c14n.c

xml开源解析代码.版本为libxml2-2.6.29,可支持GB3212.网络消息发送XML时很有用.

    xmlFree(ctx);
}

/**
 * xmlC14NNewCtx:
 * @doc: 		the XML document for canonization
 * @is_visible_callback:the function to use to determine is node visible 
 *			or not
 * @user_data: 		the first parameter for @is_visible_callback function
 *			(in most cases, it is nodes set)
 * @inclusive_ns_prefixe the list of inclusive namespace prefixes 
 *			ended with a NULL or NULL if there is no
 *			inclusive namespaces (only for exclusive 
 *			canonicalization)
 * @with_comments: 	include comments in the result (!=0) or not (==0)
 * @buf: 		the output buffer to store canonical XML; this 
 *			buffer MUST have encoder==NULL because C14N requires
 *			UTF-8 output
 *  		
 * Creates new C14N context object to store C14N parameters.
 *
 * Returns pointer to newly created object (success) or NULL (fail)
 */
static xmlC14NCtxPtr
xmlC14NNewCtx(xmlDocPtr doc,  
	      xmlC14NIsVisibleCallback is_visible_callback, void* user_data,
              int exclusive, xmlChar ** inclusive_ns_prefixes,
              int with_comments, xmlOutputBufferPtr buf)
{
    xmlC14NCtxPtr ctx = NULL;

    if ((doc == NULL) || (buf == NULL)) {
        xmlC14NErrParam("creating new context");
        return (NULL);
    }

    /*
     *  Validate the encoding output buffer encoding
     */
    if (buf->encoder != NULL) {
        xmlC14NErr(ctx, (xmlNodePtr) doc, XML_C14N_REQUIRES_UTF8,
"xmlC14NNewCtx: output buffer encoder != NULL but C14N requires UTF8 output\n");
        return (NULL);
    }

    /*
     *  Validate the XML document encoding value, if provided.
     */
    if (doc->charset != XML_CHAR_ENCODING_UTF8) {
        xmlC14NErr(ctx, (xmlNodePtr) doc, XML_C14N_REQUIRES_UTF8,
		   "xmlC14NNewCtx: source document not in UTF8\n");
        return (NULL);
    }

    /*
     * Allocate a new xmlC14NCtxPtr and fill the fields.
     */
    ctx = (xmlC14NCtxPtr) xmlMalloc(sizeof(xmlC14NCtx));
    if (ctx == NULL) {
	xmlC14NErrMemory("creating context");
        return (NULL);
    }
    memset(ctx, 0, sizeof(xmlC14NCtx));

    /*
     * initialize C14N context
     */
    ctx->doc = doc;
    ctx->with_comments = with_comments;
    ctx->is_visible_callback = is_visible_callback;
    ctx->user_data = user_data;
    ctx->buf = buf;
    ctx->parent_is_doc = 1;
    ctx->pos = XMLC14N_BEFORE_DOCUMENT_ELEMENT;
    ctx->ns_rendered = xmlC14NVisibleNsStackCreate();

    if(ctx->ns_rendered == NULL) {
        xmlC14NErr(ctx, (xmlNodePtr) doc, XML_C14N_CREATE_STACK,
		   "xmlC14NNewCtx: xmlC14NVisibleNsStackCreate failed\n");
	xmlC14NFreeCtx(ctx);
        return (NULL);
    }

    /*
     * Set "exclusive" flag, create a nodes set for namespaces
     * stack and remember list of incluseve prefixes
     */
    if (exclusive) {
        ctx->exclusive = 1;
        ctx->inclusive_ns_prefixes = inclusive_ns_prefixes;
    }
    return (ctx);
}

/**
 * xmlC14NExecute:
 * @doc: 		the XML document for canonization
 * @is_visible_callback:the function to use to determine is node visible 
 *			or not
 * @user_data: 		the first parameter for @is_visible_callback function
 *			(in most cases, it is nodes set)
 * @exclusive:		the exclusive flag (0 - non-exclusive canonicalization;
 *			otherwise - exclusive canonicalization)
 * @inclusive_ns_prefixes: the list of inclusive namespace prefixes 
 *			ended with a NULL or NULL if there is no
 *			inclusive namespaces (only for exclusive 
 *			canonicalization, ignored otherwise)
 * @with_comments: 	include comments in the result (!=0) or not (==0)
 * @buf: 		the output buffer to store canonical XML; this 
 *			buffer MUST have encoder==NULL because C14N requires
 *			UTF-8 output
 *  		
 * Dumps the canonized image of given XML document into the provided buffer.
 * For details see "Canonical XML" (http://www.w3.org/TR/xml-c14n) or
 * "Exclusive XML Canonicalization" (http://www.w3.org/TR/xml-exc-c14n)
 *
 * Returns non-negative value on success or a negative value on fail  
 */
int 		
xmlC14NExecute(xmlDocPtr doc, xmlC14NIsVisibleCallback is_visible_callback,
	 void* user_data, int exclusive, xmlChar **inclusive_ns_prefixes,
	 int with_comments, xmlOutputBufferPtr buf) {

