ICU-7963 Break Iterator data files update for Unicode 6.0

X-SVN-Rev: 28646

icu4c/source/data/brkitr/char.txt

@@ -1,12 +1,12 @@
 #
-#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
+#   Copyright (C) 2002-2010, International Business Machines Corporation and others.
 #       All Rights Reserved.
 #
 #   file:  char.txt 
 #
 #   ICU Character Break Rules, also known as Grapheme Cluster Boundaries
 #      See Unicode Standard Annex #29.
-#      These rules are based on TR29 Revision 13, for Unicode Version 5.1
+#      These rules are based on TR29 Revision 16, for Unicode Version 6.0
 #
 
 #

icu4c/source/data/brkitr/char_th.txt

@@ -1,12 +1,12 @@
 #
-#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
+#   Copyright (C) 2002-2010, International Business Machines Corporation and others.
 #       All Rights Reserved.
 #
 #   file:  char_th.txt 
 #
 #   ICU Character Break Rules, also known as Grapheme Cluster Boundaries
 #      See Unicode Standard Annex #29.
-#      These rules are based on TR29 Revision 13, for Unicode Version 5.1
+#      These rules are based on TR29 Revision 16, for Unicode Version 6.0
 #
 
 #

icu4c/source/data/brkitr/line.txt

@@ -1,14 +1,16 @@
-# Copyright (c) 2002-2009  International Business Machines Corporation and
+# Copyright (c) 2002-2010  International Business Machines Corporation and
 # others. All Rights Reserved.
 #
 #  file:  line.txt
 #
 #         Line Breaking Rules
 #         Implement default line breaking as defined by 
-#         Unicode Standard Annex #14 Revision 24 for Unicode 5.2
+#         Unicode Standard Annex #14 Revision 24 for Unicode 6.0
 #         http://www.unicode.org/reports/tr14/
-
-
+#
+#         TODO:  Rule LB 8 remains as it was in Unicode 5.2
+#         This is only because of a limitation of ICU break engine implementation,
+#         not because the older behavior is desirable.
 
 #
 #  Character Classes defined by TR 14.
@@ -214,6 +216,9 @@ $CM+          [$SP $ZW];
 
 #
 # LB 8         Break after zero width space
+#              TODO:  ZW SP* <break>
+#              An engine change is required to write the reverse rule for this.
+#              For now, leave the Unicode 5.2 rule, ZW <break>
 #
 $LB8Breaks    = [$LB4Breaks $ZW];
 $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
@@ -452,8 +457,10 @@ $LF $CR;
 [$SP $ZW] [$LB4NonBreaks-$CM];
 [$SP $ZW] $CM+ $CAN_CM;
 
-# LB 8 Break after zero width space
-
+# LB 8 ZW SP* <break>
+#     TODO: to implement this, we need more than one look-ahead hard break in play at a time.
+#           Requires an engine enhancement.
+#   / $SP* $ZW
 
 # LB 9,10  Combining marks.
 #    X   $CM needs to behave like X, where X is not $SP or controls.

icu4c/source/data/brkitr/sent.txt

@@ -1,12 +1,12 @@
 #
-#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
+#   Copyright (C) 2002-2010, International Business Machines Corporation and others.
 #       All Rights Reserved.
 #
 #   file:  sent.txt
 #
 #   ICU Sentence Break Rules
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX 29 Revision 13 for Unicode Version 5.1.0
+#      These rules are based on UAX 29 Revision 16 for Unicode Version 6.0
 #
 
 

icu4c/source/data/brkitr/sent_el.txt

@@ -1,12 +1,12 @@
 #
-#   Copyright (C) 2002-2009, International Business Machines Corporation and others.
+#   Copyright (C) 2002-2010, International Business Machines Corporation and others.
 #       All Rights Reserved.
 #
 #   file:  sent_el.txt
 #
 #   ICU Sentence Break Rules
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX 29 Revision 13 for Unicode Version 5.1.0
+#      These rules are based on UAX 29 Revision 16 for Unicode Version 6.0
 #
 
 

icu4c/source/data/brkitr/word.txt

@@ -1,12 +1,12 @@
 #
-# Copyright (C) 2002-2009, International Business Machines Corporation 
+# 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 13 for Unicode 5.1
+#      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.

icu4c/source/data/brkitr/word_POSIX.txt

@@ -1,12 +1,12 @@
 #
-# Copyright (C) 2002-2009, International Business Machines Corporation 
+# Copyright (C) 2002-2010, International Business Machines Corporation 
 # and others. All Rights Reserved.
 #
 # file:  word_POSIX.txt
 #
 # ICU Word Break Rules, POSIX locale.
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX-29 Revision 13 for Unicode 5.1
+#      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.

icu4c/source/data/brkitr/word_ja.txt

@@ -1,12 +1,12 @@
 #
-# Copyright (C) 2002-2009, International Business Machines Corporation 
+# Copyright (C) 2002-2010, International Business Machines Corporation 
 # and others. All Rights Reserved.
 #
 # file:  word_ja.txt
 #
 # ICU Word Break Rules
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX-29 Revision 13 for Unicode 5.1
+#      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.