parserinternals.c.svn-base

这是一个用于解析xml文件的类库。使用这个类库

	return(-1);
    }
    else
        xmlSAXVersion(ctxt->sax, 2);

    ctxt->maxatts = 0;
    ctxt->atts = NULL;
    /* Allocate the Input stack */
    ctxt->inputTab = (xmlParserInputPtr *)
	        xmlMalloc(5 * sizeof(xmlParserInputPtr));
    if (ctxt->inputTab == NULL) {
        xmlErrMemory(NULL, "cannot initialize parser context\n");
	ctxt->inputNr = 0;
	ctxt->inputMax = 0;
	ctxt->input = NULL;
	return(-1);
    }
    ctxt->inputNr = 0;
    ctxt->inputMax = 5;
    ctxt->input = NULL;

    ctxt->version = NULL;
    ctxt->encoding = NULL;
    ctxt->standalone = -1;
    ctxt->hasExternalSubset = 0;
    ctxt->hasPErefs = 0;
    ctxt->html = 0;
    ctxt->external = 0;
    ctxt->instate = XML_PARSER_START;
    ctxt->token = 0;
    ctxt->directory = NULL;

    /* Allocate the Node stack */
    ctxt->nodeTab = (xmlNodePtr *) xmlMalloc(10 * sizeof(xmlNodePtr));
    if (ctxt->nodeTab == NULL) {
        xmlErrMemory(NULL, "cannot initialize parser context\n");
	ctxt->nodeNr = 0;
	ctxt->nodeMax = 0;
	ctxt->node = NULL;
	ctxt->inputNr = 0;
	ctxt->inputMax = 0;
	ctxt->input = NULL;
	return(-1);
    }
    ctxt->nodeNr = 0;
    ctxt->nodeMax = 10;
    ctxt->node = NULL;

    /* Allocate the Name stack */
    ctxt->nameTab = (const xmlChar **) xmlMalloc(10 * sizeof(xmlChar *));
    if (ctxt->nameTab == NULL) {
        xmlErrMemory(NULL, "cannot initialize parser context\n");
	ctxt->nodeNr = 0;
	ctxt->nodeMax = 0;
	ctxt->node = NULL;
	ctxt->inputNr = 0;
	ctxt->inputMax = 0;
	ctxt->input = NULL;
	ctxt->nameNr = 0;
	ctxt->nameMax = 0;
	ctxt->name = NULL;
	return(-1);
    }
    ctxt->nameNr = 0;
    ctxt->nameMax = 10;
    ctxt->name = NULL;

    /* Allocate the space stack */
    ctxt->spaceTab = (int *) xmlMalloc(10 * sizeof(int));
    if (ctxt->spaceTab == NULL) {
        xmlErrMemory(NULL, "cannot initialize parser context\n");
	ctxt->nodeNr = 0;
	ctxt->nodeMax = 0;
	ctxt->node = NULL;
	ctxt->inputNr = 0;
	ctxt->inputMax = 0;
	ctxt->input = NULL;
	ctxt->nameNr = 0;
	ctxt->nameMax = 0;
	ctxt->name = NULL;
	ctxt->spaceNr = 0;
	ctxt->spaceMax = 0;
	ctxt->space = NULL;
	return(-1);
    }
    ctxt->spaceNr = 1;
    ctxt->spaceMax = 10;
    ctxt->spaceTab[0] = -1;
    ctxt->space = &ctxt->spaceTab[0];
    ctxt->userData = ctxt;
    ctxt->myDoc = NULL;
    ctxt->wellFormed = 1;
    ctxt->nsWellFormed = 1;
    ctxt->valid = 1;
    ctxt->loadsubset = xmlLoadExtDtdDefaultValue;
    ctxt->validate = xmlDoValidityCheckingDefaultValue;
    ctxt->pedantic = xmlPedanticParserDefaultValue;
    ctxt->linenumbers = xmlLineNumbersDefaultValue;
    ctxt->keepBlanks = xmlKeepBlanksDefaultValue;
    if (ctxt->keepBlanks == 0)
	ctxt->sax->ignorableWhitespace = xmlSAX2IgnorableWhitespace;

    ctxt->vctxt.userData = ctxt;
    ctxt->vctxt.error = xmlParserValidityError;
    ctxt->vctxt.warning = xmlParserValidityWarning;
    if (ctxt->validate) {
	if (xmlGetWarningsDefaultValue == 0)
	    ctxt->vctxt.warning = NULL;
	else
	    ctxt->vctxt.warning = xmlParserValidityWarning;
	ctxt->vctxt.nodeMax = 0;
    }
    ctxt->replaceEntities = xmlSubstituteEntitiesDefaultValue;
    ctxt->record_info = 0;
    ctxt->nbChars = 0;
    ctxt->checkIndex = 0;
    ctxt->inSubset = 0;
    ctxt->errNo = XML_ERR_OK;
    ctxt->depth = 0;
    ctxt->charset = XML_CHAR_ENCODING_UTF8;
    ctxt->catalogs = NULL;
    xmlInitNodeInfoSeq(&ctxt->node_seq);
    return(0);
}

