11 typedef struct convert_key convert_key;
19 static const convert_key s2j_table[] = {
20 {"mb","nb"}, {"mp","np"}, {"mv","nv"}, {"mm","nm"},
22 /* sindar:シンダール parantir:パランティア feanor:フェアノール */
23 {"ar$","a-ru$"}, {"ir$","ia$"}, {"or$","o-ru$"},
24 {"ra","ラ"}, {"ri","リ"}, {"ru","ル"}, {"re","レ"}, {"ro","ロ"},
25 {"ir","ia"}, {"ur","ua"}, {"er","ea"}, {"ar","aル"},
26 {"sha","シャ"}, {"shi","シ"}, {"shu","シュ"}, {"she","シェ"}, {"sho","ショ"},
27 {"tha","サ"}, {"thi","シ"}, {"thu","ス"}, {"the","セ"}, {"tho","ソ"},
28 {"cha","ハ"}, {"chi","ヒ"}, {"chu","フ"}, {"che","ヘ"}, {"cho","ホ"},
29 {"dha","ザ"}, {"dhi","ジ"}, {"dhu","ズ"}, {"dhe","ゼ"}, {"dho","ゾ"},
30 {"ba","バ"}, {"bi","ビ"}, {"bu","ブ"}, {"be","ベ"}, {"bo","ボ"},
31 {"ca","カ"}, {"ci","キ"}, {"cu","ク"}, {"ce","ケ"}, {"co","コ"},
32 {"da","ダ"}, {"di","ディ"}, {"du","ドゥ"}, {"de","デ"}, {"do","ド"},
33 {"fa","ファ"}, {"fi","フィ"}, {"fu","フ"}, {"fe","フェ"}, {"fo","フォ"},
34 {"ga","ガ"}, {"gi","ギ"}, {"gu","グ"}, {"ge","ゲ"}, {"go","ゴ"},
35 {"ha","ハ"}, {"hi","ヒ"}, {"hu","フ"}, {"he","ヘ"}, {"ho","ホ"},
36 {"ja","ジャ"}, {"ji","ジ"}, {"ju","ジュ"}, {"je","ジェ"}, {"jo","ジョ"},
37 {"ka","カ"}, {"ki","キ"}, {"ku","ク"}, {"ke","ケ"}, {"ko","コ"},
38 {"la","ラ"}, {"li","リ"}, {"lu","ル"}, {"le","レ"}, {"lo","ロ"},
39 {"ma","マ"}, {"mi","ミ"}, {"mu","ム"}, {"me","メ"}, {"mo","モ"},
40 {"na","ナ"}, {"ni","ニ"}, {"nu","ヌ"}, {"ne","ネ"}, {"no","ノ"},
41 {"pa","パ"}, {"pi","ピ"}, {"pu","プ"}, {"pe","ペ"}, {"po","ポ"},
43 {"sa","サ"}, {"si","シ"}, {"su","ス"}, {"se","セ"}, {"so","ソ"},
44 {"ta","タ"}, {"ti","ティ"}, {"tu","トゥ"}, {"te","テ"}, {"to","ト"},
45 {"va","ヴァ"}, {"vi","ヴィ"}, {"vu","ヴ"}, {"ve","ヴェ"}, {"vo","ヴォ"},
46 {"wa","ワ"}, {"wi","ウィ"}, {"wu","ウ"}, {"we","ウェ"}, {"wo","ウォ"},
47 {"ya","ヤ"}, {"yu","ユ"}, {"yo","ヨ"},
48 {"za","ザ"}, {"zi","ジ"}, {"zu","ズ"}, {"ze","ゼ"}, {"zo","ゾ"},
49 {"dh","ズ"}, {"ch","フ"}, {"th","ス"},
50 {"b","ブ"}, {"c","ク"}, {"d","ド"}, {"f","フ"}, {"g","グ"},
51 {"h","フ"}, {"j","ジュ"}, {"k","ク"}, {"l","ル"}, {"m","ム"},
52 {"n","ン"}, {"p","プ"}, {"q","ク"}, {"r","ル"}, {"s","ス"},
53 {"t","ト"}, {"v","ヴ"}, {"w","ウ"}, {"y","イ"},
54 {"a","ア"}, {"i","イ"}, {"u","ウ"}, {"e","エ"}, {"o","オ"},
60 * @brief シンダリンを日本語の読みに変換する
61 * @param kana 変換後の日本語文字列ポインタ
62 * @param sindarin 変換前のシンダリン文字列ポインタ
66 void sindarin_to_kana(char *kana, const char *sindarin)
71 sprintf(kana, "%s$", sindarin);
