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
|
/*
* libpinyin
* Library to deal with pinyin.
*
* Copyright (C) 2015 Peng Wu <alexepico@gmail.com>
*
* 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 3 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, see <http://www.gnu.org/licenses/>.
*/
#ifndef FLEXIBLE_SINGLE_GRAM_H
#define FLEXIBLE_SINGLE_GRAM_H
namespace pinyin{
typedef GArray * FlexibleBigramPhraseArray;
/**
* FlexibleSingleGram:
* @ArrayHeader: the struct ArrayHeader.
* @ArrayItem: the struct ArrayItem.
*
* The flexible single gram is mainly used for training purpose.
*
*/
template<typename ArrayHeader, typename ArrayItem>
class FlexibleSingleGram{
template<typename MH, typename AH,
typename AI>
friend class FlexibleBigram;
private:
MemoryChunk m_chunk;
FlexibleSingleGram(void * buffer, size_t length, bool copy){
if (copy)
m_chunk.set_content(0, buffer, length);
else
m_chunk.set_chunk(buffer, length, NULL);
}
public:
/**
* ArrayItemWithToken:
*
* Define the struct ArrayItemWithToken type.
*
*/
typedef struct{
phrase_token_t m_token;
ArrayItem m_item;
} ArrayItemWithToken;
private:
static bool token_less_than(const ArrayItemWithToken & lhs,
const ArrayItemWithToken & rhs){
return lhs.m_token < rhs.m_token;
}
public:
/**
* FlexibleSingleGram::FlexibleSingleGram:
*
* The constructor of the FlexibleSingleGram.
*
*/
FlexibleSingleGram(){
m_chunk.set_size(sizeof(ArrayHeader));
memset(m_chunk.begin(), 0, sizeof(ArrayHeader));
}
/**
* FlexibleSingleGram::retrieve_all:
* @array: the array to store all items in this single gram.
* @returns: whether the retrieve operation is successful.
*
* Retrieve all items in this single gram.
*
*/
bool retrieve_all(/* out */ FlexibleBigramPhraseArray array){
const ArrayItemWithToken * begin = (const ArrayItemWithToken *)
((const char *)(m_chunk.begin()) + sizeof(ArrayHeader));
const ArrayItemWithToken * end = (const ArrayItemWithToken *)
m_chunk.end();
ArrayItemWithToken item;
for ( const ArrayItemWithToken * cur_item = begin;
cur_item != end;
++cur_item){
/* Note: optimize this with g_array_append_vals? */
item.m_token = cur_item->m_token;
item.m_item = cur_item->m_item;
g_array_append_val(array, item);
}
return true;
}
/**
* FlexibleSingleGram::search:
* @range: the token range.
* @array: the array to store the array items with token in the range.
* @returns: whether the search operation is successful.
*
* Search the array items with token in the range.
*
* Note: The array result may contain many items.
*
*/
bool search(/* in */ PhraseIndexRange * range,
/* out */ FlexibleBigramPhraseArray array){
const ArrayItemWithToken * begin = (const ArrayItemWithToken *)
((const char *)(m_chunk.begin()) + sizeof(ArrayHeader));
const ArrayItemWithToken * end = (const ArrayItemWithToken *)
m_chunk.end();
ArrayItemWithToken compare_item;
compare_item.m_token = range->m_range_begin;
const ArrayItemWithToken * cur_item = std_lite::lower_bound
(begin, end, compare_item, token_less_than);
ArrayItemWithToken item;
for ( ; cur_item != end; ++cur_item){
if ( cur_item->m_token >= range->m_range_end )
break;
item.m_token = cur_item->m_token;
item.m_item = cur_item->m_item;
g_array_append_val(array, item);
}
return true;
}
/**
* FlexibleSingleGram::insert_array_item:
* @token: the phrase token to be inserted.
* @item: the array item of this token.
* @returns: whether the insert operation is successful.
*
* Insert the array item of the token.
*
*/
bool insert_array_item(/* in */ phrase_token_t token,
/* in */ const ArrayItem & item){
ArrayItemWithToken * begin = (ArrayItemWithToken *)
((const char *)(m_chunk.begin()) + sizeof(ArrayHeader));
ArrayItemWithToken * end = (ArrayItemWithToken *)
m_chunk.end();
ArrayItemWithToken compare_item;
compare_item.m_token = token;
ArrayItemWithToken * cur_item = std_lite::lower_bound
(begin, end, compare_item, token_less_than);
ArrayItemWithToken insert_item;
insert_item.m_token = token;
insert_item.m_item = item;
for ( ; cur_item != end; ++cur_item ){
if ( cur_item->m_token > token ){
size_t offset = sizeof(ArrayHeader) +
sizeof(ArrayItemWithToken) * (cur_item - begin);
m_chunk.insert_content(offset, &insert_item,
sizeof(ArrayItemWithToken));
return true;
}
if ( cur_item->m_token == token ){
return false;
}
}
m_chunk.insert_content(m_chunk.size(), &insert_item,
sizeof(ArrayItemWithToken));
return true;
}
/**
* FlexibleSingleGram::remove_array_item:
* @token: the phrase token to be removed.
