charset: update to unicode v7.0 block allocations

diff --git a/charset-ucplanes.inc.pl b/charset-ucplanes.inc.pl
index ce57a941ab0a5410e9a001e125714850d0764743..9378dab152aa688cd53c083c9cf9996e7279dd44 100644 (file)
--- a/charset-ucplanes.inc.pl
+++ b/charset-ucplanes.inc.pl
@@ -7,9 +7,11 @@ my %uniblock = (
        0x007, '<td colspan="1" class="X L Greek">grk',
        0x008, '<td colspan="2" class="X L Cyrillic">cyr',
        0x00A, '<td colspan="1" class="X L Armenian">arm',
        0x007, '<td colspan="1" class="X L Greek">grk',
        0x008, '<td colspan="2" class="X L Cyrillic">cyr',
        0x00A, '<td colspan="1" class="X L Armenian">arm',

-       0x00B, '<td colspan="6" class="X L Aramaic">aramaic',
-       0x011, '<td colspan="1" class="Xr">',
-       0x012, '<td colspan="15" class="X L Brahmic">brahmic',
+       0x00B, '<td colspan="1" class="X L Aramaic">heb',
+       0x00C, '<td colspan="2" class="X L Arabic">arabic',
+       0x00E, '<td colspan="3" class="X L Aramaic">aram',
+       0x010, '<td colspan="2" class="X L Aramaic">aramaic',
+       0x012, '<td colspan="14" class="X L Brahmic">brahmic',

        0x020, '<td colspan="1" class="X L Brahmic">mm',
        0x021, '<td colspan="1" class="X L Aramaic">geor',
        0x022, '<td colspan="2" class="X L Hangul">jamo',
        0x020, '<td colspan="1" class="X L Brahmic">mm',
        0x021, '<td colspan="1" class="X L Aramaic">geor',
        0x022, '<td colspan="2" class="X L Hangul">jamo',


@@ -18,20 +20,20 @@ my %uniblock = (
        0x02D, '<td colspan="1" class="X L Alpha">ger',
        0x02E, '<td colspan="2" class="X L Brahmic">brahm',
        0x030, '<td colspan="1" class="X L Aramaic">mon',
        0x02D, '<td colspan="1" class="X L Alpha">ger',
        0x02E, '<td colspan="2" class="X L Brahmic">brahm',
        0x030, '<td colspan="1" class="X L Aramaic">mon',

-       0x031, '<td colspan="1" class="X Xr L Syllabic">can',
+       0x031, '<td colspan="1" class="X L Syllabic">can',

        0x032, '<td colspan="8" class="X L Brahmic">brahmic',
        0x03A, '<td colspan="4" class="X L Latin">extensions',
        0x03E, '<td colspan="2" class="X L Greek">greek',
        0x040, '<td colspan="1" class="X Po">·…',
        0x032, '<td colspan="8" class="X L Brahmic">brahmic',
        0x03A, '<td colspan="4" class="X L Latin">extensions',
        0x03E, '<td colspan="2" class="X L Greek">greek',
        0x040, '<td colspan="1" class="X Po">·…',

-       0x041, '<td colspan="3" class="X So">misc',
+       0x041, '<td colspan="3" class="X So">symbols',

        0x044, '<td colspan="2" class="X Sm">maths',
        0x046, '<td colspan="3" class="X So">technical',
        0x049, '<td colspan="1" class="X Latin">()',
        0x04A, '<td colspan="2" class="X So">draw',
        0x04C, '<td colspan="4" class="X So">symbols',
        0x050, '<td colspan="2" class="X L Alpha">braille',
        0x044, '<td colspan="2" class="X Sm">maths',
        0x046, '<td colspan="3" class="X So">technical',
        0x049, '<td colspan="1" class="X Latin">()',
        0x04A, '<td colspan="2" class="X So">draw',
        0x04C, '<td colspan="4" class="X So">symbols',
        0x050, '<td colspan="2" class="X L Alpha">braille',

-       0x052, '<td colspan="1" class="X So">→',
-       0x053, '<td colspan="3" class="X Sm">math',
+       0x052, '<td colspan="1" class="X So">arr',
+       0x053, '<td colspan="3" class="X Sm">maths',

        0x056, '<td colspan="2" class="X So">misc',
        0x058, '<td colspan="2" class="X L Greek">ancient',
        0x05A, '<td colspan="2" class="X L Alpha">ext',
        0x056, '<td colspan="2" class="X So">misc',
        0x058, '<td colspan="2" class="X L Greek">ancient',
        0x05A, '<td colspan="2" class="X L Alpha">ext',


