charset: describe unicode plane abbreviations

diff --git a/charset-ucplanes.inc.pl b/charset-ucplanes.inc.pl
index fce05ffdffd8c4eeac540f5151dd80c024664990..7939c3a4860607b5f1124598843a2c1bece2e29c 100644 (file)
--- a/charset-ucplanes.inc.pl
+++ b/charset-ucplanes.inc.pl
@@ -2,55 +2,56 @@ use utf8;
 +{
        0x0000 => [0x008, 'X Po',               'ascii'],
        0x0008 => [0x020, 'X L Latin',          'latin'],
 +{
        0x0000 => [0x008, 'X Po',               'ascii'],
        0x0008 => [0x020, 'X L Latin',          'latin'],

-       0x0028 => [0x010, 'X Mn',               'comb'], # also spacing Sk
-       0x0038 => [0x008, 'X L Greek',          'grk'],
-       0x0040 => [0x010, 'X L Cyrillic',       'cyr'],
-       0x0050 => [0x008, 'X L Armenian',       'arm'],
-       0x0058 => [0x008, 'X L Aramaic',        'heb'],
+       0x0028 => [0x010, 'X Mn',               'diac', 'diacritics'], # also spacing Sk
+       0x0038 => [0x008, 'X L Greek',          'grk', 'greek'],
+       0x0040 => [0x010, 'X L Cyrillic',       'cyr', 'cyrillic'],
+       0x0050 => [0x008, 'X L Armenian',       'arm', 'armenian'],
+       0x0058 => [0x008, 'X L Aramaic',        'heb', 'hebrew'],

        0x0060 => [0x010, 'X L Arabic',         'arabic'],
        0x0060 => [0x010, 'X L Arabic',         'arabic'],

-       0x0070 => [0x010, 'X L Aramaic',        'aram'],
-       0x0080 => [0x010, 'X L Aramaic',        'aramaic'],
-       0x0090 => [0x070, 'X L Brahmic',        'brahmic'],
-       0x0100 => [0x008, 'X L Brahmic',        'mm'],
-       0x0108 => [0x008, 'X L Aramaic',        'geor'],
+       0x0070 => [0x020, 'X L African',        'rtl', 'various right-to-left scripts'],
+       0x0090 => [0x050, 'X L Brahmic',        'brahmic'],
+       0x00E0 => [0x010, 'X L Brahmic Khmer',  's-br', 'south brahmic: lao and thai'],
+       0x00F0 => [0x010, 'X L Brahmic',        'tibet', 'tibetan'],
+       0x0100 => [0x008, 'X L Brahmic',        'mm', 'myanmar'],
+       0x0108 => [0x008, 'X L Aramaic',        'geor', 'georgian'],

        0x0110 => [0x010, 'X L Hangul',         'jamo'],
        0x0120 => [0x018, 'X L African',        'ethiopic'],
        0x0110 => [0x010, 'X L Hangul',         'jamo'],
        0x0120 => [0x018, 'X L African',        'ethiopic'],

-       0x0138 => [0x030, 'X L Syllabic',       'aboriginal'],
-       0x0168 => [0x008, 'X L Alpha',          'ger'],
-       0x0170 => [0x010, 'X L Brahmic',        'brahm'],
-       0x0180 => [0x008, 'X L Aramaic',        'mon'],
-       0x0188 => [0x008, 'X L Syllabic',       'can'],
+       0x0138 => [0x030, 'X L Syllabic',       'aboriginal', 'cherokee and canadian syllabics'],
+       0x0168 => [0x008, 'X L Alpha',          'ger', 'germanic runes'],
+       0x0170 => [0x010, 'X L Brahmic',        'brahm', 'various brahmic'],
+       0x0180 => [0x008, 'X L Aramaic',        'mon', 'mongolian'],
+       0x0188 => [0x008, 'X L Syllabic',       'can', 'canadian supplement'],

        0x0190 => [0x040, 'X L Brahmic',        'brahmic'],
        0x01D0 => [0x020, 'X L Latin',          'extensions'],
        0x01F0 => [0x010, 'X L Greek',          'greek'],
        0x0190 => [0x040, 'X L Brahmic',        'brahmic'],
        0x01D0 => [0x020, 'X L Latin',          'extensions'],
        0x01F0 => [0x010, 'X L Greek',          'greek'],

-       0x0200 => [0x008, 'X Po',               '·…'],
+       0x0200 => [0x008, 'X Po',               '·…', 'punctuation'],

        0x0208 => [0x018, 'X So',               'symbols'],
        0x0220 => [0x010, 'X Sm',               'maths'],
        0x0230 => [0x018, 'X So',               'technical'],
        0x0208 => [0x018, 'X So',               'symbols'],
        0x0220 => [0x010, 'X Sm',               'maths'],
        0x0230 => [0x018, 'X So',               'technical'],

-       0x0248 => [0x008, 'X Latin',            '()'],
-       0x0250 => [0x010, 'X So',               'draw'],
+       0x0248 => [0x008, 'X Latin',            '()', 'enclosed alphanumerics'],
+       0x0250 => [0x010, 'X So',               'draw', 'box drawing and shapes'],

