diff options
Diffstat (limited to 'i18npool/source/breakiterator/data/char_in.txt')
-rw-r--r-- | i18npool/source/breakiterator/data/char_in.txt | 109 |
1 files changed, 109 insertions, 0 deletions
diff --git a/i18npool/source/breakiterator/data/char_in.txt b/i18npool/source/breakiterator/data/char_in.txt new file mode 100644 index 000000000..414259524 --- /dev/null +++ b/i18npool/source/breakiterator/data/char_in.txt @@ -0,0 +1,109 @@ +# +# Copyright (C) 2002-2009, International Business Machines Corporation and others. +# All Rights Reserved. +# +# file: char.txt +# +# ICU Character Break Rules, also known as Grapheme Cluster Boundaries +# See Unicode Standard Annex #29. +# These rules are based on TR29 Revision 13, for Unicode Version 5.1 +# + +# +# Character Class Definitions. +# +$CR = [\p{Grapheme_Cluster_Break = CR}]; +$LF = [\p{Grapheme_Cluster_Break = LF}]; +$Control = [\p{Grapheme_Cluster_Break = Control}]; +$Prepend = [\p{Grapheme_Cluster_Break = Prepend}]; +$Extend = [\p{Grapheme_Cluster_Break = Extend}]; +$SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}]; +$BengaliLetter = [\u0985-\u09B9 \u09CE \u09DC-\u09E1 \u09F0-\u09F1]; +$BengaliSignVirama = \u09CD; +$GujaratiLetter = [\u0A85-\u0A8C \u0A8F-\u0A90 \u0A93-\u0AB9 \u0AE0-\u0AE1]; +$GujaratiSignVirama = \u0ACD; +$DevanagariLetter = [\u0904-\u0939 \u0958-\u0961 \u0972-\u097F]; +$DevanagariSignVirama = \u094D; +$KannadaLetter = [\u0C85-\u0CB9 \u0CDE-\u0CE1]; +$KannadaSignVirama = \u0CCD; +$MalayalamLetter = [\u0D05-\u0D39 \u0D60-\u0D61 \u0D7A-\u0D7F]; +$MalayalamSignVirama = \u0D4D; +$OdiaLetter = [\u0B05-\u0B39 \u0B5C-\u0B61 \u0B71]; +$OdiaSignVirama = \u0B4D; +$GurmukhiLetter = [\u0A05-\u0A39 \u0A59-\u0A5E]; +$GurmukhiSignVirama = \u0A4D; +$TamilKa = \u0B95; +$TamilSignVirama = \u0BCD; +$TamilSsa = \u0BB7; +$TeluguLetter = [\u0C05-\u0C39 \u0C58-\u0C61]; +$TeluguSignVirama = \u0C4D; + +# +# Korean Syllable Definitions +# +$L = [\p{Grapheme_Cluster_Break = L}]; +$V = [\p{Grapheme_Cluster_Break = V}]; +$T = [\p{Grapheme_Cluster_Break = T}]; + +$LV = [\p{Grapheme_Cluster_Break = LV}]; +$LVT = [\p{Grapheme_Cluster_Break = LVT}]; + + +## ------------------------------------------------- +!!chain; + +!!forward; + +$CR $LF; + +$BengaliLetter ($BengaliSignVirama $BengaliLetter?)+; +$GujaratiLetter ($GujaratiSignVirama $GujaratiLetter?)+; +$DevanagariLetter ($DevanagariSignVirama $DevanagariLetter?)+; +$KannadaLetter ($KannadaSignVirama $KannadaLetter?)+; +$MalayalamLetter ($MalayalamSignVirama $MalayalamLetter?)+; +$OdiaLetter ($OdiaSignVirama $OdiaLetter?)+; +$GurmukhiLetter ($GurmukhiSignVirama $GurmukhiLetter?)+; +$TamilKa $TamilSignVirama $TamilSsa; +$TeluguLetter ($TeluguSignVirama $TeluguLetter?)+; + +$L ($L | $V | $LV | $LVT); +($LV | $V) ($V | $T); +($LVT | $T) $T; + +[^$Control $CR $LF] $Extend; + +[^$Control $CR $LF] $SpacingMark; +$Prepend [^$Control $CR $LF]; + + +## ------------------------------------------------- + +!!reverse; +$LF $CR; +($BengaliLetter? $BengaliSignVirama)+ $BengaliLetter; +($GujaratiLetter? $GujaratiSignVirama)+ $GujaratiLetter; +($DevanagariLetter? $DevanagariSignVirama)+ $DevanagariLetter; +($KannadaLetter? $KannadaSignVirama)+ $KannadaLetter; +($MalayalamLetter? $MalayalamSignVirama)+ $MalayalamLetter; +($OdiaLetter? $OdiaSignVirama)+ $OdiaLetter; +($GurmukhiLetter? $GurmukhiSignVirama)+ $GurmukhiLetter; +$TamilSsa $TamilSignVirama $TamilKa; +($TeluguLetter? $TeluguSignVirama)+ $TeluguLetter; +($L | $V | $LV | $LVT) $L; +($V | $T) ($LV | $V); +$T ($LVT | $T); + +$Extend [^$Control $CR $LF]; +$SpacingMark [^$Control $CR $LF]; +[^$Control $CR $LF] $Prepend; + + +## ------------------------------------------------- + +!!safe_reverse; + + +## ------------------------------------------------- + +!!safe_forward; + |