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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
|
require "spec"
require "char/reader"
require "../../support/string"
private def assert_invalid_byte_sequence(bytes, *, file = __FILE__, line = __LINE__)
reader = Char::Reader.new(String.new bytes)
reader.current_char.should eq(Char::REPLACEMENT), file: file, line: line
reader.current_char_width.should eq(1), file: file, line: line
reader.error.should eq(bytes[0]), file: file, line: line
end
private def assert_reads_at_end(bytes, char, *, file = __FILE__, line = __LINE__)
str = String.new bytes
reader = Char::Reader.new(str, pos: bytes.size)
reader.previous_char.should eq(char), file: file, line: line
reader.current_char.should eq(char), file: file, line: line
reader.current_char_width.should eq(bytes.size), file: file, line: line
reader.pos.should eq(0), file: file, line: line
reader.error.should be_nil, file: file, line: line
end
private def assert_invalid_byte_sequence_at_end(bytes, *, file = __FILE__, line = __LINE__)
str = String.new bytes
reader = Char::Reader.new(str, pos: bytes.size)
reader.previous_char
reader.current_char.should eq(Char::REPLACEMENT), file: file, line: line
reader.current_char_width.should eq(1), file: file, line: line
reader.pos.should eq(bytes.size - 1), file: file, line: line
reader.error.should eq(bytes[-1]), file: file, line: line
end
describe "Char::Reader" do
it "iterates through empty string" do
reader = Char::Reader.new("")
reader.pos.should eq(0)
reader.current_char.ord.should eq(0)
reader.error.should be_nil
reader.has_next?.should be_false
expect_raises IndexError do
reader.next_char
end
end
it "iterates through string of size one" do
reader = Char::Reader.new("a")
reader.pos.should eq(0)
reader.current_char.should eq('a')
reader.has_next?.should be_true
reader.next_char.ord.should eq(0)
reader.has_next?.should be_false
expect_raises IndexError do
reader.next_char
end
end
it "iterates through chars" do
reader = Char::Reader.new("há日本語")
reader.pos.should eq(0)
reader.current_char.ord.should eq(104)
reader.has_next?.should be_true
reader.next_char.ord.should eq(225)
reader.pos.should eq(1)
reader.current_char.ord.should eq(225)
reader.next_char.ord.should eq(26085)
reader.next_char.ord.should eq(26412)
reader.next_char.ord.should eq(35486)
reader.has_next?.should be_true
reader.next_char.ord.should eq(0)
reader.has_next?.should be_false
expect_raises IndexError do
reader.next_char
end
end
it "peeks next char" do
reader = Char::Reader.new("há日本語")
reader.peek_next_char.ord.should eq(225)
end
it "sets pos" do
reader = Char::Reader.new("há日本語")
reader.pos = 1
reader.pos.should eq(1)
reader.current_char.ord.should eq(225)
end
describe "#each" do
it "yields chars" do
reader = Char::Reader.new("abc")
chars = [] of Char
reader.each do |char|
chars << char
end.should be_nil
chars.should eq ['a', 'b', 'c']
end
it "does not yield if empty" do
reader = Char::Reader.new("")
reader.each do |char|
fail "reader each shouldn't yield on empty string"
end.should be_nil
end
it "checks bounds after block" do
string = "f"
reader = Char::Reader.new(string)
reader.each do |c|
c.should eq 'f'
reader.next_char
end
end
end
it "starts at end" do
reader = Char::Reader.new(at_end: "")
reader.pos.should eq(0)
reader.current_char.ord.should eq(0)
reader.has_previous?.should be_false
reader.has_next?.should be_false
end
it "gets previous char (ascii)" do
reader = Char::Reader.new(at_end: "hello")
reader.pos.should eq(4)
reader.current_char.should eq('o')
reader.has_previous?.should be_true
reader.has_next?.should be_true
reader.previous_char.should eq('l')
reader.has_next?.should be_true
reader.previous_char.should eq('l')
reader.previous_char.should eq('e')
reader.previous_char.should eq('h')
reader.has_previous?.should be_false
expect_raises IndexError do
reader.previous_char
end
end
it "gets previous char (unicode)" do
reader = Char::Reader.new(at_end: "há日本語")
reader.pos.should eq(9)
reader.current_char.should eq('語')
reader.has_previous?.should be_true
reader.has_next?.should be_true
reader.previous_char.should eq('本')
reader.has_next?.should be_true
reader.previous_char.should eq('日')
reader.previous_char.should eq('á')
reader.previous_char.should eq('h')
reader.has_previous?.should be_false
end
it "starts at pos" do
reader = Char::Reader.new("há日本語", pos: 9)
reader.pos.should eq(9)
reader.current_char.should eq('語')
end
