Lines Matching full:data
4 # RBBI Test Data
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
16 # <data> ... </data> test data. May span multiple lines.
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
37 <data>•\u00c0.•</data>
39 …data>•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165:"JAVA\u821c\u8165\u7fc8\u51ce\u306d,\u2494\…
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
53 <data>•\u0003•\N{COMBINING GRAVE ACCENT}•\r•\N{COMBINING GRAVE ACCENT}•</data>
54 <data>•\u0085•\N{COMBINING MACRON}•A\N{COMBINING MACRON}•</data>
57 <data>•\U00011000•\U00010020•\U00010000\N{COMBINING MACRON}•</data>
58 <data>•\ud800\udc00•\udbff\udfff•a•</data>
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>
65 …data>•a\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\u0304\u0301\u0302\u0303\…
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>
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>
90 <data>•\u0baa\u0bc1•\u0baa\u0bc1•</data>
93 <data>•\u0f40\u0f7d•\u0000•\u0f7e•</data>
98 <data>•\uffff•\uffff• •a•</data>
101 <data>•A\uff9e•B\uff9f\uff9e\uff9f•C•</data>
113 #<data>•a•b•c•</data>
114 #<data>•a\u0301\u0302• •b\u0303\u0304•</data>
117 #<data>•\u0904\u0903• •\u0937\u093E• •\u0904\u093F• •\u0937\u0940• •\u0937\u0949• •\u0937\u094A• •\…
122 #<data>•\u0e40\u0e01•\u0e44\u0301\u0e23\u0302\u0303•\u0e40•\u0e40\u0e02•\u0e02• •</data>
137 <data>•hello<200> •there<200> •goodbye<200></data>
138 <data>•hello<200> •12345<100> •,•</data>
142 # Test data originally in RBBIAPITest::TestFirstNextFollowing() and TestLastPreviousPreceding()
146 <data>•This<200> •is<200> •a<200> •word<200> •break<200>.• • •Isn't<200> •it<200>?• •2.25<100></dat…
151 # Data originally from TestDefaultRuleBasedWordIteration()
153 <data>•Write<200> •wordrules<200>.• •123.456<100> •alpha\u00adbeta\u00adgamma<200> •\u092f\u0939<20…
154 <data>• •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200…
157 …data>• •\u0968\u0966.\u0969\u096f<100> •\u0967\u0966\u0966.\u0966\u0966<100> •\N{RUPEE SIGN}•\u096…
159 <data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢…
161 …data>•Badges<200>?• •BADGES<200>!•?•!• •We<200> •don't<200> •need<200> •no<200> •STINKING<200> •BA…
164 …data>•\uc5f0\ud569<200> •\uc7a5\ub85c\uad50\ud68c<200> •\u1109\u1161\u11bc\u1112\u1161\u11bc<200> …
166 …data>•Hello<200>,• •how<200> •are<200> •you<200> •\uc5f0\ud569<200> •\uc7a5\ub85c\uad50\ud68c<200>…
169 …data>•abc\U00010300<200> •abc\N{DESERET SMALL LETTER ENG}<200> •abc\N{MATHEMATICAL BOLD SMALL Z}<2…
172 <data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data>
176 …data>•abc<200>\N{HIRAGANA LETTER SMALL A}<400>\N{HIRAGANA LETTER VU}\N{COMBINING ACUTE ACCENT}<400…
179 <data>•芽キャベツ<400>芽キャﾍﾞツ<400></data>
184 #<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>…
185 <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<…
188 <data>•中だるみ<400>蔵王の森<400>ウ離島<400></data>
191 …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<4…
194 <data>•def\N{COMBINING ACUTE ACCENT}\N{SYRIAC ABBREVIATION MARK}ghi<200> •</data>
197 <data>•aa\N{COMBINING GRAVE ACCENT}a<200> •</data>
200 # <data>•ＩＳＮ'Ｔ<200> •１９<100>日<400></data>
209 …data>•\uc0c1\ud56d<200> •\ud55c\uc778<200> •\uc5f0\ud569<200> •\uc7a5\ub85c\uad50\ud68c<200> •\u11…
213 #<data>•\ud55c\uad6d<200>\ub300\ud559\uad50<200>\uc790\uc5f0<200>\uacfc\ud559<200>\ub300\ud559<200>…
214 …data>•\ud604\uc7ac<200>\ub294<200> •\uac80\ucc30<200>\uc774<200> •\ubd84\uc2dd<200>\ud68c\uacc4<20…
216 <data>•abc<200>\u4e01<400>\u4e02<400>\u3005<400>\u4e03\u4e03<400>abc<200> •</data>
218 <data>•\u06c9<200>\uc799\ufffa•</data>
228 <data>•ΑΒΓ<200> •БВГ<200> •אבג֓<200> •ابت<200> •١٢٣<100> •\u10A0\u10A1\u10A2<200> •ABC<200> •</data>
230 <data>•\u0301•A<200></data>
237 # this test data. The current RBBI rules do not special case Hindi in
238 # any way, making this test data much less signfificant.
