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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
|
function test_len(t)
t:are_equal(utf8.len("A"), 1)
t:are_equal(utf8.len("¢"), 1)
t:are_equal(utf8.len("€"), 1)
t:are_equal(utf8.len("𐍈"), 1)
t:are_equal(utf8.len("ab"), 2)
t:are_equal(utf8.len("A€B"), 3)
t:are_equal(utf8.len("你好"), 2)
end
function test_char(t)
t:are_equal(utf8.char(65), "A")
t:are_equal(utf8.char(0x20AC), "€")
t:are_equal(utf8.char(65, 66, 67), "ABC")
end
function test_codepoint(t)
t:are_equal(utf8.codepoint("A"), 65)
t:are_equal(utf8.codepoint("€"), 0x20AC)
local c1, c2, c3 = utf8.codepoint("ABC", 1, 3)
t:are_equal(c1, 65)
t:are_equal(c2, 66)
t:are_equal(c3, 67)
-- test range
t:are_equal(utf8.codepoint("ABC", 2), 66)
t:are_equal(utf8.codepoint("ABC", 2, 2), 66)
end
function test_offset(t)
t:are_equal(utf8.offset("ABC", 1), 1)
t:are_equal(utf8.offset("ABC", 2), 2)
t:are_equal(utf8.offset("ABC", 4), 4)
t:are_equal(utf8.offset("ABC", 5), nil)
-- "€" is 3 bytes (0xE2 0x82 0xAC)
t:are_equal(utf8.offset("€BC", 1), 1)
t:are_equal(utf8.offset("€BC", 2), 4)
t:are_equal(utf8.offset("€BC", 3), 5)
t:are_equal(utf8.offset("你好", 1), 1)
t:are_equal(utf8.offset("你好", 2), 4)
t:are_equal(utf8.offset("你好", 3), 7)
end
function test_codes(t)
local s = "A€"
local codes = {}
for p, c in utf8.codes(s) do
table.insert(codes, {p, c})
end
t:are_equal(#codes, 2)
t:are_equal(codes[1][1], 1)
t:are_equal(codes[1][2], 65)
-- "€" starts at 2? No, byte offset.
-- "A" is 1 byte. "€" starts at 2.
t:are_equal(codes[2][1], 2)
t:are_equal(codes[2][2], 0x20AC)
end
function test_charpattern(t)
t:require(utf8.charpattern)
end
function test_sub(t)
t:are_equal(utf8.sub("ABC", 1, 1), "A")
t:are_equal(utf8.sub("ABC", 2, 2), "B")
t:are_equal(utf8.sub("ABC", 1, 2), "AB")
t:are_equal(utf8.sub("你好", 1, 1), "你")
t:are_equal(utf8.sub("你好", 2, 2), "好")
t:are_equal(utf8.sub("你好", 1, 2), "你好")
-- mixed
t:are_equal(utf8.sub("A你好B", 2, 3), "你好")
t:are_equal(utf8.sub("A你好B", 1, 3), "A你好")
t:are_equal(utf8.sub("A你好B", 2, 4), "你好B")
-- negative
t:are_equal(utf8.sub("ABC", -1), "C")
t:are_equal(utf8.sub("ABC", -2), "BC")
t:are_equal(utf8.sub("你好", -1), "好")
t:are_equal(utf8.sub("你好", -2), "你好")
t:are_equal(utf8.sub("你好", 1, -1), "你好")
t:are_equal(utf8.sub("你好", 1, -2), "你")
-- out of bounds
t:are_equal(utf8.sub("ABC", 4), "")
t:are_equal(utf8.sub("ABC", 1, 5), "ABC")
t:are_equal(utf8.sub("ABC", 0), "ABC")
t:are_equal(utf8.sub("ABC", -10), "ABC")
end
function test_lastof(t)
t:are_equal(utf8.lastof("ABC", "A"), 1)
t:are_equal(utf8.lastof("ABC", "B"), 2)
t:are_equal(utf8.lastof("ABC", "C"), 3)
t:are_equal(utf8.lastof("ABCA", "A"), 4)
t:are_equal(utf8.lastof("你好", "你"), 1)
t:are_equal(utf8.lastof("你好", "好"), 2)
t:are_equal(utf8.lastof("你好你", "你"), 3)
t:are_equal(utf8.lastof("A你好A", "A"), 4)
t:are_equal(utf8.lastof("A你好A", "好"), 3)
