1 // © 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
3 /********************************************************************
4 * COPYRIGHT:
5 * Copyright (c) 1997-2016, International Business Machines Corporation and
6 * others. All Rights Reserved.
7 ********************************************************************/
8 /********************************************************************************
9 *
10 * File encoll.C
11 *
12 * Modification History:
13 * Name Description
14 * Madhu Katragadda Ported for C API
15 *********************************************************************************/
16 /**
17 * CollationEnglishTest is a third level test class. This tests the locale
18 * specific primary, secondary and tertiary rules. For example, the ignorable
19 * character '-' in string "black-bird". The en_US locale uses the default
20 * collation rules as its sorting sequence.
21 */
22
23 #include <stdlib.h>
24 #include <string.h>
25
26 #include "unicode/utypes.h"
27
28 #if !UCONFIG_NO_COLLATION
29
30 #include "unicode/ucol.h"
31 #include "unicode/uloc.h"
32 #include "cintltst.h"
33 #include "encoll.h"
34 #include "ccolltst.h"
35 #include "callcoll.h"
36 #include "cmemory.h"
37 #include "unicode/ustring.h"
38
39 static UCollator *myCollation = NULL;
40 const static UChar testSourceCases[][MAX_TOKEN_LEN] = {
41 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, 0},
42 {(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},
43 {(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},
44 {(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},
45 {(UChar)0x0048 /* 'H' */, (UChar)0x0065 /* 'e' */, (UChar)0x006C /* 'l' */, (UChar)0x006C /* 'l' */, (UChar)0x006F /* 'o' */, 0},
46 {(UChar)0x0041 /* 'A' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
47 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
48 {(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},
49 {(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},
50 {(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},
51 {(UChar)0x0070 /* 'p' */, 0x00EA, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, 0},
52 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0},
53 {0x00C4, (UChar)0x0042 /* 'B' */, 0x0308, (UChar)0x0043 /* 'C' */, 0x0308, 0},
54 {(UChar)0x0061 /* 'a' */, 0x0308, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
55 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, (UChar)0x0072 /* 'r' */, 0},
56 {(UChar)0x0072 /* 'r' */, (UChar)0x006F /* 'o' */, (UChar)0x006C /* 'l' */, (UChar)0x0065 /* 'e' */, (UChar)0x0073 /* 's' */, 0},
57 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
58 {(UChar)0x0041 /* 'A' */, 0},
59 {(UChar)0x0041 /* 'A' */, 0},
60 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, 0},
61 {(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},
62 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, 0},
63 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0062 /* 'b' */, 0},
64 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0062 /* 'b' */, 0},
65 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
66 {(UChar)0x0041 /* 'A' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
67 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
68 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
69 {0x00E6, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
70 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 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)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
74 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
75 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
76 {(UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x0048 /* 'H' */, (UChar)0x0063 /* 'c' */, 0},
77 {(UChar)0x0061 /* 'a' */, 0x0308, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
78 {(UChar)0x0074 /* 't' */, (UChar)0x0068 /* 'h' */, (UChar)0x0069 /* 'i' */, 0x0302, (UChar)0x0073 /* 's' */, 0},
79 {(UChar)0x0070 /* 'p' */, 0x00EA, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */},
80 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (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)0x0061 /* 'a' */, 0x00E6, (UChar)0x0063 /* 'c' */, 0},
87 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
88 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
89 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0}
90 };
91
92 const static UChar testTargetCases[][MAX_TOKEN_LEN] = {
93 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
94 {(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},
95 {(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},
96 {(UChar)0x0062 /* 'b' */, (UChar)0x006C /* 'l' */, (UChar)0x0061 /* 'a' */, (UChar)0x0063 /* 'c' */, (UChar)0x006B /* 'k' */, 0},
97 {(UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, (UChar)0x006C /* 'l' */, (UChar)0x006C /* 'l' */, (UChar)0x006F /* 'o' */, 0},