    xmlC14NCtxPtr ctx;
    int ret;

    if ((buf == NULL) || (doc == NULL)) {
        xmlC14NErrParam("executing c14n");
        return (-1);
    }

    /*
     *  Validate the encoding output buffer encoding
     */
    if (buf->encoder != NULL) {
        xmlC14NErr(NULL, (xmlNodePtr) doc, XML_C14N_REQUIRES_UTF8,
"xmlC14NExecute: output buffer encoder != NULL but C14N requires UTF8 output\n");
        return (-1);
    }

    ctx = xmlC14NNewCtx(doc, is_visible_callback, user_data, 
			exclusive, inclusive_ns_prefixes,
                        with_comments, buf);
    if (ctx == NULL) {
        xmlC14NErr(NULL, (xmlNodePtr) doc, XML_C14N_CREATE_CTXT,
		   "xmlC14NExecute: unable to create C14N context\n");
        return (-1);
    }



    /*  
     * Root Node
     * The root node is the parent of the top-level document element. The 
     * result of processing each of its child nodes that is in the node-set 
     * in document order. The root node does not generate a byte order mark, 
     * XML declaration, nor anything from within the document type 
     * declaration.
     */
    if (doc->children != NULL) {
        ret = xmlC14NProcessNodeList(ctx, doc->children);
        if (ret < 0) {
            xmlC14NErrInternal("processing docs children list");
            xmlC14NFreeCtx(ctx);
            return (-1);
        }
    }

    /*
     * Flush buffer to get number of bytes written
     */
    ret = xmlOutputBufferFlush(buf);
    if (ret < 0) {
        xmlC14NErrInternal("flushing output buffer");
        xmlC14NFreeCtx(ctx);
        return (-1);
    }

    /* 
     * Cleanup
     */
    xmlC14NFreeCtx(ctx);
    return (ret);
}

/**
 * xmlC14NDocSaveTo:
 * @doc: 		the XML document for canonization
 * @nodes: 		the nodes set to be included in the canonized image
 *      		or NULL if all document nodes should be included
 * @exclusive:		the exclusive flag (0 - non-exclusive canonicalization;
 *			otherwise - exclusive canonicalization)
 * @inclusive_ns_prefixes: the list of inclusive namespace prefixes 
 *			ended with a NULL or NULL if there is no
 *			inclusive namespaces (only for exclusive 
 *			canonicalization, ignored otherwise)
 * @with_comments: 	include comments in the result (!=0) or not (==0)
 * @buf: 		the output buffer to store canonical XML; this 
 *			buffer MUST have encoder==NULL because C14N requires
 *			UTF-8 output
 *  		
 * Dumps the canonized image of given XML document into the provided buffer.
 * For details see "Canonical XML" (http://www.w3.org/TR/xml-c14n) or
 * "Exclusive XML Canonicalization" (http://www.w3.org/TR/xml-exc-c14n)
 *
 * Returns non-negative value on success or a negative value on fail  
 */
int
xmlC14NDocSaveTo(xmlDocPtr doc, xmlNodeSetPtr nodes,
                 int exclusive, xmlChar ** inclusive_ns_prefixes,
                 int with_comments, xmlOutputBufferPtr buf) {
    return(xmlC14NExecute(doc, 
			(xmlC14NIsVisibleCallback)xmlC14NIsNodeInNodeset,
			nodes,
			exclusive,
			inclusive_ns_prefixes,
			with_comments,
			buf));
}


