icuSources/test/testdata/rbbitst.txt

   1 # Copyright (c) 2001-2003 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 #   <data> ... </data>   test data.  May span multiple lines.
  16 #      <>        Break position, status == 0
  17 #      •         Break position, status == 0   (Bullet, \u2022)
  18 #      <nnn>     Break position, status == nnn
  19 #      \         Escape.  Normal ICU unescape applied.
  20 #      \ at end of line  ->  Line Continuation.  Remove both the backslash and the new line
  21 #
  22 #
  23
  24
  25
  26 ########################################################################################
  27 #
  28 #
  29 #       G r a p h e m e    C l u s t e r     T e s t s
  30 #
  31 #
  32 ##########################################################################################
  33 <char>
  34
  35 <data>•a•b•c• •,•\u0666•</data>                 # Quick Test
  36 <data>•\r•\r•\r\n•\r\n•\n•\r•</data>            # don't break CR/LF
  37
  38 # Always break after controls.  Combining chars don't combine with them.
  39 <data>•\u0003•\N{COMBINING GRAVE ACCENT}•\r•\N{COMBINING GRAVE ACCENT}•</data>
  40 <data>•\u0085•\N{COMBINING MACRON}•A\N{COMBINING MACRON}•</data>
  41
  42 # Surrogates
  43 <data>•\U00011000•\U00010020•\U00010000\N{COMBINING MACRON}•</data>
  44 <data>•\ud800\udc00•\udbff\udfff•a•</data>
  45
  46 # Extend (Combining chars) combine.
  47 <data>•A\N{COMBINING GRAVE ACCENT}•B•</data>
  48 <data>•\N{GREEK SMALL LETTER MU}\N{COMBINING LOW LINE}\N{COMBINING HORN}•</data>
  49 <data>•a\u0301•b\u0302•c\u0303•d\u0304•e\u0305•f\u0306•g\u0307•h\u0308•i\u0309•</data>
  50
  51 <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>
  52
  53 # Don't break Hangul Syllables
  54 #   L : \u1100
  55 #   V : \u1161
  56 #   T : \u11A8
  57 #  LV : \uAC00
  58 # LVT : \uAC01
  59
  60 <data>•\u1100\u1161\u11a8•\u1100\u1161\u11a8•</data>  #LVT
  61 <data>•\u1100\u1161•\u1100\u1161•</data>
  62 <data>•\u1100\u1161\u11a8•\u1161•\u1100•\u11a8•\u1161\u1161\u1161\u11a8•</data>
  63 <data>•\u1100\u1100\uac01•\u1100\uac01•\u1100\uac01\u0301•\uac01•</data>
  64 <data>•\u1100\u0301•\u1161\u11a8\u0301•\u11a8•</data>
  65
  66
  67
  68 # Hindi combining chars.  (An old test)
  69 <data>•भ••ा•\u0930•\u0924• •\u0938\u0941\u0902•\u0926•\u0930•
  70 •\u0939•\u094c•\u0964•</data>
  71 <data>•\u0916\u0947•\u0938\u0941\u0902•\u0926•\u0930•\u0939•\u094c•\u0964•</data>
  72
  73
  74 #  Bug 1587.  Tamil.  \u0baa\u0bc1 should be two separate characters, even though
  75 #                     Hyangmi would perfer that it be one.
  76 <data>•\u0baa•\u0bc1•\u0baa•\u0bc1•</data>
  77
  78 #   Regression test for bug 1889
  79 <data>•\u0f40\u0f7d•\u0000•\u0f7e•</data>
  80
  81
  82 #     0xffff is a legal character, and should not stop the break iterator early.
  83 #     (Requires special casing in implementation, which is why it gets a test.)
