drop hopefully unnecessary catalan word breaking rules

various regression tests for the issues that prompted its inclusion all now
pass in its absence

Change-Id: Ia375322335b4272aa6c3d626b2d98bc64465bf1c

i18npool/CustomTarget_breakiterator.mk

@@ -70,7 +70,6 @@ i18npool_BRKTXTS := \
     char.brk \
     count_word_fi.brk \
     count_word.brk \
-    dict_word_ca.brk \
     dict_word_fi.brk \
     dict_word_he.brk \
     dict_word_hu.brk \

i18npool/source/breakiterator/data/dict_word_ca.txt

-#
-#   Copyright (C) 2002-2003, International Business Machines Corporation and others.
-#       All Rights Reserved.
-#
-#   file:  dict_word.txt   
-#
-#   ICU Word Break Rules
-#      See Unicode Standard Annex #29.
-#      These rules are based on Version 4.0.0, dated 2003-04-17
-#
-
-
-
-####################################################################################
-#
-#  Character class definitions from TR 29
-#
-####################################################################################
-$Katakana  = [[:Script = KATAKANA:] [:name = KATAKANA-HIRAGANA PROLONGED SOUND MARK:] 
-                                   [:name = HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
-                                   [:name = HALFWIDTH KATAKANA VOICED SOUND MARK:]
-                                   [:name = HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK:]];
-
-$Ideographic = [:Ideographic:];
-$Hangul = [:Script = HANGUL:];
-
-$ALetter   = [[:Alphabetic:] [:name= COMMERCIAL AT:] [:name= HEBREW PUNCTUATION GERESH:]
-                           - $Ideographic
-                           - $Katakana
-                           - $Hangul
-                           - [:Script = Thai:]
-                           - [:Script = Lao:]
-                           - [:Script = Hiragana:]];
-                           
-$MidLetter = [[:name = APOSTROPHE:] [:name = GRAVE ACCENT:] \u0084 [:name = SOFT HYPHEN:] [:name = MIDDLE DOT:] [:name = GREEK TONOS:] [:name= FULL STOP:] 
-              [:name = HEBREW PUNCTUATION GERSHAYIM:] [:name = DOUBLE VERTICAL LINE:] [:name = LEFT SINGLE QUOTATION MARK:]
-              [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:] 
-              [:name = HYPHEN-MINUS:] ];
-
-$SufixLetter = [:name= FULL STOP:];
-              
-
-$MidNum    = [[:LineBreak = Infix_Numeric:] [:name= COMMERCIAL AT:] \u0084 [:name = GREEK TONOS:] [:name = ARABIC DECIMAL SEPARATOR:]
-             [:name = LEFT SINGLE QUOTATION MARK:] [:name = RIGHT SINGLE QUOTATION MARK:] [:name = SINGLE HIGH-REVERSED-9 QUOTATION MARK:]
-             [:name = PRIME:]];
-$Numeric   = [:LineBreak = Numeric:];
-
-
-$TheZWSP = \u200b;
-
-#
-#  Character Class Definitions.
-#    The names are those from TR29.
-#
-$CR         = \u000d;
-$LF         = \u000a;
-$Control    = [[[:Zl:] [:Zp:] [:Cc:] [:Cf:]] - $TheZWSP];
-$Extend     = [[:Grapheme_Extend = TRUE:]]; 
-
-
-
-
-####################################################################################
-#
-#  Word Break Rules.    Definitions and Rules specific to word break begin Here. 
-#
-####################################################################################
-
-$Format    = [[:Cf:] - $TheZWSP];
-
-
-
-# Rule 3:  Treat a grapheme cluster as if it were a single character.
-#          Hangul Syllables are easier to deal with here than they are in Grapheme Clusters
-#          because we don't need to find the boundaries between adjacent syllables -
-#          they won't be word boundaries.
-#
-
-
-#
-#  "Extended"  definitions.  Grapheme Cluster + Format Chars, treated like the base char.
-#
-$ALetterEx    = $ALetter   $Extend*; 
-$NumericEx    = $Numeric   $Extend*;
-$MidNumEx     = $MidNum    $Extend*;
-$MidLetterEx  = $MidLetter $Extend*;
-$SufixLetterEx= $SufixLetter $Extend*;
-$KatakanaEx   = $Katakana  $Extend*;
-$IdeographicEx= $Ideographic  $Extend*;
-$HangulEx = $Hangul  $Extend*;
-$FormatEx     = $Format    $Extend*;
-
-
-#
-#  Numbers.  Rules 8, 11, 12 form the TR.
-#
-$NumberSequence = $NumericEx ($FormatEx* $MidNumEx? $FormatEx* $NumericEx)*;
-$NumberSequence {100};
-
-#
-#  Words.  Alpha-numerics.  Rule 5, 6, 7, 9, 10
-#     - must include at least one letter. 
-#     - may include both letters and numbers.
-#     - may include  MideLetter, MidNumber punctuation.
-#
-$LetterSequence = $ALetterEx ($FormatEx* $MidLetterEx? $FormatEx* $ALetterEx)*;     # rules #6, #7
-($NumberSequence $FormatEx*)? $LetterSequence ($FormatEx* ($NumberSequence | $LetterSequence))* $SufixLetterEx? {200};
-
-[[:P:][:S:]]*;
-
-#
-#  Do not break between Katakana.   Rule #13.
-#
-$KatakanaEx ($FormatEx* $KatakanaEx)* {300};
-[:Hiragana:] $Extend* {300};
-
-#
-#  Ideographic Characters.  Stand by themselves as words.
-#                           Separated from the "Everything Else" rule, below, only so that they
-#                           can be tagged with a return value.   TODO:  is this what we want?
-#
-$IdeographicEx ($FormatEx* $IdeographicEx)* {400};
-$HangulEx ($FormatEx* $HangulEx)* {400};
-
-#
-#  Everything Else, with no tag.
-#                   Non-Control chars combine with $Extend (combining) chars.
-#                   Controls are do not.
-#
-[^$Control [:Ideographic:]] $Extend*;
-$CR $LF;
-
-#
-#  Reverse Rules.   Back up over any of the chars that can group together.
-#                   (Reverse rules do not need to be exact; they can back up  too far,
-#                   but must back up at least enough, and must stop on a boundary.)
-#
-
-# NonStarters are the set of all characters that can appear at the 2nd - nth position of
-#    a word.   (They may also be the first.)   The reverse rule skips over these, until it
-#    reaches something that can only be the start (and probably only) char in a "word".
-#    A space or punctuation meets the test.
-#
-$NonStarters = [$Numeric $ALetter $Katakana $Ideographic $Hangul [:P:] [:S:] $MidLetter $MidNum $SufixLetter $Extend $Format];
-
-#!.*;
-! ($NonStarters* | \n \r) .;
-