1# Copyright (c) 2001-2015 International Business Machines 2# Corporation and others. All Rights Reserved. 3# 4# RBBI Test Data 5# 6# File: rbbitst.txt 7# 8# The format of this file looks vaguely like some kind of xml-ish markup, 9# but it is NOT. The syntax is this.. 10# 11# <word> any following data is for word break testing 12# <sent> any following data is for sentence break testing 13# <line> any following data is for line break testing 14# <char> any following data is for char break testing 15# <locale local_name> Switch to the named locale at the next occurence of <word>, <sent>, etc. 16# <data> ... </data> test data. May span multiple lines. 17# <> Break position, status == 0 18# • Break position, status == 0 (Bullet, \u2022) 19# <nnn> Break position, status == nnn 20# \ Escape. Normal ICU unescape applied. 21# \ at end of line -> Line Continuation. Remove both the backslash and the new line 22# 23# In ICU4C, this test data is run by intltest, rbbi/RBBITest/TestExtended. 24# In ICU4J, this test data is run by com.ibm.icu.dev.test.rbbi.RBBITestExtended 25# 26# There are two copies of this file in the source repository, 27# [ICU4C] source/test/testdata/rbbitst.txt 28# [ICU4J] main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt 29# 30# ICU4C's copy is the master. If any changes are made to ICU4J's copy, make sure they 31# are merged back into ICU4C's copy of the file, lest they get overwritten later. 32# TODO: figure out how to have a single copy of the file for use by both C and Java. 33 34 35## FILTERED BREAK TESTS 36 37# (William Bradford, public domain. http://catalog.hathitrust.org/Record/008651224 ) - edited. 38<locale en> 39<sent> 40<data>\ 41•In the meantime Mr. •Weston arrived with his small ship, which he had now recovered. •Capt. •Gorges, who informed the Sgt. here that one purpose of his going east was to meet with Mr. •Weston, took this opportunity to call him to account for some abuses he had to lay to his charge.•</data> 42 43<locale en@ss=standard> 44<sent> 45<data>\ 46•In the meantime Mr. Weston arrived with his small ship, which he had now recovered. •Capt. Gorges, who informed the Sgt. here that one purpose of his going east was to meet with Mr. Weston, took this opportunity to call him to account for some abuses he had to lay to his charge.•</data> 47 48## END FILTERED BREAK TESTS 49 50<locale> 51 52# Temp debugging tests 53<sent> 54<data>•\u00c0.•</data> 55 56#<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•</data> 57######################################################################################## 58# 59# 60# G r a p h e m e C l u s t e r T e s t s 61# 62# 63########################################################################################## 64<char> 65 66<data>•a•b•c• •,•\u0666•</data> # Quick Test 67<data>•\r•\r•\r\n•\r\n•\n•\r•</data> # don't break CR/LF 68 69# Always break after controls. Combining chars don't combine with them. 70<data>•\u0003•\N{COMBINING GRAVE ACCENT}•\r•\N{COMBINING GRAVE ACCENT}•</data> 71<data>•\u0085•\N{COMBINING MACRON}•A\N{COMBINING MACRON}•</data> 72 73# Surrogates 74<data>•\U00011000•\U00010020•\U00010000\N{COMBINING MACRON}•</data> 75<data>•\ud800\udc00•\udbff\udfff•a•</data> 76 77# Extend (Combining chars) combine. 78<data>•A\N{COMBINING GRAVE ACCENT}•B•</data> 79<data>•\N{GREEK SMALL LETTER MU}\N{COMBINING LOW LINE}\N{COMBINING HORN}•</data> 80<data>•a\u0301•b\u0302•c\u0303•d\u0304•e\u0305•f\u0306•g\u0307•h\u0308•i\u0309•</data> 81 82<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> 83 84# Don't break Hangul Syllables 85# L : \u1100 86# V : \u1161 87# T : \u11A8 88# LV : \uAC00 89# LVT : \uAC01 90 91<data>•\u1100\u1161\u11a8•\u1100\u1161\u11a8•</data> #LVT 92<data>•\u1100\u1161•\u1100\u1161•</data> 93<data>•\u1100\u1161\u11a8•\u1161•\u1100•\u11a8•\u1161\u1161\u1161\u11a8•</data> 94<data>•\u1100\u1100\uac01•\u1100\uac01•\u1100\uac01\u0301•\uac01•</data> 95<data>•\u1100\u0301•\u1161\u11a8\u0301•\u11a8•</data> 96 97 98 99# Hindi combining chars. (An old test) 100# TODO: Update these tests for Unicode 5.1 Extended Grapheme clusters 101#<data>•भ••ा•\u0930•\u0924• •\u0938\u0941\u0902•\u0926•\u0930• 102#•\u0939•\u094c•\u0964•</data> 103#<data>•\u0916\u0947•\u0938\u0941\u0902•\u0926•\u0930•\u0939•\u094c•\u0964•</data> 104 105 106# Bug 1587. Tamil. \u0baa\u0bc1 is an Extended Grpaheme Cluster 107<data>•\u0baa\u0bc1•\u0baa\u0bc1•</data> 108 109# Regression test for bug 1889 110<data>•\u0f40\u0f7d•\u0000•\u0f7e•</data> 111 112 113# 0xffff is a legal character, and should not stop the break iterator early. 