1 /********************************************************************
2 * COPYRIGHT:
3 * Copyright (c) 1997-2009, International Business Machines Corporation and
4 * others. All Rights Reserved.
5 ********************************************************************/
6 /********************************************************************************
7 *
8 * File encoll.C
9 *
10 * Modification History:
11 * Name Description
12 * Madhu Katragadda Ported for C API
13 *********************************************************************************/
14 /**
15 * CollationEnglishTest is a third level test class. This tests the locale
16 * specific primary, secondary and tertiary rules. For example, the ignorable
17 * character '-' in string "black-bird". The en_US locale uses the default
18 * collation rules as its sorting sequence.
19 */
20
21 #include <stdlib.h>
22 #include <string.h>
23
24 #include "unicode/utypes.h"
25
26 #if !UCONFIG_NO_COLLATION
27
28 #include "unicode/ucol.h"
29 #include "unicode/uloc.h"
30 #include "cintltst.h"
31 #include "encoll.h"
32 #include "ccolltst.h"
33 #include "callcoll.h"
34 #include "unicode/ustring.h"
35
36 static UCollator *myCollation = NULL;
37 const static UChar testSourceCases[][MAX_TOKEN_LEN] = {
38 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, 0},
39 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x002D /* '-' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
40 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x0020 /* ' ' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
41 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x002D /* '-' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
42 {(UChar)0x0048 /* 'H' */, (UChar)0x0065 /* 'e' */, (UChar)0x006C /* 'l' */, (UChar)0x006C /* 'l' */, (UChar)0x006F /* 'o' */, 0},
43 {(UChar)0x0041 /* 'A' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
44 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
45 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
46 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x002D /* '-' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
47 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x002D /* '-' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
48 {(UChar)0x0070 /* 'p' */, 0x00EA, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, 0},
49 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0},
50 {0x00C4, (UChar)0x0042 /* 'B' */, 0x0308, (UChar)0x0043 /* 'C' */, 0x0308, 0},
51 {(UChar)0x0061 /* 'a' */, 0x0308, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
52 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, (UChar)0x0072 /* 'r' */, 0},
53 {(UChar)0x0072 /* 'r' */, (UChar)0x006F /* 'o' */, (UChar)0x006C /* 'l' */, (UChar)0x0065 /* 'e' */, (UChar)0x0073 /* 's' */, 0},
54 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
55 {(UChar)0x0041 /* 'A' */, 0},
56 {(UChar)0x0041 /* 'A' */, 0},
57 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, 0},
58 {(UChar)0x0074 /* 't' */, (UChar)0x0063 /* 'c' */, (UChar)0x006F /* 'o' */, (UChar)0x006D /* 'm' */, (UChar)0x0070 /* 'p' */, (UChar)0x0061 /* 'a' */, (UChar)0x0072 /* 'r' */, (UChar)0x0065 /* 'e' */, (UChar)0x0070 /* 'p' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0069 /* 'i' */, (UChar)0x006E /* 'n' */, 0},
59 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, 0},
60 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0062 /* 'b' */, 0},
61 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0062 /* 'b' */, 0},
62 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
63 {(UChar)0x0041 /* 'A' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
64 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
65 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
66 {0x00E6, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
67 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
68 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
69 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
