icuSources/test/testdata/rbbitst.txt

   1 # Copyright (c) 2001-2013 International Business Machines
   2 # Corporation and others. All Rights Reserved.
   3 #
   4 # RBBI Test Data
   5 #
   6 #   File:  rbbitst.txt
   7 #
   8 #     The format of this file looks vaguely like some kind of xml-ish markup,
   9 #     but it is NOT.  The syntax is this..
  10 #
  11 #   <word>    any following data is for word break testing
  12 #   <sent>    any following data is for sentence break testing
  13 #   <line>    any following data is for line break testing
  14 #   <char>    any following data is for char break testing
  15 #   <locale local_name>  Switch to the named locale at the next occurence of <word>, <sent>, etc.
  16 #   <data> ... </data>   test data.  May span multiple lines.
  17 #      <>        Break position, status == 0
  18 #      •         Break position, status == 0   (Bullet, \u2022)
  19 #      <nnn>     Break position, status == nnn
  20 #      \         Escape.  Normal ICU unescape applied.
  21 #      \ at end of line  ->  Line Continuation.  Remove both the backslash and the new line
  22 #
  23 # In ICU4C, this test data is run by intltest, rbbi/RBBITest/TestExtended.
  24 # In ICU4J, this test data is run by com.ibm.icu.dev.test.rbbi.RBBITestExtended
  25 #
  26 # There are two copies of this file in the source repository,
  27 #   [ICU4C]   source/test/testdata/rbbitst.txt
  28 #   [ICU4J]   main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt
  29 #
  30 # ICU4C's copy is the master.  If any changes are made to ICU4J's copy, make sure they
  31 #  are merged back into ICU4C's copy of the file, lest they get overwritten later.
  32 # TODO:  figure out how to have a single copy of the file for use by both C and Java.
  33
  34
  35 #   Temp debugging tests
  36 <char>
  37 <data>•\U00010020•\U00010000\u0301•x•</data>
  38 <data>•\U00010020•\U00010000\N{COMBINING MACRON}•</data>
  39
  40 ########################################################################################
  41 #
  42 #
  43 #       G r a p h e m e    C l u s t e r     T e s t s
  44 #
  45 #
  46 ##########################################################################################
  47 <char>
  48
  49 <data>•a•b•c• •,•\u0666•</data>                 # Quick Test
  50 <data>•\r•\r•\r\n•\r\n•\n•\r•</data>            # don't break CR/LF
  51
  52 # Always break after controls.  Combining chars don't combine with them.
  53 <data>•\u0003•\N{COMBINING GRAVE ACCENT}•\r•\N{COMBINING GRAVE ACCENT}•</data>
  54 <data>•\u0085•\N{COMBINING MACRON}•A\N{COMBINING MACRON}•</data>
  55
  56 # Surrogates
  57 <data>•\U00011000•\U00010020•\U00010000\N{COMBINING MACRON}•</data>
  58 <data>•\ud800\udc00•\udbff\udfff•a•</data>
  59
  60 # Extend (Combining chars) combine.
  61 <data>•A\N{COMBINING GRAVE ACCENT}•B•</data>
  62 <data>•\N{GREEK SMALL LETTER MU}\N{COMBINING LOW LINE}\N{COMBINING HORN}•</data>
  63 <data>•a\u0301•b\u0302•c\u0303•d\u0304•e\u0305•f\u0306•g\u0307•h\u0308•i\u0309•</data>
  64
  65 <data>•a\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304•</data>
  66
  67 # Don't break Hangul Syllables
  68 #   L : \u1100
  69 #   V : \u1161
  70 #   T : \u11A8
  71 #  LV : \uAC00
  72 # LVT : \uAC01
  73
  74 <data>•\u1100\u1161\u11a8•\u1100\u1161\u11a8•</data>  #LVT
  75 <data>•\u1100\u1161•\u1100\u1161•</data>
  76 <data>•\u1100\u1161\u11a8•\u1161•\u1100•\u11a8•\u1161\u1161\u1161\u11a8•</data>
  77 <data>•\u1100\u1100\uac01•\u1100\uac01•\u1100\uac01\u0301•\uac01•</data>
  78 <data>•\u1100\u0301•\u1161\u11a8\u0301•\u11a8•</data>
  79
  80
  81
  82 # Hindi combining chars.  (An old test)
  83 #   TODO:  Update these tests for Unicode 5.1 Extended Grapheme clusters
  84 #<data>•भ••ा•\u0930•\u0924• •\u0938\u0941\u0902•\u0926•\u0930•
  85 #•\u0939•\u094c•\u0964•</data>
  86 #<data>•\u0916\u0947•\u0938\u0941\u0902•\u0926•\u0930•\u0939•\u094c•\u0964•</data>
  87
  88
  89 #  Bug 1587.  Tamil.  \u0baa\u0bc1 is an Extended Grpaheme Cluster
  90 <data>•\u0baa\u0bc1•\u0baa\u0bc1•</data>
  91
  92 #   Regression test for bug 1889
  93 <data>•\u0f40\u0f7d•\u0000•\u0f7e•</data>
  94
  95
  96 #     0xffff is a legal character, and should not stop the break iterator early.
  97 #     (Requires special casing in implementation, which is why it gets a test.)
