testhtml.c

ReactOS是一些高手根据Windows XP的内核编写出的类XP。内核实现机理和API函数调用几乎相同。甚至可以兼容XP的程序。喜欢研究系统内核的人可以看一看。

    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 void
referenceDebug(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 void
ignorableWhitespaceDebug(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 void
processingInstructionDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *target,
                      const xmlChar *data)
{
    fprintf(stdout, "SAX.processingInstruction(%s, %s)\n",
            (char *) target, (char *) data);
}

/**
 * commentDebug:
 * @ctxt:  An XML parser context
 * @value:  the comment content
 *
 * A comment has been parsed.
 */
static void
commentDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *value)
{
    fprintf(stdout, "SAX.comment(%s)\n", value);
}

/**
 * warningDebug:
 * @ctxt:  An XML parser context
 * @msg:  the message to display/transmit
 * @...:  extra parameters for the message display
 *
 * Display and format a warning messages, gives file, line, position and
 * extra parameters.
 */
static void
warningDebug(void *ctx ATTRIBUTE_UNUSED, const char *msg, ...)
{
    va_list args;

    va_start(args, msg);
    fprintf(stdout, "SAX.warning: ");
    vfprintf(stdout, msg, args);
    va_end(args);
}

/**
 * errorDebug:
 * @ctxt:  An XML parser context
 * @msg:  the message to display/transmit
 * @...:  extra parameters for the message display
 *
 * Display and format a error messages, gives file, line, position and
 * extra parameters.
 */
static void
errorDebug(void *ctx ATTRIBUTE_UNUSED, const char *msg, ...)
{
    va_list args;

    va_start(args, msg);
    fprintf(stdout, "SAX.error: ");
    vfprintf(stdout, msg, args);
    va_end(args);
}

/**
 * fatalErrorDebug:
 * @ctxt:  An XML parser context
 * @msg:  the message to display/transmit
 * @...:  extra parameters for the message display
 *
 * Display and format a fatalError messages, gives file, line, position and
 * extra parameters.
 */
static void
fatalErrorDebug(void *ctx ATTRIBUTE_UNUSED, const char *msg, ...)
{
    va_list args;

    va_start(args, msg);
    fprintf(stdout, "SAX.fatalError: ");
    vfprintf(stdout, msg, args);
    va_end(args);
}

xmlSAXHandler debugSAXHandlerStruct = {
    internalSubsetDebug,
    isStandaloneDebug,
    hasInternalSubsetDebug,
    hasExternalSubsetDebug,
    resolveEntityDebug,
    getEntityDebug,
    entityDeclDebug,
    notationDeclDebug,
    attributeDeclDebug,
    elementDeclDebug,
    unparsedEntityDeclDebug,
    setDocumentLocatorDebug,
    startDocumentDebug,
    endDocumentDebug,
    startElementDebug,
    endElementDebug,
    referenceDebug,
    charactersDebug,
    ignorableWhitespaceDebug,
    processingInstructionDebug,
    commentDebug,
    warningDebug,
    errorDebug,
    fatalErrorDebug,
    getParameterEntityDebug,
    cdataDebug,
    NULL,
    1,
    NULL,
    NULL,
    NULL,
    NULL
};

xmlSAXHandlerPtr debugSAXHandler = &debugSAXHandlerStruct;
/************************************************************************
 *									*
 *				Debug					*
 *									*
 ************************************************************************/

static void
parseSAXFile(char *filename) {
    htmlDocPtr doc = NULL;

    /*
     * Empty callbacks for checking
     */
#ifdef LIBXML_PUSH_ENABLED
    if (push) {
	FILE *f;

#if defined(_WIN32) || defined (__DJGPP__) && !defined (__CYGWIN__)
	f = fopen(filename, "rb");
#else
	f = fopen(filename, "r");
#endif
	if (f != NULL) {
	    int res, size = 3;
	    char chars[4096];
	    htmlParserCtxtPtr ctxt;

