icuSources/test/testdata/rbbitst.txt

   1 # Copyright (c) 2001-2008 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 #
  24
  25
  26 #   Temp debugging tests
  27 <line>
  28 #     to test for bug #4097920
  29 <data>•dog,cat,mouse •(one)•(two)\n<100></data>
  30
  31 ########################################################################################
  32 #
  33 #
  34 #       G r a p h e m e    C l u s t e r     T e s t s
  35 #
  36 #
  37 ##########################################################################################
  38 <char>
  39
  40 <data>•a•b•c• •,•\u0666•</data>                 # Quick Test
  41 <data>•\r•\r•\r\n•\r\n•\n•\r•</data>            # don't break CR/LF
  42
  43 # Always break after controls.  Combining chars don't combine with them.
  44 <data>•\u0003•\N{COMBINING GRAVE ACCENT}•\r•\N{COMBINING GRAVE ACCENT}•</data>
  45 <data>•\u0085•\N{COMBINING MACRON}•A\N{COMBINING MACRON}•</data>
  46
  47 # Surrogates
  48 <data>•\U00011000•\U00010020•\U00010000\N{COMBINING MACRON}•</data>
  49 <data>•\ud800\udc00•\udbff\udfff•a•</data>
  50
  51 # Extend (Combining chars) combine.
  52 <data>•A\N{COMBINING GRAVE ACCENT}•B•</data>
  53 <data>•\N{GREEK SMALL LETTER MU}\N{COMBINING LOW LINE}\N{COMBINING HORN}•</data>
  54 <data>•a\u0301•b\u0302•c\u0303•d\u0304•e\u0305•f\u0306•g\u0307•h\u0308•i\u0309•</data>
  55
  56 <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>
  57
  58 # Don't break Hangul Syllables
  59 #   L : \u1100
  60 #   V : \u1161
  61 #   T : \u11A8
  62 #  LV : \uAC00
  63 # LVT : \uAC01
  64
  65 <data>•\u1100\u1161\u11a8•\u1100\u1161\u11a8•</data>  #LVT
  66 <data>•\u1100\u1161•\u1100\u1161•</data>
  67 <data>•\u1100\u1161\u11a8•\u1161•\u1100•\u11a8•\u1161\u1161\u1161\u11a8•</data>
  68 <data>•\u1100\u1100\uac01•\u1100\uac01•\u1100\uac01\u0301•\uac01•</data>
  69 <data>•\u1100\u0301•\u1161\u11a8\u0301•\u11a8•</data>
  70
  71
  72
  73 # Hindi combining chars.  (An old test)
  74 #   TODO:  Update these tests for Unicode 5.1 Extended Grapheme clusters
  75 #<data>•भ••ा•\u0930•\u0924• •\u0938\u0941\u0902•\u0926•\u0930•
  76 #•\u0939•\u094c•\u0964•</data>
  77 #<data>•\u0916\u0947•\u0938\u0941\u0902•\u0926•\u0930•\u0939•\u094c•\u0964•</data>
  78
  79
  80 #  Bug 1587.  Tamil.  \u0baa\u0bc1 is an Extended Grpaheme Cluster
  81 <data>•\u0baa\u0bc1•\u0baa\u0bc1•</data>
  82
  83 #   Regression test for bug 1889
  84 <data>•\u0f40\u0f7d•\u0000•\u0f7e•</data>
  85
  86
  87 #     0xffff is a legal character, and should not stop the break iterator early.
  88 #     (Requires special casing in implementation, which is why it gets a test.)
