[apple/icu.git] / icuSources / test / testdata / ssearch.xml

<?xml version="1.0" encoding="UTF-8"?>

<!-- Copyright (c) 2007-2008 IBM Corporation and others. All rights reserved -->

<!-- Test data file for string search  -->
<!DOCTYPE stringsearch-tests [
<!ELEMENT stringsearch-tests (test-case+)>
<!ATTLIST stringsearch-tests debug IDREF #IMPLIED >
<!ELEMENT test-case (pattern, pre?, m?, post?)>
<!ATTLIST test-case 
          id ID #REQUIRED
          locale CDATA "en" 
          strength (PRIMARY | SECONDARY | TERTIARY | QUATERNARY | IDENTICAL) "TERTIARY" 
          norm (ON | OFF) "OFF"
          >

<!ELEMENT pattern (#PCDATA)>
<!ELEMENT pre  (#PCDATA)>
<!ELEMENT m    (#PCDATA)>
<!ELEMENT post (#PCDATA)>
]>

<stringsearch-tests debug="test32">
  <!-- debug="test11"     (for copying into the above element)  -->
    
    <!-- Very simple match  -->
    <test-case id="test01" >
       <pattern>abc</pattern>
       <pre>xxx</pre><m>abc</m><post>yyy</post>
    </test-case>
    
    <!-- Very simple no-match  -->
    <test-case id="test02" >
       <pattern>abc</pattern>
       <pre>xxx</pre><post>yyy</post>
    </test-case>

    <!-- Match after several near-misses. -->
    <test-case id="test03" >
       <pattern>string</pattern>
       <pre>silly spring stling strxng strilg strinx stri</pre><m>string</m><post> fling</post>
    </test-case>
    
    <test-case id="test04" strength="PRIMARY" >
       <pattern>FUSS</pattern>
       <pre>abc</pre><m>fuss</m><post>sss</post>
    </test-case>
    
    <test-case id="test05" strength="PRIMARY" >
       <pattern>FUSS</pattern>
       <pre>abc</pre><m>fuß</m><post>sss</post>
    </test-case>

  <test-case id="test05.5" strength="PRIMARY" >
    <pattern>fuss</pattern>
    <pre>a </pre>
    <m>fuß</m>
    <post>ball table</post>
  </test-case>

  <test-case id="test06" strength="PRIMARY" >
      <pattern>fuß</pattern>
       <pre>abc</pre><m>fuss</m><post>xyz</post>
    </test-case>
    
    <test-case id="test07" strength="SECONDARY" >
      <pattern>fuß</pattern>
      <pre>abcfussxyz</pre>
    </test-case>
    
    <test-case id="test08" strength="PRIMARY" >
      <pattern>fus</pattern>
      <pre>abcfuß</pre><post>xyz</post>
    </test-case>
    
    <!-- A good match following an initial match that failed because
         of not ending on a character boundary -->
    <test-case id="test09" strength="PRIMARY">
      <pattern>fus</pattern>
      <pre>fuß  </pre><m>fus</m><post>sss</post>
    </test-case>


    <!-- Test cases from usrchdat.c  BREAKITERATOREXACT -->

    <test-case id="test10" strength="TERTIARY">
      <pattern>fox</pattern>
      <m>fox</m><post>y fox</post>
    </test-case>

    <test-case id="test11" strength="PRIMARY" locale="de_DE@collation=phonebook">
      <pattern>toe</pattern>
      <pre>This is a </pre><m>Tö</m><post>ne</post>
    </test-case>
    
    <test-case id="test11a" strength="SECONDARY" locale="de_DE@collation=phonebook">
      <pattern>toe</pattern>
      <pre>This is a </pre><post>Töne</post>
    </test-case>
    
    <test-case id="test12" strength="TERTIARY">
      <pattern>e</pattern>
      <pre>tésting that é doés not match </pre><m>e</m><post></post>
    </test-case>
    
    <test-case id="test13" strength="PRIMARY" locale="fr">
      <pattern>e</pattern>
      <pre></pre><m>É</m><post>É</post>
    </test-case>
    
