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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983
// SPDX-License-Identifier: MIT
//! Decoding of bech32 encoded strings as specified by [BIP-173] and [BIP-350].
//!
//! You should only need to use this module directly if you want control over exactly what is
//! checked and when it is checked (correct bech32 characters, valid checksum, valid checksum for
//! specific checksum algorithm, etc). If you are parsing/validating modern (post BIP-350) bitcoin
//! segwit addresses consider using the higher crate level API.
//!
//! If you do find yourself using this module directly then consider using the most general type
//! that serves your purposes, each type can be created by parsing an address string to `new`. You
//! likely do not want to arbitrarily transition from one type to the next even though possible. And
//! be prepared to spend some time with the bips - you have been warned :)
//!
//! # Details
//!
//! A Bech32 string is at most 90 characters long and consists of:
//!
//! - The human-readable part, which is intended to convey the type of data, or anything else that
//! is relevant to the reader. This part MUST contain 1 to 83 US-ASCII characters.
//! - The separator, which is always "1".
//! - The data part, which is at least 6 characters long and only consists of alphanumeric
//! characters excluding "1", "b", "i", and "o".
//!
//! The types in this module heavily lean on the wording in BIP-173: *We first
//! describe the general checksummed base32 format called Bech32 and then define Segregated Witness
//! addresses using it.*
//!
//! - `UncheckedHrpstring`: Parses the general checksummed base32 format and provides checksum validation.
//! - `CheckedHrpstring`: Provides access to the data encoded by a general checksummed base32 string and segwit checks.
//! - `SegwitHrpstring`: Provides access to the data encoded by a segwit address.
//!
//! # Examples
//!
//! ```
//! use bech32::{Bech32, Bech32m, Fe32, Hrp};
//! use bech32::primitives::decode::{CheckedHrpstring, SegwitHrpstring, UncheckedHrpstring};
//! use bech32::segwit::VERSION_1;
//!
//! // An arbitrary HRP and a string of valid bech32 characters.
//! let s = "abcd143hj65vxw49rts6kcw35u6r6tgzguyr03vvveeewjqpn05efzq444444";
//! assert!(UncheckedHrpstring::new(s).is_ok());
//! // But it has an invalid checksum.
//! assert!(CheckedHrpstring::new::<Bech32>(s).is_err());
//! assert!(CheckedHrpstring::new::<Bech32m>(s).is_err());
//! assert!(SegwitHrpstring::new(s).is_err());
//!
//! // An arbitrary HRP, a string of valid bech32 characters, and a valid bech32 checksum.
//! let s = "abcd14g08d6qejxtdg4y5r3zarvary0c5xw7kxugcx9";
//! assert!(UncheckedHrpstring::new(s).is_ok());
//! assert!(CheckedHrpstring::new::<Bech32>(s).is_ok());
//! // But not a valid segwit address.
//! assert!(SegwitHrpstring::new(s).is_err());
//! // And not a valid bech32m checksum.
//! assert!(CheckedHrpstring::new::<Bech32m>(s).is_err());
//!
//! // A valid Bitcoin taproot address.
//! let s = "bc1pdp43hj65vxw49rts6kcw35u6r6tgzguyr03vvveeewjqpn05efzq7un9w0";
//! assert!(UncheckedHrpstring::new(s).is_ok());
//! assert!(CheckedHrpstring::new::<Bech32m>(s).is_ok());
//! assert!(SegwitHrpstring::new(s).is_ok());
//! // But not a valid segwit v0 checksum.
//! assert!(CheckedHrpstring::new::<Bech32>(s).is_err());
//!
//! // Get the HRP, witness version, and encoded data.
//! let address = "bc1pdp43hj65vxw49rts6kcw35u6r6tgzguyr03vvveeewjqpn05efzq7un9w0";
//! let segwit = SegwitHrpstring::new(address).expect("valid segwit address");
//! let _encoded_data = segwit.byte_iter();
//! assert_eq!(segwit.hrp(), Hrp::parse("bc").unwrap());
//! assert_eq!(segwit.witness_version(), VERSION_1);
//! ```
//!
//! [BIP-173]: <https://github.com/bitcoin/bips/blob/master/bip-0173.mediawiki>
//! [BIP-350]: <https://github.com/bitcoin/bips/blob/master/bip-0350.mediawiki>
use core::{fmt, iter, slice, str};
use crate::error::write_err;
use crate::primitives::checksum::{self, Checksum};
use crate::primitives::gf32::Fe32;
use crate::primitives::hrp::{self, Hrp};
use crate::primitives::iter::{Fe32IterExt, FesToBytes};
use crate::primitives::segwit::{self, WitnessLengthError, VERSION_0};
use crate::{Bech32, Bech32m};
/// Separator between the hrp and payload (as defined by BIP-173).
const SEP: char = '1';
/// An HRP string that has been parsed but not yet had the checksum checked.
///
/// Parsing an HRP string only checks validity of the characters, it does not validate the
/// checksum in any way.
///
/// Unless you are attempting to validate a string with multiple checksums then you likely do not
/// want to use this type directly, instead use [`CheckedHrpstring::new(s)`].
///
/// # Examples
///
/// ```
/// use bech32::{Bech32, Bech32m, primitives::decode::UncheckedHrpstring};
///
/// let addr = "BC1QW508D6QEJXTDG4Y5R3ZARVARY0C5XW7KV8F3T4";
/// let unchecked = UncheckedHrpstring::new(addr).expect("valid bech32 character encoded string");
/// if unchecked.has_valid_checksum::<Bech32>() {
/// // Remove the checksum and do something with the data.
