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# Temp debugging tests 36<sent> 37<data>•\u00c0.•</data> 38 39#<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> 40######################################################################################## 41# 42# 43# G r a p h e m e C l u s t e r T e s t s 44# 45# 46########################################################################################## 47<char> 48 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 51 52# Always break after controls. Combining chars don't combine with them. 53<data>•\u0003•\N{COMBINING GRAVE ACCENT}•\r•\N{COMBINING GRAVE ACCENT}•</data> 54<data>•\u0085•\N{COMBINING MACRON}•A\N{COMBINING MACRON}•</data> 55 56# Surrogates 57<data>•\U00011000•\U00010020•\U00010000\N{COMBINING MACRON}•</data> 58<data>•\ud800\udc00•\udbff\udfff•a•</data> 59 60# Extend (Combining chars) combine. 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> 64 65<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> 66 67# Don't break Hangul Syllables 68# L : \u1100 69# V : \u1161 70# T : \u11A8 71# LV : \uAC00 72# LVT : \uAC01 73 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> 79 80 81 82# Hindi combining chars. (An old test) 83# TODO: Update these tests for Unicode 5.1 Extended Grapheme clusters 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> 87 88 89# Bug 1587. Tamil. \u0baa\u0bc1 is an Extended Grpaheme Cluster 90<data>•\u0baa\u0bc1•\u0baa\u0bc1•</data> 91 92# Regression test for bug 1889 93<data>•\u0f40\u0f7d•\u0000•\u0f7e•</data> 94 95 96# 0xffff is a legal character, and should not stop the break iterator early. 97# (Requires special casing in implementation, which is why it gets a test.) 98<data>•\uffff•\uffff• •a•</data> 99 100# Treat Japanese Half Width voicing marks as combining 101<data>•A\uff9e•B\uff9f\uff9e\uff9f•C•</data> 102 103######################################################################################## 104# 105# 106# 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 107# 108# 109########################################################################################## 110#<xgc> 111 112# Plain Vanilla grapheme clusters 113#<data>•a•b•c•</data> 114#<data>•a\u0301\u0302• •b\u0303\u0304•</data> 115 116# Assorted Hindi combining marks 117#<data>•\u0904\u0903• •\u0937\u093E• •\u0904\u093F• •\u0937\u0940• •\u0937\u0949• •\u0937\u094A• •\u0937\u094B• •\u0937\u094C•</data> 118 119# Thai Clusters 120# $Prepend $Extend* $PrependBase $Extend*; 121# 122#<data>•\u0e40\u0e01•\u0e44\u0301\u0e23\u0302\u0303•\u0e40•\u0e40\u0e02•\u0e02• •</data> 123 124 125######################################################################################## 126# 127# 128# W o r d B o u n d a r y T e s t s 129# 130# 131########################################################################################## 132 133<word> 134# 135# Quick sanity test 136# 137<data>•hello<200> •there<200> •goodbye<200></data> 138<data>•hello<200> •12345<100> •,•</data> 139 140 141# 142# Test data originally in RBBIAPITest::TestFirstNextFollowing() and TestLastPreviousPreceding() 143# 144 145<word> 146<data>•This<200> •is<200> •a<200> •word<200> •break<200>.• • •Isn't<200> •it<200>?• •2.25<100></data> 147 148 149 150# 151# Data originally from TestDefaultRuleBasedWordIteration() 152# 153<data>•Write<200> •wordrules<200>.• •123.456<100> •alpha\u00adbeta\u00adgamma<200> •\u092f\u0939<200> •</data> 154<data>• •\u0939\u093f\u0928\u094d\u200d\u0926\u0940<200> •\u0939\u0948<200> •\u0905\u093e\u092a<200> •\u0938\u093f\u0916\u094b\u0917\u0947<200>?•</data> 155 156#Hindi Numbers 157<data>• •\u0968\u0966.\u0969\u096f<100> •\u0967\u0966\u0966.\u0966\u0966<100> •\N{RUPEE SIGN}•\u0967,\u0967\u0966\u0966.\u0966\u0966<100> • •\u0905\u092e\u091c<200>\n•</data> 158 159<data>•\u0938\u094d\u200d\u0935\u0924\u0902deadTA\u0930<200>\r•It's<200> •$•30.10<100> •12,34<100>¢•£•¤•¥•alpha\u05f3beta\u05f4gamma<200> •</data> 160 161<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> 162 163#Hangul 164<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> 165 166<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> 167 168# Words containing non-BMP letters 169<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> 170 171# Unassigned code points 172<data>•abc<200>\U0001D800•def<200>\U0001D3FF• •</data> 173 174# Hiragana & Katakana stay together, but separates from each other and Latin. 