* @item: the content of the removed array item.
* @returns: whether the remove operation is successful.
*
* Remove the array item of the token.
*
*/
bool remove_array_item(/* in */ phrase_token_t token,
/* out */ ArrayItem & item)
{
/* clear retval */
memset(&item, 0, sizeof(ArrayItem));
const ArrayItemWithToken * begin = (const ArrayItemWithToken *)
((const char *)(m_chunk.begin()) + sizeof(ArrayHeader));
const ArrayItemWithToken * end = (const ArrayItemWithToken *)
m_chunk.end();
ArrayItemWithToken compare_item;
compare_item.m_token = token;
const ArrayItemWithToken * cur_item = std_lite::lower_bound
(begin, end, compare_item, token_less_than);
for ( ; cur_item != end; ++cur_item){
if ( cur_item->m_token > token )
return false;
if ( cur_item->m_token == token ){
memcpy(&item, &(cur_item->m_item), sizeof(ArrayItem));
size_t offset = sizeof(ArrayHeader) +
sizeof(ArrayItemWithToken) * (cur_item - begin);
m_chunk.remove_content(offset, sizeof(ArrayItemWithToken));
return true;
}
}
return false;
}
/**
* FlexibleSingleGram::get_array_item:
* @token: the phrase token.
* @item: the array item of the token.
* @returns: whether the get operation is successful.
*
* Get the array item of the token.
*
*/
bool get_array_item(/* in */ phrase_token_t token,
/* out */ ArrayItem & item)
{
/* clear retval */
memset(&item, 0, sizeof(ArrayItem));
const ArrayItemWithToken * begin = (const ArrayItemWithToken *)
((const char *)(m_chunk.begin()) + sizeof(ArrayHeader));
const ArrayItemWithToken * end = (const ArrayItemWithToken *)
m_chunk.end();
ArrayItemWithToken compare_item;
compare_item.m_token = token;
const ArrayItemWithToken * cur_item = std_lite::lower_bound
(begin, end, compare_item, token_less_than);
for ( ; cur_item != end; ++cur_item){
if ( cur_item->m_token > token )
return false;
if ( cur_item->m_token == token ){
memcpy(&item, &(cur_item->m_item), sizeof(ArrayItem));
return true;
}
}
return false;
}
/**
* FlexibleSingleGram::set_array_item:
* @token: the phrase token.
* @item: the array item of the token.
* @returns: whether the set operation is successful.
*
* Set the array item of the token.
*
*/
bool set_array_item(/* in */ phrase_token_t token,
/* in */ const ArrayItem & item){
ArrayItemWithToken * begin = (ArrayItemWithToken *)
((const char *)(m_chunk.begin()) + sizeof(ArrayHeader));
ArrayItemWithToken * end = (ArrayItemWithToken *)
m_chunk.end();
ArrayItemWithToken compare_item;
compare_item.m_token = token;
ArrayItemWithToken * cur_item = std_lite::lower_bound
(begin, end, compare_item, token_less_than);
for ( ; cur_item != end; ++cur_item ){
if ( cur_item->m_token > token ){
return false;
}
if ( cur_item->m_token == token ){
memcpy(&(cur_item->m_item), &item, sizeof(ArrayItem));
return true;
}
}
return false;
}
/**
* FlexibleSingleGram::get_array_header:
* @header: the array header of this single gram.
* @returns: whether the get operation is successful.
*
* Get the array header of this single gram.
*
*/
bool get_array_header(/* out */ ArrayHeader & header){
/* clear retval */
memset(&header, 0, sizeof(ArrayHeader));
char * buf_begin = (char *)m_chunk.begin();
memcpy(&header, buf_begin, sizeof(ArrayHeader));
return true;
}
/**
* FlexibleSingleGram::set_array_header:
* @header: the array header of this single gram.
* @returns: whether the set operation is successful.
*
* Set the array header of this single gram.
*
*/
bool set_array_header(/* in */ const ArrayHeader & header){
char * buf_begin = (char *)m_chunk.begin();
memcpy(buf_begin, &header, sizeof(ArrayHeader));
return true;
}
};
};
#endif
|
