Various character set additions and tweaks. [rsc] --rw-rw-r-- M 1372441 rsc sys 5244 Jan 27 11:58 sys/src/cmd/tcs/html.c /n/sourcesdump/2006/0127/plan9/sys/src/cmd/tcs/html.c:324,330 - /n/sourcesdump/2006/0128/plan9/sys/src/cmd/tcs/html.c:324,330 else if((s = findbyrune(*r)) != nil) Bprint(&b, "&%s;", s); else - Bprint(&b, "&#x%04x;", *r); + Bprint(&b, "&#%d;", *r); } Bflush(&b); } [rsc] --rw-r--r-- M 1372441 rsc sys 16466 Jan 27 12:26 sys/src/cmd/tcs/8859.h [rsc] --rw-rw-r-- M 1372441 glenda sys 7921 Jan 27 12:26 sys/src/cmd/tcs/cyrillic.h /n/sourcesdump/2006/0127/plan9/sys/src/cmd/tcs/cyrillic.h:106,138 - /n/sourcesdump/2006/0128/plan9/sys/src/cmd/tcs/cyrillic.h:106,111 0x0401,0x0451,0x0301,0x0300,0x0301,0x0300,0x2192,0x2190, 0x2193,0x2191,0x00f7,0x00b1,0x2116,0x00a4, -1, -1, }; - long tabcp1251[256] = - { - 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f, - 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f, - 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27,0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f, - 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f, - 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f, - 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57,0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f, - 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f, - 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f, - 0x0402,0x0403,0x201a,0x0453,0x201e,0x2026,0x2020,0x2021, - -1,0x2030,0x0409,0x2039,0x040a,0x040c,0x040b,0x040f, - 0x0452,0x2018,0x2019,0x201c,0x201d,0x2022,0x2013,0x2014, - -1,0x2122,0x0459,0x203a,0x045a,0x045c,0x045b,0x045f, - 0x00a0,0x040e,0x045e,0x0408,0x00a4,0x0490,0x00a6,0x00a7, - 0x0401,0x00a9,0x0404,0x00ab,0x00ac,0x00ad,0x00ae,0x0407, - 0x00b0,0x00b1,0x0406,0x0456,0x0491,0x00b5,0x00b6,0x00b7, - 0x0451,0x2116,0x0454,0x00bb,0x0458,0x0405,0x0455,0x0457, - 0x0410,0x0411,0x0412,0x0413,0x0414,0x0415,0x0416,0x0417, - 0x0418,0x0419,0x041a,0x041b,0x041c,0x041d,0x041e,0x041f, - 0x0420,0x0421,0x0422,0x0423,0x0424,0x0425,0x0426,0x0427, - 0x0428,0x0429,0x042a,0x042b,0x042c,0x042d,0x042e,0x042f, - 0x0430,0x0431,0x0432,0x0433,0x0434,0x0435,0x0436,0x0437, - 0x0438,0x0439,0x043a,0x043b,0x043c,0x043d,0x043e,0x043f, - 0x0440,0x0441,0x0442,0x0443,0x0444,0x0445,0x0446,0x0447, - 0x0448,0x0449,0x044a,0x044b,0x044c,0x044d,0x044e,0x044f, - }; long tabov[256] = { 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f, [rsc] --rw-r--r-- M 1372441 rsc sys 19274 Jan 27 12:26 sys/src/cmd/tcs/misc.h [rsc] --rw-rw-r-- M 1372441 glenda sys 591 Jan 27 12:26 sys/src/cmd/tcs/mkfile /n/sourcesdump/2006/0127/plan9/sys/src/cmd/tcs/mkfile:24,29 - /n/sourcesdump/2006/0128/plan9/sys/src/cmd/tcs/mkfile:24,32 tcs.$O gb.$O: gb.h tcs.$O: cyrillic.h tcs.$O: conv.h + tcs.$O: 8859.h + tcs.$O: ms.h + tcs.$O: misc.h conv%.$O: conv.h conv_ksc.$O: ksc.h [rsc] --rw-r--r-- M 1372441 rsc sys 44069 Jan 27 12:26 sys/src/cmd/tcs/ms.h [rsc] --rw-rw-r-- M 1372441 glenda sys 15489 Jan 27 12:26 sys/src/cmd/tcs/tcs.c [diffs elided - too long] [diff -c /n/sourcesdump/2006/0127/plan9/sys/src/cmd/tcs/tcs.c /n/sourcesdump/2006/0128/plan9/sys/src/cmd/tcs/tcs.c] [rsc] --rw-rw-r-- M 1372441 glenda sys 2682 Jan 27 12:46 sys/man/1/tcs /n/sourcesdump/2006/0127/plan9/sys/man/1/tcs:108,113 - /n/sourcesdump/2006/0128/plan9/sys/man/1/tcs:108,116 .B 8859-9 Latin-5 (Finnish .. Portuguese) .TP + .B html + Unicode as encoded by HTML + .TP .B koi8 KOI-8 (GOST 19769-74) .TP /n/sourcesdump/2006/0127/plan9/sys/man/1/tcs:156,161 - /n/sourcesdump/2006/0128/plan9/sys/man/1/tcs:159,167 Unknown Kanji will be converted into .B 0xFFFD characters. + .TP + .B tcs -t html + Convert UTF into character set-independent HTML. .TP .B tcs -lv Print an up to date list of the supported character sets.