114# (Requires special casing in implementation, which is why it gets a test.) 115<data>•\uffff•\uffff• •a•</data> 116 117# Treat Japanese Half Width voicing marks as combining 118<data>•A\uff9e•B\uff9f\uff9e\uff9f•C•</data> 119 120######################################################################################## 121# 122# 123# 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 124# 125# 126########################################################################################## 127#<xgc> 128 129# Plain Vanilla grapheme clusters 130#<data>•a•b•c•</data> 131#<data>•a\u0301\u0302• •b\u0303\u0304•</data> 132 133# Assorted Hindi combining marks 134#<data>•\u0904\u0903• •\u0937\u093E• •\u0904\u093F• •\u0937\u0940• •\u0937\u0949• •\u0937\u094A• •\u0937\u094B• •\u0937\u094C•</data> 135 136# Thai Clusters 137# $Prepend $Extend* $PrependBase $Extend*; 138# 139#<data>•\u0e40\u0e01•\u0e44\u0301\u0e23\u0302\u0303•\u0e40•\u0e40\u0e02•\u0e02• •</data> 140 141 142######################################################################################## 143# 144# 145# W o r d B o u n d a r y T e s t s 146# 147# 148########################################################################################## 149 150<word> 151# 152# Quick sanity test 153# 154<data>•hello<200> •there<200> •goodbye<200></data> 155<data>•hello<200> •12345<100> •,•</data> 156 157 158# 159# Test data originally in RBBIAPITest::TestFirstNextFollowing() and TestLastPreviousPreceding() 160# 161 162<word> 163<data>•This<200> •is<200> •a<200> •word<200> •break<200>.• • •Isn't<200> •it<200>?• •2.25<100></data> 164 165 166 167# 168# Data originally from TestDefaultRuleBasedWordIteration() 169# 170<data>•Write<200> •wordrules<200>.• •123.456<100> •alpha\u00adbeta\u00adgamma<200> •\u092f\u0939<200> •</data> 171<data>• •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200> •\u0938\u093f\u0916\u094b\u0917\u0947<200>?•</data> 172 173#Hindi Numbers 174<data>• •\u0968\u0966.\u0969\u096f<100> •\u0967\u0966\u0966.\u0966\u0966<100> •\N{RUPEE SIGN}•\u0967,\u0967\u0966\u0966.\u0966\u0966<100> • •\u0905\u092e\u091c<200>\n•</data> 175 176<data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢•£•¤•¥•alpha\u05f3beta\u05f4gamma<200> •</data> 177 178<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> 179 180#Hangul 181<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> 182 183<data>•Hello<200>,• •how<200> •are<200> •you<200> •\uc5f0\ud569<200> •\uc7a5\ub85c\uad50\ud68c<200> •\u1109\u1161\u11bc\u1112\u1161\u11bc<200> •\u1112\u1161\u11ab\u110b\u1175\u11ab<200> •</data> 184 185# Words containing non-BMP letters 186<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> 187 188# Unassigned code points 189<data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data> 190 191# Hiragana & Katakana stay together, but separates from each other and Latin. 192# *** what to do about theoretical combos of chars? i.e. hiragana + accent 193#<data>•abc<200>\N{HIRAGANA LETTER SMALL A}<400>\N{HIRAGANA LETTER VU}\N{COMBINING ACUTE ACCENT}<400>\N{HIRAGANA ITERATION MARK}<400>\N{KATAKANA LETTER SMALL A}\N{KATAKANA ITERATION MARK}\N{HALFWIDTH KATAKANA LETTER WO}\N{HALFWIDTH KATAKANA LETTER N}<400>def<200>#•</data> 194 195# test normalization/dictionary handling of halfwidth katakana: same dictionary phrase in fullwidth and halfwidth 196<data>•芽キャベツ<400>芽キャﾍﾞツ<400></data> 197 198# more Japanese tests 199# TODO: some script=common characters in the Hiragana and the Katakana block may not be treated correctly 200# (was formerly true for U+30FC); need to check and fix if so. 201#<data>•どー<400>せ<400>日本語<400>を<400>勉強<400>する<400>理由<400>について<400> •て<400>こと<400>は<400>我<400>でも<400>知<400>ら<400>も<400>い<400>こと<400>なん<400>だ<400>。•</data> 202<data>•日本語<400>を<400>勉強<400>する<400>理由<400>について<400> •て<400>こと<400>は<400>我<400>でも<400>知<400>ら<400>も<400>い<400>こと<400>なん<400>だ<400>。•</data> 203 204# Testing of word boundary for dictionary word containing both kanji and kana 205<data>•中だるみ<400>蔵王の森<400>ウ離島<400></data> 206 207# Testing of Chinese segmentation (taken from a Chinese news article) 208<data>•400<100>余<400>名<400>中央<400>委员<400>和<400>中央<400>候补<400>委员<400>都<400>领<400>到了<400>“•推荐<400>票<400>”•，•有<400>资格<400>在<400>200<100>多<400>名<400>符合<400>条件<400>的<400>63<100>岁<400>以下<400>中共<400>正<400>部<400>级<400>干部<400>中<400>，•选出<400>他们<400>属意<400>的<400>中央<400>政治局<400>委员<400>以<400>向<400>政治局<400>常委<400>会<400>举荐<400>。•</data> 209 210# Words with interior formatting characters 211<data>•def\N{COMBINING ACUTE ACCENT}\N{SYRIAC ABBREVIATION MARK}ghi<200> •</data> 212 213# to test for bug #4097779 214<data>•aa\N{COMBINING GRAVE ACCENT}a<200> •</data> 215 216# fullwidth numeric, midletter characters etc should be treated like their halfwidth counterparts 217# <data>•ＩＳＮ'Ｔ<200> •１９<100>日<400></data> 218# why was this added with the dbbi stuff? 