icuSources/test/testdata/rbbitst.txt

   1 # Copyright (c) 2001-2006 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 <data>•भ••ा•\u0930•\u0924• •\u0938\u0941\u0902•\u0926•\u0930•
  75 •\u0939•\u094c•\u0964•</data>
  76 <data>•\u0916\u0947•\u0938\u0941\u0902•\u0926•\u0930•\u0939•\u094c•\u0964•</data>
  77
  78
  79 #  Bug 1587.  Tamil.  \u0baa\u0bc1 should be two separate characters, even though
  80 #                     Hyangmi would perfer that it be one.
  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 #       W o r d    B o u n d a r y      T e s t s
  98 #
  99 #
 100 ##########################################################################################
 101
 102 <word>
 103 #
 104 # Quick sanity test
 105 #
 106 <data>•hello<200> •there<200> •goodbye<200></data>
 107 <data>•hello<200> •12345<100> •,•</data>
 108
 109
 110 #
 111 # Test data originally in RBBIAPITest::TestFirstNextFollowing() and TestLastPreviousPreceding()
 112 #
 113
 114 <word>
 115 <data>•This<200> •is<200> •a<200> •word<200> •break<200>.• • •Isn't<200> •it<200>?• •2.25<100></data>
 116
 117
 118
 119 #
 120 # Data originally from TestDefaultRuleBasedWordIteration()
 121 #
 122 <data>•Write<200> •wordrules<200>.• •123.456<100> •alpha\u00adbeta\u00adgamma<200> •\u092f\u0939<200> •</data>
 123 <data>• •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200> •\u0938\u093f\u0916\u094b\u0917\u0947<200>?•</data>
 124
 125 #Hindi Numbers
 126 <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>
 127
 128 <data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢•£•¤•¥•alpha\u05f3beta\u05f4gamma<200> •</data>
 129
 130 <data>•Badges<200>?• •BADGES<200>!•?•!• •We<200> •don't<200> •need<200> •no<200> •STINKING<200> •BADGES<200>!•!•1000,233,456.000<100> •1,23.322<100>%•123.1222<100>$•123,000.20<100> •179.01<100>%•X<200> •Now<200>\r•is<200>\n•the<200>\r\n•time<200> •</data>
 131
 132 #Hangul
 133 <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>
 134
 135
 136 # Words containing non-BMP letters
 137 <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>
 138
 139 # Unassigned code points
 140 <data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data>
 141
 142 # Hiragana & Katakana stay together, but separates from each other and Latin.
 143 <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>
 144
 145 # Words with interior formatting characters
 146 <data>•def\N{COMBINING ACUTE ACCENT}\N{SYRIAC ABBREVIATION MARK}ghi<200> •</data>
 147
 148 # to test for bug #4097779
 149 <data>•aa\N{COMBINING GRAVE ACCENT}a<200> •</data>
 150
 151
 152 #      to test for bug #4098467
 153 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 154 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 155 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 156 #      Both sequences should be semantically identical and break the same way.
 157 #      precomposed syllables...
 158 <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>
 159
 160 <data>•abc<200>\u4e01<400>\u4e02<400>\u3005<200>\u4e03<400>\u4e03<400>abc<200> •</data>
 161
 162 <data>•\u06c9\uc799\ufffa<200></data>
 163
 164 #
 165 #      Try some words from other scripts.
 166 #
 167
 168 #       Try some words from other scripts.
 169 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 170 #
 171 <data>•ΑΒΓ<200> •БВГ<200> •אבג֓<200> •ابت<200> •١٢٣<100> •\u10A0\u10A1\u10A2<200> •ABC<200> •</data>
 172
 173 <data>•\u0301•A<200></data>
 174
 175
 176 #
 177 #  Hindi word break tests, imported from the old RBBI tests.
 178 #    An historical note:  a much earlier version of ICU break iterators had a number
 179 #    of special case rules for Hindi, which were tested by an earlier version of
 180 #    this test data.  The current RBBI rules do not special case Hindi in
 181 #    any way, making this test data much less signfificant.
