diff options
Diffstat (limited to 'localedata/locales/mr_IN')
| -rw-r--r-- | localedata/locales/mr_IN | 76 |
1 files changed, 65 insertions, 11 deletions
diff --git a/localedata/locales/mr_IN b/localedata/locales/mr_IN index 179ae3c08c..c8d4e4b84e 100644 --- a/localedata/locales/mr_IN +++ b/localedata/locales/mr_IN @@ -43,28 +43,82 @@ copy "hi_IN" END LC_CTYPE LC_COLLATE - -% Copy the template from ISO/IEC 14651 +% CLDR collation rules for Marathi: +% (see: https://unicode.org/cldr/trac/browser/trunk/common/collation/mr.xml) +% +% <collation type="standard"> +% <cr><![CDATA[ +% [normalization on] +% [reorder Deva Beng Guru Gujr Orya Taml Telu Knda Mlym Sinh] +% # +% # The following tailoring is an adjustment of the +% # DUCET collation order for ANUSVARA, CANDRABINDU, +% # and VISARGA. Instead of being sorted with secondary +% # weights, they are collated on primary level before +% # the independent vowels. CANDRABINDU is secondary +% # different from ANUSVARA. This gives a sort order +% # similar to Hindi. +% # +% &ॐ<ं<<ँ<ः +% # +% # The following tailoring is an adjustment of the +% # DUCET collation order for LLA. Instead of being +% # sorted after LA, LLA is sorted after HA. +% # +% &ह<ळ +% # +% # KSSA is sorted after LLA. +% # +% <क्ष +% # +% # JNYA is sorted after KSSA. +% # +% <ज्ञ +% ]]></cr> +% </collation> +% +% And CLDR also lists the following +% index characters: +% (see: https://unicode.org/cldr/trac/browser/trunk/common/main/mr.xml) +% +% <exemplarCharacters type="index">[\u200D ॐ \u0902 ः अ आ इ ई उ ऊ ऋ ऌ ए ऐ ऑ ओ औ क ख ग घ ङ च छ ज झ ञ ट ठ ड ढ ण त थ द ध न प फ ब भ म य र ल व श ष स ह ळ ऽ \u0945 \u094D]</exemplarCharacters> +% +% The following rules implement the same order for glibc. copy "iso14651_t1" -% customize sorting required for mr_IN -collating-element <dv_ksha> from "<U0915><U094D><U0937>" -collating-element <dv_dnya> from "<U091C><U094D><U091E>" -collating-element <dv_shra> from "<U0936><U094D><U0930>" +collating-symbol <anusvara> +collating-symbol <candrabindu> +collating-symbol <visarga> + +collating-element <dv_ksha> from "<U0915><U094D><U0937>" % क ् ष = क्ष +collating-element <dv_dnya> from "<U091C><U094D><U091E>" % ज ् ञ = ज्ञ +% This not in CLDR but it was in the old mr_IN collation in glibc: +collating-element <dv_shra> from "<U0936><U094D><U0930>" % श ् र = श्र collating-symbol <d_ksha> collating-symbol <d_dnya> collating-symbol <d_shra> -reorder-after <d_ha> +reorder-after <S0950> % DEVANAGARI OM +<anusvara> +<visarga> + +<U0902> <anusvara>;<ANUSVARA>;<MIN>;<U0902> % DEVANAGARI SIGN ANUSVARA +<U0901> <anusvara>;"<ANUSVARA><VRNT1>";<MIN>;<U0901> % DEVANAGARI SIGN CANDRABINDU +<U0903> <visarga>;<VISARGA>;<MIN>;<U0903> % DEVANAGARI SIGN VISARGA + +reorder-after <S0939> % <U0939> <S0939>;<BASE>;<MIN>;<U0939> % DEVANAGARI LETTER HA +<S0933> % DEVANAGARI LETTER LLA <d_ksha> <d_dnya> +% This not in CLDR but it was in the old mr_IN collation in glibc: <d_shra> -reorder-after <U0939> -<dv_ksha> <d_ksha>;<BAS>;<MIN>;IGNORE -<dv_dnya> <d_dnya>;<BAS>;<MIN>;IGNORE -<dv_shra> <d_shra>;<BAS>;<MIN>;IGNORE +<U0933> <S0933>;<BASE>;<MIN>;<U0933> % DEVANAGARI LETTER LLA +<dv_ksha> <d_ksha>;<BASE>;<MIN>;"<U0915><U094D><U0937>" % क ् ष = क्ष +<dv_dnya> <d_dnya>;<BASE>;<MIN>;IGNORE +% This not in CLDR but it was in the old mr_IN collation in glibc: +<dv_shra> <d_shra>;<BASE>;<MIN>;IGNORE reorder-end |