Add firstLetter data for ~50 additional languages

Based on CLDR 29 data files.

This did the relatively easy languages in CLDR 29 (Which is most
of them). I skipped languages with complicated tailoring files.

Change-Id: I8367604f7d3a1cdef9cb4e15813893c8cbfff1ff

diff --git a/includes/collation/IcuCollation.php b/includes/collation/IcuCollation.php
index 9c0b96e..4110472 100644 (file)
--- a/includes/collation/IcuCollation.php
+++ b/includes/collation/IcuCollation.php
@@ -133,48 +133,106 @@ class IcuCollation extends Collation {
                'vi' => [ "Ă", "Â", "Đ", "Ê", "Ô", "Ơ", "Ư" ],
                // Not verified, but likely correct
                'af' => [],
-               'ast' => [ "Ch", "Ll", "Ñ" ],
+               'am' => [],
+               'ar' => [],
+               'as' => [ "\xe0\xa6\x82", "\xe0\xa6\x81", "\xe0\xa6\x83", "\xe0\xa7\x8e", "ক্ষ " ],
+               'ast' => [ "Ch", "Ll", "Ñ" ], // Not in libicu?
                'az' => [ "Ç", "Ə", "Ğ", "İ", "Ö", "Ş", "Ü" ],
                'bg' => [],
+               'bo' => [],
                'br' => [ "Ch", "C'h" ],
+               'bs-Cyrl' => [],
                'ca' => [],
-               'co' => [],
+               'chr' => [],
+               'co' => [], // Not in libicu?
                'da' => [ "Æ", "Ø", "Å" ],
                'de' => [],
+               'de-AT@collation=phonebook' => [ 'ä', 'ö', 'ü', 'ß' ],
                'dsb' => [ "Č", "Ć", "Dź", "Ě", "Ch", "Ł", "Ń", "Ŕ", "Š", "Ś", "Ž", "Ź" ],
+               'ee' => [ "Dz", "Ɖ", "Ɛ", "Ƒ", "Gb", "Ɣ", "Kp", "Ny", "Ŋ", "Ɔ", "Ts", "Ʋ" ],
                'el' => [],
                'eo' => [ "Ĉ", "Ĝ", "Ĥ", "Ĵ", "Ŝ", "Ŭ" ],
                'es' => [ "Ñ" ],
                'et' => [ "Š", "Ž", "Õ", "Ä", "Ö", "Ü", "W" ], // added W for CollationEt (xx-uca-et)
-               'eu' => [ "Ñ" ],
+               'eu' => [ "Ñ" ], // Not in libicu?
+               'fil' => [ "Ñ", "Ng" ],
                'fo' => [ "Á", "Ð", "Í", "Ó", "Ú", "Ý", "Æ", "Ø", "Å" ],
-               'fur' => [ "À", "Á", "Â", "È", "Ì", "Ò", "Ù" ],
-               'fy' => [],
+               'fr-CA' => [], // fr-CA sorts accents slightly different from fr.
+               'fur' => [ "À", "Á", "Â", "È", "Ì", "Ò", "Ù" ], // not in libicu
+               'fy' => [], // not in libicu
                'ga' => [],
-               'gd' => [],
+               'gd' => [], // not in libicu
                'gl' => [ "Ch", "Ll", "Ñ" ],
+               'gu' => [ "\xe0\xaa\x82", "\xe0\xaa\x83", "\xe0\xaa\x81", "\xe0\xaa\xb3" ],
+               'ha' => [ 'Ɓ', 'Ɗ', 'Ƙ', 'Sh', 'Ts', 'Ƴ' ],
+               'haw' => [ 'ʻ' ],
+               'he' => [],
+               'hi' => [ "\xe0\xa4\x82", "\xe0\xa4\x83" ],
+               'hy' => [ "և" ],
+               'id' => [],
+               'ig' => [ "Ch", "Gb", "Gh", "Gw", "Ị", "Kp", "Kw", "Ṅ", "Nw", "Ny", "Ọ", "Sh", "Ụ" ],
+               'ka' => [],
+               'km' => [
+                       "រ", "ឫ", "ឬ", "ល", "ឭ", "ឮ", "\xe1\x9e\xbb\xe1\x9f\x86",
+                       "\xe1\x9f\x86", "\xe1\x9e\xb6\xe1\x9f\x86", "\xe1\x9f\x87",
+                       "\xe1\x9e\xb7\xe1\x9f\x87", "\xe1\x9e\xbb\xe1\x9f\x87",
+                       "\xe1\x9f\x81\xe1\x9f\x87", "\xe1\x9f\x84\xe1\x9f\x87",
+               ],
+               'kn' => [ "\xe0\xb2\x81", "\xe0\xb2\x83", "\xe0\xb3\xb1", "\xe0\xb3\xb2" ],