@@ -42,19 +44,23 @@ my %uniblock = (
        0x066, '<td colspan="2" class="X Xd L Han">compat',
        0x068, '<td colspan="8" class="X L Han" style="border-bottom:none">',
        0x070, '<td colspan="16" rowspan="2" class="X L Han" style="border-top:none">cjk ideographs A', #+2
        0x066, '<td colspan="2" class="X Xd L Han">compat',
        0x068, '<td colspan="8" class="X L Han" style="border-bottom:none">',
        0x070, '<td colspan="16" rowspan="2" class="X L Han" style="border-top:none">cjk ideographs A', #+2

-       0x09C, '<td colspan="16" rowspan="10" class="X L Han">cjk unified ideographs',
+       0x09C, '<td colspan="16" rowspan="11" class="X L Han">cjk unified ideographs',

        0x140, '<td colspan="9" class="X L Syllabic">yi',
        0x140, '<td colspan="9" class="X L Syllabic">yi',

-       0x149, '<td colspan="1" class="X Xr L Latin">lisu',
+       0x149, '<td colspan="1" class="X L Latin">lisu',

        0x14A, '<td colspan="2" class="X L Syllabic">vai',
        0x14C, '<td colspan="1" class="X L Cyrillic">cyr',
        0x14A, '<td colspan="2" class="X L Syllabic">vai',
        0x14C, '<td colspan="1" class="X L Cyrillic">cyr',

-       0x14D, '<td colspan="1" class="X Xr L Syllabic">bam',
+       0x14D, '<td colspan="1" class="X L Syllabic">bam',

        0x14E, '<td colspan="2" class="X L Latin">lat-D',
        0x14E, '<td colspan="2" class="X L Latin">lat-D',

-       0x150, '<td colspan="8" class="X L Brahmic">brahmic',
-       0x158, '<td colspan="8" class="X L Hangul">hangeul syllables',
+       0x150, '<td colspan="6" class="X L Brahmic">brahmic',
+       0x156, '<td colspan="2" class="X L Alpha">ext',
+       0x158, '<td colspan="8" class="X L Hangul" style="border-bottom:none">',

        0x160, '<td colspan="16" rowspan="5" class="X L Hangul" style="border-top:none">hangeul syllables',
        0x1B0, '<td colspan="16" class="X Cs">surrogates',
        0x160, '<td colspan="16" rowspan="5" class="X L Hangul" style="border-top:none">hangeul syllables',
        0x1B0, '<td colspan="16" class="X Cs">surrogates',

-       0x1C0, '<td colspan="16" rowspan="3" class="X Co">private use',
-       0x1F0, '<td colspan="4" class="X L Han">cjk compat',
+       0x1C0, '<td colspan="16" rowspan="3" class="X Co" style="border-bottom:none">private use',
+       0x1F0, '<td colspan="2" class="X Co" style="border-top:none">',
+       0x1F2, '<td colspan="4" class="X L Han">cjk compat',
+       0x1F6, '<td colspan="8" class="X L Arabic">presentation',
+       0x1FE, '<td colspan="2" class="X L Latin">width',

        0xFB0, '<td colspan="5" class="X Xd L">presentation',
        0xFB5, '<td colspan="11" class="X Xd L Arabic" style="border-bottom:none">',
        0xFC0, '<td colspan="16" class="X Xd L Arabic" style="border-top:none; border-bottom:none">arabic presentation forms A',
        0xFB0, '<td colspan="5" class="X Xd L">presentation',
        0xFB5, '<td colspan="11" class="X Xd L Arabic" style="border-bottom:none">',
        0xFC0, '<td colspan="16" class="X Xd L Arabic" style="border-top:none; border-bottom:none">arabic presentation forms A',

diff --git a/charset-unicode.inc.pl b/charset-unicode.inc.pl
index b072344666176a0a63ac08e9023384770722e99e..2b709c287b9f716f50fc5bfd56712b44289c1b0b 100644 (file)
--- a/charset-unicode.inc.pl
+++ b/charset-unicode.inc.pl
@@ -22,9 +22,10 @@ my %uniblock = (
        0x075, '<td colspan="3" class="X L Arabic">arabic+',
        0x078, '<td colspan="4" class="X L African">thaana',
        0x07C, '<td colspan="4" class="X L African">n\'ko',
        0x075, '<td colspan="3" class="X L Arabic">arabic+',
        0x078, '<td colspan="4" class="X L African">thaana',
        0x07C, '<td colspan="4" class="X L African">n\'ko',

