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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700
//! Lexicon [string formats].
//!
//! [string formats]: https://atproto.com/specs/lexicon#string-formats
use std::{cell::OnceCell, cmp, ops::Deref, str::FromStr};
use chrono::DurationRound;
use langtag::{LanguageTag, LanguageTagBuf};
use regex::Regex;
use serde::{de::Error, Deserialize, Deserializer, Serialize, Serializer};
/// Common trait implementations for Lexicon string formats that are newtype wrappers
/// around `String`.
macro_rules! string_newtype {
($name:ident) => {
impl FromStr for $name {
type Err = &'static str;
fn from_str(s: &str) -> Result<Self, Self::Err> {
Self::new(s.into())
}
}
impl<'de> Deserialize<'de> for $name {
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where
D: Deserializer<'de>,
{
let value = Deserialize::deserialize(deserializer)?;
Self::new(value).map_err(D::Error::custom)
}
}
impl Into<String> for $name {
fn into(self) -> String {
self.0
}
}
impl AsRef<str> for $name {
fn as_ref(&self) -> &str {
self.as_str()
}
}
impl Deref for $name {
type Target = str;
fn deref(&self) -> &Self::Target {
self.as_str()
}
}
};
}
/// An AT Protocol identifier.
#[derive(Clone, Debug, PartialEq, Eq, Deserialize, Serialize)]
#[serde(untagged)]
pub enum AtIdentifier {
Did(Did),
Handle(Handle),
}
impl From<Did> for AtIdentifier {
fn from(did: Did) -> Self {
AtIdentifier::Did(did)
}
}
impl From<Handle> for AtIdentifier {
fn from(handle: Handle) -> Self {
AtIdentifier::Handle(handle)
}
}
impl FromStr for AtIdentifier {
type Err = &'static str;
fn from_str(s: &str) -> Result<Self, Self::Err> {
if let Ok(did) = s.parse() {
Ok(AtIdentifier::Did(did))
} else {
s.parse().map(AtIdentifier::Handle)
}
}
}
impl Into<String> for AtIdentifier {
fn into(self) -> String {
match self {
AtIdentifier::Did(did) => did.into(),
AtIdentifier::Handle(handle) => handle.into(),
}
}
}
impl AsRef<str> for AtIdentifier {
fn as_ref(&self) -> &str {
match self {
AtIdentifier::Did(did) => did.as_ref(),
AtIdentifier::Handle(handle) => handle.as_ref(),
}
}
}
/// A [CID in string format].
///
/// [CID in string format]: https://atproto.com/specs/data-model#link-and-cid-formats
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct Cid(cid::Cid);
impl Cid {
/// Prepares a CID for use as a Lexicon string.
pub fn new(cid: cid::Cid) -> Self {
Self(cid)
}
}
impl FromStr for Cid {
type Err = cid::Error;
fn from_str(s: &str) -> Result<Self, Self::Err> {
s.parse().map(Self)
}
}
impl<'de> Deserialize<'de> for Cid {
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where
D: Deserializer<'de>,
{
let value: String = Deserialize::deserialize(deserializer)?;
Self::from_str(&value).map_err(D::Error::custom)
}
}
impl Serialize for Cid {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
{
serializer.serialize_str(&self.0.to_string())
}
}
impl AsRef<cid::Cid> for Cid {
fn as_ref(&self) -> &cid::Cid {
&self.0
}
}
/// A Lexicon timestamp.
#[derive(Clone, Debug, Eq)]
pub struct Datetime {
/// Serialized form. Preserved during parsing to ensure round-trip re-serialization.
serialized: String,
/// Parsed form.
dt: chrono::DateTime<chrono::FixedOffset>,
}
impl PartialEq for Datetime {
fn eq(&self, other: &Self) -> bool {
self.dt == other.dt
}
}
impl Ord for Datetime {
fn cmp(&self, other: &Self) -> cmp::Ordering {
self.dt.cmp(&other.dt)
}
}
impl PartialOrd for Datetime {
fn partial_cmp(&self, other: &Self) -> Option<cmp::Ordering> {
Some(self.cmp(other))
}
}
impl Datetime {
/// Returns a `Datetime` which corresponds to the current date and time in UTC.
