aboutsummaryrefslogtreecommitdiff
path: root/tests/utf8.test
blob: 74a5aa8de4e92feb838873f37fff3222c8c65d9a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
source [file dirname [info script]]/testing.tcl

needs constraint utf8

test utf8-1.1 "Pattern matching - ?" {
	string match "abc?def" "abc\u00b5def"
} 1

test utf8-1.2 "Pattern matching - ?" {
	string match "abc?def" "abc\u2704def"
} 1

test utf8-1.3 "Pattern utf-8 literal" {
	string match "ab\u00b5\u2704?" "ab\u00b5\u2704x" 
} 1

test utf8-1.4 "Pattern utf-8 char sets" {
	string match "a\[b\u00b5\]\u2704?" "a\u00b5\u2704x" 
} 1

test utf8-1.5 "Pattern utf-8 char sets" {
	string match "a\[b\u00b5\]\u2704?" "a\u00b6\u2704x" 
} 0
test utf8-1.6 "Pattern utf-8 char sets" {
	string match "a\[b\u00b5\]\u2704?" "ab\u2704x" 
} 1
test utf8-1.7 "Pattern utf-8 char sets" {
	string match "a\[b\u00b5\]?" "a\u2704x"
} 0
test utf8-1.8 "Pattern utf-8 char sets" {
	string match "a\[\u00b5-\u00c3\]" "a\ubd"
} 1
test utf8-1.9 "Pattern utf-8 char sets" {
	string match "a\[\u00b5-\u00c3\]" "a\uc4"
} 0

test utf8-2.1 "Pattern utf-8 nocase" {
	string match -nocase "a\u1edc\u1ef4*" "A\u1edd\u1ef5XX"
} 1

test utf8-2.2 "Pattern utf-8 case difference" {
	string match "a\u1edc\u1ef4*" "A\u1edd\u1ef5XX"
} 0

test utf8-3.1 "lsearch -glob" {
	lsearch -glob {1 d a\u00b5xyb c} a\ub5*b
} 2

test utf8-3.2 "switch -glob" {
	switch -glob -- a\ub5xyb a\ub5*b { set x 1 } default { set x 0 }
	set x
} 1

set x "\ub5test"
test utf8-3.3 "info procs" {
	proc $x {} { info procs \[\ub5X]???? }
	$x
} $x

test utf8-3.3 "info commands" {
	info commands \[\ub5X]????
} $x

test utf8-3.4 "proc name with invalid utf-8" {
	catch { proc ab\xc2 {} {} } msg
} 0

test utf8-3.5 "rename to invalid name" {
	catch { rename ab\xc2 ab\xc3 } msg
} 0

catch {rename ab\xc3 ""}

test utf8-4.1 "split with utf-8" {
	split "zy\u2702xw" x
} "zy\u2702 w"

test utf8-4.2 "split with utf-8" {
	split "zy\u2702xw" \u2702
} "zy xw"

test utf8-4.2 "split with utf-8" {
	split "zy\u2702xw" {}
} "z y \u2702 x w"

test utf8-5.1 "string first with utf-8" {
	string first w "zy\u2702xw"
} 4

test utf8-5.2 "string first with utf-8" {
	string first \u2702 "\ub5zy\u2702xw"
} 3

test utf8-5.3 "string first with utf-8" {
	string first \u2704 "\ub5zy\u2702xw"
} -1

test utf8-5.4 "string first with utf-8" {
	string first \u2702 "\ub5zy\u2702xw\u2702BB"
} 3

test utf8-6.1 "string last with utf-8" {
	string last w "zy\u2702xw"
} 4

test utf8-6.2 "string last with utf-8" {
	string last \u2702 "\ub5zy\u2702xw"
} 3

test utf8-6.3 "string last with utf-8" {
	string last \u2704 "\ub5zy\u2702xw"
} -1

test utf8-6.4 "string last with utf-8" {
	string last \u2702 "\ub5zy\u2702xw\u2702BB"
} 6

test utf8-7.1 "string reverse" {
	string reverse \ub5Test\u2702
} \u2702tseT\ub5

test utf8-7.2 {append counts correctly} {
	set x \u2702XYZ
	append x \u2702XYZ
	list [string length $x] [string bytelength $x]
} {8 12}

test utf8-7.3 {Upper, lower for titlecase utf-8} {
	list [string toupper \u01c5] [string tolower \u01c5]
} "\u01c4 \u01c6"

test utf8-7.4 {Case folding may change encoded length} {
	list [string bytelength \u0131] [string bytelength [string toupper \u0131]]
} {2 1}

test utf8-8.1 {Chars outside the BMP} jim {
	string length \u{12000}\u{13000}
} 2

test utf8-8.2 {Chars outside the BMP} jim {
	string match "ab\[\u{12000}c\]d" ab\u{12000}d
} 1

test utf8-8.3 {Chars outside the BMP} jim {
	string last d "ab\u{101fff}cd"
} 4

test utf8-8.4 {Longer sequences} {
	string length \u12000
} 2

testreport