  98 <data>•\uffff•\uffff• •a•</data>
  99
 100 #  Treat Japanese Half Width voicing marks as combining
 101 <data>•A\uff9e•B\uff9f\uff9e\uff9f•C•</data>
 102
 103 ########################################################################################
 104 #
 105 #
 106 #       E x t e n d e d    G r a p h e m e    C l u s t e r     T e s t s
 107 #
 108 #
 109 ##########################################################################################
 110 #<xgc>
 111
 112 # Plain Vanilla grapheme clusters
 113 #<data>•a•b•c•</data>
 114 #<data>•a\u0301\u0302• •b\u0303\u0304•</data>
 115
 116 # Assorted Hindi combining marks
 117 #<data>•\u0904\u0903• •\u0937\u093E• •\u0904\u093F• •\u0937\u0940• •\u0937\u0949• •\u0937\u094A• •\u0937\u094B• •\u0937\u094C•</data>
 118
 119 # Thai Clusters
 120 # $Prepend $Extend* $PrependBase $Extend*;
 121 #
 122 #<data>•\u0e40\u0e01•\u0e44\u0301\u0e23\u0302\u0303•\u0e40•\u0e40\u0e02•\u0e02• •</data>
 123
 124
 125 ########################################################################################
 126 #
 127 #
 128 #       W o r d    B o u n d a r y      T e s t s
 129 #
 130 #
 131 ##########################################################################################
 132
 133 <word>
 134 #
 135 # Quick sanity test
 136 #
 137 <data>•hello<200> •there<200> •goodbye<200></data>
 138 <data>•hello<200> •12345<100> •,•</data>
 139
 140
 141 #
 142 # Test data originally in RBBIAPITest::TestFirstNextFollowing() and TestLastPreviousPreceding()
 143 #
 144
 145 <word>
 146 <data>•This<200> •is<200> •a<200> •word<200> •break<200>.• • •Isn't<200> •it<200>?• •2.25<100></data>
 147
 148
 149
 150 #
 151 # Data originally from TestDefaultRuleBasedWordIteration()
 152 #
 153 <data>•Write<200> •wordrules<200>.• •123.456<100> •alpha\u00adbeta\u00adgamma<200> •\u092f\u0939<200> •</data>
 154 <data>• •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200> •\u0938\u093f\u0916\u094b\u0917\u0947<200>?•</data>
 155
 156 #Hindi Numbers
 157 <data>• •\u0968\u0966.\u0969\u096f<100> •\u0967\u0966\u0966.\u0966\u0966<100> •\N{RUPEE SIGN}•\u0967,\u0967\u0966\u0966.\u0966\u0966<100> • •\u0905\u092e\u091c<200>\n•</data>
 158
 159 <data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢•£•¤•¥•alpha\u05f3beta\u05f4gamma<200> •</data>
 160
 161 <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>
 162
 163 #Hangul
 164 <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>
 165
 166
 167 # Words containing non-BMP letters
 168 <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>
 169
 170 # Unassigned code points
 171 <data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data>
 172
 173 # Hiragana & Katakana stay together, but separates from each other and Latin.
 174 # *** what to do about theoretical combos of chars? i.e. hiragana + accent
 175 #<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>
 176
 177 # test normalization/dictionary handling of halfwidth katakana: same dictionary phrase in fullwidth and halfwidth
 178 <data>•芽キャベツ<400>芽キャﾍﾞツ<400></data>
 179
 180 # more Japanese tests
 181 # TODO: Currently, U+30FC and other characters (script=common) in the Hiragana
 182 # and the Katakana block are not treated correctly. Enable this later.
 183 #<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>
 184 <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>
 185
 186 # Testing of word boundary for dictionary word containing both kanji and kana
 187 <data>•中だるみ<400>蔵王の森<400>ウ離島<400></data>
 188
 189 # Testing of Chinese segmentation (taken from a Chinese news article)
 190 <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>
 191
 192 # Words with interior formatting characters
 193 <data>•def\N{COMBINING ACUTE ACCENT}\N{SYRIAC ABBREVIATION MARK}ghi<200> •</data>
 194
 195 # to test for bug #4097779
 196 <data>•aa\N{COMBINING GRAVE ACCENT}a<200> •</data>
 197
 198 # fullwidth numeric, midletter characters etc should be treated like their halfwidth counterparts
 199 # <data>•ＩＳＮ'Ｔ<200> •１９<100>日<400></data>
 200 # why was this added with the dbbi stuff?
 201
 202 #      to test for bug #4098467
 203 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 204 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 205 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 206 #      Both sequences should be semantically identical and break the same way.
 207 #      precomposed syllables...
 208 <data>•\uc0c1\ud56d<200> •\ud55c\uc778<200> •\uc5f0\ud569<200> •\uc7a5\ub85c\uad50\ud68c<200> •\u1109\u1161\u11bc\u1112\u1161\u11bc<200> •\u1112\u1161\u11ab\u110b\u1175\u11ab<200> •\u110b\u1167\u11ab\u1112\u1161\u11b8<200> •\u110c\u1161\u11bc\u1105\u1169\u1100\u116d\u1112\u116c<200> •</data>
 209
 210 # more Korean tests (Jamo not tested here, not counted as dictionary characters)
 211 # Disable them now because we don't include a Korean dictionary.
 212 #<data>•\ud55c\uad6d<200>\ub300\ud559\uad50<200>\uc790\uc5f0<200>\uacfc\ud559<200>\ub300\ud559<200>\ubb3c\ub9ac\ud559\uacfc<200></data>
 213 #<data>•\ud604\uc7ac<200>\ub294<200> •\uac80\ucc30<200>\uc774<200> •\ubd84\uc2dd<200>\ud68c\uacc4<200>\ubb38\uc81c<200>\ub97c<200> •\uc870\uc0ac<200>\ud560<200> •\uac00\ub2a5\uc131<200>\uc740<200> •\uc5c6\ub2e4<200>\u002e•</data>
 214
 215 <data>•abc<200>\u4e01<400>\u4e02<400>\u3005<400>\u4e03\u4e03<400>abc<200> •</data>
 216
 217 <data>•\u06c9<200>\uc799\ufffa•</data>
 218
 219
 220 #
 221 #      Try some words from other scripts.
 222 #
 223
 224 #       Try some words from other scripts.
 225 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 226 #
 227 <data>•ΑΒΓ<200> •БВГ<200> •אבג֓<200> •ابت<200> •١٢٣<100> •\u10A0\u10A1\u10A2<200> •ABC<200> •</data>
 228
 229 <data>•\u0301•A<200></data>
 230
 231
 232 #
 233 #  Hindi word break tests, imported from the old RBBI tests.
 234 #    An historical note:  a much earlier version of ICU break iterators had a number
 235 #    of special case rules for Hindi, which were tested by an earlier version of
 236 #    this test data.  The current RBBI rules do not special case Hindi in
 237 #    any way, making this test data much less signfificant.
