Struct WarcRecord

pub struct WarcRecord {
    pub version: String,
    pub header: HashMap<CaseString, String>,
    pub content: Vec<u8>,
}

WARC Record

A record consists of the version string, a list of headers and the actual content (in bytes)

Usage

use rust_warc::WarcRecord;

/* test.warc:
WARC/1.1
WARC-Type: warcinfo
WARC-Date: 2006-09-19T17:20:14Z
WARC-Record-ID: multiline
 uuid value
Content-Type: text/plain
Content-Length: 4

test

*/

let mut data = &include_bytes!("test.warc")[..];

let item = WarcRecord::parse(&mut data).unwrap();

assert_eq!(item.version, "WARC/1.1");

// header names are case insensitive
assert_eq!(item.header.get(&"content-type".into()), Some(&"text/plain".into()));
// and may span multiple lines
assert_eq!(item.header.get(&"Warc-Record-ID".into()), Some(&"multiline\nuuid value".into()));

assert_eq!(item.content, "test".as_bytes());

Fields

version: String

WARC version string (WARC/1.1)

header: HashMap<CaseString, String>

Record header fields

content: Vec<u8>

Record content block

Implementations

impl WarcRecord

pub fn parse(read: impl BufRead) -> Result<Self, WarcError>

pub fn write_into(&self, f: &mut dyn Write) -> Result<()>