98 {(UChar)0x0041 /* 'A' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
99 {(UChar)0x0041 /* 'A' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
100 {(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},
101 {(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},
102 {(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},
103 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0},
104 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, (UChar)0x0072 /* 'r' */, 0},
105 {0x00C4, (UChar)0x0042 /* 'B' */, 0x0308, (UChar)0x0043 /* 'C' */, 0x0308, 0},
106 {(UChar)0x0041 /* 'A' */, 0x0308, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
107 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, 0},
108 {(UChar)0x0072 /* 'r' */, (UChar)0x006F /* 'o' */, 0x0302, (UChar)0x006C /* 'l' */, (UChar)0x0065 /* 'e' */, 0},
109 {(UChar)0x0041 /* 'A' */, 0x00E1, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, 0},
110 {(UChar)0x0041 /* 'A' */, 0x00E1, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, 0},
111 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
112 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
113 {(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},
114 {(UChar)0x0061 /* 'a' */, (UChar)0x0042 /* 'B' */, (UChar)0x0063 /* 'c' */, 0},
115 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0042 /* 'B' */, 0},
116 {(UChar)0x0061 /* 'a' */, (UChar)0x0026 /* '&' */, (UChar)0x0062 /* 'b' */, 0},
117 {(UChar)0x0061 /* 'a' */, (UChar)0x0023 /* '#' */, (UChar)0x0063 /* 'c' */, 0},
118 {(UChar)0x0061 /* 'a' */, (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 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
121 {0x00C4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
122 {0x00C4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, (UChar)0x0064 /* 'd' */, (UChar)0x0061 /* 'a' */, 0},
123 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0023 /* '#' */, (UChar)0x0063 /* 'c' */, 0},
124 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
125 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x003D /* '=' */, (UChar)0x0063 /* 'c' */, 0},
126 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* 'b' */, (UChar)0x0064 /* 'd' */, 0},
127 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
128 {(UChar)0x0061 /* 'a' */, (UChar)0x0043 /* 'C' */, (UChar)0x0048 /* 'H' */, (UChar)0x0063 /* 'c' */, 0},
129 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
130 {(UChar)0x0074 /* 't' */, (UChar)0x0068 /* 'h' */, 0x00EE, (UChar)0x0073 /* 's' */, 0},
131 {(UChar)0x0070 /* 'p' */, 0x00E9, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, 0x00E9, 0},
132 {(UChar)0x0061 /* 'a' */, (UChar)0x0042 /* 'B' */, (UChar)0x0043 /* 'C' */, 0},
133 {(UChar)0x0061 /* 'a' */, (UChar)0x0062 /* '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)0x0061 /* 'a' */, 0x00C6, (UChar)0x0063 /* 'c' */, 0},
139 {(UChar)0x0061 /* 'a' */, (UChar)0x0042 /* 'B' */, (UChar)0x0064 /* 'd' */, 0},
140 {0x00E4, (UChar)0x0062 /* 'b' */, (UChar)0x0063 /* 'c' */, 0},
141 {(UChar)0x0070 /* 'p' */, 0x00EA, (UChar)0x0063 /* 'c' */, (UChar)0x0068 /* 'h' */, (UChar)0x0065 /* 'e' */, 0}
142 };
143
144 const static UCollationResult results[] = {
145 UCOL_LESS,
146 UCOL_LESS, /*UCOL_GREATER,*/
147 UCOL_LESS,
148 UCOL_GREATER,
149 UCOL_GREATER,
150 UCOL_EQUAL,
151 UCOL_LESS,
152 UCOL_LESS,
153 UCOL_LESS,
154 UCOL_LESS, /*UCOL_GREATER,*/ /* 10 */
155 UCOL_GREATER,
156 UCOL_LESS,
157 UCOL_EQUAL,
158 UCOL_LESS,
159 UCOL_GREATER,
160 UCOL_GREATER,
161 UCOL_GREATER,
162 UCOL_LESS,
163 UCOL_LESS,
164 UCOL_LESS, /* 20 */
165 UCOL_LESS,
166 UCOL_LESS,
167 UCOL_LESS,
168 UCOL_GREATER,
169 UCOL_GREATER,
170 UCOL_GREATER,
171 /* Test Tertiary > 26 */
172 UCOL_LESS,
173 UCOL_LESS,
174 UCOL_GREATER,
175 UCOL_LESS, /* 30 */
176 UCOL_GREATER,
177 UCOL_EQUAL,
178 UCOL_GREATER,
179 UCOL_LESS,
180 UCOL_LESS,
181 UCOL_LESS,
182 /* test identical > 36 */
183 UCOL_EQUAL,
184 UCOL_EQUAL,
185 /* test primary > 38 */
186 UCOL_EQUAL,
187 UCOL_EQUAL, /* 40 */
188 UCOL_LESS,
189 UCOL_EQUAL,
190 UCOL_EQUAL,
191 /* test secondary > 43 */
192 UCOL_LESS,
193 UCOL_LESS,
194 UCOL_EQUAL,
195 UCOL_LESS,
196 UCOL_LESS,
197 UCOL_LESS /* 49 */
198 };
199
200 const static UChar testBugs[][MAX_TOKEN_LEN] = {
201 {(UChar)0x0061 /* 'a' */, 0},
202 {(UChar)0x0041 /* 'A' */, 0},
203 {(UChar)0x0065 /* 'e' */, 0},
204 {(UChar)0x0045 /* 'E' */, 0},
205 {0x00e9, 0},
206 {0x00e8, 0},
207 {0x00ea, 0},
208 {0x00eb, 0},
209 {(UChar)0x0065 /* 'e' */, (UChar)0x0061 /* 'a' */, 0},
210 {(UChar)0x0078 /* 'x' */, 0}
211
212 };
213
214 /* 0x0300 is grave, 0x0301 is acute
215 the order of elements in this array must be different than the order in CollationFrenchTest */
216 const static UChar testAcute[][MAX_TOKEN_LEN] = {
217 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0},
218 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0301, 0},
219 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
