1 /* Interface to libxml2.
2 Copyright (C) 2010 Free Software Foundation, Inc.
4 This file is part of GNU Emacs.
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.
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.
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/>. */
24 #include <libxml/tree.h>
25 #include <libxml/parser.h>
26 #include <libxml/HTMLparser.h>
31 Lisp_Object
make_dom (xmlNode
*node
)
33 if (node
->type
== XML_ELEMENT_NODE
)
35 Lisp_Object result
= Fcons (intern (node
->name
), Qnil
);
38 Lisp_Object plist
= Qnil
;
40 /* First add the attributes. */
41 property
= node
->properties
;
42 while (property
!= NULL
)
44 if (property
->children
&&
45 property
->children
->content
)
47 plist
= Fcons (Fcons (intern (property
->name
),
48 build_string (property
->children
->content
)),
51 property
= property
->next
;
53 result
= Fcons (Fnreverse (plist
), result
);
55 /* Then add the children of the node. */
56 child
= node
->children
;
59 result
= Fcons (make_dom (child
), result
);
63 return Fnreverse (result
);
65 else if (node
->type
== XML_TEXT_NODE
)
68 return build_string (node
->content
);
77 parse_string (Lisp_Object string
, Lisp_Object base_url
, int htmlp
)
81 Lisp_Object result
= Qnil
;
83 const char *burl
= "";
87 CHECK_STRING (string
);
89 if (! NILP (base_url
))
91 CHECK_STRING (base_url
);
92 burl
= SDATA (base_url
);
96 ? htmlReadMemory (SDATA (string
), SBYTES (string
), burl
, "utf-8",
97 HTML_PARSE_RECOVER
|HTML_PARSE_NONET
|
98 HTML_PARSE_NOWARNING
|HTML_PARSE_NOERROR
)
99 : xmlReadMemory (SDATA (string
), SBYTES (string
), burl
, "utf-8",
100 XML_PARSE_NONET
|XML_PARSE_NOWARNING
|
105 node
= xmlDocGetRootElement (doc
);
107 result
= make_dom (node
);
115 DEFUN ("xml-parse-html-string-internal", Fxml_parse_html_string_internal
,
116 Sxml_parse_html_string_internal
,
118 doc
: /* Parse STRING as an HTML document and return the parse tree.
119 If BASE-URL is non-nil, it is used to expand relative URLs. */)
120 (Lisp_Object string
, Lisp_Object base_url
)
122 return parse_string (string
, base_url
, 1);
125 DEFUN ("xml-parse-string-internal", Fxml_parse_string_internal
,
126 Sxml_parse_string_internal
,
128 doc
: /* Parse STRING as an XML document and return the parse tree.
129 If BASE-URL is non-nil, it is used to expand relative URLs. */)
130 (Lisp_Object string
, Lisp_Object base_url
)
132 return parse_string (string
, base_url
, 0);
136 /***********************************************************************
138 ***********************************************************************/
142 defsubr (&Sxml_parse_html_string_internal
);
143 defsubr (&Sxml_parse_string_internal
);
146 #endif /* HAVE_LIBXML2 */