* locales/iso14651_t1_common: Add rules for sorting Malayalam.

Patch by Santhosh Thottingal <santhosh.thottingal@gmail.com>.
This commit is contained in:
Ulrich Drepper 2009-02-11 15:42:53 +00:00
parent 40e2fc8b70
commit 638633961d
2 changed files with 330 additions and 0 deletions

View File

@ -1,3 +1,8 @@
2009-02-11 Ulrich Drepper <drepper@redhat.com>
* locales/iso14651_t1_common: Add rules for sorting Malayalam.
Patch by Santhosh Thottingal <santhosh.thottingal@gmail.com>.
2009-02-06 Ulrich Drepper <drepper@redhat.com>
[BZ #7098]

View File

@ -66,6 +66,7 @@ script <TELUGU>
script <GURUMUKHI>
script <KANNADA>
script <SINHALA>
script <MALAYALAM>
# Déclaration des symboles internes / Declaration of internal symbols
#
@ -910,6 +911,129 @@ collating-symbol <kvd-visarg>
collating-symbol <k-halant>
collating-symbol <k-lenght_mark>
collating-symbol <k-ai_lenght_mark>
#
# <MALAYALAM>
# mlvs- denotes Malayalam vowel sign
# mlvw- denotes Malayalam vowel
# ml-visarga - dentos Malayalam Visarga
# consonant + virama is considered half of consonant or consonant without vowel part
# so it consonant + virama should be considered as cluster and should be
# sorted before the consonant. All consonants are considered to have an implicit a vowel
# part associated with it.
collating-element <ml-chillu-n> from "<U0D28><U0D4D>"
collating-element <ml-chillu-nn> from "<U0D23><U0D4D>"
collating-element <ml-chillu-r> from "<U0D30><U0D4D>"
collating-element <ml-chillu-l> from "<U0D32><U0D4D>"
collating-element <ml-chillu-ll> from "<U0D33><U0D4D>"
collating-element <ml-chillu-k> from "<U0D15><U0D4D>"
collating-element <ml-kh> from "<U0D16><U0D4D>"
collating-element <ml-g> from "<U0D17><U0D4D>"
collating-element <ml-gh> from "<U0D18><U0D4D>"
collating-element <ml-ng> from "<U0D19><U0D4D>"
collating-element <ml-ch> from "<U0D1A><U0D4D>"
collating-element <ml-chh> from "<U0D1B><U0D4D>"
collating-element <ml-j> from "<U0D1C><U0D4D>"
collating-element <ml-jh> from "<U0D1D><U0D4D>"
collating-element <ml-ny> from "<U0D1E><U0D4D>"
collating-element <ml-t> from "<U0D1F><U0D4D>"
collating-element <ml-tt> from "<U0D20><U0D4D>"
collating-element <ml-d> from "<U0D21><U0D4D>"
collating-element <ml-dh> from "<U0D22><U0D4D>"
collating-element <ml-th> from "<U0D24><U0D4D>"
collating-element <ml-thh> from "<U0D25><U0D4D>"
collating-element <ml-dd> from "<U0D26><U0D4D>"
collating-element <ml-ddh> from "<U0D27><U0D4D>"
collating-element <ml-p> from "<U0D2A><U0D4D>"
collating-element <ml-ph> from "<U0D2B><U0D4D>"
collating-element <ml-b> from "<U0D2C><U0D4D>"
collating-element <ml-bh> from "<U0D2D><U0D4D>"
collating-element <ml-m> from "<U0D2E><U0D4D>"
collating-element <ml-y> from "<U0D2F><U0D4D>"
collating-element <ml-v> from "<U0D35><U0D4D>"
collating-element <ml-s> from "<U0D38><U0D4D>"
collating-element <ml-ss> from "<U0D36><U0D4D>"
collating-element <ml-sh> from "<U0D37><U0D4D>"
collating-element <ml-h> from "<U0D39><U0D4D>"
collating-element <ml-zh> from "<U0D34><U0D4D>"
collating-element <ml-rr> from "<U0D31><U0D4D>"
collating-element <ml-samvruthokaram> from "<U0D41><U0D4D>"
collating-element <ml-split-o> from "<U0D46><U0D3E>" # U+0D4A MALAYALAM VOWEL SIGN O = U+0D46 MALAYALAM VOWEL SIGN E + U+0D3E MALAYALAM VOWEL SIGN AA
collating-element <ml-split-oo> from "<U0D47><U0D3E>" # U+0D4B MALAYALAM VOWEL SIGN OO = U+0D47 MALAYALAM VOWEL SIGN EE + U+0D3E MALAYALAM VOWEL SIGN AA
collating-element <ml-split-au> from "<U0D46><U0D57>" # U+0D4C MALAYALAM VOWEL SIGN AU = U+0D46 MALAYALAM VOWEL SIGN E + U+0D57 MALAYALAM AU LENGTH MARK