240 <data>•\u0917\u092a\u00ad\u0936\u092a<200>!•\u092f\u0939<200> •\u0939\u093f\u0928\u094d\u200d\u0926…
241 …0> •\u0905\u092e\u091c<200>\n•\u0938\u094d\u200d\u0935\u0924\u0902\u0924\u094d\u0930<200>\r•</data>
246 <data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data>
251 <data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data>
254 <data>•Parlez<200>-•vous<200> •français<200> •?•</data>
266 # Test data originally from RBBI RBBITest::TestDefaultRuleBasedSentenceIteration()
272 <data>•This\n<100></data>
273 <data>•Hello! •how are you? •I'am fine. •Thankyou. •How are you \
274 doing? •This\n<100> costs $20,00,000. •</data>
278 <data>•"Sentence ending with a quote." •Bye.•</data>
280 # Sentence, and test data, ending without a period or other terminator.
281 <data>•Here is a random sentence, no ending period<100></data>
284 <data>• (This is it). •Testing the sentence iterator. •\
289 •Not on my time (el timo.)! •</data>
291 <data>•Hello. •So what!!\u2029•"But now," he said, \
301 •Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100></data>
303 <data>•No breaks when . is surrounded by UPPER.Case letters. •</data>
304 <data>•No breaks when . is followed by Numeric .4 a.4 C.4 3.1 .•</data>
305 <data>•No breaks when . is followed by a lower, with possible intervening punct .,a .$a .)a. •</dat…
310 …data>•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165:"JAVA\u821c\u8165\u7fc8\u51ce\u306d,\u2494\…
316 <data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data>
322 …data>•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165\u9de8\u97e48888\u821c\u8165\u7fc8\u51ce\u30…
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 <data>•How do you do? •(fine). •</data>
333 <data>•Hello.123<100></data> # Rule 6
334 <data>•Hello?•123<100></data>
336 <data>•HELLO.Bye<100></data> # Rule 7
337 <data>•HELLO?•Bye<100></data>
339 <data>•Hello.goodbye<100></data> #Rule 8
340 <data>•Hello. •Goodbye<100></data>
341 <data>•Hello. goodbye<100></data>
348 …data>•\<P>Provides a set of "lightweight" (all-java\<FONT SIZE="-2">\<SUP>TM\</SUP>\</FO…
349 <data>•Another test.\u2029•</data>
354 <data>•Today is the 27th of May, 1998. •</data>
355 <data>•Tomorrow with be 28 May 1998. •</data>
356 <data>•The day after will be the 30th.\u2029•</data>
361 …data>•The type of all primitive \<code>boolean\</code> values accessed in the target VM. •Calls t…
367 <data>•Constructs a randomly generated BigInteger, uniformly distributed over the range \<tt>0\</tt…
368 •</data>
374 <data>•\u0928\u092e\u0938\u094d\u200d\u0924\u0947 \u0930\u092e\u0947\u0936\u0905\u093e\u092a\u0915\…
376 …0902\u0924\u094d\u0930 \u0926\u093f\u0935\u093e\u0938) \u0939\u0948\u0964 •Let's end here. •</data>
380 <data>\
381 …0644\u0645\u062d\u0627\u0631\u0641\u0020\u0627\u0644\u0636\u0631\u0648\u0631\u064a\u0629. •</data>
384 <data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end he…
433 <data>• •\u00A1•</data>
434 <data>• •\u0041•</data>
435 <data>• •\u0009•</data>
436 <data>• •\u00B4•</data>
437 <data>• \u000C<100></data> # LB3C × BK
438 <data>• •\u2014•</data>
439 <data>• •\uFFFC•</data>
440 <data>• \u0029•</data> # LB 8 × CL
441 # <data>• • \u0301•</data> # LB 7a Treat SP CM* as if it were ID #TODO: SP CM
442 <data>• \u0021•</data> # LB 8 × EX
443 #<data>• \u00A0•</data> # LB 11b × GL TODO: fix.
