summaryrefslogtreecommitdiffstats
path: root/src/ZYTradSimpConverter.cc
blob: e7548e0507ebd6ab76064bb821816862d39a382f (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
/* vim:set et ts=4 sts=4:
 *
 * ibus-libzhuyin - New Zhuyin engine based on libzhuyin for IBus
 *
 * Copyright (c) 2014 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, 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.
 */

#ifdef HAVE_CONFIG_H
#  include "config.h"
#endif

#include "ZYTradSimpConverter.h"

#ifdef HAVE_OPENCC
#  include <opencc.h>
#else
#  include <cstring>
#  include <cstdlib>
#endif

#include "ZYTypes.h"
#include "ZYString.h"

namespace ZY {

#ifdef HAVE_OPENCC

class opencc {
public:
    opencc (void)
    {
        m_cc = opencc_open (OPENCC_DEFAULT_CONFIG_TRAD_TO_SIMP);
        g_assert (m_cc != NULL);
    }

    ~opencc (void)
    {
        opencc_close (m_cc);
    }

    void convert (const gchar *in, String &out)
    {
        char * converted = opencc_convert_utf8 (m_cc, in, -1);
        g_assert (converted != NULL);
        out = converted;
        opencc_convert_utf8_free (converted);
    }

private:
    opencc_t m_cc;
};

void
TradSimpConverter::tradToSimp (const gchar *in, String &out)
{
    static opencc cc;
    cc.convert (in, out);
}

#else

static gint _xcmp (const gchar *p1, const gchar *p2, const gchar *str)
{
    for (;;) {
        // both reach end
        if (p1 == p2 && *str == '\0')
            return 0;
        // p1 reaches end
        if (p1 == p2)
            return -1;
        // str reaches end
        if (*str == '\0')
            return 1;

        if (*p1 < *str)
            return -1;
        if (*p1 > *str)
            return 1;

        p1 ++; str ++;
    };
}

static gint _cmp (gconstpointer p1, gconstpointer p2)
{
    const gchar **pp = (const gchar **) p1;
    const gchar **s2 = (const gchar **) p2;

    return _xcmp (pp[0], pp[1], s2[0]);
}

#include "ZYTradSimpConverterTable.h"

void
TradSimpConverter::tradToSimp (const gchar *in, String &out)
{
    const gchar *pend;
    const gchar *pp[2];
    glong len;
    glong begin;

    if (!g_utf8_validate (in, -1 , NULL)) {
        g_warning ("\%s\" is not an utf8 string!", in);
        g_assert_not_reached ();
    }

    begin = 0;
    pend = in + std::strlen (in);
    len = g_utf8_strlen (in, -1);   // length in charactoers
    pp[0] = in;

    while (pp[0] != pend) {
        glong slen  = std::min (len - begin, (glong) TRAD_TO_SIMP_MAX_LEN); // the length of sub string in character
        pp[1] = g_utf8_offset_to_pointer (pp[0], slen);    // the end of sub string

        for (;;) {
            const gchar **result;
            result = (const gchar **) std::bsearch (pp, trad_to_simp,
                                            G_N_ELEMENTS (trad_to_simp), sizeof (trad_to_simp[0]),
                                            _cmp);

            if (result != NULL) {
                // found item in table,
                // append the trad to out and adjust pointers
                out << result[1];
                pp[0] = pp[1];
                begin += slen;
                break;
            }

            if (slen == 1) {
                // if only one character left,
                // append origin character to out and adjust pointers
                out.append (pp[0], pp[1] - pp[0]);
                pp[0] = pp[1];
                begin += 1;
                break;
            }

            // if more than on characters left,
            // adjust pp[1] to previous character
            pp[1] = g_utf8_prev_char (pp[1]);
            slen--;
        }
    }
}

#endif

};