# defning symbols
collating-symbol <mlvw-shorta>
collating-symbol <mlvw-aa>
collating-symbol <mlvw-i>
collating-symbol <mlvw-ii>
collating-symbol <mlvw-u>
collating-symbol <mlvw-uu>
collating-symbol <mlvw-vocalicr>
collating-symbol <mlvw-vocalicrr>
collating-symbol <mlvw-vocalicl>
collating-symbol <mlvw-vocalicll>
collating-symbol <mlvw-shorte>
collating-symbol <mlvw-e>
collating-symbol <mlvw-ai>
collating-symbol <mlvw-shorto>
collating-symbol <mlvw-o>
collating-symbol <mlvw-au>
collating-symbol <ml-ka>
collating-symbol <ml-kha>
collating-symbol <ml-ga>
collating-symbol <ml-gga>
collating-symbol <ml-gha>
collating-symbol <ml-nga>
collating-symbol <ml-cha>
collating-symbol <ml-chha>
collating-symbol <ml-ja>
collating-symbol <ml-jja>
collating-symbol <ml-jha>
collating-symbol <ml-nya>
collating-symbol <ml-ta>
collating-symbol <ml-tta>
collating-symbol <ml-da>
collating-symbol <ml-dha>
collating-symbol <ml-nna>
collating-symbol <ml-tha>
collating-symbol <ml-thha>
collating-symbol <ml-dda>
collating-symbol <ml-ddha>
collating-symbol <ml-na>
collating-symbol <ml-pa>
collating-symbol <ml-pha>
collating-symbol <ml-ba>
collating-symbol <ml-bba>
collating-symbol <ml-bha>
collating-symbol <ml-ma>
collating-symbol <ml-ya>
collating-symbol <ml-ra>
collating-symbol <ml-rra>
collating-symbol <ml-la>
collating-symbol <ml-lla>
collating-symbol <ml-va>
collating-symbol <ml-sha>
collating-symbol <ml-ssa>
collating-symbol <ml-sa>
collating-symbol <ml-ha>
collating-symbol <ml-avagrah>
collating-symbol <ml-zha>
collating-symbol <mlvs-aa>
collating-symbol <mlvs-i>
collating-symbol <mlvs-ii>
collating-symbol <mlvs-u>
collating-symbol <mlvs-uu>
collating-symbol <mlvs-vocalicr>
collating-symbol <mlvs-vocalicrr>
collating-symbol <mlvs-vocalicl>
collating-symbol <mlvs-vocalicll>
collating-symbol <mlvs-shorte>
collating-symbol <mlvs-e>
collating-symbol <mlvs-ai>
collating-symbol <mlvs-shorto>
collating-symbol <mlvs-o>
collating-symbol <mlvs-au>
collating-symbol <ml-visarga>
collating-symbol <ml-virama>
# Ordre des symboles internes / Order of internal symbols
#
@ -1733,6 +1857,83 @@ collating-symbol <k-ai_lenght_mark>
<k-halant>
<k-lenght_mark>
<k-ai_lenght_mark>
#
# <MALAYALAM>
#
# collation weights in order
<mlvw-shorta>
<mlvw-aa>
<mlvw-i>
<mlvw-ii>
<mlvw-u>
<mlvw-uu>
<mlvw-vocalicr>
<mlvw-vocalicrr>
<mlvw-vocalicl>
<mlvw-vocalicll>
<mlvw-shorte>
<mlvw-e>
<mlvw-ai>
<mlvw-shorto>
<mlvw-o>
<mlvw-au>
<ml-ka>
<ml-kha>
<ml-ga>
<ml-gga>
<ml-gha>
<ml-nga>
<ml-cha>
<ml-chha>
<ml-ja>
<ml-jja>
<ml-jha>
<ml-nya>
<ml-ta>
<ml-tta>
<ml-da>
<ml-dha>
<ml-nna>
<ml-tha>
<ml-thha>
<ml-dda>
<ml-ddha>
<ml-na>
<ml-pa>
<ml-pha>
<ml-ba>
<ml-bba>
<ml-bha>
<ml-ma>
<ml-ya>
<ml-ra>
<ml-la>
<ml-va>
<ml-ssa>
<ml-sha>
<ml-sa>
<ml-ha>
<ml-lla>
<ml-zha>
<ml-rra>
<ml-avagrah>
<ml-virama>
<mlvs-aa>
<mlvs-i>
<mlvs-ii>
<mlvs-u>
<mlvs-uu>
<mlvs-vocalicr>
<mlvs-vocalicrr>
<mlvs-vocalicl>
<mlvs-vocalicll>
<mlvs-shorte>
<mlvs-e>
<mlvs-ai>
<mlvs-shorto>
<mlvs-o>
<mlvs-au>
<ml-visarga>
order_start <SPECIAL>;forward;backward;forward;forward,position
#
@ -4052,6 +4253,130 @@ order_start <SINHALA>;forward;forward;forward;forward,position
<U0DDE> <U0DDE>;<BAS>;<MIN>;IGNORE
<U0DCA> <U0DCA>;<BAS>;<MIN>;IGNORE
order_start <MALAYALAM>;forward;forward;forward;forward,position