219 220# to test for bug #4098467 221# What follows is a string of Korean characters (I found it in the Yellow Pages 222# ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed 223# it correctly), first as precomposed syllables, and then as conjoining jamo. 224# Both sequences should be semantically identical and break the same way. 225# precomposed syllables... 226<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> 227 228# more Korean tests (Jamo not tested here, not counted as dictionary characters) 229# Disable them now because we don't include a Korean dictionary. 230#<data>•\ud55c\uad6d<200>\ub300\ud559\uad50<200>\uc790\uc5f0<200>\uacfc\ud559<200>\ub300\ud559<200>\ubb3c\ub9ac\ud559\uacfc<200></data> 231#<data>•\ud604\uc7ac<200>\ub294<200> •\uac80\ucc30<200>\uc774<200> •\ubd84\uc2dd<200>\ud68c\uacc4<200>\ubb38\uc81c<200>\ub97c<200> •\uc870\uc0ac<200>\ud560<200> •\uac00\ub2a5\uc131<200>\uc740<200> •\uc5c6\ub2e4<200>\u002e•</data> 232 233<data>•abc<200>\u4e01<400>\u4e02<400>\u3005<400>\u4e03\u4e03<400>abc<200> •</data> 234 235<data>•\u06c9<200>\uc799\ufffa•</data> 236 237 238# 239# Try some words from other scripts. 240# 241 242# Try some words from other scripts. 243# Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin 244# 245<data>•ΑΒΓ<200> •БВГ<200> •אבג֓<200> •ابت<200> •١٢٣<100> •\u10A0\u10A1\u10A2<200> •ABC<200> •</data> 246 247<data>•\u0301•A<200></data> 248 249 250# 251# Hindi word break tests, imported from the old RBBI tests. 252# An historical note: a much earlier version of ICU break iterators had a number 253# of special case rules for Hindi, which were tested by an earlier version of 254# this test data. The current RBBI rules do not special case Hindi in 255# any way, making this test data much less signfificant. 256# 257<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> 258•\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> 259 260# 261# Failures from monkey tests 262# 263<data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data> 264 265# 266# Jitterbug 5276 - treat Japanese half width voicing marks as Grapheme Extend 267# 268<data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data> 269 270# User guide example: 271<data>•Parlez<200>-•vous<200> •français<200> •?•</data> 272 273# Test for #11673 274<word> 275<data>•ジョージア<400> •</data> 276 277######################################################################################## 278# 279# 280# S e n t e n c e B o u n d a r y T e s t s 281# 282# 283########################################################################################## 284 285 286# 287# Test data originally from RBBI RBBITest::TestDefaultRuleBasedSentenceIteration() 288# 289<sent> 290 291 292<sent> 293<data>•This\n<100></data> 294<data>•Hello! •how are you? •I'am fine. •Thankyou. •How are you \ 295doing? •This\n<100> costs $20,00,000. •</data> 296 297 298# Sentence ending in a quote. 299<data>•"Sentence ending with a quote." •Bye.•</data> 300 301# Sentence, and test data, ending without a period or other terminator. 302<data>•Here is a random sentence, no ending period<100></data> 303 304 305<data>• (This is it). •Testing the sentence iterator. •\ 306"This isn't it." •Hi! \ 307•This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\ 308"This isn't it." •\ 309Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!! •Don't rock the boat.\u2029•Because I am the daddy, that is why. 310•Not on my time (el timo.)! •</data> 311 312<data>•Hello. •So what!!\u2029•"But now," he said, \ 313"I know!" •\ 314Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!). •One species, B. anthracis, is highly virulent. 315•Wolf said about Sounder:\ 316"Beautifully thought-out and directed." •\ 317Have you ever said, "This is where\tI shall live"? •He answered, \ 318"You may not!" •Another popular saying is: "How do you do?". \n•\ 319Yet another popular saying is: \ 320'I'm fine thanks.' •\ 321What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tall!!\ 322•Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100></data> 323 324<data>•No breaks when . is surrounded by UPPER.Case letters. •</data> 325<data>•No breaks when . is followed by Numeric .4 a.4 C.4 3.1 .•</data> 326<data>•No breaks when . is followed by a lower, with possible intervening punct .,a .$a .)a. •</data> 327 328# 329# Sentence Breaks: no break at the boundary between CJK and other letters 330# 331<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> 332 333# 334# Treat fullwidth variants of .!? the same as their 335# normal counterparts 336# 337<data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data> 338 339 340# 341# Don't break sentences at boundary between CJK and digits 342# 343<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> 344 345# 346# Breaks around '(' following a sentence TERM. (Rule 9) 347# 348<data>•How do you do?