+               'kok' => [ "\xe0\xa4\x82", "\xe0\xa4\x83", "ळ", "क्ष" ],
                'kk' => [ "Ү", "І" ],
                'kl' => [ "Æ", "Ø", "Å" ],
-               'ku' => [ "Ç", "Ê", "Î", "Ş", "Û" ],
+               'ku' => [ "Ç", "Ê", "Î", "Ş", "Û" ], // ku is not in libicu
                'ky' => [ "Ё" ],
-               'la' => [],
+               'la' => [], // la is not in libicu
                'lb' => [],
-               'mo' => [ "Ă", "Â", "Î", "Ş", "Ţ" ],
+               'lkt' => [ 'Č', 'Ǧ', 'Ȟ', 'Š', 'Ž' ],
+               'ln' => [ 'Ɛ' ],
+               'lo' => [],
+               'ml' => [],
+               'mn' => [],
+               'mr' => [ "\xe0\xa4\x82", "\xe0\xa4\x83", "ळ", "क्ष", "ज्ञ" ],
+               'mo' => [ "Ă", "Â", "Î", "Ş", "Ţ" ], // no mo in libicu
+               'ms' => [],
                'mt' => [ "Ċ", "Ġ", "Għ", "Ħ", "Ż" ],
+               'nb' => [ "Æ", "Ø", "Å" ],
+               'ne' => [],
+               'nn' => [ "Æ", "Ø", "Å" ],
+               // no is not in the libicu list. You should probably use nb or nn instead.
                'no' => [ "Æ", "Ø", "Å" ],
-               'oc' => [],
-               'rm' => [],
+               'oc' => [], // not in libicu
+               'om' => [ 'Ch', 'Dh', 'Kh', 'Ny', 'Ph', 'Sh' ],
+               'or' => [ "\xe0\xac\x81", "\xe0\xac\x82", "\xe0\xac\x83", "କ୍ଷ" ],
+               'pa' => [ "\xe0\xa9\x8d" ],
+               'rm' => [], // not in libicu
                'ro' => [ "Ă", "Â", "Î", "Ş", "Ţ" ],
-               'rup' => [ "Ă", "Â", "Î", "Ľ", "Ń", "Ş", "Ţ" ],
+               'rup' => [ "Ă", "Â", "Î", "Ľ", "Ń", "Ş", "Ţ" ], // not in libicu
                'sco' => [],
+               'se' => [
+                       'Á', 'Č', 'Ʒ', 'Ǯ', 'Đ', 'Ǧ', 'Ǥ', 'Ǩ', 'Ŋ',
+                       'Š', 'Ŧ', 'Ž', 'Ø', 'Æ', 'Ȧ', 'Ä', 'Ö'
+               ],
+               'si' => [ "\xe0\xb6\x82", "\xe0\xb6\x83", "\xe0\xb6\xa4" ],
                'sl' => [ "Č", "Š", "Ž" ],
                'smn' => [ "Á", "Č", "Đ", "Ŋ", "Š", "Ŧ", "Ž", "Æ", "Ø", "Å", "Ä", "Ö" ],
                'sq' => [ "Ç", "Dh", "Ë", "Gj", "Ll", "Nj", "Rr", "Sh", "Th", "Xh", "Zh" ],
+               'sr-Latn' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
+               'sw' => [],
+               'te' => [ "\xe0\xb0\x81", "\xe0\xb0\x82", "\xe0\xb0\x83" ],
+               'th' => [ "ฯ", "\xe0\xb9\x86", "\xe0\xb9\x8d", "\xe0\xb8\xba" ],
                'tk' => [ "Ç", "Ä", "Ž", "Ň", "Ö", "Ş", "Ü", "Ý" ],
-               'tl' => [ "Ñ", "Ng" ],
+               'tl' => [ "Ñ", "Ng" ], // not in libicu
+               'to' => [ "Ng", "ʻ" ],
                'tr' => [ "Ç", "Ğ", "İ", "Ö", "Ş", "Ü" ],
-               'tt' => [ "Ә", "Ө", "Ү", "Җ", "Ң", "Һ" ],
-               'uz' => [ "Ch", "G'", "Ng", "O'", "Sh" ],
+               'tt' => [ "Ә", "Ө", "Ү", "Җ", "Ң", "Һ" ], // not in libicu
+               'uz' => [ "Ch", "G'", "Ng", "O'", "Sh" ], // not in libicu
+               'vo' => [ "Ä", "Ö", "Ü" ],
+               'yi' => [
+                       "\xd7\x91\xd6\xbf", "\xd7\x9b\xd6\xbc", "\xd7\xa4\xd6\xbc",
+                       "\xd7\xa9\xd7\x82", "\xd7\xaa\xd6\xbc"
+               ],
+               'yo' => [ "Ẹ", "Gb", "Ọ", "Ṣ" ],
+               'zu' => [],
        ];
 
        /**