uriparse 0.6.4

A URI parser including relative references
Documentation 
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

use std::hash::{Hash, Hasher};

#[rustfmt::skip]
pub const UNRESERVED_CHAR_MAP: [u8; 256] = [
 // 0     1     2     3     4     5     6     7     8     9     A     B     C     D     E     F
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // 0
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // 1
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, b'-', b'.',    0, // 2
 b'0', b'1', b'2', b'3', b'4', b'5', b'6', b'7', b'8', b'9',    0,    0,    0,    0,    0,    0, // 3
    0, b'A', b'B', b'C', b'D', b'E', b'F', b'G', b'H', b'I', b'J', b'K', b'L', b'M', b'N', b'O', // 4
 b'P', b'Q', b'R', b'S', b'T', b'U', b'V', b'W', b'X', b'Y', b'Z',    0,    0,    0,    0, b'_', // 5
    0, b'a', b'b', b'c', b'd', b'e', b'f', b'g', b'h', b'i', b'j', b'k', b'l', b'm', b'n', b'o', // 6
 b'p', b'q', b'r', b's', b't', b'u', b'v', b'w', b'x', b'y', b'z',    0,    0,    0, b'~',    0, // 7
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // 8
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // 9
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // A
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // B
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // C
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // D
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // E
    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0, // F
];

pub fn get_percent_encoded_value(
    first_digit: Option<u8>,
    second_digit: Option<u8>,
) -> Result<(u8, bool), ()> {
    match (first_digit, second_digit) {
        (Some(first_digit), Some(second_digit)) => {
            let first_digit = hex_digit_to_decimal(first_digit)?;
            let second_digit = hex_digit_to_decimal(second_digit)?;
            let hex_value = first_digit.0 * 16 + second_digit.0;
            let uppercase = first_digit.1 && second_digit.1;
            Ok((hex_value, uppercase))
        }
        _ => Err(()),
    }
}

fn hex_digit_to_decimal(digit: u8) -> Result<(u8, bool), ()> {
    match digit {
        _ if digit >= b'A' && digit <= b'F' => Ok((digit - b'A' + 10, true)),
        _ if digit >= b'a' && digit <= b'f' => Ok((digit - b'a' + 10, false)),
        _ if digit.is_ascii_digit() => Ok((digit - b'0', true)),
        _ => Err(()),
    }
}

/// This function is unsafe because it makes the assumption that the given string is valid ASCII-US.
pub unsafe fn normalize_string(string: &mut String, case_sensitive: bool) {
    let bytes = string.as_mut_vec();
    let mut read_index = 0;
    let mut write_index = 0;

    while read_index < bytes.len() {
        let byte = bytes[read_index];
        read_index += 1;

        if byte == b'%' {
            let first_digit = bytes.get(read_index).cloned();
            let second_digit = bytes.get(read_index + 1).cloned();
            let (hex_value, _) = get_percent_encoded_value(first_digit, second_digit).unwrap();
            read_index += 2;

            if UNRESERVED_CHAR_MAP[hex_value as usize] != 0 {
                bytes[write_index] = hex_value;
                write_index += 1;
            } else {
                bytes[write_index] = b'%';
                bytes[write_index + 1] = first_digit.unwrap().to_ascii_uppercase();
                bytes[write_index + 2] = second_digit.unwrap().to_ascii_uppercase();
                write_index += 3;
            }
        } else {
            if !case_sensitive {
                bytes[write_index] = byte.to_ascii_lowercase();
            } else {
                bytes[write_index] = byte;
            }

            write_index += 1;
        }
    }

    bytes.truncate(write_index);
}

pub fn percent_encoded_hash<H>(value: &[u8], state: &mut H, case_sensitive: bool)
where
    H: Hasher,
{
    let mut bytes = value.iter();
    let mut length = 0;

    while let Some(byte) = bytes.next() {
        length += 1;

        match byte {
            b'%' => {
                let first_digit = bytes.next().cloned();
                let second_digit = bytes.next().cloned();
                let (hex_value, _) = get_percent_encoded_value(first_digit, second_digit).unwrap();

                if UNRESERVED_CHAR_MAP[hex_value as usize] == 0 {
                    b'%'.hash(state);
                    first_digit.unwrap().to_ascii_uppercase().hash(state);
                    second_digit.unwrap().to_ascii_uppercase().hash(state);
                } else if case_sensitive {
                    hex_value.hash(state);
                } else {
                    hex_value.to_ascii_lowercase().hash(state);
                }
            }
            _ => {
                if case_sensitive {
                    byte.hash(state)
                } else {
                    byte.to_ascii_lowercase().hash(state)
                }
            }
        }
    }

    length.hash(state);
}

fn percent_encoded_equality_helper(
    byte: u8,
    first_digit: Option<u8>,
    second_digit: Option<u8>,
    case_sensitive: bool,
) -> bool {
    if UNRESERVED_CHAR_MAP[byte as usize] == 0 {
        return false;
    }

