/* * testHTML.c : a small tester program for HTML input. * * See Copyright for the status of this software. * * daniel@veillard.com */ #include "libxml.h" #ifdef LIBXML_HTML_ENABLED #include <string.h>#include <stdarg.h>  #ifdef HAVE_SYS_TYPES_H#include <sys/types.h>#endif#ifdef HAVE_SYS_STAT_H#include <sys/stat.h>#endif#ifdef HAVE_FCNTL_H#include <fcntl.h>#endif#ifdef HAVE_UNISTD_H#include <unistd.h>#endif#ifdef HAVE_STDLIB_H#include <stdlib.h>#endif #include <libxml/xmlmemory.h>#include <libxml/HTMLparser.h>#include <libxml/HTMLtree.h>#include <libxml/debugXML.h>#include <libxml/xmlerror.h>#include <libxml/globals.h> #ifdef LIBXML_DEBUG_ENABLEDstatic int debug = 0;#endifstatic int copy = 0;static int sax = 0;static int repeat = 0;static int noout = 0;#ifdef LIBXML_PUSH_ENABLEDstatic int push = 0;#endif /* LIBXML_PUSH_ENABLED */static char *encoding = NULL;static int options = 0; static xmlSAXHandler emptySAXHandlerStruct = {    NULL, /* internalSubset */    NULL, /* isStandalone */    NULL, /* hasInternalSubset */    NULL, /* hasExternalSubset */    NULL, /* resolveEntity */    NULL, /* getEntity */    NULL, /* entityDecl */    NULL, /* notationDecl */    NULL, /* attributeDecl */    NULL, /* elementDecl */    NULL, /* unparsedEntityDecl */    NULL, /* setDocumentLocator */    NULL, /* startDocument */    NULL, /* endDocument */    NULL, /* startElement */    NULL, /* endElement */    NULL, /* reference */    NULL, /* characters */    NULL, /* ignorableWhitespace */    NULL, /* processingInstruction */    NULL, /* comment */    NULL, /* xmlParserWarning */    NULL, /* xmlParserError */    NULL, /* xmlParserError */    NULL, /* getParameterEntity */    NULL, /* cdataBlock */    NULL, /* externalSubset */    1,    /* initialized */    NULL, /* private */    NULL, /* startElementNsSAX2Func */    NULL, /* endElementNsSAX2Func */    NULL  /* xmlStructuredErrorFunc */}; static xmlSAXHandlerPtr emptySAXHandler = &emptySAXHandlerStruct;extern xmlSAXHandlerPtr debugSAXHandler; /************************************************************************ *									* *				Debug Handlers				* *									* ************************************************************************/ /** * isStandaloneDebug: * @ctxt:  An XML parser context * * Is this document tagged standalone ? * * Returns 1 if true */static intisStandaloneDebug(void *ctx ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.isStandalone()\n");    return(0);} /** * hasInternalSubsetDebug: * @ctxt:  An XML parser context * * Does this document has an internal subset * * Returns 1 if true */static inthasInternalSubsetDebug(void *ctx ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.hasInternalSubset()\n");    return(0);} /** * hasExternalSubsetDebug: * @ctxt:  An XML parser context * * Does this document has an external subset * * Returns 1 if true */static inthasExternalSubsetDebug(void *ctx ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.hasExternalSubset()\n");    return(0);} /** * hasInternalSubsetDebug: * @ctxt:  An XML parser context * * Does this document has an internal subset */static voidinternalSubsetDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name,	       const xmlChar *ExternalID, const xmlChar *SystemID){    fprintf(stdout, "SAX.internalSubset(%s,", name);    if (ExternalID == NULL)	fprintf(stdout, " ,");    else	fprintf(stdout, " %s,", ExternalID);    if (SystemID == NULL)	fprintf(stdout, " )\n");    else	fprintf(stdout, " %s)\n", SystemID);} /** * resolveEntityDebug: * @ctxt:  An XML parser context * @publicId: The public ID of the entity * @systemId: The system ID of the entity * * Special entity resolver, better left to the parser, it has * more context than the application layer. * The default behaviour is to NOT resolve the entities, in that case * the ENTITY_REF nodes are built in the structure (and the parameter * values). * * Returns the xmlParserInputPtr if inlined or NULL for DOM behaviour. */static xmlParserInputPtrresolveEntityDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *publicId, const xmlChar *systemId){    /* xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; */      fprintf(stdout, "SAX.resolveEntity(");    if (publicId != NULL)	fprintf(stdout, "%s", (char *)publicId);    else	fprintf(stdout, " ");    if (systemId != NULL)	fprintf(stdout, ", %s)\n", (char *)systemId);    else	fprintf(stdout, ", )\n");/*********    if (systemId != NULL) {        return(xmlNewInputFromFile(ctxt, (char *) systemId));    } *********/    return(NULL);} /** * getEntityDebug: * @ctxt:  An XML parser context * @name: The entity name * * Get an entity by name * * Returns the xmlParserInputPtr if inlined or NULL for DOM behaviour. */static xmlEntityPtrgetEntityDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name){    fprintf(stdout, "SAX.getEntity(%s)\n", name);    return(NULL);} /** * getParameterEntityDebug: * @ctxt:  An XML parser context * @name: The entity name * * Get a parameter entity by name * * Returns the xmlParserInputPtr */static xmlEntityPtrgetParameterEntityDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name){    fprintf(stdout, "SAX.getParameterEntity(%s)\n", name);    return(NULL);}  /** * entityDeclDebug: * @ctxt:  An XML parser context * @name:  the entity name * @type:  the entity type * @publicId: The public ID of the entity * @systemId: The system ID of the entity * @content: the entity value (without processing). * * An entity definition has been parsed */static voidentityDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, int type,          const xmlChar *publicId, const xmlChar *systemId, xmlChar *content){    fprintf(stdout, "SAX.entityDecl(%s, %d, %s, %s, %s)\n",            name, type, publicId, systemId, content);} /** * attributeDeclDebug: * @ctxt:  An XML parser context * @name:  the attribute name * @type:  the attribute type * * An attribute definition has been parsed */static voidattributeDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *elem, const xmlChar *name,              int type, int def, const xmlChar *defaultValue,	      xmlEnumerationPtr tree ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.attributeDecl(%s, %s, %d, %d, %s, ...)\n",            elem, name, type, def, defaultValue);} /** * elementDeclDebug: * @ctxt:  An XML parser context * @name:  the element name * @type:  the element type * @content: the element value (without processing). * * An element definition has been parsed */static voidelementDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, int type,	    xmlElementContentPtr content ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.elementDecl(%s, %d, ...)\n",            name, type);} /** * notationDeclDebug: * @ctxt:  An XML parser context * @name: The name of the notation * @publicId: The public ID of the entity * @systemId: The system ID of the entity * * What to do when a notation declaration has been parsed. */static voidnotationDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name,	     const xmlChar *publicId, const xmlChar *systemId){    fprintf(stdout, "SAX.notationDecl(%s, %s, %s)\n",            (char *) name, (char *) publicId, (char *) systemId);} /** * unparsedEntityDeclDebug: * @ctxt:  An XML parser context * @name: The name of the entity * @publicId: The public ID of the entity * @systemId: The system ID of the entity * @notationName: the name of the notation * * What to do when an unparsed entity declaration is parsed */static voidunparsedEntityDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name,		   const xmlChar *publicId, const xmlChar *systemId,		   const xmlChar *notationName){    fprintf(stdout, "SAX.unparsedEntityDecl(%s, %s, %s, %s)\n",            (char *) name, (char *) publicId, (char *) systemId,	    (char *) notationName);} /** * setDocumentLocatorDebug: * @ctxt:  An XML parser context * @loc: A SAX Locator * * Receive the document locator at startup, actually xmlDefaultSAXLocator * Everything