summaryrefslogtreecommitdiffstats
path: root/ucb/source/regexp/regexp.cxx
blob: 8b8dcbc85b8f0c6efe648cadadf5491e6d090b58 (plain)
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
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
 * This file is part of the LibreOffice project.
 *
 * This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/.
 *
 * This file incorporates work covered by the following license notice:
 *
 *   Licensed to the Apache Software Foundation (ASF) under one or more
 *   contributor license agreements. See the NOTICE file distributed
 *   with this work for additional information regarding copyright
 *   ownership. The ASF licenses this file to you under the Apache
 *   License, Version 2.0 (the "License"); you may not use this file
 *   except in compliance with the License. You may obtain a copy of
 *   the License at http://www.apache.org/licenses/LICENSE-2.0 .
 */

#include <regexp.hxx>

#include <cstddef>

#include <osl/diagnose.h>
#include <com/sun/star/lang/IllegalArgumentException.hpp>
#include <rtl/character.hxx>
#include <rtl/ustrbuf.hxx>
#include <rtl/ustring.hxx>
#include <utility>

using namespace com::sun::star;
using namespace ucb_impl;


//  Regexp


inline Regexp::Regexp(Kind eTheKind, OUString aThePrefix,
                      bool bTheEmptyDomain, OUString aTheInfix,
                      bool bTheTranslation,
                      OUString aTheReversePrefix):
    m_eKind(eTheKind),
    m_aPrefix(std::move(aThePrefix)),
    m_aInfix(std::move(aTheInfix)),
    m_aReversePrefix(std::move(aTheReversePrefix)),
    m_bEmptyDomain(bTheEmptyDomain),
    m_bTranslation(bTheTranslation)
{
    OSL_ASSERT(m_eKind == KIND_DOMAIN
               || (!m_bEmptyDomain && m_aInfix.isEmpty()));
    OSL_ASSERT(m_bTranslation || m_aReversePrefix.isEmpty());
}


namespace {

bool matchStringIgnoreCase(sal_Unicode const ** pBegin,
                           sal_Unicode const * pEnd,
                           OUString const & rString)
{
    sal_Unicode const * p = *pBegin;

    sal_Unicode const * q = rString.getStr();
    sal_Unicode const * qEnd = q + rString.getLength();

    if (pEnd - p < qEnd - q)
        return false;

    while (q != qEnd)
    {
        if (rtl::compareIgnoreAsciiCase(*p++, *q++) != 0)
            return false;
    }

    *pBegin = p;
    return true;
}

}

bool Regexp::matches(OUString const & rString) const
{
    sal_Unicode const * pBegin = rString.getStr();
    sal_Unicode const * pEnd = pBegin + rString.getLength();

    bool bMatches = false;

    sal_Unicode const * p = pBegin;
    if (matchStringIgnoreCase(&p, pEnd, m_aPrefix))
    {
        switch (m_eKind)
        {
            case KIND_PREFIX:
                bMatches = true;
                break;

            case KIND_AUTHORITY:
                bMatches = p == pEnd || *p == '/' || *p == '?' || *p == '#';
                break;

            case KIND_DOMAIN:
                if (!m_bEmptyDomain)
                {
                    if (p == pEnd || *p == '/' || *p == '?' || *p == '#')
                        break;
                    ++p;
                }
                for (;;)
                {
                    sal_Unicode const * q = p;
                    if (matchStringIgnoreCase(&q, pEnd, m_aInfix)
                        && (q == pEnd || *q == '/' || *q == '?' || *q == '#'))
                    {
                        bMatches = true;
                        break;
                    }

                    if (p == pEnd)
                        break;

                    sal_Unicode c = *p++;
                    if (c == '/' || c == '?' || c == '#')
                        break;
                }
                break;
        }
    }

