Commit | Line | Data |
---|---|---|
381408e2 | 1 | /* Interface to libxml2. |
73b0cd50 | 2 | Copyright (C) 2010-2011 Free Software Foundation, Inc. |
381408e2 LMI |
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 | ||
c9735e30 PE |
31 | static Lisp_Object |
32 | make_dom (xmlNode *node) | |
381408e2 | 33 | { |
4b9832a6 CY |
34 | if (node->type == XML_ELEMENT_NODE) |
35 | { | |
c45e5276 | 36 | Lisp_Object result = Fcons (intern ((char *) node->name), Qnil); |
4b9832a6 CY |
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 | { | |
c45e5276 PE |
48 | char *content = (char *) property->children->content; |
49 | plist = Fcons (Fcons (intern ((char *) property->name), | |
50 | build_string (content)), | |
4b9832a6 CY |
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); | |
381408e2 | 66 | } |
3c2317e8 | 67 | else if (node->type == XML_TEXT_NODE || node->type == XML_CDATA_SECTION_NODE) |
4b9832a6 CY |
68 | { |
69 | if (node->content) | |
c45e5276 | 70 | return build_string ((char *) node->content); |
4b9832a6 CY |
71 | else |
72 | return Qnil; | |
381408e2 | 73 | } |
4b9832a6 | 74 | else |
381408e2 LMI |
75 | return Qnil; |
76 | } | |
77 | ||
78 | static Lisp_Object | |
1b217849 | 79 | parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url, int htmlp) |
381408e2 LMI |
80 | { |
81 | xmlDoc *doc; | |
82 | xmlNode *node; | |
c97c655f | 83 | Lisp_Object result = Qnil; |
55e572ef | 84 | const char *burl = ""; |
1b217849 LMI |
85 | EMACS_INT bytes; |
86 | EMACS_INT istart, iend; | |
8b620f11 | 87 | |
381408e2 | 88 | LIBXML_TEST_VERSION; |
8b620f11 | 89 | |
1b217849 | 90 | validate_region (&start, &end); |
20a5e996 | 91 | |
1b217849 LMI |
92 | istart = XINT (start); |
93 | iend = XINT (end); | |
94 | ||
95 | if (istart < GPT && GPT < iend) | |
96 | move_gap (iend); | |
381408e2 | 97 | |
4b9832a6 CY |
98 | if (! NILP (base_url)) |
99 | { | |
100 | CHECK_STRING (base_url); | |
42a5b22f | 101 | burl = SSDATA (base_url); |
4b9832a6 | 102 | } |
8b620f11 | 103 | |
1b217849 | 104 | bytes = CHAR_TO_BYTE (iend) - CHAR_TO_BYTE (istart); |
20a5e996 | 105 | |
1b217849 | 106 | if (htmlp) |
c45e5276 | 107 | doc = htmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)), |
1b217849 LMI |
108 | bytes, burl, "utf-8", |
109 | HTML_PARSE_RECOVER|HTML_PARSE_NONET| | |
3c2317e8 LMI |
110 | HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR| |
111 | HTML_PARSE_NOBLANKS); | |
1b217849 | 112 | else |
c45e5276 | 113 | doc = xmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)), |
1b217849 LMI |
114 | bytes, burl, "utf-8", |
115 | XML_PARSE_NONET|XML_PARSE_NOWARNING| | |
87302331 | 116 | XML_PARSE_NOBLANKS |XML_PARSE_NOERROR); |
4b9832a6 CY |
117 | |
118 | if (doc != NULL) | |
119 | { | |
120 | node = xmlDocGetRootElement (doc); | |
121 | if (node != NULL) | |
122 | result = make_dom (node); | |
123 | xmlFreeDoc (doc); | |
124 | xmlCleanupParser (); | |
125 | } | |
8b620f11 | 126 | |
381408e2 LMI |
127 | return result; |
128 | } | |
129 | ||
1b217849 LMI |
130 | DEFUN ("libxml-parse-html-region", Flibxml_parse_html_region, |
131 | Slibxml_parse_html_region, | |
132 | 2, 3, 0, | |
133 | doc: /* Parse the region as an HTML document and return the parse tree. | |
4b9832a6 | 134 | If BASE-URL is non-nil, it is used to expand relative URLs. */) |
1b217849 | 135 | (Lisp_Object start, Lisp_Object end, Lisp_Object base_url) |
381408e2 | 136 | { |
1b217849 | 137 | return parse_region (start, end, base_url, 1); |
381408e2 LMI |
138 | } |
139 | ||
1b217849 LMI |
140 | DEFUN ("libxml-parse-xml-region", Flibxml_parse_xml_region, |
141 | Slibxml_parse_xml_region, | |
142 | 2, 3, 0, | |
143 | doc: /* Parse the region as an XML document and return the parse tree. | |
4b9832a6 | 144 | If BASE-URL is non-nil, it is used to expand relative URLs. */) |
1b217849 | 145 | (Lisp_Object start, Lisp_Object end, Lisp_Object base_url) |
381408e2 | 146 | { |
1b217849 | 147 | return parse_region (start, end, base_url, 0); |
381408e2 LMI |
148 | } |
149 | ||
150 | \f | |
151 | /*********************************************************************** | |
152 | Initialization | |
153 | ***********************************************************************/ | |
154 | void | |
155 | syms_of_xml (void) | |
156 | { | |
1b217849 LMI |
157 | defsubr (&Slibxml_parse_html_region); |
158 | defsubr (&Slibxml_parse_xml_region); | |
381408e2 LMI |
159 | } |
160 | ||
161 | #endif /* HAVE_LIBXML2 */ |