aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/icu/i18n/strmatch.cpp
blob: b6a5c94e98d407750aca8de2f42e6a39d55bbef1 (plain) (blame)
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
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
*   Copyright (c) 2001-2012, International Business Machines Corporation
*   and others.  All Rights Reserved.
**********************************************************************
*   Date        Name        Description
*   07/23/01    aliu        Creation.
**********************************************************************
*/

#include "unicode/utypes.h"

#if !UCONFIG_NO_TRANSLITERATION

#include "strmatch.h"
#include "rbt_data.h"
#include "util.h"
#include "unicode/uniset.h"
#include "unicode/utf16.h"

U_NAMESPACE_BEGIN

UOBJECT_DEFINE_RTTI_IMPLEMENTATION(StringMatcher)

StringMatcher::StringMatcher(const UnicodeString& theString,
                             int32_t start,
                             int32_t limit,
                             int32_t segmentNum,
                             const TransliterationRuleData& theData) :
    data(&theData),
    segmentNumber(segmentNum),
    matchStart(-1),
    matchLimit(-1)
{
    theString.extractBetween(start, limit, pattern);
}

StringMatcher::StringMatcher(const StringMatcher& o) :
    UnicodeFunctor(o),
    UnicodeMatcher(o),
    UnicodeReplacer(o),
    pattern(o.pattern),
    data(o.data),
    segmentNumber(o.segmentNumber),
    matchStart(o.matchStart),
    matchLimit(o.matchLimit)
{
}

/**
 * Destructor
 */
StringMatcher::~StringMatcher() {
}

/**
 * Implement UnicodeFunctor
 */
StringMatcher* StringMatcher::clone() const {
    return new StringMatcher(*this);
}

/**
 * UnicodeFunctor API.  Cast 'this' to a UnicodeMatcher* pointer
 * and return the pointer.
 */
UnicodeMatcher* StringMatcher::toMatcher() const {
  StringMatcher  *nonconst_this = const_cast<StringMatcher *>(this);
  UnicodeMatcher *nonconst_base = static_cast<UnicodeMatcher *>(nonconst_this);
  
  return nonconst_base;
}

/**
 * UnicodeFunctor API.  Cast 'this' to a UnicodeReplacer* pointer
 * and return the pointer.
 */
UnicodeReplacer* StringMatcher::toReplacer() const {
  StringMatcher  *nonconst_this = const_cast<StringMatcher *>(this);
  UnicodeReplacer *nonconst_base = static_cast<UnicodeReplacer *>(nonconst_this);
  
  return nonconst_base;
}

/**
 * Implement UnicodeMatcher
 */
UMatchDegree StringMatcher::matches(const Replaceable& text,
                                    int32_t& offset,
                                    int32_t limit,
                                    UBool incremental) {
    int32_t i;
    int32_t cursor = offset;
    if (limit < cursor) {
        // Match in the reverse direction
        for (i=pattern.length()-1; i>=0; --i) {
            char16_t keyChar = pattern.charAt(i);
            UnicodeMatcher* subm = data->lookupMatcher(keyChar);
            if (subm == nullptr) {
                if (cursor > limit &&
                    keyChar == text.charAt(cursor)) {
                    --cursor;
                } else {
                    return U_MISMATCH;
                }
            } else {
                UMatchDegree m =
                    subm->matches(text, cursor, limit, incremental);
                if (m != U_MATCH) {
                    return m;
                }
            }
        }
        // Record the match position, but adjust for a normal
        // forward start, limit, and only if a prior match does not
        // exist -- we want the rightmost match.
        if (matchStart < 0) {
            matchStart = cursor+1;
            matchLimit = offset+1;
        }
    } else {
        for (i=0; i<pattern.length(); ++i) {
            if (incremental && cursor == limit) {
                // We've reached the context limit without a mismatch and
                // without completing our match.
                return U_PARTIAL_MATCH;
            }
            char16_t keyChar = pattern.charAt(i);
            UnicodeMatcher* subm = data->lookupMatcher(keyChar);
            if (subm == nullptr) {
                // Don't need the cursor < limit check if
                // incremental is true (because it's done above); do need
                // it otherwise.
                if (cursor < limit &&
                    keyChar == text.charAt(cursor)) {
                    ++cursor;
                } else {
                    return U_MISMATCH;
                }
            } else {
                UMatchDegree m =
                    subm->matches(text, cursor, limit, incremental);
                if (m != U_MATCH) {
                    return m;
                }
            }
        }
        // Record the match position
        matchStart = offset;
        matchLimit = cursor;
    }