72 for (idx = 0; kana[idx]; idx++)
73 if (isupper(kana[idx])) kana[idx] = (char)tolower(kana[idx]);
75 for (idx = 0; s2j_table[idx].key1 != NULL; idx++)
77 cptr pat1 = s2j_table[idx].key1;
78 cptr pat2 = s2j_table[idx].key2;
79 int len = strlen(pat1);
85 if (strncmp(src, pat1, len) == 0)
111 while (kana[idx] != '$') idx++;
117 /*! 日本語動詞活用 (打つ>打って,打ち etc)
118 * JVERB_AND: 殴る,蹴る > 殴り,蹴る
119 * JVERB_TO: 殴る,蹴る > 殴って蹴る
120 * JVERB_OR: 殴る,蹴る > 殴ったり蹴ったり */
121 static const struct jverb_table_t {
125 { "する", {"し", "して", "した"}},
126 { "いる", {"いて", "いて", "いた"}},
128 { "える", {"え", "えて", "えた"}},
129 { "ける", {"け", "けて", "けた"}},
130 { "げる", {"げ", "えて", "げた"}},
131 { "せる", {"せ", "せて", "せた"}},
132 { "ぜる", {"ぜ", "ぜて", "ぜた"}},
133 { "てる", {"て", "てって", "てった"}},
134 { "でる", {"で", "でて", "でた"}},
135 { "ねる", {"ね", "ねて", "ねた"}},
136 { "へる", {"へ", "へて", "へた"}},
137 { "べる", {"べ", "べて", "べた"}},
138 { "める", {"め", "めて", "めた"}},
139 { "れる", {"れ", "れて", "れた"}},
141 { "う", {"い", "って", "った"}},
142 { "く", {"き", "いて", "いた"}},
143 { "ぐ", {"ぎ", "いで", "いだ"}},
144 { "す", {"し", "して", "した"}},
145 { "ず", {"じ", "じて", "じた"}},
146 { "つ", {"ち", "って", "った"}},
147 { "づ", {"ぢ", "って", "った"}},
148 { "ぬ", {"に", "ねて", "ねた"}},
149 { "ふ", {"ひ", "へて", "へた"}},
150 { "ぶ", {"び", "んで", "んだ"}},
151 { "む", {"み", "んで", "んだ"}},
152 { "る", {"り", "って", "った"}},
153 { NULL, {"そして", "ことにより", "ことや"}},
157 * @brief jverb_table_tに従って動詞を活用する
158 * @param in 変換元文字列ポインタ
159 * @param out 変換先文字列ポインタ
160 * @param flag 変換種類を指定(JVERB_AND/JVERB_TO/JVERB_OR)
164 void jverb(const char *in, char *out, int flag)
166 const struct jverb_table_t * p;
167 int in_len = strlen(in);
171 for (p = jverb_table; p->from; p++) {
172 int from_len = strlen(p->from);
173 if (strncmp(&in[in_len-from_len], p->from, from_len) == 0) {
174 strcpy(&out[in_len - from_len], p->to[flag - 1]);
180 strcpy(&out[in_len], p->to[flag - 1]);
184 * @brief 文字コードをSJISからEUCに変換する / Convert SJIS string to EUC string
185 * @param str 変換する文字列のポインタ
189 void sjis2euc(char *str)
192 unsigned char c1, c2;
195 int len = strlen(str);
197 C_MAKE(tmp, len+1, byte);
199 for (i = 0; i < len; i++)
208 c1 = c1 * 2 - (c1 >= 0xe0 ? 0xe0 : 0x60);
213 c1 = c1 * 2 - (c1 >= 0xe0 ? 0xe1 : 0x61);
214 c2 += 0x60 + (c2 < 0x7f);
223 strcpy(str, (char *)tmp);
225 C_KILL(tmp, len+1, byte);