/**
 * xmlFreeParserCtxt:
 * @ctxt:  an XML parser context
 *
 * Free all the memory used by a parser context. However the parsed
 * document in ctxt->myDoc is not freed.
 */

void
xmlFreeParserCtxt(xmlParserCtxtPtr ctxt)
{
    xmlParserInputPtr input;

    if (ctxt == NULL) return;

    while ((input = inputPop(ctxt)) != NULL) { /* Non consuming */
        xmlFreeInputStream(input);
    }
    if (ctxt->spaceTab != NULL) xmlFree(ctxt->spaceTab);
    if (ctxt->nameTab != NULL) xmlFree((xmlChar * *)ctxt->nameTab);
    if (ctxt->nodeTab != NULL) xmlFree(ctxt->nodeTab);
    if (ctxt->inputTab != NULL) xmlFree(ctxt->inputTab);
    if (ctxt->version != NULL) xmlFree((char *) ctxt->version);
    if (ctxt->encoding != NULL) xmlFree((char *) ctxt->encoding);
    if (ctxt->extSubURI != NULL) xmlFree((char *) ctxt->extSubURI);
    if (ctxt->extSubSystem != NULL) xmlFree((char *) ctxt->extSubSystem);
#ifdef LIBXML_SAX1_ENABLED
    if ((ctxt->sax != NULL) &&
        (ctxt->sax != (xmlSAXHandlerPtr) &xmlDefaultSAXHandler))
#else
    if (ctxt->sax != NULL)
#endif /* LIBXML_SAX1_ENABLED */
        xmlFree(ctxt->sax);
    if (ctxt->directory != NULL) xmlFree((char *) ctxt->directory);
    if (ctxt->vctxt.nodeTab != NULL) xmlFree(ctxt->vctxt.nodeTab);
    if (ctxt->atts != NULL) xmlFree((xmlChar * *)ctxt->atts);
    if (ctxt->dict != NULL) xmlDictFree(ctxt->dict);
    if (ctxt->nsTab != NULL) xmlFree((char *) ctxt->nsTab);
    if (ctxt->pushTab != NULL) xmlFree(ctxt->pushTab);
    if (ctxt->attallocs != NULL) xmlFree(ctxt->attallocs);
    if (ctxt->attsDefault != NULL) 
        xmlHashFree(ctxt->attsDefault, (xmlHashDeallocator) xmlFree);
    if (ctxt->attsSpecial != NULL)
        xmlHashFree(ctxt->attsSpecial, NULL);
    if (ctxt->freeElems != NULL) {
        xmlNodePtr cur, next;

	cur = ctxt->freeElems;
	while (cur != NULL) {
	    next = cur->next;
	    xmlFree(cur);
	    cur = next;
	}
    }
    if (ctxt->freeAttrs != NULL) {
        xmlAttrPtr cur, next;

	cur = ctxt->freeAttrs;
	while (cur != NULL) {
	    next = cur->next;
	    xmlFree(cur);
	    cur = next;
	}
    }
    /*
     * cleanup the error strings
     */
    if (ctxt->lastError.message != NULL)
        xmlFree(ctxt->lastError.message);
    if (ctxt->lastError.file != NULL)
        xmlFree(ctxt->lastError.file);
    if (ctxt->lastError.str1 != NULL)
        xmlFree(ctxt->lastError.str1);
    if (ctxt->lastError.str2 != NULL)
        xmlFree(ctxt->lastError.str2);
    if (ctxt->lastError.str3 != NULL)
        xmlFree(ctxt->lastError.str3);

#if 0 // def  LIBXML_CATALOG_ENABLED
    if (ctxt->catalogs != NULL)
	xmlCatalogFreeLocal(ctxt->catalogs);
#endif
    xmlFree(ctxt);
}