    <test-case id="test14" strength="PRIMARY" locale="fr">
      <pattern>O</pattern>
      <pre>C</pre><m>O\u0302</m><post>TÉ</post>
    </test-case>


    <!-- Test cases from usrchdat.c  STRENGTH -->


    <test-case id="test15" strength="PRIMARY" locale="en">
      <pattern>fox</pattern>
      <pre>The quick brown </pre><m>fox</m><post> jumps over the lazy foxes</post>
    </test-case>
    
    <test-case id="test16" strength="PRIMARY" locale="fr">
      <pattern>peche</pattern>
      <pre>blackbirds pat </pre><m>p\u00E9ch\u00E9</m><post> </post>
    </test-case>
    
    <test-case id="test17" strength="PRIMARY" locale="fr">
      <pattern>peche</pattern>
      <pre>blackbirds pat </pre><m>p\u00EAche</m><post> </post>
    </test-case>
    
    <test-case id="test18" strength="PRIMARY" locale="fr">
      <pattern>peche</pattern>
      <pre>blackbirds pat </pre><m>p\u00E9che</m><post>r </post>
    </test-case>
    
    <test-case id="test19" strength="PRIMARY" locale="fr">
      <pattern>peche</pattern>
      <pre>blackbirds pat </pre><m>p\u00EAche</m><post>r </post>
    </test-case>
    
    <test-case id="test20" strength="PRIMARY" locale="es">
      <pattern>channel</pattern>
      <pre>A </pre><m>channel</m><post>, </post>
    </test-case>
    
    <test-case id="test21" strength="PRIMARY" locale="es">
      <pattern>channel</pattern>
      <pre>A </pre><m>CHANNEL</m><post>, </post>
    </test-case>
    
    <test-case id="test22" strength="PRIMARY" locale="es">
      <pattern>channel</pattern>
      <pre>A </pre><m>Channel</m><post>s, </post>
    </test-case>
    
    <test-case id="test23" strength="PRIMARY" locale="es">
      <pattern>channel</pattern>
      <pre>A </pre><m>channel</m><post>... </post>
    </test-case>
    
    <test-case id="test24" strength="TERTIARY" locale="en">
      <pattern>A\u0300</pattern>
      <pre>A miss, and then </pre><m>\u00c0</m><post> should match but not A"</post>
    </test-case>
    
    <!-- TODO:  In the original test data, this test matched at IDENTICAL strength.
                Doesn't seem right.  The characters are different.
                -->
    <test-case id="test24a" strength="IDENTICAL" locale="en">
      <pattern>A\u0300</pattern>
      <pre>At IDENTICAL, shoud this match?  </pre><m>\u00c0</m><post></post>
    </test-case>
    
    <test-case id="test25" strength="SECONDARY" locale="en">
      <pattern>Ű</pattern>
      <pre>12</pre><m>ű</m><post> Ű</post>
    </test-case>
    
    <test-case id="test26" strength="SECONDARY" locale="en">
      <pattern>A</pattern>
      <pre>12</pre><m>a</m><post>...</post>
    </test-case>


    <!--  Test Cases from usrchdat.c,  VARIABLE -->
    <test-case id="test27" strength="TERTIARY" locale="en">
      <pattern>blackbird</pattern>
      <pre>black-bird </pre><m>blackbird</m><post>...</post>
    </test-case>

    <test-case id="test28" strength="TERTIARY" locale="en">
      <pattern>go</pattern>
      <pre> on</pre>
    </test-case>

    <!-- TODO:  this gives an U_ILLEGAL_ARGUMENT error when opening
                the UStringSearch.  How did the orignal test run? -->
    <!--
    <test-case id="test29" strength="PRIMARY" locale="en">
      <pattern>  </pattern>
      <pre></pre><m></m><post>abc</post>
    </test-case>
    -->

    <test-case id="test30" strength="SECONDARY" locale="en">
      <pattern>abc</pattern>
      <pre>  a bc   ab c    a  bc     ab  c"</pre>
    </test-case>

