1 <?xml version="1.0" encoding="UTF-8"?>
3 <!-- Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html -->
4 <!-- Copyright (c) 2007-2009 IBM Corporation and others. All rights reserved -->
6 <!-- Test data file for string search -->
7 <!DOCTYPE stringsearch-tests [
8 <!ELEMENT stringsearch-tests (test-case+)>
9 <!ATTLIST stringsearch-tests debug IDREF #IMPLIED >
10 <!ELEMENT test-case (pattern, pre?, m?, post?)>
14 strength (PRIMARY | SECONDARY | TERTIARY | QUATERNARY | IDENTICAL) "TERTIARY"
16 alternate_handling (NON_IGNORABLE | SHIFTED) "NON_IGNORABLE"
19 <!ELEMENT pattern (#PCDATA)>
20 <!ELEMENT pre (#PCDATA)>
21 <!ELEMENT m (#PCDATA)>
22 <!ELEMENT post (#PCDATA)>
26 <!-- debug="test11" (for copying into the above element) -->
28 <!-- Very simple match -->
29 <test-case id="test01" >
30 <pattern>abc</pattern>
31 <pre>xxx</pre><m>abc</m><post>yyy</post>
34 <!-- Very simple no-match -->
35 <test-case id="test02" >
36 <pattern>abc</pattern>
37 <pre>xxx</pre><post>yyy</post>
40 <!-- Match after several near-misses. -->
41 <test-case id="test03" >
42 <pattern>string</pattern>
43 <pre>silly spring stling strxng strilg strinx stri</pre><m>string</m><post> fling</post>
46 <test-case id="test04" strength="PRIMARY" >
47 <pattern>FUSS</pattern>
48 <pre>abc</pre><m>fuss</m><post>sss</post>
51 <test-case id="test05" strength="PRIMARY" >
52 <pattern>FUSS</pattern>
53 <pre>abc</pre><m>fuß</m><post>sss</post>
56 <test-case id="test05.5" strength="PRIMARY" >
57 <pattern>fuss</pattern>
60 <post>ball table</post>
63 <test-case id="test06" strength="PRIMARY" >
64 <pattern>fuß</pattern>
65 <pre>abc</pre><m>fuss</m><post>xyz</post>
68 <test-case id="test07" strength="SECONDARY" >
69 <pattern>fuß</pattern>
73 <test-case id="test08" strength="PRIMARY" >
74 <pattern>fus</pattern>
75 <pre>abcfuß</pre><post>xyz</post>
78 <!-- A good match following an initial match that failed because
79 of not ending on a character boundary -->
80 <test-case id="test09" strength="PRIMARY">
81 <pattern>fus</pattern>
82 <pre>fuß </pre><m>fus</m><post>sss</post>
86 <!-- Test cases from usrchdat.c BREAKITERATOREXACT -->
88 <test-case id="test10" strength="TERTIARY">
89 <pattern>fox</pattern>
90 <m>fox</m><post>y fox</post>
93 <test-case id="test11" strength="PRIMARY" locale="de_DE@collation=phonebook">
94 <pattern>toe</pattern>
95 <pre>This is a </pre><m>Tö</m><post>ne</post>
98 <test-case id="test11a" strength="SECONDARY" locale="de_DE@collation=phonebook">
99 <pattern>toe</pattern>
100 <pre>This is a </pre><post>Töne</post>
103 <test-case id="test12" strength="TERTIARY">
105 <pre>tésting that é doés not match </pre><m>e</m><post></post>
108 <test-case id="test13" strength="PRIMARY" locale="fr">
110 <pre></pre><m>É</m><post>É</post>
113 <test-case id="test14" strength="PRIMARY" locale="fr">
115 <pre>C</pre><m>O\u0302</m><post>TÉ</post>
119 <!-- Test cases from usrchdat.c STRENGTH -->
122 <test-case id="test15" strength="PRIMARY" locale="en">
123 <pattern>fox</pattern>
124 <pre>The quick brown </pre><m>fox</m><post> jumps over the lazy foxes</post>
127 <test-case id="test16" strength="PRIMARY" locale="fr">
128 <pattern>peche</pattern>
129 <pre>blackbirds pat </pre><m>p\u00E9ch\u00E9</m><post> </post>
132 <test-case id="test17" strength="PRIMARY" locale="fr">
133 <pattern>peche</pattern>
134 <pre>blackbirds pat </pre><m>p\u00EAche</m><post> </post>
137 <test-case id="test18" strength="PRIMARY" locale="fr">
138 <pattern>peche</pattern>
139 <pre>blackbirds pat </pre><m>p\u00E9che</m><post>r </post>
142 <test-case id="test19" strength="PRIMARY" locale="fr">
143 <pattern>peche</pattern>
144 <pre>blackbirds pat </pre><m>p\u00EAche</m><post>r </post>
147 <test-case id="test20" strength="PRIMARY" locale="es">
148 <pattern>channel</pattern>
149 <pre>A </pre><m>channel</m><post>, </post>
152 <test-case id="test21" strength="PRIMARY" locale="es">
153 <pattern>channel</pattern>
154 <pre>A </pre><m>CHANNEL</m><post>, </post>
157 <test-case id="test22" strength="PRIMARY" locale="es">
158 <pattern>channel</pattern>
159 <pre>A </pre><m>Channel</m><post>s, </post>
162 <test-case id="test23" strength="PRIMARY" locale="es">
163 <pattern>channel</pattern>
164 <pre>A </pre><m>channel</m><post>... </post>
167 <test-case id="test24" strength="TERTIARY" locale="en">
168 <pattern>A\u0300</pattern>
169 <pre>A miss, and then </pre><m>\u00c0</m><post> should match but not A"</post>
172 <!-- TODO: In the original test data, this test matched at IDENTICAL strength.