175# *** what to do about theoretical combos of chars? i.e. hiragana + accent 176#<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> 177 178# test normalization/dictionary handling of halfwidth katakana: same dictionary phrase in fullwidth and halfwidth 179<data>•芽キャベツ<400>芽キャﾍﾞツ<400></data> 180 181# more Japanese tests 182# TODO: some script=common characters in the Hiragana and the Katakana block may not be treated correctly 183# (was formerly true for U+30FC); need to check and fix if so. 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>知<400>ら<400>も<400>い<400>こと<400>なん<400>だ<400>。•</data> 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<400>い<400>こと<400>なん<400>だ<400>。•</data> 186 187# Testing of word boundary for dictionary word containing both kanji and kana 188<data>•中だるみ<400>蔵王の森<400>ウ離島<400></data> 189 190# Testing of Chinese segmentation (taken from a Chinese news article) 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<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> 192 193# Words with interior formatting characters 194<data>•def\N{COMBINING ACUTE ACCENT}\N{SYRIAC ABBREVIATION MARK}ghi<200> •</data> 195 196# to test for bug #4097779 197<data>•aa\N{COMBINING GRAVE ACCENT}a<200> •</data> 198 199# fullwidth numeric, midletter characters etc should be treated like their halfwidth counterparts 200# <data>•ＩＳＮ'Ｔ<200> •１９<100>日<400></data> 201# why was this added with the dbbi stuff? 202 203# to test for bug #4098467 204# What follows is a string of Korean characters (I found it in the Yellow Pages 205# ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed 206# it correctly), first as precomposed syllables, and then as conjoining jamo. 207# Both sequences should be semantically identical and break the same way. 208# precomposed syllables... 209<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> 210 211# more Korean tests (Jamo not tested here, not counted as dictionary characters) 212# Disable them now because we don't include a Korean dictionary. 213#<data>•\ud55c\uad6d<200>\ub300\ud559\uad50<200>\uc790\uc5f0<200>\uacfc\ud559<200>\ub300\ud559<200>\ubb3c\ub9ac\ud559\uacfc<200></data> 214#<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> 215 216<data>•abc<200>\u4e01<400>\u4e02<400>\u3005<400>\u4e03\u4e03<400>abc<200> •</data> 217 218<data>•\u06c9<200>\uc799\ufffa•</data> 219 220 221# 222# Try some words from other scripts. 223# 224 225# Try some words from other scripts. 226# Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin 227# 228<data>•ΑΒΓ<200> •БВГ<200> •אבג֓<200> •ابت<200> •١٢٣<100> •\u10A0\u10A1\u10A2<200> •ABC<200> •</data> 229 230<data>•\u0301•A<200></data> 231 232 233# 234# Hindi word break tests, imported from the old RBBI tests. 235# An historical note: a much earlier version of ICU break iterators had a number 236# of special case rules for Hindi, which were tested by an earlier version of 237# this test data. The current RBBI rules do not special case Hindi in 238# any way, making this test data much less signfificant. 239# 240<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> 241•\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> 242 243# 244# Failures from monkey tests 245# 246<data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data> 247 248# 249# Jitterbug 5276 - treat Japanese half width voicing marks as Grapheme Extend 250# 251<data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data> 252 253# User guide example: 254<data>•Parlez<200>-•vous<200> •français<200> •?•</data> 255 256# Test for #11673 257<word> 258<data>•ジョージア<400> •</data> 259 260######################################################################################## 261# 262# 263# S e n t e n c e B o u n d a r y T e s t s 264# 265# 266########################################################################################## 267 268 269# 270# Test data originally from RBBI RBBITest::TestDefaultRuleBasedSentenceIteration() 271# 272<sent> 273 274 275<sent> 276<data>•This\n<100></data> 277<data>•Hello! •how are you? •I'am fine. •Thankyou. •How are you \ 278doing? •This\n<100> costs $20,00,000. •</data> 279 280 281# Sentence ending in a quote. 