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
|
/*
* libpinyin
* Library to deal with pinyin.
*
* Copyright (C) 2010 Peng Wu
*
* 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 02111-1307 USA
*/
#include "pinyin.h"
#include <stdio.h>
#include <assert.h>
#include <glib.h>
/* export interpolation model as textual format */
bool gen_unigram(FILE * output, FacadePhraseIndex * phrase_index);
bool gen_bigram(FILE * output, FacadePhraseIndex * phrase_index, Bigram * bigram);
bool begin_data(FILE * output){
fprintf(output, "\\data model interpolation\n");
return true;
}
bool end_data(FILE * output){
fprintf(output, "\\end\n");
return true;
}
int main(int argc, char * argv[]){
FILE * output = stdout;
const char * bigram_filename = "bigram.db";
FacadePhraseIndex phrase_index;
//gb_char binary file
MemoryChunk * chunk = new MemoryChunk;
chunk->load("gb_char.bin");
phrase_index.load(1, chunk);
//gbk_char binary file
chunk = new MemoryChunk;
chunk->load("gbk_char.bin");
phrase_index.load(2, chunk);
Bigram bigram;
bigram.attach(bigram_filename, ATTACH_READONLY);
begin_data(output);
gen_unigram(output, &phrase_index);
gen_bigram(output, &phrase_index, &bigram);
end_data(output);
return 0;
}
bool gen_unigram(FILE * output, FacadePhraseIndex * phrase_index) {
fprintf(output, "\\1-gram\n");
for ( size_t i = 0; i < PHRASE_INDEX_LIBRARY_COUNT; i++) {
PhraseIndexRange range;
int result = phrase_index->get_range(i, range);
if ( result )
continue;
PhraseItem item;
for ( size_t j = range.m_range_begin; j < range.m_range_end; j++) {
int result = phrase_index->get_phrase_item(j, item);
if ( result == ERROR_NO_ITEM )
continue;
assert( result == ERROR_OK);
size_t freq = item.get_unigram_frequency();
if ( 0 == freq )
continue;
char * phrase = taglib_token_to_string(phrase_index, j);
if ( phrase )
fprintf(output, "\\item %s count %ld\n", phrase, freq);
g_free(phrase);
}
}
return true;
}
bool gen_bigram(FILE * output, FacadePhraseIndex * phrase_index, Bigram * bigram){
fprintf(output, "\\2-gram\n");
/* Retrieve all user items. */
GArray * items = g_array_new(FALSE, FALSE, sizeof(phrase_token_t));
bigram->get_all_items(items);
PhraseItem item;
for(size_t i = 0; i < items->len; i++){
phrase_token_t token = g_array_index(items, phrase_token_t, i);
SingleGram * single_gram = NULL;
bigram->load(token, single_gram);
BigramPhraseWithCountArray array = g_array_new(FALSE, FALSE, sizeof(BigramPhraseItemWithCount));
single_gram->retrieve_all(array);
for(size_t j = 0; j < array->len; j++) {
BigramPhraseItemWithCount * item = &g_array_index(array, BigramPhraseItemWithCount, j);
char * word1 = taglib_token_to_string(phrase_index, token);
char * word2 = taglib_token_to_string(phrase_index, item->m_token);
guint32 freq = item->m_count;
if ( word1 && word2)
fprintf(output, "\\item %s %s count %d\n", word1, word2, freq);
g_free(word1); g_free(word2);
}
g_array_free(array, TRUE);
}
g_array_free(items, TRUE);
return true;
}
|