(•Fine). •</data> 349<data>•How do you do? •(Fine). •</data> 350<data>•How do you do?(•fine). •</data> 351<data>•How do you do? •(fine). •</data> 352 353# 354<data>•Hello.123<100></data> # Rule 6 355<data>•Hello?•123<100></data> 356 357<data>•HELLO.Bye<100></data> # Rule 7 358<data>•HELLO?•Bye<100></data> 359 360<data>•Hello.goodbye<100></data> #Rule 8 361<data>•Hello. •Goodbye<100></data> 362<data>•Hello. goodbye<100></data> 363 364 365 366# 367# test for bug #4158381: No breaks when there are no terminators around 368# 369<data>•\<P>Provides a set of "lightweight" (all-java\<FONT SIZE="-2">\<SUP>TM\</SUP>\</FONT> language) components that, to the maximum degree possible, work the same on all platforms. •</data> 370<data>•Another test.\u2029•</data> 371 372# test for bug #4143071: Make sure sentences that end with digits 373# work right 374# 375<data>•Today is the 27th of May, 1998. •</data> 376<data>•Tomorrow with be 28 May 1998. •</data> 377<data>•The day after will be the 30th.\u2029•</data> 378 379# test for bug #4152416: Make sure sentences ending with a capital 380# letter are treated correctly 381# 382<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> 383 384# test for bug #4152117: Make sure sentence breaking is handling 385# punctuation correctly [COULD NOT REPRODUCE THIS BUG, BUT TEST IS 386# HERE TO MAKE SURE IT DOESN'T CROP UP] 387# 388<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. 389•</data> 390 391# sentence breaks for hindi which used Devanagari script 392# make sure there is sentence break after ?,danda(hindi phrase separator), 393# fullstop followed by space. (VERY old test) 394# 395<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>\ 396\u0915\u0948\u0938\u0947 \u0939\u0948?•\u0935\u0939 \u0915\u094d\u200d\u092f\u093e\n\ 397<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> 398 399# Regression test for bug #1984, Sentence break in Arabic text. 400 401<data>\ 402•\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> 403 404# Try a few more of the less common sentence endings. 405<data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end here. •</data> 406 407 408 409 410################################################################ 411# 412# 413# L I N E B R E A K 414# 415# 416################################################################ 417 418<line> 419# 420# Test Character for each of the line break classes. 421# 422# 00A1;AI # INVERTED EXCLAMATION MARK ¡ 423# 0041;AL # LATIN CAPITAL LETTER A 424# 0009;BA # <control> 425# 00B4;BB # ACUTE ACCENT 426# 000C;BK # <control> 427# 2014;B2 # EM DASH 428# FFFC;CB # OBJECT REPLACEMENT CHARACTER 429# 0029;CL # RIGHT PARENTHESIS 430# 0301;CM # COMBINING ACUTE ACCENT 431# 0021;EX # EXCLAMATION MARK 432# 00A0;GL # NO-BREAK SPACE 433# 002D;HY # HYPHEN-MINUS 434# 4E00;ID # <CJK Ideograph, First> 435# 2024;IN # ONE DOT LEADER 436# 002C;IS # COMMA 437# 000A;LF # <control> 438# 0E5A;NS # THAI CHARACTER ANGKHANKHU 439# 0032;NU # DIGIT TWO 440# 0028;OP # LEFT PARENTHESIS 441# 0025;PO # PERCENT SIGN 442# 0024;PR # DOLLAR SIGN 443# 0022;QU # QUOTATION MARK 444# 0E01;SA # THAI CHARACTER KO KAI 445# DB7F;SG # Surrogate 446# 0020;SP # SPACE 447# 002F;SY # SOLIDUS / 448# F8FF;XX # Private Use 449# 200B;ZW # ZERO WIDTH SPACE 450 451 452# 2b Always break at end of text 453 454<data>• •\u00A1•</data> 455<data>• •\u0041•</data> 456<data>• •\u0009•</data> 457<data>• •\u00B4•</data> 458<data>• \u000C<100></data> # LB3C × BK 459<data>• •\u2014•</data> 460<data>• •\uFFFC•</data> 461<data>• \u0029•</data> # LB 8 × CL 462# <data>• • \u0301•</data> # LB 7a Treat SP CM* as if it were ID #TODO: SP CM 463<data>• \u0021•</data> # LB 8 × EX 464#<data>• \u00A0•</data> # LB 11b × GL TODO: fix. 465<data>• •\u002D•</data> 466<data>• •\u4E00•</data> 467<data>• •\u2024•</data> 468<data>• \u002C•</data> # LB 8 × IS 469<data>• \u000A<100></data> # LB3C × ( BK | CR | LF | NL ) 470<data>• •\u0E5A•</data> 471<data>• •\u0032•</data> 472<data>• •\u0028•</data> 473<data>• •\u0025•</data> 474<data>• •\u0024•</data> 475<data>• •\u0022•</data> 476<data>• •\u0E01•</data> 477<data>• •\uDB7F•</data> 478<data>• \u0020•</data> # LB4 - don't break before space. 479<data>• \u002F•</data> # LB 8 × SY 480<data>• •\uF8FF•</data> 481<data>• \u200B•</data> # LB4 - don't break before ZA 482 483 484# 3a Always break after hard line breaks. 485# 3c Never break before hard line breaks. 