///
/// The timestamp uses microsecond precision.
pub fn now() -> Self {
Self::new(chrono::Utc::now().fixed_offset())
}
/// Constructs a new Lexicon timestamp.
///
/// The timestamp is rounded to microsecond precision.
pub fn new(dt: chrono::DateTime<chrono::FixedOffset>) -> Self {
let dt = dt
.duration_round(chrono::Duration::microseconds(1))
.expect("delta does not exceed limits");
// This serialization format is compatible with ISO 8601.
let serialized = dt.to_rfc3339_opts(chrono::SecondsFormat::Micros, true);
Self { serialized, dt }
}
}
impl FromStr for Datetime {
type Err = chrono::ParseError;
fn from_str(s: &str) -> Result<Self, Self::Err> {
// The `chrono` crate only supports RFC 3339 parsing, but Lexicon restricts
// datetimes to the subset that is also valid under ISO 8601. Apply a regex that
// validates enough of the relevant ISO 8601 format that the RFC 3339 parser can
// do the rest.
const RE_ISO_8601: OnceCell<Regex> = OnceCell::new();
if RE_ISO_8601
.get_or_init(|| Regex::new(r"^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\.[0-9]+)?(Z|(\+[0-9]{2}|\-[0-9][1-9]):[0-9]{2})$").unwrap())
.is_match(&s)
{
let dt = chrono::DateTime::parse_from_rfc3339(s)?;
Ok(Self {
serialized: s.into(),
dt,
})
} else {
// Simulate an invalid `ParseError`.
Err(chrono::DateTime::parse_from_rfc3339("invalid").expect_err("invalid"))
}
}
}
impl<'de> Deserialize<'de> for Datetime {
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where
D: Deserializer<'de>,
{
let value: String = Deserialize::deserialize(deserializer)?;
Self::from_str(&value).map_err(D::Error::custom)
}
}
impl Serialize for Datetime {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
{
serializer.serialize_str(&self.serialized)
}
}
impl AsRef<chrono::DateTime<chrono::FixedOffset>> for Datetime {
fn as_ref(&self) -> &chrono::DateTime<chrono::FixedOffset> {
&self.dt
}
}
/// A generic [DID Identifier].
///
/// [DID Identifier]: https://atproto.com/specs/did
#[derive(Clone, Debug, PartialEq, Eq, Serialize)]
#[serde(transparent)]
pub struct Did(String);
string_newtype!(Did);
impl Did {
/// Parses a `Did` from the given string.
pub fn new(did: String) -> Result<Self, &'static str> {
const RE_DID: OnceCell<Regex> = OnceCell::new();
// https://atproto.com/specs/did#at-protocol-did-identifier-syntax
if did.len() > 2048 {
Err("DID too long")
} else if !RE_DID
.get_or_init(|| Regex::new(r"^did:[a-z]+:[a-zA-Z0-9._:%-]*[a-zA-Z0-9._-]$").unwrap())
.is_match(&did)
{
Err("Invalid DID")
} else {
Ok(Self(did))
}
}
/// Returns the DID method.
pub fn method(&self) -> &str {
&self.0[..4 + self.0[4..].find(':').unwrap()]
}
/// Returns the DID as a string slice.
pub fn as_str(&self) -> &str {
self.0.as_str()
}
}
/// A [Handle Identifier].
///
/// [Handle Identifier]: https://atproto.com/specs/handle
#[derive(Clone, Debug, PartialEq, Eq, Serialize)]
#[serde(transparent)]
pub struct Handle(String);
string_newtype!(Handle);
impl Handle {
/// Parses a `Handle` from the given string.
pub fn new(handle: String) -> Result<Self, &'static str> {
const RE_HANDLE: OnceCell<Regex> = OnceCell::new();
// https://atproto.com/specs/handle#handle-identifier-syntax
if handle.len() > 253 {
Err("Handle too long")
} else if !RE_HANDLE
.get_or_init(|| Regex::new(r"^([a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?$").unwrap())
.is_match(&handle)
{
Err("Invalid handle")
} else {
Ok(Self(handle))
}
}
/// Returns the handle as a string slice.
pub fn as_str(&self) -> &str {
self.0.as_str()
}
}
/// A [Namespaced Identifier].