 182 #
 183 <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>
 184 •\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>
 185
 186 #
 187 #  Failures from monkey tests
 188 #
 189 <data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data>
 190
 191 #
 192 # Jitterbug 5276 - treat Japanese half width voicing marks as Grapheme Extend
 193 #
 194 <data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data>
 195
 196 ########################################################################################
 197 #
 198 #
 199 #       S e n t e n c e     B o u n d a r y      T e s t s
 200 #
 201 #
 202 ##########################################################################################
 203
 204
 205 #
 206 # Test data originally from RBBI RBBITest::TestDefaultRuleBasedSentenceIteration()
 207 #
 208 <sent>
 209
 210
 211 <sent>
 212 <data>•This\n<100></data>
 213 <data>•Hello! •how are you? •I'am fine. •Thankyou. •How are you \
 214 doing? •This\n<100> costs $20,00,000. •</data>
 215
 216
 217 # Sentence ending in a quote.
 218 <data>•"Sentence ending with a quote." •Bye.•</data>
 219
 220 # Sentence, and test data, ending without a period or other terminator.
 221 <data>•Here is a random sentence, no ending period<100></data>
 222
 223
 224 <data>•  (This is it).  •Testing the sentence iterator. •\
 225 "This isn't it." •Hi! \
 226 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
 227 "This isn't it." •\
 228 Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!! •Don't rock the boat.\u2029•Because I am the daddy, that is why.
 229 •Not on my time (el timo.)! •</data>
 230
 231 <data>•Hello.  •So what!!\u2029•"But now," he said, \
 232 "I know!" •\
 233 Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!). •One species, B. anthracis, is highly virulent.
 234 •Wolf said about Sounder:\
 235 "Beautifully thought-out and directed." •\
 236 Have you ever said, "This is where\tI shall live"? •He answered, \
 237 "You may not!" •Another popular saying is: "How do you do?". \n•\
 238 Yet another popular saying is: \
 239 'I'm fine thanks.' •\
 240 What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tall!!\
 241 •Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100></data>
 242
 243 <data>•No breaks when . is surrounded by UPPER.Case letters.  •</data>
 244 <data>•No breaks when . is followed by Numeric .4 a.4 C.4 3.1 .•</data>
 245 <data>•No breaks when . is followed by a lower, with possible intervening punct .,a .$a .)a. •</data>
 246
 247 #
 248 #  Sentence Breaks: no break at the boundary between CJK and other letters
 249 #
 250 <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>
 251
 252 #
 253 #      Treat fullwidth variants of .!? the same as their
 254 #      normal counterparts
 255 #
 256 <data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data>
 257
 258
 259 #
 260 #       Don't break sentences at boundary between CJK and digits
 261 #
 262 <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>
 263
 264 #
 265 #      Breaks around '(' following a sentence TERM.  (Rule 9)
 266 #
 267 <data>•How do you do?(•Fine). •</data>
 268 <data>•How do you do? •(Fine). •</data>
 269 <data>•How do you do?(•fine). •</data>
 270 <data>•How do you do? •(fine). •</data>
 271
 272 #
 273 <data>•Hello.123<100></data>    # Rule 6
 274 <data>•Hello?•123<100></data>
 275
 276 <data>•HELLO.Bye<100></data>    # Rule 7
 277 <data>•HELLO?•Bye<100></data>
 278
 279 <data>•Hello.goodbye<100></data>  #Rule 8
 280 <data>•Hello. •Goodbye<100></data>
 281 <data>•Hello. goodbye<100></data>
 282
 283
 284
 285 #
 286 #        test for bug #4158381: No breaks when there are no terminators around
 287 #
 288 <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>
 289 <data>•Another test.\u2029•</data>
 290
 291 #        test for bug #4143071: Make sure sentences that end with digits
 292 #        work right
 293 #
 294 <data>•Today is the 27th of May, 1998.  •</data>
 295 <data>•Tomorrow with be 28 May 1998.  •</data>
 296 <data>•The day after will be the 30th.\u2029•</data>
 297
 298 #        test for bug #4152416: Make sure sentences ending with a capital
 299 #        letter are treated correctly
 300 #
 301 <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>
 302
 303 #        test for bug #4152117: Make sure sentence breaking is handling
 304 #        punctuation correctly [COULD NOT REPRODUCE THIS BUG, BUT TEST IS
 305 #        HERE TO MAKE SURE IT DOESN'T CROP UP]
 306 #
 307 <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.
