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
// Copyright 2015 The tiny-http Contributors
// Copyright 2015 The rust-chunked-transfer Contributors
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//	http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

use std::error::Error;
use std::fmt;
use std::io::Error as IoError;
use std::io::ErrorKind;
use std::io::Read;
use std::io::Result as IoResult;

/// Reads HTTP chunks and sends back real data.
///
/// # Example
///
/// ```
/// use chunked_transfer::Decoder;
/// use std::io::Read;
///
/// let encoded = b"3\r\nhel\r\nb\r\nlo world!!!\r\n0\r\n\r\n";
/// let mut decoded = String::new();
///
/// let mut decoder = Decoder::new(encoded as &[u8]);
/// decoder.read_to_string(&mut decoded);
///
/// assert_eq!(decoded, "hello world!!!");
/// ```
pub struct Decoder<R> {
    // where the chunks come from
    source: R,

    // remaining size of the chunk being read
    // none if we are not in a chunk
    remaining_chunks_size: Option<usize>,
}

impl<R> Decoder<R>
where
    R: Read,
{
    pub fn new(source: R) -> Decoder<R> {
        Decoder {
            source,
            remaining_chunks_size: None,
        }
    }

    /// Unwraps the Decoder into its inner `Read` source.
    pub fn into_inner(self) -> R {
        self.source
    }

    fn read_chunk_size(&mut self) -> IoResult<usize> {
        let mut chunk_size_bytes = Vec::new();
        let mut has_ext = false;

        loop {
            let byte = match self.source.by_ref().bytes().next() {
                Some(b) => b?,
                None => return Err(IoError::new(ErrorKind::InvalidInput, DecoderError)),
            };

            if byte == b'\r' {
                break;
            }

            if byte == b';' {
                has_ext = true;
                break;
            }

            chunk_size_bytes.push(byte);
        }

        // Ignore extensions for now
        if has_ext {
            loop {
                let byte = match self.source.by_ref().bytes().next() {
                    Some(b) => b?,
                    None => return Err(IoError::new(ErrorKind::InvalidInput, DecoderError)),
                };
                if byte == b'\r' {
                    break;
                }
            }
        }

        self.read_line_feed()?;

        let chunk_size = String::from_utf8(chunk_size_bytes)
            .ok()
            .and_then(|c| usize::from_str_radix(c.trim(), 16).ok())
            .ok_or(IoError::new(ErrorKind::InvalidInput, DecoderError))?;

        Ok(chunk_size)
    }

    fn read_carriage_return(&mut self) -> IoResult<()> {
        match self.source.by_ref().bytes().next() {
            Some(Ok(b'\r')) => Ok(()),
            _ => Err(IoError::new(ErrorKind::InvalidInput, DecoderError)),
        }
    }

    fn read_line_feed(&mut self) -> IoResult<()> {
        match self.source.by_ref().bytes().next() {
            Some(Ok(b'\n')) => Ok(()),
            _ => Err(IoError::new(ErrorKind::InvalidInput, DecoderError)),
        }
    }
}

impl<R> Read for Decoder<R>
where
    R: Read,
{
    fn read(&mut self, buf: &mut [u8]) -> IoResult<usize> {
        let remaining_chunks_size = match self.remaining_chunks_size {
            Some(c) => c,
            None => {
                // first possibility: we are not in a chunk, so we'll attempt to determine
                // the chunks size
                let chunk_size = self.read_chunk_size()?;

                // if the chunk size is 0, we are at EOF
                if chunk_size == 0 {
                    self.read_carriage_return()?;
                    self.read_line_feed()?;
                    return Ok(0);
                }

                chunk_size
            }
        };

        // second possibility: we continue reading from a chunk
        if buf.len() < remaining_chunks_size {
            let read = self.source.read(buf)?;
            self.remaining_chunks_size = Some(remaining_chunks_size - read);
            return Ok(read);
        }

        // third possibility: the read request goes further than the current chunk
        // we simply read until the end of the chunk and return
        assert!(buf.len() >= remaining_chunks_size);

        let buf = &mut buf[..remaining_chunks_size];
        let read = self.source.read(buf)?;

        self.remaining_chunks_size = if read == remaining_chunks_size {
            self.read_carriage_return()?;
            self.read_line_feed()?;
            None
        } else {
            Some(remaining_chunks_size - read)
        };