173 Doesn't seem right. The characters are different.
175 <test-case id="test24a" strength="IDENTICAL" locale="en">
176 <pattern>A\u0300</pattern>
177 <pre>At IDENTICAL, shoud this match? </pre><m>\u00c0</m><post></post>
180 <test-case id="test24b" strength="IDENTICAL" alternate_handling="SHIFTED" locale="en">
181 <pattern>A\u0300</pattern>
182 <pre>At IDENTICAL, shoud this match? </pre>
187 <test-case id="test25" strength="SECONDARY" locale="en">
189 <pre>12</pre><m>ű</m><post> Ű</post>
192 <test-case id="test26" strength="SECONDARY" locale="en">
194 <pre>12</pre><m>a</m><post>...</post>
198 <!-- Test Cases from usrchdat.c, VARIABLE -->
199 <test-case id="test27" strength="TERTIARY" locale="en">
200 <pattern>blackbird</pattern>
201 <pre>black-bird </pre><m>blackbird</m><post>...</post>
204 <test-case id="test28" strength="TERTIARY" locale="en">
205 <pattern>go</pattern>
209 <!-- TODO: this gives an U_ILLEGAL_ARGUMENT error when opening
210 the UStringSearch. How did the orignal test run? -->
212 <test-case id="test29" strength="PRIMARY" locale="en">
214 <pre></pre><m></m><post>abc</post>
218 <test-case id="test30" strength="SECONDARY" locale="en">
219 <pattern>abc</pattern>
220 <pre> a bc ab c a bc ab c"</pre>
223 <test-case id="test31" strength="SECONDARY" locale="en">
224 <pattern>abc</pattern>
225 <pre> ---------------</pre>
229 <!-- Normalization test cases from usrchdat.c -->
230 <test-case id="test32" strength="TERTIARY" norm="ON">
231 <pattern>a\u0325\u0300</pattern>
232 <pre></pre><m>a\u0300\u0325</m>
236 <test-case id="test32a" strength="TERTIARY" norm="OFF">
237 <pattern>a\u0325\u0300</pattern>
238 <pre>a\u0300\u0325</pre>
242 <!-- COMPOSITEBOUNDARIES from usrchdat.c
243 Boundaries are not identical to orignal test data because
244 of matching only full combining sequences
246 <test-case id="test40" strength="TERTIARY">
248 <pre>À</pre> <!-- \u00C0 -->
251 <test-case id="test41" strength="TERTIARY">
253 <pre>À</pre><m>A</m><post>C</post>
256 <test-case id="test42" strength="TERTIARY">
257 <pattern>A\u030A</pattern>
263 <!-- SUPPLEMENTARYCANONICAL from usrchdat.c -->
264 <test-case id="test50" strength="TERTIARY">
265 <pattern>\uD800\uDC00</pattern>
266 <pre>abc \uD802\uDC00 \uD800\uDC01 \uD801\uDC00 </pre><m>\uD800\uDC00</m>
267 <post>abc abc\uD800\uDC00 \uD800\uD800\uDC00 \uD800\uDC00\uDC00</post>
270 <test-case id="test51" strength="TERTIARY">
271 <pattern>\\uD834\\uDDB9</pattern>
272 <pre>and</pre><m>\\uD834\\uDDB9</m><post>this sentence</post>
275 <test-case id="test52" strength="TERTIARY">
276 <pattern> \\uD834\\uDDB9 </pattern>
277 <pre>and</pre><m> \\uD834\\uDDB9 </m><post>this sentence</post>
280 <test-case id="test53" strength="TERTIARY">
281 <pattern>-\\uD834\\uDDB9-</pattern>
282 <pre>and</pre><m>-\\uD834\\uDDB9-</m><post>this sentence</post>
285 <test-case id="test54" strength="TERTIARY">
286 <pattern>,\\uD834\\uDDB9,</pattern>
287 <pre>and</pre><m>,\\uD834\\uDDB9,</m><post>this sentence</post>
290 <test-case id="test55" strength="TERTIARY">
291 <pattern>?\\uD834\\uDDB9?</pattern>
292 <pre>and</pre><m>?\\uD834\\uDDB9?</m><post>this sentence</post>
296 <!-- Long combining sequences -->
297 <!-- Backwards search fails because patterns ends w/ ignorables
298 <test-case id="test60" strength="PRIMARY">
299 <pattern>A\u0301\u0301\u0301\u0301</pattern>
300 <m>A\u0301\u0301\u0301\u0301\u0301</m>
304 <test-case id="test61" strength="TERTIARY">
305 <pattern>A\u0301\u0301\u0301\u0301</pattern>
306 <pre>A\u0301\u0301\u0301\u0301\u0301</pre>
309 <test-case id="test62" strength="TERTIARY">