/**
 * xmlNewParserCtxt:
 *
 * Allocate and initialize a new parser context.
 *
 * Returns the xmlParserCtxtPtr or NULL
 */

xmlParserCtxtPtr
xmlNewParserCtxt()
{
    xmlParserCtxtPtr ctxt;

    ctxt = (xmlParserCtxtPtr) xmlMalloc(sizeof(xmlParserCtxt));
    if (ctxt == NULL) {
	xmlErrMemory(NULL, "cannot allocate parser context\n");
	return(NULL);
    }
    memset(ctxt, 0, sizeof(xmlParserCtxt));
    if (xmlInitParserCtxt(ctxt) < 0) {
        xmlFreeParserCtxt(ctxt);
	return(NULL);
    }
    return(ctxt);
}

/************************************************************************
 *									*
 *		Handling of node informations				*
 *									*
 ************************************************************************/

/**
 * xmlClearParserCtxt:
 * @ctxt:  an XML parser context
 *
 * Clear (release owned resources) and reinitialize a parser context
 */

void
xmlClearParserCtxt(xmlParserCtxtPtr ctxt)
{
  if (ctxt==NULL)
    return;
  xmlClearNodeInfoSeq(&ctxt->node_seq);
  xmlInitParserCtxt(ctxt);
}

/**
 * xmlParserFindNodeInfo:
 * @ctx:  an XML parser context
 * @node:  an XML node within the tree
 *
 * Find the parser node info struct for a given node
 * 
 * Returns an xmlParserNodeInfo block pointer or NULL
 */
const xmlParserNodeInfo* xmlParserFindNodeInfo(const xmlParserCtxtPtr ctx,
                                               const xmlNodePtr node)
{
  unsigned long pos;

  /* Find position where node should be at */
  pos = xmlParserFindNodeInfoIndex(&ctx->node_seq, node);
  if (pos < ctx->node_seq.length && ctx->node_seq.buffer[pos].node == node)
    return &ctx->node_seq.buffer[pos];
  else
    return NULL;
}


/**
 * xmlInitNodeInfoSeq:
 * @seq:  a node info sequence pointer
 *
 * -- Initialize (set to initial state) node info sequence
 */
void
xmlInitNodeInfoSeq(xmlParserNodeInfoSeqPtr seq)
{
  seq->length = 0;
  seq->maximum = 0;
  seq->buffer = NULL;
}

/**
 * xmlClearNodeInfoSeq:
 * @seq:  a node info sequence pointer
 *
 * -- Clear (release memory and reinitialize) node
 *   info sequence
 */
void
xmlClearNodeInfoSeq(xmlParserNodeInfoSeqPtr seq)
{
  if ( seq->buffer != NULL )
    xmlFree(seq->buffer);
  xmlInitNodeInfoSeq(seq);
}


/**
 * xmlParserFindNodeInfoIndex:
 * @seq:  a node info sequence pointer
 * @node:  an XML node pointer
 *
 * 
 * xmlParserFindNodeInfoIndex : Find the index that the info record for
 *   the given node is or should be at in a sorted sequence
 *
 * Returns a long indicating the position of the record
 */
unsigned long xmlParserFindNodeInfoIndex(const xmlParserNodeInfoSeqPtr seq,
                                         const xmlNodePtr node)
{
  unsigned long upper, lower, middle;
  int found = 0;

  /* Do a binary search for the key */
  lower = 1;
  upper = seq->length;
  middle = 0;
  while ( lower <= upper && !found) {
    middle = lower + (upper - lower) / 2;
    if ( node == seq->buffer[middle - 1].node )
      found = 1;
    else if ( node < seq->buffer[middle - 1].node )
      upper = middle - 1;
    else
      lower = middle + 1;
  }

  /* Return position */
  if ( middle == 0 || seq->buffer[middle - 1].node < node )
    return middle;
  else 
    return middle - 1;
}


/**
 * xmlParserAddNodeInfo:
 * @ctxt:  an XML parser context
 * @info:  a node info sequence pointer
 *
 * Insert node info record into the sorted sequence
 */
void
xmlParserAddNodeInfo(xmlParserCtxtPtr ctxt,
                     const xmlParserNodeInfoPtr info)
{
    unsigned long pos;

    /* Find pos and check to see if node is already in the sequence */
    pos = xmlParserFindNodeInfoIndex(&ctxt->node_seq, (xmlNodePtr)
                                     info->node);
    if (pos < ctxt->node_seq.length
        && ctxt->node_seq.buffer[pos].node == info->node) {
        ctxt->node_seq.buffer[pos] = *info;
    }