486 487<data>• •\u00A1\u2028<100>\u00A1•</data> 488<data>• •\u0041\u2028<100>\u0041•</data> 489<data>• •\u0009\u2028<100>\u0009•</data> 490<data>• •\u00B4\u2028<100>\u00B4•</data> 491<data>• \u000C<100>\u2028<100>\u000C<100></data> 492<data>• •\u2014\u2028<100>\u2014•</data> 493<data>• •\uFFFC\u2028<100>\uFFFC•</data> 494<data>• \u0029\u2028<100>\u0029•</data> 495#<data>• \u0301\u2028<100>\u0301•</data> # TODO: fix. 496<data>• \u0021\u2028<100>\u0021•</data> 497#<data>• \u00A0\u2028<100>\u00A0•</data> # TODO: fix 498<data>• •\u002D\u2028<100>\u002D•</data> 499<data>• •\u4E00\u2028<100>\u4E00•</data> 500<data>• •\u2024\u2028<100>\u2024•</data> 501<data>• \u002C\u2028<100>\u002C•</data> 502<data>• \u000A<100>\u2028<100>\u000A<100></data> 503<data>• •\u0E5A\u2028<100>\u0E5A•</data> 504<data>• •\u0032\u2028<100>\u0032•</data> 505<data>• •\u0028\u2028<100>\u0028•</data> 506<data>• •\u0025\u2028<100>\u0025•</data> 507<data>• •\u0024\u2028<100>\u0024•</data> 508<data>• •\u0022\u2028<100>\u0022•</data> 509<data>• •\u0E01\u2028<100>\u0E01•</data> 510<data>• •\uDB7F\u2028<100>\uDB7F•</data> 511<data>• \u0020\u2028<100>\u0020•</data> 512<data>• \u002F\u2028<100>\u002F•</data> 513<data>• •\uF8FF\u2028<100>\uF8FF•</data> 514<data>• \u200B\u2028<100>\u200B•</data> 515 516# User Guide example 517 518<data>•Parlez-•vous •français ?•</data> 519 520# 521# Old Line Break Test data. Orginally located in RBBITest::TestDefaultRuleBasedLineIteration() 522# 523 524<line> 525 526<data>•Multi-•Level •example •of •a •semi-•idiotic •non-•sensical •(non-•important) •sentence. 527<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> 528 529<line> 530<data>•Hello! •how\r\n<100> •(are)\r<100> •you? •I'am •fine- •Thankyou. •foo\u00a0bar 531<100>How, •are, •you? •This, •costs •$20,00,000.•</data> 532 533# test for bug #4068133 534# 535<data>•\u96f6•\u4e00\u3002•\u4e8c\u3001•\u4e09\u3002\u3001•\u56db\u3001\u3002\u3001•\u4e94,•\u516d.•\u4e03.\u3001,\u3002•\u516b•</data> 536 537# to test for bug #4086052 538<data>•foo\u00a0bar•</data> 539 540# to test for bug #4097920 541<data>•dog,cat,mouse •(one)•(two)\n<100></data> 542 543# to test for bug #4035266 544<data>•The •balance •is •$-23,456.78, •not •-•$32,456.78!\n<100></data> 545 546 547# to test for bug #4098467 548# What follows is a string of Korean characters (I found it in the Yellow Pages 549# ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed 550# it correctly), first as precomposed syllables, and then as conjoining jamo. 551# Both sequences should be semantically identical and break the same way. 552# precomposed syllables... (I == Rich Gillam?) 553# 554<data>•\uc0c1•\ud56d •\ud55c•\uc778 •\uc5f0•\ud569 •\uc7a5•\ub85c•\uad50•\ud68c•</data> 555 556# conjoining jamo... 557<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> 558 559# to test for bug #4117554: Fullwidth .!? should be treated as postJwrd 560<data>•\u4e01\uff0e•\u4e02\uff01•\u4e03\uff1f•</data> 561 562# Surrogate line break tests. 563# 564<data>•\u4e01•\ud840\udc01•\u4e02•abc •\ue000 •\udb80\udc01•</data> #This line and the following are equivalent. 565<data>•\u4e01•\U00020001•\u4e02•abc •\ue000 •\U000f0001•</data> 566 567# Regression for bug 836 568# Note: Unicode 5.1 changed this behavior 569# Unicode 5.2 changed it again, there is no break following the '(' 570<data>•AAA(AAA •</data> 571 572# Try some words from other scripts. 573# Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin 574# 575<data>•ΑΒΓ •БВГ •אבג֓ •ابت •١٢٣ •\u10A0\u10A1\u10A2 •ABC •</data> 576 577# 578# ticket #4853: unpaired surrogates should behave like AL 579# 580<data>•abc\ud801xyz•</data> 581 582# 583# Regression tests for failures that originally came from the monkey test. 584# Monkey test failure lines can, with slight reformatting, be copied into this section 585# as test cases. The error display from here is more informative. 586# 587<data>•\ufffc•\u30e3\u000c<100>\u1b39\u300a\u002f\u203a\u200b•\ufffc•\uaf64•\udcfb•</data> 588<data>•\u114d\u31f3•\ube44\u002d•\u0362\u24e2\u276e\u2014\u205f\ufe16•\uc877•\u0fd0\u000a<100>\u20a3•</data> 589<data>•\u080a\u215b\U0001d7d3\u002c•\u2025\U000e012e•\u02df\u118d\u0029\ua8d6\u0085<100>\u6cc4\u2024\u202f\ufffc•</data> 590 591# Test for #10176 (in root) 592<line> 593<data>•abc/•s •def•</data> 594<data>•abc/\u05D9 •def•</data> 595<data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data> 596<data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05EA•</data> 597 598 599 600######################################################################################## 601# 602# 603# T i t l e B o u n d a r y T e s t s 604# 605# 606########################################################################################## 607<title> 608<data>•Here •is •a •short •sample •sentence. •And •another.•</data> 609<data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE. •AND •ANOTHER.•</data> 610<data>• •Start •and •end •with •spaces •</data> 611<data>•Include 123 456 ^& •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data> 612 613<data>•Combining\u0301 \u0301•ma\u0306rks •bye •</data> 614<data>•123 •Start •with •a •number.