310 <pattern>A\u0301\u0301\u0301\u0301</pattern>
311 <m>A\u0301\u0301\u0301\u0301</m>
314 <!-- stand-alone combining marks don't match attached marks -->
315 <test-case id="test63" strength="TERTIARY">
316 <pattern>\u0301</pattern>
317 <pre>A\u0301\u0301\u0301\u0301</pre>
320 <test-case id="test64" strength="TERTIARY">
321 <pattern>\u0301</pattern>
322 <post>\u0301\u0301\u0301\u0301</post>
325 <!-- stand-alone combining mark does match an un-attached combining mark -->
326 <test-case id="test65" strength="TERTIARY">
327 <pattern>\u0301</pattern>
328 <m>\u0301</m><post>A\u0301\u0301</post>
331 <test-case id="test66" strength="TERTIARY">
332 <pattern>\u0301</pattern>
336 <!-- stand-alone combining marks at end of the target text -->
337 <test-case id="test67" strength="TERTIARY">
338 <pattern>\u0301</pattern>
339 <pre>abcd\r</pre><m>\u0301</m>
342 <!-- attached combining marks at end of the target text, no match -->
343 <test-case id="test68" strength="TERTIARY">
344 <pattern>\u0301</pattern>
345 <pre>abcd\u0301</pre>
350 <!-- no match within expansions at the start -->
351 <test-case id="test70" strength="PRIMARY">
352 <pattern>Eligature</pattern>
356 <test-case id="test71" strength="PRIMARY">
357 <pattern>AEligature</pattern>
361 <test-case id="test72" strength="PRIMARY">
362 <pattern>AEligature</pattern>
366 <!-- unattached combining Tilde will not match a Tilde that is
367 part of a composed Ñ (\u00D1) -->
368 <test-case id="test73" strength="SECONDARY">
369 <pattern>\u0303</pattern> <!-- combining tilde -->
370 <pre>Ñ
</pre><m>\u0303</m>
373 <test-case id="test74" strength="SECONDARY">
374 <pattern>\u0303</pattern> <!-- combining tilde -->
375 <pre>Ñ 
</pre><m>\u0303</m><post>a</post>
378 <test-case id="test75" strength="TERTIARY" locale="fr">
379 <pattern>\u00EA</pattern>
380 <pre>p</pre><m>\u00EA</m><post>che</post>
383 <test-case id="test76" strength="TERTIARY" locale="fr">
384 <pattern>\u00EA</pattern>
385 <pre>p</pre><m>e\u0302</m><post>che</post>
388 <test-case id="test77" strength="TERTIARY" locale="fr">
389 <pattern>e\u0302</pattern>
390 <pre>p</pre><m>\u00EA</m><post>che</post>
393 <!-- Test cases from ticket:5382 -->
394 <test-case id="test78" strength="SECONDARY" locale="hu_HU">
395 <pattern>\u0170</pattern>
400 <test-case id="test79" strength="SECONDARY" locale="hu_HU">
401 <pattern>\u0170</pattern>
407 <test-case id="test80" strength="SECONDARY" locale="hu_HU">
408 <pattern>\u0170</pattern>
413 <!-- Test cases from ticket:5959 -->
414 <test-case id="test81" strength="SECONDARY">
415 <pattern>\u2166</pattern>
419 <test-case id="test82" strength="SECONDARY">
420 <pattern>VII</pattern>
424 <test-case id="test83" strength="IDENTICAL" alternate_handling="SHIFTED" locale="en">
425 <pattern>Universal Declaration of Human Rights</pattern>
426 <pre>Proclaims this </pre><m>Universal Declaration of Human Rights</m><post> as a common standard of achievement for all peoples and all nations</post>
429 <test-case id="test83b" strength="TERTIARY" alternate_handling="SHIFTED" locale="en">
430 <pattern>Universal Declaration of Human Rights</pattern>
431 <pre>Proclaims this </pre>
432 <m>Universal-Declaration-of-Human-Rights</m>
433 <post> as a common standard of achievement for all peoples and all nations</post>
436 <test-case id="test84" strength="TERTIARY" locale="en">
437 <pattern>\u05E9\u0591\u05E9</pattern>
438 <m>\u05E9\u0592\u05E9</m>
441 <test-case id="test84b" strength="IDENTICAL" locale="en">
442 <pattern>\u05E9\u0591\u05E9</pattern>
443 <pre>\u05E9\u0592\u05E9</pre>
445 </stringsearch-tests>