    <test-case id="test31" strength="SECONDARY" locale="en">
      <pattern>abc</pattern>
      <pre>           ---------------</pre>
    </test-case>


    <!--  Normalization test cases from usrchdat.c  -->
    <test-case id="test32" strength="TERTIARY"  norm="ON">
      <pattern>a\u0325\u0300</pattern>
      <pre></pre><m>a\u0300\u0325</m>
    </test-case>


    <test-case id="test32a" strength="TERTIARY"  norm="OFF">
      <pattern>a\u0325\u0300</pattern>
      <pre>a\u0300\u0325</pre>
    </test-case>


    <!-- COMPOSITEBOUNDARIES from usrchdat.c
         Boundaries are not identical to orignal test data because
         of matching only full combining sequences
    -->
    <test-case id="test40" strength="TERTIARY">
      <pattern>A</pattern>
      <pre>À</pre>   <!-- \u00C0 -->
    </test-case>
    
    <test-case id="test41" strength="TERTIARY">
      <pattern>A</pattern>
      <pre>À</pre><m>A</m><post>C</post>
    </test-case>
    
    <test-case id="test42" strength="TERTIARY">
      <pattern>A\u030A</pattern>
      <pre>À\u01FA</pre>
    </test-case>


    <!-- SUPPLEMENTARYCANONICAL from usrchdat.c  -->
    <test-case id="test50" strength="TERTIARY">
      <pattern>\uD800\uDC00</pattern>
      <pre>abc \uD802\uDC00 \uD800\uDC01 \uD801\uDC00 </pre><m>\uD800\uDC00</m>
      <post>abc abc\uD800\uDC00 \uD800\uD800\uDC00 \uD800\uDC00\uDC00</post>
    </test-case>
    
    <test-case id="test51" strength="TERTIARY">
      <pattern>\\uD834\\uDDB9</pattern>
      <pre>and</pre><m>\\uD834\\uDDB9</m><post>this sentence</post>
    </test-case>

    <test-case id="test52" strength="TERTIARY">
      <pattern> \\uD834\\uDDB9 </pattern>
      <pre>and</pre><m> \\uD834\\uDDB9 </m><post>this sentence</post>
    </test-case>
    
    <test-case id="test53" strength="TERTIARY">
      <pattern>-\\uD834\\uDDB9-</pattern>
      <pre>and</pre><m>-\\uD834\\uDDB9-</m><post>this sentence</post>
    </test-case>
    
    <test-case id="test54" strength="TERTIARY">
      <pattern>,\\uD834\\uDDB9,</pattern>
      <pre>and</pre><m>,\\uD834\\uDDB9,</m><post>this sentence</post>
    </test-case>
    
    <test-case id="test55" strength="TERTIARY">
      <pattern>?\\uD834\\uDDB9?</pattern>
      <pre>and</pre><m>?\\uD834\\uDDB9?</m><post>this sentence</post>
    </test-case>
    

    <!-- Long combining sequences  -->
    <test-case id="test60" strength="PRIMARY">
      <pattern>A\u0301\u0301\u0301\u0301</pattern>
      <m>A\u0301\u0301\u0301\u0301\u0301</m>
    </test-case>
    
    <test-case id="test61" strength="TERTIARY">
      <pattern>A\u0301\u0301\u0301\u0301</pattern>
          <pre>A\u0301\u0301\u0301\u0301\u0301</pre>
    </test-case>
    
    <test-case id="test62" strength="TERTIARY">
      <pattern>A\u0301\u0301\u0301\u0301</pattern>
            <m>A\u0301\u0301\u0301\u0301</m>
    </test-case>

    <!-- stand-alone combining marks don't match attached marks  -->
    <test-case id="test63" strength="TERTIARY">
      <pattern>\u0301</pattern>
      <pre>A\u0301\u0301\u0301\u0301</pre>
    </test-case>
    
    <test-case id="test64" strength="TERTIARY">
      <pattern>\u0301</pattern>
      <post>\u0301\u0301\u0301\u0301</post>
    </test-case>