282<data>•"Sentence ending with a quote." •Bye.•</data> 283 284# Sentence, and test data, ending without a period or other terminator. 285<data>•Here is a random sentence, no ending period<100></data> 286 287 288<data>• (This is it). •Testing the sentence iterator. •\ 289"This isn't it." •Hi! \ 290•This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\ 291"This isn't it." •\ 292Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!! •Don't rock the boat.\u2029•Because I am the daddy, that is why. 293•Not on my time (el timo.)! •</data> 294 295<data>•Hello. •So what!!\u2029•"But now," he said, \ 296"I know!" •\ 297Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!). •One species, B. anthracis, is highly virulent. 298•Wolf said about Sounder:\ 299"Beautifully thought-out and directed." •\ 300Have you ever said, "This is where\tI shall live"? •He answered, \ 301"You may not!" •Another popular saying is: "How do you do?". \n•\ 302Yet another popular saying is: \ 303'I'm fine thanks.' •\ 304What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tall!!\ 305•Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100></data> 306 307<data>•No breaks when . is surrounded by UPPER.Case letters. •</data> 308<data>•No breaks when . is followed by Numeric .4 a.4 C.4 3.1 .•</data> 309<data>•No breaks when . is followed by a lower, with possible intervening punct .,a .$a .)a. •</data> 310 311# 312# Sentence Breaks: no break at the boundary between CJK and other letters 313# 314<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> 315 316# 317# Treat fullwidth variants of .!? the same as their 318# normal counterparts 319# 320<data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data> 321 322 323# 324# Don't break sentences at boundary between CJK and digits 325# 326<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> 327 328# 329# Breaks around '(' following a sentence TERM. (Rule 9) 330# 331<data>•How do you do?(•Fine). •</data> 332<data>•How do you do? •(Fine). •</data> 333<data>•How do you do?(•fine). •</data> 334<data>•How do you do? •(fine). •</data> 335 336# 337<data>•Hello.123<100></data> # Rule 6 338<data>•Hello?•123<100></data> 339 340<data>•HELLO.Bye<100></data> # Rule 7 341<data>•HELLO?•Bye<100></data> 342 343<data>•Hello.goodbye<100></data> #Rule 8 344<data>•Hello. •Goodbye<100></data> 345<data>•Hello. goodbye<100></data> 346 347 348 349# 350# test for bug #4158381: No breaks when there are no terminators around 351# 352<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> 353<data>•Another test.\u2029•</data> 354 355# test for bug #4143071: Make sure sentences that end with digits 356# work right 357# 358<data>•Today is the 27th of May, 1998. •</data> 359<data>•Tomorrow with be 28 May 1998. •</data> 360<data>•The day after will be the 30th.\u2029•</data> 361 362# test for bug #4152416: Make sure sentences ending with a capital 363# letter are treated correctly 364# 365<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> 366 367# test for bug #4152117: Make sure sentence breaking is handling 368# punctuation correctly [COULD NOT REPRODUCE THIS BUG, BUT TEST IS 369# HERE TO MAKE SURE IT DOESN'T CROP UP] 370# 371<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. 372•</data> 373 374# sentence breaks for hindi which used Devanagari script 375# make sure there is sentence break after ?,danda(hindi phrase separator), 376# fullstop followed by space. (VERY old test) 377# 378<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>\ 379\u0915\u0948\u0938\u0947 \u0939\u0948?•\u0935\u0939 \u0915\u094d\u200d\u092f\u093e\n\ 380<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> 381 382# Regression test for bug #1984, Sentence break in Arabic text. 383 384<data>\ 385•\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> 386 387# Try a few more of the less common sentence endings. 388<data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end here. •</data> 389 390 391 392 393################################################################ 394# 395# 396# L I N E B R E A K 397# 398# 399################################################################ 400 401<line> 402# 403# Test Character for each of the line break classes. 