File: e2k-xml-utils.c

package info (click to toggle)
evolution-data-server 1.6.3-5etch3
  • links: PTS
  • area: main
  • in suites: etch
  • size: 59,384 kB
  • ctags: 43,218
  • sloc: ansic: 319,315; tcl: 30,499; xml: 19,166; sh: 18,776; perl: 11,529; cpp: 8,259; java: 7,653; makefile: 6,448; awk: 1,338; yacc: 1,103; sed: 772; cs: 505; lex: 134; asm: 14
file content (255 lines) | stat: -rw-r--r-- 6,491 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */

/* Copyright (C) 2001-2004 Novell, Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU Lesser General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 */

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#include "e2k-xml-utils.h"
#include <stdlib.h>
#include <libxml/HTMLparser.h>
#include <libxml/parserInternals.h>
#include <libxml/xmlmemory.h>

static void
my_xml_parser_error_handler (void *ctx, const char *msg, ...)
{
	;
}

/**
 * e2k_parse_xml:
 * @buf: the data to parse
 * @len: the length of the buffer, or -1 if it is '\0'-terminated
 *
 * Parses the XML document in @buf.
 *
 * Return value: a pointer to an #xmlDoc
 **/
xmlDoc *
e2k_parse_xml (const char *buf, int len)
{
	static xmlSAXHandler *sax;
	xmlParserCtxtPtr ctxt;
	xmlDoc *doc;

	g_return_val_if_fail (buf != NULL, NULL);

	if (!sax) {
		xmlInitParser();
		sax = xmlMalloc (sizeof (xmlSAXHandler));
#if LIBXML_VERSION > 20600
		xmlSAXVersion (sax, 2);
#else
		memcpy (sax, &xmlDefaultSAXHandler, sizeof (xmlSAXHandler));
#endif
		sax->warning = my_xml_parser_error_handler;
		sax->error = my_xml_parser_error_handler;
	}

	if (len == -1)
		len = strlen (buf);
	ctxt = xmlCreateMemoryParserCtxt (buf, len);
	if (!ctxt)
		return NULL;

	xmlFree (ctxt->sax);
        ctxt->sax = sax;
#if LIBXML_VERSION > 20600
	ctxt->sax2 = 1;
	ctxt->str_xml = xmlDictLookup (ctxt->dict, BAD_CAST "xml", 3);
	ctxt->str_xmlns = xmlDictLookup (ctxt->dict, BAD_CAST "xmlns", 5);
	ctxt->str_xml_ns = xmlDictLookup (ctxt->dict, XML_XML_NAMESPACE, 36);
#endif

	/* We set recover to TRUE because Exchange will let you
	 * put control-characters into data, which will make the
	 * XML be not well-formed.
	 */
	ctxt->recovery = TRUE;
	ctxt->vctxt.error = my_xml_parser_error_handler;
	ctxt->vctxt.warning = my_xml_parser_error_handler;

	xmlParseDocument (ctxt);

	doc = ctxt->myDoc;
	ctxt->sax = NULL;
	xmlFreeParserCtxt (ctxt);

	return doc;
}

/**
 * e2k_parse_html:
 * @buf: the data to parse
 * @len: the length of the buffer, or -1 if it is '\0'-terminated
 *
 * Parses the HTML document in @buf.
 *
 * Return value: a pointer to an #xmlDoc
 **/
xmlDoc *
e2k_parse_html (const char *buf, int len)
{
	xmlDoc *doc;
#if LIBXML_VERSION > 20600
	static xmlSAXHandler *sax;
	htmlParserCtxtPtr ctxt;

	g_return_val_if_fail (buf != NULL, NULL);

	if (!sax) {
		xmlInitParser();
		sax = xmlMalloc (sizeof (htmlSAXHandler));
		memcpy (sax, &htmlDefaultSAXHandler, sizeof (xmlSAXHandlerV1));
		sax->warning = my_xml_parser_error_handler;
		sax->error = my_xml_parser_error_handler;
	}

	if (len == -1)
		len = strlen (buf);
	ctxt = htmlCreateMemoryParserCtxt (buf, len);
	if (!ctxt)
		return NULL;

        xmlFree (ctxt->sax);
        ctxt->sax = sax;
	ctxt->vctxt.error = my_xml_parser_error_handler;
	ctxt->vctxt.warning = my_xml_parser_error_handler;

	htmlParseDocument (ctxt);
	doc = ctxt->myDoc;

	ctxt->sax = NULL;
	htmlFreeParserCtxt (ctxt);

#else /* LIBXML_VERSION <= 20600 */
	char *buf_copy = g_strndup (buf, len);

	doc = htmlParseDoc (buf_copy, NULL);
	g_free (buf_copy);
#endif

	return doc;
}

/**
 * e2k_g_string_append_xml_escaped:
 * @string: a %GString containing XML data
 * @value: data to append to @string
 *
 * Appends @value to @string, escaping any characters that can't appear
 * unencoded in XML text (eg, "<").
 **/
void
e2k_g_string_append_xml_escaped (GString *string, const char *value)
{
	while (*value) {
		switch (*value) {
		case '<':
			g_string_append (string, "&lt;");
			break;
		case '>':
			g_string_append (string, "&gt;");
			break;
		case '&':
			g_string_append (string, "&amp;");
			break;
		case '"':
			g_string_append (string, "&quot;");
			break;

		default:
			g_string_append_c (string, *value);
			break;
		}
		value++;
	}
}

/**
 * e2k_xml_find:
 * @node: a node of an xml document
 * @name: the name of the element to find
 *
 * Starts or continues a pre-order depth-first search of an xml
 * document for an element named @name. @node is used as the starting
 * point of the search, but is not examined itself.
 *
 * To search the complete document, pass the root node of the document
 * as @node on the first call, and then on each successive call,
 * pass the previous match as @node.
 *
 * Return value: the first matching element after @node, or %NULL when
 * there are no more matches.
 **/
xmlNode *
e2k_xml_find (xmlNode *node, const char *name)
{
	return e2k_xml_find_in (node, NULL, name);
}

/**
 * e2k_xml_find_in:
 * @node: a node of an xml document
 * @top: top of the search space
 * @name: the name of the element to find
 *
 * Starts or continues a pre-order depth-first search of a subset of
 * an xml document for an element named @name. @node is used as the
 * starting point of the search, but is not examined itself. @top is
 * the upper-most node that will be examined.
 *
 * To search the complete tree under a given node, pass that node as
 * both @node and @top on the first call, and then on each successive
 * call, pass the previous match as @node (with the original node
 * still as @top).
 *
 * Return value: the first matching element after @node, or %NULL when
 * there are no more matches.
 **/
xmlNode *
e2k_xml_find_in (xmlNode *node, xmlNode *top, const char *name)
{
	g_return_val_if_fail (name != NULL, NULL);

	while (node) {
		/* If the current node has children, then the first
		 * child is the next node to examine. If it doesn't
		 * have children but does have a younger sibling, then
		 * that sibling is next up. Otherwise, climb back up
		 * the tree until we find a node that does have a
		 * younger sibling.
		 */
		if (node->children)
			node = node->children;
		else {
			while (node && !node->next && node != top)
				node = node->parent;
			if (!node || node == top)
				return NULL;
			node = node->next;
		}

		if (node->name && !strcmp (node->name, name))
			return node;
	}

	return NULL;
}