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

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

<!-- Copyright (c) 2007-2009 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"
          alternate_handling (NON_IGNORABLE | SHIFTED) "NON_IGNORABLE"
          >

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

<stringsearch-tests>
  <!-- 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="test24b" strength="IDENTICAL" alternate_handling="SHIFTED" 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  -->
    <!-- Backwards search fails because patterns ends w/ ignorables
    <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>

  <test-case id="test83" strength="IDENTICAL" alternate_handling="SHIFTED" locale="en">
    <pattern>Universal Declaration of Human Rights</pattern>
    <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>
  </test-case>

  <test-case id="test83b" strength="TERTIARY" alternate_handling="SHIFTED" locale="en">
    <pattern>Universal Declaration of Human Rights</pattern>
    <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>
  </test-case>

  <test-case id="test84" strength="TERTIARY" locale="en">
    <pattern>\u05E9\u0591\u05E9</pattern>
    <m>\u05E9\u0592\u05E9</m>
  </test-case>

  <test-case id="test84b" strength="IDENTICAL" locale="en">
    <pattern>\u05E9\u0591\u05E9</pattern>
    <pre>\u05E9\u0592\u05E9</pre>
  </test-case>
</stringsearch-tests>
Commit	Line	Data
46f4442e A	1	<?xml version="1.0" encoding="UTF-8"?>
46f4442e A	2
729e4ab9	3	<!-- Copyright (c) 2007-2009 IBM Corporation and others. All rights reserved -->
46f4442e A	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"
729e4ab9	15	alternate_handling (NON_IGNORABLE \| SHIFTED) "NON_IGNORABLE"
46f4442e A	16	>
	17
	18	<!ELEMENT pattern (#PCDATA)>
	19	<!ELEMENT pre (#PCDATA)>
	20	<!ELEMENT m (#PCDATA)>
	21	<!ELEMENT post (#PCDATA)>
	22	]>
	23
729e4ab9	24	<stringsearch-tests>
46f4442e A	25	<!-- debug="test11" (for copying into the above element) -->
	26
	27	<!-- Very simple match -->
	28	<test-case id="test01" >
	29	<pattern>abc</pattern>
	30	<pre>xxx</pre><m>abc</m><post>yyy</post>
	31	</test-case>
	32
	33	<!-- Very simple no-match -->
	34	<test-case id="test02" >
	35	<pattern>abc</pattern>
	36	<pre>xxx</pre><post>yyy</post>
	37	</test-case>
	38
	39	<!-- Match after several near-misses. -->
	40	<test-case id="test03" >
	41	<pattern>string</pattern>
	42	<pre>silly spring stling strxng strilg strinx stri</pre><m>string</m><post> fling</post>
	43	</test-case>
	44
	45	<test-case id="test04" strength="PRIMARY" >
	46	<pattern>FUSS</pattern>
	47	<pre>abc</pre><m>fuss</m><post>sss</post>
	48	</test-case>
	49
	50	<test-case id="test05" strength="PRIMARY" >
	51	<pattern>FUSS</pattern>
	52	<pre>abc</pre><m>fuß</m><post>sss</post>
	53	</test-case>
	54
	55	<test-case id="test05.5" strength="PRIMARY" >
	56	<pattern>fuss</pattern>
	57	<pre>a </pre>
	58	<m>fuß</m>
	59	<post>ball table</post>
	60	</test-case>
	61
	62	<test-case id="test06" strength="PRIMARY" >
	63	<pattern>fuß</pattern>
	64	<pre>abc</pre><m>fuss</m><post>xyz</post>
	65	</test-case>
	66
	67	<test-case id="test07" strength="SECONDARY" >
	68	<pattern>fuß</pattern>
	69	<pre>abcfussxyz</pre>
	70	</test-case>
	71