/**
 * xmlC14NDocDumpMemory:
 * @doc: 		the XML document for canonization
 * @nodes: 		the nodes set to be included in the canonized image
 *      		or NULL if all document nodes should be included
 * @exclusive:		the exclusive flag (0 - non-exclusive canonicalization;
 *			otherwise - exclusive canonicalization)
 * @inclusive_ns_prefixes: the list of inclusive namespace prefixes 
 *			ended with a NULL or NULL if there is no
 *			inclusive namespaces (only for exclusive 
 *			canonicalization, ignored otherwise)
 * @with_comments: 	include comments in the result (!=0) or not (==0)
 * @doc_txt_ptr: 	the memory pointer for allocated canonical XML text;
 *			the caller of this functions is responsible for calling
 *			xmlFree() to free allocated memory 
 *  		
 * Dumps the canonized image of given XML document into memory.
 * For details see "Canonical XML" (http://www.w3.org/TR/xml-c14n) or
 * "Exclusive XML Canonicalization" (http://www.w3.org/TR/xml-exc-c14n)
 *
 * Returns the number of bytes written on success or a negative value on fail  
 */
int
xmlC14NDocDumpMemory(xmlDocPtr doc, xmlNodeSetPtr nodes,
                     int exclusive, xmlChar ** inclusive_ns_prefixes,
                     int with_comments, xmlChar ** doc_txt_ptr)
{
    int ret;
    xmlOutputBufferPtr buf;

    if (doc_txt_ptr == NULL) {
        xmlC14NErrParam("dumping doc to memory");
        return (-1);
    }

    *doc_txt_ptr = NULL;

    /*
     * create memory buffer with UTF8 (default) encoding 
     */
    buf = xmlAllocOutputBuffer(NULL);
    if (buf == NULL) {
        xmlC14NErrMemory("creating output buffer");
        return (-1);
    }

    /*
     * canonize document and write to buffer
     */
    ret = xmlC14NDocSaveTo(doc, nodes, exclusive, inclusive_ns_prefixes,
                           with_comments, buf);
    if (ret < 0) {
        xmlC14NErrInternal("saving doc to output buffer");
        (void) xmlOutputBufferClose(buf);
        return (-1);
    }

    ret = buf->buffer->use;
    if (ret > 0) {
        *doc_txt_ptr = xmlStrndup(buf->buffer->content, ret);
    }
    (void) xmlOutputBufferClose(buf);

    if ((*doc_txt_ptr == NULL) && (ret > 0)) {
        xmlC14NErrMemory("coping canonicanized document");
        return (-1);
    }
    return (ret);
}

/**
 * xmlC14NDocSave:
 * @doc: 		the XML document for canonization
 * @nodes: 		the nodes set to be included in the canonized image
 *      		or NULL if all document nodes should be included
 * @exclusive:		the exclusive flag (0 - non-exclusive canonicalization;
 *			otherwise - exclusive canonicalization)
 * @inclusive_ns_prefixes: the list of inclusive namespace prefixes 
 *			ended with a NULL or NULL if there is no
 *			inclusive namespaces (only for exclusive 
 *			canonicalization, ignored otherwise)
 * @with_comments: 	include comments in the result (!=0) or not (==0)
 * @filename: 		the filename to store canonical XML image
 * @compression:	the compression level (zlib requred): 
 *				-1 - libxml default,
 *				 0 - uncompressed, 
 *				>0 - compression level
 *  		
 * Dumps the canonized image of given XML document into the file.
 * For details see "Canonical XML" (http://www.w3.org/TR/xml-c14n) or
 * "Exclusive XML Canonicalization" (http://www.w3.org/TR/xml-exc-c14n)
 *
 * Returns the number of bytes written success or a negative value on fail  
 */
int
xmlC14NDocSave(xmlDocPtr doc, xmlNodeSetPtr nodes,
               int exclusive, xmlChar ** inclusive_ns_prefixes,
               int with_comments, const char *filename, int compression)
{
    xmlOutputBufferPtr buf;
    int ret;

    if (filename == NULL) {
        xmlC14NErrParam("saving doc");
        return (-1);
    }
#ifdef HAVE_ZLIB_H
    if (compression < 0)
        compression = xmlGetCompressMode();
#endif

    /* 
     * save the content to a temp buffer, use default UTF8 encoding.
     */
    buf = xmlOutputBufferCreateFilename(filename, NULL, compression);
    if (buf == NULL) {
        xmlC14NErrInternal("creating temporary filename");
        return (-1);
    }