  89 <data>•\uffff•\uffff• •a•</data>
  90
  91 #  Treat Japanese Half Width voicing marks as combining
  92 <data>•A\uff9e•B\uff9f\uff9e\uff9f•C•</data>
  93
  94 ########################################################################################
  95 #
  96 #
  97 #       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
  98 #
  99 #
 100 ##########################################################################################
 101 #<xgc>
 102
 103 # Plain Vanilla grapheme clusters
 104 #<data>•a•b•c•</data>
 105 #<data>•a\u0301\u0302• •b\u0303\u0304•</data>
 106
 107 # Assorted Hindi combining marks
 108 #<data>•\u0904\u0903• •\u0937\u093E• •\u0904\u093F• •\u0937\u0940• •\u0937\u0949• •\u0937\u094A• •\u0937\u094B• •\u0937\u094C•</data>
 109
 110 # Thai Clusters
 111 # $Prepend $Extend* $PrependBase $Extend*;
 112 #
 113 #<data>•\u0e40\u0e01•\u0e44\u0301\u0e23\u0302\u0303•\u0e40•\u0e40\u0e02•\u0e02• •</data>
 114
 115
 116 ########################################################################################
 117 #
 118 #
 119 #       W o r d    B o u n d a r y      T e s t s
 120 #
 121 #
 122 ##########################################################################################
 123
 124 <word>
 125 #
 126 # Quick sanity test
 127 #
 128 <data>•hello<200> •there<200> •goodbye<200></data>
 129 <data>•hello<200> •12345<100> •,•</data>
 130
 131
 132 #
 133 # Test data originally in RBBIAPITest::TestFirstNextFollowing() and TestLastPreviousPreceding()
 134 #
 135
 136 <word>
 137 <data>•This<200> •is<200> •a<200> •word<200> •break<200>.• • •Isn't<200> •it<200>?• •2.25<100></data>
 138
 139
 140
 141 #
 142 # Data originally from TestDefaultRuleBasedWordIteration()
 143 #
 144 <data>•Write<200> •wordrules<200>.• •123.456<100> •alpha\u00adbeta\u00adgamma<200> •\u092f\u0939<200> •</data>
 145 <data>• •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200> •\u0938\u093f\u0916\u094b\u0917\u0947<200>?•</data>
 146
 147 #Hindi Numbers
 148 <data>• •\u0968\u0966.\u0969\u096f<100> •\u0967\u0966\u0966.\u0966\u0966<100> •\N{RUPEE SIGN}•\u0967,\u0967\u0966\u0966.\u0966\u0966<100> • •\u0905\u092e\u091c<200>\n•</data>
 149
 150 <data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢•£•¤•¥•alpha\u05f3beta\u05f4gamma<200> •</data>
 151
 152 <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>
 153
 154 #Hangul
 155 <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>
 156
 157
 158 # Words containing non-BMP letters
 159 <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>
 160
 161 # Unassigned code points
 162 <data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data>
 163
 164 # Hiragana & Katakana stay together, but separates from each other and Latin.
 165 <data>•abc<200>\N{HIRAGANA LETTER SMALL A}<300>\N{HIRAGANA LETTER VU}\N{COMBINING ACUTE ACCENT}<300>\N{HIRAGANA ITERATION MARK}<300>\N{KATAKANA LETTER SMALL A}\N{KATAKANA ITERATION MARK}\N{HALFWIDTH KATAKANA LETTER WO}\N{HALFWIDTH KATAKANA LETTER N}<300>def<200>#•</data>
 166
 167 # Words with interior formatting characters
 168 <data>•def\N{COMBINING ACUTE ACCENT}\N{SYRIAC ABBREVIATION MARK}ghi<200> •</data>
 169
 170 # to test for bug #4097779
 171 <data>•aa\N{COMBINING GRAVE ACCENT}a<200> •</data>
 172
 173
 174 #      to test for bug #4098467
 175 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 176 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 177 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 178 #      Both sequences should be semantically identical and break the same way.
 179 #      precomposed syllables...
 180 <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>
 181
 182 <data>•abc<200>\u4e01<400>\u4e02<400>\u3005<200>\u4e03<400>\u4e03<400>abc<200> •</data>
 183
 184 <data>•\u06c9\uc799\ufffa<200></data>
 185
 186 #
 187 #      Try some words from other scripts.
 188 #
 189
 190 #       Try some words from other scripts.
 191 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 192 #
 193 <data>•ΑΒΓ<200> •БВГ<200> •אבג֓<200> •ابت<200> •١٢٣<100> •\u10A0\u10A1\u10A2<200> •ABC<200> •</data>
 194
 195 <data>•\u0301•A<200></data>
 196
 197
 198 #
 199 #  Hindi word break tests, imported from the old RBBI tests.