-       0x080, '<td colspan="4" class="X Xr L Hebrew">samaritan',
-       0x084, '<td colspan="2" class="X Xr L Aramaic">manda',
-       0x086, '<td colspan="10" class="">reserved',
+       0x080, '<td colspan="4" class="X L Hebrew">samaritan',
+       0x084, '<td colspan="2" class="X L Aramaic">manda',
+       0x086, '<td colspan="4" class="">reserved',
+       0x08A, '<td colspan="6" class="X L Arabic">arabic ext-A',

        0x090, '<td colspan="8" class="X L Brahmic">devanagari',
        0x098, '<td colspan="8" class="X L Brahmic">bengali',
        0x0A0, '<td colspan="8" class="X L Brahmic">gurmukhi',
        0x090, '<td colspan="8" class="X L Brahmic">devanagari',
        0x098, '<td colspan="8" class="X L Brahmic">bengali',
        0x0A0, '<td colspan="8" class="X L Brahmic">gurmukhi',


@@ -55,28 +56,30 @@ my %uniblock = (
        0x176, '<td colspan="2" class="X L Brahmic" title="tagbanwa">tagb',
        0x178, '<td colspan="8" class="X L Brahmic Khmer">khmer',
        0x180, '<td colspan="11" class="X L Aramaic">mongolian',
        0x176, '<td colspan="2" class="X L Brahmic" title="tagbanwa">tagb',
        0x178, '<td colspan="8" class="X L Brahmic Khmer">khmer',
        0x180, '<td colspan="11" class="X L Aramaic">mongolian',

-       0x18B, '<td colspan="5" class="X Xr L Syllabic">canadian+',
+       0x18B, '<td colspan="5" class="X L Syllabic">canadian+',

        0x190, '<td colspan="5" class="X L Brahmic">limbu',
        0x195, '<td colspan="3" class="X L Brahmic">tai le',
        0x198, '<td colspan="6" class="X L Brahmic">new tai lue',
        0x19E, '<td colspan="2" class="X L Brahmic Khmer" title="khmer symbols">khmer',
        0x1A0, '<td colspan="2" class="X L Brahmic">lontara',
        0x190, '<td colspan="5" class="X L Brahmic">limbu',
        0x195, '<td colspan="3" class="X L Brahmic">tai le',
        0x198, '<td colspan="6" class="X L Brahmic">new tai lue',
        0x19E, '<td colspan="2" class="X L Brahmic Khmer" title="khmer symbols">khmer',
        0x1A0, '<td colspan="2" class="X L Brahmic">lontara',

-       0x1A2, '<td colspan="9" class="X Xr L Brahmic">tai tham',
-       0x1AB, '<td colspan="5" class="">reserved',
+       0x1A2, '<td colspan="9" class="X L Brahmic">tai tham',
+       0x1AB, '<td colspan="5" class="X Mn">diacritics+',

        0x1B0, '<td colspan="8" class="X L Brahmic">balinese',
        0x1B8, '<td colspan="4" class="X L Brahmic">sundanese',
        0x1B0, '<td colspan="8" class="X L Brahmic">balinese',
        0x1B8, '<td colspan="4" class="X L Brahmic">sundanese',

-       0x1BC, '<td colspan="4" class="X Xr L Brahmic">batak',
+       0x1BC, '<td colspan="4" class="X L Brahmic">batak',

        0x1C0, '<td colspan="5" class="X L Brahmic">lepcha',
        0x1C5, '<td colspan="3" class="X L Alpha">ol chiki',
        0x1C0, '<td colspan="5" class="X L Brahmic">lepcha',
        0x1C5, '<td colspan="3" class="X L Alpha">ol chiki',

-       0x1C8, '<td colspan="5" class="">reserved',
-       0x1CD, '<td colspan="3" class="X Xr Brahmic">vedic',
+       0x1C8, '<td colspan="1" class="X Xr L Cyrillic">cyr',
+       0x1C9, '<td colspan="3" class="">reserved',
+       0x1CC, '<td colspan="1" class="X L Brahmic">sn',
+       0x1CD, '<td colspan="3" class="X L Brahmic">vedic',