  <!-- stand-alone combining mark does match an un-attached combining mark -->
    <test-case id="test65" strength="TERTIARY">
       <pattern>\u0301</pattern>
       <m>\u0301</m><post>A\u0301\u0301</post>
    </test-case>

    <test-case id="test66" strength="TERTIARY">
       <pattern>\u0301</pattern>
       <m>\u0301</m>
    </test-case>
          
    <!-- stand-alone combining marks at end of the target text -->
    <test-case id="test67" strength="TERTIARY">
       <pattern>\u0301</pattern>
       <pre>abcd\r</pre><m>\u0301</m>
    </test-case>

      <!-- attached combining marks at end of the target text, no match -->
    <test-case id="test68" strength="TERTIARY">
       <pattern>\u0301</pattern>
       <pre>abcd\u0301</pre>
    </test-case>


   <!-- no match within expansions at the start -->
    <test-case id="test70" strength="PRIMARY">
      <pattern>Eligature</pattern>
      <pre>Æligature</pre>
    </test-case>

    <test-case id="test71" strength="PRIMARY">
      <pattern>AEligature</pattern>
      <m>Æligature</m>
    </test-case>

    <test-case id="test72" strength="PRIMARY">
        <pattern>AEligature</pattern>
        <m>Æligature</m>
    </test-case>
    
    <!-- unattached combining Tilde will not match a Tilde that is
         part of a composed Ñ  (\u00D1)  -->
    <test-case id="test73" strength="SECONDARY">
        <pattern>\u0303</pattern>  <!-- combining tilde -->
        <pre>Ñ&#x0d;</pre><m>\u0303</m>
    </test-case>
    
    <test-case id="test74" strength="SECONDARY">
        <pattern>\u0303</pattern>  <!-- combining tilde -->
        <pre>Ñ &#x0d;</pre><m>\u0303</m><post>a</post>
    </test-case>

  <test-case id="test75" strength="TERTIARY" locale="fr">
    <pattern>\u00EA</pattern>
    <pre>p</pre><m>\u00EA</m><post>che</post>
  </test-case>

  <test-case id="test76" strength="TERTIARY" locale="fr">
    <pattern>\u00EA</pattern>
    <pre>p</pre><m>e\u0302</m><post>che</post>
  </test-case>

  <test-case id="test77" strength="TERTIARY" locale="fr">
    <pattern>e\u0302</pattern>
    <pre>p</pre><m>\u00EA</m><post>che</post>
  </test-case>

  <!-- Test cases from ticket:5382 -->
  <test-case id="test78" strength="SECONDARY" locale="hu_HU">
    <pattern>\u0170</pattern>
    <m>\u0171</m>
    <post>12</post>
  </test-case>

  <test-case id="test79" strength="SECONDARY" locale="hu_HU">
    <pattern>\u0170</pattern>
    <pre>1</pre>
    <m>\u0171</m>
    <post>2</post>
  </test-case>

  <test-case id="test80" strength="SECONDARY" locale="hu_HU">
    <pattern>\u0170</pattern>
    <pre>12</pre>
    <m>\u0171</m>
  </test-case>
  
  <!-- Test cases from ticket:5959 -->
  <test-case id="test81" strength="SECONDARY">
    <pattern>\u2166</pattern>
    <m>VII</m>
  </test-case>