 238 #
 239 <data>•\u0917\u092a\u00ad\u0936\u092a<200>!•\u092f\u0939<200> •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200> •\u0938\u093f\u0916\u094b\u0917\u0947<200>?•\n•:•\u092a\u094d\u0930\u093e\u092f\u0903<200>
 240 •\u0935\u0930\u094d\u0937\u093e<200>\r\n•\u092a\u094d\u0930\u0915\u093e\u0936<200>,•\u0924\u0941\u092e\u093e\u0930\u094b<200> •\u092e\u093f\u0924\u094d\u0930<200> •\u0915\u093e<200> •\u092a\u0924\u094d\u0930<200> •\u092a\u095d\u094b<200> •\u0938\u094d\u0924\u094d\u0930\u093f<200>.• •\u0968\u0966.\u0969\u096f<100> •\u0967\u0966\u0966.\u0966\u0966<100>\u20a8•\u0967,\u0967\u0966\u0966.\u0966\u0966<100> •\u0905\u092e\u091c<200>\n•\u0938\u094d\u200d\u0935\u0924\u0902\u0924\u094d\u0930<200>\r•</data>
 241
 242 #
 243 #  Failures from monkey tests
 244 #
 245 <data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data>
 246
 247 #
 248 # Jitterbug 5276 - treat Japanese half width voicing marks as Grapheme Extend
 249 #
 250 <data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data>
 251
 252 # User guide example:
 253 <data>•Parlez<200>-•vous<200> •français<200> •?•</data>
 254
 255 ########################################################################################
 256 #
 257 #
 258 #       S e n t e n c e     B o u n d a r y      T e s t s
 259 #
 260 #
 261 ##########################################################################################
 262
 263
 264 #
 265 # Test data originally from RBBI RBBITest::TestDefaultRuleBasedSentenceIteration()
 266 #
 267 <sent>
 268
 269
 270 <sent>
 271 <data>•This\n<100></data>
 272 <data>•Hello! •how are you? •I'am fine. •Thankyou. •How are you \
 273 doing? •This\n<100> costs $20,00,000. •</data>
 274
 275
 276 # Sentence ending in a quote.
 277 <data>•"Sentence ending with a quote." •Bye.•</data>
 278
 279 # Sentence, and test data, ending without a period or other terminator.
 280 <data>•Here is a random sentence, no ending period<100></data>
 281
 282
 283 <data>•  (This is it).  •Testing the sentence iterator. •\
 284 "This isn't it." •Hi! \
 285 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
 286 "This isn't it." •\
 287 Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!! •Don't rock the boat.\u2029•Because I am the daddy, that is why.
 288 •Not on my time (el timo.)! •</data>
 289
 290 <data>•Hello.  •So what!!\u2029•"But now," he said, \
 291 "I know!" •\
 292 Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!). •One species, B. anthracis, is highly virulent.
 293 •Wolf said about Sounder:\
 294 "Beautifully thought-out and directed." •\
 295 Have you ever said, "This is where\tI shall live"? •He answered, \
 296 "You may not!" •Another popular saying is: "How do you do?". \n•\
 297 Yet another popular saying is: \
 298 'I'm fine thanks.' •\
 299 What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tall!!\
 300 •Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100></data>
 301
 302 <data>•No breaks when . is surrounded by UPPER.Case letters.  •</data>
 303 <data>•No breaks when . is followed by Numeric .4 a.4 C.4 3.1 .•</data>
 304 <data>•No breaks when . is followed by a lower, with possible intervening punct .,a .$a .)a. •</data>
 305
 306 #
 307 #  Sentence Breaks: no break at the boundary between CJK and other letters
 308 #
 309 <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•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165\u9de8\u97e4JAVA\u821c\u8165\u7fc8\u51ce\u306d\ue30b\u2494\u56d8\u4ec0\u60b1\u8560\u51ba\u611d\u57b6\u2510\u5d46\u97e5\u7751\u3002•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165\u9de8\u97e4\u6470\u8790JAVA\u821c\u8165\u7fc8\u51ce\u306d\ue30b\u2494\u56d8\u4ec0\u60b1\u8560\u51ba\u611d\u57b6\u2510\u5d46\u97e5\u7751\u2048•He said, "I can go there."\u2029•Bye, now.•</data>
 310
 311 #
 312 #      Treat fullwidth variants of .!? the same as their
 313 #      normal counterparts
 314 #
 315 <data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data>
 316
 317
 318 #
 319 #       Don't break sentences at boundary between CJK and digits
 320 #
 321 <data>•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165\u9de8\u97e48888\u821c\u8165\u7fc8\u51ce\u306d\ue30b\u2494\u56d8\u4ec0\u60b1\u8560\u51ba\u611d\u57b6\u2510\u5d46\u97e5\u7751\u3002•Bye, now<100></data>
 322
 323 #
 324 #      Breaks around '(' following a sentence TERM.  (Rule 9)
 325 #
 326 <data>•How do you do?(•Fine). •</data>
 327 <data>•How do you do? •(Fine). •</data>
 328 <data>•How do you do?(•fine). •</data>
 329 <data>•How do you do? •(fine). •</data>
 330
 331 #
 332 <data>•Hello.123<100></data>    # Rule 6
 333 <data>•Hello?•123<100></data>
 334
 335 <data>•HELLO.Bye<100></data>    # Rule 7
 336 <data>•HELLO?•Bye<100></data>
 337
 338 <data>•Hello.goodbye<100></data>  #Rule 8
 339 <data>•Hello. •Goodbye<100></data>
 340 <data>•Hello. goodbye<100></data>
 341
 342
 343
 344 #
 345 #        test for bug #4158381: No breaks when there are no terminators around
 346 #
 347 <data>•\<P>Provides a set of &quot;lightweight&quot; (all-java\<FONT SIZE="-2">\<SUP>TM\</SUP>\</FONT> language) components that, to the maximum degree possible, work the same on all platforms.  •</data>
 348 <data>•Another test.\u2029•</data>
 349
 350 #        test for bug #4143071: Make sure sentences that end with digits
 351 #        work right
 352 #
 353 <data>•Today is the 27th of May, 1998.  •</data>
 354 <data>•Tomorrow with be 28 May 1998.  •</data>
 355 <data>•The day after will be the 30th.\u2029•</data>
 356
 357 #        test for bug #4152416: Make sure sentences ending with a capital
 358 #        letter are treated correctly
 359 #
 360 <data>•The type of all primitive \<code>boolean\</code> values accessed in the target VM.  •Calls to xxx will return an implementor of this interface.  \u2029•</data>
 361
 362 #        test for bug #4152117: Make sure sentence breaking is handling
 363 #        punctuation correctly [COULD NOT REPRODUCE THIS BUG, BUT TEST IS
 364 #        HERE TO MAKE SURE IT DOESN'T CROP UP]
 365 #
 366 <data>•Constructs a randomly generated BigInteger, uniformly distributed over the range \<tt>0\</tt> to \<tt>(2\<sup>numBits\</sup> - 1\)\</tt>, inclusive.  •The uniformity of the distribution assumes that a fair source of random bits is provided in \<tt>rnd\</tt>.  •Note that this constructor always constructs a non-negative biginteger.  \n•Ahh abc.