70 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
71 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
72 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
73 {(UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x0048 /* 'H' */, (UChar)0x0063 /* 'c' */, 0},
74 {(UChar)0x0061 /* 'a' */, 0x0308, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
75 {(UChar)0x0074 /* 't' */, (UChar)0x0068 /* 'h' */, (UChar)0x0069 /* 'i' */, 0x0302, (UChar)0x0073 /* 's' */, 0},
76 {(UChar)0x0070 /* 'p' */, 0x00EA, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */},
77 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
78 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
79 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
80 {(UChar)0x0061 /* 'a' */, 0x00E6, (UChar)0x0063 /* 'c' */, 0},
81 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
82 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
83 {(UChar)0x0061 /* 'a' */, 0x00E6, (UChar)0x0063 /* 'c' */, 0},
84 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
85 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
86 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0}
87 };
88
89 const static UChar testTargetCases[][MAX_TOKEN_LEN] = {
90 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
91 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
92 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x002D /* '-' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
93 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, 0},
94 {(UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, (UChar)0x006C /* 'l' */, (UChar)0x006C /* 'l' */, (UChar)0x006F /* 'o' */, 0},
95 {(UChar)0x0041 /* 'A' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
96 {(UChar)0x0041 /* 'A' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
97 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, (UChar)0x0073 /* 's' */, 0},
98 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, (UChar)0x0073 /* 's' */, 0},
99 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, (UChar)0x0062 /* 'b' */, (UChar)0x0069 /* 'i' */, (UChar)0x0072 /* 'r' */, (UChar)0x0064 /* 'd' */, 0},
100 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0},
101 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, (UChar)0x0072 /* 'r' */, 0},
102 {0x00C4, (UChar)0x0042 /* 'B' */, 0x0308, (UChar)0x0043 /* 'C' */, 0x0308, 0},
103 {(UChar)0x0041 /* 'A' */, 0x0308, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
104 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, 0},
105 {(UChar)0x0072 /* 'r' */, (UChar)0x006F /* 'o' */, 0x0302, (UChar)0x006C /* 'l' */, (UChar)0x0065 /* 'e' */, 0},
106 {(UChar)0x0041 /* 'A' */, 0x00E1, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, 0},
107 {(UChar)0x0041 /* 'A' */, 0x00E1, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, 0},
108 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
109 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
110 {(UChar)0x0054 /* 'T' */, (UChar)0x0043 /* 'C' */, (UChar)0x006F /* 'o' */, (UChar)0x006D /* 'm' */, (UChar)0x0070 /* 'p' */, (UChar)0x0061 /* 'a' */, (UChar)0x0072 /* 'r' */, (UChar)0x0065 /* 'e' */, (UChar)0x0050 /* 'P' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0069 /* 'i' */, (UChar)0x006E /* 'n' */, 0},
111 {(UChar)0x0061 /* 'a' */, (UChar)0x0042 /* 'B' */, (UChar)0x0063 /* 'c' */, 0},
112 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0042 /* 'B' */, 0},
113 {(UChar)0x0061 /* 'a' */, (UChar)0x0026 /* '&' */, (UChar)0x0062 /* 'b' */, 0},
114 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0063 /* 'c' */, 0},
115 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
116 {0x00C4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
117 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
118 {0x00C4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
119 {0x00C4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
120 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0023 /* '#' */, (UChar)0x0063 /* 'c' */, 0},
