3 * Library to deal with pinyin.
5 * Copyright (C) 2011 Peng Wu <alexepico@gmail.com>
7 * This program is free software; you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation; either version 2 of the License, or
10 * (at your option) any later version.
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with this program; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
27 #include "pinyin_custom2.h"
28 #include "chewing_key.h"
29 #include "pinyin_parser2.h"
30 #include "pinyin_parser_table.h"
33 using namespace pinyin;
35 static bool check_pinyin_options(guint32 options, const pinyin_index_item_t * item) {
36 guint32 flags = item->m_flags;
37 assert (flags & IS_PINYIN);
39 /* handle incomplete pinyin. */
40 if (flags & PINYIN_INCOMPLETE) {
41 if (!(options & PINYIN_INCOMPLETE))
45 /* handle correct pinyin, currently only one flag per item. */
46 flags &= PINYIN_CORRECT_ALL;
47 options &= PINYIN_CORRECT_ALL;
50 if ((flags & options) != flags)
57 static bool check_chewing_options(guint32 options, const chewing_index_item_t * item) {
58 guint32 flags = item->m_flags;
59 assert (flags & IS_CHEWING);
61 /* handle incomplete chewing. */
62 if (flags & CHEWING_INCOMPLETE) {
63 if (!(options & CHEWING_INCOMPLETE))
71 /* methods for Chewing Keys to access pinyin parser table. */
72 const char * ChewingKeyRest::get_pinyin_string(){
73 if (m_table_index == 0)
76 /* check end boundary. */
77 assert(m_table_index < G_N_ELEMENTS(content_table));
78 return content_table[m_table_index].m_pinyin_str;
81 const char * ChewingKeyRest::get_chewing_string(){
82 if (m_table_index == 0)
85 /* check end boundary. */
86 assert(m_table_index < G_N_ELEMENTS(content_table));
87 return content_table[m_table_index].m_chewing_str;
91 static bool compare_less_than(const pinyin_index_item_t & lhs,
92 const pinyin_index_item_t & rhs){
93 return 0 > strcmp(lhs.m_pinyin_input, rhs.m_pinyin_input);
96 int FullPinyinParser2::parse_one_key (guint32 options, ChewingKey & key,
97 ChewingKeyRest & key_rest,
98 const char * pinyin, int len) const {
99 /* "'" are not accepted in parse_one_key. */
100 assert(NULL == strchr(pinyin, '\''));
101 gchar * input = g_strndup(pinyin, len);
103 guint16 tone = CHEWING_ZERO_TONE; guint16 tone_pos = 0;
104 guint16 parsed_len = len;
105 key = ChewingKey(); key_rest = ChewingKeyRest();
107 /* find the tone in the last character. */
108 char chr = input[parsed_len - 1];
109 if ( '0' < chr && chr <= '5' ) {
112 tone_pos = parsed_len;
115 /* parse pinyin core staff here. */
116 pinyin_index_item_t item;
117 memset(&item, 0, sizeof(item));
119 for (; parsed_len > 0; --parsed_len) {
120 input[parsed_len] = '\0';
121 item.m_pinyin_input = input;
122 std_lite::pair<const pinyin_index_item_t *,
123 const pinyin_index_item_t *> range;
124 range = std_lite::equal_range
125 (pinyin_index, pinyin_index + G_N_ELEMENTS(pinyin_index),
126 item, compare_less_than);
128 guint16 len = range.second - range.first;
131 const pinyin_index_item_t * index = range.first;
133 if (!check_pinyin_options(options, index))
136 key_rest.m_table_index = index->m_table_index;
137 key = content_table[key_rest.m_table_index].m_chewing_key;
142 /* post processing tone. */
143 if ( parsed_len == tone_pos ) {
144 if (tone != CHEWING_ZERO_TONE) {
150 key_rest.m_raw_begin = 0; key_rest.m_raw_end = parsed_len;
156 int FullPinyinParser2::parse (guint32 options, ChewingKeyVector & keys,
157 ChewingKeyRestVector & key_rests,
158 const char *str, int len) const {