 367 •</data>
 368
 369 #        sentence breaks for hindi which used Devanagari script
 370 #        make sure there is sentence break after ?,danda(hindi phrase separator),
 371 #        fullstop followed by space.  (VERY old test)
 372 #
 373 <data>•\u0928\u092e\u0938\u094d\u200d\u0924\u0947 \u0930\u092e\u0947\u0936\u0905\u093e\u092a\u0915\u0948\u0938\u0947 \u0939\u0948?•\u092e\u0948 \u0905\u091a\u094d\u200d \u091b\u093e \u0939\u0942\u0901\u0964 •\u0905\u093e\u092a\r\n<100>\
 374 \u0915\u0948\u0938\u0947 \u0939\u0948?•\u0935\u0939 \u0915\u094d\u200d\u092f\u093e\n\
 375 <100>\u0939\u0948?•\u092f\u0939 \u0905\u093e\u092e \u0939\u0948. •\u092f\u0939 means "this". •"\u092a\u095d\u093e\u0908" meaning "education" or "studies". •\u0905\u093e\u091c(\u0938\u094d\u200d\u0935\u0924\u0902\u0924\u094d\u0930 \u0926\u093f\u0935\u093e\u0938) \u0939\u0948\u0964 •Let's end here. •</data>
 376
 377 #         Regression test for bug #1984, Sentence break in Arabic text.
 378
 379 <data>\
 380 •\u0623\u0633\u0627\u0633\u064b\u0627\u060c\u0020\u062a\u062a\u0639\u0627"\u0645\u0644\u0020\u0627\u0644\u062d\u0648\u0627\u0633\u064a\u0628\u0020"\u0641\u0642\u0637\u0020\u0645\u0639\u0020\u0627\u0644\u0623\u0631\u0642\u0627\u0645\u060c\u0648\u062a\u0642\u0648\u0645\u0020\u0628\u062a\u062e\u0632\u064a\u0646\u0020\u0627\u0644\u0623\u062d\u0631\u0641\u0020\u0648\u0627\u0644\u0645\u062d\u0627\u0631\u0641\u0020\u0627\u0644\u0623\u062e\u0631\u0649\u0020\u0628\u0639\u062f\u0020\u0623\u0646\u062a\u064f\u0639\u0637\u064a\u0020\u0631\u0642\u0645\u0627\u0020\u0645\u0639\u064a\u0646\u0627\u0020\u0644\u0643\u0644\u0020\u0648\u0627\u062d\u062f\u0020\u0645\u0646\u0647\u0627\u002e\u0020•\u0648\u0642\u0628\u0644\u0020\u0627\u062e\u062a\u0631\u0627\u0639\u0022\u064a\u0648\u0646\u0650\u0643\u0648\u062f\u0022\u060c\u0020\u0643\u0627\u0646\u0020\u0647\u0646\u0627\u0643\u0020\u0645\u0626\u0627\u062a\u0020\u0627\u0644\u0623\u0646\u0638\u0645\u0629\u0020\u0644\u0644\u062a\u0634\u0641\u064a\u0631\u0648\u062a\u062e\u0635\u064a\u0635\u0020\u0647\u0630\u0647\u0020\u0627\u0644\u0623\u0631\u0642\u0627\u0645\u0020\u0644\u0644\u0645\u062d\u0627\u0631\u0641\u060c\u0020\u0648\u0644\u0645\u0020\u064a\u0648\u062c\u062f\u0020\u0646\u0638\u0627\u0645\u062a\u0634\u0641\u064a\u0020\u0639\u0644\u0649\u0020\u062c\u0645\u064a\u0639\u0020\u0627\u0644\u0645\u062d\u0627\u0631\u0641\u0020\u0627\u0644\u0636\u0631\u0648\u0631\u064a\u0629.  •</data>
 381
 382 #         Try a few more of the less common sentence endings.
 383 <data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end here. •</data>
 384
 385
 386
 387
 388 ################################################################
 389 #
 390 #
 391 #        L I N E     B R E A K
 392 #
 393 #
 394 ################################################################
 395
 396 <line>
 397 #
 398 # Test Character for each of the line break classes.
 399 #
 400 # 00A1;AI # INVERTED EXCLAMATION MARK  ¡
 401 # 0041;AL # LATIN CAPITAL LETTER A
 402 # 0009;BA # <control>
 403 # 00B4;BB # ACUTE ACCENT
 404 # 000C;BK # <control>
 405 # 2014;B2 # EM DASH
 406 # FFFC;CB # OBJECT REPLACEMENT CHARACTER
 407 # 0029;CL # RIGHT PARENTHESIS
 408 # 0301;CM # COMBINING ACUTE ACCENT
 409 # 0021;EX # EXCLAMATION MARK
 410 # 00A0;GL # NO-BREAK SPACE
 411 # 002D;HY # HYPHEN-MINUS
 412 # 4E00;ID # <CJK Ideograph, First>
 413 # 2024;IN # ONE DOT LEADER
 414 # 002C;IS # COMMA
 415 # 000A;LF # <control>
 416 # 0E5A;NS # THAI CHARACTER ANGKHANKHU
 417 # 0032;NU # DIGIT TWO
 418 # 0028;OP # LEFT PARENTHESIS
 419 # 0025;PO # PERCENT SIGN
 420 # 0024;PR # DOLLAR SIGN
 421 # 0022;QU # QUOTATION MARK
 422 # 0E01;SA # THAI CHARACTER KO KAI
 423 # DB7F;SG # Surrogate
 424 # 0020;SP # SPACE
 425 # 002F;SY # SOLIDUS /
 426 # F8FF;XX # Private Use
 427 # 200B;ZW # ZERO WIDTH SPACE
 428
 429
 430 # 2b  Always break at end of text
 431
 432 <data>•  •\u00A1•</data>
 433 <data>•  •\u0041•</data>
 434 <data>•  •\u0009•</data>
 435 <data>•  •\u00B4•</data>
 436 <data>•    \u000C<100></data>    # LB3C  × BK
 437 <data>•  •\u2014•</data>
 438 <data>•  •\uFFFC•</data>
 439 <data>•   \u0029•</data>    # LB 8   × CL
 440 # <data>• • \u0301•</data>    # LB 7a   Treat SP CM* as if it were ID  #TODO:  SP CM
 441 <data>•   \u0021•</data>    # LB 8   × EX
 442 #<data>•   \u00A0•</data>    # LB 11b   × GL   TODO:  fix.
