cshannon 0.2.1

An implementation of compression algorithms leading up to Huffman's encoding
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

// Copyright 2020 Prathmesh Prabhu
//
// 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.

//! bytes module implements tokenization of a string into bytes.
//!
//! The stream makes zero copies internally while iterating over the stream.

use crate::tokens::{Token, TokenPacker, Tokenizer};
use anyhow::{Error, Result};
use std::convert::From;
use std::fmt;
use std::hash::Hash;

/// A [`Token`] consisting of a single byte of data.
#[derive(Clone, Copy, Debug, Default, Eq, Hash, Ord, PartialEq, PartialOrd)]
pub struct Byte(u8);

impl std::fmt::Display for Byte {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(f, "{:#04x}", &self.0)
    }
}

impl Token for Byte {
    type Tokenizer = ByteTokenizer;
    type Packer = BytePacker;

    fn bit_count(&self) -> usize {
        8
    }
}

impl From<u8> for Byte {
    fn from(data: u8) -> Self {
        Self(data)
    }
}

pub struct ByteTokenizer;

impl Tokenizer for ByteTokenizer {
    type T = Byte;
    type Iter<R: std::io::Read> = ByteIter<R>;

    fn tokenize<R: std::io::Read>(r: R) -> Result<Self::Iter<R>> {
        Ok(ByteIter(r))
    }
}

/// Provides a method to create a [`Byte`] stream from text.
#[derive(Clone, Debug)]
pub struct ByteIter<R: std::io::Read>(R);

impl<R: std::io::Read> std::iter::Iterator for ByteIter<R> {
    type Item = Result<Byte>;
    fn next(&mut self) -> Option<Self::Item> {
        let mut buf: [u8; 1] = [0; 1];
        match self.0.read(&mut buf[..]) {
            Err(e) => Some(Err(Error::new(e))),
            Ok(0) => None,
            Ok(1) => Some(Ok(Byte(buf[0]))),
            Ok(l) => panic!("read {} bytes in 1 byte buffer", l),
        }
    }
}

/// Provides a method to pack a [`Byte`] stream to text.
#[derive(Clone, Debug, Default)]
pub struct BytePacker;

impl TokenPacker for BytePacker {
    type T = Byte;

    fn pack<I, W: std::io::Write>(i: I, mut w: W) -> Result<()>
    where
        I: std::iter::Iterator<Item = Self::T>,
    {
        let mut buf: [u8; 1] = [0; 1];
        for b in i {
            buf[0] = b.0;
            if let Err(e) = w.write_all(&buf[..]) {
                return Err(Error::new(e));
            }
        }
        w.flush()?;
        Ok(())
    }
}

#[cfg(test)]
mod tests {
    use super::*;
    use std::io::Cursor;

    const TEXT: &str = "
Ah! well a-day! what evil looks
Had I from old and young!
Instead of the cross, the Albatross
About my neck was hung.
";
    #[test]
    fn roundtrip() {
        let mut r = Cursor::new(TEXT);
        let d = ByteTokenizer::tokenize(&mut r).unwrap();
        let i = d.map(|t| t.unwrap());
        let mut wc: Cursor<Vec<u8>> = Cursor::new(vec![]);
        BytePacker::pack(i, &mut wc).unwrap();
        let got = std::str::from_utf8(&wc.get_ref()[..]).unwrap();
        assert_eq!(got, TEXT);
    }
}