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
292
293
294
295
296
|
# frozen_string_literal: true
return if RUBY_ENGINE != "ruby"
require_relative "test_helper"
module Prism
class EncodingTest < TestCase
codepoints_1byte = 0...0x100
codepoints_2bytes = 0...0x10000
encodings = {
Encoding::ASCII => codepoints_1byte,
Encoding::ASCII_8BIT => codepoints_1byte,
Encoding::CP850 => codepoints_1byte,
Encoding::CP852 => codepoints_1byte,
Encoding::CP855 => codepoints_1byte,
Encoding::GB1988 => codepoints_1byte,
Encoding::IBM437 => codepoints_1byte,
Encoding::IBM720 => codepoints_1byte,
Encoding::IBM737 => codepoints_1byte,
Encoding::IBM775 => codepoints_1byte,
Encoding::IBM852 => codepoints_1byte,
Encoding::IBM855 => codepoints_1byte,
Encoding::IBM857 => codepoints_1byte,
Encoding::IBM860 => codepoints_1byte,
Encoding::IBM861 => codepoints_1byte,
Encoding::IBM862 => codepoints_1byte,
Encoding::IBM863 => codepoints_1byte,
Encoding::IBM864 => codepoints_1byte,
Encoding::IBM865 => codepoints_1byte,
Encoding::IBM866 => codepoints_1byte,
Encoding::IBM869 => codepoints_1byte,
Encoding::ISO_8859_1 => codepoints_1byte,
Encoding::ISO_8859_2 => codepoints_1byte,
Encoding::ISO_8859_3 => codepoints_1byte,
Encoding::ISO_8859_4 => codepoints_1byte,
Encoding::ISO_8859_5 => codepoints_1byte,
Encoding::ISO_8859_6 => codepoints_1byte,
Encoding::ISO_8859_7 => codepoints_1byte,
Encoding::ISO_8859_8 => codepoints_1byte,
Encoding::ISO_8859_9 => codepoints_1byte,
Encoding::ISO_8859_10 => codepoints_1byte,
Encoding::ISO_8859_11 => codepoints_1byte,
Encoding::ISO_8859_13 => codepoints_1byte,
Encoding::ISO_8859_14 => codepoints_1byte,
Encoding::ISO_8859_15 => codepoints_1byte,
Encoding::ISO_8859_16 => codepoints_1byte,
Encoding::KOI8_R => codepoints_1byte,
Encoding::KOI8_U => codepoints_1byte,
Encoding::MACCENTEURO => codepoints_1byte,
Encoding::MACCROATIAN => codepoints_1byte,
Encoding::MACCYRILLIC => codepoints_1byte,
Encoding::MACGREEK => codepoints_1byte,
Encoding::MACICELAND => codepoints_1byte,
Encoding::MACROMAN => codepoints_1byte,
Encoding::MACROMANIA => codepoints_1byte,
Encoding::MACTHAI => codepoints_1byte,
Encoding::MACTURKISH => codepoints_1byte,
Encoding::MACUKRAINE => codepoints_1byte,
Encoding::TIS_620 => codepoints_1byte,
Encoding::Windows_1250 => codepoints_1byte,
Encoding::Windows_1251 => codepoints_1byte,
Encoding::Windows_1252 => codepoints_1byte,
Encoding::Windows_1253 => codepoints_1byte,
Encoding::Windows_1254 => codepoints_1byte,
Encoding::Windows_1255 => codepoints_1byte,
Encoding::Windows_1256 => codepoints_1byte,
Encoding::Windows_1257 => codepoints_1byte,
Encoding::Windows_1258 => codepoints_1byte,
Encoding::Windows_874 => codepoints_1byte,
Encoding::Big5 => codepoints_2bytes,
Encoding::Big5_HKSCS => codepoints_2bytes,
Encoding::Big5_UAO => codepoints_2bytes,
Encoding::CP949 => codepoints_2bytes,
Encoding::CP950 => codepoints_2bytes,
Encoding::CP951 => codepoints_2bytes,
Encoding::EUC_KR => codepoints_2bytes,
Encoding::GBK => codepoints_2bytes,
Encoding::GB12345 => codepoints_2bytes,
Encoding::GB2312 => codepoints_2bytes,
Encoding::MACJAPANESE => codepoints_2bytes,
Encoding::Shift_JIS => codepoints_2bytes,
Encoding::SJIS_DoCoMo => codepoints_2bytes,