444 <data>• •\u002D•</data>
445 <data>• •\u4E00•</data>
446 <data>• •\u2024•</data>
447 <data>• \u002C•</data> # LB 8 × IS
448 <data>• \u000A<100></data> # LB3C × ( BK | CR | LF | NL )
449 <data>• •\u0E5A•</data>
450 <data>• •\u0032•</data>
451 <data>• •\u0028•</data>
452 <data>• •\u0025•</data>
453 <data>• •\u0024•</data>
454 <data>• •\u0022•</data>
455 <data>• •\u0E01•</data>
456 <data>• •\uDB7F•</data>
457 <data>• \u0020•</data> # LB4 - don't break before space.
458 <data>• \u002F•</data> # LB 8 × SY
459 <data>• •\uF8FF•</data>
460 <data>• \u200B•</data> # LB4 - don't break before ZA
466 <data>• •\u00A1\u2028<100>\u00A1•</data>
467 <data>• •\u0041\u2028<100>\u0041•</data>
468 <data>• •\u0009\u2028<100>\u0009•</data>
469 <data>• •\u00B4\u2028<100>\u00B4•</data>
470 <data>• \u000C<100>\u2028<100>\u000C<100></data>
471 <data>• •\u2014\u2028<100>\u2014•</data>
472 <data>• •\uFFFC\u2028<100>\uFFFC•</data>
473 <data>• \u0029\u2028<100>\u0029•</data>
474 #<data>• \u0301\u2028<100>\u0301•</data> # TODO: fix.
475 <data>• \u0021\u2028<100>\u0021•</data>
476 #<data>• \u00A0\u2028<100>\u00A0•</data> # TODO: fix
477 <data>• •\u002D\u2028<100>\u002D•</data>
478 <data>• •\u4E00\u2028<100>\u4E00•</data>
479 <data>• •\u2024\u2028<100>\u2024•</data>
480 <data>• \u002C\u2028<100>\u002C•</data>
481 <data>• \u000A<100>\u2028<100>\u000A<100></data>
482 <data>• •\u0E5A\u2028<100>\u0E5A•</data>
483 <data>• •\u0032\u2028<100>\u0032•</data>
484 <data>• •\u0028\u2028<100>\u0028•</data>
485 <data>• •\u0025\u2028<100>\u0025•</data>
486 <data>• •\u0024\u2028<100>\u0024•</data>
487 <data>• •\u0022\u2028<100>\u0022•</data>
488 <data>• •\u0E01\u2028<100>\u0E01•</data>
489 <data>• •\uDB7F\u2028<100>\uDB7F•</data>
490 <data>• \u0020\u2028<100>\u0020•</data>
491 <data>• \u002F\u2028<100>\u002F•</data>
492 <data>• •\uF8FF\u2028<100>\uF8FF•</data>
493 <data>• \u200B\u2028<100>\u200B•</data>
497 <data>•Parlez-•vous •français ?•</data>
500 # Old Line Break Test data. Orginally located in RBBITest::TestDefaultRuleBasedLineIteration()
505 <data>•Multi-•Level •example •of •a •semi-•idiotic •non-•sensical •(non-•important) •sentence.