230 * @brief 文字コードをEUCからSJISに変換する / Convert EUC string to SJIS string
231 * @param str 変換する文字列のポインタ
235 void euc2sjis(char *str)
238 unsigned char c1, c2;
241 int len = strlen(str);
243 C_MAKE(tmp, len+1, byte);
245 for (i = 0; i < len; i++)
254 c1 = (c1 >> 1) + (c1 < 0xdf ? 0x31 : 0x71);
255 c2 -= 0x60 + (c2 < 0xe0);
259 c1 = (c1 >> 1) + (c1 < 0xdf ? 0x30 : 0x70);
270 strcpy(str, (char *)tmp);
272 C_KILL(tmp, len+1, byte);
277 * @brief strを環境に合った文字コードに変換し、変換前の文字コードを返す。strの長さに制限はない。
278 * @param str 変換する文字列のポインタ
281 * 1: ASCII (Never known to be ASCII in this function.)<br>
285 byte codeconv(char *str)
290 for (i = 0; str[i]; i++)
299 if (!(c1 & 0x80)) continue;
305 if (((0xa1 <= c1 && c1 <= 0xdf) || (0xfd <= c1 && c1 <= 0xfe)) &&
306 (0xa1 <= c2 && c2 <= 0xfe))
308 /* Only EUC is allowed */
323 else if (((0x81 <= c1 && c1 <= 0x9f) &&
324 ((0x40 <= c2 && c2 <= 0x7e) || (0x80 <= c2 && c2 <= 0xfc))) ||
325 ((0xe0 <= c1 && c1 <= 0xfc) &&
326 (0x40 <= c2 && c2 <= 0x7e)))
328 /* Only SJIS is allowed */
363 /* Return kanji code */
368 * @brief 文字列sのxバイト目が漢字の1バイト目かどうか判定する
369 * @param s 判定する文字列のポインタ
370 * @param x 判定する位置(バイト)
371 * @return 漢字の1バイト目ならばTRUE
373 bool iskanji2(cptr s, int x)
377 for (i = 0; i < x; i++)
379 if (iskanji(s[i])) i++;
381 if ((x == i) && iskanji(s[x])) return TRUE;
387 * @brief 文字列の文字コードがASCIIかどうかを判定する
388 * @param str 判定する文字列へのポインタ
389 * @return 文字列の文字コードがASCIIならTRUE、そうでなければFALSE
391 static bool is_ascii_str(cptr str)
394 if (!(0x00 < *str && *str <= 0x7f))
401 * @brief 文字列の文字コードがUTF-8かどうかを判定する
402 * @param str 判定する文字列へのポインタ
403 * @return 文字列の文字コードがUTF-8ならTRUE、そうでなければFALSE
405 static bool is_utf8_str(cptr str)
407 const unsigned char* p;
408 for (p = (const unsigned char*)str; *p; p++) {
410 if (0x00 < *p && *p <= 0x7f) continue;
412 if ((*p & 0xe0) == 0xc0) subseq_num = 1;
413 if ((*p & 0xf0) == 0xe0) subseq_num = 2;
414 if ((*p & 0xf8) == 0xf0) subseq_num = 3;
416 if (subseq_num == 0) return FALSE;
417 while (subseq_num--) {
419 if (!*p || (*p & 0xc0) != 0x80) return FALSE;
428 static const struct ms_to_jis_unicode_conv_t {
431 } ms_to_jis_unicode_conv[] = {
432 {{0xef, 0xbd, 0x9e}, {0xe3, 0x80, 0x9c}}, /* FULLWIDTH TILDE -> WAVE DASH */
433 {{0xef, 0xbc, 0x8d}, {0xe2, 0x88, 0x92}}, /* FULLWIDTH HYPHEN-MINUS -> MINUS SIGN */
