diff options
author | Mike FABIAN <mfabian@redhat.com> | 2017-12-11 18:26:22 +0100 |
---|---|---|
committer | Mike FABIAN <mfabian@redhat.com> | 2018-02-27 17:47:50 +0100 |
commit | 159738548130d5ac4fe6178977e940ed5f8cfdc4 (patch) | |
tree | 03f90b90e7bb794cfdbd4b3e66c9fff7ad6a9b24 /localedata/locales/mr_IN | |
parent | ce6636b06b67d6bb9b3d6927bf2a926b9b7478f5 (diff) | |
download | glibc-159738548130d5ac4fe6178977e940ed5f8cfdc4.tar glibc-159738548130d5ac4fe6178977e940ed5f8cfdc4.tar.gz glibc-159738548130d5ac4fe6178977e940ed5f8cfdc4.tar.bz2 glibc-159738548130d5ac4fe6178977e940ed5f8cfdc4.zip |
Adapt collation in several locales to the new iso14651_t1_common file
[BZ #22550] - es_ES locale (and other es_* locales): collation should
treat ñ as a primary different character, sync the collation
for Spanish with CLDR
[BZ #21547] - Tibetan script collation broken (Dzongkha and Tibetan)
* localedata/Makefile: Add new test files.
* localedata/lv_LV.UTF-8.in: Adapt test file to new collation order.
* localedata/sv_SE.ISO-8859-1.in: Adapt test file to new collation order.
* localedata/uk_UA.UTF-8.in: Adapt test file to new collation order.
* localedata/am_ET.UTF-8.in: New test file.
* localedata/az_AZ.UTF-8.in: Likewise.
* localedata/be_BY.UTF-8.in: Likewise.
* localedata/ber_DZ.UTF-8.in: Likewise.
* localedata/ber_MA.UTF-8.in: Likewise.
* localedata/bg_BG.UTF-8.in: Likewise.
* localedata/br_FR.UTF-8.in: Likewise.
* localedata/cmn_TW.UTF-8.in: Likewise.
* localedata/crh_UA.UTF-8.in: Likewise.
* localedata/csb_PL.UTF-8.in: Likewise.
* localedata/cv_RU.UTF-8.in: Likewise.
* localedata/cy_GB.UTF-8.in: Likewise.
* localedata/dz_BT.UTF-8.in: Likewise.
* localedata/eo.UTF-8.in: Likewise.
* localedata/es_ES.UTF-8.in: Likewise.
* localedata/fa_IR.UTF-8.in: Likewise.
* localedata/fi_FI.UTF-8.in: Likewise.
* localedata/fil_PH.UTF-8.in: Likewise.
* localedata/fur_IT.UTF-8.in: Likewise.
* localedata/gez_ER.UTF-8@abegede.in: Likewise.
* localedata/ha_NG.UTF-8.in: Likewise.
* localedata/ig_NG.UTF-8.in: Likewise.
* localedata/ik_CA.UTF-8.in: Likewise.
* localedata/kk_KZ.UTF-8.in: Likewise.
* localedata/ku_TR.UTF-8.in: Likewise.
* localedata/ky_KG.UTF-8.in: Likewise.
* localedata/ln_CD.UTF-8.in: Likewise.
* localedata/mi_NZ.UTF-8.in: Likewise.
* localedata/ml_IN.UTF-8.in: Likewise.
* localedata/mn_MN.UTF-8.in: Likewise.
* localedata/mr_IN.UTF-8.in: Likewise.
* localedata/mt_MT.UTF-8.in: Likewise.
* localedata/nb_NO.UTF-8.in: Likewise.
* localedata/om_KE.UTF-8.in: Likewise.
* localedata/os_RU.UTF-8.in: Likewise.
* localedata/ps_AF.UTF-8.in: Likewise.
* localedata/ro_RO.UTF-8.in: Likewise.
* localedata/ru_RU.UTF-8.in: Likewise.
* localedata/sc_IT.UTF-8.in: Likewise.
* localedata/se_NO.UTF-8.in: Likewise.
* localedata/sq_AL.UTF-8.in: Likewise.
* localedata/sv_SE.UTF-8.in: Likewise.
* localedata/szl_PL.UTF-8.in: Likewise.
* localedata/tg_TJ.UTF-8.in: Likewise.
* localedata/tk_TM.UTF-8.in: Likewise.
* localedata/tt_RU.UTF-8.in: Likewise.
* localedata/tt_RU.UTF-8@iqtelif.in: Likewise.