  84 <data>•\uffff•\uffff• •a•</data>
  85
  86
  87 ########################################################################################
  88 #
  89 #
  90 #       W o r d    B o u n d a r y      T e s t s
  91 #
  92 #
  93 ##########################################################################################
  94
  95 <word>
  96 #
  97 # Quick sanity test
  98 #
  99 <data>•hello<200> •there<200> •goodbye<200></data>
 100 <data>•hello<200> •12345<100> •,•</data>
 101
 102
 103 #
 104 # Test data originally in RBBIAPITest::TestFirstNextFollowing() and TestLastPreviousPreceding()
 105 #
 106
 107 <word>
 108 <data>•This<200> •is<200> •a<200> •word<200> •break<200>.• • •Isn't<200> •it<200>?• •2.25<100></data>
 109
 110
 111
 112 #
 113 # Data originally from TestDefaultRuleBasedWordIteration()
 114 #
 115 <data>•Write<200> •wordrules<200>.• •123.456<100> •alpha\u00adbeta\u00adgamma<200> •\u092f\u0939<200> •</data>
 116 <data>• •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200> •\u0938\u093f\u0916\u094b\u0917\u0947<200>?•</data>
 117
 118 #Hindi Numbers
 119 <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>
 120
 121 <data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢•£•¤•¥•alpha\u05f3beta\u05f4gamma<200> •</data>
 122
 123 <data>•Badges<200>?• •BADGES<200>!•?•!• •We<200> •don't<200> •need<200> •no<200> •STINKING<200> •BADGES<200>!•!•1000,233,456.000<100> •1,23.322<100>%•123.1222<100>$•123,000.20<100> •179.01<100>%•X<200> •Now<200>\r•is<200>\n•the<200>\r\n•time<200> •</data>
 124
 125 #Hangul
 126 <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>
 127
 128
 129 # Words containing non-BMP letters
 130 <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>
 131
 132 # Unassigned code points
 133 <data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data>
 134
 135 # Hiragana & Katakana stay together, but separates from each other and Latin.
 136 <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>
 137
 138 # Words with interior formatting characters
 139 <data>•def\N{COMBINING ACUTE ACCENT}\N{SYRIAC ABBREVIATION MARK}ghi<200> •</data>
 140
 141 # to test for bug #4097779
 142 <data>•aa\N{COMBINING GRAVE ACCENT}a<200> •</data>
 143
 144
 145 #      to test for bug #4098467
 146 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 147 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 148 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 149 #      Both sequences should be semantically identical and break the same way.
 150 #      precomposed syllables...
 151 <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>
 152
 153 <data>•abc<200>\u4e01<400>\u4e02<400>\u3005<200>\u4e03<400>\u4e03<400>abc<200> •</data>
 154
 155 <data>•\u06c9\uc799<200>\ufffa•</data>
 156
 157 #
 158 #      Try some words from other scripts.
 159 #
 160
 161 #       Try some words from other scripts.
 162 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 163 #
 164 <data>•ΑΒΓ<200> •БВГ<200> •אבג֓<200> •ابت<200> •١٢٣<100> •\u10A0\u10A1\u10A2<200> •ABC<200> •</data>
 165
 166 <data>•\u0301•A<200></data>
 167
 168
 169 #
 170 #  Hindi word break tests, imported from the old RBBI tests.
 171 #    An historical note:  a much earlier version of ICU break iterators had a number
 172 #    of special case rules for Hindi, which were tested by an earlier version of
 173 #    this test data.  The current RBBI rules do not special case Hindi in
 174 #    any way, making this test data much less signfificant.
 175 #
 176 <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>
 177 •\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>
 178
 179 ########################################################################################
 180 #
 181 #
 182 #       S e n t e n c e     B o u n d a r y      T e s t s
 183 #
 184 #
 185 ##########################################################################################
 186
 187
 188 #
 189 # Test data originally from RBBI RBBITest::TestDefaultRuleBasedSentenceIteration()
 190 #
 191 <sent>
 192
 193
 194 <sent>
 195 <data>•This\n•</data>
 196 <data>•Hello! •how are you? •I'am fine. •Thankyou. •How are you \
 197 doing? •This\n• costs $20,00,000. •</data>
 198
 199
 200 # Sentence ending in a quote.
 201 <data>•"Sentence ending with a quote." •Bye.•</data>
 202
 203 # Sentence, and test data, ending without a period or other terminator.
 204 <data>•Here is a random sentence, no ending period•</data>
 205
 206
 207 <data>•  (This is it).  •Testing the sentence iterator. •\
 208 "This isn't it." •Hi! \
 209 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
 210 "This isn't it." •\
 211 Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!•! •Don't rock the boat.\u2029•Because I am the daddy, that is why.
 212 •Not on my time (el timo.)•! •</data>
 213
 214 <data>•Hello.  •So what!•!\u2029•"But now," he said, \
 215 "I know!" •\
 216 Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!)•. •One species, B. anthracis, is highly virulent.
