rustyknife
Email parsing library with a focus on reliably handling malformed data
Features:
- Python module
- Email header parsing
- ESMTP command parsing
- Unit testing with a high coverage
- Supports internationalized email headers through RFC 2047 and RFC 2231 decoding
- Used to parse the content of millions of emails every day
- SMTPUTF8 support
- UTF-8 Internationalized Email Headers support
Roadmap:
- Decoding of all common ESMTP extensions
- Support more email content syntax
Examples
Email header decoding
use rustyknife::behaviour::Intl;
use rustyknife::types::{DomainPart, DotAtom, Mailbox};
use rustyknife::rfc5322::{Address, Group, Mailbox as IMFMailbox};
use rustyknife::rfc5322::from;
let (rem, parsed) = from::<Intl>(b" A Group(Some people)\r
:Chris Jones <c@(Chris's host.)public.example>,\r
joe@example.org,\r
John <jdoe@one.test> (my dear friend); (the end of the group)\r\n").unwrap();
// `rem` contains the unparsed remainder.
assert!(rem.is_empty());
assert_eq!(parsed, [Address::Group(Group{
dname: "A Group".into(),
members: vec![
IMFMailbox { dname: Some("Chris Jones".into()),
address: Mailbox::from_imf(b"c@public.example").unwrap() },
IMFMailbox { dname: None,
address: Mailbox::from_imf(b"joe@example.org").unwrap() },
IMFMailbox { dname: Some("John".into()),
address: Mailbox::from_imf(b"jdoe@one.test").unwrap() }
]
})]);ESMTP command parsing
use rustyknife::behaviour::Intl;
use rustyknife::types::{Mailbox, QuotedString, Domain};
use rustyknife::rfc5321::{mail_command, Path, ReversePath, Param};
let (_, (path, params)) = mail_command::<Intl>(b"MAIL FROM:<\"mr bob\"@example.com> RET=FULL ENVID=abc123\r\n").unwrap();
assert_eq!(path, ReversePath::Path(
Path(Mailbox(QuotedString::from_smtp(b"\"mr bob\"").unwrap().into(),
Domain::from_smtp(b"example.com").unwrap().into()),
vec![])));
assert_eq!(params, [Param::new("RET", Some("FULL")).unwrap(),
Param::new("ENVID", Some("abc123")).unwrap()]);RFC 2047 encoded word decoding
use rustyknife::rfc2047::encoded_word;
let (_, decoded) = encoded_word(b"=?x-sjis?B?lEWWQI7Kg4GM9ZTygs6CtSiPzik=?=").unwrap();
assert_eq!(decoded, "忍法写メ光飛ばし(笑)");
