xref: /external/icu4c/data/brkitr/word.txt

#
# Copyright (C) 2002-2010, International Business Machines Corporation 
# and others. All Rights Reserved.
#
# file:  word.txt
#
# ICU Word Break Rules
#      See Unicode Standard Annex #29.
#      These rules are based on UAX-29 Revision 16 for Unicode 6.0
#
# Note:  Updates to word.txt will usually need to be merged into
#        word_POSIX.txt and word_ja.txt also.

##############################################################################
#
#  Character class definitions from TR 29
#
##############################################################################

!!chain;


#
#  Character Class Definitions.
#

$CR           = [\p{Word_Break = CR}];
$LF           = [\p{Word_Break = LF}];
$Newline      = [\p{Word_Break = Newline}];
$Extend       = [\p{Word_Break = Extend}];
$Format       = [\p{Word_Break = Format}];
$Katakana     = [\p{Word_Break = Katakana}];
$ALetter      = [\p{Word_Break = ALetter}];
$MidNumLet    = [\p{Word_Break = MidNumLet}];
$MidLetter    = [\p{Word_Break = MidLetter}];
$MidNum       = [\p{Word_Break = MidNum}];
$Numeric      = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];


#   Dictionary character set, for triggering language-based break engines. Currently
#   limited to LineBreak=Complex_Context. Note that this set only works in Unicode
#   5.0 or later as the definition of Complex_Context was corrected to include all
#   characters requiring dictionary break.

$dictionary   = [:LineBreak = Complex_Context:];
$Control        = [\p{Grapheme_Cluster_Break = Control}]; 
$ALetterPlus  = [$ALetter [$dictionary-$Extend-$Control]];   # Note:  default ALetter does not
                                                             #  include the dictionary characters.

#
#  Rules 4    Ignore Format and Extend characters, 
#             except when they appear at the beginning of a region of text.
#
$KatakanaEx     = $Katakana     ($Extend |  $Format)*;
$ALetterEx      = $ALetterPlus  ($Extend |  $Format)*;
$MidNumLetEx    = $MidNumLet    ($Extend |  $Format)*;
$MidLetterEx    = $MidLetter    ($Extend |  $Format)*;
$MidNumEx       = $MidNum       ($Extend |  $Format)*;
$NumericEx      = $Numeric      ($Extend |  $Format)*;
$ExtendNumLetEx = $ExtendNumLet ($Extend |  $Format)*;

$Hiragana       = [\p{script=Hiragana}];
$Ideographic    = [\p{Ideographic}];
$HiraganaEx     = $Hiragana     ($Extend |  $Format)*;
$IdeographicEx  = $Ideographic  ($Extend |  $Format)*;

## -------------------------------------------------

!!forward;


# Rule 3 - CR x LF
#
$CR $LF;

# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
#          of a region of Text.   The rule here comes into play when the start of text
#          begins with a group of Format chars, or with a "word" consisting of a single
#          char that is not in any of the listed word break categories followed by
#          format char(s).
[^$CR $LF $Newline]? ($Extend |  $Format)+;

$NumericEx {100};
$ALetterEx {200};
$KatakanaEx {300};       # note:  these status values override those from rule 5
$HiraganaEx {300};       #        by virtual of being numerically larger.
$IdeographicEx {400};    #

#
# rule 5
#    Do not break between most letters.
#
$ALetterEx $ALetterEx {200};

# rule 6 and 7
$ALetterEx ($MidLetterEx | $MidNumLetEx) $ALetterEx {200};

# rule 8

$NumericEx $NumericEx {100};

# rule 9

$ALetterEx $NumericEx {200};

# rule 10

$NumericEx $ALetterEx {200};

# rule 11 and 12 

$NumericEx ($MidNumEx | $MidNumLetEx) $NumericEx {100};

# rule 13

$KatakanaEx  $KatakanaEx {300};

# rule 13a/b

$ALetterEx      $ExtendNumLetEx {200};    #  (13a)
$NumericEx      $ExtendNumLetEx {100};    #  (13a)
$KatakanaEx     $ExtendNumLetEx {300};    #  (13a)
$ExtendNumLetEx $ExtendNumLetEx {200};    #  (13a)

$ExtendNumLetEx $ALetterEx  {200};    #  (13b)
$ExtendNumLetEx $NumericEx  {100};    #  (13b)
$ExtendNumLetEx $KatakanaEx {300};    #  (13b)
 


## -------------------------------------------------

!!reverse;

$BackALetterEx     = ($Format | $Extend)* $ALetterPlus;
$BackMidNumLetEx   = ($Format | $Extend)* $MidNumLet;
$BackNumericEx     = ($Format | $Extend)* $Numeric;
$BackMidNumEx      = ($Format | $Extend)* $MidNum;
$BackMidLetterEx   = ($Format | $Extend)* $MidLetter;
$BackKatakanaEx    = ($Format | $Extend)* $Katakana;
$BackExtendNumLetEx= ($Format | $Extend)* $ExtendNumLet;

# rule 3
$LF $CR;

# rule 4
($Format | $Extend)*  [^$CR $LF $Newline]?;

# rule 5

$BackALetterEx $BackALetterEx;

# rule 6 and 7

$BackALetterEx ($BackMidLetterEx | $BackMidNumLetEx) $BackALetterEx;


# rule 8

$BackNumericEx $BackNumericEx;

# rule 9

$BackNumericEx $BackALetterEx;

# rule 10

$BackALetterEx $BackNumericEx;

# rule 11 and 12

$BackNumericEx ($BackMidNumEx | $BackMidNumLetEx) $BackNumericEx;

# rule 13

$BackKatakanaEx $BackKatakanaEx;

# rules 13 a/b
#
$BackExtendNumLetEx ($BackALetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
($BackALetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx; 

## -------------------------------------------------

!!safe_reverse;

# rule 3
($Extend | $Format)+ .?;

# rule 6
($MidLetter | $MidNumLet) $BackALetterEx;

# rule 11
($MidNum | $MidNumLet) $BackNumericEx;

# For dictionary-based break
$dictionary $dictionary;

## -------------------------------------------------

!!safe_forward;

# rule 4
($Extend | $Format)+ .?;

# rule 6
($MidLetterEx | $MidNumLetEx) $ALetterEx;

# rule 11
($MidNumEx | $MidNumLetEx) $NumericEx;

# For dictionary-based break
$dictionary $dictionary;