ICU 56 update step 1

source/test/testdata/rbbitst.txt

-# Copyright (c) 2001-2014 International Business Machines
+# Copyright (c) 2001-2015 International Business Machines
 # Corporation and others. All Rights Reserved.
 #
 # RBBI Test Data
 #
 #   File:  rbbitst.txt
 #
 #     The format of this file looks vaguely like some kind of xml-ish markup,
 #     but it is NOT.  The syntax is this..
 #
 #   <word>    any following data is for word break testing
@@ skipping 13 matching lines @@
 #
 # There are two copies of this file in the source repository,
 #   [ICU4C]   source/test/testdata/rbbitst.txt
 #   [ICU4J]   main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt
 #
 # ICU4C's copy is the master.  If any changes are made to ICU4J's copy, make sure they
 #  are merged back into ICU4C's copy of the file, lest they get overwritten later.
 # TODO:  figure out how to have a single copy of the file for use by both C and Java.
 
 
+## FILTERED BREAK TESTS
+
+# (William Bradford, public domain. http://catalog.hathitrust.org/Record/008651224 ) - edited.
+<locale en>
+<sent>
+<data>\
+•In the meantime Mr. •Weston arrived with his small ship, which he had now recovered. •Capt. •Gorges, who informed the Sgt. here that one purpose of his going east was to meet with Mr. •Weston, took this opportunity to call him to account for some abuses he had to lay to his charge.•</data>
+
+<locale en@ss=standard>
+<sent>
+<data>\
+•In the meantime Mr. Weston arrived with his small ship, which he had now recovered. •Capt. Gorges, who informed the Sgt. here that one purpose of his going east was to meet with Mr. Weston, took this opportunity to call him to account for some abuses he had to lay to his charge.•</data>
+
+## END FILTERED BREAK TESTS
+
+<locale>
+
 #   Temp debugging tests 
 <sent>
 <data>•\u00c0.•</data>
 
 #<data>•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165:"JAVA\u821c\u8165\u7fc8\u51ce\u306d,\u2494\u56d8\u4ec0\u60b1\u8560\u51ba\u611d\u57b6\u2510\u5d46".\u2029•</data>
 ########################################################################################
 #
 #
 #       G r a p h e m e    C l u s t e r     T e s t s
 #
@@ skipping 111 matching lines @@
 #Hindi Numbers
 <data>• •\u0968\u0966.\u0969\u096f<100> •\u0967\u0966\u0966.\u0966\u0966<100> •\N{RUPEE SIGN}•\u0967,\u0967\u0966\u0966.\u0966\u0966<100> • •\u0905\u092e\u091c<200>\n•</data>
 
 <data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢•£•¤•¥•alpha\u05f3beta\u05f4gamma<200> •</data>
 
 <data>•Badges<200>?• •BADGES<200>!•?•!• •We<200> •don't<200> •need<200> •no<200> •STINKING<200> •BADGES<200>!•!•1000,233,456.000<100> •1,23.322<100>%•123.1222<100>$•123,000.20<100> •179.01<100>%•X<200> •Now<200>\r•is<200>\n•the<200>\r\n•time<200> •</data>
 
 #Hangul
 <data>•\uc5f0\ud569<200> •\uc7a5\ub85c\uad50\ud68c<200> •\u1109\u1161\u11bc\u1112\u1161\u11bc<200> •\u1112\u1161\u11ab\u110b\u1175\u11ab<200> •Hello<200>,• •how<200> •are<200> •you<200> •</data>
 
+<data>•Hello<200>,• •how<200> •are<200> •you<200> •\uc5f0\ud569<200> •\uc7a5\ub85c\uad50\ud68c<200> •\u1109\u1161\u11bc\u1112\u1161\u11bc<200> •\u1112\u1161\u11ab\u110b\u1175\u11ab<200> •</data>
 
 # Words containing non-BMP letters
 <data>•abc\U00010300<200> •abc\N{DESERET SMALL LETTER ENG}<200> •abc\N{MATHEMATICAL BOLD SMALL Z}<200> •abc\N{MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL}<200> •</data>
 