	72	<test-case id="test08" strength="PRIMARY" >
	73	<pattern>fus</pattern>
	74	<pre>abcfuß</pre><post>xyz</post>
	75	</test-case>
	76
	77	<!-- A good match following an initial match that failed because
	78	of not ending on a character boundary -->
	79	<test-case id="test09" strength="PRIMARY">
	80	<pattern>fus</pattern>
	81	<pre>fuß </pre><m>fus</m><post>sss</post>
	82	</test-case>
	83
	84
	85	<!-- Test cases from usrchdat.c BREAKITERATOREXACT -->
	86
	87	<test-case id="test10" strength="TERTIARY">
	88	<pattern>fox</pattern>
89	<m>fox</m><post>y fox</post>
90	</test-case>
91
92	<test-case id="test11" strength="PRIMARY" locale="de_DE@collation=phonebook">
93	<pattern>toe</pattern>
94	<pre>This is a </pre><m>Tö</m><post>ne</post>
95	</test-case>
96
97	<test-case id="test11a" strength="SECONDARY" locale="de_DE@collation=phonebook">
98	<pattern>toe</pattern>
99	<pre>This is a </pre><post>Töne</post>
100	</test-case>
101
102	<test-case id="test12" strength="TERTIARY">
103	<pattern>e</pattern>
104	<pre>tésting that é doés not match </pre><m>e</m><post></post>
105	</test-case>
106
107	<test-case id="test13" strength="PRIMARY" locale="fr">
108	<pattern>e</pattern>
109	<pre></pre><m>É</m><post>É</post>
110	</test-case>
111
112	<test-case id="test14" strength="PRIMARY" locale="fr">
113	<pattern>O</pattern>
114	<pre>C</pre><m>O\u0302</m><post>TÉ</post>
115	</test-case>
116
117
118	<!-- Test cases from usrchdat.c STRENGTH -->
119
120
121	<test-case id="test15" strength="PRIMARY" locale="en">
122	<pattern>fox</pattern>
123	<pre>The quick brown </pre><m>fox</m><post> jumps over the lazy foxes</post>
124	</test-case>
125
126	<test-case id="test16" strength="PRIMARY" locale="fr">
127	<pattern>peche</pattern>
128	<pre>blackbirds pat </pre><m>p\u00E9ch\u00E9</m><post> </post>
129	</test-case>
130
131	<test-case id="test17" strength="PRIMARY" locale="fr">
132	<pattern>peche</pattern>
133	<pre>blackbirds pat </pre><m>p\u00EAche</m><post> </post>
134	</test-case>
135
136	<test-case id="test18" strength="PRIMARY" locale="fr">
137	<pattern>peche</pattern>
138	<pre>blackbirds pat </pre><m>p\u00E9che</m><post>r </post>
139	</test-case>
140
141	<test-case id="test19" strength="PRIMARY" locale="fr">
142	<pattern>peche</pattern>
143	<pre>blackbirds pat </pre><m>p\u00EAche</m><post>r </post>
144	</test-case>
145
146	<test-case id="test20" strength="PRIMARY" locale="es">
147	<pattern>channel</pattern>
148	<pre>A </pre><m>channel</m><post>, </post>
149	</test-case>
150
151	<test-case id="test21" strength="PRIMARY" locale="es">
152	<pattern>channel</pattern>
153	<pre>A </pre><m>CHANNEL</m><post>, </post>
154	</test-case>
155
156	<test-case id="test22" strength="PRIMARY" locale="es">
157	<pattern>channel</pattern>
158	<pre>A </pre><m>Channel</m><post>s, </post>
159	</test-case>
160
161	<test-case id="test23" strength="PRIMARY" locale="es">
162	<pattern>channel</pattern>
163	<pre>A </pre><m>channel</m><post>... </post>
164	</test-case>
165
166	<test-case id="test24" strength="TERTIARY" locale="en">
167	<pattern>A\u0300</pattern>
168	<pre>A miss, and then </pre><m>\u00c0</m><post> should match but not A"</post>
169	</test-case>
170
171	<!-- TODO: In the original test data, this test matched at IDENTICAL strength.
