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
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2014-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* dictionarydata.h
*
* created on: 2012may31
* created by: Markus W. Scherer & Maxime Serrano
*/
#include "dictionarydata.h"
#include "unicode/ucharstrie.h"
#include "unicode/bytestrie.h"
#include "unicode/udata.h"
#include "cmemory.h"
#if !UCONFIG_NO_BREAK_ITERATION
U_NAMESPACE_BEGIN
const int32_t DictionaryData::TRIE_TYPE_BYTES = 0;
const int32_t DictionaryData::TRIE_TYPE_UCHARS = 1;
const int32_t DictionaryData::TRIE_TYPE_MASK = 7;
const int32_t DictionaryData::TRIE_HAS_VALUES = 8;
const int32_t DictionaryData::TRANSFORM_NONE = 0;
const int32_t DictionaryData::TRANSFORM_TYPE_OFFSET = 0x1000000;
const int32_t DictionaryData::TRANSFORM_TYPE_MASK = 0x7f000000;
const int32_t DictionaryData::TRANSFORM_OFFSET_MASK = 0x1fffff;
DictionaryMatcher::~DictionaryMatcher() {
}
UCharsDictionaryMatcher::~UCharsDictionaryMatcher() {
udata_close(file);
}
int32_t UCharsDictionaryMatcher::getType() const {
return DictionaryData::TRIE_TYPE_UCHARS;
}
int32_t UCharsDictionaryMatcher::matches(UText *text, int32_t maxLength, int32_t limit,
int32_t *lengths, int32_t *cpLengths, int32_t *values,
int32_t *prefix) const {
UCharsTrie uct(characters);
int32_t startingTextIndex = static_cast<int32_t>(utext_getNativeIndex(text));
int32_t wordCount = 0;
int32_t codePointsMatched = 0;
for (UChar32 c = utext_next32(text); c >= 0; c=utext_next32(text)) {
UStringTrieResult result = (codePointsMatched == 0) ? uct.first(c) : uct.next(c);
int32_t lengthMatched = static_cast<int32_t>(utext_getNativeIndex(text)) - startingTextIndex;
codePointsMatched += 1;
if (USTRINGTRIE_HAS_VALUE(result)) {
if (wordCount < limit) {
if (values != nullptr) {
values[wordCount] = uct.getValue();
}
if (lengths != nullptr) {
lengths[wordCount] = lengthMatched;
}
if (cpLengths != nullptr) {
cpLengths[wordCount] = codePointsMatched;
}
++wordCount;
}
if (result == USTRINGTRIE_FINAL_VALUE) {
break;
}
}
else if (result == USTRINGTRIE_NO_MATCH) {
break;
}
if (lengthMatched >= maxLength) {
break;
}
}
if (prefix != nullptr) {
*prefix = codePointsMatched;
}
return wordCount;
}
BytesDictionaryMatcher::~BytesDictionaryMatcher() {
udata_close(file);
}
UChar32 BytesDictionaryMatcher::transform(UChar32 c) const {
if ((transformConstant & DictionaryData::TRANSFORM_TYPE_MASK) == DictionaryData::TRANSFORM_TYPE_OFFSET) {
if (c == 0x200D) {
return 0xFF;
} else if (c == 0x200C) {
return 0xFE;
}
int32_t delta = c - (transformConstant & DictionaryData::TRANSFORM_OFFSET_MASK);
if (delta < 0 || 0xFD < delta) {
return U_SENTINEL;
}
return static_cast<UChar32>(delta);
}
return c;
}
int32_t BytesDictionaryMatcher::getType() const {
return DictionaryData::TRIE_TYPE_BYTES;
}
int32_t BytesDictionaryMatcher::matches(UText *text, int32_t maxLength, int32_t limit,
int32_t *lengths, int32_t *cpLengths, int32_t *values,
int32_t *prefix) const {
BytesTrie bt(characters);
int32_t startingTextIndex = static_cast<int32_t>(utext_getNativeIndex(text));
int32_t wordCount = 0;
int32_t codePointsMatched = 0;
for (UChar32 c = utext_next32(text); c >= 0; c=utext_next32(text)) {
UStringTrieResult result = (codePointsMatched == 0) ? bt.first(transform(c)) : bt.next(transform(c));
