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 static Lisp_Object
  32 make_dom (xmlNode *node)
  33 {
  34   if (node->type == XML_ELEMENT_NODE)
  35     {
  36       Lisp_Object result = Fcons (intern ((char *) node->name), Qnil);
  37       xmlNode *child;
  38       xmlAttr *property;
  39       Lisp_Object plist = Qnil;
  40
  41       /* First add the attributes. */
  42       property = node->properties;
  43       while (property != NULL)
  44         {
  45           if (property->children &&
  46               property->children->content)
  47             {
  48               char *content = (char *) property->children->content;
  49               plist = Fcons (Fcons (intern ((char *) property->name),
  50                                     build_string (content)),
  51                              plist);
  52             }
  53           property = property->next;
  54         }
  55       result = Fcons (Fnreverse (plist), result);
  56
  57       /* Then add the children of the node. */
  58       child = node->children;
  59       while (child != NULL)
  60         {
  61           result = Fcons (make_dom (child), result);
  62           child = child->next;
  63         }
  64
  65       return Fnreverse (result);
  66     }
  67   else if (node->type == XML_TEXT_NODE || node->type == XML_CDATA_SECTION_NODE)
  68     {
  69       if (node->content)
  70         return build_string ((char *) node->content);
  71       else
  72         return Qnil;
  73     }
  74   else if (node->type == XML_COMMENT_NODE)
  75     {
  76       if (node->content)
  77         return list3 (intern ("comment"), Qnil,
  78                       build_string ((char *) node->content));
  79       else
  80         return Qnil;
  81     }
  82   else
  83     return Qnil;
  84 }
  85
  86 static Lisp_Object
  87 parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url, int htmlp)
  88 {
  89   xmlDoc *doc;
  90   Lisp_Object result = Qnil;
  91   const char *burl = "";
  92   EMACS_INT bytes;
  93   EMACS_INT istart, iend;
  94
  95   LIBXML_TEST_VERSION;
  96
  97   validate_region (&start, &end);
  98
  99   istart = XINT (start);
 100   iend = XINT (end);
 101
 102   if (istart < GPT && GPT < iend)
 103     move_gap (iend);
 104
 105   if (! NILP (base_url))
 106     {
 107       CHECK_STRING (base_url);
 108       burl = SSDATA (base_url);
 109     }
 110
 111   bytes = CHAR_TO_BYTE (iend) - CHAR_TO_BYTE (istart);
 112
 113   if (htmlp)
 114     doc = htmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)),
 115                           bytes, burl, "utf-8",
 116                           HTML_PARSE_RECOVER|HTML_PARSE_NONET|
 117                           HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR|
 118                           HTML_PARSE_NOBLANKS);
 119   else
 120     doc = xmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)),
 121                          bytes, burl, "utf-8",
 122                          XML_PARSE_NONET|XML_PARSE_NOWARNING|
 123                          XML_PARSE_NOBLANKS |XML_PARSE_NOERROR);
 124
 125   if (doc != NULL)
 126     {
 127       /* If the document is just comments, then this should get us the
 128          nodes anyway. */
 129       xmlNode *n = doc->children->next;
 130       Lisp_Object r = Qnil;
 131
 132       while (n) {
 133         if (!NILP (r))
 134           result = Fcons (r, result);
 135         r = make_dom (n);
 136         n = n->next;
 137       }
 138
 139       if (NILP (result)) {
 140         /* The document isn't just comments, so get the tree the
 141            proper way. */
 142         xmlNode *node = xmlDocGetRootElement (doc);
 143         if (node != NULL)
 144           result = make_dom (node);
 145       } else
 146         result = Fcons (intern ("top"),
 147                         Fcons (Qnil, Fnreverse (Fcons (r, result))));
 148
 149       xmlFreeDoc (doc);
 150     }
 151
 152   return result;
 153 }
 154
 155 DEFUN ("libxml-parse-html-region", Flibxml_parse_html_region,
 156        Slibxml_parse_html_region,
 157        2, 3, 0,
 158        doc: /* Parse the region as an HTML document and return the parse tree.
 159 If BASE-URL is non-nil, it is used to expand relative URLs.  */)
 160   (Lisp_Object start, Lisp_Object end, Lisp_Object base_url)
 161 {
 162   return parse_region (start, end, base_url, 1);
 163 }
 164
 165 DEFUN ("libxml-parse-xml-region", Flibxml_parse_xml_region,
 166        Slibxml_parse_xml_region,
 167        2, 3, 0,
 168        doc: /* Parse the region as an XML document and return the parse tree.
 169 If BASE-URL is non-nil, it is used to expand relative URLs.  */)
 170   (Lisp_Object start, Lisp_Object end, Lisp_Object base_url)
 171 {
 172   return parse_region (start, end, base_url, 0);
 173 }
 174
 175 \f
 176 /***********************************************************************
 177                             Initialization
 178  ***********************************************************************/
 179 void
 180 syms_of_xml (void)
 181 {
 182   defsubr (&Slibxml_parse_html_region);
 183   defsubr (&Slibxml_parse_xml_region);
 184 }
 185
 186 #endif /* HAVE_LIBXML2 */