  <test-case id="test82" strength="SECONDARY">
    <pattern>VII</pattern>
    <m>\u2166</m>
  </test-case>
</stringsearch-tests>
Commit	Line	Data
46f4442e A	1	<?xml version="1.0" encoding="UTF-8"?>
	2
	3	<!-- Copyright (c) 2007-2008 IBM Corporation and others. All rights reserved -->
	4
	5	<!-- Test data file for string search -->
	6	<!DOCTYPE stringsearch-tests [
	7	<!ELEMENT stringsearch-tests (test-case+)>
	8	<!ATTLIST stringsearch-tests debug IDREF #IMPLIED >
	9	<!ELEMENT test-case (pattern, pre?, m?, post?)>
	10	<!ATTLIST test-case
	11	id ID #REQUIRED
	12	locale CDATA "en"
	13	strength (PRIMARY \| SECONDARY \| TERTIARY \| QUATERNARY \| IDENTICAL) "TERTIARY"
	14	norm (ON \| OFF) "OFF"
	15	>
	16
	17	<!ELEMENT pattern (#PCDATA)>
	18	<!ELEMENT pre (#PCDATA)>
	19	<!ELEMENT m (#PCDATA)>
	20	<!ELEMENT post (#PCDATA)>
	21	]>
	22
	23	<stringsearch-tests debug="test32">
	24	<!-- debug="test11" (for copying into the above element) -->
	25
	26	<!-- Very simple match -->
	27	<test-case id="test01" >
	28	<pattern>abc</pattern>
	29	<pre>xxx</pre><m>abc</m><post>yyy</post>
	30	</test-case>
	31
	32	<!-- Very simple no-match -->
	33	<test-case id="test02" >
	34	<pattern>abc</pattern>
	35	<pre>xxx</pre><post>yyy</post>
	36	</test-case>
	37
	38	<!-- Match after several near-misses. -->
	39	<test-case id="test03" >
	40	<pattern>string</pattern>
	41	<pre>silly spring stling strxng strilg strinx stri</pre><m>string</m><post> fling</post>
	42	</test-case>
	43
	44	<test-case id="test04" strength="PRIMARY" >
	45	<pattern>FUSS</pattern>
	46	<pre>abc</pre><m>fuss</m><post>sss</post>
	47	</test-case>
	48
	49	<test-case id="test05" strength="PRIMARY" >
	50	<pattern>FUSS</pattern>
	51	<pre>abc</pre><m>fuß</m><post>sss</post>
	52	</test-case>
	53
	54	<test-case id="test05.5" strength="PRIMARY" >
	55	<pattern>fuss</pattern>
	56	<pre>a </pre>
	57	<m>fuß</m>
	58	<post>ball table</post>
	59	</test-case>
	60
	61	<test-case id="test06" strength="PRIMARY" >
	62	<pattern>fuß</pattern>
	63	<pre>abc</pre><m>fuss</m><post>xyz</post>
	64	</test-case>
65
66	<test-case id="test07" strength="SECONDARY" >
67	<pattern>fuß</pattern>
68	<pre>abcfussxyz</pre>
69	</test-case>
70
71	<test-case id="test08" strength="PRIMARY" >
72	<pattern>fus</pattern>
73	<pre>abcfuß</pre><post>xyz</post>
74	</test-case>
75
76	<!-- A good match following an initial match that failed because
77	of not ending on a character boundary -->
78	<test-case id="test09" strength="PRIMARY">
79	<pattern>fus</pattern>
80	<pre>fuß </pre><m>fus</m><post>sss</post>
81	</test-case>
82
83
84	<!-- Test cases from usrchdat.c BREAKITERATOREXACT -->
85
86	<test-case id="test10" strength="TERTIARY">
87	<pattern>fox</pattern>
88	<m>fox</m><post>y fox</post>
89	</test-case>
90
91	<test-case id="test11" strength="PRIMARY" locale="de_DE@collation=phonebook">
92	<pattern>toe</pattern>
93	<pre>This is a </pre><m>Tö</m><post>ne</post>
94	</test-case>
95
96	<test-case id="test11a" strength="SECONDARY" locale="de_DE@collation=phonebook">
97	<pattern>toe</pattern>
98	<pre>This is a </pre><post>Töne</post>
99	</test-case>
100
101	<test-case id="test12" strength="TERTIARY">
102	<pattern>e</pattern>