404# 405# 00A1;AI # INVERTED EXCLAMATION MARK ¡ 406# 0041;AL # LATIN CAPITAL LETTER A 407# 0009;BA # <control> 408# 00B4;BB # ACUTE ACCENT 409# 000C;BK # <control> 410# 2014;B2 # EM DASH 411# FFFC;CB # OBJECT REPLACEMENT CHARACTER 412# 0029;CL # RIGHT PARENTHESIS 413# 0301;CM # COMBINING ACUTE ACCENT 414# 0021;EX # EXCLAMATION MARK 415# 00A0;GL # NO-BREAK SPACE 416# 002D;HY # HYPHEN-MINUS 417# 4E00;ID # <CJK Ideograph, First> 418# 2024;IN # ONE DOT LEADER 419# 002C;IS # COMMA 420# 000A;LF # <control> 421# 0E5A;NS # THAI CHARACTER ANGKHANKHU 422# 0032;NU # DIGIT TWO 423# 0028;OP # LEFT PARENTHESIS 424# 0025;PO # PERCENT SIGN 425# 0024;PR # DOLLAR SIGN 426# 0022;QU # QUOTATION MARK 427# 0E01;SA # THAI CHARACTER KO KAI 428# DB7F;SG # Surrogate 429# 0020;SP # SPACE 430# 002F;SY # SOLIDUS / 431# F8FF;XX # Private Use 432# 200B;ZW # ZERO WIDTH SPACE 433 434 435# 2b Always break at end of text 436 437<data>• •\u00A1•</data> 438<data>• •\u0041•</data> 439<data>• •\u0009•</data> 440<data>• •\u00B4•</data> 441<data>• \u000C<100></data> # LB3C × BK 442<data>• •\u2014•</data> 443<data>• •\uFFFC•</data> 444<data>• \u0029•</data> # LB 8 × CL 445# <data>• • \u0301•</data> # LB 7a Treat SP CM* as if it were ID #TODO: SP CM 446<data>• \u0021•</data> # LB 8 × EX 447#<data>• \u00A0•</data> # LB 11b × GL TODO: fix. 448<data>• •\u002D•</data> 449<data>• •\u4E00•</data> 450<data>• •\u2024•</data> 451<data>• \u002C•</data> # LB 8 × IS 452<data>• \u000A<100></data> # LB3C × ( BK | CR | LF | NL ) 453<data>• •\u0E5A•</data> 454<data>• •\u0032•</data> 455<data>• •\u0028•</data> 456<data>• •\u0025•</data> 457<data>• •\u0024•</data> 458<data>• •\u0022•</data> 459<data>• •\u0E01•</data> 460<data>• •\uDB7F•</data> 461<data>• \u0020•</data> # LB4 - don't break before space. 462<data>• \u002F•</data> # LB 8 × SY 463<data>• •\uF8FF•</data> 464<data>• \u200B•</data> # LB4 - don't break before ZA 465 466 467# 3a Always break after hard line breaks. 468# 3c Never break before hard line breaks. 469 470<data>• •\u00A1\u2028<100>\u00A1•</data> 471<data>• •\u0041\u2028<100>\u0041•</data> 472<data>• •\u0009\u2028<100>\u0009•</data> 473<data>• •\u00B4\u2028<100>\u00B4•</data> 474<data>• \u000C<100>\u2028<100>\u000C<100></data> 475<data>• •\u2014\u2028<100>\u2014•</data> 476<data>• •\uFFFC\u2028<100>\uFFFC•</data> 477<data>• \u0029\u2028<100>\u0029•</data> 478#<data>• \u0301\u2028<100>\u0301•</data> # TODO: fix. 479<data>• \u0021\u2028<100>\u0021•</data> 480#<data>• \u00A0\u2028<100>\u00A0•</data> # TODO: fix 481<data>• •\u002D\u2028<100>\u002D•</data> 482<data>• •\u4E00\u2028<100>\u4E00•</data> 483<data>• •\u2024\u2028<100>\u2024•</data> 484<data>• \u002C\u2028<100>\u002C•</data> 485<data>• \u000A<100>\u2028<100>\u000A<100></data> 486<data>• •\u0E5A\u2028<100>\u0E5A•</data> 487<data>• •\u0032\u2028<100>\u0032•</data> 488<data>• •\u0028\u2028<100>\u0028•</data> 489<data>• •\u0025\u2028<100>\u0025•</data> 490<data>• •\u0024\u2028<100>\u0024•</data> 491<data>• •\u0022\u2028<100>\u0022•</data> 492<data>• •\u0E01\u2028<100>\u0E01•</data> 493<data>• •\uDB7F\u2028<100>\uDB7F•</data> 494<data>• \u0020\u2028<100>\u0020•</data> 495<data>• \u002F\u2028<100>\u002F•</data> 496<data>• •\uF8FF\u2028<100>\uF8FF•</data> 497<data>• \u200B\u2028<100>\u200B•</data> 498 499# User Guide example 500 501<data>•Parlez-•vous •français ?•</data> 502 503# 504# Old Line Break Test data. Orginally located in RBBITest::TestDefaultRuleBasedLineIteration() 505# 506 507<line> 508 509<data>•Multi-•Level •example •of •a •semi-•idiotic •non-•sensical •(non-•important) •sentence. 510<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> 511 512<line> 513<data>•Hello! •how\r\n<100> •(are)\r<100> •you? •I'am •fine- •Thankyou. •foo\u00a0bar 514<100>How, •are, •you? •This, •costs •$20,00,000.•</data> 515 516# test for bug #4068133 517# 518<data>•\u96f6•\u4e00\u3002•\u4e8c\u3001•\u4e09\u3002\u3001•\u56db\u3001\u3002\u3001•\u4e94,•\u516d.•\u4e03.\u3001,\u3002•\u516b•</data> 519 520# to test for bug #4086052 521<data>•foo\u00a0bar•</data> 522 523# to test for bug #4097920 524<data>•dog,cat,mouse •(one)•(two)\n<100></data> 525 526# to test for bug #4035266 527<data>•The •balance •is •$-23,456.78, •not •-•$32,456.78!