506 …8<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>
509 <data>•Hello! •how\r\n<100> •(are)\r<100> •you? •I'am •fine- •Thankyou. •foo\u00a0bar
510 <100>How, •are, •you? •This, •costs •$20,00,000.•</data>
514 <data>•\u96f6•\u4e00\u3002•\u4e8c\u3001•\u4e09\u3002\u3001•\u56db\u3001\u3002\u3001•\u4e94,•\u516d.…
517 <data>•foo\u00a0bar•</data>
520 <data>•dog,cat,mouse •(one)•(two)\n<100></data>
523 <data>•The •balance •is •$-23,456.78, •not •-•$32,456.78!\n<100></data>
533 <data>•\uc0c1•\ud56d •\ud55c•\uc778 •\uc5f0•\ud569 •\uc7a5•\ub85c•\uad50•\ud68c•</data>
536 …data>•\u1109\u1161\u11bc•\u1112\u1161\u11bc •\u1112\u1161\u11ab•\u110b\u1175\u11ab •\u110b\u1167\u…
539 <data>•\u4e01\uff0e•\u4e02\uff01•\u4e03\uff1f•</data>
543 <data>•\u4e01•\ud840\udc01•\u4e02•abc •\ue000 •\udb80\udc01•</data> #This line and the following a…
544 <data>•\u4e01•\U00020001•\u4e02•abc •\ue000 •\U000f0001•</data>
549 <data>•AAA(AAA •</data>
554 <data>•ΑΒΓ •БВГ •אבג֓ •ابت •١٢٣ •\u10A0\u10A1\u10A2 •ABC •</data>
559 <data>•abc\ud801xyz•</data>
566 <data>•\ufffc•\u30e3\u000c<100>\u1b39\u300a\u002f\u203a\u200b•\ufffc•\uaf64•\udcfb•</data>
567 <data>•\u114d\u31f3•\ube44\u002d•\u0362\u24e2\u276e\u2014\u205f\ufe16•\uc877•\u0fd0\u000a<100>\u20a…
568 <data>•\u080a\u215b\U0001d7d3\u002c•\u2025\U000e012e•\u02df\u118d\u0029\ua8d6\u0085<100>\u6cc4\u202…
572 <data>•abc/•s •def•</data>
573 <data>•abc/\u05D9 •def•</data>
574 <data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data>
575 <data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05E…
587 <data>•Here •is •a •short •sample •sentence. •And •another.•</data>
588 <data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE. •AND •ANOTHER.•</data>
589 <data>• •Start •and •end •with •spaces •</data>
590 <data>•Include 123 456 ^& •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data>
592 <data>•Combining\u0301 \u0301•ma\u0306rks •bye •</data>
593 <data>•123 •Start •with •a •number.•</data>
595 <data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data>
596 <data>•' '' •start •with •case-•ignorable & •case-•insensitive •cha'r'a'cter•</data>
597 <data>• ''•aaa' •bbb '•ccc' '•ddd''' '''•eee '''•fff''' •ggg ''•</data>
608 # Test data originally from the test code source file
609 # // @suwit -- Thai sample data from GVT Guideline
611 <data>•\u0E2B\u0E19\u0E36\u0E48\u0E07<200>\u0E04\u0E33<200>\u0E44\u0E17\u0E22<200>\
614 \u0e1e\u0e22\u0e32\u0e07\u0e04\u0e4c<200></data>
616 # Test data originally from http://bugs.icu-project.org/trac/search?q=r30327
617 <data>•กู<200> •กิน<200>กุ้ง<200> •ปิ้่<200>งอ<200>ยู่<200>ใน<200>ถ้ำ<200></data>
619 <data>•\u0E01\u0E39<200>\u0020•\u0E01\u0E34\u0E19<200>\u0E01\u0E38\u0E49\u0E07<200>\
621 \u0E43\u0E19<200>\u0E16\u0E49\u0E33<200></data>
624 <data>•0E01\u0E39\u0020•\u0E01\u0E34\u0E19•\u0E01\u0E38\u0E49\u0E07\
626 \u0E43\u0E19•\u0E16\u0E49\u0E33•</data>
