src/xml.c

   1 /* Interface to libxml2.
   2    Copyright (C) 2010-2011 Free Software Foundation, Inc.
   3
   4 This file is part of GNU Emacs.
   5
   6 GNU Emacs is free software: you can redistribute it and/or modify
   7 it under the terms of the GNU General Public License as published by
   8 the Free Software Foundation, either version 3 of the License, or
   9 (at your option) any later version.
  10
  11 GNU Emacs is distributed in the hope that it will be useful,
  12 but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 GNU General Public License for more details.
  15
  16 You should have received a copy of the GNU General Public License
  17 along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */
  18
  19 #include <config.h>
  20
  21 #ifdef HAVE_LIBXML2
  22
  23 #include <setjmp.h>
  24 #include <libxml/tree.h>
  25 #include <libxml/parser.h>
  26 #include <libxml/HTMLparser.h>
  27
  28 #include "lisp.h"
  29 #include "buffer.h"
  30
  31 Lisp_Object make_dom (xmlNode *node)
  32 {
  33   if (node->type == XML_ELEMENT_NODE)
  34     {
  35       Lisp_Object result = Fcons (intern ((char *) node->name), Qnil);
  36       xmlNode *child;
  37       xmlAttr *property;
  38       Lisp_Object plist = Qnil;
  39
  40       /* First add the attributes. */
  41       property = node->properties;
  42       while (property != NULL)
  43         {
  44           if (property->children &&
  45               property->children->content)
  46             {
  47               char *content = (char *) property->children->content;
  48               plist = Fcons (Fcons (intern ((char *) property->name),
  49                                     build_string (content)),
  50                              plist);
  51             }
  52           property = property->next;
  53         }
  54       result = Fcons (Fnreverse (plist), result);
  55
  56       /* Then add the children of the node. */
  57       child = node->children;
  58       while (child != NULL)
  59         {
  60           result = Fcons (make_dom (child), result);
  61           child = child->next;
  62         }
  63
  64       return Fnreverse (result);
  65     }
  66   else if (node->type == XML_TEXT_NODE || node->type == XML_CDATA_SECTION_NODE)
  67     {
  68       if (node->content)
  69         return build_string ((char *) node->content);
  70       else
  71         return Qnil;
  72     }
  73   else
  74     return Qnil;
  75 }
  76
  77 static Lisp_Object
  78 parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url, int htmlp)
  79 {
  80   xmlDoc *doc;
  81   xmlNode *node;
  82   Lisp_Object result = Qnil;
  83   const char *burl = "";
  84   EMACS_INT bytes;
  85   EMACS_INT istart, iend;
  86
  87   LIBXML_TEST_VERSION;
  88
  89   validate_region (&start, &end);
  90
  91   istart = XINT (start);
  92   iend = XINT (end);
  93
  94   if (istart < GPT && GPT < iend)
  95     move_gap (iend);
  96
  97   if (! NILP (base_url))
  98     {
  99       CHECK_STRING (base_url);
 100       burl = SSDATA (base_url);
 101     }
 102
 103   bytes = CHAR_TO_BYTE (iend) - CHAR_TO_BYTE (istart);
 104
 105   if (htmlp)
 106     doc = htmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)),
 107                           bytes, burl, "utf-8",
 108                           HTML_PARSE_RECOVER|HTML_PARSE_NONET|
 109                           HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR|
 110                           HTML_PARSE_NOBLANKS);
 111   else
 112     doc = xmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)),
 113                          bytes, burl, "utf-8",
 114                          XML_PARSE_NONET|XML_PARSE_NOWARNING|
 115                          XML_PARSE_NOERROR);
 116
 117   if (doc != NULL)
 118     {
 119       node = xmlDocGetRootElement (doc);
 120       if (node != NULL)
 121         result = make_dom (node);
 122       xmlFreeDoc (doc);
 123       xmlCleanupParser ();
 124     }
 125
 126   return result;
 127 }
 128
 129 DEFUN ("libxml-parse-html-region", Flibxml_parse_html_region,
 130        Slibxml_parse_html_region,
 131        2, 3, 0,
 132        doc: /* Parse the region as an HTML document and return the parse tree.
 133 If BASE-URL is non-nil, it is used to expand relative URLs.  */)
 134   (Lisp_Object start, Lisp_Object end, Lisp_Object base_url)
 135 {
 136   return parse_region (start, end, base_url, 1);
 137 }
 138
 139 DEFUN ("libxml-parse-xml-region", Flibxml_parse_xml_region,
 140        Slibxml_parse_xml_region,
 141        2, 3, 0,
 142        doc: /* Parse the region as an XML document and return the parse tree.
 143 If BASE-URL is non-nil, it is used to expand relative URLs.  */)
 144   (Lisp_Object start, Lisp_Object end, Lisp_Object base_url)
 145 {
 146   return parse_region (start, end, base_url, 0);
 147 }
 148
 149 \f
 150 /***********************************************************************
 151                             Initialization
 152  ***********************************************************************/
 153 void
 154 syms_of_xml (void)
 155 {
 156   defsubr (&Slibxml_parse_html_region);
 157   defsubr (&Slibxml_parse_xml_region);
 158 }
 159
 160 #endif /* HAVE_LIBXML2 */