\n<100></data> 528 529 530# to test for bug #4098467 531# What follows is a string of Korean characters (I found it in the Yellow Pages 532# ad for the Korean Presbyterian Church of San Francisco, and I hope I transcribed 533# it correctly), first as precomposed syllables, and then as conjoining jamo. 534# Both sequences should be semantically identical and break the same way. 535# precomposed syllables... (I == Rich Gillam?) 536# 537<data>•\uc0c1•\ud56d •\ud55c•\uc778 •\uc5f0•\ud569 •\uc7a5•\ub85c•\uad50•\ud68c•</data> 538 539# conjoining jamo... 540<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> 541 542# to test for bug #4117554: Fullwidth .!? should be treated as postJwrd 543<data>•\u4e01\uff0e•\u4e02\uff01•\u4e03\uff1f•</data> 544 545# Surrogate line break tests. 546# 547<data>•\u4e01•\ud840\udc01•\u4e02•abc •\ue000 •\udb80\udc01•</data> #This line and the following are equivalent. 548<data>•\u4e01•\U00020001•\u4e02•abc •\ue000 •\U000f0001•</data> 549 550# Regression for bug 836 551# Note: Unicode 5.1 changed this behavior 552# Unicode 5.2 changed it again, there is no break following the '(' 553<data>•AAA(AAA •</data> 554 555# Try some words from other scripts. 556# Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin 557# 558<data>•ΑΒΓ •БВГ •אבג֓ •ابت •١٢٣ •\u10A0\u10A1\u10A2 •ABC •</data> 559 560# 561# ticket #4853: unpaired surrogates should behave like AL 562# 563<data>•abc\ud801xyz•</data> 564 565# 566# Regression tests for failures that originally came from the monkey test. 567# Monkey test failure lines can, with slight reformatting, be copied into this section 568# as test cases. The error display from here is more informative. 569# 570<data>•\ufffc•\u30e3\u000c<100>\u1b39\u300a\u002f\u203a\u200b•\ufffc•\uaf64•\udcfb•</data> 571<data>•\u114d\u31f3•\ube44\u002d•\u0362\u24e2\u276e\u2014\u205f\ufe16•\uc877•\u0fd0\u000a<100>\u20a3•</data> 572<data>•\u080a\u215b\U0001d7d3\u002c•\u2025\U000e012e•\u02df\u118d\u0029\ua8d6\u0085<100>\u6cc4\u2024\u202f\ufffc•</data> 573 574# Test for #10176 (in root) 575<line> 576<data>•abc/•s •def•</data> 577<data>•abc/\u05D9 •def•</data> 578<data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data> 579<data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05EA•</data> 580 581 582 583######################################################################################## 584# 585# 586# T i t l e B o u n d a r y T e s t s 587# 588# 589########################################################################################## 590<title> 591<data>•Here •is •a •short •sample •sentence. •And •another.•</data> 592<data>•HERE •IS •A •SHORT •SAMPLE •SENTENCE. •AND •ANOTHER.•</data> 593<data>• •Start •and •end •with •spaces •</data> 594<data>•Include 123 456 ^& •some 54332 •numbers 4445•abc123•abc •ending 1223 •</data> 595 596<data>•Combining\u0301 \u0301•ma\u0306rks •bye •</data> 597<data>•123 •Start •with •a •number.•</data> 598 599<data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data> 600<data>•' '' •start •with •case-•ignorable & •case-•insensitive •cha'r'a'cter•</data> 601<data>• ''•aaa' •bbb '•ccc' '•ddd''' '''•eee '''•fff''' •ggg ''•</data> 602# Note: apostrophe is case-ignorable. space is not cased. 603 604########################################################################################## 605# 606# Thai Tests 607# 608########################################################################################## 609<locale th> 610<word> 611# 612# Test data originally from the test code source file 613# // @suwit -- Thai sample data from GVT Guideline 614# 615<data>•\u0E2B\u0E19\u0E36\u0E48\u0E07<200>\u0E04\u0E33<200>\u0E44\u0E17\u0E22<200>\ 616\u0E2A\u0E32\u0E21\u0E32\u0E23\u0E16<200>\u0E1B\u0E23\u0E30\u0E01\u0E2D\u0E1A<200>\ 617\u0E14\u0E49\u0E27\u0E22<200>\u0e2b\u0e25\u0e32\u0e22<200>\ 618\u0e1e\u0e22\u0e32\u0e07\u0e04\u0e4c<200></data> 619 620# Test data originally from http://bugs.icu-project.org/trac/search?q=r30327 621<data>•กู<200> •กิน<200>กุ้ง<200> •ปิ้่<200>งอ<200>ยู่<200>ใน<200>ถ้ำ<200></data> 622 623<data>•\u0E01\u0E39<200>\u0020•\u0E01\u0E34\u0E19<200>\u0E01\u0E38\u0E49\u0E07<200>\ 624\u0020•\u0E1B\u0E34\u0E49\u0E48<200>\u0E07\u0E2D<200>\u0E22\u0E39\u0E48<200>\ 625\u0E43\u0E19<200>\u0E16\u0E49\u0E33<200></data> 626 627<line> 