File: CustomParser.cc

package info (click to toggle)
squid3 3.4.8-6+deb8u5
  • links: PTS
  • area: main
  • in suites: jessie
  • size: 32,116 kB
  • sloc: cpp: 165,380; ansic: 21,998; sh: 12,166; makefile: 5,974; perl: 2,153; sql: 322; awk: 118
file content (317 lines) | stat: -rw-r--r-- 8,822 bytes parent folder | download
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
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317

/*
 * DEBUG: section 86    ESI processing
 * AUTHOR: Robert Collins
 *
 * SQUID Web Proxy Cache          http://www.squid-cache.org/
 * ----------------------------------------------------------
 *
 *  Squid is the result of efforts by numerous individuals from
 *  the Internet community; see the CONTRIBUTORS file for full
 *  details.   Many organizations have provided support for Squid's
 *  development; see the SPONSORS file for full details.  Squid is
 *  Copyrighted (C) 2001 by the Regents of the University of
 *  California; see the COPYRIGHT file for full details.  Squid
 *  incorporates software developed and/or copyrighted by other
 *  sources; see the CREDITS file for full details.
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  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 General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
 *
 */

#include "squid.h"
#include "base/Vector.h"
#include "esi/CustomParser.h"
#include "Debug.h"
#include "libTrie/Trie.h"
#include "libTrie/TrieCharTransform.h"

Trie *ESICustomParser::SearchTrie=NULL;

EsiParserDefinition(ESICustomParser);

Trie *
ESICustomParser::GetTrie()
{
    if (SearchTrie)
        return SearchTrie;

    SearchTrie = new Trie(new TrieCaseless);

    static const ESITAG_t ESITAG_value = ESITAG;

    assert (SearchTrie->add
            ("<esi:",5,(void *)&ESITAG_value));

    static const ESITAG_t ESIENDTAG_value = ESIENDTAG;

    assert (SearchTrie->add
            ("</esi:",6,(void *)&ESIENDTAG_value));

    static const ESITAG_t ESICOMMENT_value = ESICOMMENT;

    assert (SearchTrie->add
            ("<!--",4,(void *)&ESICOMMENT_value));

    return SearchTrie;
}

ESICustomParser::ESICustomParser(ESIParserClient *aClient) :
        theClient(aClient),
        lastTag(ESITAG)
{}

ESICustomParser::~ESICustomParser()
{
    theClient = NULL;
}

char const *
ESICustomParser::findTag(char const *buffer, size_t bufferLength)
{
    size_t myOffset (0);
    ESITAG_t *resulttype = NULL;

    while (myOffset < bufferLength &&
            (resulttype = static_cast<ESITAG_t *>(GetTrie()->findPrefix (buffer + myOffset, bufferLength - myOffset)))
            == NULL)
        ++myOffset;

    if (myOffset == bufferLength)
        return NULL;

    debugs(86, 9, "ESICustomParser::findTag: found " << *resulttype);

    lastTag = *resulttype;

    return buffer + myOffset;
}

bool
ESICustomParser::parse(char const *dataToParse, size_t const lengthOfData, bool const endOfStream)
{
    debugs(86, 9, "ESICustomParser::parse: Appending data to internal buffer");
    content.append (dataToParse, lengthOfData);

    if (!endOfStream) {
        return true;
    }

    size_t openESITags (0);
    //erring on the safe side. Probably rawBuf would be ok too
    char const *currentPos = content.termedBuf();
    size_t remainingCount = content.size();
    char const *tag = NULL;

    while ((tag = findTag(currentPos, remainingCount))) {
        if (tag - currentPos)
            theClient->parserDefault (currentPos,tag - currentPos);

        switch (lastTag) {

        case ESITAG: {
            ++openESITags;
            char *tagEnd = strchr(const_cast<char *>(tag), '>');

            if (!tagEnd) {
                error = "Could not find end ('>') of tag";
                return false;
            }

            if (tagEnd - tag > (ssize_t)remainingCount) {
                error = "Tag ends beyond the parse buffer.";
                return false;
            }

            if (*(tagEnd - 1) == '/')
                --openESITags;

            char * endofName = strpbrk(const_cast<char *>(tag), w_space);

            if (!endofName || endofName > tagEnd)
                endofName = const_cast<char *>(tagEnd);

