summaryrefslogtreecommitdiffstats
path: root/utils/segment/ngseg.cpp
blob: 25b9361c29ebfbcde57f835608953eb66acadaa9 (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
/* 
 *  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., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

#include <stdio.h>
#include <stdlib.h>
#include <locale.h>
#include "pinyin_internal.h"

/* n-gram based sentence segment. */

/* Note:
 * Currently libpinyin supports ucs4 characters.
 * This is a pre-processor tool for raw corpus,
 * and skips non-Chinese characters.
 */

/* TODO:
 * Try to add punctuation mark and english support,
 * such as ',', '.', '?', '!', <english>, and other punctuations.
 */

enum CONTEXT_STATE{
    CONTEXT_INIT,
    CONTEXT_SEGMENTABLE,
    CONTEXT_UNKNOWN
};

void print_help(){
    printf("Usage: ngseg [--generate-extra-enter]\n");
}

bool deal_with_segmentable(PhraseLookup * phrase_lookup,
                           GArray * current_ucs4){
    char * result_string = NULL;
    MatchResults results = g_array_new(FALSE, FALSE, sizeof(phrase_token_t));
    phrase_lookup->get_best_match(current_ucs4->len,
                                  (ucs4_t *) current_ucs4->data, results);

    phrase_lookup->convert_to_utf8(results, "\n", result_string);

    if (result_string) {
        printf("%s\n", result_string);
    } else {
        char * tmp_string = g_ucs4_to_utf8
            ( (ucs4_t *) current_ucs4->data, current_ucs4->len,
              NULL, NULL, NULL);
        fprintf(stderr, "Un-segmentable sentence encountered:%s\n",
                tmp_string);
        g_array_free(results, TRUE);
        return false;
    }
    g_array_free(results, TRUE);
    g_free(result_string);
    return true;
}

bool deal_with_unknown(GArray * current_ucs4){
    char * result_string = g_ucs4_to_utf8
        ( (ucs4_t *) current_ucs4->data, current_ucs4->len,
          NULL, NULL, NULL);
    printf("%s\n", result_string);
    g_free(result_string);
    return true;
}


int main(int argc, char * argv[]){
    int i = 1;
    bool gen_extra_enter = false;

    setlocale(LC_ALL, "");
    /* deal with options */
    while ( i < argc ){
        if ( strcmp ("--help", argv[i]) == 0 ){
            print_help();
            exit(0);
        } else if ( strcmp("--generate-extra-enter", argv[i]) == 0 ){
            gen_extra_enter = true;
        } else {
            print_help();
            exit(EINVAL);
        }
        ++i;
    }

    /* init phrase table */
    FacadePhraseTable phrase_table;
    MemoryChunk * chunk = new MemoryChunk;
    chunk->load("phrase_index.bin");
    phrase_table.load(chunk, NULL);

    /* init phrase index */
    FacadePhraseIndex phrase_index;
    for (size_t i = 0; i < PHRASE_INDEX_LIBRARY_COUNT; ++i) {
        const char * bin_file = pinyin_phrase_files[i];
        if (NULL == bin_file)
            continue;

        chunk = new MemoryChunk;
        bool retval = chunk->load(bin_file);
        if (!retval) {
            fprintf(stderr, "open %s failed!\n", bin_file);
            exit(ENOENT);
        }

        phrase_index.load(i, chunk);
    }

    /* init bi-gram */
    Bigram system_bigram;
    system_bigram.attach("bigram.db", ATTACH_READONLY);
    Bigram user_bigram;

    /* init phrase lookup */
    PhraseLookup phrase_lookup(&phrase_table, &phrase_index,
                               &system_bigram, &user_bigram);


    CONTEXT_STATE state, next_state;
    GArray * current_ucs4 = g_array_new(TRUE, TRUE, sizeof(ucs4_t));
    phrase_token_t token = null_token;

    /* split the sentence */
    char * linebuf = NULL; size_t size = 0; ssize_t read;
    while( (read = getline(&linebuf, &size, stdin)) != -1 ){
        if ( '\n' ==  linebuf[strlen(linebuf) - 1] ) {
            linebuf[strlen(linebuf) - 1] = '\0';
        }

        /* check non-ucs4 characters */
        const glong num_of_chars = g_utf8_strlen(linebuf, -1);
        glong len = 0;
        ucs4_t * sentence = g_utf8_to_ucs4(linebuf, -1, NULL, &len, NULL);
        if ( len != num_of_chars ) {
            fprintf(stderr, "non-ucs4 characters encountered:%s.\n", linebuf);
            printf("\n");
            continue;
        }

        /* only new-line persists. */
        if ( 0  == num_of_chars ) {
            printf("\n");
            continue;
        }

        state = CONTEXT_INIT;
        bool result = phrase_table.search( 1, sentence, token);
        g_array_append_val( current_ucs4, sentence[0]);
        if ( result & SEARCH_OK )
            state = CONTEXT_SEGMENTABLE;
        else
            state = CONTEXT_UNKNOWN;

        for ( int i = 1; i < num_of_chars; ++i) {
            bool result = phrase_table.search( 1, sentence + i, token);
            if ( result & SEARCH_OK )
                next_state = CONTEXT_SEGMENTABLE;
            else
                next_state = CONTEXT_UNKNOWN;

            if ( state == next_state ){
                g_array_append_val(current_ucs4, sentence[i]);
                continue;
            }

            assert ( state != next_state );
            if ( state == CONTEXT_SEGMENTABLE )
                deal_with_segmentable(&phrase_lookup, current_ucs4);

            if ( state == CONTEXT_UNKNOWN )
                deal_with_unknown(current_ucs4);

            /* save the current character */
            g_array_set_size(current_ucs4, 0);
            g_array_append_val(current_ucs4, sentence[i]);
            state = next_state;
        }

        if ( current_ucs4->len ) {
            /* this seems always true. */
            if ( state == CONTEXT_SEGMENTABLE )
                deal_with_segmentable(&phrase_lookup, current_ucs4);

            if ( state == CONTEXT_UNKNOWN )
                deal_with_unknown(current_ucs4);
            g_array_set_size(current_ucs4, 0);
        }

        /* print extra enter */
        if ( gen_extra_enter )
            printf("\n");
    }

    /* print enter at file tail */
    printf("\n");
    g_array_free(current_ucs4, TRUE);
    free(linebuf);
    return 0;
}