Update ICU to 54.1 step 1

source/test/testdata/rbbitst.txt

-# Copyright (c) 2001-2013 International Business Machines
+# Copyright (c) 2001-2014 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 14 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.
 
 
 #   Temp debugging tests 
-<word>
-<data>•Isn't<200></data>
-<char>
-<data>•\U00010020•\U00010000\N{COMBINING MACRON}•</data>
+<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
 #
 #
 ##########################################################################################
 <char>
 
 <data>•a•b•c• •,•\u0666•</data>                 # Quick Test
@@ skipping 121 matching lines @@
 <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>
 
 # test normalization/dictionary handling of halfwidth katakana: same dictionary phrase in fullwidth and halfwidth
 <data>•芽キャベツ<400>芽キャﾍﾞツ<400></data>
 
 # more Japanese tests
-# TODO: Currently, U+30FC and other characters (script=common) in the Hiragana
-# and the Katakana block are not treated correctly. Enable this later.
+# TODO: some script=common characters in the Hiragana and the Katakana block may not be treated correctly
+# (was formerly true for U+30FC); need to check and fix if so.
 #<data>•どー<400>せ<400>日本語<400>を<400>勉強<400>する<400>理由<400>について<400>　•て<400>こと<400>は<400>我<400>でも<400>知<400>ら<400>も<400>い<400>こと<400>なん<400>だ<400>。•</data>
 <data>•日本語<400>を<400>勉強<400>する<400>理由<400>について<400>　•て<400>こと<400>は<400>我<400>でも<400>知<400>ら<400>も<400>い<400>こと<400>なん<400>だ<400>。•</data>
 
 # Testing of word boundary for dictionary word containing both kanji and kana
 <data>•中だるみ<400>蔵王の森<400>ウ離島<400></data>
 
 # Testing of Chinese segmentation (taken from a Chinese news article)
 <data>•400<100>余<400>名<400>中央<400>委员<400>和<400>中央<400>候补<400>委员<400>都<400>领<400>到了<400>“•推荐<400>票<400>”•，•有<400>资格<400>在<400>200<100>多<400>名<400>符合<400>条件<400>的<400>63<100>岁<400>以下<400>中共<400>正<400>部<400>级<400>干部<400>中<400>，•选出<400>他们<400>属意<400>的<400>中央<400>政治局<400>委员<400>以<400>向<400>政治局<400>常委<400>会<400>举荐<400>。•</data>
 
 # Words with interior formatting characters
@@ skipping 392 matching lines @@
 <title>
 <data>•Here •is •a •short •sample •sentence.  •And •another.•</data>
 <data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE.  •AND •ANOTHER.•</data>
 <data>•  •Start •and •end •with •spaces   •</data>
 <data>•Include 123 456 ^&  •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data>
 
 <data>•Combining\u0301 \u0301•ma\u0306rks  •bye  •</data>
 <data>•123  •Start •with •a •number.•</data>
 
 <data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data>
-
+<data>•'  '' •start •with •case-•ignorable & •case-•insensitive •cha'r'a'cter•</data>
+<data>•  ''•aaa' •bbb '•ccc' '•ddd''' '''•eee   '''•fff'''   •ggg  ''•</data>
+# Note: apostrophe is case-ignorable. space is not cased.
 
 ##########################################################################################
 #
 #   Thai Tests
 #
 ##########################################################################################
 <locale th>
 <word>
 #
 # Test data originally from the test code source file
@@ skipping 77 matching lines @@
 \u0e41\u0e25\u0e30•\
 \u0e40\u0e03\u0e35•\
 \u0e22\u0e07•\
 \u0e43\u0e2b\u0e21\u0e48•</data>
 
 # Test for #10296
 <line>
 <data>•ใช•มั้ย•</data>
 <data>•มั๊ยล่ะ•ที่รัก•</data>
 
+# Test for #10593
+<line>
+<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>
+
 ##########################################################################################
 #
 #   Lao Tests
 #
 ##########################################################################################
 <locale en>
 # Basic check for #7647
 <line>
 <data>•ສະບາຍດີ•</data>
 <data>•ດີ•ຂອບໃຈ•</data>
 <data>•ເຈົ້າ•ເວົ້າ•ພາສາ•ອັງກິດ•ໄດ້•ບໍ່•</data>
 <data>•ກະລຸນາ•ເວົ້າ•ຊ້າ•ໆ•</data>
 