    /* Otherwise, we need to add new node to buffer */
    else {
        if (ctxt->node_seq.length + 1 > ctxt->node_seq.maximum) {
            xmlParserNodeInfo *tmp_buffer;
            unsigned int byte_size;

            if (ctxt->node_seq.maximum == 0)
                ctxt->node_seq.maximum = 2;
            byte_size = (sizeof(*ctxt->node_seq.buffer) *
			(2 * ctxt->node_seq.maximum));

            if (ctxt->node_seq.buffer == NULL)
                tmp_buffer = (xmlParserNodeInfo *) xmlMalloc(byte_size);
            else
                tmp_buffer =
                    (xmlParserNodeInfo *) xmlRealloc(ctxt->node_seq.buffer,
                                                     byte_size);

            if (tmp_buffer == NULL) {
		xmlErrMemory(ctxt, "failed to allocate buffer\n");
                return;
            }
            ctxt->node_seq.buffer = tmp_buffer;
            ctxt->node_seq.maximum *= 2;
        }

        /* If position is not at end, move elements out of the way */
        if (pos != ctxt->node_seq.length) {
            unsigned long i;

            for (i = ctxt->node_seq.length; i > pos; i--)
                ctxt->node_seq.buffer[i] = ctxt->node_seq.buffer[i - 1];
        }

        /* Copy element and increase length */
        ctxt->node_seq.buffer[pos] = *info;
        ctxt->node_seq.length++;
    }
}

/************************************************************************
 *									*
 *		Defaults settings					*
 *									*
 ************************************************************************/
/**
 * xmlPedanticParserDefault:
 * @val:  int 0 or 1 
 *
 * Set and return the previous value for enabling pedantic warnings.
 *
 * Returns the last value for 0 for no substitution, 1 for substitution.
 */

int
xmlPedanticParserDefault(int val) {
    int old = xmlPedanticParserDefaultValue;

    xmlPedanticParserDefaultValue = val;
    return(old);
}

/**
 * xmlLineNumbersDefault:
 * @val:  int 0 or 1 
 *
 * Set and return the previous value for enabling line numbers in elements
 * contents. This may break on old application and is turned off by default.
 *
 * Returns the last value for 0 for no substitution, 1 for substitution.
 */

int
xmlLineNumbersDefault(int val) {
    int old = xmlLineNumbersDefaultValue;

    xmlLineNumbersDefaultValue = val;
    return(old);
}

/**
 * xmlSubstituteEntitiesDefault:
 * @val:  int 0 or 1 
 *
 * Set and return the previous value for default entity support.
 * Initially the parser always keep entity references instead of substituting
 * entity values in the output. This function has to be used to change the
 * default parser behavior
 * SAX::substituteEntities() has to be used for changing that on a file by
 * file basis.
 *
 * Returns the last value for 0 for no substitution, 1 for substitution.
 */

int
xmlSubstituteEntitiesDefault(int val) {
    int old = xmlSubstituteEntitiesDefaultValue;

    xmlSubstituteEntitiesDefaultValue = val;
    return(old);
}

/**
 * xmlKeepBlanksDefault:
 * @val:  int 0 or 1 
 *
 * Set and return the previous value for default blanks text nodes support.
 * The 1.x version of the parser used an heuristic to try to detect
 * ignorable white spaces. As a result the SAX callback was generating
 * xmlSAX2IgnorableWhitespace() callbacks instead of characters() one, and when
 * using the DOM output text nodes containing those blanks were not generated.
 * The 2.x and later version will switch to the XML standard way and
 * ignorableWhitespace() are only generated when running the parser in
 * validating mode and when the current element doesn't allow CDATA or
 * mixed content.
 * This function is provided as a way to force the standard behavior 
 * on 1.X libs and to switch back to the old mode for compatibility when
 * running 1.X client code on 2.X . Upgrade of 1.X code should be done
 * by using xmlIsBlankNode() commodity function to detect the "empty"
 * nodes generated.
 * This value also affect autogeneration of indentation when saving code
 * if blanks sections are kept, indentation is not generated.
 *
 * Returns the last value for 0 for no substitution, 1 for substitution.
 */

int
xmlKeepBlanksDefault(int val) {
    int old = xmlKeepBlanksDefaultValue;

    xmlKeepBlanksDefaultValue = val;
    xmlIndentTreeOutput = !val;
    return(old);
}