 308 •</data>
 309
 310 #        sentence breaks for hindi which used Devanagari script
 311 #        make sure there is sentence break after ?,danda(hindi phrase separator),
 312 #        fullstop followed by space.  (VERY old test)
 313 #
 314 <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>\
 315 \u0915\u0948\u0938\u0947 \u0939\u0948?•\u0935\u0939 \u0915\u094d\u200d\u092f\u093e\n\
 316 <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>
 317
 318 #         Regression test for bug #1984, Sentence break in Arabic text.
 319
 320 <data>\
 321 •\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>
 322
 323 #         Try a few more of the less common sentence endings.
 324 <data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end here. •</data>
 325
 326
 327
 328
 329 ################################################################
 330 #
 331 #
 332 #        L I N E     B R E A K
 333 #
 334 #
 335 ################################################################
 336
 337 <line>
 338 #
 339 # Test Character for each of the line break classes.
 340 #
 341 # 00A1;AI # INVERTED EXCLAMATION MARK  ¡
 342 # 0041;AL # LATIN CAPITAL LETTER A
 343 # 0009;BA # <control>
 344 # 00B4;BB # ACUTE ACCENT
 345 # 000C;BK # <control>
 346 # 2014;B2 # EM DASH
 347 # FFFC;CB # OBJECT REPLACEMENT CHARACTER
 348 # 0029;CL # RIGHT PARENTHESIS
 349 # 0301;CM # COMBINING ACUTE ACCENT
 350 # 0021;EX # EXCLAMATION MARK
 351 # 00A0;GL # NO-BREAK SPACE
 352 # 002D;HY # HYPHEN-MINUS
 353 # 4E00;ID # <CJK Ideograph, First>
 354 # 2024;IN # ONE DOT LEADER
 355 # 002C;IS # COMMA
 356 # 000A;LF # <control>
 357 # 0E5A;NS # THAI CHARACTER ANGKHANKHU
 358 # 0032;NU # DIGIT TWO
 359 # 0028;OP # LEFT PARENTHESIS
 360 # 0025;PO # PERCENT SIGN
 361 # 0024;PR # DOLLAR SIGN
 362 # 0022;QU # QUOTATION MARK
 363 # 0E01;SA # THAI CHARACTER KO KAI
 364 # DB7F;SG # Surrogate
 365 # 0020;SP # SPACE
 366 # 002F;SY # SOLIDUS /
 367 # F8FF;XX # Private Use
 368 # 200B;ZW # ZERO WIDTH SPACE
 369
 370
 371 # 2b  Always break at end of text
 372
 373 <data>•  •\u00A1•</data>
 374 <data>•  •\u0041•</data>
 375 <data>•  •\u0009•</data>
 376 <data>•  •\u00B4•</data>
 377 <data>•    \u000C<100></data>    # LB3C  × BK
 378 <data>•  •\u2014•</data>
 379 <data>•  •\uFFFC•</data>
 380 <data>•   \u0029•</data>    # LB 8   × CL
 381 # <data>• • \u0301•</data>    # LB 7a   Treat SP CM* as if it were ID  #TODO:  SP CM
 382 <data>•   \u0021•</data>    # LB 8   × EX
 383 #<data>•   \u00A0•</data>    # LB 11b   × GL   TODO:  fix.
 384 <data>•  •\u002D•</data>
 385 <data>•  •\u4E00•</data>
 386 <data>•  •\u2024•</data>
 387 <data>•   \u002C•</data>    # LB 8   × IS
 388 <data>•   \u000A<100></data>    # LB3C   × ( BK | CR | LF | NL )
 389 <data>•  •\u0E5A•</data>
 390 <data>•  •\u0032•</data>
 391 <data>•  •\u0028•</data>
 392 <data>•  •\u0025•</data>
 393 <data>•  •\u0024•</data>
 394 <data>•  •\u0022•</data>
 395 <data>•  •\u0E01•</data>
 396 <data>•  •\uDB7F•</data>
 397 <data>•   \u0020•</data>     # LB4 - don't break before space.