int32_t lengthMatched = static_cast<int32_t>(utext_getNativeIndex(text)) - startingTextIndex;
codePointsMatched += 1;
if (USTRINGTRIE_HAS_VALUE(result)) {
if (wordCount < limit) {
if (values != nullptr) {
values[wordCount] = bt.getValue();
}
if (lengths != nullptr) {
lengths[wordCount] = lengthMatched;
}
if (cpLengths != nullptr) {
cpLengths[wordCount] = codePointsMatched;
}
++wordCount;
}
if (result == USTRINGTRIE_FINAL_VALUE) {
break;
}
}
else if (result == USTRINGTRIE_NO_MATCH) {
break;
}
if (lengthMatched >= maxLength) {
break;
}
}
if (prefix != nullptr) {
*prefix = codePointsMatched;
}
return wordCount;
}
U_NAMESPACE_END
U_NAMESPACE_USE
U_CAPI int32_t U_EXPORT2
udict_swap(const UDataSwapper *ds, const void *inData, int32_t length,
void *outData, UErrorCode *pErrorCode) {
const UDataInfo *pInfo;
int32_t headerSize;
const uint8_t *inBytes;
uint8_t *outBytes;
const int32_t *inIndexes;
int32_t indexes[DictionaryData::IX_COUNT];
int32_t i, offset, size;
headerSize = udata_swapDataHeader(ds, inData, length, outData, pErrorCode);
if (pErrorCode == nullptr || U_FAILURE(*pErrorCode)) return 0;
pInfo = (const UDataInfo *)((const char *)inData + 4);
if (!(pInfo->dataFormat[0] == 0x44 &&
pInfo->dataFormat[1] == 0x69 &&
pInfo->dataFormat[2] == 0x63 &&
pInfo->dataFormat[3] == 0x74 &&
pInfo->formatVersion[0] == 1)) {
udata_printError(ds, "udict_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized as dictionary data\n",
pInfo->dataFormat[0], pInfo->dataFormat[1], pInfo->dataFormat[2], pInfo->dataFormat[3], pInfo->formatVersion[0]);
*pErrorCode = U_UNSUPPORTED_ERROR;
return 0;
}
inBytes = (const uint8_t *)inData + headerSize;
outBytes = (outData == nullptr) ? nullptr : (uint8_t *)outData + headerSize;
inIndexes = (const int32_t *)inBytes;
if (length >= 0) {
length -= headerSize;
if (length < (int32_t)(sizeof(indexes))) {
udata_printError(ds, "udict_swap(): too few bytes (%d after header) for dictionary data\n", length);
*pErrorCode = U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
}
for (i = 0; i < DictionaryData::IX_COUNT; i++) {
indexes[i] = udata_readInt32(ds, inIndexes[i]);
}
size = indexes[DictionaryData::IX_TOTAL_SIZE];
if (length >= 0) {
if (length < size) {
udata_printError(ds, "udict_swap(): too few bytes (%d after header) for all of dictionary data\n", length);
*pErrorCode = U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
if (inBytes != outBytes) {
uprv_memcpy(outBytes, inBytes, size);
}
offset = 0;
ds->swapArray32(ds, inBytes, sizeof(indexes), outBytes, pErrorCode);
offset = (int32_t)sizeof(indexes);
int32_t trieType = indexes[DictionaryData::IX_TRIE_TYPE] & DictionaryData::TRIE_TYPE_MASK;
int32_t nextOffset = indexes[DictionaryData::IX_RESERVED1_OFFSET];
if (trieType == DictionaryData::TRIE_TYPE_UCHARS) {
ds->swapArray16(ds, inBytes + offset, nextOffset - offset, outBytes + offset, pErrorCode);
} else if (trieType == DictionaryData::TRIE_TYPE_BYTES) {
// nothing to do
} else {
udata_printError(ds, "udict_swap(): unknown trie type!\n");
*pErrorCode = U_UNSUPPORTED_ERROR;
return 0;
}
// these next two sections are empty in the current format,
// but may be used later.
offset = nextOffset;
nextOffset = indexes[DictionaryData::IX_RESERVED2_OFFSET];
offset = nextOffset;
nextOffset = indexes[DictionaryData::IX_TOTAL_SIZE];
offset = nextOffset;
}
return headerSize + size;
}
#endif
|