•</data> 615 616<data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data> 617<data>•' '' •start •with •case-•ignorable & •case-•insensitive •cha'r'a'cter•</data> 618<data>• ''•aaa' •bbb '•ccc' '•ddd''' '''•eee '''•fff''' •ggg ''•</data> 619# Note: apostrophe is case-ignorable. space is not cased. 620 621########################################################################################## 622# 623# Thai Tests 624# 625########################################################################################## 626<locale th> 627<word> 628# 629# Test data originally from the test code source file 630# // @suwit -- Thai sample data from GVT Guideline 631# 632<data>•\u0E2B\u0E19\u0E36\u0E48\u0E07<200>\u0E04\u0E33<200>\u0E44\u0E17\u0E22<200>\ 633\u0E2A\u0E32\u0E21\u0E32\u0E23\u0E16<200>\u0E1B\u0E23\u0E30\u0E01\u0E2D\u0E1A<200>\ 634\u0E14\u0E49\u0E27\u0E22<200>\u0e2b\u0e25\u0e32\u0e22<200>\ 635\u0e1e\u0e22\u0e32\u0e07\u0e04\u0e4c<200></data> 636 637# Test data originally from http://bugs.icu-project.org/trac/search?q=r30327 638<data>•กู<200> •กิน<200>กุ้ง<200> •ปิ้่<200>งอ<200>ยู่<200>ใน<200>ถ้ำ<200></data> 639 640<data>•\u0E01\u0E39<200>\u0020•\u0E01\u0E34\u0E19<200>\u0E01\u0E38\u0E49\u0E07<200>\ 641\u0020•\u0E1B\u0E34\u0E49\u0E48<200>\u0E07\u0E2D<200>\u0E22\u0E39\u0E48<200>\ 642\u0E43\u0E19<200>\u0E16\u0E49\u0E33<200></data> 643 644<line> 645<data>•0E01\u0E39\u0020•\u0E01\u0E34\u0E19•\u0E01\u0E38\u0E49\u0E07\ 646\u0020•\u0E1B\u0E34\u0E49\u0E48•\u0E07\u0E2D•\u0E22\u0E39\u0E48•\ 647\u0E43\u0E19•\u0E16\u0E49\u0E33•</data> 648 649# Data originally from intltest RBBITest::TestThaiLineBreak() 650# 651# \u0e2f-- the Thai paiyannoi character-- isn't a letter. It's a symbol that 652# represents elided letters at the end of a long word. It should be bound to 653# the end of the word and not treated as an independent punctuation mark. 654# 655# the one time where the paiyannoi occurs somewhere other than at the end 656# of a word is in the Thai abbrevation for "etc.", which both begins and 657# ends with a paiyannoi 658# 659<line> 660<data>•\u0e2a\u0e16\u0e32\u0e19\u0e35\u0e2f•\ 661\u0e08\u0e30•\ 662\u0e23\u0e30\u0e14\u0e21•\ 663\u0e40\u0e08\u0e49\u0e32•\ 664\u0e2b\u0e19\u0e49\u0e32\u0e17\u0e35\u0e48•\ 665\u0e2d\u0e2d\u0e01•\ 666\u0e21\u0e32•\ 667\u0e40\u0e23\u0e48\u0e07•\ 668\u0e23\u0e30\u0e1a\u0e32\u0e22•\ 669\u0e2d\u0e22\u0e48\u0e32\u0e07•\ 670\u0e40\u0e15\u0e47\u0e21•\ 671\u0e2f\u0e25\u0e2f•\ 672\u0e17\u0e35\u0e48•\ 673\u0e19\u0e31\u0e49\u0e19•</data> 674 675# Data originally from RBBITest::TestMixedThaiLineBreak() 676# @suwit -- Test Arabic numerals, Thai numerals, Punctuation and English characters start 677# 678<line> 679<data>•\u0E1B\u0E35•\ 680\u0E1E\u0E38\u0E17\u0E18\u0E28\u0E31\u0E01\u0E23\u0E32\u0E0A •\ 6812545 •\ 682\u0E40\u0E1B\u0E47\u0E19•\ 683\u0E1B\u0E35•\ 684\u0E09\u0E25\u0E2D\u0E07•\ 685\u0E04\u0E23\u0E1A•\ 686\u0E23\u0E2D\u0E1A •\ 687\"\u0E52\u0E52\u0E50 •\ 688\u0E1b\u0E35\" •\ 689\u0E02\u0E2d\u0E07•\ 690\u0E01\u0E23\u0E38\u0E07•\ 691\u0E23\u0E31\u0E15\u0E19\u0E42\u0E01\u0E2A\u0E34\u0E19\u0E17\u0E23\u0E4C •\ 692(\u0E01\u0E23\u0E38\u0E07\u0E40\u0E17\u0E1e\u0E2F•\ 693\u0E2B\u0E23\u0E37\u0E2D •\ 694Bangkok)•</data> 695 696# Data originally from RBBITest::TestMaiyamok() 697# The Thai maiyamok character is a shorthand symbol that means "repeat the previous 698# word". Instead of appearing as a word unto itself, however, it's kept together 699# with the word before it. 700# 701<line> 702<data>•\u0e44\u0e1b\u0e46•\ 703\u0e21\u0e32\u0e46•\ 704\u0e23\u0e30\u0e2b\u0e27\u0e48\u0e32\u0e07•\ 705\u0e01\u0e23\u0e38\u0e07•\ 706\u0e40\u0e17\u0e1e•\ 707\u0e41\u0e25\u0e30•\ 708\u0e40\u0e03\u0e35•\ 709\u0e22\u0e07•\ 710\u0e43\u0e2b\u0e21\u0e48•</data> 711 712# Test for #10296 713<line> 714<data>•ใช•มั้ย•</data> 715<data>•มั๊ยล่ะ•ที่รัก•</data> 716 717# Test for #10593 718<line> 719<data>•เล่น•ผ่าน•ทาง•บลูทูธ•บน•อุปกรณ์•</data> 720 721# Test for city names #10691 722<line> 723<data>•ไป•ที่•ซานฟรานซิสโก•</data> 724 725# Test for #10630, #10631 726<line> 727<data>•แท็ก•แอปพลิเคชัน•เป็น•พิเศษ•</data> 728 729# Test for #11019 730<line> 731<data>•เบ•เบราว์เซอร์•โพ•โพสต์•โพสท์•</data> 732 733# Test for #11688 734<line> 735<data>•อัปเดต•อีเวนต์•</data> 736 737########################################################################################## 738# 739# Lao Tests 740# 741########################################################################################## 742<locale en> 743# Basic check for #7647 744<line> 745<data>•ສະບາຍດີ•</data> 746<data>•ດີ•ຂອບໃຈ•</data> 747<data>•ເຈົ້າ•ເວົ້າ•ພາສາ•ອັງກິດ•ໄດ້•ບໍ່•</data> 748<data>•ກະລຸນາ•ເວົ້າ•ຊ້າ•ໆ•</data> 749 750########################################################################################## 751# 752# Burmese/Myanmar Tests 753# 