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
|
// Copyright 2013-2014 The rust-url developers.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
use crate::test::TestFn;
use std::char;
use idna::Errors;
pub fn collect_tests<F: FnMut(String, TestFn)>(add_test: &mut F) {
// https://www.unicode.org/Public/idna/13.0.0/IdnaTestV2.txt
for (i, line) in include_str!("IdnaTestV2.txt").lines().enumerate() {
if line.is_empty() || line.starts_with('#') {
continue;
}
// Remove comments
let line = match line.find('#') {
Some(index) => &line[0..index],
None => line,
};
let mut pieces = line.split(';').map(|x| x.trim()).collect::<Vec<&str>>();
let source = unescape(&pieces.remove(0));
// ToUnicode
let mut to_unicode = unescape(&pieces.remove(0));
if to_unicode.is_empty() {
to_unicode = source.clone();
}
let to_unicode_status = status(pieces.remove(0));
// ToAsciiN
let to_ascii_n = pieces.remove(0);
let to_ascii_n = if to_ascii_n.is_empty() {
to_unicode.clone()
} else {
to_ascii_n.to_owned()
};
let to_ascii_n_status = pieces.remove(0);
let to_ascii_n_status = if to_ascii_n_status.is_empty() {
to_unicode_status.clone()
} else {
status(to_ascii_n_status)
};
// ToAsciiT
let to_ascii_t = pieces.remove(0);
let to_ascii_t = if to_ascii_t.is_empty() {
to_ascii_n.clone()
} else {
to_ascii_t.to_owned()
};
let to_ascii_t_status = pieces.remove(0);
let to_ascii_t_status = if to_ascii_t_status.is_empty() {
to_ascii_n_status.clone()
} else {
status(to_ascii_t_status)
};
let test_name = format!("UTS #46 line {}", i + 1);
add_test(
test_name,
TestFn::dyn_test_fn(move || {
let config = idna::Config::default()
.use_std3_ascii_rules(true)
.verify_dns_length(true)
.check_hyphens(true);
// http://unicode.org/reports/tr46/#Deviations
// applications that perform IDNA2008 lookup are not required to check
// for these contexts, so we skip all tests annotated with C*
// Everybody ignores V2
// https://github.com/servo/rust-url/pull/240
// https://github.com/whatwg/url/issues/53#issuecomment-181528158
// http://www.unicode.org/review/pri317/
// "The special error codes X3 and X4_2 are now returned where a toASCII error code
// was formerly being generated in toUnicode due to an empty label."
// This is not implemented yet, so we skip toUnicode X4_2 tests for now, too.
let (to_unicode_value, to_unicode_result) =
config.transitional_processing(false).to_unicode(&source);
let to_unicode_result = to_unicode_result.map(|()| to_unicode_value);
check(
&source,
(&to_unicode, &to_unicode_status),
to_unicode_result,
|e| e.starts_with('C') || e == "V2" || e == "X4_2",
);
let to_ascii_n_result = config.transitional_processing(false).to_ascii(&source);
check(
&source,
(&to_ascii_n, &to_ascii_n_status),
to_ascii_n_result,
|e| e.starts_with('C') || e == "V2",
);
let to_ascii_t_result = config.transitional_processing(true).to_ascii(&source);
check(
&source,
(&to_ascii_t, &to_ascii_t_status),
to_ascii_t_result,
|e| e.starts_with('C') || e == "V2",
);
}),
)
}
}
#[allow(clippy::redundant_clone)]
fn check<F>(source: &str, expected: (&str, &[&str]), actual: Result<String, Errors>, ignore: F)
where
F: Fn(&str) -> bool,
{
if !expected.1.is_empty() {
if !expected.1.iter().copied().any(ignore) {
let res = actual.ok();
assert_eq!(
res.clone(),
None,
"Expected error {:?}. result: {} | source: {}",
expected.1,
res.unwrap(),
source,
);
}
} else {
assert!(
actual.is_ok(),
"Couldn't parse {} | error: {:?}",
source,
actual.err().unwrap(),
);
assert_eq!(actual.unwrap(), expected.0, "source: {}", source);
}
}
fn unescape(input: &str) -> String {
let mut output = String::new();
let mut chars = input.chars();
loop {
match chars.next() {
None => return output,
Some(c) => {
if c == '\\' {
match chars.next().unwrap() {
'\\' => output.push('\\'),
'u' => {
let c1 = chars.next().unwrap().to_digit(16).unwrap();
let c2 = chars.next().unwrap().to_digit(16).unwrap();
let c3 = chars.next().unwrap().to_digit(16).unwrap();
let c4 = chars.next().unwrap().to_digit(16).unwrap();
match char::from_u32(((c1 * 16 + c2) * 16 + c3) * 16 + c4) {
Some(c) => output.push(c),
None => {
output
.push_str(&format!("\\u{:X}{:X}{:X}{:X}", c1, c2, c3, c4));
}
};
}
_ => panic!("Invalid test data input"),
}
} else {
output.push(c);
}
}
}
}
}
fn status(status: &str) -> Vec<&str> {
if status.is_empty() || status == "[]" {
return Vec::new();
}
let mut result = status.split(", ").collect::<Vec<_>>();
assert!(result[0].starts_with('['));
result[0] = &result[0][1..];
let idx = result.len() - 1;
let last = &mut result[idx];
assert!(last.ends_with(']'));
*last = &last[..last.len() - 1];
result
}
|