628 # Data originally from intltest RBBITest::TestThaiLineBreak()
639 <data>•\u0e2a\u0e16\u0e32\u0e19\u0e35\u0e2f•\
652 \u0e19\u0e31\u0e49\u0e19•</data>
654 # Data originally from RBBITest::TestMixedThaiLineBreak()
658 <data>•\u0E1B\u0E35•\
673 Bangkok)•</data>
675 # Data originally from RBBITest::TestMaiyamok()
681 <data>•\u0e44\u0e1b\u0e46•\
689 \u0e43\u0e2b\u0e21\u0e48•</data>
693 <data>•ใช•มั้ย•</data>
694 <data>•มั๊ยล่ะ•ที่รัก•</data>
698 <data>•เล่น•ผ่าน•ทาง•บลูทูธ•บน•อุปกรณ์•</data>
702 <data>•ไป•ที่•ซานฟรานซิสโก•</data>
706 <data>•แท็ก•แอปพลิเคชัน•เป็น•พิเศษ•</data>
710 <data>•เบ•เบราว์เซอร์•โพ•โพสต์•โพสท์•</data>
720 <data>•ສະບາຍດີ•</data>
721 <data>•ດີ•ຂອບໃຈ•</data>
722 <data>•ເຈົ້າ•ເວົ້າ•ພາສາ•ອັງກິດ•ໄດ້•ບໍ່•</data>
723 <data>•ກະລຸນາ•ເວົ້າ•ຊ້າ•ໆ•</data>
733 <data>•လူ•တိုင်း•သည် •တူညီ •လွတ်လပ်•သော •ဂုဏ်•သိ•က္•ခါ•ဖြ•င့် •လည်းကောင်း၊ •</data>
734 <data>•တူညီ•လွတ်လပ်•သော •အ•ခွ•င့်•အရေး•များ•ဖြ•င့် •လည်းကောင်း၊ •မွေး•ဖွား•လာ•သူများ •ဖြစ်သည်။•</da…
735 <data>•ထို•သူ•တို့၌ •ပိုင်းခြား •ဝေဖန်•တတ်•သော •ဉာဏ်•နှ•င့် •ကျ•င့်•ဝတ် •သိတတ်•သော •စိတ်•တို့•ရှိ•က…
736 <data>•ထို•သူ•တို့သည် •အချင်းချင်း •မေတ္တာ•ထား၍ •ဆက်ဆံ•ကျ•င့်•သုံး•</data>
744 # Test data originally from http://bugs.icu-project.org/trac/search?q=r30327
749 <data>•តើ<200>លោក<200>មក<200>ពី<200>ប្រទេស<200>ណា<200></data>
750 <data>•សណ្ដូក<200>ក<200>បណ្ដែត<200>ខ្លួន<200></data>
751 <data>•ពណ៌ស<200>ម្ដេច<200>ថា<200>ខ្មៅ<200></data>
752 #ប្រយោគ|ពី|របៀប|រួបរួម|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data>
753 <data>•ប្រយោគ<200>ពី<200>របៀប<200>ដែល<200>និង<200>ភាព<200>ផ្សេងគ្នា<200>ដែល<200>អាច<200>ចូល<200></d…
754 #ប្រយោគ|ពី|របៀប|ជា|មួយ|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data>
755 <data>•សូម<200>ចំណាយពេល<200>បន្តិច<200>ដើម្បី<200>អធិស្ឋាន<200>អរព្រះគុណ<200>ដល់<200>ព្រះអង្គ<200><…
756 <data>•ការ<200>ថោកទាប<200>បរិប្បូណ៌<200>ដោយ<200></data>
757 <data>•ប្រើប្រាស់<200>ស្អាត<200>ទាំង<200>ចិត្ត<200>សិស្ស<200>នោះ<200></data>
758 <data>•បើ<200>អ្នក<200>ប្រព្រឺត្ត<200>អំពើអាក្រក់<200>មុខ<200>ជា<200>មាន<200></data>
759 <data>•ប្រដាប់<200>ប្រដា<200>រ<200>រៀនសូត្រ<200>បន្ទប់<200>រៀន<200></data>
760 <data>•ដើរតួ<200>មនុស្សគ<200>ឥត<200>បញ្ចេញ<200>យោបល់<200>សោះ<200>ឡើយ<200></data>
761 <data>•មិន<200>អាច<200>ឲ្យ<200>យើង<200>ធ្វើ<200>កសិកម្ម<200>បាន<200>ឡើយ<200></data>
762 <data>•បន្ត<200>សេចក្ត<200>ទៅទៀត<200></data>
763 <data>•ក្រុម<200>ប៉ូលិស<200>បណ្តាក់<200>គ្នា<200></data>
764 <data>•គ្មាន<200>សុខ<200>សំរាន្ត<200>ដង<200>ណា<200></data>
765 <data>•បាន<200>សុខភាព<200>បរិប្បូណ៌<200></data>
766 <data>•ជា<200>មេចោរ<200>ខ្ញុំ<200>នឹង<200>ស្លាប់<200>ទៅវិញ<200>ជា<200>មេចោរ<200></data>
767 <data>•ឯ<200>ការ<200>វាយ<200>ផ្ចាល<200>ដែល<200>នាំ<200></data>
768 <data>•គេ<200>ដឹក<200>ទៅ<200>សំឡាប់<200></data>
769 #អ្នក|ដែល|ជា|មន្ត្រី|ធំ|លើ|គាត់|ទេ<200></data>
770 <data>•យក<200>ទៅ<200>សម្លាប់ចោល<200>ស្ងាត់<200></data>
771 <data>•ត្រូវ<200>បាន<200>គេ<200>សម្លាប់<200></data>