 217 •Wolf said about Sounder:\
 218 "Beautifully thought-out and directed." •\
 219 Have you ever said, "This is where\tI shall live"? •He answered, \
 220 "You may not!" •Another popular saying is: "How do you do?"•. \n•\
 221 Yet another popular saying is: \
 222 'I'm fine thanks.' •\
 223 What is the proper use of the abbreviation pp.•? •Yes, I am definatelly 12" tall!•!\
 224 •Now\r•is\n•the\r\n•time\n•\r•for\r•\r•</data>
 225
 226 <data>•No breaks when . is surrounded by UPPER.Case letters.  •</data>
 227 <data>•No breaks when . is followed by Numeric .4 a.4 C.4 3.1 .•</data>
 228 <data>•No breaks when . is followed by a lower, with possible intervening punct .,a .$a .)a. •</data>
 229
 230 #
 231 #  Sentence Breaks: no break at the boundary between CJK and other letters
 232 #
 233 <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>
 234
 235 #
 236 #      Treat fullwidth variants of .!? the same as their
 237 #      normal counterparts
 238 #
 239 <data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data>"
 240
 241
 242 #
 243 #       Don't break sentences at boundary between CJK and digits
 244 #
 245 <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•</data>"
 246
 247 #
 248 #      Breaks around '(' following a sentence TERM.  (Rule 9)
 249 #
 250 <data>•How do you do?(•Fine). •</data>
 251 <data>•How do you do? •(Fine). •</data>
 252 <data>•How do you do?(•fine). •</data>
 253 <data>•How do you do? •(fine). •</data>
 254
 255 #
 256 <data>•Hello.123•</data>    # Rule 6
 257 <data>•Hello?•123•</data>
 258
 259 <data>•HELLO.Bye•</data>    # Rule 7
 260 <data>•HELLO?•Bye•</data>
 261
 262 <data>•Hello.goodbye•</data>  #Rule 8
 263 <data>•Hello. •Goodbye•</data>
 264 <data>•Hello. goodbye•</data>
 265 <data>•Hello.)@#$%^&*()""   goodbye•</data>
 266
 267
 268
 269 #
 270 #        test for bug #4158381: No breaks when there are no terminators around
 271 #
 272 <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>
 273 <data>•Another test.\u2029•</data>
 274
 275 #        test for bug #4143071: Make sure sentences that end with digits
 276 #        work right
 277 #
 278 <data>•Today is the 27th of May, 1998.  •</data>
 279 <data>•Tomorrow with be 28 May 1998.  •</data>
 280 <data>•The day after will be the 30th.\u2029•</data>
 281
 282 #        test for bug #4152416: Make sure sentences ending with a capital
 283 #        letter are treated correctly
 284 #
 285 <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>
 286
 287 #        test for bug #4152117: Make sure sentence breaking is handling
 288 #        punctuation correctly [COULD NOT REPRODUCE THIS BUG, BUT TEST IS
 289 #        HERE TO MAKE SURE IT DOESN'T CROP UP]
 290 #
 291 <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.
 292 •</data>
 293
 294 #        sentence breaks for hindi which used Devanagari script
 295 #        make sure there is sentence break after ?,danda(hindi phrase separator),
 296 #        fullstop followed by space.  (VERY old test)
 297 #
 298 <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•\
 299 \u0915\u0948\u0938\u0947 \u0939\u0948?•\u0935\u0939 \u0915\u094d\u200d\u092f\u093e\n\
 300 •\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>
 301
 302 #         Regression test for bug #1984, Sentence break in Arabic text.
 303
 304 <data>\
 305 •\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>"
 306
 307 #         Try a few more of the less common sentence endings.
 308 <data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end here. •</data>
 309
 310
 311
 312
 313 ################################################################
 314 #
 315 #
 316 #        L I N E     B R E A K
 317 #
 318 #
 319 ################################################################
 320
 321 <line>
 322 #
 323 # Test Character for each of the line break classes.