        0x1D0, '<td colspan="8" class="X L Latin">phonetic',
        0x1D8, '<td colspan="4" class="X L Latin">phonetic+',
        0x1D0, '<td colspan="8" class="X L Latin">phonetic',
        0x1D8, '<td colspan="4" class="X L Latin">phonetic+',

-       0x1DC, '<td colspan="4" class="X Mn">combining',
+       0x1DC, '<td colspan="4" class="X Mn">diacritics+',

        0x1E0, '<td colspan="16" class="X L Latin">latin extended additional',
        0x1F0, '<td colspan="16" class="X L Greek">greek+',
        0x200, '<td colspan="7" class="X Po">general punctuation',
        0x1E0, '<td colspan="16" class="X L Latin">latin extended additional',
        0x1F0, '<td colspan="16" class="X L Greek">greek+',
        0x200, '<td colspan="7" class="X Po">general punctuation',

-       0x207, '<td colspan="3" class="X Latin">suþscript', # suth now means "sub and/or sup"
+       0x207, '<td colspan="3" class="X L Latin">suþscript', # suth now means "sub and/or sup"

        0x20A, '<td colspan="3" class="X Sc">currency',
        0x20D, '<td colspan="3" class="X Mn">overlay',
        0x210, '<td colspan="5" class="X So">letterlike',
        0x20A, '<td colspan="3" class="X Sc">currency',
        0x20D, '<td colspan="3" class="X Mn">overlay',
        0x210, '<td colspan="5" class="X So">letterlike',


@@ -129,29 +132,31 @@ my %uniblock = (
        0xA00, '<td colspan="16" rowspan="4" class="X L Syllabic">yi',
        0xA40, '<td colspan="9" class="X L Syllabic" style="border-top:none">yi',
        0xA49, '<td colspan="4" class="X L Syllabic">yi radicals',
        0xA00, '<td colspan="16" rowspan="4" class="X L Syllabic">yi',
        0xA40, '<td colspan="9" class="X L Syllabic" style="border-top:none">yi',
        0xA49, '<td colspan="4" class="X L Syllabic">yi radicals',

-       0xA4D, '<td colspan="3" class="X Xr L Latin">lisu',
+       0xA4D, '<td colspan="3" class="X L Latin">lisu',

        0xA50, '<td colspan="16" class="X L Syllabic">vai',
        0xA60, '<td colspan="4" class="X L Syllabic" style="border-top:none">vai',
        0xA64, '<td colspan="6" class="X L Cyrillic">cyrillic extended-B',
        0xA50, '<td colspan="16" class="X L Syllabic">vai',
        0xA60, '<td colspan="4" class="X L Syllabic" style="border-top:none">vai',
        0xA64, '<td colspan="6" class="X L Cyrillic">cyrillic extended-B',

-       0xA6A, '<td colspan="6" class="X Xr L Syllabic">bamum',
+       0xA6A, '<td colspan="6" class="X L Syllabic">bamum',

        0xA70, '<td colspan="2" class="X L Mn">tones',
        0xA72, '<td colspan="14" class="X L Latin">latin extended-D',
        0xA80, '<td colspan="3" class="X L Brahmic">sylheti',
        0xA70, '<td colspan="2" class="X L Mn">tones',
        0xA72, '<td colspan="14" class="X L Latin">latin extended-D',
        0xA80, '<td colspan="3" class="X L Brahmic">sylheti',

-       0xA83, '<td colspan="1" class="X Xr No">in',
+       0xA83, '<td colspan="1" class="X No">in',

        0xA84, '<td colspan="4" class="X L Brahmic">phags-pa',
        0xA88, '<td colspan="6" class="X L Brahmic">saurashtra',
        0xA84, '<td colspan="4" class="X L Brahmic">phags-pa',
        0xA88, '<td colspan="6" class="X L Brahmic">saurashtra',

-       0xA8E, '<td colspan="2" class="X Xr L Brahmic">deva+',
+       0xA8E, '<td colspan="2" class="X L Brahmic">deva+',

        0xA90, '<td colspan="3" class="X L Brahmic">kayah li',
        0xA93, '<td colspan="3" class="X L Brahmic">rejang',
        0xA90, '<td colspan="3" class="X L Brahmic">kayah li',
        0xA93, '<td colspan="3" class="X L Brahmic">rejang',