754########################################################################################## 755<locale en> 756# Basic sanity check for #10326 (some text from http://www.unicode.org/udhr/d/udhr_mya.txt) 757<line> 758<data>•လူ•တိုင်း•သည် •တူညီ •လွတ်လပ်•သော •ဂုဏ်•သိ•က္•ခါ•ဖြ•င့် •လည်းကောင်း၊ •</data> 759<data>•တူညီ•လွတ်လပ်•သော •အ•ခွ•င့်•အရေး•များ•ဖြ•င့် •လည်းကောင်း၊ •မွေး•ဖွား•လာ•သူများ •ဖြစ်သည်။•</data> 760<data>•ထို•သူ•တို့၌ •ပိုင်းခြား •ဝေဖန်•တတ်•သော •ဉာဏ်•နှ•င့် •ကျ•င့်•ဝတ် •သိတတ်•သော •စိတ်•တို့•ရှိ•ကြ၍ •</data> 761<data>•ထို•သူ•တို့သည် •အချင်းချင်း •မေတ္တာ•ထား၍ •ဆက်ဆံ•ကျ•င့်•သုံး•</data> 762 763########################################################################################## 764# 765# Khmer Tests 766# 767########################################################################################## 768 769# Test data originally from http://bugs.icu-project.org/trac/search?q=r30327 770# from the file testdata/wordsegments.txt 771<locale en> 772<word> 773 774<data>•តើ<200>លោក<200>មក<200>ពី<200>ប្រទេស<200>ណា<200></data> 775<data>•សណ្ដូក<200>ក<200>បណ្ដែត<200>ខ្លួន<200></data> 776<data>•ពណ៌ស<200>ម្ដេច<200>ថា<200>ខ្មៅ<200></data> 777#ប្រយោគ|ពី|របៀប|រួបរួម|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data> 778<data>•ប្រយោគ<200>ពី<200>របៀប<200>ដែល<200>និង<200>ភាព<200>ផ្សេងគ្នា<200>ដែល<200>អាច<200>ចូល<200></data> 779#ប្រយោគ|ពី|របៀប|ជា|មួយ|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data> 780<data>•សូម<200>ចំណាយពេល<200>បន្តិច<200>ដើម្បី<200>អធិស្ឋាន<200>អរព្រះគុណ<200>ដល់<200>ព្រះអង្គ<200></data> 781<data>•ការ<200>ថោកទាប<200>បរិប្បូណ៌<200>ដោយ<200></data> 782<data>•ប្រើប្រាស់<200>ស្អាត<200>ទាំង<200>ចិត្ត<200>សិស្ស<200>នោះ<200></data> 783<data>•បើ<200>អ្នក<200>ប្រព្រឺត្ត<200>អំពើអាក្រក់<200>មុខ<200>ជា<200>មាន<200></data> 784<data>•ប្រដាប់<200>ប្រដា<200>រ<200>រៀនសូត្រ<200>បន្ទប់<200>រៀន<200></data> 785<data>•ដើរតួ<200>មនុស្សគ<200>ឥត<200>បញ្ចេញ<200>យោបល់<200>សោះ<200>ឡើយ<200></data> 786<data>•មិន<200>អាច<200>ឲ្យ<200>យើង<200>ធ្វើ<200>កសិកម្ម<200>បាន<200>ឡើយ<200></data> 787<data>•បន្ត<200>សេចក្ត<200>ទៅទៀត<200></data> 788<data>•ក្រុម<200>ប៉ូលិស<200>បណ្តាក់<200>គ្នា<200></data> 789<data>•គ្មាន<200>សុខ<200>សំរាន្ត<200>ដង<200>ណា<200></data> 790<data>•បាន<200>សុខភាព<200>បរិប្បូណ៌<200></data> 791<data>•ជា<200>មេចោរ<200>ខ្ញុំ<200>នឹង<200>ស្លាប់<200>ទៅវិញ<200>ជា<200>មេចោរ<200></data> 792<data>•ឯ<200>ការ<200>វាយ<200>ផ្ចាល<200>ដែល<200>នាំ<200></data> 793<data>•គេ<200>ដឹក<200>ទៅ<200>សំឡាប់<200></data> 794#អ្នក|ដែល|ជា|មន្ត្រី|ធំ|លើ|គាត់|ទេ<200></data> 795<data>•យក<200>ទៅ<200>សម្លាប់ចោល<200>ស្ងាត់<200></data> 796<data>•ត្រូវ<200>បាន<200>គេ<200>សម្លាប់<200></data> 797<data>•នៅក្នុង<200>ស្រុក<200>ខ្ល<200>ងហ្ស៊ុន<200></data> 798 799 800# 801# Jitterbug 3671 Test Case 802# 803<data>•สวัสดี<200>ครับ<200>สบาย<200>ดี<200>ไหม<200> •ครับ<200></data> 804 805# 806# Trac ticket 5595 Test Case 807<data>•บท<200>ที่๑พายุ<200>ไซโคลน<200>โด<200>โรธี<200>อาศัย<200>อยู่<200>ท่ามกลาง<200>\ 808ทุ่งใหญ่<200>ใน<200>แคนซัส<200>กับ<200>ลุง<200>เฮ<200>นรี<200>ชาวไร่<200>และ<200>ป้า<200>เอ็ม<200>\ 809ภรรยา<200>ชาวไร่<200>บ้าน<200>ของ<200>พวก<200>เขา<200>หลัง<200>เล็ก<200>เพราะ<200>ไม้<200>\ 810สร้าง<200>บ้าน<200>ต้อง<200>ขน<200>มา<200>ด้วย<200>เกวียน<200>เป็น<200>ระยะ<200>ทาง<200>หลาย<200>\ 811ไมล์<200></data> 812 813#################################################################################### 814# 815# Tailored (locale specific) breaking. 816# 817#################################################################################### 818 819# Japanese line break tailoring test 820 821<locale ja> 822<line> 823<data>•\u3041•\u3043•\u3045•\u31f1•</data> 824<locale en> 825<line> 826<data>•\u3041\u3043\u3045\u31f1•</data> 827 828# The following data was originally in RBBITest::TestJapaneseWordBreak() 829<locale ja> 830<word> 831<data>•\u4ECA\u65E5<400>\u306F<400>\u3044\u3044<400>\u5929\u6C17<400>\u3067\u3059<400>\u306D<400>\u3002•\u000D\u000A•</data> 832 833# UBreakIteratorType UBRK_WORD, Locale "ja" 834# Don't break in runs of hiragana or runs of ideograph, where the latter includes \u3005 \u3007 \u303B (cldrbug #2009). 835# \u79C1\u9054\u306B\u4E00\u3007\u3007\u3007\u306E\u30B3\u30F3\u30D4\u30E5\u30FC\u30BF\u304C\u3042\u308B\u3002\u5948\u3005\u306F\u30EF\u30FC\u30C9\u3067\u3042\u308B\u3002 836# modified to work with dbbi code - should verify 837 838<locale ja> 839<word> 840<data>•私<400>達<400>に<400>一<400>〇<400>〇〇<400>の<400>コンピュータ<400>が<400>ある<400>。<0>奈々<400>は<400>ワード<400>で<400>ある<400>。•</data> 841 842# Test for #10176 (in ja) 843<line> 844<data>•abc/•s •def•</data> 845<data>•abc/\u05D9 •def•</data> 846<data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data> 847<data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05EA•</data> 848 849 850<locale root> 851<word> 852<data>•私<400>達<400>に<400>一<400>〇<400>〇〇<400>の<400>コンピュータ<400>が<400>ある<400>。