src/xml.c

   1 /* Interface to libxml2.
   2    Copyright (C) 2010 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     Lisp_Object result = Fcons (intern (node->name), Qnil);
  35     xmlNode *child;
  36     xmlAttr *property;
  37
  38     /* First add the attributes. */
  39     property = node->properties;
  40     while (property != NULL) {
  41       if (property->children &&
  42           property->children->content) {
  43         char *pname = xmalloc (strlen (property->name) + 2);
  44         *pname = ':';
  45         strcpy(pname + 1, property->name);
  46         result = Fcons (Fcons (intern (pname),
  47                                build_string(property->children->content)),
  48                         result);
  49         xfree (pname);
  50       }
  51       property = property->next;
  52     }
  53     /* Then add the children of the node. */
  54     child = node->children;
  55     while (child != NULL) {
  56       result = Fcons (make_dom (child), result);
  57       child = child->next;
  58     }
  59     return Fnreverse (result);
  60   } else if (node->type == XML_TEXT_NODE) {
  61     Lisp_Object content = Qnil;
  62
  63     if (node->content)
  64       content = build_string (node->content);
  65
  66     return Fcons (intern (node->name), content);
  67   } else
  68     return Qnil;
  69 }
  70
  71 static Lisp_Object
  72 parse_buffer (Lisp_Object string, Lisp_Object base_url, int htmlp)
  73 {
  74   xmlDoc *doc;
  75   xmlNode *node;
  76   Lisp_Object result;
  77   int ibeg, iend;
  78   char *burl = "";
  79
  80   LIBXML_TEST_VERSION;
  81
  82   CHECK_STRING (string);
  83
  84   if (! NILP (base_url)) {
  85     CHECK_STRING (base_url);
  86     burl = SDATA (base_url);
  87   }
  88
  89   if (htmlp)
  90     doc = htmlReadMemory (SDATA (string), SBYTES (string), burl, "utf-8",
  91                           HTML_PARSE_RECOVER|HTML_PARSE_NONET|
  92                           HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR);
  93   else
  94     doc = xmlReadMemory (SDATA (string), SBYTES (string), burl, "utf-8",
  95                          XML_PARSE_NONET|XML_PARSE_NOWARNING|
  96                          XML_PARSE_NOERROR);
  97
  98   if (doc != NULL) {
  99     node = xmlDocGetRootElement (doc);
 100     if (node != NULL)
 101       result = make_dom (node);
 102
 103     xmlFreeDoc (doc);
 104     xmlCleanupParser ();
 105   }
 106
 107   return result;
 108 }
 109
 110 DEFUN ("html-parse-string", Fhtml_parse_string, Shtml_parse_string,
 111        0, 2, 0,
 112        doc: /* Parse the string as an HTML document and return the parse tree.
 113 If BASE-URL is non-nil, it will be used to expand relative URLs in
 114 the HTML document.*/)
 115      (string, base_url)
 116      Lisp_Object string, base_url;
 117 {
 118   return parse_buffer (string, base_url, 1);
 119 }
 120
 121 DEFUN ("xml-parse-string", Fxml_parse_string, Sxml_parse_string,
 122        0, 2, 0,
 123        doc: /* Parse the string as an XML document and return the parse tree.
 124 If BASE-URL is non-nil, it will be used to expand relative URLs in
 125 the XML document.*/)
 126      (string, base_url)
 127      Lisp_Object string, base_url;
 128 {
 129   return parse_buffer (string, base_url, 0);
 130 }
 131
 132 \f
 133 /***********************************************************************
 134                             Initialization
 135  ***********************************************************************/
 136 void
 137 syms_of_xml (void)
 138 {
 139   defsubr (&Shtml_parse_string);
 140   defsubr (&Sxml_parse_string);
 141 }
 142
 143 #endif /* HAVE_LIBXML2 */