 443 <data>•  •\u002D•</data>
 444 <data>•  •\u4E00•</data>
 445 <data>•  •\u2024•</data>
 446 <data>•   \u002C•</data>    # LB 8   × IS
 447 <data>•   \u000A<100></data>    # LB3C   × ( BK | CR | LF | NL )
 448 <data>•  •\u0E5A•</data>
 449 <data>•  •\u0032•</data>
 450 <data>•  •\u0028•</data>
 451 <data>•  •\u0025•</data>
 452 <data>•  •\u0024•</data>
 453 <data>•  •\u0022•</data>
 454 <data>•  •\u0E01•</data>
 455 <data>•  •\uDB7F•</data>
 456 <data>•   \u0020•</data>     # LB4 - don't break before space.
 457 <data>•   \u002F•</data>     # LB 8  × SY
 458 <data>•  •\uF8FF•</data>
 459 <data>•   \u200B•</data>     # LB4 - don't break before ZA
 460
 461
 462 # 3a  Always break after hard line breaks.
 463 # 3c  Never break before hard line breaks.
 464
 465 <data>•  •\u00A1\u2028<100>\u00A1•</data>
 466 <data>•  •\u0041\u2028<100>\u0041•</data>
 467 <data>•  •\u0009\u2028<100>\u0009•</data>
 468 <data>•  •\u00B4\u2028<100>\u00B4•</data>
 469 <data>•   \u000C<100>\u2028<100>\u000C<100></data>
 470 <data>•  •\u2014\u2028<100>\u2014•</data>
 471 <data>•  •\uFFFC\u2028<100>\uFFFC•</data>
 472 <data>•   \u0029\u2028<100>\u0029•</data>
 473 #<data>•   \u0301\u2028<100>\u0301•</data>    # TODO:  fix.
 474 <data>•   \u0021\u2028<100>\u0021•</data>
 475 #<data>•   \u00A0\u2028<100>\u00A0•</data>    # TODO:  fix
 476 <data>•  •\u002D\u2028<100>\u002D•</data>
 477 <data>•  •\u4E00\u2028<100>\u4E00•</data>
 478 <data>•  •\u2024\u2028<100>\u2024•</data>
 479 <data>•   \u002C\u2028<100>\u002C•</data>
 480 <data>•   \u000A<100>\u2028<100>\u000A<100></data>
 481 <data>•  •\u0E5A\u2028<100>\u0E5A•</data>
 482 <data>•  •\u0032\u2028<100>\u0032•</data>
 483 <data>•  •\u0028\u2028<100>\u0028•</data>
 484 <data>•  •\u0025\u2028<100>\u0025•</data>
 485 <data>•  •\u0024\u2028<100>\u0024•</data>
 486 <data>•  •\u0022\u2028<100>\u0022•</data>
 487 <data>•  •\u0E01\u2028<100>\u0E01•</data>
 488 <data>•  •\uDB7F\u2028<100>\uDB7F•</data>
 489 <data>•   \u0020\u2028<100>\u0020•</data>
 490 <data>•   \u002F\u2028<100>\u002F•</data>
 491 <data>•  •\uF8FF\u2028<100>\uF8FF•</data>
 492 <data>•   \u200B\u2028<100>\u200B•</data>
 493
 494 # User Guide example
 495
 496 <data>•Parlez-•vous •français ?•</data>
 497
 498 #
 499 #  Old Line Break Test data.  Orginally located in RBBITest::TestDefaultRuleBasedLineIteration()
 500 #
 501
 502 <line>
 503
 504 <data>•Multi-•Level •example •of •a •semi-•idiotic •non-•sensical •(non-•important) •sentence.
 505 <100>Hi  •Hello •How\n<100>are\r<100>you\u2028<100>fine.\t•good.  •Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100>all•</data>
 506
 507 <line>
 508 <data>•Hello! •how\r\n<100> •(are)\r<100> •you? •I'am •fine- •Thankyou. •foo\u00a0bar
 509 <100>How, •are, •you? •This, •costs •$20,00,000.•</data>
 510
 511 #     test for bug #4068133
 512 #
 513 <data>•\u96f6•\u4e00\u3002•\u4e8c\u3001•\u4e09\u3002\u3001•\u56db\u3001\u3002\u3001•\u4e94,•\u516d.•\u4e03.\u3001,\u3002•\u516b•</data>
 514
 515 #     to test for bug #4086052
 516 <data>•foo\u00a0bar•</data>
 517
 518 #     to test for bug #4097920
 519 <data>•dog,cat,mouse •(one)•(two)\n<100></data>
 520
 521 #     to test for bug #4035266
 522 <data>•The •balance •is •$-23,456.78, •not •-•$32,456.78!\n<100></data>
 523
 524
 525 #      to test for bug #4098467
 526 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 527 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 528 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 529 #      Both sequences should be semantically identical and break the same way.
 530 #      precomposed syllables...  (I == Rich Gillam?)
 531 #
 532 <data>•\uc0c1•\ud56d •\ud55c•\uc778 •\uc5f0•\ud569 •\uc7a5•\ub85c•\uad50•\ud68c•</data>
 533
 534 #      conjoining jamo...
 535 <data>•\u1109\u1161\u11bc•\u1112\u1161\u11bc •\u1112\u1161\u11ab•\u110b\u1175\u11ab •\u110b\u1167\u11ab•\u1112\u1161\u11b8 •\u110c\u1161\u11bc•\u1105\u1169•\u1100\u116d•\u1112\u116c•</data>
 536
 537 #      to test for bug #4117554: Fullwidth .!? should be treated as postJwrd
 538 <data>•\u4e01\uff0e•\u4e02\uff01•\u4e03\uff1f•</data>
 539
 540 #      Surrogate line break tests.