172	Doesn't seem right. The characters are different.
173	-->
174	<test-case id="test24a" strength="IDENTICAL" locale="en">
175	<pattern>A\u0300</pattern>
176	<pre>At IDENTICAL, shoud this match? </pre><m>\u00c0</m><post></post>
177	</test-case>
729e4ab9 A	178
	179	<test-case id="test24b" strength="IDENTICAL" alternate_handling="SHIFTED" locale="en">
	180	<pattern>A\u0300</pattern>
	181	<pre>At IDENTICAL, shoud this match? </pre>
	182	<m>\u00c0</m>
	183	<post></post>
	184	</test-case>
	185
	186	<test-case id="test25" strength="SECONDARY" locale="en">
46f4442e A	187	<pattern>Ű</pattern>
	188	<pre>12</pre><m>ű</m><post> Ű</post>
	189	</test-case>
	190
	191	<test-case id="test26" strength="SECONDARY" locale="en">
	192	<pattern>A</pattern>
	193	<pre>12</pre><m>a</m><post>...</post>
	194	</test-case>
	195
	196
	197	<!-- Test Cases from usrchdat.c, VARIABLE -->
	198	<test-case id="test27" strength="TERTIARY" locale="en">
	199	<pattern>blackbird</pattern>
	200	<pre>black-bird </pre><m>blackbird</m><post>...</post>
	201	</test-case>
	202
	203	<test-case id="test28" strength="TERTIARY" locale="en">
	204	<pattern>go</pattern>
	205	<pre> on</pre>
	206	</test-case>
	207
	208	<!-- TODO: this gives an U_ILLEGAL_ARGUMENT error when opening
	209	the UStringSearch. How did the orignal test run? -->
	210	<!--
	211	<test-case id="test29" strength="PRIMARY" locale="en">
	212	<pattern> </pattern>
	213	<pre></pre><m></m><post>abc</post>
	214	</test-case>
	215	-->
	216
	217	<test-case id="test30" strength="SECONDARY" locale="en">
	218	<pattern>abc</pattern>
	219	<pre> a bc ab c a bc ab c"</pre>
	220	</test-case>
	221
	222	<test-case id="test31" strength="SECONDARY" locale="en">
	223	<pattern>abc</pattern>
	224	<pre> ---------------</pre>
	225	</test-case>
	226
	227
	228	<!-- Normalization test cases from usrchdat.c -->
	229	<test-case id="test32" strength="TERTIARY" norm="ON">
	230	<pattern>a\u0325\u0300</pattern>
	231	<pre></pre><m>a\u0300\u0325</m>
	232	</test-case>
	233
	234
	235	<test-case id="test32a" strength="TERTIARY" norm="OFF">
	236	<pattern>a\u0325\u0300</pattern>
	237	<pre>a\u0300\u0325</pre>
	238	</test-case>
	239
	240
	241	<!-- COMPOSITEBOUNDARIES from usrchdat.c
	242	Boundaries are not identical to orignal test data because
	243	of matching only full combining sequences
	244	-->
	245	<test-case id="test40" strength="TERTIARY">
	246	<pattern>A</pattern>
	247	<pre>À</pre> <!-- \u00C0 -->
	248	</test-case>
	249
	250	<test-case id="test41" strength="TERTIARY">
251	<pattern>A</pattern>
252	<pre>À</pre><m>A</m><post>C</post>
253	</test-case>
254
255	<test-case id="test42" strength="TERTIARY">
256	<pattern>A\u030A</pattern>
257	<pre>À\u01FA</pre>
258	</test-case>
259
260
261
262	<!-- SUPPLEMENTARYCANONICAL from usrchdat.c -->
263	<test-case id="test50" strength="TERTIARY">
264	<pattern>\uD800\uDC00</pattern>
265	<pre>abc \uD802\uDC00 \uD800\uDC01 \uD801\uDC00 </pre><m>\uD800\uDC00</m>
