From 33648048a420946e464ea40183ee0eb19aca6282 Mon Sep 17 00:00:00 2001
From: Santhosh Thottingal <santhosh.thottingal@gmail.com>
Date: Fri, 26 Dec 2008 23:42:53 +0530
Subject: corrected with implicit a for all consonants, added canonical
 equivalende definition, fixed samvruthokaram positioning

---
 collation/iso14651_t1_common | 185 ++++++++++++++++++++++++++++++-------------
 1 file changed, 128 insertions(+), 57 deletions(-)

diff --git a/collation/iso14651_t1_common b/collation/iso14651_t1_common
index 3e963d9..393359b 100644
--- a/collation/iso14651_t1_common
+++ b/collation/iso14651_t1_common
@@ -664,9 +664,47 @@ collating-symbol <g-halant>
 # <NKT> denotes Nukta characters
 # <NUM> denotes Numerals
 #
+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-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-a>
 collating-symbol <mlvw-aa>
 collating-symbol <mlvw-i>
 collating-symbol <mlvw-ii>
@@ -697,12 +735,12 @@ collating-symbol <ml-nya>
 collating-symbol <ml-ta>
 collating-symbol <ml-tta>
 collating-symbol <ml-da>
-collating-symbol <ml-dda>
+collating-symbol <ml-dha>
 collating-symbol <ml-nna>
 collating-symbol <ml-tha>
 collating-symbol <ml-thha>
-collating-symbol <ml-dha>
-collating-symbol <ml-dhha>
+collating-symbol <ml-dda>
+collating-symbol <ml-ddha>
 collating-symbol <ml-na>
 collating-symbol <ml-pa>
 collating-symbol <ml-pha>
@@ -722,6 +760,7 @@ collating-symbol <ml-sa>
 collating-symbol <ml-ha>
 collating-symbol <ml-avagrah>
 collating-symbol <ml-zha>
+collating-symbol <mlvs-a>
 collating-symbol <mlvs-aa>
 collating-symbol <mlvs-i>
 collating-symbol <mlvs-ii>
@@ -1341,7 +1380,7 @@ endif
 #
 # collation weights in order
 
