omnom

Trait BufReadExt

Source 
pub trait BufReadExt: BufRead {
    // Provided methods
    fn read_while<P>(
        &mut self,
        buf: &mut Vec<u8>,
        predicate: P,
    ) -> Result<usize>
       where P: FnMut(u8) -> bool { ... }
    fn skip(&mut self, n: usize) -> Result<()> { ... }
    fn skip_while<P>(&mut self, predicate: P) -> Result<usize>
       where P: FnMut(u8) -> bool { ... }
    fn skip_until(&mut self, byte: u8) -> Result<usize> { ... }
}
Expand description

Extend BufRead with methods for streaming parsing.

Provided Methods§

Source

fn read_while<P>(&mut self, buf: &mut Vec<u8>, predicate: P) -> Result<usize>
where P: FnMut(u8) -> bool,

Read bytes based on a predicate.

read_while takes a predicate as an argument. It will call this on each byte, and copy it to the slice if the predicate evaluates to true. Returns the amount of bytes read.

§Errors

If this function encounters an error of the kind ErrorKind::Interrupted then the error is ignored and the operation will continue.

If any other read error is encountered then this function immediately returns. Any bytes which have already been read will be appended to buf.

§Examples

[std::io::Cursor][Cursor] is a type that implements BufRead. In this example, we use [Cursor] to read bytes in a byte slice until we encounter a hyphen:

use std::io::{self, BufRead};
use omnom::prelude::*;

let mut cursor = io::Cursor::new(b"lorem-ipsum");
let mut buf = vec![];

let num_bytes = cursor.read_while(&mut buf, |b| b != b'-')
    .expect("reading from cursor won't fail");
assert_eq!(buf, b"lorem");
Examples found in repository?
examples/mime.rs (line 96)
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
fn parse_mime(s: &str) -> Option<Mime> {
    // parse the "type"
    //
    // ```txt
    // text/html; charset=utf-8;
    // ^^^^^
    // ```
    let mut s = Cursor::new(s);
    let mut base_type = vec![];
    match s.read_until(b'/', &mut base_type).unwrap() {
        0 => return None,
        _ => base_type.pop(),
    };
    validate_code_points(&base_type)?;

    // parse the "subtype"
    //
    // ```txt
    // text/html; charset=utf-8;
    //      ^^^^^
    // ```
    let mut sub_type = vec![];
    s.read_until(b';', &mut sub_type).unwrap();
    if let Some(b';') = sub_type.last() {
        sub_type.pop();
    }
    validate_code_points(&sub_type)?;

    // instantiate our mime struct
    let mut mime = Mime {
        base_type: String::from_utf8(base_type).unwrap(),
        sub_type: String::from_utf8(sub_type).unwrap(),
        parameters: None,
    };

    // parse parameters into a hashmap
    //
    // ```txt
    // text/html; charset=utf-8;
    //           ^^^^^^^^^^^^^^^
    // ```
    loop {
        // Stop parsing if there's no more bytes to consume.
        if s.fill_buf().unwrap().len() == 0 {
            break;
        }

        // Trim any whitespace.
        //
        // ```txt
        // text/html; charset=utf-8;
        //           ^
        // ```
        s.skip_while(is_http_whitespace_char).ok()?;

        // Get the param name.
        //
        // ```txt
        // text/html; charset=utf-8;
        //            ^^^^^^^
        // ```
        let mut param_name = vec![];
        s.read_while(&mut param_name, |b| b != b';' && b != b'=')
            .ok()?;
        validate_code_points(&param_name)?;
        let mut param_name = String::from_utf8(param_name).ok()?;
        param_name.make_ascii_lowercase();

        // Ignore param names without values.
        //
        // ```txt
        // text/html; charset=utf-8;
        //                   ^
        // ```
        let mut token = vec![0; 1];
        s.read_exact(&mut token).unwrap();
        if token[0] == b';' {
            continue;
        }

        // Get the param value.
        //
        // ```txt
        // text/html; charset=utf-8;
        //                    ^^^^^^
        // ```
        let mut param_value = vec![];
        s.read_until(b';', &mut param_value).ok()?;
        if let Some(b';') = param_value.last() {
            param_value.pop();
        }
        validate_code_points(&param_value)?;
        let mut param_value = String::from_utf8(param_value).ok()?;
        param_value.make_ascii_lowercase();

        // Insert attribute pair into hashmap.
        if let None = mime.parameters {
            mime.parameters = Some(HashMap::new());
        }
        mime.parameters.as_mut()?.insert(param_name, param_value);
    }

    Some(mime)
}
Source

fn skip(&mut self, n: usize) -> Result<()>

Skip the first n bytes.