Encoding::SJIS_KDDI => codepoints_2bytes,
Encoding::SJIS_SoftBank => codepoints_2bytes,
Encoding::Windows_31J => codepoints_2bytes
}
# By default we don't test every codepoint in these encodings because they
# are 3 and 4 byte representations so it can drastically slow down the test
# suite.
if ENV["PRISM_TEST_ALL_ENCODINGS"]
codepoints_unicode = (0...0x110000)
codepoints_eucjp = [
*(0...0x10000),
*(0...0x10000).map { |bytes| bytes | 0x8F0000 }
]
codepoints_emacs_mule = [
*(0...0x80),
*((0x81...0x90).flat_map { |byte1| (0x90...0x100).map { |byte2| byte1 << 8 | byte2 } }),
*((0x90...0x9C).flat_map { |byte1| (0xA0...0x100).flat_map { |byte2| (0xA0...0x100).flat_map { |byte3| byte1 << 16 | byte2 << 8 | byte3 } } }),
*((0xF0...0xF5).flat_map { |byte2| (0xA0...0x100).flat_map { |byte3| (0xA0...0x100).flat_map { |byte4| 0x9C << 24 | byte3 << 16 | byte3 << 8 | byte4 } } }),
]
codepoints_gb18030 = [
*(0...0x80),
*((0x81..0xFE).flat_map { |byte1| (0x40...0x100).map { |byte2| byte1 << 8 | byte2 } }),
*((0x81..0xFE).flat_map { |byte1| (0x30...0x40).flat_map { |byte2| (0x81..0xFE).flat_map { |byte3| (0x2F...0x41).map { |byte4| byte1 << 24 | byte2 << 16 | byte3 << 8 | byte4 } } } }),
]
codepoints_euc_tw = [
*(0..0x7F),
*(0xA1..0xFF).flat_map { |byte1| (0xA1..0xFF).map { |byte2| (byte1 << 8) | byte2 } },
*(0xA1..0xB0).flat_map { |byte2| (0xA1..0xFF).flat_map { |byte3| (0xA1..0xFF).flat_map { |byte4| 0x8E << 24 | byte2 << 16 | byte3 << 8 | byte4 } } }
]
encodings.merge!(
Encoding::UTF_8 => codepoints_unicode,
Encoding::UTF8_MAC => codepoints_unicode,
Encoding::UTF8_DoCoMo => codepoints_unicode,
Encoding::UTF8_KDDI => codepoints_unicode,
Encoding::UTF8_SoftBank => codepoints_unicode,
Encoding::CESU_8 => codepoints_unicode,
Encoding::CP51932 => codepoints_eucjp,
Encoding::EUC_JP => codepoints_eucjp,
Encoding::EUCJP_MS => codepoints_eucjp,
Encoding::EUC_JIS_2004 => codepoints_eucjp,
Encoding::EMACS_MULE => codepoints_emacs_mule,
Encoding::STATELESS_ISO_2022_JP => codepoints_emacs_mule,
Encoding::STATELESS_ISO_2022_JP_KDDI => codepoints_emacs_mule,
Encoding::GB18030 => codepoints_gb18030,
Encoding::EUC_TW => codepoints_euc_tw
)
end
encodings.each do |encoding, range|
encoding.names.each do |name|
next if name == "locale"
define_method(:"test_encoding_#{name}") do
assert_encoding(encoding, name, range)
end
end
end
def test_coding
result = Prism.parse("# coding: utf-8\n'string'")
actual = result.value.statements.body.first.unescaped.encoding
assert_equal Encoding.find("utf-8"), actual
end
def test_coding_with_whitespace
result = Prism.parse("# coding \t \r \v : \t \v \r ascii-8bit \n'string'")
actual = result.value.statements.body.first.unescaped.encoding
assert_equal Encoding.find("ascii-8bit"), actual
end
def test_emacs_style
result = Prism.parse("# -*- coding: utf-8 -*-\n'string'")
actual = result.value.statements.body.first.unescaped.encoding
assert_equal Encoding.find("utf-8"), actual
end
# This test may be a little confusing. Basically when we use our strpbrk, it
# takes into account the encoding of the file.
def test_strpbrk_multibyte
result = Prism.parse(<<~RUBY)
# encoding: Shift_JIS
%w[\x81\x5c]
RUBY
assert(result.errors.empty?)
