summaryrefslogtreecommitdiffstats
path: root/tests/lookup/test_phrase_lookup.cpp
blob: 3d5fbec22ae58915fe81e2dc17a4f869b355c0ad (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
/* 
 *  libpinyin
 *  Library to deal with pinyin.
 *  
 *  Copyright (C) 2011 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 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 <locale.h>
#include "pinyin_internal.h"

void print_help(){
    printf("Usage: test_phrase_lookup\n");
}

bool try_phrase_lookup(PhraseLookup * phrase_lookup,
                       ucs4_t * ucs4_str, glong ucs4_len){
    char * result_string = NULL;
    MatchResults results = g_array_new(FALSE, FALSE, sizeof(phrase_token_t));
    phrase_lookup->get_best_match(ucs4_len, ucs4_str, results);
#if 0
    for ( size_t i = 0; i < results->len; ++i) {
        phrase_token_t * token = &g_array_index(results, phrase_token_t, i);
        if ( *token == null_token )
            continue;
        printf("%d:%d\t", i, *token);
    }
    printf("\n");
#endif
    phrase_lookup->convert_to_utf8(results, "\n", result_string);
    if (result_string)
        printf("%s\n", result_string);
    else
        fprintf(stderr, "Error: Un-segmentable sentence encountered!\n");
    g_array_free(results, TRUE);
    g_free(result_string);
    return true;
}

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

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


    /* init phrase table */
    FacadePhraseTable phrase_table;
    MemoryChunk * chunk = new MemoryChunk;
    chunk->load("../../data/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;

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

        phrase_index.load(i, chunk);
        g_free(filename);
    }

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

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

    /* try one 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';
        }

        if ( strcmp ( linebuf, "quit" ) == 0)
            break;

        /* 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 are not accepted.\n");
            g_free(sentence);
            continue;
        }

        try_phrase_lookup(&phrase_lookup, sentence, len);
        g_free(sentence);
    }

    free(linebuf);
    return 0;
}