 398 <data>•   \u002F•</data>     # LB 8  × SY
 399 <data>•  •\uF8FF•</data>
 400 <data>•   \u200B•</data>     # LB4 - don't break before ZA
 401
 402
 403 # 3a  Always break after hard line breaks.
 404 # 3c  Never break before hard line breaks.
 405
 406 <data>•  •\u00A1\u2028<100>\u00A1•</data>
 407 <data>•  •\u0041\u2028<100>\u0041•</data>
 408 <data>•  •\u0009\u2028<100>\u0009•</data>
 409 <data>•  •\u00B4\u2028<100>\u00B4•</data>
 410 <data>•   \u000C<100>\u2028<100>\u000C<100></data>
 411 <data>•  •\u2014\u2028<100>\u2014•</data>
 412 <data>•  •\uFFFC\u2028<100>\uFFFC•</data>
 413 <data>•   \u0029\u2028<100>\u0029•</data>
 414 #<data>•   \u0301\u2028<100>\u0301•</data>    # TODO:  fix.
 415 <data>•   \u0021\u2028<100>\u0021•</data>
 416 #<data>•   \u00A0\u2028<100>\u00A0•</data>    # TODO:  fix
 417 <data>•  •\u002D\u2028<100>\u002D•</data>
 418 <data>•  •\u4E00\u2028<100>\u4E00•</data>
 419 <data>•  •\u2024\u2028<100>\u2024•</data>
 420 <data>•   \u002C\u2028<100>\u002C•</data>
 421 <data>•   \u000A<100>\u2028<100>\u000A<100></data>
 422 <data>•  •\u0E5A\u2028<100>\u0E5A•</data>
 423 <data>•  •\u0032\u2028<100>\u0032•</data>
 424 <data>•  •\u0028\u2028<100>\u0028•</data>
 425 <data>•  •\u0025\u2028<100>\u0025•</data>
 426 <data>•  •\u0024\u2028<100>\u0024•</data>
 427 <data>•  •\u0022\u2028<100>\u0022•</data>
 428 <data>•  •\u0E01\u2028<100>\u0E01•</data>
 429 <data>•  •\uDB7F\u2028<100>\uDB7F•</data>
 430 <data>•   \u0020\u2028<100>\u0020•</data>
 431 <data>•   \u002F\u2028<100>\u002F•</data>
 432 <data>•  •\uF8FF\u2028<100>\uF8FF•</data>
 433 <data>•   \u200B\u2028<100>\u200B•</data>
 434
 435
 436 #
 437 #  Old Line Break Test data.  Orginally located in RBBITest::TestDefaultRuleBasedLineIteration()
 438 #
 439
 440 <line>
 441
 442 <data>•Multi-•Level •example •of •a •semi-•idiotic •non-•sensical •(non-•important) •sentence.
 443 <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>
 444
 445 <line>
 446 <data>•Hello! •how\r\n<100> •(are)\r<100> •you? •I'am •fine- •Thankyou. •foo\u00a0bar
 447 <100>How, •are, •you? •This, •costs •$20,00,000.•</data>
 448
 449 #     test for bug #4068133
 450 #
 451 <data>•\u96f6•\u4e00\u3002•\u4e8c\u3001•\u4e09\u3002\u3001•\u56db\u3001\u3002\u3001•\u4e94,•\u516d.•\u4e03.\u3001,\u3002•\u516b•</data>
 452
 453 #     to test for bug #4086052
 454 <data>•foo\u00a0bar•</data>
 455
 456 #     to test for bug #4097920
 457 <data>•dog,cat,mouse •(one)•(two)\n<100></data>
 458
 459 #     to test for bug #4035266
 460 <data>•The •balance •is •$-23,456.78, •not •-•$32,456.78!\n<100></data>
 461
 462
 463 #      to test for bug #4098467
 464 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 465 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 466 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 467 #      Both sequences should be semantically identical and break the same way.
