mirror of
https://github.com/storytold/craft-libs.git
synced 2026-11-14 22:42:46 +00:00
Dylan M. TaylorandMartin Ball
090f121943
What MailCraft's mime and charset crates still had that craft-mime did not: strict RFC 4648 base64 (crates/charset), mailto: links (RFC 6068, crates/mime) and the Windows code page to charset label table (crates/pst). With these, MailCraft's charset crate has nothing craft-mime lacks. Co-authored-by: Martin Ball <98639962+benandez@users.noreply.github.com>
82 lines
3.1 KiB
Rust
82 lines
3.1 KiB
Rust
//! Base64: the RFC 4648 test vectors, the strict refusals, and that only the one spelling of a
|
|
//! value decodes, on every config.
|
|
|
|
use super::*;
|
|
use proptest::prelude::*;
|
|
|
|
#[test]
|
|
fn the_rfc_vectors_round_trip_in_every_config() {
|
|
let vectors = [("", ""), ("f", "Zg=="), ("fo", "Zm8="), ("foo", "Zm9v"), ("foob", "Zm9vYg=="), ("fooba", "Zm9vYmE="), ("foobar", "Zm9vYmFy")];
|
|
for (plain, coded) in vectors {
|
|
assert_eq!(STANDARD.encode(plain), coded);
|
|
assert_eq!(URL_SAFE.encode(plain), coded);
|
|
assert_eq!(STANDARD_NO_PAD.encode(plain), coded.trim_end_matches('='));
|
|
assert_eq!(URL_SAFE_NO_PAD.encode(plain), coded.trim_end_matches('='));
|
|
assert_eq!(STANDARD.decode(coded).unwrap(), plain.as_bytes());
|
|
assert_eq!(URL_SAFE_NO_PAD.decode(coded.trim_end_matches('=')).unwrap(), plain.as_bytes());
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn the_two_alphabets_differ_in_the_last_two_symbols() {
|
|
assert_eq!(STANDARD.encode([0xfb, 0xff]), "+/8=");
|
|
assert_eq!(URL_SAFE.encode([0xfb, 0xff]), "-_8=");
|
|
assert!(URL_SAFE.decode("+/8=").is_err());
|
|
assert!(STANDARD.decode("-_8=").is_err());
|
|
}
|
|
|
|
#[test]
|
|
fn what_is_not_exactly_base64_is_refused() {
|
|
for bad in ["Zg", "Zg=", "Zg===", "Z", "Z===", "====", "Zm9v\n", " Zm9v", "Zm 9v", "Zh==", "Zm9=", "Zm=v", "Zm9v=", "é", "Zm9\u{0}"] {
|
|
assert!(STANDARD.decode(bad).is_err(), "{bad:?}");
|
|
}
|
|
for bad in ["Zg==", "Z", "Zh", "Zm9v\n", "Zm 9v", "Zg=", "Zm9="] {
|
|
assert!(STANDARD_NO_PAD.decode(bad).is_err(), "{bad:?}");
|
|
}
|
|
assert!(STANDARD_NO_PAD.decode("Zm8").is_ok());
|
|
}
|
|
|
|
#[test]
|
|
fn hostile_inputs_do_not_panic() {
|
|
let big = vec![b'A'; 1 << 20];
|
|
for cfg in [STANDARD, STANDARD_NO_PAD, URL_SAFE, URL_SAFE_NO_PAD] {
|
|
assert_eq!(cfg.decode(&big).map(|b| b.len()).unwrap_or(0), 786_432);
|
|
for bytes in [&b""[..], b"=", b"==", b"===", b"\xff\xfe", b"=A=A", b"AA=A"] {
|
|
let _ = cfg.decode(bytes);
|
|
}
|
|
}
|
|
}
|
|
|
|
const CONFIGS: [Config; 4] = [STANDARD, STANDARD_NO_PAD, URL_SAFE, URL_SAFE_NO_PAD];
|
|
|
|
proptest! {
|
|
#[test]
|
|
fn what_is_encoded_decodes_to_itself(data in proptest::collection::vec(any::<u8>(), 0..400)) {
|
|
for config in CONFIGS {
|
|
prop_assert_eq!(config.decode(config.encode(&data)).ok(), Some(data.clone()));
|
|
}
|
|
}
|
|
|
|
/// Strict: a text is accepted only when it is the one spelling of its bytes.
|
|
#[test]
|
|
fn what_decodes_is_the_one_spelling_of_its_bytes(
|
|
data in proptest::collection::vec(any::<u8>(), 0..400),
|
|
junk in proptest::collection::vec(any::<u8>(), 0..64),
|
|
text in "[A-Za-z0-9+/=_ -]{0,40}",
|
|
) {
|
|
for config in CONFIGS {
|
|
let mut cut = config.encode(&data).into_bytes();
|
|
cut.pop();
|
|
let mut pad = cut.clone();
|
|
if let Some(first) = pad.first_mut() {
|
|
*first = b'=';
|
|
}
|
|
for candidate in [junk.as_slice(), text.as_bytes(), cut.as_slice(), pad.as_slice()] {
|
|
if let Ok(bytes) = config.decode(candidate) {
|
|
prop_assert_eq!(config.encode(&bytes).into_bytes(), candidate.to_vec());
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|