Source

fn skip_while<P>(&mut self, predicate: P) -> Result<usize>
where P: FnMut(u8) -> bool,

Skip bytes while the predicate is true.

Examples found in repository?
examples/mime.rs (line 87)
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
fn parse_mime(s: &str) -> Option<Mime> {
    // parse the "type"
    //
    // ```txt
    // text/html; charset=utf-8;
    // ^^^^^
    // ```
    let mut s = Cursor::new(s);
    let mut base_type = vec![];
    match s.read_until(b'/', &mut base_type).unwrap() {
        0 => return None,
        _ => base_type.pop(),
    };
    validate_code_points(&base_type)?;

    // parse the "subtype"
    //
    // ```txt
    // text/html; charset=utf-8;
    //      ^^^^^
    // ```
    let mut sub_type = vec![];
    s.read_until(b';', &mut sub_type).unwrap();
    if let Some(b';') = sub_type.last() {
        sub_type.pop();
    }
    validate_code_points(&sub_type)?;

    // instantiate our mime struct
    let mut mime = Mime {
        base_type: String::from_utf8(base_type).unwrap(),
        sub_type: String::from_utf8(sub_type).unwrap(),
        parameters: None,
    };

    // parse parameters into a hashmap
    //
    // ```txt
    // text/html; charset=utf-8;
    //           ^^^^^^^^^^^^^^^
    // ```
    loop {
        // Stop parsing if there's no more bytes to consume.
        if s.fill_buf().unwrap().len() == 0 {
            break;
        }

        // Trim any whitespace.
        //
        // ```txt
        // text/html; charset=utf-8;
        //           ^
        // ```
        s.skip_while(is_http_whitespace_char).ok()?;

        // Get the param name.
        //
        // ```txt
        // text/html; charset=utf-8;
        //            ^^^^^^^
        // ```
        let mut param_name = vec![];
        s.read_while(&mut param_name, |b| b != b';' && b != b'=')
            .ok()?;
        validate_code_points(&param_name)?;
        let mut param_name = String::from_utf8(param_name).ok()?;
        param_name.make_ascii_lowercase();

        // Ignore param names without values.
        //
        // ```txt
        // text/html; charset=utf-8;
        //                   ^
        // ```
        let mut token = vec![0; 1];
        s.read_exact(&mut token).unwrap();
        if token[0] == b';' {
            continue;
        }

        // Get the param value.
        //
        // ```txt
        // text/html; charset=utf-8;
        //                    ^^^^^^
        // ```
        let mut param_value = vec![];
        s.read_until(b';', &mut param_value).ok()?;
        if let Some(b';') = param_value.last() {
            param_value.pop();
        }
        validate_code_points(&param_value)?;
        let mut param_value = String::from_utf8(param_value).ok()?;
        param_value.make_ascii_lowercase();

        // Insert attribute pair into hashmap.
        if let None = mime.parameters {
            mime.parameters = Some(HashMap::new());
        }
        mime.parameters.as_mut()?.insert(param_name, param_value);
    }

    Some(mime)
}
Source

fn skip_until(&mut self, byte: u8) -> Result<usize>

Skip bytes until the delimiter byte or EOF is reached.

This function will read bytes from the underlying stream until the delimiter or EOF is found. Once found, all bytes up to, and including, the delimiter (if found) will be skipped.

If successful, this function will return the total number of bytes read.

§Errors

This function will ignore all instances of ErrorKind::Interrupted and will otherwise return any errors returned by BufRead::fill_buf.

If an I/O error is encountered then all bytes read so far will be present in buf and its length will have been adjusted appropriately.

§Examples

std::io::Cursor is a type that implements BufRead. In this example, we use Cursor to read all the bytes in a byte slice in hyphen delimited segments:

use std::io::{self, BufRead, Read};
use omnom::prelude::*;

let mut cursor = io::Cursor::new(b"lorem-ipsum");

// skip up to and including '-'
let num_bytes = cursor.skip_until(b'-').unwrap();
assert_eq!(num_bytes, 6);

// read the rest of the bytes
let mut buf = [0; 5];
cursor.read_exact(&mut buf).unwrap();
assert_eq!(&buf, b"ipsum");

Dyn Compatibility§

This trait is not dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety", so this trait is not object safe.

Implementors§