	    /* if (repeat) */
		size = 4096;
	    res = fread(chars, 1, 4, f);
	    if (res > 0) {
		ctxt = htmlCreatePushParserCtxt(emptySAXHandler, NULL,
			    chars, res, filename, XML_CHAR_ENCODING_NONE);
		while ((res = fread(chars, 1, size, f)) > 0) {
		    htmlParseChunk(ctxt, chars, res, 0);
		}
		htmlParseChunk(ctxt, chars, 0, 1);
		doc = ctxt->myDoc;
		htmlFreeParserCtxt(ctxt);
	    }
	    if (doc != NULL) {
		fprintf(stdout, "htmlSAXParseFile returned non-NULL\n");
		xmlFreeDoc(doc);
	    }
	    fclose(f);
	}
	if (!noout) {
#if defined(_WIN32) || defined (__DJGPP__) && !defined (__CYGWIN__)
		f = fopen(filename, "rb");
#else
		f = fopen(filename, "r");
#endif
	    if (f != NULL) {
		int res, size = 3;
		char chars[4096];
		htmlParserCtxtPtr ctxt;

		/* if (repeat) */
		    size = 4096;
		res = fread(chars, 1, 4, f);
		if (res > 0) {
		    ctxt = htmlCreatePushParserCtxt(debugSAXHandler, NULL,
				chars, res, filename, XML_CHAR_ENCODING_NONE);
		    while ((res = fread(chars, 1, size, f)) > 0) {
			htmlParseChunk(ctxt, chars, res, 0);
		    }
		    htmlParseChunk(ctxt, chars, 0, 1);
		    doc = ctxt->myDoc;
		    htmlFreeParserCtxt(ctxt);
		}
		if (doc != NULL) {
		    fprintf(stdout, "htmlSAXParseFile returned non-NULL\n");
		    xmlFreeDoc(doc);
		}
		fclose(f);
	    }
	}
    } else {	
#endif /* LIBXML_PUSH_ENABLED */
	doc = htmlSAXParseFile(filename, NULL, emptySAXHandler, NULL);
	if (doc != NULL) {
	    fprintf(stdout, "htmlSAXParseFile returned non-NULL\n");
	    xmlFreeDoc(doc);
	}

	if (!noout) {
	    /*
	     * Debug callback
	     */
	    doc = htmlSAXParseFile(filename, NULL, debugSAXHandler, NULL);
	    if (doc != NULL) {
		fprintf(stdout, "htmlSAXParseFile returned non-NULL\n");
		xmlFreeDoc(doc);
	    }
	}
#ifdef LIBXML_PUSH_ENABLED
    }
#endif /* LIBXML_PUSH_ENABLED */
}

static void
parseAndPrintFile(char *filename) {
    htmlDocPtr doc = NULL;

    /*
     * build an HTML tree from a string;
     */
#ifdef LIBXML_PUSH_ENABLED
    if (push) {
	FILE *f;

#if defined(_WIN32) || defined (__DJGPP__) && !defined (__CYGWIN__)
	f = fopen(filename, "rb");
#else
	f = fopen(filename, "r");
#endif
	if (f != NULL) {
	    int res, size = 3;
	    char chars[4096];
	    htmlParserCtxtPtr ctxt;

	    /* if (repeat) */
		size = 4096;
	    res = fread(chars, 1, 4, f);
	    if (res > 0) {
		ctxt = htmlCreatePushParserCtxt(NULL, NULL,
			    chars, res, filename, XML_CHAR_ENCODING_NONE);
		while ((res = fread(chars, 1, size, f)) > 0) {
		    htmlParseChunk(ctxt, chars, res, 0);
		}
		htmlParseChunk(ctxt, chars, 0, 1);
		doc = ctxt->myDoc;
		htmlFreeParserCtxt(ctxt);
	    }
	    fclose(f);
	}
    } else {	
	doc = htmlReadFile(filename, NULL, options);
    }
#else
	doc = htmlReadFile(filename,NULL,options);
#endif
    if (doc == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"Could not parse %s\n", filename);
    }