 200 #    An historical note:  a much earlier version of ICU break iterators had a number
 201 #    of special case rules for Hindi, which were tested by an earlier version of
 202 #    this test data.  The current RBBI rules do not special case Hindi in
 203 #    any way, making this test data much less signfificant.
 204 #
 205 <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>
 206 •\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>
 207
 208 #
 209 #  Failures from monkey tests
 210 #
 211 <data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data>
 212
 213 #
 214 # Jitterbug 5276 - treat Japanese half width voicing marks as Grapheme Extend
 215 #
 216 <data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data>
 217
 218 ########################################################################################
 219 #
 220 #
 221 #       S e n t e n c e     B o u n d a r y      T e s t s
 222 #
 223 #
 224 ##########################################################################################
 225
 226
 227 #
 228 # Test data originally from RBBI RBBITest::TestDefaultRuleBasedSentenceIteration()
 229 #
 230 <sent>
 231
 232
 233 <sent>
 234 <data>•This\n<100></data>
 235 <data>•Hello! •how are you? •I'am fine. •Thankyou. •How are you \
 236 doing? •This\n<100> costs $20,00,000. •</data>
 237
 238
 239 # Sentence ending in a quote.
 240 <data>•"Sentence ending with a quote." •Bye.•</data>
 241
 242 # Sentence, and test data, ending without a period or other terminator.
 243 <data>•Here is a random sentence, no ending period<100></data>
 244
 245
 246 <data>•  (This is it).  •Testing the sentence iterator. •\
 247 "This isn't it." •Hi! \
 248 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
 249 "This isn't it." •\
 250 Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!! •Don't rock the boat.\u2029•Because I am the daddy, that is why.
 251 •Not on my time (el timo.)! •</data>
 252
 253 <data>•Hello.  •So what!!\u2029•"But now," he said, \
 254 "I know!" •\
 255 Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!). •One species, B. anthracis, is highly virulent.
 256 •Wolf said about Sounder:\
 257 "Beautifully thought-out and directed." •\
 258 Have you ever said, "This is where\tI shall live"? •He answered, \
 259 "You may not!" •Another popular saying is: "How do you do?". \n•\
 260 Yet another popular saying is: \
 261 'I'm fine thanks.' •\
 262 What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tall!!\
 263 •Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100></data>
 264
 265 <data>•No breaks when . is surrounded by UPPER.Case letters.  •</data>
 266 <data>•No breaks when . is followed by Numeric .4 a.4 C.4 3.1 .•</data>
 267 <data>•No breaks when . is followed by a lower, with possible intervening punct .,a .$a .)a. •</data>
 268
 269 #
 270 #  Sentence Breaks: no break at the boundary between CJK and other letters
 271 #
 272 <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>
 273
 274 #
 275 #      Treat fullwidth variants of .!? the same as their
 276 #      normal counterparts
 277 #
 278 <data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data>
 279
 280
 281 #
 282 #       Don't break sentences at boundary between CJK and digits
 283 #
 284 <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>
 285
 286 #
 287 #      Breaks around '(' following a sentence TERM.  (Rule 9)
 288 #
 289 <data>•How do you do?(•Fine). •</data>
 290 <data>•How do you do? •(Fine). •</data>
 291 <data>•How do you do?(•fine). •</data>
 292 <data>•How do you do? •(fine). •</data>
 293
 294 #
 295 <data>•Hello.123<100></data>    # Rule 6
 296 <data>•Hello?•123<100></data>
 297
 298 <data>•HELLO.Bye<100></data>    # Rule 7
 299 <data>•HELLO?•Bye<100></data>
 300
 301 <data>•Hello.goodbye<100></data>  #Rule 8
 302 <data>•Hello. •Goodbye<100></data>
 303 <data>•Hello. goodbye<100></data>
 304
 305
 306
 307 #
 308 #        test for bug #4158381: No breaks when there are no terminators around
 309 #
 310 <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>
 311 <data>•Another test.\u2029•</data>
 312
 313 #        test for bug #4143071: Make sure sentences that end with digits
 314 #        work right
 315 #
 316 <data>•Today is the 27th of May, 1998.  •</data>
 317 <data>•Tomorrow with be 28 May 1998.  •</data>
 318 <data>•The day after will be the 30th.\u2029•</data>
 319
 320 #        test for bug #4152416: Make sure sentences ending with a capital
 321 #        letter are treated correctly
 322 #
 323 <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>
 324
 325 #        test for bug #4152117: Make sure sentence breaking is handling
 326 #        punctuation correctly [COULD NOT REPRODUCE THIS BUG, BUT TEST IS
 327 #        HERE TO MAKE SURE IT DOESN'T CROP UP]
 328 #
 329 <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.