<0>奈々<400>は<400>ワード<400>で<400>ある<400>。•</data> 853# The following test is for #10300 854<data>•例えば<400>オーストラリア<400>。•</data> 855# The following test is for #10571 856<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>ある<400>。•</data> 857 858# UBreakIteratorType UBRK_SENTENCE, Locale "el" 859# Add break after Greek question mark (cldrbug #2069). 860# "\u0391\u03B2, \u03B3\u03B4; \u0395 \u03B6\u03B7\u037E \u0398 \u03B9\u03BA. " 861# "\u039B\u03BC \u03BD\u03BE! \u039F\u03C0, \u03A1\u03C2? \u03A3" 862# which is "Αβ, γδ; Ε ζη; Θ ικ. Λμ νξ! Οπ, Ρς? Σ" 863 864<locale root> 865<sent> 866<data>•Αβ, γδ; Ε ζη; Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data> 867 868<locale el> 869<sent> 870<data>•Αβ, γδ; •Ε ζη; •Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data> 871 872# UBreakIteratorType UBRK_WORD, Locale "en_US_POSIX" 873# Words don't include colon or period (cldrbug #1969). 874 875<locale en_US> 876<word> 877<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \ 878•for<200> •CS<200>-•types<200>.•</data> 879<data>•\uFF92\uFF76\uFF9E<400> •</data> 880 881<locale en_US_POSIX> 882<word> 883<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct<200>.•field<200> \ 884•for<200> •CS<200>-•types<200>.•</data> 885<data>•\u06c9<200>\uc799\ufffa•</data> 886<data>•\uFF92\uFF76\uFF9E<400> •</data> 887 888 889# UBreakIteratorType UBRK_CHARACTER, Locale "th" 890# Clusters should not include spacing Thai/Lao vowels (prefix or postfix), except for [SARA] AM (cldrbug #2161). 891# Update: As of Unicode 6.1 root has same behavior as th for this. 892# 893# "\u0E01\u0E23\u0E30\u0E17\u0E48\u0E2D\u0E21\u0E23\u0E08\u0E19\u0E32 " 894# "(\u0E2A\u0E38\u0E0A\u0E32\u0E15\u0E34-\u0E08\u0E38\u0E11\u0E32\u0E21\u0E32\u0E28) " 895# "\u0E40\u0E14\u0E47\u0E01\u0E21\u0E35\u0E1B\u0E31\u0E0D\u0E2B\u0E32 " 896# which is "กระท่อมรจนา (สุชาติ-จุฑามาศ) เด็กมีปัญหา " 897 898<locale th> 899<char> 900<data>•\u0E01•\u0E23•\u0E30•\u0E17\u0E48•\u0E2D•\u0E21•\u0E23•\u0E08•\u0E19•\u0E32• •\ 901(•\u0E2A\u0E38•\u0E0A•\u0E32•\u0E15\u0E34•-•\u0E08\u0E38•\u0E11•\u0E32•\u0E21•\u0E32•\u0E28•)• •\ 902\u0E40•\u0E14\u0E47•\u0E01•\u0E21\u0E35•\u0E1B\u0E31•\u0E0D•\u0E2B•\u0E32• •</data> 903 904# Finnish line breaking 905# 906# These rules deal with hyphens when there is a space on the leading side. 907# There should be a break opportunity between the space and the hyphen, and not after the hyphen. 908# See CLDR ticket 3029. 909# See ICU ticket 8151 910 911<locale root> 912<line> 913<data>•abc •- •def •abc •-•def •abc- •def •abc-•def•</data> # With ASCII hyphen 914<data>•abc •‐ •def •abc •‐•def •abc‐ •def •abc‐•def•</data> # With Unicode u2010 hyphen 915 916<locale fi> 917<line> 918# TODO: problems with Finnish line break rules cause these two lines to fail. 919#<data>•abc •- •def •abc •-def •abc- •def •abc-•def•</data> # With ASCII hyphen 920#<data>•abc •‐ •def •abc •‐def •abc‐ •def •abc‐•def•</data> # With Unicode u2010 hyphen 921 922<data>•abc •- •def •abc •-def •abc- •def •</data> # With ASCII hyphen 923<data>•abc •‐ •def •abc •‐def •abc‐ •def •</data> # With Unicode u2010 hyphen 924 925# Test for #10176 (in fi) 926<line> 927<data>•abc/•s •def•</data> 928<data>•abc/\u05D9 •def•</data> 929<data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data> 930<data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05EA•</data> 931 932#################################################################################### 933# 934# Test CSS line break variants: strict, normal, loose 935# 936#################################################################################### 937 938<locale ja@lb=strict> 939<line> 940# •no brk before 3063 •no brk before 301C•no brk btw 2026 •no brk before FF01• 941<data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 942 943<locale ja@lb=normal> 944<line> 945# •brk OK before 3063 •brk OK before 301C •no brk btw 2026 •no brk before FF01• 946<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 947 948<locale ja@lb=loose> 949<line> 950# •brk OK before 3063 •brk OK before 301C •brk OK btw 2026 •brk OK before FF01• 951<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026•\u2026\u0020•u30A2•\uFF01\u0020•</data> 952 953<locale en@lb=strict> 954<line> 955# •no brk before 3063 •no brk before 301C•no brk btw 2026 •no brk before FF01• 956<data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 957 958<locale en@lb=normal> 959<line> 960# •brk OK before 3063 •no brk before 301C •no brk btw 2026 •no brk before FF01• 961<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 962 963<locale en@lb=loose> 964<line> 965# •brk OK before 3063 •no brk before 301C •brk OK btw 2026 •no brk before FF01• 966<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026•\u2026\u0020•u30A2\uFF01\u0020•</data> 967