    offset = cursor;
    return U_MATCH;
}

/**
 * Implement UnicodeMatcher
 */
UnicodeString& StringMatcher::toPattern(UnicodeString& result,
                                        UBool escapeUnprintable) const
{
    result.truncate(0);
    UnicodeString str, quoteBuf;
    if (segmentNumber > 0) {
        result.append((char16_t)40); /*(*/
    }
    for (int32_t i=0; i<pattern.length(); ++i) {
        char16_t keyChar = pattern.charAt(i);
        const UnicodeMatcher* m = data->lookupMatcher(keyChar);
        if (m == nullptr) {
            ICU_Utility::appendToRule(result, keyChar, false, escapeUnprintable, quoteBuf);
        } else {
            ICU_Utility::appendToRule(result, m->toPattern(str, escapeUnprintable),
                         true, escapeUnprintable, quoteBuf);
        }
    }
    if (segmentNumber > 0) {
        result.append((char16_t)41); /*)*/
    }
    // Flush quoteBuf out to result
    ICU_Utility::appendToRule(result, -1,
                              true, escapeUnprintable, quoteBuf);
    return result;
}

/**
 * Implement UnicodeMatcher
 */
UBool StringMatcher::matchesIndexValue(uint8_t v) const {
    if (pattern.length() == 0) {
        return true;
    }
    UChar32 c = pattern.char32At(0);
    const UnicodeMatcher *m = data->lookupMatcher(c);
    return (m == nullptr) ? ((c & 0xFF) == v) : m->matchesIndexValue(v);
}

/**
 * Implement UnicodeMatcher
 */
void StringMatcher::addMatchSetTo(UnicodeSet& toUnionTo) const {
    UChar32 ch;
    for (int32_t i=0; i<pattern.length(); i+=U16_LENGTH(ch)) {
        ch = pattern.char32At(i);
        const UnicodeMatcher* matcher = data->lookupMatcher(ch);
        if (matcher == nullptr) {
            toUnionTo.add(ch);
        } else {
            matcher->addMatchSetTo(toUnionTo);
        }
    }
}

/**
 * UnicodeReplacer API
 */
int32_t StringMatcher::replace(Replaceable& text,
                               int32_t start,
                               int32_t limit,
                               int32_t& /*cursor*/) {
    
    int32_t outLen = 0;
    
    // Copy segment with out-of-band data
    int32_t dest = limit;
    // If there was no match, that means that a quantifier
    // matched zero-length.  E.g., x (a)* y matched "xy".
    if (matchStart >= 0) {
        if (matchStart != matchLimit) {
            text.copy(matchStart, matchLimit, dest);
            outLen = matchLimit - matchStart;
        }
    }
    
    text.handleReplaceBetween(start, limit, UnicodeString()); // delete original text
    
    return outLen;
}

/**
 * UnicodeReplacer API
 */
UnicodeString& StringMatcher::toReplacerPattern(UnicodeString& rule,
                                                UBool /*escapeUnprintable*/) const {
    // assert(segmentNumber > 0);
    rule.truncate(0);
    rule.append((char16_t)0x0024 /*$*/);
    ICU_Utility::appendNumber(rule, segmentNumber, 10, 1);
    return rule;
}

/**
 * Remove any match info.  This must be called before performing a
 * set of matches with this segment.
 */
 void StringMatcher::resetMatch() {
    matchStart = matchLimit = -1;
}

/**
 * Union the set of all characters that may output by this object
 * into the given set.
 * @param toUnionTo the set into which to union the output characters
 */
void StringMatcher::addReplacementSetTo(UnicodeSet& /*toUnionTo*/) const {
    // The output of this replacer varies; it is the source text between
    // matchStart and matchLimit.  Since this varies depending on the
    // input text, we can't compute it here.  We can either do nothing
    // or we can add ALL characters to the set.  It's probably more useful
    // to do nothing.
}

/**
 * Implement UnicodeFunctor
 */
void StringMatcher::setData(const TransliterationRuleData* d) {
    data = d;
    int32_t i = 0;
    while (i<pattern.length()) {
        UChar32 c = pattern.char32At(i);
        UnicodeFunctor* f = data->lookup(c);
        if (f != nullptr) {
            f->setData(data);
        }
        i += U16_LENGTH(c);
    }
}

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_TRANSLITERATION */

//eof