/* * testSAX.c : a small tester program for parsing using the SAX API. * * See Copyright for the status of this software. * * daniel@veillard.com */ #include "libxml.h" #ifdef HAVE_SYS_TIME_H #include #endif #ifdef HAVE_SYS_TIMEB_H #include #endif #ifdef HAVE_TIME_H #include #endif #ifdef LIBXML_SAX1_ENABLED #include #include #ifdef HAVE_SYS_TYPES_H #include #endif #ifdef HAVE_SYS_STAT_H #include #endif #ifdef HAVE_FCNTL_H #include #endif #ifdef HAVE_UNISTD_H #include #endif #ifdef HAVE_STDLIB_H #include #endif #ifdef HAVE_STRING_H #include #endif #include #include #include #include /* only for xmlNewInputFromFile() */ #include #include #include static int debug = 0; static int copy = 0; static int recovery = 0; static int push = 0; static int speed = 0; static int noent = 0; static int quiet = 0; static int nonull = 0; static int sax2 = 0; static int repeat = 0; static int callbacks = 0; static int timing = 0; /* * Timing routines. */ /* * Internal timing routines to remove the necessity to have unix-specific * function calls */ #ifndef HAVE_GETTIMEOFDAY #ifdef HAVE_SYS_TIMEB_H #ifdef HAVE_SYS_TIME_H #ifdef HAVE_FTIME static int my_gettimeofday(struct timeval *tvp, void *tzp) { struct timeb timebuffer; ftime(&timebuffer); if (tvp) { tvp->tv_sec = timebuffer.time; tvp->tv_usec = timebuffer.millitm * 1000L; } return (0); } #define HAVE_GETTIMEOFDAY 1 #define gettimeofday my_gettimeofday #endif /* HAVE_FTIME */ #endif /* HAVE_SYS_TIME_H */ #endif /* HAVE_SYS_TIMEB_H */ #endif /* !HAVE_GETTIMEOFDAY */ #if defined(HAVE_GETTIMEOFDAY) static struct timeval begin, end; /* * startTimer: call where you want to start timing */ static void startTimer(void) { gettimeofday(&begin, NULL); } /* * endTimer: call where you want to stop timing and to print out a * message about the timing performed; format is a printf * type argument */ static void XMLCDECL endTimer(const char *fmt, ...) { long msec; va_list ap; gettimeofday(&end, NULL); msec = end.tv_sec - begin.tv_sec; msec *= 1000; msec += (end.tv_usec - begin.tv_usec) / 1000; #ifndef HAVE_STDARG_H #error "endTimer required stdarg functions" #endif va_start(ap, fmt); vfprintf(stderr, fmt, ap); va_end(ap); fprintf(stderr, " took %ld ms\n", msec); } #elif defined(HAVE_TIME_H) /* * No gettimeofday function, so we have to make do with calling clock. * This is obviously less accurate, but there's little we can do about * that. */ #ifndef CLOCKS_PER_SEC #define CLOCKS_PER_SEC 100 #endif static clock_t begin, end; static void startTimer(void) { begin = clock(); } static void XMLCDECL endTimer(const char *fmt, ...) { long msec; va_list ap; end = clock(); msec = ((end - begin) * 1000) / CLOCKS_PER_SEC; #ifndef HAVE_STDARG_H #error "endTimer required stdarg functions" #endif va_start(ap, fmt); vfprintf(stderr, fmt, ap); va_end(ap); fprintf(stderr, " took %ld ms\n", msec); } #else /* * We don't have a gettimeofday or time.h, so we just don't do timing */ static void startTimer(void) { /* * Do nothing */ } static void XMLCDECL endTimer(char *format, ...) { /* * We cannot do anything because we don't have a timing function */ #ifdef HAVE_STDARG_H va_start(ap, format); vfprintf(stderr, format, ap); va_end(ap); fprintf(stderr, " was not timed\n", msec); #else /* We don't have gettimeofday, time or stdarg.h, what crazy world is * this ?! */ #endif } #endif /* * empty SAX block */ 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, NULL, NULL, /* startElementNs */ NULL, /* endElementNs */ 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 int isStandaloneDebug(void *ctx ATTRIBUTE_UNUSED) { callbacks++; if (quiet) return(0); 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 int hasInternalSubsetDebug(void *ctx ATTRIBUTE_UNUSED) { callbacks++; if (quiet) return(0); 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 int hasExternalSubsetDebug(void *ctx ATTRIBUTE_UNUSED) { callbacks++; if (quiet) return(0); fprintf(stdout, "SAX.hasExternalSubset()\n"); return(0); } /** * internalSubsetDebug: * @ctxt: An XML parser context * * Does this document has an internal subset */ static void internalSubsetDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, const xmlChar *ExternalID, const xmlChar *SystemID) { callbacks++; if (quiet) return; 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); } /** * externalSubsetDebug: * @ctxt: An XML parser context * * Does this document has an external subset */ static void externalSubsetDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, const xmlChar *ExternalID, const xmlChar *SystemID) { callbacks++; if (quiet) return; fprintf(stdout, "SAX.externalSubset(%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 xmlParserInputPtr resolveEntityDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *publicId, const xmlChar *systemId) { callbacks++; if (quiet) return(NULL); /* 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 xmlEntityPtr getEntityDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name) { callbacks++; if (quiet) return(NULL); 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 xmlEntityPtr getParameterEntityDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name) { callbacks++; if (quiet) return(NULL); 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 void entityDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, int type, const xmlChar *publicId, const xmlChar *systemId, xmlChar *content) { const xmlChar *nullstr = BAD_CAST "(null)"; /* not all libraries handle printing null pointers nicely */ if (publicId == NULL) publicId = nullstr; if (systemId == NULL) systemId = nullstr; if (content == NULL) content = (xmlChar *)nullstr; callbacks++; if (quiet) return; 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 void attributeDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar * elem, const xmlChar * name, int type, int def, const xmlChar * defaultValue, xmlEnumerationPtr tree) { callbacks++; if (quiet) return; if (defaultValue == NULL) fprintf(stdout, "SAX.attributeDecl(%s, %s, %d, %d, NULL, ...)\n", elem, name, type, def); else fprintf(stdout, "SAX.attributeDecl(%s, %s, %d, %d, %s, ...)\n", elem, name, type, def, defaultValue); xmlFreeEnumeration(tree); } /** * 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 void elementDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, int type, xmlElementContentPtr content ATTRIBUTE_UNUSED) { callbacks++; if (quiet) return; 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 void notationDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, const xmlChar *publicId, const xmlChar *systemId) { callbacks++; if (quiet) return; 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 void unparsedEntityDeclDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, const xmlChar *publicId, const xmlChar *systemId, const xmlChar *notationName) { const xmlChar *nullstr = BAD_CAST "(null)"; if (publicId == NULL) publicId = nullstr; if (systemId == NULL) systemId = nullstr; if (notationName == NULL) notationName = nullstr; callbacks++; if (quiet) return; 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 void setDocumentLocatorDebug(void *ctx ATTRIBUTE_UNUSED, xmlSAXLocatorPtr loc ATTRIBUTE_UNUSED) { callbacks++; if (quiet) return; fprintf(stdout, "SAX.setDocumentLocator()\n"); } /** * startDocumentDebug: * @ctxt: An XML parser context * * called when the document start being processed. */ static void startDocumentDebug(void *ctx ATTRIBUTE_UNUSED) { callbacks++; if (quiet) return; fprintf(stdout, "SAX.startDocument()\n"); } /** * endDocumentDebug: * @ctxt: An XML parser context * * called when the document end has been detected. */ static void endDocumentDebug(void *ctx ATTRIBUTE_UNUSED) { callbacks++; if (quiet) return; fprintf(stdout, "SAX.endDocument()\n"); } /** * startElementDebug: * @ctxt: An XML parser context * @name: The element name * * called when an opening tag has been processed. */ static void startElementDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name, const xmlChar **atts) { int i; callbacks++; if (quiet) return; 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) fprintf(stdout, "%s'", atts[i]); } } fprintf(stdout, ")\n"); } /** * endElementDebug: * @ctxt: An XML parser context * @name: The element name * * called when the end of an element has been detected. */ static void endElementDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *name) { callbacks++; if (quiet) return; 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 void charactersDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *ch, int len) { char output[40]; int i; callbacks++; if (quiet) return; for (i = 0;(i 0) { ctxt = xmlCreatePushParserCtxt(emptySAXHandler, NULL, chars, ret, filename); while ((ret = fread(chars, 1, 3, f)) > 0) { xmlParseChunk(ctxt, chars, ret, 0); } xmlParseChunk(ctxt, chars, 0, 1); xmlFreeParserCtxt(ctxt); } fclose(f); } else { xmlGenericError(xmlGenericErrorContext, "Cannot read file %s\n", filename); } } /* * Debug callback */ #if defined(_WIN32) || defined (__DJGPP__) && !defined (__CYGWIN__) f = fopen(filename, "rb"); #else f = fopen(filename, "r"); #endif if (f != NULL) { int ret; char chars[10]; xmlParserCtxtPtr ctxt; ret = fread(chars, 1, 4, f); if (ret > 0) { if (sax2) ctxt = xmlCreatePushParserCtxt(debugSAX2Handler, NULL, chars, ret, filename); else ctxt = xmlCreatePushParserCtxt(debugSAXHandler, NULL, chars, ret, filename); while ((ret = fread(chars, 1, 3, f)) > 0) { xmlParseChunk(ctxt, chars, ret, 0); } ret = xmlParseChunk(ctxt, chars, 0, 1); xmlFreeParserCtxt(ctxt); if (ret != 0) { fprintf(stdout, "xmlSAXUserParseFile returned error %d\n", ret); } } fclose(f); } } else { #endif /* LIBXML_PUSH_ENABLED */ if (!speed) { /* * Empty callbacks for checking */ if ((!quiet) && (!nonull)) { res = xmlSAXUserParseFile(emptySAXHandler, NULL, filename); if (res != 0) { fprintf(stdout, "xmlSAXUserParseFile returned error %d\n", res); } } /* * Debug callback */ callbacks = 0; if (repeat) { int i; for (i = 0;i < 99;i++) { if (sax2) res = xmlSAXUserParseFile(debugSAX2Handler, NULL, filename); else res = xmlSAXUserParseFile(debugSAXHandler, NULL, filename); } } if (sax2) res = xmlSAXUserParseFile(debugSAX2Handler, NULL, filename); else res = xmlSAXUserParseFile(debugSAXHandler, NULL, filename); if (res != 0) { fprintf(stdout, "xmlSAXUserParseFile returned error %d\n", res); } if (quiet) fprintf(stdout, "%d callbacks generated\n", callbacks); } else { /* * test 100x the SAX parse */ int i; for (i = 0; i<100;i++) res = xmlSAXUserParseFile(emptySAXHandler, NULL, filename); if (res != 0) { fprintf(stdout, "xmlSAXUserParseFile returned error %d\n", res); } } #ifdef LIBXML_PUSH_ENABLED } #endif } int main(int argc, char **argv) { int i; int files = 0; LIBXML_TEST_VERSION /* be safe, plus calls xmlInitParser */ for (i = 1; i < argc ; i++) { if ((!strcmp(argv[i], "-debug")) || (!strcmp(argv[i], "--debug"))) debug++; else if ((!strcmp(argv[i], "-copy")) || (!strcmp(argv[i], "--copy"))) copy++; else if ((!strcmp(argv[i], "-recover")) || (!strcmp(argv[i], "--recover"))) recovery++; else if ((!strcmp(argv[i], "-push")) || (!strcmp(argv[i], "--push"))) #ifdef LIBXML_PUSH_ENABLED push++; #else fprintf(stderr,"'push' not enabled in library - ignoring\n"); #endif /* LIBXML_PUSH_ENABLED */ else if ((!strcmp(argv[i], "-speed")) || (!strcmp(argv[i], "--speed"))) speed++; else if ((!strcmp(argv[i], "-timing")) || (!strcmp(argv[i], "--timing"))) { nonull++; timing++; quiet++; } else if ((!strcmp(argv[i], "-repeat")) || (!strcmp(argv[i], "--repeat"))) { repeat++; quiet++; } else if ((!strcmp(argv[i], "-noent")) || (!strcmp(argv[i], "--noent"))) noent++; else if ((!strcmp(argv[i], "-quiet")) || (!strcmp(argv[i], "--quiet"))) quiet++; else if ((!strcmp(argv[i], "-sax2")) || (!strcmp(argv[i], "--sax2"))) sax2++; else if ((!strcmp(argv[i], "-nonull")) || (!strcmp(argv[i], "--nonull"))) nonull++; } if (noent != 0) xmlSubstituteEntitiesDefault(1); for (i = 1; i < argc ; i++) { if (argv[i][0] != '-') { if (timing) { startTimer(); } parseAndPrintFile(argv[i]); if (timing) { endTimer("Parsing"); } files ++; } } xmlCleanupParser(); xmlMemoryDump(); return(0); } #else int main(int argc ATTRIBUTE_UNUSED, char **argv ATTRIBUTE_UNUSED) { printf("%s : SAX1 parsing support not compiled in\n", argv[0]); return(0); } #endif /* LIBXML_SAX1_ENABLED */