ICU 56 update step 1

source/data/brkitr/sent.txt

 #
-#   Copyright (C) 2002-2011, International Business Machines Corporation and others.
+#   Copyright (C) 2002-2015, 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 19 for Unicode Version 6.1
+#      These rules are based on UAX #29 Revision 26 for Unicode Version 8.0
 #
 
 
 #
 # Character categories as defined in TR 29
 #
 $CR        = [\p{Sentence_Break = CR}];
 $LF        = [\p{Sentence_Break = LF}];
 $Extend    = [\p{Sentence_Break = Extend}];
 $Sep       = [\p{Sentence_Break = Sep}];
@@ skipping 37 matching lines @@
 # Rule 4 - Break after $Sep.
 # Rule 5 - Ignore $Format and $Extend
 #
 [^$Sep $CR $LF]? ($Extend | $Format)*;
 
 
 # Rule 6
 $ATermEx $NumericEx;
 
 # Rule 7
-$UpperEx $ATermEx $UpperEx;
+($UpperEx | $LowerEx) $ATermEx $UpperEx;
 
 #Rule 8
 $NotLettersEx = [^$OLetter $Upper $Lower $Sep $CR $LF $ATerm $STerm] ($Extend | $Format)*;
 $ATermEx $CloseEx* $SpEx* $NotLettersEx* $Lower;
 
 # Rule 8a
 ($STermEx | $ATermEx) $CloseEx* $SpEx* ($SContinueEx | $STermEx | $ATermEx);
 
 #Rule 9, 10, 11
 ($STermEx | $ATermEx) $CloseEx* $SpEx* ($Sep | $CR | $LF)?;
@@ skipping 32 matching lines @@
 #        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.
 #