#ifdef LIBXML_TREE_ENABLED
    /*
     * test intermediate copy if needed.
     */
    if (copy) {
        htmlDocPtr tmp;

        tmp = doc;
	doc = xmlCopyDoc(doc, 1);
	xmlFreeDoc(tmp);
    }
#endif

#ifdef LIBXML_OUTPUT_ENABLED
    /*
     * print it.
     */
    if (!noout) { 
#ifdef LIBXML_DEBUG_ENABLED
	if (!debug) {
	    if (encoding)
		htmlSaveFileEnc("-", doc, encoding);
	    else
		htmlDocDump(stdout, doc);
	} else
	    xmlDebugDumpDocument(stdout, doc);
#else
	if (encoding)
	    htmlSaveFileEnc("-", doc, encoding);
	else
	    htmlDocDump(stdout, doc);
#endif
    }	
#endif /* LIBXML_OUTPUT_ENABLED */

    /*
     * free it.
     */
    xmlFreeDoc(doc);
}

int main(int argc, char **argv) {
    int i, count;
    int files = 0;

    for (i = 1; i < argc ; i++) {
#ifdef LIBXML_DEBUG_ENABLED
	if ((!strcmp(argv[i], "-debug")) || (!strcmp(argv[i], "--debug")))
	    debug++;
	else
#endif
	    if ((!strcmp(argv[i], "-copy")) || (!strcmp(argv[i], "--copy")))
	    copy++;
#ifdef LIBXML_PUSH_ENABLED
	else if ((!strcmp(argv[i], "-push")) || (!strcmp(argv[i], "--push")))
	    push++;
#endif /* LIBXML_PUSH_ENABLED */
	else if ((!strcmp(argv[i], "-sax")) || (!strcmp(argv[i], "--sax")))
	    sax++;
	else if ((!strcmp(argv[i], "-noout")) || (!strcmp(argv[i], "--noout")))
	    noout++;
	else if ((!strcmp(argv[i], "-repeat")) ||
	         (!strcmp(argv[i], "--repeat")))
	    repeat++;
	else if ((!strcmp(argv[i], "-encode")) ||
	         (!strcmp(argv[i], "--encode"))) {
	    i++;
	    encoding = argv[i];
        }
    }
    for (i = 1; i < argc ; i++) {
	if ((!strcmp(argv[i], "-encode")) ||
	         (!strcmp(argv[i], "--encode"))) {
	    i++;
	    continue;
        }
	if (argv[i][0] != '-') {
	    if (repeat) {
		for (count = 0;count < 100 * repeat;count++) {
		    if (sax)
			parseSAXFile(argv[i]);
		    else   
			parseAndPrintFile(argv[i]);
		}    
	    } else {
		if (sax)
		    parseSAXFile(argv[i]);
		else   
		    parseAndPrintFile(argv[i]);
	    }
	    files ++;
	}
    }
    if (files == 0) {
	printf("Usage : %s [--debug] [--copy] [--copy] HTMLfiles ...\n",
	       argv[0]);
	printf("\tParse the HTML files and output the result of the parsing\n");
#ifdef LIBXML_DEBUG_ENABLED
	printf("\t--debug : dump a debug tree of the in-memory document\n");
#endif
	printf("\t--copy : used to test the internal copy implementation\n");
	printf("\t--sax : debug the sequence of SAX callbacks\n");
	printf("\t--repeat : parse the file 100 times, for timing\n");
	printf("\t--noout : do not print the result\n");
#ifdef LIBXML_PUSH_ENABLED
	printf("\t--push : use the push mode parser\n");
#endif /* LIBXML_PUSH_ENABLED */
	printf("\t--encode encoding : output in the given encoding\n");
    }
    xmlCleanupParser();
    xmlMemoryDump();

    return(0);
}
#else /* !LIBXML_HTML_ENABLED */
#include <stdio.h>
int main(int argc ATTRIBUTE_UNUSED, char **argv ATTRIBUTE_UNUSED) {
    printf("%s : HTML support not compiled in\n", argv[0]);
    return(0);
}
#endif