ICU-66108.tar.gz

[apple/icu.git] / icuSources / data / brkitr / rules / sent.txt

diff --git a/icuSources/data/brkitr/rules/sent.txt b/icuSources/data/brkitr/rules/sent.txt
index 49970ee3aeb298b08bea1ed75965f95c7c2ca0bf..eb1224ea5ee6c1fcdcb47f8f6a401bb34a2f0be4 100644 (file)
--- a/icuSources/data/brkitr/rules/sent.txt
+++ b/icuSources/data/brkitr/rules/sent.txt
@@ -1,6 +1,5 @@
-#
-#   Copyright (C) 2016 and later: Unicode, Inc. and others.
-#   License & terms of use: http://www.unicode.org/copyright.html#License
+# 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.
@@ -9,9 +8,10 @@
 #
 #   ICU Sentence Break Rules
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX #29 Revision 26 for Unicode Version 8.0
+#      These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
 #
 
+!!quoted_literals_only;
 
 #
 # Character categories as defined in TR 29
@@ -34,7 +34,7 @@ $Close     = [\p{Sentence_Break = Close}];
 #
 # Define extended forms of the character classes,
 #   incorporate trailing Extend or Format chars.
-#   Rules 4 and 5.  
+#   Rules 4 and 5.
 
 $SpEx       = $Sp      ($Extend | $Format)*;
 $LowerEx    = $Lower   ($Extend | $Format)*;
@@ -50,7 +50,6 @@ $CloseEx    = $Close   ($Extend | $Format)*;
 ## -------------------------------------------------
 
 !!chain;
-!!forward;
 
 # Rule 3 - break after separators.  Keep CR/LF together.
 #
@@ -79,44 +78,6 @@ $ATermEx $CloseEx* $SpEx* $NotLettersEx* $Lower;
 #Rule 9, 10, 11
 ($STermEx | $ATermEx) $CloseEx* $SpEx* ($Sep | $CR | $LF)?;
 
-#Rule 12
+#Rule 998
 [[^$STerm $ATerm $Close $Sp $Sep $LF $CR $Format $Extend]{bof}] ($Extend | $Format | $Close | $Sp)* .;
 [[^$STerm $ATerm $Close $Sp $Sep $LF $CR $Format $Extend]{bof}] ($Extend | $Format | $Close | $Sp)* ([$Sep $LF $CR {eof}] | $CR $LF){100};
-
-## -------------------------------------------------
-
-!!reverse;
-
-$SpEx_R       = ($Extend | $Format)* $Sp;
-$ATermEx_R    = ($Extend | $Format)* $ATerm;
-$STermEx_R    = ($Extend | $Format)* $STerm;
-$CloseEx_R    = ($Extend | $Format)* $Close;
-
-#
-#  Reverse rules.
-#     For now, use the old style inexact reverse rules, which are easier
-#     to write, but less efficient.
-#     TODO:  exact reverse rules.  It appears that exact reverse rules
-#            may require improving support for look-ahead breaks in the
-#            builder.  Needs more investigation.
-#
-
-[{bof}] (.? | $LF $CR) [^$Sep $CR $LF]* [$Sep $CR $LF {eof}] ($SpEx_R* $CloseEx_R* ($STermEx_R | $ATermEx_R))*;
-#.*;
-
-# Explanation for this rule:
-#
-#    It needs to back over
-#        The $Sep at which we probably begin
-#        All of the non $Sep chars leading to the preceding $Sep
-#        The preceding $Sep, which will be the second one that the rule matches.
-#        Any immediately preceding STerm or ATerm sequences.  We need to see these
-#              to get the correct rule status when moving forwards again.
-#        
-# [{bof}]           inhibit rule chaining.  Without this, rule would loop on itself and match
-#                   the entire string.
-#
-# (.? | $LF $CR)    Match one $Sep instance.  Use .? rather than $Sep because position might be
-#                   at the beginning of the string at this point, and we don't want to fail.
-#                   Can only use {eof} once, and it is used later.
-#