772 <data>•នៅក្នុង<200>ស្រុក<200>ខ្ល<200>ងហ្ស៊ុន<200></data>
778 <data>•สวัสดี<200>ครับ<200>สบาย<200>ดี<200>ไหม<200> •ครับ<200></data>
782 <data>•บท<200>ที่๑พายุ<200>ไซโคลน<200>โด<200>โรธี<200>อาศัย<200>อยู่<200>ท่ามกลาง<200>\
786 ไมล์<200></data>
798 <data>•\u3041•\u3043•\u3045•\u31f1•</data>
801 <data>•\u3041\u3043\u3045\u31f1•</data>
803 # The following data was originally in RBBITest::TestJapaneseWordBreak()
806 <data>•\u4ECA\u65E5<400>\u306F<400>\u3044\u3044<400>\u5929\u6C17<400>\u3067\u3059<400>\u306D<400>\u…
815 <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>…
819 <data>•abc/•s •def•</data>
820 <data>•abc/\u05D9 •def•</data>
821 <data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data>
822 <data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05E…
827 <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>…
829 <data>•例えば<400>オーストラリア<400>。•</data>
831 <data>•一部<400>の<400>地域<400>では<400>、<0>ブラジル<400>、<0>インドネシア<400>、<0>オーストリア<400>、<0>ニュージーランド<400>で<400…
841 <data>•Αβ, γδ; Ε ζη; Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data>
845 <data>•Αβ, γδ; •Ε ζη; •Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data>
852 <data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
853 •for<200> •CS<200>-•types<200>.•</data>
854 <data>•\uFF92\uFF76\uFF9E<400> •</data>
858 <data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct<200>.•field<2…
859 •for<200> •CS<200>-•types<200>.•</data>
860 <data>•\u06c9<200>\uc799\ufffa•</data>
861 <data>•\uFF92\uFF76\uFF9E<400> •</data>
875 <data>•\u0E01•\u0E23•\u0E30•\u0E17\u0E48•\u0E2D•\u0E21•\u0E23•\u0E08•\u0E19•\u0E32• •\
877 \u0E40•\u0E14\u0E47•\u0E01•\u0E21\u0E35•\u0E1B\u0E31•\u0E0D•\u0E2B•\u0E32• •</data>
888 <data>•abc •- •def •abc •-•def •abc- •def •abc-•def•</data> # With ASCII hyphen
889 <data>•abc •‐ •def •abc •‐•def •abc‐ •def •abc‐•def•</data> # With Unicode u2010 hyphen
894 #<data>•abc •- •def •abc •-def •abc- •def •abc-•def•</data> # With ASCII hyphen
895 #<data>•abc •‐ •def •abc •‐def •abc‐ •def •abc‐•def•</data> # With Unicode u2010 hyphen
897 <data>•abc •- •def •abc •-def •abc- •def •</data> # With ASCII hyphen
898 <data>•abc •‐ •def •abc •‐def •abc‐ •def •</data> # With Unicode u2010 hyphen
902 <data>•abc/•s •def•</data>
903 <data>•abc/\u05D9 •def•</data>
904 <data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data>
905 <data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05E…
916 <data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</…
921 <data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•…
926 <data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026•\u2026\u0020•u30A2•\uFF01\u0020…
931 <data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</…
936 <data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•<…
941 <data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026•\u2026\u0020•u30A2\uFF01\u0020•<…