* localedata/ug_CN.UTF-8.in: Likewise.
* localedata/uz_UZ.UTF-8.in: Likewise.
* localedata/vi_VN.UTF-8.in: Likewise.
* localedata/yi_US.UTF-8.in: Likewise.
* localedata/yo_NG.UTF-8.in: Likewise.
* localedata/zh_CN.UTF-8.in: Likewise.
* localedata/locales/am_ET: Adapt collation rules to new iso14651_t1_common
file and fix bugs in the collation.
* localedata/locales/az_AZ: Likewise.
* localedata/locales/be_BY: Likewise.
* localedata/locales/ber_DZ: Likewise.
* localedata/locales/ber_MA: Likewise.
* localedata/locales/bg_BG: Likewise.
* localedata/locales/br_FR: Likewise.
* localedata/locales/br_FR@euro: Likewise.
* localedata/locales/ca_ES: Likewise.
* localedata/locales/cns11643_stroke: Likewise.
* localedata/locales/crh_UA: Likewise.
* localedata/locales/cs_CZ: Likewise.
* localedata/locales/csb_PL: Likewise.
* localedata/locales/cv_RU: Likewise.
* localedata/locales/cy_GB: Likewise.
* localedata/locales/da_DK: Likewise.
* localedata/locales/dz_BT: Likewise.
* localedata/locales/en_CA: Likewise.
* localedata/locales/eo: Likewise.
* localedata/locales/es_CU: Likewise.
* localedata/locales/es_EC: Likewise.
* localedata/locales/es_ES: Likewise.
* localedata/locales/es_US: Likewise.
* localedata/locales/et_EE: Likewise.
* localedata/locales/fa_IR: Likewise.
* localedata/locales/fi_FI: Likewise.
* localedata/locales/fil_PH: Likewise.
* localedata/locales/fur_IT: Likewise.
* localedata/locales/gez_ER@abegede: Likewise.
* localedata/locales/ha_NG: Likewise.
* localedata/locales/hr_HR: Likewise.
* localedata/locales/hsb_DE: Likewise.
* localedata/locales/hu_HU: Likewise.
* localedata/locales/ig_NG: Likewise.
* localedata/locales/ik_CA: Likewise.
* localedata/locales/is_IS: Likewise.
* localedata/locales/iso14651_t1_pinyin: Likewise.
* localedata/locales/kk_KZ: Likewise.
* localedata/locales/ku_TR: Likewise.
* localedata/locales/ky_KG: Likewise.
* localedata/locales/ln_CD: Likewise.
* localedata/locales/lt_LT: Likewise.
* localedata/locales/lv_LV: Likewise.
* localedata/locales/mi_NZ: Likewise.
* localedata/locales/ml_IN: Likewise.
* localedata/locales/mn_MN: Likewise.
* localedata/locales/mr_IN: Likewise.
* localedata/locales/mt_MT: Likewise.
* localedata/locales/nb_NO: Likewise.
* localedata/locales/om_KE: Likewise.
* localedata/locales/os_RU: Likewise.
* localedata/locales/pl_PL: Likewise.
* localedata/locales/ps_AF: Likewise.
* localedata/locales/ro_RO: Likewise.
* localedata/locales/ru_RU: Likewise.
* localedata/locales/ru_UA: Likewise.
* localedata/locales/sc_IT: Likewise.
* localedata/locales/se_NO: Likewise.
* localedata/locales/si_LK: Likewise.
* localedata/locales/sq_AL: Likewise.
* localedata/locales/sv_FI: Likewise.
* localedata/locales/sv_FI@euro: Likewise.
* localedata/locales/sv_SE: Likewise.
* localedata/locales/szl_PL: Likewise.
* localedata/locales/tg_TJ: Likewise.
* localedata/locales/ti_ER: Likewise.
* localedata/locales/tk_TM: Likewise.
* localedata/locales/tl_PH: Likewise.
* localedata/locales/tr_TR: Likewise.
* localedata/locales/tt_RU: Likewise.
* localedata/locales/tt_RU@iqtelif: Likewise.
* localedata/locales/ug_CN: Likewise.
* localedata/locales/uk_UA: Likewise.
* localedata/locales/uz_UZ: Likewise.
* localedata/locales/uz_UZ@cyrillic: Likewise.
* localedata/locales/vi_VN: Likewise.
* localedata/locales/yi_US: Likewise.
* localedata/locales/yo_NG: Likewise.
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 |