src/esi/Libxml2Parser.cc

   1 /*
   2  * $Id$
   3  *
   4  * AUTHOR: Joachim Bauch (mail@joachim-bauch.de)
   5  *
   6  * SQUID Web Proxy Cache          http://www.squid-cache.org/
   7  * ----------------------------------------------------------
   8  *
   9  *  Squid is the result of efforts by numerous individuals from
  10  *  the Internet community; see the CONTRIBUTORS file for full
  11  *  details.   Many organizations have provided support for Squid's
  12  *  development; see the SPONSORS file for full details.  Squid is
  13  *  Copyrighted (C) 2001 by the Regents of the University of
  14  *  California; see the COPYRIGHT file for full details.  Squid
  15  *  incorporates software developed and/or copyrighted by other
  16  *  sources; see the CREDITS file for full details.
  17  *
  18  *  This program is free software; you can redistribute it and/or modify
  19  *  it under the terms of the GNU General Public License as published by
  20  *  the Free Software Foundation; either version 2 of the License, or
  21  *  (at your option) any later version.
  22  *
  23  *  This program is distributed in the hope that it will be useful,
  24  ;  but WITHOUT ANY WARRANTY; without even the implied warranty of
  25  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  26  *  GNU General Public License for more details.
  27  *
  28  *  You should have received a copy of the GNU General Public License
  29  *  along with this program; if not, write to the Free Software
  30  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
  31  *
  32  */
  33
  34 /*
  35  * The ESI Libxml2 parser is Copyright (c) 2004 by Joachim Bauch
  36  * http://www.joachim-bauch.de
  37  * mail@joachim-bauch.de
  38  */
  39
  40 #include "squid.h"
  41
  42 #if USE_SQUID_ESI && HAVE_LIBXML2
  43
  44 #include "esi/Libxml2Parser.h"
  45
  46 // the global document that will store the resolved entity
  47 // definitions
  48 static htmlDocPtr entity_doc = NULL;
  49
  50 EsiParserDefinition(ESILibxml2Parser);
  51
  52 // the SAX callback functions
  53 void esi_startElementSAXFunc(void * ctx, const xmlChar * name, const xmlChar ** atts)
  54 {
  55     int count=0;
  56     xmlChar **tmp = (xmlChar **)atts;
  57
  58     while (tmp && *tmp != NULL) {
  59         ++count;
  60         ++tmp;
  61     }
  62
  63     // we increased on every key and value
  64     count /= 2;
  65
  66     ESILibxml2Parser *p = (ESILibxml2Parser *)ctx;
  67
  68     p->getClient()->start((const char *)name, (const char **)atts, count);
  69 }
  70
  71 void esi_endElementSAXFunc(void * ctx, const xmlChar * name)
  72 {
  73     ESILibxml2Parser *p = (ESILibxml2Parser *)ctx;
  74     p->getClient()->end((const char *)name);
  75 }
  76
  77 void esi_commentSAXFunc(void * ctx, const xmlChar * value)
  78 {
  79     ESILibxml2Parser *p = (ESILibxml2Parser *)ctx;
  80     p->getClient()->parserComment((const char *)value);
  81 }
  82
  83 void esi_charactersSAXFunc(void *ctx, const xmlChar *ch, int len)
  84 {
  85     ESILibxml2Parser *p = (ESILibxml2Parser *)ctx;
  86     p->getClient()->parserDefault((const char *)ch, len);
  87 }
  88
  89 xmlEntityPtr esi_getEntitySAXFunc(void * ctx,  const xmlChar * name)
  90 {
  91     xmlEntityPtr res = xmlGetDocEntity(entity_doc, name);
  92
  93     if (res == NULL) {
  94         const htmlEntityDesc *ent = htmlEntityLookup(name);
  95
  96         if (ent != NULL) {
  97             char tmp[32];
  98             snprintf(tmp, 32, "&#%d;", ent->value);
  99             res = xmlAddDocEntity(entity_doc, (const xmlChar *)name, XML_INTERNAL_GENERAL_ENTITY, NULL, NULL, (const xmlChar *)tmp);
 100         }
 101     }
 102
 103     return res;
 104 }
 105
 106 ESILibxml2Parser::ESILibxml2Parser(ESIParserClient *aClient) : theClient (aClient)
 107 {
 108     xmlSAXHandler sax;
 109     htmlDefaultSAXHandlerInit();
 110     memset(&sax, 0, sizeof(sax));
 111     sax.startElement = esi_startElementSAXFunc;
 112     sax.endElement = esi_endElementSAXFunc;
 113     sax.comment = esi_commentSAXFunc;
 114     sax.characters = esi_charactersSAXFunc;
 115     sax.getEntity = esi_getEntitySAXFunc;
 116
 117     /* TODO: grab the document encoding from the headers */
 118     parser = xmlCreatePushParserCtxt(&sax, static_cast<void *>(this), NULL, 0, NULL);
 119     xmlSetFeature(parser, "substitute entities", 0);
 120
 121     if (entity_doc == NULL)
 122         entity_doc = htmlNewDoc(NULL, NULL);
 123 }
 124
 125 ESILibxml2Parser::~ESILibxml2Parser()
 126 {
 127     xmlFreeParserCtxt(parser);
 128     parser = NULL;
 129 }
 130
 131 bool
 132 ESILibxml2Parser::parse(char const *dataToParse, size_t const lengthOfData, bool const endOfStream)
 133 {
 134     return (xmlParseChunk(parser, dataToParse, lengthOfData, endOfStream) == 0);
 135 }
 136
 137 long int
 138 ESILibxml2Parser::lineNumber() const
 139 {
 140     return (long int)xmlSAX2GetLineNumber(parser);
 141 }
 142
 143 char const *
 144 ESILibxml2Parser::errorString() const
 145 {
 146     xmlErrorPtr error = xmlGetLastError();
 147
 148     if (error == NULL)
 149         return NULL;
 150
 151     return error->message;
 152 }
 153
 154 #endif /* USE_SQUID_ESI */