<U0D66> <0>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D67> <1>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D68> <2>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D69> <3>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D6A> <4>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D6B> <5>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D6C> <6>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D6D> <7>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D6E> <8>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D6F> <9>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
<U0D05> <mlvw-shorta> ;<BAS>;<MIN>;IGNORE
<U0D06> <mlvw-aa> ;<BAS>;<MIN>;IGNORE
<U0D07> <mlvw-i> ;<BAS>;<MIN>;IGNORE
<U0D08> <mlvw-ii> ;<BAS>;<MIN>;IGNORE
<U0D09> <mlvw-u> ;<BAS>;<MIN>;IGNORE
<U0D0A> <mlvw-uu>;<BAS>;<MIN>;IGNORE
<U0D0B> <mlvw-vocalicr>;<BAS>;<MIN>;IGNORE
<U0D60> <mlvw-vocalicrr>;<BAS>;<MIN>;IGNORE
<U0D0C> <mlvw-vocalicl>;<BAS>;<MIN>;IGNORE
<U0D61> <mlvw-vocalicll>;<BAS>;<MIN>;IGNORE
<U0D0E> <mlvw-shorte>;<BAS>;<MIN>;IGNORE
<U0D0F> <mlvw-e>;<BAS>;<MIN>;IGNORE
<U0D10> <mlvw-ai>;<BAS>;<MIN>;IGNORE
<U0D12> <mlvw-shorto>;<BAS>;<MIN>;IGNORE
<U0D13> <mlvw-o>;<BAS>;<MIN>;IGNORE
<U0D14> <mlvw-au>;<BAS>;<MIN>;IGNORE
<ml-chillu-k> "<ml-ka><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D15> "<ml-ka><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-kh> "<ml-kha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D16> "<ml-kha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-g> "<ml-ga><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D17> "<ml-ga><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-gh> "<ml-gha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D18> "<ml-gha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-ng> "<ml-nga><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D19> "<ml-nga><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-ch> "<ml-cha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D1A> "<ml-cha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-chh> "<ml-chha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D1B> "<ml-chha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-j> "<ml-ja><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D1C> "<ml-ja><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-jh> "<ml-jha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D1D> "<ml-jha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-ny> "<ml-nya><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D1E> "<ml-nya><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-t> "<ml-ta><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D1F> "<ml-ta><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-tt> "<ml-tta><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D20> "<ml-tta><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-d> "<ml-da><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D21> "<ml-da><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-dh> "<ml-dha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D22> "<ml-dha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-chillu-nn> "<ml-nna><ml-virama>";<BAS>;<MIN>;IGNORE # ണ്‍ = ണ + ് + zwj
<U0D23> "<ml-nna><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE # ണ = ണ + ് + അ
<ml-th> "<ml-tha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D24> "<ml-tha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-thh> "<ml-thha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D25> "<ml-thha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-dd> "<ml-dda><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D26> "<ml-dda><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-ddh> "<ml-ddha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D27> "<ml-ddha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-chillu-n> "<ml-chillu-n>";<BAS>;<MIN>;IGNORE # ന്‍= ന + ് + zwj
