXFunc) (void *ctx);
  */
 typedef int (*hasExternalSubsetSAXFunc) (void *ctx);
 
+/************************************************************************
+ *									*
+ *			The SAX version 2 API extensions		*
+ *									*
+ ************************************************************************/
+/**
+ * XML_SAX2_MAGIC:
+ *
+ * Special constant found in SAX2 blocks initialized fields
+ */
+#define XML_SAX2_MAGIC 0xDEEDBEAF
+
+/**
+ * startElementNsSAX2Func:
+ * @ctx:  the user data (XML parser context)
+ * @localname:  the local name of the element
+ * @prefix:  the element namespace prefix if available
+ * @URI:  the element namespace name if available
+ * @nb_namespaces:  number of namespace definitions on that node
+ * @namespaces:  pointer to the array of prefix/URI pairs namespace definitions
+ * @nb_attributes:  the number of attributes on that node
+ *
+ * SAX2 callback when an element start has been detected by the parser.
+ * It provides the namespace informations for the element, as well as
+ * the new namespace declarations on the element.
+ * The number of attributes is given in this callback but the attributes
+ * themselves will be provided as separate callbacks.
+ */
+
+typedef void (*startElementNsSAX2Func) (void *ctx,
+					const xmlChar *localname,
+					const xmlChar *prefix,
+					const xmlChar *URI,
+					int nb_namespaces,
+					const xmlChar **namespaces,
+					int nb_attributes);
+ 
+/**
+ * endElementNsSAX2Func:
+ * @ctx:  the user data (XML parser context)
+ * @localname:  the local name of the element
+ * @prefix:  the element namespace prefix if available
+ * @URI:  the element namespace name if available
+ *
+ * SAX2 callback when an element end has been detected by the parser.
+ * It provides the namespace informations for the element.
+ */
+
+typedef void (*endElementNsSAX2Func)   (void *ctx,
+					const xmlChar *localname,
+					const xmlChar *prefix,
+					const xmlChar *URI);
+
+/**
+ * attributeNsSAX2Func:
+ * @ctx:  the user data (XML parser context)
+ * @localname:  the local name of the attribute
+ * @prefix:  the attribute namespace prefix if available
+ * @URI:  the attribute namespace name if available
+ * @value:  pointer to the attribute value string
+ * @valuelen:  lenght of the attribute value string in bytes
+ *
+ * SAX2 callback when an attribute has been detected by the parser.
+ * It provides the namespace informations for the attribute, as well as
+ * the value of the attribute (note that @value may not be zero terminated
+ * and use of the @valuelen is needed to find the value end).
+ */
+typedef void (*attributeNsSAX2Func)    (void *ctx,
+					const xmlChar *localname,
+					const xmlChar *prefix,
+					const xmlChar *URI,
+					const xmlChar *value,
+					int valuelen);
+
 struct _xmlSAXHandler {
     internalSubsetSAXFunc internalSubset;
     isStandaloneSAXFunc isStandalone;
@@ -613,6 +688,11 @@ struct _xmlSAXHandler {
     cdataBlockSAXFunc cdataBlock;
     externalSubsetSAXFunc externalSubset;
     int initialized;
+    /* The following fields are extensions available only on version 2 */
+    void *_private;
+    startElementNsSAX2Func startElementNs;
+    endElementNsSAX2Func endElementNs;
+    attributeNsSAX2Func attributeNs;
 };
 
 /**

parser.c

@@ -3682,8 +3682,8 @@ xmlParseEntityDecl(xmlParserCtxtPtr ctxt) {
 			ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc,
 					    BAD_CAST "fake", NULL, NULL);
 
-		    entityDecl(ctxt, name, XML_INTERNAL_GENERAL_ENTITY,
+		    xmlSAX2EntityDecl(ctxt, name, XML_INTERNAL_GENERAL_ENTITY,
-			       NULL, NULL, value);
+			              NULL, NULL, value);
 		}
 	    } else {
 	        URI = xmlParseExternalID(ctxt, &literal, 1);
@@ -3775,9 +3775,9 @@ xmlParseEntityDecl(xmlParserCtxtPtr ctxt) {
 			if (ctxt->myDoc->intSubset == NULL)
 			    ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc,
 						BAD_CAST "fake", NULL, NULL);
-			entityDecl(ctxt, name,
+			xmlSAX2EntityDecl(ctxt, name,
-				    XML_EXTERNAL_GENERAL_PARSED_ENTITY,
+				          XML_EXTERNAL_GENERAL_PARSED_ENTITY,
-				    literal, URI, NULL);
+				          literal, URI, NULL);
 		    }
 		}
 	    }
@@ -3816,7 +3816,7 @@ xmlParseEntityDecl(xmlParserCtxtPtr ctxt) {
 		    (ctxt->sax->getEntity != NULL))
 		    cur = ctxt->sax->getEntity(ctxt->userData, name);
 		if ((cur == NULL) && (ctxt->userData==ctxt)) {
-		    cur = getEntity(ctxt, name);
+		    cur = xmlSAX2GetEntity(ctxt, name);
 		}
 	    }
             if (cur != NULL) {
@@ -5746,7 +5746,7 @@ xmlParseEntityRef(xmlParserCtxtPtr ctxt) {
 		        ent = xmlGetPredefinedEntity(name);
 		    if ((ctxt->wellFormed == 1 ) && (ent == NULL) &&
 			(ctxt->userData==ctxt)) {
-			ent = getEntity(ctxt, name);
+			ent = xmlSAX2GetEntity(ctxt, name);
 		    }
 		}
 		/*
@@ -5942,7 +5942,7 @@ xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, const xmlChar ** str) {
 		    if (ent == NULL)
 		        ent = xmlGetPredefinedEntity(name);
 		    if ((ent == NULL) && (ctxt->userData==ctxt)) {
-			ent = getEntity(ctxt, name);
+			ent = xmlSAX2GetEntity(ctxt, name);
 		    }
 		}
 		/*