103	<pre>tésting that é doés not match </pre><m>e</m><post></post>
104	</test-case>
105
106	<test-case id="test13" strength="PRIMARY" locale="fr">
107	<pattern>e</pattern>
108	<pre></pre><m>É</m><post>É</post>
109	</test-case>
110
111	<test-case id="test14" strength="PRIMARY" locale="fr">
112	<pattern>O</pattern>
113	<pre>C</pre><m>O\u0302</m><post>TÉ</post>
114	</test-case>
115
116
117	<!-- Test cases from usrchdat.c STRENGTH -->
118
119
120	<test-case id="test15" strength="PRIMARY" locale="en">
121	<pattern>fox</pattern>
122	<pre>The quick brown </pre><m>fox</m><post> jumps over the lazy foxes</post>
123	</test-case>
124
125	<test-case id="test16" strength="PRIMARY" locale="fr">
126	<pattern>peche</pattern>
127	<pre>blackbirds pat </pre><m>p\u00E9ch\u00E9</m><post> </post>
128	</test-case>
129
130	<test-case id="test17" strength="PRIMARY" locale="fr">
131	<pattern>peche</pattern>
132	<pre>blackbirds pat </pre><m>p\u00EAche</m><post> </post>
133	</test-case>
134
135	<test-case id="test18" strength="PRIMARY" locale="fr">
136	<pattern>peche</pattern>
137	<pre>blackbirds pat </pre><m>p\u00E9che</m><post>r </post>
138	</test-case>
139
140	<test-case id="test19" strength="PRIMARY" locale="fr">
141	<pattern>peche</pattern>
142	<pre>blackbirds pat </pre><m>p\u00EAche</m><post>r </post>
143	</test-case>
144
145	<test-case id="test20" strength="PRIMARY" locale="es">
146	<pattern>channel</pattern>
147	<pre>A </pre><m>channel</m><post>, </post>
148	</test-case>
149
150	<test-case id="test21" strength="PRIMARY" locale="es">
151	<pattern>channel</pattern>
152	<pre>A </pre><m>CHANNEL</m><post>, </post>
153	</test-case>
154
155	<test-case id="test22" strength="PRIMARY" locale="es">
156	<pattern>channel</pattern>
157	<pre>A </pre><m>Channel</m><post>s, </post>
158	</test-case>
159
160	<test-case id="test23" strength="PRIMARY" locale="es">
161	<pattern>channel</pattern>
162	<pre>A </pre><m>channel</m><post>... </post>
163	</test-case>
164
165	<test-case id="test24" strength="TERTIARY" locale="en">
166	<pattern>A\u0300</pattern>
167	<pre>A miss, and then </pre><m>\u00c0</m><post> should match but not A"</post>
168	</test-case>
169
170	<!-- TODO: In the original test data, this test matched at IDENTICAL strength.
171	Doesn't seem right. The characters are different.
172	-->
173	<test-case id="test24a" strength="IDENTICAL" locale="en">
174	<pattern>A\u0300</pattern>
175	<pre>At IDENTICAL, shoud this match? </pre><m>\u00c0</m><post></post>
176	</test-case>
177
178	<test-case id="test25" strength="SECONDARY" locale="en">
179	<pattern>Ű</pattern>
180	<pre>12</pre><m>ű</m><post> Ű</post>
181	</test-case>
182
183	<test-case id="test26" strength="SECONDARY" locale="en">
184	<pattern>A</pattern>
185	<pre>12</pre><m>a</m><post>...</post>
186	</test-case>
187
188
189	<!-- Test Cases from usrchdat.c, VARIABLE -->
190	<test-case id="test27" strength="TERTIARY" locale="en">
191	<pattern>blackbird</pattern>
192	<pre>black-bird </pre><m>blackbird</m><post>...</post>
193	</test-case>
194
195	<test-case id="test28" strength="TERTIARY" locale="en">
196	<pattern>go</pattern>
197	<pre> on</pre>
198	</test-case>
199
200	<!-- TODO: this gives an U_ILLEGAL_ARGUMENT error when opening