628<data>•0E01\u0E39\u0020•\u0E01\u0E34\u0E19•\u0E01\u0E38\u0E49\u0E07\ 629\u0020•\u0E1B\u0E34\u0E49\u0E48•\u0E07\u0E2D•\u0E22\u0E39\u0E48•\ 630\u0E43\u0E19•\u0E16\u0E49\u0E33•</data> 631 632# Data originally from intltest RBBITest::TestThaiLineBreak() 633# 634# \u0e2f-- the Thai paiyannoi character-- isn't a letter. It's a symbol that 635# represents elided letters at the end of a long word. It should be bound to 636# the end of the word and not treated as an independent punctuation mark. 637# 638# the one time where the paiyannoi occurs somewhere other than at the end 639# of a word is in the Thai abbrevation for "etc.", which both begins and 640# ends with a paiyannoi 641# 642<line> 643<data>•\u0e2a\u0e16\u0e32\u0e19\u0e35\u0e2f•\ 644\u0e08\u0e30•\ 645\u0e23\u0e30\u0e14\u0e21•\ 646\u0e40\u0e08\u0e49\u0e32•\ 647\u0e2b\u0e19\u0e49\u0e32\u0e17\u0e35\u0e48•\ 648\u0e2d\u0e2d\u0e01•\ 649\u0e21\u0e32•\ 650\u0e40\u0e23\u0e48\u0e07•\ 651\u0e23\u0e30\u0e1a\u0e32\u0e22•\ 652\u0e2d\u0e22\u0e48\u0e32\u0e07•\ 653\u0e40\u0e15\u0e47\u0e21•\ 654\u0e2f\u0e25\u0e2f•\ 655\u0e17\u0e35\u0e48•\ 656\u0e19\u0e31\u0e49\u0e19•</data> 657 658# Data originally from RBBITest::TestMixedThaiLineBreak() 659# @suwit -- Test Arabic numerals, Thai numerals, Punctuation and English characters start 660# 661<line> 662<data>•\u0E1B\u0E35•\ 663\u0E1E\u0E38\u0E17\u0E18\u0E28\u0E31\u0E01\u0E23\u0E32\u0E0A •\ 6642545 •\ 665\u0E40\u0E1B\u0E47\u0E19•\ 666\u0E1B\u0E35•\ 667\u0E09\u0E25\u0E2D\u0E07•\ 668\u0E04\u0E23\u0E1A•\ 669\u0E23\u0E2D\u0E1A •\ 670\"\u0E52\u0E52\u0E50 •\ 671\u0E1b\u0E35\" •\ 672\u0E02\u0E2d\u0E07•\ 673\u0E01\u0E23\u0E38\u0E07•\ 674\u0E23\u0E31\u0E15\u0E19\u0E42\u0E01\u0E2A\u0E34\u0E19\u0E17\u0E23\u0E4C •\ 675(\u0E01\u0E23\u0E38\u0E07\u0E40\u0E17\u0E1e\u0E2F•\ 676\u0E2B\u0E23\u0E37\u0E2D •\ 677Bangkok)•</data> 678 679# Data originally from RBBITest::TestMaiyamok() 680# The Thai maiyamok character is a shorthand symbol that means "repeat the previous 681# word". Instead of appearing as a word unto itself, however, it's kept together 682# with the word before it. 683# 684<line> 685<data>•\u0e44\u0e1b\u0e46•\ 686\u0e21\u0e32\u0e46•\ 687\u0e23\u0e30\u0e2b\u0e27\u0e48\u0e32\u0e07•\ 688\u0e01\u0e23\u0e38\u0e07•\ 689\u0e40\u0e17\u0e1e•\ 690\u0e41\u0e25\u0e30•\ 691\u0e40\u0e03\u0e35•\ 692\u0e22\u0e07•\ 693\u0e43\u0e2b\u0e21\u0e48•</data> 694 695# Test for #10296 696<line> 697<data>•ใช•มั้ย•</data> 698<data>•มั๊ยล่ะ•ที่รัก•</data> 699 700# Test for #10593 701<line> 702<data>•เล่น•ผ่าน•ทาง•บลูทูธ•บน•อุปกรณ์•</data> 703 704# Test for city names #10691 705<line> 706<data>•ไป•ที่•ซานฟรานซิสโก•</data> 707 708# Test for #10630, #10631 709<line> 710<data>•แท็ก•แอปพลิเคชัน•เป็น•พิเศษ•</data> 711 712# Test for #11019 713<line> 714<data>•เบ•เบราว์เซอร์•โพ•โพสต์•โพสท์•</data> 715 716# Test for #11688 717<line> 718<data>•อัปเดต•อีเวนต์•</data> 719 720########################################################################################## 721# 722# Lao Tests 723# 724########################################################################################## 725<locale en> 726# Basic check for #7647 727<line> 728<data>•ສະບາຍດີ•</data> 729<data>•ດີ•ຂອບໃຈ•</data> 730<data>•ເຈົ້າ•ເວົ້າ•ພາສາ•ອັງກິດ•ໄດ້•ບໍ່•</data> 731<data>•ກະລຸນາ•ເວົ້າ•ຊ້າ•ໆ•</data> 732 733########################################################################################## 734# 735# Burmese/Myanmar Tests 736# 737########################################################################################## 738<locale en> 739# Basic sanity check for #10326 (some text from http://www.unicode.org/udhr/d/udhr_mya.txt) 740<line> 741<data>•လူ•တိုင်း•သည် •တူညီ •လွတ်လပ်•သော •ဂုဏ်•သိ•က္•ခါ•ဖြ•င့် •လည်းကောင်း၊ •</data> 742<data>•တူညီ•လွတ်လပ်•သော •အ•ခွ•င့်•အရေး•များ•ဖြ•င့် •လည်းကောင်း၊ •မွေး•ဖွား•လာ•သူများ •ဖြစ်သည်။•</data> 743<data>•ထို•သူ•တို့၌ •ပိုင်းခြား •ဝေဖန်•တတ်•သော •ဉာဏ်•နှ•င့် •ကျ•င့်•ဝတ် •သိတတ်•သော •စိတ်•တို့•ရှိ•ကြ၍ •</data> 744<data>•ထို•သူ•တို့သည် •အချင်းချင်း •မေတ္တာ•ထား၍ •ဆက်ဆံ•ကျ•င့်•သုံး•</data> 745 746########################################################################################## 747# 748# Khmer Tests 749# 750########################################################################################## 751 752# Test data originally from