http/uri/
scheme.rs

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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
use std::convert::TryFrom;
use std::fmt;
use std::hash::{Hash, Hasher};
use std::str::FromStr;

use bytes::Bytes;

use super::{ErrorKind, InvalidUri};
use crate::byte_str::ByteStr;

/// Represents the scheme component of a URI
#[derive(Clone)]
pub struct Scheme {
    pub(super) inner: Scheme2,
}

#[derive(Clone, Debug)]
pub(super) enum Scheme2<T = Box<ByteStr>> {
    None,
    Standard(Protocol),
    Other(T),
}

#[derive(Copy, Clone, Debug)]
pub(super) enum Protocol {
    Http,
    Https,
}

impl Scheme {
    /// HTTP protocol scheme
    pub const HTTP: Scheme = Scheme {
        inner: Scheme2::Standard(Protocol::Http),
    };

    /// HTTP protocol over TLS.
    pub const HTTPS: Scheme = Scheme {
        inner: Scheme2::Standard(Protocol::Https),
    };

    pub(super) fn empty() -> Self {
        Scheme {
            inner: Scheme2::None,
        }
    }

    /// Return a str representation of the scheme
    ///
    /// # Examples
    ///
    /// ```
    /// # use http::uri::*;
    /// let scheme: Scheme = "http".parse().unwrap();
    /// assert_eq!(scheme.as_str(), "http");
    /// ```
    #[inline]
    pub fn as_str(&self) -> &str {
        use self::Protocol::*;
        use self::Scheme2::*;

        match self.inner {
            Standard(Http) => "http",
            Standard(Https) => "https",
            Other(ref v) => &v[..],
            None => unreachable!(),
        }
    }
}

impl<'a> TryFrom<&'a [u8]> for Scheme {
    type Error = InvalidUri;
    #[inline]
    fn try_from(s: &'a [u8]) -> Result<Self, Self::Error> {
        use self::Scheme2::*;

        match Scheme2::parse_exact(s)? {
            None => Err(ErrorKind::InvalidScheme.into()),
            Standard(p) => Ok(Standard(p).into()),
            Other(_) => {
                let bytes = Bytes::copy_from_slice(s);

                // Safety: postcondition on parse_exact() means that s and
                // hence bytes are valid UTF-8.
                let string = unsafe { ByteStr::from_utf8_unchecked(bytes) };

                Ok(Other(Box::new(string)).into())
            }
        }
    }
}

impl<'a> TryFrom<&'a str> for Scheme {
    type Error = InvalidUri;
    #[inline]
    fn try_from(s: &'a str) -> Result<Self, Self::Error> {
        TryFrom::try_from(s.as_bytes())
    }
}

impl FromStr for Scheme {
    type Err = InvalidUri;

    fn from_str(s: &str) -> Result<Self, Self::Err> {
        TryFrom::try_from(s)
    }
}

impl fmt::Debug for Scheme {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        fmt::Debug::fmt(self.as_str(), f)
    }
}

impl fmt::Display for Scheme {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.write_str(self.as_str())
    }
}

impl AsRef<str> for Scheme {
    #[inline]
    fn as_ref(&self) -> &str {
        self.as_str()
    }
}

impl PartialEq for Scheme {
    fn eq(&self, other: &Scheme) -> bool {
        use self::Protocol::*;
        use self::Scheme2::*;

        match (&self.inner, &other.inner) {
            (&Standard(Http), &Standard(Http)) => true,
            (&Standard(Https), &Standard(Https)) => true,
            (Other(a), Other(b)) => a.eq_ignore_ascii_case(b),
            (&None, _) | (_, &None) => unreachable!(),
            _ => false,
        }
    }
}

impl Eq for Scheme {}

/// Case-insensitive equality
///
/// # Examples
///
/// ```
/// # use http::uri::Scheme;
/// let scheme: Scheme = "HTTP".parse().unwrap();
/// assert_eq!(scheme, *"http");
/// ```
impl PartialEq<str> for Scheme {
    fn eq(&self, other: &str) -> bool {
        self.as_str().eq_ignore_ascii_case(other)
    }
}

/// Case-insensitive equality
impl PartialEq<Scheme> for str {
    fn eq(&self, other: &Scheme) -> bool {
        other == self
    }
}

/// Case-insensitive hashing
impl Hash for Scheme {
    fn hash<H>(&self, state: &mut H)
    where
        H: Hasher,
    {
        match self.inner {
            Scheme2::None => (),
            Scheme2::Standard(Protocol::Http) => state.write_u8(1),
            Scheme2::Standard(Protocol::Https) => state.write_u8(2),
            Scheme2::Other(ref other) => {
                other.len().hash(state);
                for &b in other.as_bytes() {
                    state.write_u8(b.to_ascii_lowercase());
                }
            }
        }
    }
}

impl<T> Scheme2<T> {
    pub(super) fn is_none(&self) -> bool {
        matches!(*self, Scheme2::None)
    }
}

// Require the scheme to not be too long in order to enable further
// optimizations later.
const MAX_SCHEME_LEN: usize = 64;

// scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
//
// SCHEME_CHARS is a table of valid characters in the scheme part of a URI.  An
// entry in the table is 0 for invalid characters. For valid characters the
// entry is itself (i.e.  the entry for 43 is b'+' because b'+' == 43u8). An
// important characteristic of this table is that all entries above 127 are
// invalid. This makes all of the valid entries a valid single-byte UTF-8 code
// point. This means that a slice of such valid entries is valid UTF-8.
#[rustfmt::skip]
const SCHEME_CHARS: [u8; 256] = [
    //  0      1      2      3      4      5      6      7      8      9
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, //   x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, //  1x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, //  2x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, //  3x
        0,     0,     0,  b'+',     0,  b'-',  b'.',     0,  b'0',  b'1', //  4x
     b'2',  b'3',  b'4',  b'5',  b'6',  b'7',  b'8',  b'9',  b':',     0, //  5x
        0,     0,     0,     0,     0,  b'A',  b'B',  b'C',  b'D',  b'E', //  6x
     b'F',  b'G',  b'H',  b'I',  b'J',  b'K',  b'L',  b'M',  b'N',  b'O', //  7x
     b'P',  b'Q',  b'R',  b'S',  b'T',  b'U',  b'V',  b'W',  b'X',  b'Y', //  8x
     b'Z',     0,     0,     0,     0,     0,     0,  b'a',  b'b',  b'c', //  9x
     b'd',  b'e',  b'f',  b'g',  b'h',  b'i',  b'j',  b'k',  b'l',  b'm', // 10x
     b'n',  b'o',  b'p',  b'q',  b'r',  b's',  b't',  b'u',  b'v',  b'w', // 11x
     b'x',  b'y',  b'z',     0,     0,     0,  b'~',     0,     0,     0, // 12x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 13x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 14x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 15x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 16x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 17x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 18x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 19x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 20x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 21x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 22x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 23x
        0,     0,     0,     0,     0,     0,     0,     0,     0,     0, // 24x
        0,     0,     0,     0,     0,     0                              // 25x
];

impl Scheme2<usize> {
    // Postcondition: On all Ok() returns, s is valid UTF-8
    fn parse_exact(s: &[u8]) -> Result<Scheme2<()>, InvalidUri> {
        match s {
            b"http" => Ok(Protocol::Http.into()),
            b"https" => Ok(Protocol::Https.into()),
            _ => {
                if s.len() > MAX_SCHEME_LEN {
                    return Err(ErrorKind::SchemeTooLong.into());
                }

                // check that each byte in s is a SCHEME_CHARS which implies
                // that it is a valid single byte UTF-8 code point.
                for &b in s {
                    match SCHEME_CHARS[b as usize] {
                        b':' => {
                            // Don't want :// here
                            return Err(ErrorKind::InvalidScheme.into());
                        }
                        0 => {
                            return Err(ErrorKind::InvalidScheme.into());
                        }
                        _ => {}
                    }
                }

                Ok(Scheme2::Other(()))
            }
        }
    }

    pub(super) fn parse(s: &[u8]) -> Result<Scheme2<usize>, InvalidUri> {
        if s.len() >= 7 {
            // Check for HTTP
            if s[..7].eq_ignore_ascii_case(b"http://") {
                // Prefix will be striped
                return Ok(Protocol::Http.into());
            }
        }

        if s.len() >= 8 {
            // Check for HTTPs
            if s[..8].eq_ignore_ascii_case(b"https://") {
                return Ok(Protocol::Https.into());
            }
        }

        if s.len() > 3 {
            for i in 0..s.len() {
                let b = s[i];

                match SCHEME_CHARS[b as usize] {
                    b':' => {
                        // Not enough data remaining
                        if s.len() < i + 3 {
                            break;
                        }

                        // Not a scheme
                        if &s[i + 1..i + 3] != b"//" {
                            break;
                        }

                        if i > MAX_SCHEME_LEN {
                            return Err(ErrorKind::SchemeTooLong.into());
                        }

                        // Return scheme
                        return Ok(Scheme2::Other(i));
                    }
                    // Invald scheme character, abort
                    0 => break,
                    _ => {}
                }
            }
        }

        Ok(Scheme2::None)
    }
}

impl Protocol {
    pub(super) fn len(&self) -> usize {
        match *self {
            Protocol::Http => 4,
            Protocol::Https => 5,
        }
    }
}

impl<T> From<Protocol> for Scheme2<T> {
    fn from(src: Protocol) -> Self {
        Scheme2::Standard(src)
    }
}

#[doc(hidden)]
impl From<Scheme2> for Scheme {
    fn from(src: Scheme2) -> Self {
        Scheme { inner: src }
    }
}

#[cfg(test)]
mod test {
    use super::*;

    #[test]
    fn scheme_eq_to_str() {
        assert_eq!(&scheme("http"), "http");
        assert_eq!(&scheme("https"), "https");
        assert_eq!(&scheme("ftp"), "ftp");
        assert_eq!(&scheme("my+funky+scheme"), "my+funky+scheme");
    }

    #[test]
    fn invalid_scheme_is_error() {
        Scheme::try_from("my_funky_scheme").expect_err("Unexpectly valid Scheme");

        // Invalid UTF-8
        Scheme::try_from([0xC0].as_ref()).expect_err("Unexpectly valid Scheme");
    }

    fn scheme(s: &str) -> Scheme {
        s.parse().expect(&format!("Invalid scheme: {}", s))
    }
}