ICU update to 54.1 - step 5

source/data/brkitr/word.txt

 #
 # Copyright (C) 2002-2013, 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 22 for Unicode Version 6.3
 #
@@ skipping 17 matching lines @@
 $LF                 = [\p{Word_Break = LF}];
 $Newline            = [\p{Word_Break = Newline}];
 $Extend             = [\p{Word_Break = Extend}];
 $Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
 $Format             = [\p{Word_Break = Format}];
 $Katakana           = [\p{Word_Break = Katakana}];
 $Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
 $ALetter            = [\p{Word_Break = ALetter}];
 $Single_Quote       = [\p{Word_Break = Single_Quote}];
 $Double_Quote       = [\p{Word_Break = Double_Quote}];
-$MidNumLet          = [\p{Word_Break = MidNumLet}];
+# Remove two full stop characters from $MidNumLet and add them to $MidNum
+# to break a hostname into its components at the cost of breaking
+# 'e.g.' and 'i.e.' as well.
+# $MidNumLet is used in rules 6/7 (rules of our interest) and rules 11/12.
+# Because it's OR'd with $MidNum in rules 11/12, rules 11/12 are not affected
+# while rules 6/7 are reverted to the old behavior we want.
+$MidNumLet    = [[\p{Word_Break = MidNumLet}] - [\u002E \uFF0E]];
 $MidLetter          = [\p{Word_Break = MidLetter}];
-$MidNum             = [\p{Word_Break = MidNum}];
-$Numeric            = [\p{Word_Break = Numeric}];
+$MidNum       = [\p{Word_Break = MidNum}[\u002E \uFF0E]];
+$Numeric      = [\p{Word_Break = Numeric}[\uff10-\uff19]]; #includes fullwidth digits
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
 
 $Han                = [:Han:];
 $Hiragana           = [:Hiragana:];
 
 
 #   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.
@@ skipping 214 matching lines @@
 ($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx);
 
 # rule 7b
 $Double_QuoteEx $Hebrew_LetterEx;
 
 # rule 11
 ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx;
 
 # For dictionary-based break
 $dictionary $dictionary;