    /*
     * canonize document and write to buffer
     */
    ret = xmlC14NDocSaveTo(doc, nodes, exclusive, inclusive_ns_prefixes,
                           with_comments, buf);
    if (ret < 0) {
        xmlC14NErrInternal("cannicanize document to buffer");
        (void) xmlOutputBufferClose(buf);
        return (-1);
    }

    /* 
     * get the numbers of bytes written 
     */
    ret = xmlOutputBufferClose(buf);
    return (ret);
}



/*
 * Macro used to grow the current buffer.
 */
#define growBufferReentrant() {						\
    buffer_size *= 2;							\
    buffer = (xmlChar *)						\
    		xmlRealloc(buffer, buffer_size * sizeof(xmlChar));	\
    if (buffer == NULL) {						\
	xmlC14NErrMemory("growing buffer");				\
	return(NULL);							\
    }									\
}

/** 
 * xmlC11NNormalizeString:
 * @input:		the input string
 * @mode:		the normalization mode (attribute, comment, PI or text)
 *
 * Converts a string to a canonical (normalized) format. The code is stolen
 * from xmlEncodeEntitiesReentrant(). Added normalization of \x09, \x0a, \x0A
 * and the @mode parameter
 *
 * Returns a normalized string (caller is responsible for calling xmlFree())
 * or NULL if an error occurs
 */
static xmlChar *
xmlC11NNormalizeString(const xmlChar * input,
                       xmlC14NNormalizationMode mode)
{
    const xmlChar *cur = input;
    xmlChar *buffer = NULL;
    xmlChar *out = NULL;
    int buffer_size = 0;

    if (input == NULL)
        return (NULL);

    /*
     * allocate an translation buffer.
     */
    buffer_size = 1000;
    buffer = (xmlChar *) xmlMallocAtomic(buffer_size * sizeof(xmlChar));
    if (buffer == NULL) {
	xmlC14NErrMemory("allocating buffer");
        return (NULL);
    }
    out = buffer;

    while (*cur != '\0') {
        if ((out - buffer) > (buffer_size - 10)) {
            int indx = out - buffer;

            growBufferReentrant();
            out = &buffer[indx];
        }

        if ((*cur == '<') && ((mode == XMLC14N_NORMALIZE_ATTR) ||
                              (mode == XMLC14N_NORMALIZE_TEXT))) {
            *out++ = '&';
            *out++ = 'l';
            *out++ = 't';
            *out++ = ';';
        } else if ((*cur == '>') && (mode == XMLC14N_NORMALIZE_TEXT)) {
            *out++ = '&';
            *out++ = 'g';
            *out++ = 't';
            *out++ = ';';
        } else if ((*cur == '&') && ((mode == XMLC14N_NORMALIZE_ATTR) ||
                                     (mode == XMLC14N_NORMALIZE_TEXT))) {
            *out++ = '&';
            *out++ = 'a';
            *out++ = 'm';
            *out++ = 'p';
            *out++ = ';';
        } else if ((*cur == '"') && (mode == XMLC14N_NORMALIZE_ATTR)) {
            *out++ = '&';
            *out++ = 'q';
            *out++ = 'u';
            *out++ = 'o';
            *out++ = 't';
            *out++ = ';';
        } else if ((*cur == '\x09') && (mode == XMLC14N_NORMALIZE_ATTR)) {
            *out++ = '&';
            *out++ = '#';
            *out++ = 'x';
            *out++ = '9';
            *out++ = ';';
        } else if ((*cur == '\x0A') && (mode == XMLC14N_NORMALIZE_ATTR)) {
            *out++ = '&';
            *out++ = '#';
            *out++ = 'x';
            *out++ = 'A';
            *out++ = ';';
        } else if ((*cur == '\x0D') && ((mode == XMLC14N_NORMALIZE_ATTR) ||
                                        (mode == XMLC14N_NORMALIZE_TEXT) ||
                                        (mode == XMLC14N_NORMALIZE_COMMENT) ||
					(mode == XMLC14N_NORMALIZE_PI))) {
            *out++ = '&';
            *out++ = '#';
            *out++ = 'x';
            *out++ = 'D';
            *out++ = ';';
        } else {
            /*
             * Works because on UTF-8, all extended sequences cannot
             * result in bytes in the ASCII range.
             */
            *out++ = *cur;
        }
        cur++;
    }
    *out++ = 0;
    return (buffer);
}
#endif /* LIBXML_OUTPUT_ENABLED */
#define bottom_c14n
#include "elfgcchack.h"
#endif /* LIBXML_C14N_ENABLED */