///
/// [Namespaced Identifier]: https://atproto.com/specs/nsid
#[derive(Clone, Debug, PartialEq, Eq, Serialize)]
#[serde(transparent)]
pub struct Nsid(String);
string_newtype!(Nsid);
impl Nsid {
/// Parses an NSID from the given string.
pub fn new(nsid: String) -> Result<Self, &'static str> {
const RE_NSID: OnceCell<Regex> = OnceCell::new();
// https://atproto.com/specs/handle#handle-identifier-syntax
if nsid.len() > 317 {
Err("NSID too long")
} else if !RE_NSID
.get_or_init(|| Regex::new(r"^[a-zA-Z]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(\.[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)+(\.[a-zA-Z]([a-zA-Z]{0,61}[a-zA-Z])?)$").unwrap())
.is_match(&nsid)
{
Err("Invalid NSID")
} else {
Ok(Self(nsid))
}
}
/// Returns the domain authority part of the NSID.
pub fn domain_authority(&self) -> &str {
let split = self.0.rfind('.').expect("enforced by constructor");
&self.0[..split]
}
/// Returns the name segment of the NSID.
pub fn name(&self) -> &str {
let split = self.0.rfind('.').expect("enforced by constructor");
&self.0[split + 1..]
}
/// Returns the NSID as a string slice.
pub fn as_str(&self) -> &str {
self.0.as_str()
}
}
/// An [IETF Language Tag] string.
///
/// [IETF Language Tag]: https://en.wikipedia.org/wiki/IETF_language_tag
#[derive(Clone, Debug, PartialEq, Eq, Deserialize)]
#[serde(transparent)]
pub struct Language(LanguageTagBuf);
impl Language {
/// Creates a new language tag by parsing the given string.
pub fn new(s: String) -> Result<Self, langtag::Error> {
LanguageTagBuf::new(s.into()).map(Self).map_err(|(e, _)| e)
}
/// Returns a [`LanguageTag`] referencing this tag.
#[inline]
pub fn as_ref(&self) -> LanguageTag {
self.0.as_ref()
}
}
impl FromStr for Language {
type Err = langtag::Error;
fn from_str(s: &str) -> Result<Self, Self::Err> {
Self::new(s.into())
}
}
impl Serialize for Language {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
{
serializer.serialize_str(self.0.as_str())
}
}
#[cfg(test)]
mod tests {
use serde_json::{from_str, to_string};
use super::*;
#[test]
fn valid_datetime() {
// From https://atproto.com/specs/lexicon#datetime
for valid in &[
// preferred
"1985-04-12T23:20:50.123Z",
"1985-04-12T23:20:50.123456Z",
"1985-04-12T23:20:50.120Z",
"1985-04-12T23:20:50.120000Z",
// supported
"1985-04-12T23:20:50.12345678912345Z",
"1985-04-12T23:20:50Z",
"1985-04-12T23:20:50.0Z",
"1985-04-12T23:20:50.123+00:00",
"1985-04-12T23:20:50.123-07:00",
] {
let json_valid = format!("\"{}\"", valid);
let res = from_str::<Datetime>(&json_valid);
assert!(res.is_ok(), "valid Datetime `{}` parsed as invalid", valid);
let dt = res.unwrap();
assert_eq!(to_string(&dt).unwrap(), json_valid);
}
}
#[test]
fn invalid_datetime() {
// From https://atproto.com/specs/lexicon#datetime
for invalid in &[
"1985-04-12",
"1985-04-12T23:20Z",
"1985-04-12T23:20:5Z",
"1985-04-12T23:20:50.123",
"+001985-04-12T23:20:50.123Z",
"23:20:50.123Z",
"-1985-04-12T23:20:50.123Z",
"1985-4-12T23:20:50.123Z",
"01985-04-12T23:20:50.123Z",
"1985-04-12T23:20:50.123+00",
"1985-04-12T23:20:50.123+0000",
// ISO-8601 strict capitalization
"1985-04-12t23:20:50.123Z",
"1985-04-12T23:20:50.123z",
// RFC-3339, but not ISO-8601
"1985-04-12T23:20:50.123-00:00",
"1985-04-12 23:20:50.123Z",
// timezone is required
"1985-04-12T23:20:50.123",