 541 #
 542 <data>•\u4e01•\ud840\udc01•\u4e02•abc •\ue000 •\udb80\udc01•</data>  #This line and the following are equivalent.
 543 <data>•\u4e01•\U00020001•\u4e02•abc •\ue000 •\U000f0001•</data>
 544
 545 #      Regression for bug 836
 546 #        Note:  Unicode 5.1 changed this behavior
 547 #               Unicode 5.2 changed it again, there is no break following the '('
 548 <data>•AAA(AAA •</data>
 549
 550 #       Try some words from other scripts.
 551 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 552 #
 553 <data>•ΑΒΓ •БВГ •אבג֓ •ابت •١٢٣ •\u10A0\u10A1\u10A2 •ABC •</data>
 554
 555 #
 556 #       ticket #4853:  unpaired surrogates should behave like AL
 557 #
 558 <data>•abc\ud801xyz•</data>
 559
 560 #
 561 #     Regression tests for failures that originally came from the monkey test.
 562 #     Monkey test failure lines can, with slight reformatting, be copied into this section
 563 #     as test cases.  The error display from here is more informative.
 564 #
 565 <data>•\ufffc•\u30e3\u000c<100>\u1b39\u300a\u002f\u203a\u200b•\ufffc•\uaf64•\udcfb•</data>
 566 <data>•\u114d\u31f3•\ube44\u002d•\u0362\u24e2\u276e\u2014\u205f\ufe16•\uc877•\u0fd0\u000a<100>\u20a3•</data>
 567 <data>•\u080a\u215b\U0001d7d3\u002c•\u2025\U000e012e•\u02df\u118d\u0029\ua8d6\u0085<100>\u6cc4\u2024\u202f\ufffc•</data>
 568
 569
 570 ########################################################################################
 571 #
 572 #
 573 #       T i t l e   B o u n d a r y      T e s t s
 574 #
 575 #
 576 ##########################################################################################
 577 <title>
 578 <data>•Here •is •a •short •sample •sentence.  •And •another.•</data>
 579 <data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE.  •AND •ANOTHER.•</data>
 580 <data>•  •Start •and •end •with •spaces   •</data>
 581 <data>•Include 123 456 ^&  •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data>
 582
 583 <data>•Combining\u0301 \u0301•ma\u0306rks  •bye  •</data>
 584 <data>•123  •Start •with •a •number.•</data>
 585
 586 <data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data>
 587
 588
 589 ##########################################################################################
 590 #
 591 #   Thai Tests
 592 #
 593 ##########################################################################################
 594 <locale th>
 595 <word>
 596 #
 597 # Test data originally from the test code source file
 598 #      // @suwit -- Thai sample data from GVT Guideline
 599 #
 600 <data>•\u0E2B\u0E19\u0E36\u0E48\u0E07<200>\u0E04\u0E33<200>\u0E44\u0E17\u0E22<200>\
 601 \u0E2A\u0E32\u0E21\u0E32\u0E23\u0E16<200>\u0E1B\u0E23\u0E30\u0E01\u0E2D\u0E1A<200>\
 602 \u0E14\u0E49\u0E27\u0E22<200>\u0e2b\u0e25\u0e32\u0e22<200>\
 603 \u0e1e\u0e22\u0e32\u0e07\u0e04\u0e4c<200></data>
 604
 605 # Test data originally from http://bugs.icu-project.org/trac/search?q=r30327
 606 <data>•กู<200> •กิน<200>กุ้ง<200> •ปิ้่<200>งอ<200>ยู่<200>ใน<200>ถ้ำ<200></data>
 607
 608 <data>•\u0E01\u0E39<200>\u0020•\u0E01\u0E34\u0E19<200>\u0E01\u0E38\u0E49\u0E07<200>\
 609 \u0020•\u0E1B\u0E34\u0E49\u0E48<200>\u0E07\u0E2D<200>\u0E22\u0E39\u0E48<200>\
 610 \u0E43\u0E19<200>\u0E16\u0E49\u0E33<200></data>
 611
 612 <line>
 613 <data>•0E01\u0E39\u0020•\u0E01\u0E34\u0E19•\u0E01\u0E38\u0E49\u0E07\
 614 \u0020•\u0E1B\u0E34\u0E49\u0E48•\u0E07\u0E2D•\u0E22\u0E39\u0E48•\
 615 \u0E43\u0E19•\u0E16\u0E49\u0E33•</data>
 616
 617 # Data originally from intltest RBBITest::TestThaiLineBreak()
 618 #
 619 #  \u0e2f-- the Thai paiyannoi character-- isn't a letter.  It's a symbol that
 620 #  represents elided letters at the end of a long word.  It should be bound to
 621 #  the end of the word and not treated as an independent punctuation mark.