        0x0260 => [0x020, 'X So',               'symbols'],
        0x0280 => [0x010, 'X L Alpha',          'braille'],
        0x0260 => [0x020, 'X So',               'symbols'],
        0x0280 => [0x010, 'X L Alpha',          'braille'],

-       0x0290 => [0x008, 'X So',               'arr'],
+       0x0290 => [0x008, 'X So',               'arr', 'arrows'],

        0x0298 => [0x018, 'X Sm',               'maths'],
        0x0298 => [0x018, 'X Sm',               'maths'],

-       0x02B0 => [0x010, 'X So',               'misc'],
-       0x02C0 => [0x010, 'X L Greek',          'ancient'],
-       0x02D0 => [0x010, 'X L Alpha',          'ext'],
-       0x02E0 => [0x008, 'X Po',               '·+'],
+       0x02B0 => [0x010, 'X So',               'misc', 'miscellaneous symbols'],
+       0x02C0 => [0x010, 'X L Greek',          'ancient', 'glagolitic, latin, coptic'],
+       0x02D0 => [0x010, 'X L Alpha',          'ext', 'extensions of various alphabets'],
+       0x02E0 => [0x008, 'X Po',               '·+', 'punctuation'],

        0x02E8 => [0x018, 'X L Han',            'radicals'],
        0x0300 => [0x010, 'X L Katakana',       'japanese'],
        0x0310 => [0x020, 'X L Han',            'cjk+'],
        0x02E8 => [0x018, 'X L Han',            'radicals'],
        0x0300 => [0x010, 'X L Katakana',       'japanese'],
        0x0310 => [0x020, 'X L Han',            'cjk+'],

-       0x0330 => [0x010, 'X Xd L Han',         'compat'],
+       0x0330 => [0x010, 'X Xd L Han',         'compat', 'cjk compatibility'],

        0x0340 => [0x1A0, 'X L Han',            'cjk ideographs A'],
        0x04E0 => [0x520, 'X L Han',            'cjk unified ideographs'],
        0x0A00 => [0x048, 'X L Syllabic',       'yi'],
        0x0A48 => [0x008, 'X L Latin',          'lisu'],
        0x0A50 => [0x010, 'X L Syllabic',       'vai'],
        0x0340 => [0x1A0, 'X L Han',            'cjk ideographs A'],
        0x04E0 => [0x520, 'X L Han',            'cjk unified ideographs'],
        0x0A00 => [0x048, 'X L Syllabic',       'yi'],
        0x0A48 => [0x008, 'X L Latin',          'lisu'],
        0x0A50 => [0x010, 'X L Syllabic',       'vai'],

-       0x0A60 => [0x008, 'X L Cyrillic',       'cyr'],
-       0x0A68 => [0x008, 'X L Syllabic',       'bam'],
+       0x0A60 => [0x008, 'X L Cyrillic',       'cyr', 'cyrillic ext-B'],
+       0x0A68 => [0x008, 'X L Syllabic',       'bam', 'bamum'],

        0x0A70 => [0x010, 'X L Latin',          'lat-D'],
        0x0A80 => [0x030, 'X L Brahmic',        'brahmic'],
        0x0A70 => [0x010, 'X L Latin',          'lat-D'],
        0x0A80 => [0x030, 'X L Brahmic',        'brahmic'],

-       0x0AB0 => [0x010, 'X L Alpha',          'ext'],
+       0x0AB0 => [0x010, 'X L Alpha',          'ext', 'various extensions'],

        0x0AC0 => [0x2C0, 'X L Hangul',         'hangeul syllables'],
        0x0D80 => [0x080, 'X Cs',               'surrogates'],
        0x0E00 => [0x190, 'X Co',               'private use'],
        0x0AC0 => [0x2C0, 'X L Hangul',         'hangeul syllables'],
        0x0D80 => [0x080, 'X Cs',               'surrogates'],
        0x0E00 => [0x190, 'X Co',               'private use'],

diff --git a/charset-unicode.inc.pl b/charset-unicode.inc.pl
index 0d8685ca33e8317c5ca40cd88c58a3ba1a83877b..38449ab2cc632260ca33b9506c503dfdd8601062 100644 (file)
--- a/charset-unicode.inc.pl
+++ b/charset-unicode.inc.pl
@@ -22,7 +22,7 @@ use utf8;
        0x0070 => [0x05, 'X L Aramaic',        'syriac'],
        0x0075 => [0x03, 'X L Arabic',         'arabic+'],
        0x0078 => [0x04, 'X L African',        'thaana'],
        0x0070 => [0x05, 'X L Aramaic',        'syriac'],
        0x0075 => [0x03, 'X L Arabic',         'arabic+'],
        0x0078 => [0x04, 'X L African',        'thaana'],

-       0x007C => [0x04, 'X L African',        'n\'ko'],
+       0x007C => [0x04, 'X L African',        q(n'ko)],

        0x0080 => [0x04, 'X L Hebrew',         'samaritan'],
        0x0084 => [0x02, 'X L Aramaic',        'manda'],
        0x0086 => [0x01, 'X Xr L Aramaic',     'syr'],
        0x0080 => [0x04, 'X L Hebrew',         'samaritan'],
        0x0084 => [0x02, 'X L Aramaic',        'manda'],
        0x0086 => [0x01, 'X Xr L Aramaic',     'syr'],