// syntax looks ok, but datetime is not valid
"1985-04-12T23:99:50.123Z",
"1985-00-12T23:20:50.123Z",
] {
assert!(
from_str::<Datetime>(&format!("\"{}\"", invalid)).is_err(),
"invalid Datetime `{}` parsed as valid",
invalid,
);
}
}
#[test]
fn datetime_round_trip() {
let dt = Datetime::now();
let encoded = to_string(&dt).unwrap();
assert_eq!(from_str::<Datetime>(&encoded).unwrap(), dt);
}
#[test]
fn valid_did() {
// From https://atproto.com/specs/did#examples
for valid in &[
"did:plc:z72i7hdynmk6r22z27h6tvur",
"did:web:blueskyweb.xyz",
"did:method:val:two",
"did:m:v",
"did:method::::val",
"did:method:-:_:.",
"did:key:zQ3shZc2QzApp2oymGvQbzP8eKheVshBHbU4ZYjeXqwSKEn6N",
] {
assert!(
from_str::<Did>(&format!("\"{}\"", valid)).is_ok(),
"valid DID `{}` parsed as invalid",
valid,
);
}
}
#[test]
fn invalid_did() {
// From https://atproto.com/specs/did#examples
for invalid in &[
"did:METHOD:val",
"did:m123:val",
"DID:method:val",
"did:method:",
"did:method:val/two",
"did:method:val?two",
"did:method:val#two",
] {
assert!(
from_str::<Did>(&format!("\"{}\"", invalid)).is_err(),
"invalid DID `{}` parsed as valid",
invalid,
);
}
}
#[test]
fn did_method() {
// From https://atproto.com/specs/did#examples
for (method, did) in &[
("did:plc", "did:plc:z72i7hdynmk6r22z27h6tvur"),
("did:web", "did:web:blueskyweb.xyz"),
("did:method", "did:method:val:two"),
("did:m", "did:m:v"),
("did:method", "did:method::::val"),
("did:method", "did:method:-:_:."),
(
"did:key",
"did:key:zQ3shZc2QzApp2oymGvQbzP8eKheVshBHbU4ZYjeXqwSKEn6N",
),
] {
assert_eq!(Did::new(did.to_string()).unwrap().method(), *method);
}
}
#[test]
fn valid_handle() {
// From https://atproto.com/specs/handle#identifier-examples
for valid in &[
"jay.bsky.social",
"8.cn",
"name.t--t", // not a real TLD, but syntax ok
"XX.LCS.MIT.EDU",
"a.co",
"xn--notarealidn.com",
"xn--fiqa61au8b7zsevnm8ak20mc4a87e.xn--fiqs8s",
"xn--ls8h.test",
"example.t", // not a real TLD, but syntax ok
// Valid syntax, but must always fail resolution due to other restrictions:
"2gzyxa5ihm7nsggfxnu52rck2vv4rvmdlkiu3zzui5du4xyclen53wid.onion",
"laptop.local",
"blah.arpa",
] {
assert!(
from_str::<Handle>(&format!("\"{}\"", valid)).is_ok(),
"valid handle `{}` parsed as invalid",
valid,
);
}
}
#[test]
fn invalid_handle() {
// From https://atproto.com/specs/handle#identifier-examples
for invalid in &[
"jo@hn.test",
"💩.test",
"john..test",
"xn--bcher-.tld",
"john.0",
"cn.8",
"www.masełkowski.pl.com",
"org",
"name.org.",
] {
assert!(
from_str::<Handle>(&format!("\"{}\"", invalid)).is_err(),
"invalid handle `{}` parsed as valid",
invalid,
);
}
}
#[test]
fn valid_nsid() {
// From https://atproto.com/specs/nsid#examples
for valid in &[
"com.example.fooBar",
"net.users.bob.ping",
"a-0.b-1.c",
"a.b.c",
"cn.8.lex.stuff",
] {
assert!(
from_str::<Nsid>(&format!("\"{}\"", valid)).is_ok(),
"valid NSID `{}` parsed as invalid",
valid,
);
}
}
#[test]
fn invalid_nsid() {
// From https://atproto.com/specs/nsid#examples
for invalid in &["com.exa💩ple.thing", "com.example"] {
assert!(
from_str::<Nsid>(&format!("\"{}\"", invalid)).is_err(),
"invalid NSID `{}` parsed as valid",
invalid,
);
}
}
#[test]
fn nsid_parts() {
// From https://atproto.com/specs/nsid#examples
for (nsid, domain_authority, name) in &[
("com.example.fooBar", "com.example", "fooBar"),