 622 #
 623 #  the one time where the paiyannoi occurs somewhere other than at the end
 624 #  of a word is in the Thai abbrevation for "etc.", which both begins and
 625 #  ends with a paiyannoi
 626 #
 627 <line>
 628 <data>•\u0e2a\u0e16\u0e32\u0e19\u0e35\u0e2f•\
 629 \u0e08\u0e30•\
 630 \u0e23\u0e30\u0e14\u0e21•\
 631 \u0e40\u0e08\u0e49\u0e32•\
 632 \u0e2b\u0e19\u0e49\u0e32\u0e17\u0e35\u0e48•\
 633 \u0e2d\u0e2d\u0e01•\
 634 \u0e21\u0e32•\
 635 \u0e40\u0e23\u0e48\u0e07•\
 636 \u0e23\u0e30\u0e1a\u0e32\u0e22•\
 637 \u0e2d\u0e22\u0e48\u0e32\u0e07•\
 638 \u0e40\u0e15\u0e47\u0e21•\
 639 \u0e2f\u0e25\u0e2f•\
 640 \u0e17\u0e35\u0e48•\
 641 \u0e19\u0e31\u0e49\u0e19•</data>
 642
 643 # Data originally from RBBITest::TestMixedThaiLineBreak()
 644 #   @suwit -- Test Arabic numerals, Thai numerals, Punctuation and English characters start
 645 #
 646 <line>
 647 <data>•\u0E1B\u0E35•\
 648 \u0E1E\u0E38\u0E17\u0E18\u0E28\u0E31\u0E01\u0E23\u0E32\u0E0A •\
 649 2545 •\
 650 \u0E40\u0E1B\u0E47\u0E19•\
 651 \u0E1B\u0E35•\
 652 \u0E09\u0E25\u0E2D\u0E07•\
 653 \u0E04\u0E23\u0E1A•\
 654 \u0E23\u0E2D\u0E1A •\
 655 \"\u0E52\u0E52\u0E50 •\
 656 \u0E1b\u0E35\" •\
 657 \u0E02\u0E2d\u0E07•\
 658 \u0E01\u0E23\u0E38\u0E07•\
 659 \u0E23\u0E31\u0E15\u0E19\u0E42\u0E01\u0E2A\u0E34\u0E19\u0E17\u0E23\u0E4C •\
 660 (\u0E01\u0E23\u0E38\u0E07\u0E40\u0E17\u0E1e\u0E2F•\
 661 \u0E2B\u0E23\u0E37\u0E2D •\
 662 Bangkok)•</data>
 663
 664 # Data originally from RBBITest::TestMaiyamok()
 665 #   The Thai maiyamok character is a shorthand symbol that means "repeat the previous
 666 #   word".  Instead of appearing as a word unto itself, however, it's kept together
 667 #   with the word before it.
 668 #
 669 <line>
 670 <data>•\u0e44\u0e1b\u0e46•\
 671 \u0e21\u0e32\u0e46•\
 672 \u0e23\u0e30\u0e2b\u0e27\u0e48\u0e32\u0e07•\
 673 \u0e01\u0e23\u0e38\u0e07•\
 674 \u0e40\u0e17\u0e1e•\
 675 \u0e41\u0e25\u0e30•\
 676 \u0e40\u0e03\u0e35•\
 677 \u0e22\u0e07•\
 678 \u0e43\u0e2b\u0e21\u0e48•</data>
 679
 680
 681
 682 ##########################################################################################
 683 #
 684 #   Khmer Tests
 685 #
 686 ##########################################################################################
 687
 688 # Test data originally from http://bugs.icu-project.org/trac/search?q=r30327
 689 #  from the file testdata/wordsegments.txt
 690 <locale en>
 691 <word>
 692
 693 <data>•តើ<200>លោក<200>មក<200>ពី<200>ប្រទេស<200>ណា<200></data>
 694 <data>•សណ្ដូក<200>ក<200>បណ្ដែត<200>ខ្លួន<200></data>
 695 <data>•ពណ៌ស<200>ម្ដេច<200>ថា<200>ខ្មៅ<200></data>
 696 #ប្រយោគ|ពី|របៀប|រួបរួម|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data>
 697 <data>•ប្រយោគ<200>ពី<200>របៀប<200>ដែល<200>និង<200>ភាព<200>ផ្សេងគ្នា<200>ដែល<200>អាច<200>ចូល<200></data>
 698 #ប្រយោគ|ពី|របៀប|ជា|មួយ|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data>
 699 <data>•សូម<200>ចំណាយពេល<200>បន្តិច<200>ដើម្បី<200>អធិស្ឋាន<200>អរព្រះគុណ<200>ដល់<200>ព្រះអង្គ<200></data>
 700 <data>•ការ<200>ថោកទាប<200>បរិប្បូណ៌<200>ដោយ<200></data>
 701 <data>•ប្រើប្រាស់<200>ស្អាត<200>ទាំង<200>ចិត្ត<200>សិស្ស<200>នោះ<200></data>
 702 <data>•បើ<200>អ្នក<200>ប្រព្រឺត្ត<200>អំពើអាក្រក់<200>មុខ<200>ជា<200>មាន<200></data>
 703 <data>•ប្រដាប់<200>ប្រដា<200>រ<200>រៀនសូត្រ<200>បន្ទប់<200>រៀន<200></data>
 704 <data>•ដើរតួ<200>មនុស្សគ<200>ឥត<200>បញ្ចេញ<200>យោបល់<200>សោះ<200>ឡើយ<200></data>
 705 <data>•មិន<200>អាច<200>ឲ្យ<200>យើង<200>ធ្វើ<200>កសិកម្ម<200>បាន<200>ឡើយ<200></data>
 706 <data>•បន្ត<200>សេចក្ត<200>ទៅទៀត<200></data>
 707 <data>•ក្រុម<200>ប៉ូលិស<200>បណ្តាក់<200>គ្នា<200></data>
 708 <data>•គ្មាន<200>សុខ<200>សំរាន្ត<200>ដង<200>ណា<200></data>
 709 <data>•បាន<200>សុខភាព<200>បរិប្បូណ៌<200></data>
 710 <data>•ជា<200>មេចោរ<200>ខ្ញុំ<200>នឹង<200>ស្លាប់<200>ទៅវិញ<200>ជា<200>មេចោរ<200></data>
 711 <data>•ឯ<200>ការ<200>វាយ<200>ផ្ចាល<200>ដែល<200>នាំ<200></data>
 712 <data>•គេ<200>ដឹក<200>ទៅ<200>សំឡាប់<200></data>
 713 #អ្នក|ដែល|ជា|មន្ត្រី|ធំ|លើ|គាត់|ទេ<200></data>
 714 <data>•យក<200>ទៅ<200>សម្លាប់ចោល<200>ស្ងាត់<200></data>
 715 <data>•ត្រូវ<200>បាន<200>គេ<200>សម្លាប់<200></data>
 716 <data>•នៅក្នុង<200>ស្រុក<200>ខ្ល<200>ងហ្ស៊ុន<200></data>
 717
 718
 719 #
 720 #  Jitterbug 3671 Test Case
 721 #
 722 <data>•สวัสดี<200>ครับ<200>สบาย<200>ดี<200>ไหม<200> •ครับ<200></data>
 723
 724 #
 725 #  Trac ticket 5595 Test Case
 726 <data>•บท<200>ที่๑พายุ<200>ไซโคลน<200>โด<200>โรธี<200>อาศัย<200>อยู่<200>ท่ามกลาง<200>\
 727 ทุ่งใหญ่<200>ใน<200>แคนซัส<200>กับ<200>ลุง<200>เฮ<200>นรี<200>ชาวไร่<200>และ<200>ป้า<200>เอ็ม<200>\
 728 ภรรยา<200>ชาวไร่<200>บ้าน<200>ของ<200>พวก<200>เขา<200>หลัง<200>เล็ก<200>เพราะ<200>ไม้<200>\
 729 สร้าง<200>บ้าน<200>ต้อง<200>ขน<200>มา<200>ด้วย<200>เกวียน<200>เป็น<200>ระยะ<200>ทาง<200>หลาย<200>\
 730 ไมล์<200></data>
 731
 732 ####################################################################################
 733 #
 734 #  Tailored (locale specific) breaking.