266	<post>abc abc\uD800\uDC00 \uD800\uD800\uDC00 \uD800\uDC00\uDC00</post>
267	</test-case>
268
269	<test-case id="test51" strength="TERTIARY">
270	<pattern>\\uD834\\uDDB9</pattern>
271	<pre>and</pre><m>\\uD834\\uDDB9</m><post>this sentence</post>
272	</test-case>
273
274	<test-case id="test52" strength="TERTIARY">
275	<pattern> \\uD834\\uDDB9 </pattern>
276	<pre>and</pre><m> \\uD834\\uDDB9 </m><post>this sentence</post>
277	</test-case>
278
279	<test-case id="test53" strength="TERTIARY">
280	<pattern>-\\uD834\\uDDB9-</pattern>
281	<pre>and</pre><m>-\\uD834\\uDDB9-</m><post>this sentence</post>
282	</test-case>
283
284	<test-case id="test54" strength="TERTIARY">
285	<pattern>,\\uD834\\uDDB9,</pattern>
286	<pre>and</pre><m>,\\uD834\\uDDB9,</m><post>this sentence</post>
287	</test-case>
288
289	<test-case id="test55" strength="TERTIARY">
290	<pattern>?\\uD834\\uDDB9?</pattern>
291	<pre>and</pre><m>?\\uD834\\uDDB9?</m><post>this sentence</post>
292	</test-case>
293
294
295	<!-- Long combining sequences -->
729e4ab9	296	<!-- Backwards search fails because patterns ends w/ ignorables
46f4442e A	297	<test-case id="test60" strength="PRIMARY">
	298	<pattern>A\u0301\u0301\u0301\u0301</pattern>
	299	<m>A\u0301\u0301\u0301\u0301\u0301</m>
	300	</test-case>
729e4ab9 A	301	-->
729e4ab9 A	302
46f4442e A	303	<test-case id="test61" strength="TERTIARY">
	304	<pattern>A\u0301\u0301\u0301\u0301</pattern>
	305	<pre>A\u0301\u0301\u0301\u0301\u0301</pre>
	306	</test-case>
	307
	308	<test-case id="test62" strength="TERTIARY">
	309	<pattern>A\u0301\u0301\u0301\u0301</pattern>
	310	<m>A\u0301\u0301\u0301\u0301</m>
	311	</test-case>
	312
	313	<!-- stand-alone combining marks don't match attached marks -->
	314	<test-case id="test63" strength="TERTIARY">
	315	<pattern>\u0301</pattern>
	316	<pre>A\u0301\u0301\u0301\u0301</pre>
	317	</test-case>
	318
	319	<test-case id="test64" strength="TERTIARY">
	320	<pattern>\u0301</pattern>
	321	<post>\u0301\u0301\u0301\u0301</post>
	322	</test-case>
	323
	324	<!-- stand-alone combining mark does match an un-attached combining mark -->
	325	<test-case id="test65" strength="TERTIARY">
	326	<pattern>\u0301</pattern>
	327	<m>\u0301</m><post>A\u0301\u0301</post>
	328	</test-case>
	329
	330	<test-case id="test66" strength="TERTIARY">
	331	<pattern>\u0301</pattern>
	332	<m>\u0301</m>
	333	</test-case>
	334
	335	<!-- stand-alone combining marks at end of the target text -->
	336	<test-case id="test67" strength="TERTIARY">
	337	<pattern>\u0301</pattern>
	338	<pre>abcd\r</pre><m>\u0301</m>
	339	</test-case>
	340
	341	<!-- attached combining marks at end of the target text, no match -->
	342	<test-case id="test68" strength="TERTIARY">
	343	<pattern>\u0301</pattern>
	344	<pre>abcd\u0301</pre>
	345	</test-case>
	346
	347
	348
	349	<!-- no match within expansions at the start -->
	350	<test-case id="test70" strength="PRIMARY">
	351	<pattern>Eligature</pattern>
	352	<pre>Æligature</pre>