-<ml-virama>
+
 <mlvs-aa>
 <mlvs-i>
 <mlvs-ii>
@@ -1357,9 +1396,9 @@ endif
 <mlvs-shorto>
 <mlvs-o>
 <mlvs-au>
+<ml-virama>
 <ml-visarga>
 <mlvw-shorta>
-<mlvw-a>
 <mlvw-aa>
 <mlvw-i>
 <mlvw-ii>
@@ -1390,12 +1429,12 @@ endif
 <ml-ta>
 <ml-tta>
 <ml-da>
-<ml-dda>
+<ml-dha>
 <ml-nna>
 <ml-tha>
 <ml-thha>
-<ml-dha>
-<ml-dhha>
+<ml-dda>
+<ml-ddha>
 <ml-na>
 <ml-pa>
 <ml-pha>
@@ -3394,8 +3433,7 @@ order_start <MALAYALAM>;forward;forward;forward;forward,position
 <U0D6D> <7>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
 <U0D6E> <8>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
 <U0D6F> <9>;"<BAS><NUM>";"<MIN><MIN>";IGNORE
-<U0D04> <mlvw-shorta> ;<BAS>;<MIN>;IGNORE
-<U0D05> <mlvw-a> ;<BAS>;<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
@@ -3411,55 +3449,84 @@ order_start <MALAYALAM>;forward;forward;forward;forward,position
 <U0D12> <mlvw-shorto>;<BAS>;<MIN>;IGNORE
 <U0D13> <mlvw-o>;<BAS>;<MIN>;IGNORE
 <U0D14> <mlvw-au>;<BAS>;<MIN>;IGNORE
-<U0D15> <ml-ka>;<BAS>;<MIN>;IGNORE
-<U0D58> <ml-ka>;"<BAS><NKT>";"<MIN><MIN>";IGNORE
-<U0D16> <ml-kha>;<BAS>;<MIN>;IGNORE
-<U0D59> <ml-kha>;"<BAS><NKT>";"<MIN><MIN>";IGNORE
-<U0D17> <ml-ga>;<BAS>;<MIN>;IGNORE
-<U0D5A> <ml-ga>;"<BAS><NKT>";"<MIN><MIN>";IGNORE
-<U0D7B> <ml-gga>;<BAS>;<MIN>;IGNORE
-<U0D18> <ml-gha>;<BAS>;<MIN>;IGNORE
-<U0D19> <ml-nga>;<BAS>;<MIN>;IGNORE
-<U0D1A> <ml-cha>;<BAS>;<MIN>;IGNORE
-<U0D1B> <ml-chha>;<BAS>;<MIN>;IGNORE
-<U0D1C> <ml-ja>;<BAS>;<MIN>;IGNORE
-<U0D7C> <ml-jja>;<BAS>;<MIN>;IGNORE
-<U0D1D> <ml-jha>;<BAS>;<MIN>;IGNORE
-<U0D1E> <ml-nya>;<BAS>;<MIN>;IGNORE
-<U0D1F> <ml-ta>;<BAS>;<MIN>;IGNORE
-<U0D20> <ml-tta>;<BAS>;<MIN>;IGNORE
-<U0D21> <ml-da>;<BAS>;<MIN>;IGNORE
-<U0D7E> <ml-dda>;<BAS>;<MIN>;IGNORE
-<U0D23> <ml-nna>;<BAS>;<MIN>;IGNORE
-<U0D24> <ml-tha>;<BAS>;<MIN>;IGNORE
-<U0D25> <ml-thha>;<BAS>;<MIN>;IGNORE
-<U0D26> <ml-dha>;<BAS>;<MIN>;IGNORE
-<U0D27> <ml-dhha>;<BAS>;<MIN>;IGNORE
-<U0D28> <ml-na>;<BAS>;<MIN>;IGNORE
-<U0D2A> <ml-pa>;<BAS>;<MIN>;IGNORE
-<U0D2B> <ml-pha>;<BAS>;<MIN>;IGNORE
-<U0D2C> <ml-ba>;<BAS>;<MIN>;IGNORE
-<U0D7F> <ml-bba>;<BAS>;<MIN>;IGNORE
-<U0D2D> <ml-bha>;<BAS>;<MIN>;IGNORE
-<U0D01> <ml-anuswara>;<BAS>;<MIN>;IGNORE
-<U0D2E> <ml-ma>;<BAS>;<MIN>;IGNORE
-<U0D2F> <ml-ya>;<BAS>;<MIN>;IGNORE
-<U0D30> <ml-ra>;<BAS>;<MIN>;IGNORE
-<U0D32> <ml-la>;<BAS>;<MIN>;IGNORE
-<U0D35> <ml-va>;<BAS>;<MIN>;IGNORE
-<U0D37> <ml-ssa>;<BAS>;<MIN>;IGNORE
-<U0D36> <ml-sha>;<BAS>;<MIN>;IGNORE
-<U0D38> <ml-sa>;<BAS>;<MIN>;IGNORE
-<U0D39> <ml-ha>;<BAS>;<MIN>;IGNORE
-<U0D33> <ml-lla>;<BAS>;<MIN>;IGNORE
-<U0D34> <ml-zha>;<BAS>;<MIN>;IGNORE
-<U0D31> <ml-rra>;<BAS>;<MIN>;IGNORE
+<ml-chillu-k> "<ml-ka><ml-virama>";<BAS>;<MIN>;IGNORE # ക =ക   + ്  + zwj
+<U0D15>  "<ml-ka><ml-virama><mlvw-shorta>";<BAS>;<MIN>;IGNORE # ക =ക   + ്  + അ
+<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-na><ml-virama>";<BAS>;<MIN>;IGNORE # ന്‍= ന  + ്  + zwj
+<U0D28>  "<ml-na><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
+<U0D01>  "<ml-ma><ml-virama><mlvw-shorta>";<BAS>;<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><ml-virama>";<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
-<U0D4D> <ml-virama>;<BAS>;<MIN>;IGNORE
 <U0D3E> <mlvs-aa>;<BAS>;<MIN>;IGNORE
 <U0D3F> <mlvs-i>;<BAS>;<MIN>;IGNORE
 <U0D40> <mlvs-ii>;<BAS>;<MIN>;IGNORE
-<U0D41> <mlvs-u>;<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
@@ -3471,8 +3538,12 @@ order_start <MALAYALAM>;forward;forward;forward;forward,position
 <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
 
 
 
-- 
cgit