            *endofName = '\0';

            *tagEnd = '\0';

            Vector<char *>attributes;

            char *attribute = const_cast<char *>(endofName + 1);

            while (attribute > tag && attribute < tagEnd) {
                /* leading spaces */

                while (attribute < tagEnd && (xisspace(*attribute) || (*attribute == '/')))
                    ++attribute;

                if (! (attribute < tagEnd))
                    break;

                /* attribute name */
                attributes.push_back(attribute);

                char *nextSpace = strpbrk(attribute, w_space);

                char *equals = strchr(attribute, '=');

                if (!equals) {
                    error = "Missing attribute value.";
                    return false;
                }

                if (nextSpace && nextSpace < equals)
                    *nextSpace = '\0';
                else
                    *equals = '\0';

                ++equals;

                while (equals < tagEnd && xisspace(*equals))
                    ++equals;

                char sep = *equals;

                if (sep != '\'' && sep != '"') {
                    error = "Unknown identifier (";
                    error.append (sep);
                    error.append (")");
                    return false;
                }

                char *value = equals + 1;
                char *end = strchr(value, sep);

                if (!end) {
                    error = "Missing attribute ending separator (";
                    error.append(sep);
                    error.append(")");
                    return false;
                }
                attributes.push_back(value);
                *end = '\0';
                attribute = end + 1;
            }

            theClient->start (tag + 1, (const char **)attributes.items, attributes.size() >> 1);
            /* TODO: attributes */

            if (*(tagEnd - 1) == '/')
                theClient->end (tag + 1);

            remainingCount -= tagEnd - currentPos + 1;

            currentPos = tagEnd + 1;
        }

        break;

        case ESIENDTAG: {
            if (!openESITags)
                return false;

            char const *tagEnd = strchr(tag, '>');

            if (!tagEnd)
                return false;

            if (tagEnd - tag > (ssize_t)remainingCount)
                return false;

            char * endofName = strpbrk(const_cast<char *>(tag), w_space);

            if (!endofName || endofName > tagEnd)
                endofName = const_cast<char *>(tagEnd);

            *endofName = '\0';

            theClient->end (tag + 2);

            --openESITags;

            remainingCount -= tagEnd - currentPos + 1;

            currentPos = tagEnd + 1;
        }

        break;

        case ESICOMMENT: {
            /* Further optimisation potential:
             * 1) recognize end comments for esi and don't callback on
             * comments.
             * 2) provide the comment length to the caller.
             */
            /* Comments must not be nested, without CDATA
             * and we don't support CDATA
             */
            char *commentEnd = strstr (const_cast<char *>(tag), "-->");

            if (!commentEnd) {
                error = "missing end of comment";
                return false;
            }

            if (commentEnd - tag > (ssize_t)remainingCount) {
                error = "comment ends beyond parse buffer";
                return false;
            }

            *commentEnd = '\0';
            theClient->parserComment (tag + 4);
            remainingCount -= commentEnd - currentPos + 3;
            currentPos = commentEnd + 3;
        }

        break;
        break;

        default:
            fatal ("unknown ESI tag type found");
        };

        /*
         * Find next esi tag (open or closing) or comment
         * send tag, or full comment text
         * rinse
         */
    }

    if (remainingCount)
        theClient->parserDefault (currentPos,remainingCount);

    debugs(86, 5, "ESICustomParser::parse: Finished parsing, will return " << !openESITags);

    if (openESITags)
        error = "ESI Tags still open";

    return !openESITags;
}

long int
ESICustomParser::lineNumber() const
{
    /* We don't track lines in the body */
    return 0;
}

char const *
ESICustomParser::errorString() const
{
    if (error.size())
        return error.termedBuf();
    else
        return "Parsing error strings not implemented";
}