 735 #
 736 ####################################################################################
 737
 738 # Japanese line break tailoring test
 739
 740 <locale ja>
 741 <line>
 742 <data>•\u3041•\u3043•\u3045•\u31f1•</data>
 743 <locale en>
 744 <line>
 745 <data>•\u3041\u3043\u3045\u31f1•</data>
 746
 747 # The following data was originally in RBBITest::TestJapaneseWordBreak()
 748 <locale ja>
 749 <word>
 750 <data>•\u4ECA\u65E5<400>\u306F<400>\u3044\u3044<400>\u5929\u6C17<400>\u3067\u3059<400>\u306D<400>\u3002•\u000D\u000A•</data>
 751
 752 # UBreakIteratorType UBRK_WORD, Locale "ja"
 753 # Don't break in runs of hiragana or runs of ideograph, where the latter includes \u3005 \u3007 \u303B (cldrbug #2009).
 754 # \u79C1\u9054\u306B\u4E00\u3007\u3007\u3007\u306E\u30B3\u30F3\u30D4\u30E5\u30FC\u30BF\u304C\u3042\u308B\u3002\u5948\u3005\u306F\u30EF\u30FC\u30C9\u3067\u3042\u308B\u3002
 755 # modified to work with dbbi code - should verify
 756
 757 <locale ja>
 758 <word>
 759 <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>
 760
 761 <locale root>
 762 <word>
 763 <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>
 764
 765 # UBreakIteratorType UBRK_SENTENCE, Locale "el"
 766 # Add break after Greek question mark (cldrbug #2069).
 767 # "\u0391\u03B2, \u03B3\u03B4; \u0395 \u03B6\u03B7\u037E \u0398 \u03B9\u03BA. "
 768 # "\u039B\u03BC \u03BD\u03BE! \u039F\u03C0, \u03A1\u03C2? \u03A3"
 769 # which is "Αβ, γδ; Ε ζη; Θ ικ. Λμ νξ! Οπ, Ρς? Σ"
 770
 771 <locale root>
 772 <sent>
 773 <data>•Αβ, γδ; Ε ζη; Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data>
 774
 775 <locale el>
 776 <sent>
 777 <data>•Αβ, γδ; •Ε ζη; •Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data>
 778
 779 #  UBreakIteratorType UBRK_WORD, Locale "en_US_POSIX"
 780 #  Words don't include colon or period (cldrbug #1969).
 781
 782 <locale en_US>
 783 <word>
 784 <data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
 785 •for<200> •CS<200>-•types<200>.•</data>
 786
 787 <locale en_US_POSIX>
 788 <word>
 789 <data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct<200>.•field<200> \
 790 •for<200> •CS<200>-•types<200>.•</data>
 791
 792
 793 # UBreakIteratorType UBRK_CHARACTER, Locale "th"
 794 # Clusters should not include spacing Thai/Lao vowels (prefix or postfix), except for [SARA] AM (cldrbug #2161).
 795 # Update:  As of Unicode 6.1 root has same behavior as th for this.
 796 #
 797 # "\u0E01\u0E23\u0E30\u0E17\u0E48\u0E2D\u0E21\u0E23\u0E08\u0E19\u0E32 "
 798 # "(\u0E2A\u0E38\u0E0A\u0E32\u0E15\u0E34-\u0E08\u0E38\u0E11\u0E32\u0E21\u0E32\u0E28) "
 799 # "\u0E40\u0E14\u0E47\u0E01\u0E21\u0E35\u0E1B\u0E31\u0E0D\u0E2B\u0E32 "
 800 # which is "กระท่อมรจนา (สุชาติ-จุฑามาศ) เด็กมีปัญหา "
 801
 802 <locale th>
 803 <char>
 804 <data>•\u0E01•\u0E23•\u0E30•\u0E17\u0E48•\u0E2D•\u0E21•\u0E23•\u0E08•\u0E19•\u0E32• •\
 805 (•\u0E2A\u0E38•\u0E0A•\u0E32•\u0E15\u0E34•-•\u0E08\u0E38•\u0E11•\u0E32•\u0E21•\u0E32•\u0E28•)• •\
 806 \u0E40•\u0E14\u0E47•\u0E01•\u0E21\u0E35•\u0E1B\u0E31•\u0E0D•\u0E2B•\u0E32• •</data>
 807
 808 # Finnish line breaking
 809 #
 810 # These rules deal with hyphens when there is a space on the leading side.
 811 # There should be a break opportunity between the space and the hyphen, and not after the hyphen.
 812 # See CLDR ticket 3029.
 813 # See ICU ticket 8151
 814
 815 <locale root>
 816 <line>
 817 <data>•abc •- •def    •abc •-•def    •abc- •def   •abc-•def•</data>   # With ASCII hyphen
 818 <data>•abc •‐ •def    •abc •‐•def    •abc‐ •def   •abc‐•def•</data>   # With Unicode u2010 hyphen
 819
 820 <locale fi>
 821 <line>
 822 # TODO: problems with Finnish line break rules cause these two lines to fail.
 823 #<data>•abc •- •def    •abc •-def    •abc- •def   •abc-•def•</data>   # With ASCII hyphen
 824 #<data>•abc •‐ •def    •abc •‐def    •abc‐ •def   •abc‐•def•</data>   # With Unicode u2010 hyphen
 825
 826 <data>•abc •- •def    •abc •-def    •abc- •def   •</data>   # With ASCII hyphen
 827 <data>•abc •‐ •def    •abc •‐def    •abc‐ •def   •</data>   # With Unicode u2010 hyphen