 ##########################################################################################
 #
+#   Burmese/Myanmar Tests
+#
+##########################################################################################
+<locale en>
+# Basic sanity check for #10326 (some text from http://www.unicode.org/udhr/d/udhr_mya.txt)
+<line>
+<data>•လူ•တိုင်း•သည် •တူညီ •လွတ်လပ်•သော •ဂုဏ်•သိ•က္•ခါ•ဖြ•င့် •လည်းကောင်း၊ •</data>
+<data>•တူညီ•လွတ်လပ်•သော •အ•ခွ•င့်•အရေး•များ•ဖြ•င့် •လည်းကောင်း၊ •မွေး•ဖွား•လာ•သူများ •ဖြစ်သည်။•</data>
+<data>•ထို•သူ•တို့၌ •ပိုင်းခြား •ဝေဖန်•တတ်•သော •ဉာဏ်•နှ•င့် •ကျ•င့်•ဝတ် •သိတတ်•သော •စိတ်•တို့•ရှိ•ကြ၍ •</data>
+<data>•ထို•သူ•တို့သည် •အချင်းချင်း •မေတ္တာ•ထား၍ •ဆက်ဆံ•ကျ•င့်•သုံး•</data>
+
+##########################################################################################
+#
 #   Khmer Tests
 #
 ##########################################################################################
 
 # Test data originally from http://bugs.icu-project.org/trac/search?q=r30327
 #  from the file testdata/wordsegments.txt
 <locale en>
 <word>
 
 <data>•តើ<200>លោក<200>មក<200>ពី<200>ប្រទេស<200>ណា<200></data>
@@ skipping 70 matching lines @@
 <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>
 
 
 <locale root>
 <word>
 <data>•私<400>達<400>に<400>一<400>〇<400>〇〇<400>の<400>コンピュータ<400>が<400>ある<400>。<0>奈々<400>は<400>ワード<400>で<400>ある<400>。•</data>
 # The following test is for #10300
 <data>•例えば<400>オーストラリア<400>。•</data>
+# The following test is for #10571
+<data>•一部<400>の<400>地域<400>では<400>、<0>ブラジル<400>、<0>インドネシア<400>、<0>オーストリア<400>、<0>ニュージーランド<400>で<400>ある<400>。•</data>
 
 # UBreakIteratorType UBRK_SENTENCE, Locale "el"
 # Add break after Greek question mark (cldrbug #2069).
 # "\u0391\u03B2, \u03B3\u03B4; \u0395 \u03B6\u03B7\u037E \u0398 \u03B9\u03BA. "
 # "\u039B\u03BC \u03BD\u03BE! \u039F\u03C0, \u03A1\u03C2? \u03A3"
 # which is "Αβ, γδ; Ε ζη; Θ ικ. Λμ νξ! Οπ, Ρς? Σ"
 
 <locale root>
 <sent>
 <data>•Αβ, γδ; Ε ζη; Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data>
 
 <locale el>
 <sent>
 <data>•Αβ, γδ; •Ε ζη; •Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data>
 
 #  UBreakIteratorType UBRK_WORD, Locale "en_US_POSIX"
 #  Words don't include colon or period (cldrbug #1969).
 
 <locale en_US>
 <word>
 <data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
 •for<200> •CS<200>-•types<200>.•</data>
 <data>•\uFF92\uFF76\uFF9E<400> •</data>
 
 <locale en_US_POSIX>
 <word>
-<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct<200>.•field<200> \
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct<200>.•field<200> \
 •for<200> •CS<200>-•types<200>.•</data>
 <data>•\u06c9<200>\uc799\ufffa•</data>
 <data>•\uFF92\uFF76\uFF9E<400> •</data>
 
 
 # UBreakIteratorType UBRK_CHARACTER, Locale "th"
 # Clusters should not include spacing Thai/Lao vowels (prefix or postfix), except for [SARA] AM (cldrbug #2161).
 # Update:  As of Unicode 6.1 root has same behavior as th for this.
 #
 # "\u0E01\u0E23\u0E30\u0E17\u0E48\u0E2D\u0E21\u0E23\u0E08\u0E19\u0E32 "
@@ skipping 27 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>