t:are_equal(utf8.lastof("ABC", "D"), nil)
-- plain
t:are_equal(utf8.lastof("ABC", "A", true), 1)
t:are_equal(utf8.lastof("ABC", "B", true), 2)
t:are_equal(utf8.lastof("ABC", ".", true), nil)
t:are_equal(utf8.lastof("你好", "好", true), 2)
t:are_equal(utf8.lastof("C你好D", "好", true), 3)
t:are_equal(utf8.lastof("C你好D", "D", true), 4)
-- long string
local longstr = ("你"):rep(1000) .. "好"
t:are_equal(utf8.lastof(longstr, "好"), 1001)
t:are_equal(utf8.lastof(longstr, "你"), 1000)
t:are_equal(utf8.lastof(longstr, "好", true), 1001)
t:are_equal(utf8.lastof(longstr, "你", true), 1000)
-- pattern
t:are_equal(utf8.lastof("ABC", "."), 3)
t:are_equal(utf8.lastof("你好", "."), 2)
end
function test_find(t)
-- plain
t:are_equal({utf8.find("你好", "你", 1, true)}, {1, 1})
t:are_equal({utf8.find("你好你", "你", 2, true)}, {3, 3})
t:are_equal({utf8.find("A你好A", "A", 2, true)}, {4, 4})
t:are_equal(utf8.find("ABC", "D", 1, true), nil)
t:are_equal({utf8.find("ABC", "", 1, true)}, {1, 0})
-- pattern matching (default)
t:are_equal({utf8.find("ABC", "B")}, {2, 2})
t:are_equal({utf8.find("ABC", "([BC])")}, {2, 2, "B"}) -- Capture
t:are_equal({utf8.find("ABC", "(.)(.)")}, {1, 2, "A", "B"})
-- UTF-8 pattern matching (byte-based)
-- "你" is 3 bytes. "." matches first byte.
t:are_equal({utf8.find("你好", ".")}, {1, 1})
-- "你好", "好" -> bytes 4-6.
t:are_equal({utf8.find("你好", "好")}, {2, 2})
-- "你好", "..." (3 dots) -> matches 3 bytes (whole "你").
t:are_equal({utf8.find("你好", "...")}, {1, 1})
-- "A你好", "%w" -> matches "A".
t:are_equal({utf8.find("A你好", "%w")}, {1, 1})
end
function test_width(t)
-- char/codepoint width
t:are_equal(utf8.width(string.byte("A")), 1)
t:are_equal(utf8.width(utf8.codepoint("€")), 1)
t:are_equal(utf8.width(utf8.codepoint("你")), 2)
t:are_equal(utf8.width(0), 0)
t:are_equal(utf8.width(0x09), 4) -- TAB
-- string width
t:are_equal(utf8.width("A"), 1)
t:are_equal(utf8.width("ABC"), 3)
t:are_equal(utf8.width("你好"), 4)
t:are_equal(utf8.width("A你好"), 5)
t:are_equal(utf8.width("A\tB"), 6) -- 1 + 4 + 1
end
function test_byte(t)
t:are_equal({utf8.byte("A")}, {65})
t:are_equal({utf8.byte("€")}, {0x20AC})
t:are_equal({utf8.byte("ABC")}, {65})
t:are_equal({utf8.byte("ABC", 2)}, {66})
t:are_equal({utf8.byte("ABC", 2, 2)}, {66})
t:are_equal({utf8.byte("ABC", 1, 3)}, {65, 66, 67})
t:are_equal({utf8.byte("你好")}, {utf8.codepoint("你好", 1, 1)})
t:are_equal({utf8.byte("你好", 1, 2)}, {20320, 22909})
-- negative indices
t:are_equal({utf8.byte("ABC", -1)}, {67})
t:are_equal({utf8.byte("ABC", -2)}, {66})
t:are_equal({utf8.byte("ABC", -2, -1)}, {66, 67})
t:are_equal({utf8.byte("ABC", 1, -1)}, {65, 66, 67})
-- out of bounds
t:are_equal({utf8.byte("ABC", 4)}, {})
t:are_equal({utf8.byte("ABC", 1, 0)}, {})
end
function test_reverse(t)
t:are_equal(utf8.reverse("hello"), "olleh")
t:are_equal(utf8.reverse("你好"), "好你")
t:are_equal(utf8.reverse("hello 你好"), "好你 olleh")
end
|