it "#current_char?" do
reader = Char::Reader.new("há日本語")
reader.current_char?.should eq('h')
reader.next_char
reader.current_char?.should eq('á')
reader.next_char
reader.current_char?.should eq('日')
reader.next_char
reader.current_char?.should eq('本')
reader.next_char
reader.current_char?.should eq('語')
reader.next_char
reader.current_char?.should be_nil
reader.previous_char
reader.current_char?.should eq('語')
end
it "#next_char?" do
reader = Char::Reader.new("há日本語")
reader.next_char?.should eq('á')
reader.pos.should eq(1)
reader.next_char?.should eq('日')
reader.pos.should eq(3)
reader.next_char?.should eq('本')
reader.pos.should eq(6)
reader.next_char?.should eq('語')
reader.pos.should eq(9)
reader.next_char?.should be_nil
reader.pos.should eq(12)
reader.next_char?.should be_nil
reader.pos.should eq(12)
end
it "#previous_char?" do
reader = Char::Reader.new("há日本語", pos: 12)
reader.previous_char?.should eq('語')
reader.pos.should eq(9)
reader.previous_char?.should eq('本')
reader.pos.should eq(6)
reader.previous_char?.should eq('日')
reader.pos.should eq(3)
reader.previous_char?.should eq('á')
reader.pos.should eq(1)
reader.previous_char?.should eq('h')
reader.pos.should eq(0)
reader.previous_char?.should be_nil
reader.pos.should eq(0)
end
it "errors on invalid UTF-8" do
{% for bytes in INVALID_UTF8_BYTE_SEQUENCES %}
assert_invalid_byte_sequence Bytes{{ bytes }}
{% end %}
end
describe "#previous_char" do
it "reads on valid UTF-8" do
{% for bytes, char in VALID_UTF8_BYTE_SEQUENCES %}
assert_reads_at_end Bytes{{ bytes }}, {{ char }}
{% end %}
end
it "errors on invalid UTF-8" do
assert_invalid_byte_sequence_at_end Bytes[0x80]
assert_invalid_byte_sequence_at_end Bytes[0xbf]
assert_invalid_byte_sequence_at_end Bytes[0xc0]
assert_invalid_byte_sequence_at_end Bytes[0xff]
assert_invalid_byte_sequence_at_end Bytes[0x00, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x7f, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x9f, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xbf, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc1, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xe0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xff, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x00, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x7f, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x80, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x8f, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x90, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xbf, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc0, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc1, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc2, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xdf, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xe0, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xe0, 0x9f, 0xbf]
assert_invalid_byte_sequence_at_end Bytes[0xf0, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xff, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x00, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x7f, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x80, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x8f, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x90, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xbf, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc0, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc1, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xc2, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xdf, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xed, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xed, 0xbf, 0xbf]
assert_invalid_byte_sequence_at_end Bytes[0xf0, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xff, 0xa0, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x00, 0x80, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xef, 0x80, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xf0, 0x80, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xf5, 0x80, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xff, 0x80, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0x00, 0x90, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xef, 0x90, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xf4, 0x90, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xf5, 0x90, 0x80, 0x80]
assert_invalid_byte_sequence_at_end Bytes[0xff, 0x90, 0x80, 0x80]
end
end
end
|