 330 •</data>
 331
 332 #        sentence breaks for hindi which used Devanagari script
 333 #        make sure there is sentence break after ?,danda(hindi phrase separator),
 334 #        fullstop followed by space.  (VERY old test)
 335 #
 336 <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>\
 337 \u0915\u0948\u0938\u0947 \u0939\u0948?•\u0935\u0939 \u0915\u094d\u200d\u092f\u093e\n\
 338 <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>
 339
 340 #         Regression test for bug #1984, Sentence break in Arabic text.
 341
 342 <data>\
 343 •\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>
 344
 345 #         Try a few more of the less common sentence endings.
 346 <data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end here. •</data>
 347
 348
 349
 350
 351 ################################################################
 352 #
 353 #
 354 #        L I N E     B R E A K
 355 #
 356 #
 357 ################################################################
 358
 359 <line>
 360 #
 361 # Test Character for each of the line break classes.
 362 #
 363 # 00A1;AI # INVERTED EXCLAMATION MARK  ¡
 364 # 0041;AL # LATIN CAPITAL LETTER A
 365 # 0009;BA # <control>
 366 # 00B4;BB # ACUTE ACCENT
 367 # 000C;BK # <control>
 368 # 2014;B2 # EM DASH
 369 # FFFC;CB # OBJECT REPLACEMENT CHARACTER
 370 # 0029;CL # RIGHT PARENTHESIS
 371 # 0301;CM # COMBINING ACUTE ACCENT
 372 # 0021;EX # EXCLAMATION MARK
 373 # 00A0;GL # NO-BREAK SPACE
 374 # 002D;HY # HYPHEN-MINUS
 375 # 4E00;ID # <CJK Ideograph, First>
 376 # 2024;IN # ONE DOT LEADER
 377 # 002C;IS # COMMA
 378 # 000A;LF # <control>
 379 # 0E5A;NS # THAI CHARACTER ANGKHANKHU
 380 # 0032;NU # DIGIT TWO
 381 # 0028;OP # LEFT PARENTHESIS
 382 # 0025;PO # PERCENT SIGN
 383 # 0024;PR # DOLLAR SIGN
 384 # 0022;QU # QUOTATION MARK
 385 # 0E01;SA # THAI CHARACTER KO KAI
 386 # DB7F;SG # Surrogate
 387 # 0020;SP # SPACE
 388 # 002F;SY # SOLIDUS /
 389 # F8FF;XX # Private Use
 390 # 200B;ZW # ZERO WIDTH SPACE
 391
 392
 393 # 2b  Always break at end of text
 394
 395 <data>•  •\u00A1•</data>
 396 <data>•  •\u0041•</data>
 397 <data>•  •\u0009•</data>
 398 <data>•  •\u00B4•</data>
 399 <data>•    \u000C<100></data>    # LB3C  × BK
 400 <data>•  •\u2014•</data>
 401 <data>•  •\uFFFC•</data>
 402 <data>•   \u0029•</data>    # LB 8   × CL
 403 # <data>• • \u0301•</data>    # LB 7a   Treat SP CM* as if it were ID  #TODO:  SP CM
 404 <data>•   \u0021•</data>    # LB 8   × EX
 405 #<data>•   \u00A0•</data>    # LB 11b   × GL   TODO:  fix.