 324 #
 325 # 00A1;AI # INVERTED EXCLAMATION MARK  ¡
 326 # 0041;AL # LATIN CAPITAL LETTER A
 327 # 0009;BA # <control>
 328 # 00B4;BB # ACUTE ACCENT
 329 # 000C;BK # <control>
 330 # 2014;B2 # EM DASH
 331 # FFFC;CB # OBJECT REPLACEMENT CHARACTER
 332 # 0029;CL # RIGHT PARENTHESIS
 333 # 0301;CM # COMBINING ACUTE ACCENT
 334 # 0021;EX # EXCLAMATION MARK
 335 # 00A0;GL # NO-BREAK SPACE
 336 # 002D;HY # HYPHEN-MINUS
 337 # 4E00;ID # <CJK Ideograph, First>
 338 # 2024;IN # ONE DOT LEADER
 339 # 002C;IS # COMMA
 340 # 000A;LF # <control>
 341 # 0E5A;NS # THAI CHARACTER ANGKHANKHU
 342 # 0032;NU # DIGIT TWO
 343 # 0028;OP # LEFT PARENTHESIS
 344 # 0025;PO # PERCENT SIGN
 345 # 0024;PR # DOLLAR SIGN
 346 # 0022;QU # QUOTATION MARK
 347 # 0E01;SA # THAI CHARACTER KO KAI
 348 # DB7F;SG # Surrogate
 349 # 0020;SP # SPACE
 350 # 002F;SY # SOLIDUS /
 351 # F8FF;XX # Private Use
 352 # 200B;ZW # ZERO WIDTH SPACE
 353
 354
 355 # 2b  Always break at end of text
 356
 357 <data>•  •\u00A1•</data>
 358 <data>•  •\u0041•</data>
 359 <data>•  •\u0009•</data>
 360 <data>•  •\u00B4•</data>
 361 <data>•    \u000C•</data>    # LB3C  × BK
 362 <data>•  •\u2014•</data>
 363 <data>•  •\uFFFC•</data>
 364 <data>•   \u0029•</data>    # LB 8   × CL
 365 # <data>• • \u0301•</data>    # LB 7a   Treat SP CM* as if it were ID  #TODO:  SP CM
 366 <data>•   \u0021•</data>    # LB 8   × EX
 367 #<data>•   \u00A0•</data>    # LB 11b   × GL   TODO:  fix.
 368 <data>•  •\u002D•</data>
 369 <data>•  •\u4E00•</data>
 370 <data>•  •\u2024•</data>
 371 <data>•   \u002C•</data>    # LB 8   × IS
 372 <data>•   \u000A•</data>    # LB3C   × ( BK | CR | LF | NL )
 373 <data>•  •\u0E5A•</data>
 374 <data>•  •\u0032•</data>
 375 <data>•  •\u0028•</data>
 376 <data>•  •\u0025•</data>
 377 <data>•  •\u0024•</data>
 378 <data>•  •\u0022•</data>
 379 <data>•  •\u0E01•</data>
 380 <data>•  •\uDB7F•</data>
 381 <data>•   \u0020•</data>     # LB4 - don't break before space.
 382 <data>•   \u002F•</data>     # LB 8  × SY
 383 <data>•  •\uF8FF•</data>
 384 <data>•   \u200B•</data>     # LB4 - don't break before ZA
 385
 386
 387 # 3a  Always break after hard line breaks.
 388 # 3c  Never break before hard line breaks.
 389
 390 <data>•  •\u00A1\u2028•\u00A1•</data>
 391 <data>•  •\u0041\u2028•\u0041•</data>
 392 <data>•  •\u0009\u2028•\u0009•</data>
 393 <data>•  •\u00B4\u2028•\u00B4•</data>
 394 <data>•   \u000C•\u2028•\u000C•</data>
 395 <data>•  •\u2014\u2028•\u2014•</data>
 396 <data>•  •\uFFFC\u2028•\uFFFC•</data>
 397 <data>•   \u0029\u2028•\u0029•</data>
 398 #<data>•   \u0301\u2028•\u0301•</data>    # TODO:  fix.