 # Unassigned code points
 <data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data>
 
 # Hiragana & Katakana stay together, but separates from each other and Latin.
 # *** what to do about theoretical combos of chars? i.e. hiragana + accent
 #<data>•abc<200>\N{HIRAGANA LETTER SMALL A}<400>\N{HIRAGANA LETTER VU}\N{COMBINING ACUTE ACCENT}<400>\N{HIRAGANA ITERATION MARK}<400>\N{KATAKANA LETTER SMALL A}\N{KATAKANA ITERATION MARK}\N{HALFWIDTH KATAKANA LETTER WO}\N{HALFWIDTH KATAKANA LETTER N}<400>def<200>#•</data>
@@ skipping 69 matching lines @@
 <data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data>
 
 #
 # Jitterbug 5276 - treat Japanese half width voicing marks as Grapheme Extend
 #
 <data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data>
 
 # User guide example:
 <data>•Parlez<200>-•vous<200> •français<200> •?•</data>
 
+# Test for #11673
+<word>
+<data>•ジョージア<400> •</data>
+
 ########################################################################################
 #
 #
 #       S e n t e n c e     B o u n d a r y      T e s t s
 #
 #
 ##########################################################################################
 
 
 #
@@ skipping 432 matching lines @@
 <data>•เล่น•ผ่าน•ทาง•บลูทูธ•บน•อุปกรณ์•</data>
 
 # Test for city names #10691
 <line>
 <data>•ไป•ที่•ซานฟรานซิสโก•</data>
 
 # Test for #10630, #10631
 <line>
 <data>•แท็ก•แอปพลิเคชัน•เป็น•พิเศษ•</data>
 
+# Test for #11019
+<line>
+<data>•เบ•เบราว์เซอร์•โพ•โพสต์•โพสท์•</data>
+
+# Test for #11688
+<line>
+<data>•อัปเดต•อีเวนต์•</data>
+
 ##########################################################################################
 #
 #   Lao Tests
 #
 ##########################################################################################
 <locale en>
 # Basic check for #7647
 <line>
 <data>•ສະບາຍດີ•</data>
 <data>•ດີ•ຂອບໃຈ•</data>
@@ skipping 174 matching lines @@
 
 <data>•abc •- •def    •abc •-def    •abc- •def   •</data>   # With ASCII hyphen
 <data>•abc •‐ •def    •abc •‐def    •abc‐ •def   •</data>   # With Unicode u2010 hyphen
 
 # Test for #10176 (in fi)
 <line>
 <data>•abc/•s •def•</data>
 <data>•abc/\u05D9 •def•</data>
 <data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data>
 <data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05EA•</data>
+
+####################################################################################
+#
+#  Test CSS line break variants: strict, normal, loose
+#
+####################################################################################
+
+<locale ja@lb=strict>
+<line>
+#     •no brk before 3063              •no brk before 301C•no brk btw 2026   •no brk before FF01•
+<data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data>
+
+<locale ja@lb=normal>
+<line>
+#     •brk OK before 3063               •brk OK before 301C •no brk btw 2026   •no brk before FF01•
+<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data>
+
+<locale ja@lb=loose>
+<line>
+#     •brk OK before 3063               •brk OK before 301C •brk OK btw 2026    •brk OK before FF01•
+<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026•\u2026\u0020•u30A2•\uFF01\u0020•</data>
+
+<locale en@lb=strict>
+<line>
+#     •no brk before 3063              •no brk before 301C•no brk btw 2026   •no brk before FF01•
+<data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data>
+
+<locale en@lb=normal>
+<line>
+#     •brk OK before 3063               •no brk before 301C •no brk btw 2026  •no brk before FF01•
+<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data>
+
+<locale en@lb=loose>
+<line>
+#     •brk OK before 3063               •no brk before 301C •brk OK btw 2026   •no brk before FF01•
+<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026•\u2026\u0020•u30A2\uFF01\u0020•</data>