201	the UStringSearch. How did the orignal test run? -->
202	<!--
203	<test-case id="test29" strength="PRIMARY" locale="en">
204	<pattern> </pattern>
205	<pre></pre><m></m><post>abc</post>
206	</test-case>
207	-->
208
209	<test-case id="test30" strength="SECONDARY" locale="en">
210	<pattern>abc</pattern>
211	<pre> a bc ab c a bc ab c"</pre>
212	</test-case>
213
214	<test-case id="test31" strength="SECONDARY" locale="en">
215	<pattern>abc</pattern>
216	<pre> ---------------</pre>
217	</test-case>
218
219
220	<!-- Normalization test cases from usrchdat.c -->
221	<test-case id="test32" strength="TERTIARY" norm="ON">
222	<pattern>a\u0325\u0300</pattern>
223	<pre></pre><m>a\u0300\u0325</m>
224	</test-case>
225
226
227	<test-case id="test32a" strength="TERTIARY" norm="OFF">
228	<pattern>a\u0325\u0300</pattern>
229	<pre>a\u0300\u0325</pre>
230	</test-case>
231
232
233	<!-- COMPOSITEBOUNDARIES from usrchdat.c
234	Boundaries are not identical to orignal test data because
235	of matching only full combining sequences
236	-->
237	<test-case id="test40" strength="TERTIARY">
238	<pattern>A</pattern>
239	<pre>À</pre> <!-- \u00C0 -->
240	</test-case>
241
242	<test-case id="test41" strength="TERTIARY">
243	<pattern>A</pattern>
244	<pre>À</pre><m>A</m><post>C</post>
245	</test-case>
246
247	<test-case id="test42" strength="TERTIARY">
248	<pattern>A\u030A</pattern>
249	<pre>À\u01FA</pre>
250	</test-case>
251
252
253
254	<!-- SUPPLEMENTARYCANONICAL from usrchdat.c -->
255	<test-case id="test50" strength="TERTIARY">
256	<pattern>\uD800\uDC00</pattern>
257	<pre>abc \uD802\uDC00 \uD800\uDC01 \uD801\uDC00 </pre><m>\uD800\uDC00</m>
258	<post>abc abc\uD800\uDC00 \uD800\uD800\uDC00 \uD800\uDC00\uDC00</post>
259	</test-case>
260
261	<test-case id="test51" strength="TERTIARY">
262	<pattern>\\uD834\\uDDB9</pattern>
263	<pre>and</pre><m>\\uD834\\uDDB9</m><post>this sentence</post>
264	</test-case>
265
266	<test-case id="test52" strength="TERTIARY">
267	<pattern> \\uD834\\uDDB9 </pattern>
268	<pre>and</pre><m> \\uD834\\uDDB9 </m><post>this sentence</post>
269	</test-case>
270
271	<test-case id="test53" strength="TERTIARY">
272	<pattern>-\\uD834\\uDDB9-</pattern>
273	<pre>and</pre><m>-\\uD834\\uDDB9-</m><post>this sentence</post>
274	</test-case>
275
276	<test-case id="test54" strength="TERTIARY">
277	<pattern>,\\uD834\\uDDB9,</pattern>
278	<pre>and</pre><m>,\\uD834\\uDDB9,</m><post>this sentence</post>
279	</test-case>
280
281	<test-case id="test55" strength="TERTIARY">
282	<pattern>?\\uD834\\uDDB9?</pattern>
283	<pre>and</pre><m>?\\uD834\\uDDB9?</m><post>this sentence</post>
284	</test-case>
285
286
287	<!-- Long combining sequences -->
288	<test-case id="test60" strength="PRIMARY">
289	<pattern>A\u0301\u0301\u0301\u0301</pattern>
290	<m>A\u0301\u0301\u0301\u0301\u0301</m>
291	</test-case>
292
293	<test-case id="test61" strength="TERTIARY">
294	<pattern>A\u0301\u0301\u0301\u0301</pattern>
295	<pre>A\u0301\u0301\u0301\u0301\u0301</pre>
296	</test-case>
297
298	<test-case id="test62" strength="TERTIARY">
299	<pattern>A\u0301\u0301\u0301\u0301</pattern>
300	<m>A\u0301\u0301\u0301\u0301</m>
301	</test-case>
302
303	<!-- stand-alone combining marks don't match attached marks -->
