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
|
%prep
# Find a UTF-8 locale.
setopt multibyte
mb_ok=
langs=(en_US.UTF-8 en_GB.UTF-8 en.UTF-8
$(locale -a 2>/dev/null | sed -e 's/utf8/UTF-8/' | grep UTF-8))
for LANG in $langs; do
if [[ é = ? ]]; then
mb_ok=1
break;
fi
done
if [[ -z $mb_ok ]]; then
ZTST_unimplemented="no UTF-8 locale or multibyte mode is not implemnted"
else
print Testing multibyte with locale $LANG >&8
fi
%test
a=ténébreux
for i in {1..9}; do
print ${a[i]}
for j in {$i..9}; do
print $i $j ${a[i,j]} ${a[-j,-i]}
done
done
0:Basic indexing with multibyte characters
>t
>1 1 t x
>1 2 té ux
>1 3 tén eux
>1 4 téné reux
>1 5 ténéb breux
>1 6 ténébr ébreux
>1 7 ténébre nébreux
>1 8 ténébreu énébreux
>1 9 ténébreux ténébreux
>é
>2 2 é u
>2 3 én eu
>2 4 éné reu
>2 5 énéb breu
>2 6 énébr ébreu
>2 7 énébre nébreu
>2 8 énébreu énébreu
>2 9 énébreux ténébreu
>n
>3 3 n e
>3 4 né re
>3 5 néb bre
>3 6 nébr ébre
>3 7 nébre nébre
>3 8 nébreu énébre
>3 9 nébreux ténébre
>é
>4 4 é r
>4 5 éb br
>4 6 ébr ébr
>4 7 ébre nébr
>4 8 ébreu énébr
>4 9 ébreux ténébr
>b
>5 5 b b
>5 6 br éb
>5 7 bre néb
>5 8 breu énéb
>5 9 breux ténéb
>r
>6 6 r é
>6 7 re né
>6 8 reu éné
>6 9 reux téné
>e
>7 7 e n
>7 8 eu én
>7 9 eux tén
>u
>8 8 u é
>8 9 ux té
>x
>9 9 x t
s=é
print A${s[-2]}A B${s[-1]}B C${s[0]}C D${s[1]}D E${s[2]}E
0:Out of range subscripts with multibyte characters
>AA BéB CéC DéD EE
print ${a[(i)é]} ${a[(I)é]} ${a[${a[(i)é]},${a[(I)é]}]}
0:Reverse indexing with multibyte characters
>2 4 éné
print ${a[(r)én,(r)éb]}
0:Subscript searching with multibyte characters
>énéb
print ${a[(rb:1:)é,-1]}
print ${a[(rb:2:)é,-1]}
print ${a[(rb:3:)é,-1]}
print ${a[(rb:4:)é,-1]}
print ${a[(rb:5:)é,-1]}
0:Subscript searching with initial offset
>énébreux
>énébreux
>ébreux
>ébreux
>
print ${a[(rn:1:)é,-1]}
print ${a[(rn:2:)é,-1]}
print ${a[(rn:3:)é,-1]}
0:Subscript searching with count
>énébreux
>ébreux
>
print ${a[(R)én,(R)éb]}
0:Backward subscript searching with multibyte characters
>énéb
# Starting offsets with (R) seem to be so strange as to be hardly
# worth testing.
|