	353	</test-case>
	354
	355	<test-case id="test71" strength="PRIMARY">
	356	<pattern>AEligature</pattern>
	357	<m>Æligature</m>
	358	</test-case>
	359
	360	<test-case id="test72" strength="PRIMARY">
	361	<pattern>AEligature</pattern>
	362	<m>Æligature</m>
	363	</test-case>
	364
	365	<!-- unattached combining Tilde will not match a Tilde that is
	366	part of a composed Ñ (\u00D1) -->
367	<test-case id="test73" strength="SECONDARY">
368	<pattern>\u0303</pattern> <!-- combining tilde -->
369	<pre>Ñ </pre><m>\u0303</m>
370	</test-case>
371
372	<test-case id="test74" strength="SECONDARY">
373	<pattern>\u0303</pattern> <!-- combining tilde -->
374	<pre>Ñ </pre><m>\u0303</m><post>a</post>
375	</test-case>
376
377	<test-case id="test75" strength="TERTIARY" locale="fr">
378	<pattern>\u00EA</pattern>
379	<pre>p</pre><m>\u00EA</m><post>che</post>
380	</test-case>
381
382	<test-case id="test76" strength="TERTIARY" locale="fr">
383	<pattern>\u00EA</pattern>
384	<pre>p</pre><m>e\u0302</m><post>che</post>
385	</test-case>
386
387	<test-case id="test77" strength="TERTIARY" locale="fr">
388	<pattern>e\u0302</pattern>
389	<pre>p</pre><m>\u00EA</m><post>che</post>
390	</test-case>
391
392	<!-- Test cases from ticket:5382 -->
393	<test-case id="test78" strength="SECONDARY" locale="hu_HU">
394	<pattern>\u0170</pattern>
395	<m>\u0171</m>
396	<post>12</post>
397	</test-case>
398
399	<test-case id="test79" strength="SECONDARY" locale="hu_HU">
400	<pattern>\u0170</pattern>
401	<pre>1</pre>
402	<m>\u0171</m>
403	<post>2</post>
404	</test-case>
405
406	<test-case id="test80" strength="SECONDARY" locale="hu_HU">
407	<pattern>\u0170</pattern>
408	<pre>12</pre>
409	<m>\u0171</m>
410	</test-case>
411
412	<!-- Test cases from ticket:5959 -->
413	<test-case id="test81" strength="SECONDARY">
414	<pattern>\u2166</pattern>
415	<m>VII</m>
416	</test-case>
417
418	<test-case id="test82" strength="SECONDARY">
419	<pattern>VII</pattern>
420	<m>\u2166</m>
421	</test-case>
729e4ab9 A	422
	423	<test-case id="test83" strength="IDENTICAL" alternate_handling="SHIFTED" locale="en">
	424	<pattern>Universal Declaration of Human Rights</pattern>
	425	<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>
	426	</test-case>
	427
	428	<test-case id="test83b" strength="TERTIARY" alternate_handling="SHIFTED" locale="en">
	429	<pattern>Universal Declaration of Human Rights</pattern>
	430	<pre>Proclaims this </pre>
	431	<m>Universal-Declaration-of-Human-Rights</m>
	432	<post> as a common standard of achievement for all peoples and all nations</post>
	433	</test-case>
	434
	435	<test-case id="test84" strength="TERTIARY" locale="en">
	436	<pattern>\u05E9\u0591\u05E9</pattern>
	437	<m>\u05E9\u0592\u05E9</m>
	438	</test-case>
	439
	440	<test-case id="test84b" strength="IDENTICAL" locale="en">
	441	<pattern>\u05E9\u0591\u05E9</pattern>
	442	<pre>\u05E9\u0592\u05E9</pre>
	443	</test-case>
46f4442e A	444	</stringsearch-tests>
46f4442e A	445