summaryrefslogtreecommitdiffstats
path: root/intl/icu/source/data/brkitr/rules/title.txt
diff options
context:
space:
mode:
Diffstat (limited to 'intl/icu/source/data/brkitr/rules/title.txt')
-rw-r--r--intl/icu/source/data/brkitr/rules/title.txt26
1 files changed, 26 insertions, 0 deletions
diff --git a/intl/icu/source/data/brkitr/rules/title.txt b/intl/icu/source/data/brkitr/rules/title.txt
new file mode 100644
index 0000000000..3be2d3097c
--- /dev/null
+++ b/intl/icu/source/data/brkitr/rules/title.txt
@@ -0,0 +1,26 @@
+# Copyright (C) 2016 and later: Unicode, Inc. and others.
+# License & terms of use: http://www.unicode.org/copyright.html
+#
+# Copyright (c) 2002-2015, International Business Machines Corporation and
+# others. All Rights Reserved.
+#
+# Title Casing Break Rules
+#
+
+!!quoted_literals_only;
+
+$CaseIgnorable = [[:Mn:][:Me:][:Cf:][:Lm:][:Sk:] \u0027 \u00AD \u2019];
+$Cased = [[:Upper_Case:][:Lower_Case:][:Lt:] - $CaseIgnorable];
+$NotCased = [[^ $Cased] - $CaseIgnorable];
+
+# If the iterator begins on a CaseIgnorable, advance it past it/them.
+# This can occur at the start-of-text, or after application of the
+# safe-reverse rule.
+
+($CaseIgnorable | $NotCased)*;
+
+# Normal exact forward rule: beginning at the start of a word
+# (at a cased character), advance through the word and through
+# the uncased characters following the word.
+
+$Cased ($Cased | $CaseIgnorable)* ($NotCased | $CaseIgnorable)*;