    match get_percent_encoded_value(first_digit, second_digit) {
        Ok((hex_value, _)) => {
            if case_sensitive {
                hex_value == byte
            } else {
                hex_value.eq_ignore_ascii_case(&byte)
            }
        }
        Err(_) => false,
    }
}

pub fn percent_encoded_equality(left: &[u8], right: &[u8], case_sensitive: bool) -> bool {
    let mut left_bytes = left.iter();
    let mut right_bytes = right.iter();

    loop {
        match (left_bytes.next(), right_bytes.next()) {
            (Some(b'%'), Some(b'%')) => (),
            (Some(b'%'), Some(&right_byte)) => {
                if !percent_encoded_equality_helper(
                    right_byte,
                    left_bytes.next().cloned(),
                    left_bytes.next().cloned(),
                    case_sensitive,
                ) {
                    return false;
                }
            }
            (Some(&left_byte), Some(b'%')) => {
                if !percent_encoded_equality_helper(
                    left_byte,
                    right_bytes.next().cloned(),
                    right_bytes.next().cloned(),
                    case_sensitive,
                ) {
                    return false;
                }
            }
            (Some(left_byte), Some(right_byte)) => {
                let equal = if case_sensitive {
                    left_byte == right_byte
                } else {
                    left_byte.eq_ignore_ascii_case(&right_byte)
                };

                if !equal {
                    return false;
                }
            }
            (None, None) => return true,
            _ => return false,
        }
    }
}

#[cfg(test)]
mod test {
    use std::collections::hash_map::RandomState;
    use std::hash::BuildHasher;

    use super::*;

    #[test]
    fn test_equality() {
        // Case sensitive

        assert!(percent_encoded_equality(b"abc", b"abc", true));
        assert!(percent_encoded_equality(b"abc", b"%61bc", true));
        assert!(percent_encoded_equality(b"MNO", b"%4DNO", true));
        assert!(percent_encoded_equality(b"MNO", b"%4dNO", true));

        assert!(!percent_encoded_equality(b"abc", b"xyz", true));
        assert!(!percent_encoded_equality(b"abc", b"Abc", true));
        assert!(!percent_encoded_equality(b"abc", b"%41bc", true));
        assert!(!percent_encoded_equality(b"/", b"%2F", true));

        // Case insensitive

        assert!(percent_encoded_equality(b"abc", b"abc", false));
        assert!(percent_encoded_equality(b"abc", b"ABC", false));
        assert!(percent_encoded_equality(b"MNO", b"%4DNO", false));
        assert!(percent_encoded_equality(b"MNO", b"%4dNO", false));
        assert!(percent_encoded_equality(b"abc", b"%61bc", false));
        assert!(percent_encoded_equality(b"abc", b"%41bc", false));

        assert!(!percent_encoded_equality(b"abc", b"xyz", false));
        assert!(!percent_encoded_equality(b"/", b"%2F", false));
    }

    #[test]
    fn test_hash() {
        fn hash<State>(value: &[u8], state: &State, case_sensitive: bool) -> u64
        where
            State: BuildHasher,
        {
            let mut hasher = state.build_hasher();
            percent_encoded_hash(value, &mut hasher, case_sensitive);
            hasher.finish()
        }

        fn compare_hashes<State>(
            left: &[u8],
            right: &[u8],
            state: &State,
            case_sensitive: bool,
        ) -> bool
        where
            State: BuildHasher,
        {
            let left_hash = hash(left, state, case_sensitive);
            let right_hash = hash(right, state, case_sensitive);
            left_hash == right_hash
        }

        let state = RandomState::new();

        // Case sensitive

        assert!(compare_hashes(b"abc", b"abc", &state, true));
        assert!(compare_hashes(b"abc", b"%61bc", &state, true));
        assert!(compare_hashes(b"MNO", b"%4DNO", &state, true));
        assert!(compare_hashes(b"MNO", b"%4dNO", &state, true));

        assert!(!compare_hashes(b"abc", b"xyz", &state, true));
        assert!(!compare_hashes(b"abc", b"Abc", &state, true));
        assert!(!compare_hashes(b"abc", b"%41bc", &state, true));
        assert!(!compare_hashes(b"/", b"%2F", &state, true));

        // Case insensitive

        assert!(compare_hashes(b"abc", b"abc", &state, false));
        assert!(compare_hashes(b"abc", b"ABC", &state, false));
        assert!(compare_hashes(b"MNO", b"%4DNO", &state, false));
        assert!(compare_hashes(b"MNO", b"%4dNO", &state, false));
        assert!(compare_hashes(b"abc", b"%61bc", &state, false));
        assert!(compare_hashes(b"abc", b"%41bc", &state, false));

        assert!(!compare_hashes(b"abc", b"xyz", &state, false));
        assert!(!compare_hashes(b"/", b"%2F", &state, false));
    }
}