        Ok(read)
    }
}

#[derive(Debug, Copy, Clone)]
struct DecoderError;

impl fmt::Display for DecoderError {
    fn fmt(&self, fmt: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
        write!(fmt, "Error while decoding chunks")
    }
}

impl Error for DecoderError {
    fn description(&self) -> &str {
        "Error while decoding chunks"
    }
}

#[cfg(test)]
mod test {
    use super::Decoder;
    use std::io;
    use std::io::Read;

    /// This unit test is taken from from Hyper
    /// https://github.com/hyperium/hyper
    /// Copyright (c) 2014 Sean McArthur
    #[test]
    fn test_read_chunk_size() {
        fn read(s: &str, expected: usize) {
            let mut decoded = Decoder::new(s.as_bytes());
            let actual = decoded.read_chunk_size().unwrap();
            assert_eq!(expected, actual);
        }

        fn read_err(s: &str) {
            let mut decoded = Decoder::new(s.as_bytes());
            let err_kind = decoded.read_chunk_size().unwrap_err().kind();
            assert_eq!(err_kind, io::ErrorKind::InvalidInput);
        }

        read("1\r\n", 1);
        read("01\r\n", 1);
        read("0\r\n", 0);
        read("00\r\n", 0);
        read("A\r\n", 10);
        read("a\r\n", 10);
        read("Ff\r\n", 255);
        read("Ff   \r\n", 255);
        // Missing LF or CRLF
        read_err("F\rF");
        read_err("F");
        // Invalid hex digit
        read_err("X\r\n");
        read_err("1X\r\n");
        read_err("-\r\n");
        read_err("-1\r\n");
        // Acceptable (if not fully valid) extensions do not influence the size
        read("1;extension\r\n", 1);
        read("a;ext name=value\r\n", 10);
        read("1;extension;extension2\r\n", 1);
        read("1;;;  ;\r\n", 1);
        read("2; extension...\r\n", 2);
        read("3   ; extension=123\r\n", 3);
        read("3   ;\r\n", 3);
        read("3   ;   \r\n", 3);
        // Invalid extensions cause an error
        read_err("1 invalid extension\r\n");
        read_err("1 A\r\n");
        read_err("1;no CRLF");
    }

    #[test]
    fn test_valid_chunk_decode() {
        let source = io::Cursor::new(
            "3\r\nhel\r\nb\r\nlo world!!!\r\n0\r\n\r\n"
                .to_string()
                .into_bytes(),
        );
        let mut decoded = Decoder::new(source);

        let mut string = String::new();
        decoded.read_to_string(&mut string).unwrap();

        assert_eq!(string, "hello world!!!");
    }

    #[test]
    fn test_decode_zero_length() {
        let mut decoder = Decoder::new(b"0\r\n\r\n" as &[u8]);

        let mut decoded = String::new();
        decoder.read_to_string(&mut decoded).unwrap();

        assert_eq!(decoded, "");
    }

    #[test]
    fn test_decode_invalid_chunk_length() {
        let mut decoder = Decoder::new(b"m\r\n\r\n" as &[u8]);

        let mut decoded = String::new();
        assert!(decoder.read_to_string(&mut decoded).is_err());
    }

    #[test]
    fn invalid_input1() {
        let source = io::Cursor::new(
            "2\r\nhel\r\nb\r\nlo world!!!\r\n0\r\n"
                .to_string()
                .into_bytes(),
        );
        let mut decoded = Decoder::new(source);

        let mut string = String::new();
        assert!(decoded.read_to_string(&mut string).is_err());
    }

    #[test]
    fn invalid_input2() {
        let source = io::Cursor::new(
            "3\rhel\r\nb\r\nlo world!!!\r\n0\r\n"
                .to_string()
                .into_bytes(),
        );
        let mut decoded = Decoder::new(source);

        let mut string = String::new();
        assert!(decoded.read_to_string(&mut string).is_err());
    }
}