is available on the context, so this is useless in our case. */static voidsetDocumentLocatorDebug(void *ctx ATTRIBUTE_UNUSED, xmlSAXLocatorPtr loc ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.setDocumentLocator()\n");} /** * startDocumentDebug: * @ctxt:  An XML parser context * * called when the document start being processed. */static voidstartDocumentDebug(void *ctx ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.startDocument()\n");} /** * endDocumentDebug: * @ctxt:  An XML parser context * * called when the document end has been detected. */static voidendDocumentDebug(void *ctx ATTRIBUTE_UNUSED){    fprintf(stdout, "SAX.endDocument()\n");} /** * startElementDebug: * @ctxt:  An XML parser context * @name:  The element name * * called when an opening tag has been processed. */static voidstartElementDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, const xmlChar **atts){    int i;     fprintf(stdout, "SAX.startElement(%s", (char *) name);    if (atts != NULL) {        for (i = 0;(atts[i] != NULL);i++) {	    fprintf(stdout, ", %s", atts[i++]);	    if (atts[i] != NULL) {		unsigned char output[40];		const unsigned char *att = atts[i];		int outlen, attlen;	        fprintf(stdout, "='");		while ((attlen = strlen((char*)att)) > 0) {		    outlen = sizeof output - 1;		    htmlEncodeEntities(output, &outlen, att, &attlen, '\'');		    output[outlen] = 0;		    fprintf(stdout, "%s", (char *) output);		    att += attlen;		}		fprintf(stdout, "'");	    }	}    }    fprintf(stdout, ")\n");} /** * endElementDebug: * @ctxt:  An XML parser context * @name:  The element name * * called when the end of an element has been detected. */static voidendElementDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name){    fprintf(stdout, "SAX.endElement(%s)\n", (char *) name);} /** * charactersDebug: * @ctxt:  An XML parser context * @ch:  a xmlChar string * @len: the number of xmlChar * * receiving some chars from the parser. * Question: how much at a time ??? */static voidcharactersDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *ch, int len){    unsigned char output[40];    int inlen = len, outlen = 30;     htmlEncodeEntities(output, &outlen, ch, &inlen, 0);    output[outlen] = 0;     fprintf(stdout, "SAX.characters(%s, %d)\n", output, len);} /** * cdataDebug: * @ctxt:  An XML parser context * @ch:  a xmlChar string * @len: the number of xmlChar * * receiving some cdata chars from the parser. * Question: how much at a time ??? */static voidcdataDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *ch, int len){    unsigned char output[40];    int inlen = len, outlen = 30;     htmlEncodeEntities(output, &outlen, ch, &inlen, 0);    output[outlen] = 0;     fprintf(stdout, "SAX.cdata(%s, %d)\n", output, len);} /** * referenceDebug: * @ctxt:  An XML parser context * @name:  The entity name * * called when an entity reference is detected. */static voidreferenceDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name){    fprintf(stdout, "SAX.reference(%s)\n", name);} /** * ignorableWhitespaceDebug: * @ctxt:  An XML parser context * @ch:  a xmlChar string * @start: the first char in the string * @len: the number of xmlChar * * receiving some ignorable whitespaces from the parser. * Question: how much at a time ??? */static voidignorableWhitespaceDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *ch, int len){    char output[40];    int i;     for (i = 0;(i<len) && (i < 30);i++)	output[i] = ch[i];    output[i] = 0;     fprintf(stdout, "SAX.ignorableWhitespace(%s, %d)\n", output, len);} /** * processingInstructionDebug: * @ctxt:  An XML parser context * @target:  the target name * @data: the PI data's * @len: the number of xmlChar * * A processing instruction has been parsed. */static voidprocessingInstructionDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *target,                      const xmlChar *data){    fprintf(stdout, "SAX.processingInstruction(%s, %s)\n",

Lines 1–500 of 880. Load more