    return bMatches;
}


namespace {

bool isScheme(OUString const & rString, bool bColon)
{
    // Return true if rString matches <scheme> (plus a trailing ":" if bColon
    // is true) from RFC 2396:
    sal_Unicode const * p = rString.getStr();
    sal_Unicode const * pEnd = p + rString.getLength();
    if (p != pEnd && rtl::isAsciiAlpha(*p))
        for (++p;;)
        {
            if (p == pEnd)
                return !bColon;
            sal_Unicode c = *p++;
            if (!(rtl::isAsciiAlphanumeric(c)
                  || c == '+' || c == '-' || c == '.'))
                return bColon && c == ':' && p == pEnd;
        }
    return false;
}

void appendStringLiteral(OUStringBuffer * pBuffer,
                         OUString const & rString)
{
    OSL_ASSERT(pBuffer);

    pBuffer->append('"');
    sal_Unicode const * p = rString.getStr();
    sal_Unicode const * pEnd = p + rString.getLength();
    while (p != pEnd)
    {
        sal_Unicode c = *p++;
        if (c == '"' || c == '\\')
            pBuffer->append('\\');
        pBuffer->append(c);
    }
    pBuffer->append('"');
}

}

OUString Regexp::getRegexp() const
{
    if (m_bTranslation)
    {
        OUStringBuffer aBuffer;
        if (!m_aPrefix.isEmpty())
            appendStringLiteral(&aBuffer, m_aPrefix);
        switch (m_eKind)
        {
            case KIND_PREFIX:
                aBuffer.append("(.*)");
                break;

            case KIND_AUTHORITY:
                aBuffer.append("(([/?#].*)?)");
                break;

            case KIND_DOMAIN:
                aBuffer.append("([^/?#]" + OUStringChar(sal_Unicode(m_bEmptyDomain ? '*' : '+')));
                if (!m_aInfix.isEmpty())
                    appendStringLiteral(&aBuffer, m_aInfix);
                aBuffer.append("([/?#].*)?)");
                break;
        }
        aBuffer.append("->");
        if (!m_aReversePrefix.isEmpty())
            appendStringLiteral(&aBuffer, m_aReversePrefix);
        aBuffer.append("\\1");
        return aBuffer.makeStringAndClear();
    }
    else if (m_eKind == KIND_PREFIX && isScheme(m_aPrefix, true))
        return m_aPrefix.copy(0, m_aPrefix.getLength() - 1);
    else
    {
        OUStringBuffer aBuffer;
        if (!m_aPrefix.isEmpty())
            appendStringLiteral(&aBuffer, m_aPrefix);
        switch (m_eKind)
        {
            case KIND_PREFIX:
                aBuffer.append(".*");
                break;

            case KIND_AUTHORITY:
                aBuffer.append("([/?#].*)?");
                break;

            case KIND_DOMAIN:
                aBuffer.append("[^/?#]" + OUStringChar( m_bEmptyDomain ? '*' : '+' ));
                if (!m_aInfix.isEmpty())
                    appendStringLiteral(&aBuffer, m_aInfix);
                aBuffer.append("([/?#].*)?");
                break;
        }
        return aBuffer.makeStringAndClear();
    }
}


namespace {

bool matchString(sal_Unicode const ** pBegin, sal_Unicode const * pEnd,
                 char const * pString, size_t nStringLength)
{
    sal_Unicode const * p = *pBegin;

    unsigned char const * q = reinterpret_cast< unsigned char const * >(pString);
    unsigned char const * qEnd = q + nStringLength;

    if (pEnd - p < qEnd - q)
        return false;

    while (q != qEnd)
    {
        sal_Unicode c1 = *p++;
        sal_Unicode c2 = *q++;
        if (c1 != c2)
            return false;
    }

    *pBegin = p;
    return true;
}

bool scanStringLiteral(sal_Unicode const ** pBegin, sal_Unicode const * pEnd,
                       OUString * pString)
{
    sal_Unicode const * p = *pBegin;

    if (p == pEnd || *p++ != '"')
        return false;

