From b8fd0c833bbd910a525d270ebc8f7e87ee00cb0a Mon Sep 17 00:00:00 2001 From: Micah Cowan Date: Thu, 7 Aug 2008 02:34:28 -0700 Subject: [PATCH] Width toggle for ambiguous East Asian chars, courtesy Yi-Hsuan Hsin (#16666). --- src/ansi.c | 2 +- src/comm.c | 3 ++ src/encoding.c | 113 +++++++++++++++++++++++++++++++++++++++++++++++++++------ src/process.c | 12 ++++++ src/screen.c | 20 ++++++++++ 5 files changed, 137 insertions(+), 13 deletions(-) diff --git a/src/ansi.c b/src/ansi.c index 674b548..7b888c5 100644 --- a/src/ansi.c +++ b/src/ansi.c @@ -681,7 +681,7 @@ register int len; curr->w_rend.font = 0; } # ifdef DW_CHARS - if (curr->w_encoding == UTF8 && c >= 0x1100 && utf8_isdouble(c)) + if (curr->w_encoding == UTF8 && utf8_isdouble(c)) curr->w_mbcs = 0xff; # endif if (curr->w_encoding == UTF8 && c >= 0x0300 && utf8_iscomb(c)) diff --git a/src/comm.c b/src/comm.c index 1f61205..02337f0 100644 --- a/src/comm.c +++ b/src/comm.c @@ -112,6 +112,9 @@ struct comm comms[RC_LAST + 1] = #endif { "charset", NEED_FORE|ARGS_1 }, { "chdir", ARGS_01 }, +#ifdef DW_CHARS + { "cjkwidth", ARGS_01 }, +#endif { "clear", NEED_FORE|ARGS_0 }, { "colon", NEED_LAYER|ARGS_01 }, { "command", NEED_DISPLAY|ARGS_02 }, diff --git a/src/encoding.c b/src/encoding.c index e72057c..cdd411f 100644 --- a/src/encoding.c +++ b/src/encoding.c @@ -35,6 +35,10 @@ extern struct layer *flayer; extern char *screenencodings; +#ifdef DW_CHARS +extern int cjkwidth; +#endif + static int encmatch __P((char *, char *)); # ifdef UTF8 static int recode_char __P((int, int, int)); @@ -845,22 +849,107 @@ int encoding; } #ifdef DW_CHARS +struct interval { + int first; + int last; +}; + +/* auxiliary function for binary search in interval table */ +static int bisearch(int ucs, const struct interval *table, int max) { + int min = 0; + int mid; + + if (ucs < table[0].first || ucs > table[max].last) + return 0; + while (max >= min) { + mid = (min + max) / 2; + if (ucs > table[mid].last) + min = mid + 1; + else if (ucs < table[mid].first) + max = mid - 1; + else + return 1; + } + + return 0; +} + int utf8_isdouble(c) int c; { - return - (c >= 0x1100 && - (c <= 0x115f || /* Hangul Jamo init. consonants */ - (c >= 0x2e80 && c <= 0xa4cf && (c & ~0x0011) != 0x300a && - c != 0x303f) || /* CJK ... Yi */ - (c >= 0xac00 && c <= 0xd7a3) || /* Hangul Syllables */ - (c >= 0xdf00 && c <= 0xdfff) || /* dw combining sequence */ - (c >= 0xf900 && c <= 0xfaff) || /* CJK Compatibility Ideographs */ - (c >= 0xfe30 && c <= 0xfe6f) || /* CJK Compatibility Forms */ - (c >= 0xff00 && c <= 0xff5f) || /* Fullwidth Forms */ - (c >= 0xffe0 && c <= 0xffe6) || - (c >= 0x20000 && c <= 0x2ffff))); + /* sorted list of non-overlapping intervals of East Asian Ambiguous + * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */ + static const struct interval ambiguous[] = { + { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 }, + { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 }, + { 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 }, + { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 }, + { 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED }, + { 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA }, + { 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 }, + { 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B }, + { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 }, + { 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 }, + { 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 }, + { 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE }, + { 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 }, + { 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA }, + { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 }, + { 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB }, + { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB }, + { 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 }, + { 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 }, + { 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 }, + { 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 }, + { 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 }, + { 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 }, + { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 }, + { 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC }, + { 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 }, + { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 }, + { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 }, + { 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 }, + { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 }, + { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 }, + { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B }, + { 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 }, + { 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 }, + { 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E }, + { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 }, + { 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 }, + { 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F }, + { 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 }, + { 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF }, + { 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B }, + { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 }, + { 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 }, + { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 }, + { 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 }, + { 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 }, + { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 }, + { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 }, + { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 }, + { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F }, + { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF }, + { 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD } + }; + + return ((c >= 0x1100 && + (c <= 0x115f || /* Hangul Jamo init. consonants */ + c == 0x2329 || c == 0x232a || + (c >= 0x2e80 && c <= 0xa4cf && + c != 0x303f) || /* CJK ... Yi */ + (c >= 0xac00 && c <= 0xd7a3) || /* Hangul Syllables */ + (c >= 0xf900 && c <= 0xfaff) || /* CJK Compatibility Ideographs */ + (c >= 0xfe30 && c <= 0xfe6f) || /* CJK Compatibility Forms */ + (c >= 0xff00 && c <= 0xff60) || /* Fullwidth Forms */ + (c >= 0xffe0 && c <= 0xffe6) || + (c >= 0x20000 && c <= 0x2fffd) || + (c >= 0x30000 && c <= 0x3fffd))) || + (cjkwidth && + bisearch(c, ambiguous, + sizeof(ambiguous) / sizeof(struct interval) - 1))); } #endif diff --git a/src/process.c b/src/process.c index 11f2e86..0da7b35 100644 --- a/src/process.c +++ b/src/process.c @@ -105,6 +105,9 @@ extern int VerboseCreate; #ifdef UTF8 extern char *screenencodings; #endif +#ifdef DW_CHARS +extern int cjkwidth; +#endif static int CheckArgNum __P((int, char **)); static void ClearAction __P((struct action *)); @@ -4181,6 +4184,15 @@ int key; else Msg(0, "unknown layout subcommand"); break; +#ifdef DW_CHARS + case RC_CJKWIDTH: + if(ParseSwitch(act, &cjkwidth) == 0) + { + if(msgok) + Msg(0, "Treat ambiguous width characters as %s width", cjkwidth ? "full" : "half"); + } + break; +#endif default: #ifdef HAVE_BRAILLE /* key == -2: input from braille keybord, msgok always 0 */ diff --git a/src/screen.c b/src/screen.c index 524206e..49e7194 100644 --- a/src/screen.c +++ b/src/screen.c @@ -223,6 +223,10 @@ char *preselect = NULL; /* only used in Attach() */ char *screenencodings; #endif +#ifdef DW_CHARS +int cjkwidth; +#endif + #ifdef NETHACK int nethackflag = 0; #endif @@ -471,6 +475,9 @@ char **av; InitBuiltinTabs(); screenencodings = SaveStr(SCREENENCODINGS); #endif +#ifdef DW_CHARS + cjkwidth = 0; +#endif nwin = nwin_undef; nwin_options = nwin_undef; strcpy(screenterm, "screen"); @@ -765,6 +772,19 @@ char **av; debug1("environment says encoding=%d\n", nwin_options.encoding); #endif } +# ifdef DW_CHARS + { + char *s; + if((s = getenv("LC_ALL")) || (s = getenv("LC_CTYPE")) || + (s = getenv("LANG"))) + { + if(!strncmp(s, "zh_", 3) || !strncmp(s, "ja_", 3) || !strncmp(s, "ko_", 3)) + { + cjkwidth = 1; + } + } + } +#endif #endif if (SockMatch && strlen(SockMatch) >= MAXSTR) Panic(0, "Ridiculously long socketname - try again."); -- 2.11.4.GIT