icuSources/data/brkitr/rules/title.txt

   1 # Copyright (C) 2016 and later: Unicode, Inc. and others.
   2 # License & terms of use: http://www.unicode.org/copyright.html#License
   3 #
   4 # Copyright (c) 2002-2015, International Business Machines Corporation and
   5 # others. All Rights Reserved.
   6 #
   7 #  Title Casing Break Rules
   8 #
   9
  10
  11 $CaseIgnorable   = [[:Mn:][:Me:][:Cf:][:Lm:][:Sk:] \u0027 \u00AD \u2019];
  12 $Cased           = [[:Upper_Case:][:Lower_Case:][:Lt:]  - $CaseIgnorable];
  13 $NotCased        = [[^ $Cased] - $CaseIgnorable];
  14
  15 !!forward;
  16
  17 #  If the iterator begins on a CaseIgnorable, advance it past it/them.
  18 #  This can occur at the start-of-text, or after application of the
  19 #  safe-reverse rule.
  20
  21 ($CaseIgnorable | $NotCased)*;
  22
  23 #   Normal exact forward rule: beginning at the start of a word
  24 #         (at a cased character), advance through the word and through
  25 #         the uncased characters following the word.
  26
  27 $Cased ($Cased | $CaseIgnorable)* ($NotCased | $CaseIgnorable)*;
  28
  29
  30 #  Reverse Rules
  31 !!reverse;
  32
  33 #  Normal Rule, will work nearly universally, so long as there is a
  34 #    start-of-word preceding the current iteration position.
  35
  36 ($NotCased | $CaseIgnorable)* ($Cased | $CaseIgnorable)* $Cased;
  37
  38 #  Short rule, will be effective only when moving to the start of text,
  39 #    with no word (cased character) preceding the current iteration position.
  40
  41 ($NotCased | $CaseIgnorable)*;
  42
  43 !!safe_reverse;
  44
  45 # Safe Reverse: the exact forward rule must not start in the middle
  46 #  of a word, so the safe reverse skips over any Cased characters,
  47 #  leaving it just before the start of a word.
  48
  49 ($Cased | $CaseIgnorable)*;
  50
  51 !!safe_forward;
  52
  53 # Safe Forward, nothing needs to be done, the exact Reverse rules will
  54 #   always find valid boundaries from any starting position.
  55 #   Still, some rule is needed, so '.', a one character movement.
  56 .;