 406 <data>•  •\u002D•</data>
 407 <data>•  •\u4E00•</data>
 408 <data>•  •\u2024•</data>
 409 <data>•   \u002C•</data>    # LB 8   × IS
 410 <data>•   \u000A<100></data>    # LB3C   × ( BK | CR | LF | NL )
 411 <data>•  •\u0E5A•</data>
 412 <data>•  •\u0032•</data>
 413 <data>•  •\u0028•</data>
 414 <data>•  •\u0025•</data>
 415 <data>•  •\u0024•</data>
 416 <data>•  •\u0022•</data>
 417 <data>•  •\u0E01•</data>
 418 <data>•  •\uDB7F•</data>
 419 <data>•   \u0020•</data>     # LB4 - don't break before space.
 420 <data>•   \u002F•</data>     # LB 8  × SY
 421 <data>•  •\uF8FF•</data>
 422 <data>•   \u200B•</data>     # LB4 - don't break before ZA
 423
 424
 425 # 3a  Always break after hard line breaks.
 426 # 3c  Never break before hard line breaks.
 427
 428 <data>•  •\u00A1\u2028<100>\u00A1•</data>
 429 <data>•  •\u0041\u2028<100>\u0041•</data>
 430 <data>•  •\u0009\u2028<100>\u0009•</data>
 431 <data>•  •\u00B4\u2028<100>\u00B4•</data>
 432 <data>•   \u000C<100>\u2028<100>\u000C<100></data>
 433 <data>•  •\u2014\u2028<100>\u2014•</data>
 434 <data>•  •\uFFFC\u2028<100>\uFFFC•</data>
 435 <data>•   \u0029\u2028<100>\u0029•</data>
 436 #<data>•   \u0301\u2028<100>\u0301•</data>    # TODO:  fix.
 437 <data>•   \u0021\u2028<100>\u0021•</data>
 438 #<data>•   \u00A0\u2028<100>\u00A0•</data>    # TODO:  fix
 439 <data>•  •\u002D\u2028<100>\u002D•</data>
 440 <data>•  •\u4E00\u2028<100>\u4E00•</data>
 441 <data>•  •\u2024\u2028<100>\u2024•</data>
 442 <data>•   \u002C\u2028<100>\u002C•</data>
 443 <data>•   \u000A<100>\u2028<100>\u000A<100></data>
 444 <data>•  •\u0E5A\u2028<100>\u0E5A•</data>
 445 <data>•  •\u0032\u2028<100>\u0032•</data>
 446 <data>•  •\u0028\u2028<100>\u0028•</data>
 447 <data>•  •\u0025\u2028<100>\u0025•</data>
 448 <data>•  •\u0024\u2028<100>\u0024•</data>
 449 <data>•  •\u0022\u2028<100>\u0022•</data>
 450 <data>•  •\u0E01\u2028<100>\u0E01•</data>
 451 <data>•  •\uDB7F\u2028<100>\uDB7F•</data>
 452 <data>•   \u0020\u2028<100>\u0020•</data>
 453 <data>•   \u002F\u2028<100>\u002F•</data>
 454 <data>•  •\uF8FF\u2028<100>\uF8FF•</data>
 455 <data>•   \u200B\u2028<100>\u200B•</data>
 456
 457
 458 #
 459 #  Old Line Break Test data.  Orginally located in RBBITest::TestDefaultRuleBasedLineIteration()
 460 #
 461
 462 <line>
 463
 464 <data>•Multi-•Level •example •of •a •semi-•idiotic •non-•sensical •(non-•important) •sentence.
 465 <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>
 466
 467 <line>
 468 <data>•Hello! •how\r\n<100> •(are)\r<100> •you? •I'am •fine- •Thankyou. •foo\u00a0bar
 469 <100>How, •are, •you? •This, •costs •$20,00,000.•</data>
 470
 471 #     test for bug #4068133
 472 #
 473 <data>•\u96f6•\u4e00\u3002•\u4e8c\u3001•\u4e09\u3002\u3001•\u56db\u3001\u3002\u3001•\u4e94,•\u516d.•\u4e03.\u3001,\u3002•\u516b•</data>
 474
 475 #     to test for bug #4086052
 476 <data>•foo\u00a0bar•</data>
 477
 478 #     to test for bug #4097920
 479 <data>•dog,cat,mouse •(one)•(two)\n<100></data>
 480
 481 #     to test for bug #4035266
 482 <data>•The •balance •is •$-23,456.78, •not •-•$32,456.78!\n<100></data>
 483
 484
 485 #      to test for bug #4098467
 486 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 487 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 488 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 489 #      Both sequences should be semantically identical and break the same way.