 468 #      precomposed syllables...  (I == Rich Gillam?)
 469 #
 470 <data>•\uc0c1•\ud56d •\ud55c•\uc778 •\uc5f0•\ud569 •\uc7a5•\ub85c•\uad50•\ud68c•</data>
 471
 472 #      conjoining jamo...
 473 #      TODO:  rules update needed
 474 #<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>
 475
 476 #      to test for bug #4117554: Fullwidth .!? should be treated as postJwrd
 477 <data>•\u4e01\uff0e•\u4e02\uff01•\u4e03\uff1f•</data>
 478
 479 #      Surrogate line break tests.
 480 #
 481 <data>•\u4e01•\ud840\udc01•\u4e02•abc •\ue000 •\udb80\udc01•</data>
 482
 483 #      Regression for bug 836
 484 <data>•AAA(AAA •</data>
 485
 486 #       Try some words from other scripts.
 487 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 488 #
 489 <data>•ΑΒΓ •БВГ •אבג֓ •ابت •١٢٣ •\u10A0\u10A1\u10A2 •ABC •</data>
 490
 491
 492 ########################################################################################
 493 #
 494 #
 495 #       T i t l e   B o u n d a r y      T e s t s
 496 #
 497 #
 498 ##########################################################################################
 499 <title>
 500 <data>•Here •is •a •short •sample •sentence.  •And •another.•</data>
 501 <data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE.  •AND •ANOTHER.•</data>
 502 <data>•  •Start •and •end •with •spaces   •</data>
 503 <data>•Include 123 456 ^&  •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data>
 504
 505 <data>•Combining\u0301 \u0301•ma\u0306rks  •bye  •</data>
 506 <data>•123  •Start •with •a •number.•</data>
 507
 508 <data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data>
 509
 510
 511 ##########################################################################################
 512 #
 513 #   Thai Tests
 514 #
 515 ##########################################################################################
 516 <locale th>
 517 <word>
 518 #
 519 # Test data originally from the test code source file
 520 #      // @suwit -- Thai sample data from GVT Guideline
 521 #
 522 <data>•\u0E2B\u0E19\u0E36\u0E48\u0E07<200>\u0E04\u0E33<200>\u0E44\u0E17\u0E22<200>\
 523 \u0E2A\u0E32\u0E21\u0E32\u0E23\u0E16<200>\u0E1B\u0E23\u0E30\u0E01\u0E2D\u0E1A<200>\
 524 \u0E14\u0E49\u0E27\u0E22<200>\u0e2b\u0e25\u0e32\u0e22<200>\
 525 \u0e1e\u0e22\u0e32\u0e07\u0e04\u0e4c<200></data>
 526
 527 #
 528 #  Jitterbug 3671 Test Case
 529 #
 530 <data>•สวัสดี<200>ครับ<200>สบาย<200>ดี<200>ไหม<200> •ครับ<200></data>
 531
 532 #
 533 #  Trac ticket 5595 Test Case
 534 <data>•บท<200>ที่๑พายุ<200>ไซโคลน<200>โด<200>โรธี<200>อาศัย<200>อยู่<200>ท่ามกลาง<200>\
 535 ทุ่งใหญ่<200>ใน<200>แคนซัส<200>กับ<200>ลุง<200>เฮ<200>นรี<200>ชาวไร่<200>และ<200>ป้า<200>เอ็ม<200>\
 536 ภรรยา<200>ชาวไร่<200>บ้าน<200>ของ<200>พวก<200>เขา<200>หลัง<200>เล็ก<200>เพราะ<200>ไม้<200>\
 537 สร้าง<200>บ้าน<200>ต้อง<200>ขน<200>มา<200>ด้วย<200>เกวียน<200>เป็น<200>ระยะ<200>ทาง<200>หลาย<200>\
 538 ไมล์<200></data>
 539
 540