 399 <data>•   \u0021\u2028•\u0021•</data>
 400 #<data>•   \u00A0\u2028•\u00A0•</data>    # TODO:  fix
 401 <data>•  •\u002D\u2028•\u002D•</data>
 402 <data>•  •\u4E00\u2028•\u4E00•</data>
 403 <data>•  •\u2024\u2028•\u2024•</data>
 404 <data>•   \u002C\u2028•\u002C•</data>
 405 <data>•   \u000A•\u2028•\u000A•</data>
 406 <data>•  •\u0E5A\u2028•\u0E5A•</data>
 407 <data>•  •\u0032\u2028•\u0032•</data>
 408 <data>•  •\u0028\u2028•\u0028•</data>
 409 <data>•  •\u0025\u2028•\u0025•</data>
 410 <data>•  •\u0024\u2028•\u0024•</data>
 411 <data>•  •\u0022\u2028•\u0022•</data>
 412 <data>•  •\u0E01\u2028•\u0E01•</data>
 413 <data>•  •\uDB7F\u2028•\uDB7F•</data>
 414 <data>•   \u0020\u2028•\u0020•</data>
 415 <data>•   \u002F\u2028•\u002F•</data>
 416 <data>•  •\uF8FF\u2028•\uF8FF•</data>
 417 <data>•   \u200B\u2028•\u200B•</data>
 418
 419
 420 #
 421 #  Old Line Break Test data.  Orginally located in RBBITest::TestDefaultRuleBasedLineIteration()
 422 #
 423
 424 <line>
 425
 426 <data>•Multi-•Level •example •of •a •semi-•idiotic •non-•sensical •(non-•important) •sentence.
 427 •Hi  •Hello •How\n•are\r•you\u2028•fine.\t•good.  •Now\r•is\n•the\r\n•time\n•\r•for\r•\r•all•</data>
 428
 429 <line>
 430 <data>•Hello! •how\r\n• •(are)\r• •you? •I'am •fine- •Thankyou. •foo\u00a0bar
 431 •How, •are, •you? •This, •costs •$20,00,000.•</data>
 432
 433 #     test for bug #4068133
 434 #
 435 <data>•\u96f6•\u4e00\u3002•\u4e8c\u3001•\u4e09\u3002\u3001•\u56db\u3001\u3002\u3001•\u4e94,•\u516d.•\u4e03.\u3001,\u3002•\u516b•</data>
 436
 437 #     to test for bug #4086052
 438 <data>•foo\u00a0bar•</data>
 439
 440 #     to test for bug #4097920
 441 <data>•dog,•cat,•mouse •(one)•(two)\n•</data>
 442
 443 #     to test for bug #4035266
 444 <data>•The •balance •is •$-23,456.78, •not •-•$32,456.78!\n•</data>
 445
 446
 447 #      to test for bug #4098467
 448 #      What follows is a string of Korean characters (I found it in the Yellow Pages
 449 #      ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed
 450 #      it correctly), first as precomposed syllables, and then as conjoining jamo.
 451 #      Both sequences should be semantically identical and break the same way.
 452 #      precomposed syllables...  (I == Rich Gillam?)
 453 #
 454 <data>•\uc0c1•\ud56d •\ud55c•\uc778 •\uc5f0•\ud569 •\uc7a5•\ub85c•\uad50•\ud68c•</data>
 455
 456 #      conjoining jamo...
 457 #      TODO:  rules update needed
 458 #<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>
 459
 460 #      to test for bug #4117554: Fullwidth .!? should be treated as postJwrd
 461 <data>•\u4e01\uff0e•\u4e02\uff01•\u4e03\uff1f•</data>
 462
 463 #      Surrogate line break tests.
 464 #
 465 <data>•\u4e01•\ud840\udc01•\u4e02•abc•\ue000•\udb80\udc01•</data>
 466
 467 #      Regression for bug 836
 468 <data>•AAA•(AAA •</data>
 469
 470 #       Try some words from other scripts.
 471 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
 472 #
 473 <data>•ΑΒΓ •БВГ •אבג֓ •ابت •١٢٣ •\u10A0\u10A1\u10A2 •ABC •</data>
 474
 475
 476 ########################################################################################
 477 #
 478 #
 479 #       T i t l e   B o u n d a r y      T e s t s
 480 #
 481 #
 482 ##########################################################################################
 483 <title>
 484 <data>•Here •is •a •short •sample •sentence.  •And •another.•</data>
 485 <data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE.  •AND •ANOTHER.•</data>
 486 <data>•  •Start •and •end •with •spaces   •</data>
 487 <data>•Include 123 456 ^&  •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data>
 488
 489 <data>•Combining\u0301 \u0301•ma\u0306rks  •bye  •</data>
 490 <data>•123  •Start •with •a •number.•</data>
 491
 492 <data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data>
 493