From 56786a220fd951f5e6dabb21ef70be1dd3b80389 Mon Sep 17 00:00:00 2001 From: Mischa POSLAWSKY Date: Fri, 13 Mar 2015 08:43:00 +0100 Subject: [PATCH] charset: update to unicode v7.0 block allocations --- charset-ucplanes.inc.pl | 34 +++++++++++++++----------- charset-unicode.inc.pl | 53 ++++++++++++++++++++++------------------- charset.plp | 2 +- 3 files changed, 50 insertions(+), 39 deletions(-) diff --git a/charset-ucplanes.inc.pl b/charset-ucplanes.inc.pl index ce57a94..9378dab 100644 --- a/charset-ucplanes.inc.pl +++ b/charset-ucplanes.inc.pl @@ -7,9 +7,11 @@ my %uniblock = ( 0x007, 'grk', 0x008, 'cyr', 0x00A, 'arm', - 0x00B, 'aramaic', - 0x011, '', - 0x012, 'brahmic', + 0x00B, 'heb', + 0x00C, 'arabic', + 0x00E, 'aram', + 0x010, 'aramaic', + 0x012, 'brahmic', 0x020, 'mm', 0x021, 'geor', 0x022, 'jamo', @@ -18,20 +20,20 @@ my %uniblock = ( 0x02D, 'ger', 0x02E, 'brahm', 0x030, 'mon', - 0x031, 'can', + 0x031, 'can', 0x032, 'brahmic', 0x03A, 'extensions', 0x03E, 'greek', 0x040, '·…', - 0x041, 'misc', + 0x041, 'symbols', 0x044, 'maths', 0x046, 'technical', 0x049, '()', 0x04A, 'draw', 0x04C, 'symbols', 0x050, 'braille', - 0x052, '→', - 0x053, 'math', + 0x052, 'arr', + 0x053, 'maths', 0x056, 'misc', 0x058, 'ancient', 0x05A, 'ext', @@ -42,19 +44,23 @@ my %uniblock = ( 0x066, 'compat', 0x068, '', 0x070, 'cjk ideographs A', #+2 - 0x09C, 'cjk unified ideographs', + 0x09C, 'cjk unified ideographs', 0x140, 'yi', - 0x149, 'lisu', + 0x149, 'lisu', 0x14A, 'vai', 0x14C, 'cyr', - 0x14D, 'bam', + 0x14D, 'bam', 0x14E, 'lat-D', - 0x150, 'brahmic', - 0x158, 'hangeul syllables', + 0x150, 'brahmic', + 0x156, 'ext', + 0x158, '', 0x160, 'hangeul syllables', 0x1B0, 'surrogates', - 0x1C0, 'private use', - 0x1F0, 'cjk compat', + 0x1C0, 'private use', + 0x1F0, '', + 0x1F2, 'cjk compat', + 0x1F6, 'presentation', + 0x1FE, 'width', 0xFB0, 'presentation', 0xFB5, '', 0xFC0, 'arabic presentation forms A', diff --git a/charset-unicode.inc.pl b/charset-unicode.inc.pl index b072344..2b709c2 100644 --- a/charset-unicode.inc.pl +++ b/charset-unicode.inc.pl @@ -22,9 +22,10 @@ my %uniblock = ( 0x075, 'arabic+', 0x078, 'thaana', 0x07C, 'n\'ko', - 0x080, 'samaritan', - 0x084, 'manda', - 0x086, 'reserved', + 0x080, 'samaritan', + 0x084, 'manda', + 0x086, 'reserved', + 0x08A, 'arabic ext-A', 0x090, 'devanagari', 0x098, 'bengali', 0x0A0, 'gurmukhi', @@ -55,28 +56,30 @@ my %uniblock = ( 0x176, 'tagb', 0x178, 'khmer', 0x180, 'mongolian', - 0x18B, 'canadian+', + 0x18B, 'canadian+', 0x190, 'limbu', 0x195, 'tai le', 0x198, 'new tai lue', 0x19E, 'khmer', 0x1A0, 'lontara', - 0x1A2, 'tai tham', - 0x1AB, 'reserved', + 0x1A2, 'tai tham', + 0x1AB, 'diacritics+', 0x1B0, 'balinese', 0x1B8, 'sundanese', - 0x1BC, 'batak', + 0x1BC, 'batak', 0x1C0, 'lepcha', 0x1C5, 'ol chiki', - 0x1C8, 'reserved', - 0x1CD, 'vedic', + 0x1C8, 'cyr', + 0x1C9, 'reserved', + 0x1CC, 'sn', + 0x1CD, 'vedic', 0x1D0, 'phonetic', 0x1D8, 'phonetic+', - 0x1DC, 'combining', + 0x1DC, 'diacritics+', 0x1E0, 'latin extended additional', 0x1F0, 'greek+', 0x200, 'general punctuation', - 0x207, 'suþscript', # suth now means "sub and/or sup" + 0x207, 'suþscript', # suth now means "sub and/or sup" 0x20A, 'currency', 0x20D, 'overlay', 0x210, 'letterlike', @@ -129,29 +132,31 @@ my %uniblock = ( 0xA00, 'yi', 0xA40, 'yi', 0xA49, 'yi radicals', - 0xA4D, 'lisu', + 0xA4D, 'lisu', 0xA50, 'vai', 0xA60, 'vai', 0xA64, 'cyrillic extended-B', - 0xA6A, 'bamum', + 0xA6A, 'bamum', 0xA70, 'tones', 0xA72, 'latin extended-D', 0xA80, 'sylheti', - 0xA83, 'in', + 0xA83, 'in', 0xA84, 'phags-pa', 0xA88, 'saurashtra', - 0xA8E, 'deva+', + 0xA8E, 'deva+', 0xA90, 'kayah li', 0xA93, 'rejang', - 0xA96, 'jamo-A', - 0xA98, 'javanese', - 0xA9E, 'res', + 0xA96, 'jamo-A', + 0xA98, 'javanese', + 0xA9E, 'mm-B', 0xAA0, 'cham', - 0xAA6, 'mym-A', - 0xAA8, 'tai viet', - 0xAAE, 'mtei+', - 0xAB0, 'reserved', - 0xABC, 'manipuri', + 0xAA6, 'mm-A', + 0xAA8, 'tai viet', + 0xAAE, 'mtei+', + 0xAB0, 'ethiopic-A', + 0xAB3, 'latin ext-E', + 0xAB7, 'cherokee+', + 0xABC, 'meithei', 0xAC0, 'hangeul syllables', 0xD70, 'hangeul syllables', 0xD7B, 'haungeul jamo-B', @@ -159,7 +164,7 @@ my %uniblock = ( 0xDC0, 'low surrogates', 0xE00, 'private use', 0xF90, 'cjk compatibility ideographs', - 0xFB0, 'presentation', + 0xFB0, 'presentation', 0xFB5, '', 0xFC0, 'arabic presentation forms A', 0xFD0, '', diff --git a/charset.plp b/charset.plp index e5fdd45..d6d853e 100644 --- a/charset.plp +++ b/charset.plp @@ -164,7 +164,7 @@ for my $row (@request) { -
unicode 5.0 + unicode 7.0 proposed deprecated unassigned -- 2.30.0