-       0xA96, '<td colspan="2" class="X Xr L Hangul">jamo-A',
-       0xA98, '<td colspan="6" class="X Xr L Brahmic">javanese',
-       0xA9E, '<td colspan="2" class="">res',
+       0xA96, '<td colspan="2" class="X L Hangul">jamo-A',
+       0xA98, '<td colspan="6" class="X L Brahmic">javanese',
+       0xA9E, '<td colspan="2" class="X L Brahmic" title="myanmar extended-B">mm-B',

        0xAA0, '<td colspan="6" class="X L Brahmic">cham',
        0xAA0, '<td colspan="6" class="X L Brahmic">cham',

-       0xAA6, '<td colspan="2" class="X Xr L Brahmic" title="myanmar extended-A">mym-A',
-       0xAA8, '<td colspan="6" class="X Xr L Brahmic Khmer">tai viet',
-       0xAAE, '<td colspan="2" class="X Xr L Brahmic" title="meetei mayek extended">mtei+',
-       0xAB0, '<td colspan="12" class="">reserved',
-       0xABC, '<td colspan="4" class="X Xr L Brahmic" title="meetei mayek">manipuri',
+       0xAA6, '<td colspan="2" class="X L Brahmic" title="myanmar extended-A">mm-A',
+       0xAA8, '<td colspan="6" class="X L Brahmic Khmer">tai viet',
+       0xAAE, '<td colspan="2" class="X L Brahmic" title="meetei mayek extended">mtei+',
+       0xAB0, '<td colspan="3" class="X L African">ethiopic-A',
+       0xAB3, '<td colspan="4" class="X L Latin">latin ext-E',
+       0xAB7, '<td colspan="5" class="X Xr L Syllabic">cherokee+',
+       0xABC, '<td colspan="4" class="X L Brahmic" title="meetai mayek">meithei',

        0xAC0, '<td colspan="16" rowspan="43" class="X L Hangul">hangeul syllables',
        0xD70, '<td colspan="11" class="X L Hangul" style="border-top:none">hangeul syllables',
        0xD7B, '<td colspan="5" class="X L Hangul">haungeul jamo-B',
        0xAC0, '<td colspan="16" rowspan="43" class="X L Hangul">hangeul syllables',
        0xD70, '<td colspan="11" class="X L Hangul" style="border-top:none">hangeul syllables',
        0xD7B, '<td colspan="5" class="X L Hangul">haungeul jamo-B',


@@ -159,7 +164,7 @@ my %uniblock = (
        0xDC0, '<td colspan="16" rowspan="4" class="X Cs">low surrogates',
        0xE00, '<td colspan="16" rowspan="25" class="X Co">private use',
        0xF90, '<td colspan="16" rowspan="2" class="X L Han">cjk compatibility ideographs',
        0xDC0, '<td colspan="16" rowspan="4" class="X Cs">low surrogates',
        0xE00, '<td colspan="16" rowspan="25" class="X Co">private use',
        0xF90, '<td colspan="16" rowspan="2" class="X L Han">cjk compatibility ideographs',

-       0xFB0, '<td colspan="5" class="X Xd L">presentation',
+       0xFB0, '<td colspan="5" class="X Xd L Alpha">presentation',

        0xFB5, '<td colspan="11" class="X Xd L Arabic" style="border-bottom:none">',
        0xFC0, '<td colspan="16" class="X Xd L Arabic" style="border-top:none; border-bottom:none">arabic presentation forms A',
        0xFD0, '<td colspan="13" class="X Xd L Arabic" style="border-top:none">',
        0xFB5, '<td colspan="11" class="X Xd L Arabic" style="border-bottom:none">',
        0xFC0, '<td colspan="16" class="X Xd L Arabic" style="border-top:none; border-bottom:none">arabic presentation forms A',
        0xFD0, '<td colspan="13" class="X Xd L Arabic" style="border-top:none">',

diff --git a/charset.plp b/charset.plp
index e5fdd45966452046996d6e398e5611e499f9022e..d6d853e9176566a9a799f930d76276f75cbaff7d 100644 (file)
--- a/charset.plp
+++ b/charset.plp
@@ -164,7 +164,7 @@ for my $row (@request) {
        </table>
 
        <table class="glyphs"><tr>
        </table>
 
        <table class="glyphs"><tr>

-       <td class="X">unicode 5.0
+       <td class="X">unicode 7.0

        <td class="X Xr">proposed
        <td class="X Xd">deprecated
        <td class="">unassigned
        <td class="X Xr">proposed
        <td class="X Xd">deprecated
        <td class="">unassigned