121 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
122 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x003D /* '=' */, (UChar)0x0063 /* 'c' */, 0},
123 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0064 /* 'd' */, 0},
124 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
125 {(UChar)0x0061 /* 'a' */, (UChar)0x0043 /* 'C' */, (UChar)0x0048 /* 'H' */, (UChar)0x0063 /* 'c' */, 0},
126 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
127 {(UChar)0x0074 /* 't' */, (UChar)0x0068 /* 'h' */, 0x00EE, (UChar)0x0073 /* 's' */, 0},
128 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0},
129 {(UChar)0x0061 /* 'a' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
130 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0064 /* 'd' */, 0},
131 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
132 {(UChar)0x0061 /* 'a' */, 0x00C6, (UChar)0x0063 /* 'c' */, 0},
133 {(UChar)0x0061 /* 'a' */, (UChar)0x0042 /* 'B' */, (UChar)0x0064 /* 'd' */, 0},
134 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
135 {(UChar)0x0061 /* 'a' */, 0x00C6, (UChar)0x0063 /* 'c' */, 0},
136 {(UChar)0x0061 /* 'a' */, (UChar)0x0042 /* 'B' */, (UChar)0x0064 /* 'd' */, 0},
137 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
138 {(UChar)0x0070 /* 'p' */, 0x00EA, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, 0}
139 };
140
141 const static UCollationResult results[] = {
142 UCOL_LESS,
143 UCOL_LESS, /*UCOL_GREATER,*/
144 UCOL_LESS,
145 UCOL_GREATER,
146 UCOL_GREATER,
147 UCOL_EQUAL,
148 UCOL_LESS,
149 UCOL_LESS,
150 UCOL_LESS,
151 UCOL_LESS, /*UCOL_GREATER,*/ /* 10 */
152 UCOL_GREATER,
153 UCOL_LESS,
154 UCOL_EQUAL,
155 UCOL_LESS,
156 UCOL_GREATER,
157 UCOL_GREATER,
158 UCOL_GREATER,
159 UCOL_LESS,
160 UCOL_LESS,
161 UCOL_LESS, /* 20 */
162 UCOL_LESS,
163 UCOL_LESS,
164 UCOL_LESS,
165 UCOL_GREATER,
166 UCOL_GREATER,
167 UCOL_GREATER,
168 /* Test Tertiary > 26 */
169 UCOL_LESS,
170 UCOL_LESS,
171 UCOL_GREATER,
172 UCOL_LESS, /* 30 */
173 UCOL_GREATER,
174 UCOL_EQUAL,
175 UCOL_GREATER,
176 UCOL_LESS,
177 UCOL_LESS,
178 UCOL_LESS,
179 /* test identical > 36 */
180 UCOL_EQUAL,
181 UCOL_EQUAL,
182 /* test primary > 38 */
183 UCOL_EQUAL,
184 UCOL_EQUAL, /* 40 */
185 UCOL_LESS,
186 UCOL_EQUAL,
187 UCOL_EQUAL,
188 /* test secondary > 43 */
189 UCOL_LESS,
190 UCOL_LESS,
191 UCOL_EQUAL,
192 UCOL_LESS,
193 UCOL_LESS,
194 UCOL_LESS /* 49 */
195 };
196
197 const static UChar testBugs[][MAX_TOKEN_LEN] = {
198 {(UChar)0x0061 /* 'a' */, 0},
199 {(UChar)0x0041 /* 'A' */, 0},
200 {(UChar)0x0065 /* 'e' */, 0},
201 {(UChar)0x0045 /* 'E' */, 0},
202 {0x00e9, 0},
203 {0x00e8, 0},
204 {0x00ea, 0},
205 {0x00eb, 0},
206 {(UChar)0x0065 /* 'e' */, (UChar)0x0061 /* 'a' */, 0},
207 {(UChar)0x0078 /* 'x' */, 0}
208
209 };
210
211 /* 0x0300 is grave, 0x0301 is acute
212 the order of elements in this array must be different than the order in CollationFrenchTest */
213 const static UChar testAcute[][MAX_TOKEN_LEN] = {
214 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0},
215 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0301, 0},
216 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
217 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0300, 0},
218 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
219 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0},
220 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0},
221 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
222 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0},
223 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
224 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0},
225 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0},
226 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
227 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0},
228 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
229 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0},
230 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0},