 490 #      precomposed syllables...  (I == Rich Gillam?)
 491 #
 492 <data>•\uc0c1•\ud56d •\ud55c•\uc778 •\uc5f0•\ud569 •\uc7a5•\ub85c•\uad50•\ud68c•</data>
 493
 494 #      conjoining jamo...
 495 #      TODO:  rules update needed
 496 #<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>
 497
 498 #      to test for bug #4117554: Fullwidth .!? should be treated as postJwrd
 499 <data>•\u4e01\uff0e•\u4e02\uff01•\u4e03\uff1f•</data>
 500
 501 #      Surrogate line break tests.
 502 #
 503 <data>•\u4e01•\ud840\udc01•\u4e02•abc •\ue000 •\udb80\udc01•</data>
 504
 505 #      Regression for bug 836
 506 #        Note:  Unicode 5.1 changed this behavior
 507 #               ICU will want to change it back before releasing,
 508 #               so there is no break preceding the '('
 509 <data>•AAA•(AAA •</data>
 510
 511 #       Try some words from other scripts.
 512 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 513 #
 514 <data>•ΑΒΓ •БВГ •אבג֓ •ابت •١٢٣ •\u10A0\u10A1\u10A2 •ABC •</data>
 515
 516
 517
 518 ########################################################################################
 519 #
 520 #
 521 #       T i t l e   B o u n d a r y      T e s t s
 522 #
 523 #
 524 ##########################################################################################
 525 <title>
 526 <data>•Here •is •a •short •sample •sentence.  •And •another.•</data>
 527 <data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE.  •AND •ANOTHER.•</data>
 528 <data>•  •Start •and •end •with •spaces   •</data>
 529 <data>•Include 123 456 ^&  •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data>
 530
 531 <data>•Combining\u0301 \u0301•ma\u0306rks  •bye  •</data>
 532 <data>•123  •Start •with •a •number.•</data>
 533
 534 <data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data>
 535
 536
 537 ##########################################################################################
 538 #
 539 #   Thai Tests
 540 #
 541 ##########################################################################################
 542 <locale th>
 543 <word>
 544 #
 545 # Test data originally from the test code source file
 546 #      // @suwit -- Thai sample data from GVT Guideline
 547 #
 548 <data>•\u0E2B\u0E19\u0E36\u0E48\u0E07<200>\u0E04\u0E33<200>\u0E44\u0E17\u0E22<200>\
 549 \u0E2A\u0E32\u0E21\u0E32\u0E23\u0E16<200>\u0E1B\u0E23\u0E30\u0E01\u0E2D\u0E1A<200>\
 550 \u0E14\u0E49\u0E27\u0E22<200>\u0e2b\u0e25\u0e32\u0e22<200>\
 551 \u0e1e\u0e22\u0e32\u0e07\u0e04\u0e4c<200></data>
 552
 553 #
 554 #  Jitterbug 3671 Test Case
 555 #
 556 <data>•สวัสดี<200>ครับ<200>สบาย<200>ดี<200>ไหม<200> •ครับ<200></data>
 557
 558 #
 559 #  Trac ticket 5595 Test Case
 560 <data>•บท<200>ที่๑พายุ<200>ไซโคลน<200>โด<200>โรธี<200>อาศัย<200>อยู่<200>ท่ามกลาง<200>\
 561 ทุ่งใหญ่<200>ใน<200>แคนซัส<200>กับ<200>ลุง<200>เฮ<200>นรี<200>ชาวไร่<200>และ<200>ป้า<200>เอ็ม<200>\
 562 ภรรยา<200>ชาวไร่<200>บ้าน<200>ของ<200>พวก<200>เขา<200>หลัง<200>เล็ก<200>เพราะ<200>ไม้<200>\
 563 สร้าง<200>บ้าน<200>ต้อง<200>ขน<200>มา<200>ด้วย<200>เกวียน<200>เป็น<200>ระยะ<200>ทาง<200>หลาย<200>\
 564 ไมล์<200></data>
 565
 566