http://bugs.icu-project.org/trac/search?q=r30327 753# from the file testdata/wordsegments.txt 754<locale en> 755<word> 756 757<data>•តើ<200>លោក<200>មក<200>ពី<200>ប្រទេស<200>ណា<200></data> 758<data>•សណ្ដូក<200>ក<200>បណ្ដែត<200>ខ្លួន<200></data> 759<data>•ពណ៌ស<200>ម្ដេច<200>ថា<200>ខ្មៅ<200></data> 760#ប្រយោគ|ពី|របៀប|រួបរួម|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data> 761<data>•ប្រយោគ<200>ពី<200>របៀប<200>ដែល<200>និង<200>ភាព<200>ផ្សេងគ្នា<200>ដែល<200>អាច<200>ចូល<200></data> 762#ប្រយោគ|ពី|របៀប|ជា|មួយ|និង|ភាព|ផ្សេងគ្នា|ដែល|អាច|ចូល<200></data> 763<data>•សូម<200>ចំណាយពេល<200>បន្តិច<200>ដើម្បី<200>អធិស្ឋាន<200>អរព្រះគុណ<200>ដល់<200>ព្រះអង្គ<200></data> 764<data>•ការ<200>ថោកទាប<200>បរិប្បូណ៌<200>ដោយ<200></data> 765<data>•ប្រើប្រាស់<200>ស្អាត<200>ទាំង<200>ចិត្ត<200>សិស្ស<200>នោះ<200></data> 766<data>•បើ<200>អ្នក<200>ប្រព្រឺត្ត<200>អំពើអាក្រក់<200>មុខ<200>ជា<200>មាន<200></data> 767<data>•ប្រដាប់<200>ប្រដា<200>រ<200>រៀនសូត្រ<200>បន្ទប់<200>រៀន<200></data> 768<data>•ដើរតួ<200>មនុស្សគ<200>ឥត<200>បញ្ចេញ<200>យោបល់<200>សោះ<200>ឡើយ<200></data> 769<data>•មិន<200>អាច<200>ឲ្យ<200>យើង<200>ធ្វើ<200>កសិកម្ម<200>បាន<200>ឡើយ<200></data> 770<data>•បន្ត<200>សេចក្ត<200>ទៅទៀត<200></data> 771<data>•ក្រុម<200>ប៉ូលិស<200>បណ្តាក់<200>គ្នា<200></data> 772<data>•គ្មាន<200>សុខ<200>សំរាន្ត<200>ដង<200>ណា<200></data> 773<data>•បាន<200>សុខភាព<200>បរិប្បូណ៌<200></data> 774<data>•ជា<200>មេចោរ<200>ខ្ញុំ<200>នឹង<200>ស្លាប់<200>ទៅវិញ<200>ជា<200>មេចោរ<200></data> 775<data>•ឯ<200>ការ<200>វាយ<200>ផ្ចាល<200>ដែល<200>នាំ<200></data> 776<data>•គេ<200>ដឹក<200>ទៅ<200>សំឡាប់<200></data> 777#អ្នក|ដែល|ជា|មន្ត្រី|ធំ|លើ|គាត់|ទេ<200></data> 778<data>•យក<200>ទៅ<200>សម្លាប់ចោល<200>ស្ងាត់<200></data> 779<data>•ត្រូវ<200>បាន<200>គេ<200>សម្លាប់<200></data> 780<data>•នៅក្នុង<200>ស្រុក<200>ខ្ល<200>ងហ្ស៊ុន<200></data> 781 782 783# 784# Jitterbug 3671 Test Case 785# 786<data>•สวัสดี<200>ครับ<200>สบาย<200>ดี<200>ไหม<200> •ครับ<200></data> 787 788# 789# Trac ticket 5595 Test Case 790<data>•บท<200>ที่๑พายุ<200>ไซโคลน<200>โด<200>โรธี<200>อาศัย<200>อยู่<200>ท่ามกลาง<200>\ 791ทุ่งใหญ่<200>ใน<200>แคนซัส<200>กับ<200>ลุง<200>เฮ<200>นรี<200>ชาวไร่<200>และ<200>ป้า<200>เอ็ม<200>\ 792ภรรยา<200>ชาวไร่<200>บ้าน<200>ของ<200>พวก<200>เขา<200>หลัง<200>เล็ก<200>เพราะ<200>ไม้<200>\ 793สร้าง<200>บ้าน<200>ต้อง<200>ขน<200>มา<200>ด้วย<200>เกวียน<200>เป็น<200>ระยะ<200>ทาง<200>หลาย<200>\ 794ไมล์<200></data> 795 796#################################################################################### 797# 798# Tailored (locale specific) breaking. 799# 800#################################################################################### 801 802# Japanese line break tailoring test 803 804<locale ja> 805<line> 806<data>•\u3041•\u3043•\u3045•\u31f1•</data> 807<locale en> 808<line> 809<data>•\u3041\u3043\u3045\u31f1•</data> 810 811# The following data was originally in RBBITest::TestJapaneseWordBreak() 812<locale ja> 813<word> 814<data>•\u4ECA\u65E5<400>\u306F<400>\u3044\u3044<400>\u5929\u6C17<400>\u3067\u3059<400>\u306D<400>\u3002•\u000D\u000A•</data> 815 816# UBreakIteratorType UBRK_WORD, Locale "ja" 817# Don't break in runs of hiragana or runs of ideograph, where the latter includes \u3005 \u3007 \u303B (cldrbug #2009). 818# \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 819# modified to work with dbbi code - should verify 820 821<locale ja> 822<word> 823<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> 824 825# Test for #10176 (in ja) 826<line> 827<data>•abc/•s •def•</data> 828<data>•abc/\u05D9 •def•</data> 829<data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data> 830<data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05EA•</data> 831 832 833<locale root> 834<word> 835<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> 836# The following test is for #10300 837<data>•例えば<400>オーストラリア<400>。•</data> 838# The following test is for #10571 839<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> 840 841# UBreakIteratorType UBRK_SENTENCE, Locale "el" 842# Add break after Greek question mark (cldrbug #2069). 