<U0D28> "<ml-chillu-n><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE #ന = ന + ് + അ
<ml-p> "<ml-pa><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D2A> "<ml-pa><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-ph> "<ml-pha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D2B> "<ml-pha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-b> "<ml-ba><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D2C> "<ml-ba><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-bh> "<ml-bha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D2D> "<ml-bha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<U0D02> "<ml-ma><ml-virama>";<BAS>;<MIN>;IGNORE # = മ + ്
<ml-m> "<ml-ma><ml-virama>";"<BAS><ml-virama>";<MIN>;IGNORE # = മ + ്
<U0D2E> "<ml-ma><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE # മ = മ + ് + അ
<ml-y> "<ml-ya><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D2F> "<ml-ya><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-chillu-r> "<ml-ra><ml-virama>";<BAS>;<MIN>;IGNORE # ര = ര + ് + zwj
<U0D30> "<ml-ra><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE # ര = ര + ് + അ
<ml-chillu-l> <ml-la>;<BAS>;<MIN>;IGNORE # ല്‍ = ല + ് + zwj
<U0D32> "<ml-la><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE # ല = ല + ് + അ
<ml-v> "<ml-va><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D35> "<ml-va><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-ss> "<ml-ssa><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D37> "<ml-ssa><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-sh> "<ml-sha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D36> "<ml-sha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-s> "<ml-sa><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D38> "<ml-sa><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-h> "<ml-ha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D39> "<ml-ha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-chillu-ll> "<ml-lla><ml-virama>";<BAS>;<MIN>;IGNORE # ള്‍ = ള + ് + zwj
<U0D33> "<ml-lla><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE # ള = ള + ് + അ
<ml-zh> "<ml-zha><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D34> "<ml-zha><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<ml-rr> "<ml-rra><ml-virama>";<BAS>;<MIN>;IGNORE
<U0D31> "<ml-rra><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE
<U0D3D> <ml-avagrah>;<BAS>;<MIN>;IGNORE
<U0D3E> <mlvs-aa>;<BAS>;<MIN>;IGNORE
<U0D3F> <mlvs-i>;<BAS>;<MIN>;IGNORE
<U0D40> <mlvs-ii>;<BAS>;<MIN>;IGNORE
<ml-samvruthokaram> <mlvs-u>;<BAS>;<MIN>;IGNORE
<U0D41> <mlvs-u>;"<BAS><ml-samvruthokaram>";<MIN>;IGNORE # sort it after samvruthokaram
<U0D42> <mlvs-uu>;<BAS>;<MIN>;IGNORE
<U0D43> <mlvs-vocalicr>;<BAS>;<MIN>;IGNORE
<U0D44> <mlvs-vocalicrr>;<BAS>;<MIN>;IGNORE
<U0D62> <mlvs-vocalicl>;<BAS>;<MIN>;IGNORE
<U0D63> <mlvs-vocalicll>;<BAS>;<MIN>;IGNORE
<U0D46> <mlvs-shorte>;<BAS>;<MIN>;IGNORE
<U0D47> <mlvs-e>;<BAS>;<MIN>;IGNORE
<U0D48> <mlvs-ai>;<BAS>;<MIN>;IGNORE
<U0D4A> <mlvs-shorto>;<BAS>;<MIN>;IGNORE
<U0D4B> <mlvs-o>;<BAS>;<MIN>;IGNORE
<U0D4C> <mlvs-au>;<BAS>;<MIN>;IGNORE
<U0D57> <mlvs-au>;<BAS>;<MIN>;IGNORE
<U0D4D> <ml-virama>;<BAS>;<MIN>;IGNORE
<U0D03> <ml-visarga>;<BAS>;<MIN>;IGNORE
<ml-split-o> <mlvs-shorto>;<BAS>;<MIN>;IGNORE
<ml-split-oo> <mlvs-o>;<BAS>;<MIN>;IGNORE
<ml-split-au> <mlvs-au>;<BAS>;<MIN>;IGNORE
order_end
END LC_COLLATE