("net.users.bob.ping", "net.users.bob", "ping"),
("a-0.b-1.c", "a-0.b-1", "c"),
("a.b.c", "a.b", "c"),
("cn.8.lex.stuff", "cn.8.lex", "stuff"),
] {
let nsid = Nsid::new(nsid.to_string()).unwrap();
assert_eq!(nsid.domain_authority(), *domain_authority);
assert_eq!(nsid.name(), *name);
}
}
#[test]
fn valid_language() {
// From https://www.rfc-editor.org/rfc/rfc5646.html#appendix-A
for valid in &[
// Simple language subtag:
"de", // German
"fr", // French
"ja", // Japanese
"i-enochian", // example of a grandfathered tag
// Language subtag plus Script subtag:
"zh-Hant", // Chinese written using the Traditional Chinese script
"zh-Hans", // Chinese written using the Simplified Chinese script
"sr-Cyrl", // Serbian written using the Cyrillic script
"sr-Latn", // Serbian written using the Latin script
// Extended language subtags and their primary language subtag counterparts:
"zh-cmn-Hans-CN", // Chinese, Mandarin, Simplified script, as used in China
"cmn-Hans-CN", // Mandarin Chinese, Simplified script, as used in China
"zh-yue-HK", // Chinese, Cantonese, as used in Hong Kong SAR
"yue-HK", // Cantonese Chinese, as used in Hong Kong SAR
// Language-Script-Region:
"zh-Hans-CN", // Chinese written using the Simplified script as used in mainland China
"sr-Latn-RS", // Serbian written using the Latin script as used in Serbia
// Language-Variant:
"sl-rozaj", // Resian dialect of Slovenian
"sl-rozaj-biske", // San Giorgio dialect of Resian dialect of Slovenian
"sl-nedis", // Nadiza dialect of Slovenian
// Language-Region-Variant:
"de-CH-1901", // German as used in Switzerland using the 1901 variant orthography
"sl-IT-nedis", // Slovenian as used in Italy, Nadiza dialect
// Language-Script-Region-Variant:
"hy-Latn-IT-arevela", // Eastern Armenian written in Latin script, as used in Italy
// Language-Region:
"de-DE", // German for Germany
"en-US", // English as used in the United States
"es-419", // Spanish appropriate for the Latin America and Caribbean region using the UN region code
// Private use subtags:
"de-CH-x-phonebk",
"az-Arab-x-AZE-derbend",
// Private use registry values:
"x-whatever", // private use using the singleton 'x'
"qaa-Qaaa-QM-x-southern", // all private tags
"de-Qaaa", // German, with a private script
"sr-Latn-QM", // Serbian, Latin script, private region
"sr-Qaaa-RS", // Serbian, private script, for Serbia
// Tags that use extensions (examples ONLY -- extensions MUST be defined by RFC):
"en-US-u-islamcal",
"zh-CN-a-myext-x-private",
"en-a-myext-b-another",
// Invalid tags that are well-formed:
"ar-a-aaa-b-bbb-a-ccc", // two extensions with same single-letter prefix
] {
let json_valid = format!("\"{}\"", valid);
let res = from_str::<Language>(&json_valid);
assert!(res.is_ok(), "valid language `{}` parsed as invalid", valid);
let dt = res.unwrap();
assert_eq!(to_string(&dt).unwrap(), json_valid);
}
}
#[test]
fn invalid_language() {
// From https://www.rfc-editor.org/rfc/rfc5646.html#appendix-A
for invalid in &[
"de-419-DE", // two region tags
// use of a single-character subtag in primary position; note that there are a
// few grandfathered tags that start with "i-" that are valid
"a-DE",
] {
assert!(
from_str::<Language>(&format!("\"{}\"", invalid)).is_err(),
"invalid language `{}` parsed as valid",
invalid,
);
}
}
}