843# "\u0391\u03B2, \u03B3\u03B4; \u0395 \u03B6\u03B7\u037E \u0398 \u03B9\u03BA. " 844# "\u039B\u03BC \u03BD\u03BE! \u039F\u03C0, \u03A1\u03C2? \u03A3" 845# which is "Αβ, γδ; Ε ζη; Θ ικ. Λμ νξ! Οπ, Ρς? Σ" 846 847<locale root> 848<sent> 849<data>•Αβ, γδ; Ε ζη; Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data> 850 851<locale el> 852<sent> 853<data>•Αβ, γδ; •Ε ζη; •Θ ικ. •Λμ νξ! •Οπ, Ρς? •Σ<100></data> 854 855# UBreakIteratorType UBRK_WORD, Locale "en_US_POSIX" 856# Words don't include colon or period (cldrbug #1969). 857 858<locale en_US> 859<word> 860<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \ 861•for<200> •CS<200>-•types<200>.•</data> 862<data>•\uFF92\uFF76\uFF9E<400> •</data> 863 864<locale en_US_POSIX> 865<word> 866<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct<200>.•field<200> \ 867•for<200> •CS<200>-•types<200>.•</data> 868<data>•\u06c9<200>\uc799\ufffa•</data> 869<data>•\uFF92\uFF76\uFF9E<400> •</data> 870 871 872# UBreakIteratorType UBRK_CHARACTER, Locale "th" 873# Clusters should not include spacing Thai/Lao vowels (prefix or postfix), except for [SARA] AM (cldrbug #2161). 874# Update: As of Unicode 6.1 root has same behavior as th for this. 875# 876# "\u0E01\u0E23\u0E30\u0E17\u0E48\u0E2D\u0E21\u0E23\u0E08\u0E19\u0E32 " 877# "(\u0E2A\u0E38\u0E0A\u0E32\u0E15\u0E34-\u0E08\u0E38\u0E11\u0E32\u0E21\u0E32\u0E28) " 878# "\u0E40\u0E14\u0E47\u0E01\u0E21\u0E35\u0E1B\u0E31\u0E0D\u0E2B\u0E32 " 879# which is "กระท่อมรจนา (สุชาติ-จุฑามาศ) เด็กมีปัญหา " 880 881<locale th> 882<char> 883<data>•\u0E01•\u0E23•\u0E30•\u0E17\u0E48•\u0E2D•\u0E21•\u0E23•\u0E08•\u0E19•\u0E32• •\ 884(•\u0E2A\u0E38•\u0E0A•\u0E32•\u0E15\u0E34•-•\u0E08\u0E38•\u0E11•\u0E32•\u0E21•\u0E32•\u0E28•)• •\ 885\u0E40•\u0E14\u0E47•\u0E01•\u0E21\u0E35•\u0E1B\u0E31•\u0E0D•\u0E2B•\u0E32• •</data> 886 887# Finnish line breaking 888# 889# These rules deal with hyphens when there is a space on the leading side. 890# There should be a break opportunity between the space and the hyphen, and not after the hyphen. 891# See CLDR ticket 3029. 892# See ICU ticket 8151 893 894<locale root> 895<line> 896<data>•abc •- •def •abc •-•def •abc- •def •abc-•def•</data> # With ASCII hyphen 897<data>•abc •‐ •def •abc •‐•def •abc‐ •def •abc‐•def•</data> # With Unicode u2010 hyphen 898 899<locale fi> 900<line> 901# TODO: problems with Finnish line break rules cause these two lines to fail. 902#<data>•abc •- •def •abc •-def •abc- •def •abc-•def•</data> # With ASCII hyphen 903#<data>•abc •‐ •def •abc •‐def •abc‐ •def •abc‐•def•</data> # With Unicode u2010 hyphen 904 905<data>•abc •- •def •abc •-def •abc- •def •</data> # With ASCII hyphen 906<data>•abc •‐ •def •abc •‐def •abc‐ •def •</data> # With Unicode u2010 hyphen 907 908# Test for #10176 (in fi) 909<line> 910<data>•abc/•s •def•</data> 911<data>•abc/\u05D9 •def•</data> 912<data>•\u05E7\u05D7/\u05D9 •\u05DE\u05E2\u05D9\u05DC•</data> 913<data>•\u05D3\u05E8\u05D5\u05E9\u05D9\u05DD •\u05E9\u05D7\u05E7\u05E0\u05D9\u05DD/\u05D9\u05D5\u05EA•</data> 914 915#################################################################################### 916# 917# Test CSS line break variants: strict, normal, loose 918# 919#################################################################################### 920 921<locale ja@lb=strict> 922<line> 923# •no brk before 3063 •no brk before 301C•no brk btw 2026 •no brk before FF01• 924<data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 925 926<locale ja@lb=normal> 927<line> 928# •brk OK before 3063 •brk OK before 301C •no brk btw 2026 •no brk before FF01• 929<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 930 931<locale ja@lb=loose> 932<line> 933# •brk OK before 3063 •brk OK before 301C •brk OK btw 2026 •brk OK before FF01• 934<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031•\u301C\u0020•\u2026•\u2026\u0020•u30A2•\uFF01\u0020•</data> 935 936<locale en@lb=strict> 937<line> 938# •no brk before 3063 •no brk before 301C•no brk btw 2026 •no brk before FF01• 939<data>•\u3084\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 940 941<locale en@lb=normal> 942<line> 943# •brk OK before 3063 •no brk before 301C •no brk btw 2026 •no brk before FF01• 944<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026\u2026\u0020•\u30A2\uFF01\u0020•</data> 945 946<locale en@lb=loose> 947<line> 948# •brk OK before 3063 •no brk before 301C •brk OK btw 2026 •no brk before FF01• 949<data>•\u3084•\u3063•\u3071•\u308A\u0020•\u0031\u301C\u0020•\u2026•\u2026\u0020•u30A2\uFF01\u0020•</data> 950