Commit | Line | Data |
---|---|---|
381408e2 | 1 | /* Interface to libxml2. |
acaf905b | 2 | Copyright (C) 2010-2012 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 | } |
1e98674d LMI |
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 | } | |
4b9832a6 | 82 | else |
381408e2 LMI |
83 | return Qnil; |
84 | } | |
85 | ||
86 | static Lisp_Object | |
1b217849 | 87 | parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url, int htmlp) |
381408e2 LMI |
88 | { |
89 | xmlDoc *doc; | |
c97c655f | 90 | Lisp_Object result = Qnil; |
55e572ef | 91 | const char *burl = ""; |
1b217849 LMI |
92 | EMACS_INT bytes; |
93 | EMACS_INT istart, iend; | |
8b620f11 | 94 | |
381408e2 | 95 | LIBXML_TEST_VERSION; |
8b620f11 | 96 | |
1b217849 | 97 | validate_region (&start, &end); |
20a5e996 | 98 | |
1b217849 LMI |
99 | istart = XINT (start); |
100 | iend = XINT (end); | |
101 | ||
102 | if (istart < GPT && GPT < iend) | |
103 | move_gap (iend); | |
381408e2 | 104 | |
4b9832a6 CY |
105 | if (! NILP (base_url)) |
106 | { | |
107 | CHECK_STRING (base_url); | |
42a5b22f | 108 | burl = SSDATA (base_url); |
4b9832a6 | 109 | } |
8b620f11 | 110 | |
1b217849 | 111 | bytes = CHAR_TO_BYTE (iend) - CHAR_TO_BYTE (istart); |
20a5e996 | 112 | |
1b217849 | 113 | if (htmlp) |
c45e5276 | 114 | doc = htmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)), |
1b217849 LMI |
115 | bytes, burl, "utf-8", |
116 | HTML_PARSE_RECOVER|HTML_PARSE_NONET| | |
3c2317e8 LMI |
117 | HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR| |
118 | HTML_PARSE_NOBLANKS); | |
1b217849 | 119 | else |
c45e5276 | 120 | doc = xmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)), |
1b217849 LMI |
121 | bytes, burl, "utf-8", |
122 | XML_PARSE_NONET|XML_PARSE_NOWARNING| | |
87302331 | 123 | XML_PARSE_NOBLANKS |XML_PARSE_NOERROR); |
4b9832a6 CY |
124 | |
125 | if (doc != NULL) | |
126 | { | |
3134906c LMI |
127 | /* If the document is just comments, then this should get us the |
128 | nodes anyway. */ | |
36881d16 HK |
129 | xmlNode *n = doc->children->next; |
130 | Lisp_Object r = Qnil; | |
131 | ||
132 | while (n) { | |
14486a10 | 133 | if (!NILP (r)) |
36881d16 HK |
134 | result = Fcons (r, result); |
135 | r = make_dom (n); | |
136 | n = n->next; | |
137 | } | |
138 | ||
3134906c LMI |
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 | |
9abd0532 LMI |
146 | result = Fcons (intern ("top"), |
147 | Fcons (Qnil, Fnreverse (Fcons (r, result)))); | |
36881d16 | 148 | |
4b9832a6 | 149 | xmlFreeDoc (doc); |
4b9832a6 | 150 | } |
8b620f11 | 151 | |
381408e2 LMI |
152 | return result; |
153 | } | |
154 | ||
1b217849 LMI |
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. | |
4b9832a6 | 159 | If BASE-URL is non-nil, it is used to expand relative URLs. */) |
1b217849 | 160 | (Lisp_Object start, Lisp_Object end, Lisp_Object base_url) |
381408e2 | 161 | { |
1b217849 | 162 | return parse_region (start, end, base_url, 1); |
381408e2 LMI |
163 | } |
164 | ||
1b217849 LMI |
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. | |
4b9832a6 | 169 | If BASE-URL is non-nil, it is used to expand relative URLs. */) |
1b217849 | 170 | (Lisp_Object start, Lisp_Object end, Lisp_Object base_url) |
381408e2 | 171 | { |
1b217849 | 172 | return parse_region (start, end, base_url, 0); |
381408e2 LMI |
173 | } |
174 | ||
175 | \f | |
176 | /*********************************************************************** | |
177 | Initialization | |
178 | ***********************************************************************/ | |
179 | void | |
180 | syms_of_xml (void) | |
181 | { | |
1b217849 LMI |
182 | defsubr (&Slibxml_parse_html_region); |
183 | defsubr (&Slibxml_parse_xml_region); | |
381408e2 LMI |
184 | } |
185 | ||
186 | #endif /* HAVE_LIBXML2 */ |