231 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
232 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0},
233 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
234 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0},
235 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0},
236 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
237 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0},
238 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0}
239 };
240
241 static const UChar testMore[][MAX_TOKEN_LEN] = {
242 {(UChar)0x0061 /* 'a' */, (UChar)0x0065 /* 'e' */, 0},
243 { 0x00E6, 0},
244 { 0x00C6, 0},
245 {(UChar)0x0061 /* 'a' */, (UChar)0x0066 /* 'f' */, 0},
246 {(UChar)0x006F /* 'o' */, (UChar)0x0065 /* 'e' */, 0},
247 { 0x0153, 0},
248 { 0x0152, 0},
249 {(UChar)0x006F /* 'o' */, (UChar)0x0066 /* 'f' */, 0},
250 };
251
252
addEnglishCollTest(TestNode ** root)253 void addEnglishCollTest(TestNode** root)
254 {
255
256 addTest(root, &TestPrimary, "tscoll/encoll/TestPrimary");
257 addTest(root, &TestSecondary, "tscoll/encoll/TestSecondary");
258 addTest(root, &TestTertiary, "tscoll/encoll/TestTertiary");
259
260 }
261
TestTertiary()262 static void TestTertiary( )
263 {
264 int32_t testMoreSize;
265 UCollationResult expected=UCOL_EQUAL;
266 int32_t i,j;
267 UErrorCode status = U_ZERO_ERROR;
268 myCollation = ucol_open("en_US", &status);
269 if(U_FAILURE(status)){
270 log_err_status(status, "ERROR: in creation of rule based collator: %s\n", myErrorName(status));
271 return;
272 }
273 log_verbose("Testing English Collation with Tertiary strength\n");
274
275 ucol_setStrength(myCollation, UCOL_TERTIARY);
276 for (i = 0; i < 38 ; i++)
277 {
278 doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
279 }
280
281
282 j = 0;
283 for (i = 0; i < 10; i++)
284 {
285 for (j = i+1; j < 10; j++)
286 {
287 doTest(myCollation, testBugs[i], testBugs[j], UCOL_LESS);
288 }
289 }
290 /*test more interesting cases */
291 testMoreSize = sizeof(testMore) / sizeof(testMore[0]);
292 for (i = 0; i < testMoreSize; i++)
293 {
294 for (j = 0; j < testMoreSize; j++)
295 {
296 if (i < j) expected = UCOL_LESS;
297 if (i == j) expected = UCOL_EQUAL;
298 if (i > j) expected = UCOL_GREATER;
299 doTest(myCollation, testMore[i], testMore[j], expected );
300 }
301 }
302 ucol_close(myCollation);
303 }
304
TestPrimary()305 static void TestPrimary()
306 {
307
308 int32_t i;
309 UErrorCode status = U_ZERO_ERROR;
310 myCollation = ucol_open("en_US", &status);
311 if(U_FAILURE(status)){
312 log_err_status(status, "ERROR: in creation of rule based collator: %s\n", myErrorName(status));
313 return;
314 }
315 ucol_setStrength(myCollation, UCOL_PRIMARY);
316 log_verbose("Testing English Collation with Primary strength\n");
317 for (i = 38; i < 43 ; i++)
318 {
319 doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
320 }
321 ucol_close(myCollation);
322 }
323
TestSecondary()324 static void TestSecondary()
325 {
326 UCollationResult expected=UCOL_EQUAL;
327 int32_t i,j, testAcuteSize;
328 UErrorCode status = U_ZERO_ERROR;
329 myCollation = ucol_open("en_US", &status);
330 if(U_FAILURE(status)){
331 log_err_status(status, "ERROR: in creation of rule based collator: %s\n", myErrorName(status));
332 return;
333 }
334 ucol_setStrength(myCollation, UCOL_SECONDARY);
335 log_verbose("Testing English Collation with Secondary strength\n");
336 for (i = 43; i < 49 ; i++)
337 {
338 doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
339 }
340
341
342 /*test acute and grave ordering (compare to french collation) */
343 testAcuteSize = sizeof(testAcute) / sizeof(testAcute[0]);
344 for (i = 0; i < testAcuteSize; i++)
345 {
346 for (j = 0; j < testAcuteSize; j++)
347 {
348 if (i < j) expected = UCOL_LESS;
349 if (i == j) expected = UCOL_EQUAL;
350 if (i > j) expected = UCOL_GREATER;
351 doTest(myCollation, testAcute[i], testAcute[j], expected );
352 }
353 }
354 ucol_close(myCollation);
355 }
356
357 #endif /* #if !UCONFIG_NO_COLLATION */
358