1# 2# Copyright (C) 2002-2003, International Business Machines Corporation and others. 3# All Rights Reserved. 4# 5# file: dict_word.txt 6# 7# ICU Word Break Rules 8# See Unicode Standard Annex #29. 9# These rules are based on Version 4.0.0, dated 2003-04-17 10# 11 12 13 14#################################################################################### 15# 16# Character class definitions from TR 29 17# 18#################################################################################### 19$Katakana = [[:Script = KATAKANA:] [:name = KATAKANA-HIRAGANA PROLONGED SOUND MARK:] 20 [:name = HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK:] 21 [:name = HALFWIDTH KATAKANA VOICED SOUND MARK:] 22 [:name = HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK:]]; 23 24$Ideographic = [:Ideographic:]; 25$Hangul = [:Script = HANGUL:]; 26 27$ALetter = [\u0002 [:Alphabetic:] [:name= COMMERCIAL AT:] [:name= HEBREW PUNCTUATION GERESH:] 28 - $Ideographic 29 - $Katakana 30 - $Hangul 31 - [:Script = Thai:] 32 - [:Script = Lao:] 33 - [:Script = Hiragana:]]; 34 35$MidLetter = [[:name = APOSTROPHE:] [:name = GRAVE ACCENT:] \u0084 [:name = SOFT HYPHEN:] [:name = MIDDLE DOT:] [:name = GREEK TONOS:] [:name= FULL STOP:] 36 [:name = HEBREW PUNCTUATION GERSHAYIM:] [:name = DOUBLE VERTICAL LINE:] [:name = LEFT SINGLE QUOTATION MARK:] 37 [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:] 38 [:name = HYPHEN-MINUS:] ]; 39 40$SufixLetter = [:name= FULL STOP:]; 41 42 43$MidNum = [[:LineBreak = Infix_Numeric:] [:name= COMMERCIAL AT:] \u0084 [:name = GREEK TONOS:] [:name = ARABIC DECIMAL SEPARATOR:] 44 [:name = LEFT SINGLE QUOTATION MARK:] [:name = RIGHT SINGLE QUOTATION MARK:] [:name = SINGLE HIGH-REVERSED-9 QUOTATION MARK:] 45 [:name = PRIME:]]; 46$Numeric = [:LineBreak = Numeric:]; 47 48 49$TheZWSP = \u200b; 50 51# 52# Character Class Definitions. 53# The names are those from TR29. 54# 55$CR = \u000d; 56$LF = \u000a; 57$Control = [[[:Zl:] [:Zp:] [:Cc:] [:Cf:]] - $TheZWSP]; 58$Extend = [[:Grapheme_Extend = TRUE:]]; 59 60 61 62 63#################################################################################### 64# 65# Word Break Rules. Definitions and Rules specific to word break begin Here. 66# 67#################################################################################### 68 69$Format = [[:Cf:] - $TheZWSP]; 70 71 72 73# Rule 3: Treat a grapheme cluster as if it were a single character. 74# Hangul Syllables are easier to deal with here than they are in Grapheme Clusters 75# because we don't need to find the boundaries between adjacent syllables - 76# they won't be word boundaries. 77# 78 79 80# 81# "Extended" definitions. Grapheme Cluster + Format Chars, treated like the base char. 82# 83$ALetterEx = $ALetter $Extend*; 84$NumericEx = $Numeric $Extend*; 85$MidNumEx = $MidNum $Extend*; 86$MidLetterEx = $MidLetter $Extend*; 87$SufixLetterEx= $SufixLetter $Extend*; 88$KatakanaEx = $Katakana $Extend*; 89$IdeographicEx= $Ideographic $Extend*; 90$HangulEx = $Hangul $Extend*; 91$FormatEx = $Format $Extend*; 92 93 94# 95# Numbers. Rules 8, 11, 12 form the TR. 96# 97$NumberSequence = $NumericEx ($FormatEx* $MidNumEx? $FormatEx* $NumericEx)*; 98$NumberSequence {100}; 99 100# 101# Words. Alpha-numerics. Rule 5, 6, 7, 9, 10 102# - must include at least one letter. 103# - may include both letters and numbers. 104# - may include MideLetter, MidNumber punctuation. 105# 106$LetterSequence = $ALetterEx ($FormatEx* $MidLetterEx? $FormatEx* $ALetterEx)*; # rules #6, #7 107($NumberSequence $FormatEx*)? $LetterSequence ($FormatEx* ($NumberSequence | $LetterSequence))* $SufixLetterEx? {200}; 108 109[[:P:][:S:]]*; 110 111# 112# Do not break between Katakana. Rule #13. 113# 114$KatakanaEx ($FormatEx* $KatakanaEx)* {300}; 115[:Hiragana:] $Extend* {300}; 116 117# 118# Ideographic Characters. Stand by themselves as words. 119# Separated from the "Everything Else" rule, below, only so that they 120# can be tagged with a return value. TODO: is this what we want? 121# 122$IdeographicEx ($FormatEx* $IdeographicEx)* {400}; 123$HangulEx ($FormatEx* $HangulEx)* {400}; 124 125# 126# Everything Else, with no tag. 127# Non-Control chars combine with $Extend (combining) chars. 128# Controls are do not. 129# 130[^$Control [:Ideographic:]] $Extend*; 131$CR $LF; 132 133# 134# Reverse Rules. Back up over any of the chars that can group together. 135# (Reverse rules do not need to be exact; they can back up too far, 136# but must back up at least enough, and must stop on a boundary.) 137# 138 139# NonStarters are the set of all characters that can appear at the 2nd - nth position of 140# a word. (They may also be the first.) The reverse rule skips over these, until it 141# reaches something that can only be the start (and probably only) char in a "word". 142# A space or punctuation meets the test. 143# 144$NonStarters = [$Numeric $ALetter $Katakana $Ideographic $Hangul [:P:] [:S:] $MidLetter $MidNum $SufixLetter $Extend $Format]; 145 146#!.*; 147! ($NonStarters* | \n \r) .; 148 149