437 * @brief EUCがシステムコードである環境下向けにUTF-8から変換処理を行うサブルーチン
438 * @param str 変換する文字列のポインタ
441 static void ms_to_jis_unicode(char* str)
444 for (p = (unsigned char*)str; *p; p++) {
446 if (0x00 < *p && *p <= 0x7f) continue;
448 if ((*p & 0xe0) == 0xc0) subseq_num = 1;
449 if ((*p & 0xf0) == 0xe0) {
451 for (i = 0; i < sizeof(ms_to_jis_unicode_conv) / sizeof(ms_to_jis_unicode_conv[0]); ++ i) {
452 const struct ms_to_jis_unicode_conv_t *c = &ms_to_jis_unicode_conv[i];
453 if (memcmp(p, c->from, 3) == 0) {
459 if ((*p & 0xf8) == 0xf0) subseq_num = 3;
465 #elif defined(SJIS) && defined(WINDOWS)
469 * @brief 文字コードがUTF-8の文字列をシステムの文字コードに変換する
470 * @param utf8_str 変換するUTF-8の文字列へのポインタ
471 * @param sys_str_buffer 変換したシステムの文字コードの文字列を格納するバッファへのポインタ
472 * @param sys_str_buflen 変換したシステムの文字コードの文字列を格納するバッファの長さ
473 * @return 変換に成功した場合TRUE、失敗した場合FALSEを返す
475 static bool utf8_to_sys(char* utf8_str, char* sys_str_buffer, size_t sys_str_buflen)
479 iconv_t cd = iconv_open("EUC-JP", "UTF-8");
480 size_t utf8_len = strlen(utf8_str) + 1; /* include termination character */
481 char *from = utf8_str;
484 ms_to_jis_unicode(utf8_str);
485 ret = iconv(cd, &from, &utf8_len, &sys_str_buffer, &sys_str_buflen);
489 #elif defined(SJIS) && defined(WINDOWS)
492 int input_len = strlen(utf8_str) + 1; /* include termination character */
494 C_MAKE(utf16buf, input_len, WCHAR);
496 /* UTF-8 -> UTF-16 */
497 if (MultiByteToWideChar( CP_UTF8, 0, utf8_str, input_len, utf16buf, input_len) == 0) {
498 C_KILL(utf16buf, input_len, WCHAR);
502 /* UTF-8 -> SJIS(CP932) */
503 if (WideCharToMultiByte( CP_ACP, 0, utf16buf, -1, sys_str_buffer, sys_str_buflen, NULL, NULL ) == 0) {
504 C_KILL(utf16buf, input_len, WCHAR);
508 C_KILL(utf16buf, input_len, WCHAR);
515 * @brief 受け取った文字列の文字コードを推定し、システムの文字コードへ変換する
516 * @param strbuf 変換する文字列を格納したバッファへのポインタ。
517 * バッファは変換した文字列で上書きされる。
518 * UTF-8からSJISもしくはEUCへの変換を想定しているのでバッファの長さが足りなくなることはない。
519 * @param buflen バッファの長さ。
522 void guess_convert_to_system_encoding(char* strbuf, int buflen)
524 if (is_ascii_str(strbuf)) return;
526 if (is_utf8_str(strbuf)) {
528 C_MAKE(work, buflen, char);
529 my_strcpy(work, strbuf, buflen);
530 if (!utf8_to_sys(work, strbuf, buflen)) {
531 msg_print("警告:文字コードの変換に失敗しました");
534 C_KILL(work, buflen, char);