220 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0300, 0},
221 {(UChar)0x0065 /* 'e' */, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
222 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0},
223 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0},
224 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
225 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0},
226 {(UChar)0x0065 /* 'e' */, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
227 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0},
228 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0},
229 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
230 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0},
231 {(UChar)0x0065 /* 'e' */, 0x0301, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
232 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0},
233 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0},
234 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
235 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0},
236 {(UChar)0x0065 /* 'e' */, 0x0300, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0},
237 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0},
238 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0},
239 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0301, 0x0300, 0},
240 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0},
241 {(UChar)0x0065 /* 'e' */, 0x0300, 0x0301, (UChar)0x0065 /* 'e' */, 0x0300, 0x0301, 0}
242 };
243
244 static const UChar testMore[][MAX_TOKEN_LEN] = {
245 {(UChar)0x0061 /* 'a' */, (UChar)0x0065 /* 'e' */, 0},
246 { 0x00E6, 0},
247 { 0x00C6, 0},
248 {(UChar)0x0061 /* 'a' */, (UChar)0x0066 /* 'f' */, 0},
249 {(UChar)0x006F /* 'o' */, (UChar)0x0065 /* 'e' */, 0},
250 { 0x0153, 0},
251 { 0x0152, 0},
252 {(UChar)0x006F /* 'o' */, (UChar)0x0066 /* 'f' */, 0},
253 };
254
255
addEnglishCollTest(TestNode ** root)256 void addEnglishCollTest(TestNode** root)
257 {
258
259 addTest(root, &TestPrimary, "tscoll/encoll/TestPrimary");
260 addTest(root, &TestSecondary, "tscoll/encoll/TestSecondary");
261 addTest(root, &TestTertiary, "tscoll/encoll/TestTertiary");
262
263 }
264
TestTertiary()265 static void TestTertiary( )
266 {
267 int32_t testMoreSize;
268 UCollationResult expected=UCOL_EQUAL;
269 int32_t i,j;
270 UErrorCode status = U_ZERO_ERROR;
271 myCollation = ucol_open("en_US", &status);
272 if(U_FAILURE(status)){
273 log_err_status(status, "ERROR: in creation of rule based collator: %s\n", myErrorName(status));
274 return;
275 }
276 log_verbose("Testing English Collation with Tertiary strength\n");
277
278 ucol_setStrength(myCollation, UCOL_TERTIARY);
279 for (i = 0; i < 38 ; i++)
280 {
281 doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
282 }
283
284
285 j = 0;
286 for (i = 0; i < 10; i++)
287 {
288 for (j = i+1; j < 10; j++)
289 {
290 doTest(myCollation, testBugs[i], testBugs[j], UCOL_LESS);
291 }
292 }
293 /*test more interesting cases */
294 testMoreSize = UPRV_LENGTHOF(testMore);
295 for (i = 0; i < testMoreSize; i++)
296 {
297 for (j = 0; j < testMoreSize; j++)
298 {
299 if (i < j) expected = UCOL_LESS;
300 if (i == j) expected = UCOL_EQUAL;
301 if (i > j) expected = UCOL_GREATER;
302 doTest(myCollation, testMore[i], testMore[j], expected );
303 }
304 }
305 ucol_close(myCollation);
306 }
307
TestPrimary()308 static void TestPrimary()
309 {
310
311 int32_t i;
312 UErrorCode status = U_ZERO_ERROR;
313 myCollation = ucol_open("en_US", &status);
314 if(U_FAILURE(status)){
315 log_err_status(status, "ERROR: in creation of rule based collator: %s\n", myErrorName(status));
316 return;
317 }
318 ucol_setStrength(myCollation, UCOL_PRIMARY);
319 log_verbose("Testing English Collation with Primary strength\n");
320 for (i = 38; i < 43 ; i++)
321 {
322 doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
323 }
324 ucol_close(myCollation);
325 }
326
TestSecondary()327 static void TestSecondary()
328 {
329 UCollationResult expected=UCOL_EQUAL;
330 int32_t i,j, testAcuteSize;
331 UErrorCode status = U_ZERO_ERROR;
332 myCollation = ucol_open("en_US", &status);
333 if(U_FAILURE(status)){
334 log_err_status(status, "ERROR: in creation of rule based collator: %s\n", myErrorName(status));
335 return;
336 }
337 ucol_setStrength(myCollation, UCOL_SECONDARY);
338 log_verbose("Testing English Collation with Secondary strength\n");
339 for (i = 43; i < 49 ; i++)
340 {
341 doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
342 }
343
344
345 /*test acute and grave ordering (compare to french collation) */
346 testAcuteSize = UPRV_LENGTHOF(testAcute);
347 for (i = 0; i < testAcuteSize; i++)
348 {
349 for (j = 0; j < testAcuteSize; j++)
350 {
351 if (i < j) expected = UCOL_LESS;
352 if (i == j) expected = UCOL_EQUAL;
353 if (i > j) expected = UCOL_GREATER;
354 doTest(myCollation, testAcute[i], testAcute[j], expected );
355 }
356 }
357 ucol_close(myCollation);
358 }
359
360 #endif /* #if !UCONFIG_NO_COLLATION */
361