304	<test-case id="test63" strength="TERTIARY">
305	<pattern>\u0301</pattern>
306	<pre>A\u0301\u0301\u0301\u0301</pre>
307	</test-case>
308
309	<test-case id="test64" strength="TERTIARY">
310	<pattern>\u0301</pattern>
311	<post>\u0301\u0301\u0301\u0301</post>
312	</test-case>
313
314	<!-- stand-alone combining mark does match an un-attached combining mark -->
315	<test-case id="test65" strength="TERTIARY">
316	<pattern>\u0301</pattern>
317	<m>\u0301</m><post>A\u0301\u0301</post>
318	</test-case>
319
320	<test-case id="test66" strength="TERTIARY">
321	<pattern>\u0301</pattern>
322	<m>\u0301</m>
323	</test-case>
324
325	<!-- stand-alone combining marks at end of the target text -->
326	<test-case id="test67" strength="TERTIARY">
327	<pattern>\u0301</pattern>
328	<pre>abcd\r</pre><m>\u0301</m>
329	</test-case>
330
331	<!-- attached combining marks at end of the target text, no match -->
332	<test-case id="test68" strength="TERTIARY">
333	<pattern>\u0301</pattern>
334	<pre>abcd\u0301</pre>
335	</test-case>
336
337
338
339	<!-- no match within expansions at the start -->
340	<test-case id="test70" strength="PRIMARY">
341	<pattern>Eligature</pattern>
342	<pre>Æligature</pre>
343	</test-case>
344
345	<test-case id="test71" strength="PRIMARY">
346	<pattern>AEligature</pattern>
347	<m>Æligature</m>
348	</test-case>
349
350	<test-case id="test72" strength="PRIMARY">
351	<pattern>AEligature</pattern>
352	<m>Æligature</m>
353	</test-case>
354
355	<!-- unattached combining Tilde will not match a Tilde that is
356	part of a composed Ñ (\u00D1) -->
357	<test-case id="test73" strength="SECONDARY">
358	<pattern>\u0303</pattern> <!-- combining tilde -->
359	<pre>Ñ </pre><m>\u0303</m>
360	</test-case>
361
362	<test-case id="test74" strength="SECONDARY">
363	<pattern>\u0303</pattern> <!-- combining tilde -->
364	<pre>Ñ </pre><m>\u0303</m><post>a</post>
365	</test-case>
366
367	<test-case id="test75" strength="TERTIARY" locale="fr">
368	<pattern>\u00EA</pattern>
369	<pre>p</pre><m>\u00EA</m><post>che</post>
370	</test-case>
371
372	<test-case id="test76" strength="TERTIARY" locale="fr">
373	<pattern>\u00EA</pattern>
374	<pre>p</pre><m>e\u0302</m><post>che</post>
375	</test-case>
376
377	<test-case id="test77" strength="TERTIARY" locale="fr">
378	<pattern>e\u0302</pattern>
379	<pre>p</pre><m>\u00EA</m><post>che</post>
380	</test-case>
381
382	<!-- Test cases from ticket:5382 -->
383	<test-case id="test78" strength="SECONDARY" locale="hu_HU">
384	<pattern>\u0170</pattern>
385	<m>\u0171</m>
386	<post>12</post>
387	</test-case>
388
389	<test-case id="test79" strength="SECONDARY" locale="hu_HU">
390	<pattern>\u0170</pattern>
391	<pre>1</pre>
392	<m>\u0171</m>
393	<post>2</post>
394	</test-case>
395
396	<test-case id="test80" strength="SECONDARY" locale="hu_HU">
397	<pattern>\u0170</pattern>
398	<pre>12</pre>
399	<m>\u0171</m>
400	</test-case>
401
402	<!-- Test cases from ticket:5959 -->
403	<test-case id="test81" strength="SECONDARY">
404	<pattern>\u2166</pattern>
405	<m>VII</m>
406	</test-case>
407
408	<test-case id="test82" strength="SECONDARY">
409	<pattern>VII</pattern>
410	<m>\u2166</m>
411	</test-case>
412	</stringsearch-tests>
413