assert_equal(
(+"\x81\x5c").force_encoding(Encoding::Shift_JIS),
result.value.statements.body.first.elements.first.unescaped
)
end
def test_utf_8_variations
%w[
utf-8-unix
utf-8-dos
utf-8-mac
utf-8-*
].each do |encoding|
result = Prism.parse("# coding: #{encoding}\n'string'")
actual = result.value.statements.body.first.unescaped.encoding
assert_equal Encoding.find("utf-8"), actual
end
end
def test_first_lexed_token
encoding = Prism.lex("# encoding: ascii-8bit").value[0][0].value.encoding
assert_equal Encoding.find("ascii-8bit"), encoding
end
def test_slice_encoding
slice = Prism.parse("# encoding: Shift_JIS\nア").value.slice
assert_equal (+"ア").force_encoding(Encoding::SHIFT_JIS), slice
assert_equal Encoding::SHIFT_JIS, slice.encoding
end
private
class ConstantContext < BasicObject
def self.const_missing(const)
const
end
end
def constant_context
ConstantContext.new
end
class IdentifierContext < BasicObject
def method_missing(name, *)
name
end
end
def identifier_context
IdentifierContext.new
end
def assert_encoding_constant(name, character)
source = "# encoding: #{name}\n#{character}"
expected = constant_context.instance_eval(source)
result = Prism.parse(source)
assert result.success?
actual = result.value.statements.body.last
assert_kind_of ConstantReadNode, actual
assert_equal expected, actual.name
end
def assert_encoding_identifier(name, character)
source = "# encoding: #{name}\n#{character}"
expected = identifier_context.instance_eval(source)
result = Prism.parse(source)
assert result.success?
actual = result.value.statements.body.last
assert_kind_of CallNode, actual
assert_equal expected, actual.name
end
# Check that we can properly parse every codepoint in the given encoding.
def assert_encoding(encoding, name, range)
# I'm not entirely sure, but I believe these codepoints are incorrect in
# their parsing in CRuby. They all report as matching `[[:lower:]]` but
# then they are parsed as constants. This is because CRuby determines if
# an identifier is a constant or not by case folding it down to lowercase
# and checking if there is a difference. And even though they report
# themselves as lowercase, their case fold is different. I have reported
# this bug upstream.
case encoding
when Encoding::UTF_8, Encoding::UTF_8_MAC, Encoding::UTF8_DoCoMo, Encoding::UTF8_KDDI, Encoding::UTF8_SoftBank, Encoding::CESU_8
range = range.to_a - [
0x01c5, 0x01c8, 0x01cb, 0x01f2, 0x1f88, 0x1f89, 0x1f8a, 0x1f8b,
0x1f8c, 0x1f8d, 0x1f8e, 0x1f8f, 0x1f98, 0x1f99, 0x1f9a, 0x1f9b,
0x1f9c, 0x1f9d, 0x1f9e, 0x1f9f, 0x1fa8, 0x1fa9, 0x1faa, 0x1fab,
0x1fac, 0x1fad, 0x1fae, 0x1faf, 0x1fbc, 0x1fcc, 0x1ffc,
]
when Encoding::Windows_1253
range = range.to_a - [0xb5]
end
range.each do |codepoint|
character = codepoint.chr(encoding)
if character.match?(/[[:alpha:]]/)
if character.match?(/[[:upper:]]/)
assert_encoding_constant(name, character)
else
assert_encoding_identifier(name, character)
end
elsif character.match?(/[[:alnum:]]/)
assert_encoding_identifier(name, "_#{character}")
else
next if ["/", "{"].include?(character)
source = "# encoding: #{name}\n/(?##{character})/\n"
assert Prism.parse(source).success?
end
rescue RangeError
source = "# encoding: #{name}\n\\x#{codepoint.to_s(16)}"
refute Prism.parse(source).success?
end
end
end
end
|