    OUStringBuffer aBuffer;
    for (;;)
    {
        if (p == pEnd)
            return false;
        sal_Unicode c = *p++;
        if (c == '"')
            break;
        if (c == '\\')
        {
            if (p == pEnd)
                return false;
            c = *p++;
            if (c != '"' && c != '\\')
                return false;
        }
        aBuffer.append(c);
    }

    *pBegin = p;
    *pString = aBuffer.makeStringAndClear();
    return true;
}

}

Regexp Regexp::parse(OUString const & rRegexp)
{
    // Detect an input of '<scheme>' as an abbreviation of '"<scheme>:".*'
    // where <scheme> is as defined in RFC 2396:
    if (isScheme(rRegexp, false))
        return Regexp(Regexp::KIND_PREFIX,
                      rRegexp + ":",
                      false,
                      OUString(),
                      false,
                      OUString());

    sal_Unicode const * p = rRegexp.getStr();
    sal_Unicode const * pEnd = p + rRegexp.getLength();

    OUString aPrefix;
    scanStringLiteral(&p, pEnd, &aPrefix);

    if (p == pEnd)
        throw lang::IllegalArgumentException();

    // This and the matchString() calls below are some of the few places where
    // RTL_CONSTASCII_STRINGPARAM() should NOT be removed.
    // (c.f. https://gerrit.libreoffice.org/3117)
    if (matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM(".*")))
    {
        if (p != pEnd)
            throw lang::IllegalArgumentException();

        return Regexp(Regexp::KIND_PREFIX, aPrefix, false, OUString(),
                      false, OUString());
    }
    else if (matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM("(.*)->")))
    {
        OUString aReversePrefix;
        scanStringLiteral(&p, pEnd, &aReversePrefix);

        if (!matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM("\\1"))
            || p != pEnd)
            throw lang::IllegalArgumentException();

        return Regexp(Regexp::KIND_PREFIX, aPrefix, false, OUString(),
                      true, aReversePrefix);
    }
    else if (matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM("([/?#].*)?")))
    {
        if (p != pEnd)
            throw lang::IllegalArgumentException();

        return Regexp(Regexp::KIND_AUTHORITY, aPrefix, false, OUString(),
                      false, OUString());
    }
    else if (matchString(&p, pEnd,
                         RTL_CONSTASCII_STRINGPARAM("(([/?#].*)?)->")))
    {
        OUString aReversePrefix;
        if (!(scanStringLiteral(&p, pEnd, &aReversePrefix)
              && matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM("\\1"))
              && p == pEnd))
            throw lang::IllegalArgumentException();

        return Regexp(Regexp::KIND_AUTHORITY, aPrefix, false, OUString(),
                      true, aReversePrefix);
    }
    else
    {
        bool bOpen = false;
        if (p != pEnd && *p == '(')
        {
            ++p;
            bOpen = true;
        }

        if (!matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM("[^/?#]")))
            throw lang::IllegalArgumentException();

        if (p == pEnd || (*p != '*' && *p != '+'))
            throw lang::IllegalArgumentException();
        bool bEmptyDomain = *p++ == '*';

        OUString aInfix;
        scanStringLiteral(&p, pEnd, &aInfix);

        if (!matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM("([/?#].*)?")))
            throw lang::IllegalArgumentException();

        OUString aReversePrefix;
        if (bOpen
            && !(matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM(")->"))
                 && scanStringLiteral(&p, pEnd, &aReversePrefix)
                 && matchString(&p, pEnd, RTL_CONSTASCII_STRINGPARAM("\\1"))))
            throw lang::IllegalArgumentException();

        if (p != pEnd)
            throw lang::IllegalArgumentException();

        return Regexp(Regexp::KIND_DOMAIN, aPrefix, bEmptyDomain, aInfix,
                      bOpen, aReversePrefix);
    }
}

/* vim:set shiftwidth=4 softtabstop=4 expandtab: */