testSAX.c

/*
 * 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"

#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
#ifdef HAVE_STRING_H
#include <string.h>
#endif


#include <libxml/globals.h>
#include <libxml/xmlerror.h>
#include <libxml/parser.h>
#include <libxml/parserInternals.h> /* only for xmlNewInputFromFile() */
#include <libxml/tree.h>
#include <libxml/debugXML.h>
#include <libxml/xmlmemory.h>

static int debug = 0;
static int copy = 0;
static int recovery = 0;
static int push = 0;
static int speed = 0;
static int noent = 0;

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
};

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)
{
    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)
{
    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)
{
    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)
{
    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)
{
    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)
{
    /* 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)
{
    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)
{
    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)
{
    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 ATTRIBUTE_UNUSED)
{
    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);
}

/**
 * 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)
{
    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)
{
    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)
{
    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)
{
    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)
{
    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)
{
    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;

    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)
{
    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;

    for (i = 0;(i<len) && (i < 30);i++)
	output[i] = ch[i];
    output[i] = 0;

    fprintf(stdout, "SAX.characters(%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);
}

/**
 * cdataBlockDebug:
 * @ctx: the user data (XML parser context)
 * @value:  The pcdata content
 * @len:  the block length
 *
 * called when a pcdata block has been parsed
 */
static void
cdataBlockDebug(void *ctx ATTRIBUTE_UNUSED, const xmlChar *value, int len)
{
    fprintf(stdout, "SAX.pcdata(%.20s, %d)\n",
	    (char *) value, len);
}

/**
 * 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,
    cdataBlockDebug,
    externalSubsetDebug,
    1
};

xmlSAXHandlerPtr debugSAXHandler = &debugSAXHandlerStruct;

/************************************************************************
 *									*
 *				Debug					*
 *									*
 ************************************************************************/

static void
parseAndPrintFile(char *filename) {
    int res;

    if (push) {
	FILE *f;

	/*
	 * Empty callbacks for checking
	 */
	f = fopen(filename, "r");
	if (f != NULL) {
	    int ret;
	    char chars[10];
	    xmlParserCtxtPtr ctxt;

	    ret = fread(chars, 1, 4, f);
	    if (ret > 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
	 */
	f = fopen(filename, "r");
	if (f != NULL) {
	    int ret;
	    char chars[10];
	    xmlParserCtxtPtr ctxt;

	    ret = fread(chars, 1, 4, f);
	    if (ret > 0) {
		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 {
	if (!speed) {
	    /*
	     * Empty callbacks for checking
	     */
	    res = xmlSAXUserParseFile(emptySAXHandler, NULL, filename);
	    if (res != 0) {
		fprintf(stdout, "xmlSAXUserParseFile returned error %d\n", res);
	    }

	    /*
	     * Debug callback
	     */
	    res = xmlSAXUserParseFile(debugSAXHandler, NULL, filename);
	    if (res != 0) {
		fprintf(stdout, "xmlSAXUserParseFile returned error %d\n", res);
	    }
	} 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);
	    }
	}
    }
}


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

    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")))
	    push++;
	else if ((!strcmp(argv[i], "-speed")) ||
	         (!strcmp(argv[i], "--speed")))
	    speed++;
	else if ((!strcmp(argv[i], "-noent")) ||
	         (!strcmp(argv[i], "--noent")))
	    noent++;
    }
    if (noent != 0) xmlSubstituteEntitiesDefault(1);
    for (i = 1; i < argc ; i++) {
	if (argv[i][0] != '-') {
	    parseAndPrintFile(argv[i]);
	    files ++;
	}
    }
    xmlCleanupParser();
    xmlMemoryDump();

    return(0);
}