/// let checked = unchecked.remove_checksum::<Bech32>();
/// let _ = checked.byte_iter();
/// } else if unchecked.has_valid_checksum::<Bech32m>() {
/// // Remove the checksum and do something with the data as above.
/// } else {
/// // Checksum is not valid for either the bech32 or bech32 checksum algorithms.
/// }
/// ```
#[derive(Debug)]
pub struct UncheckedHrpstring<'s> {
/// The human-readable part, guaranteed to be lowercase ASCII characters.
hrp: Hrp,
/// This is ASCII byte values of the parsed string, guaranteed to be valid bech32 characters.
///
/// Contains the checksum if one was present in the parsed string.
data: &'s [u8],
}
impl<'s> UncheckedHrpstring<'s> {
/// Parses an bech32 encode string and constructs a [`UncheckedHrpstring`] object.
///
/// Checks for valid ASCII values, does not validate the checksum.
#[inline]
pub fn new(s: &'s str) -> Result<Self, UncheckedHrpstringError> {
let sep_pos = check_characters(s)?;
let (hrp, data) = s.split_at(sep_pos);
let ret = UncheckedHrpstring {
hrp: Hrp::parse(hrp)?,
data: data[1..].as_bytes(), // Skip the separator.
};
Ok(ret)
}
/// Returns the human-readable part.
#[inline]
pub fn hrp(&self) -> Hrp { self.hrp }
/// Validates that data has a valid checksum for the `Ck` algorithm and returns a [`CheckedHrpstring`].
#[inline]
pub fn validate_and_remove_checksum<Ck: Checksum>(
self,
) -> Result<CheckedHrpstring<'s>, ChecksumError> {
self.validate_checksum::<Ck>()?;
Ok(self.remove_checksum::<Ck>())
}
/// Validates that data has a valid checksum for the `Ck` algorithm (this may mean an empty
/// checksum if `NoChecksum` is used).
///
/// This is useful if you do not know which checksum algorithm was used and wish to validate
/// against multiple algorithms consecutively. If this function returns `true` then call
/// `remove_checksum` to get a [`CheckedHrpstring`].
#[inline]
pub fn has_valid_checksum<Ck: Checksum>(&self) -> bool {
self.validate_checksum::<Ck>().is_ok()
}
/// Validates that data has a valid checksum for the `Ck` algorithm (this may mean an empty
/// checksum if `NoChecksum` is used).
#[inline]
pub fn validate_checksum<Ck: Checksum>(&self) -> Result<(), ChecksumError> {
use ChecksumError::*;
if Ck::CHECKSUM_LENGTH == 0 {
// Called with NoChecksum
return Ok(());
}
if self.data.len() < Ck::CHECKSUM_LENGTH {
return Err(InvalidChecksumLength);
}
let mut checksum_eng = checksum::Engine::<Ck>::new();
checksum_eng.input_hrp(&self.hrp());
// Unwrap ok since we checked all characters in our constructor.
for fe in self.data.iter().map(|&b| Fe32::from_char_unchecked(b)) {
checksum_eng.input_fe(fe);
}
if checksum_eng.residue() != &Ck::TARGET_RESIDUE {
return Err(InvalidChecksum);
}
Ok(())
}
/// Removes the checksum for the `Ck` algorithm and returns an [`CheckedHrpstring`].
///
/// Data must be valid (ie, first call `has_valid_checksum` or `validate_checksum()`). This
/// function is typically paired with `has_valid_checksum` when validating against multiple
/// checksum algorithms consecutively.
///
/// # Panics
///
/// May panic if data is not valid.
#[inline]
pub fn remove_checksum<Ck: Checksum>(self) -> CheckedHrpstring<'s> {
let data_len = self.data.len() - Ck::CHECKSUM_LENGTH;
CheckedHrpstring { hrp: self.hrp(), data: &self.data[..data_len] }
}
}
/// An HRP string that has been parsed and had the checksum validated.
///
/// This type does not treat the first byte of the data in any special way i.e., as the witness
/// version byte. If you are parsing Bitcoin segwit addresses you likely want to use [`SegwitHrpstring`].
///
/// > We first describe the general checksummed base32 format called Bech32 and then
/// > define Segregated Witness addresses using it.
///
/// This type abstracts over the general checksummed base32 format called Bech32.
///
/// # Examples
///
/// ```
/// use bech32::{Bech32m, primitives::decode::CheckedHrpstring};
///
/// // Parse a general checksummed bech32 encoded string.
/// let s = "abcd14g08d6qejxtdg4y5r3zarvary0c5xw7knqc5r8";
/// let checked = CheckedHrpstring::new::<Bech32m>(s)
/// .expect("valid bech32 string with a valid checksum according to the bech32m algorithm");
///
/// // Do something with the encoded data.
/// let _ = checked.byte_iter();
/// ```
#[derive(Debug)]
pub struct CheckedHrpstring<'s> {
/// The human-readable part, guaranteed to be lowercase ASCII characters.
hrp: Hrp,
/// This is ASCII byte values of the parsed string, guaranteed to be valid bech32 characters,
/// with the checksum removed.
data: &'s [u8],
}
impl<'s> CheckedHrpstring<'s> {
/// Parses and validates an HRP string, without treating the first data character specially.
///
/// If you are validating the checksum multiple times consider using [`UncheckedHrpstring`].
///
/// This is equivalent to `UncheckedHrpstring::new().validate_and_remove_checksum::<CK>()`.
#[inline]
pub fn new<Ck: Checksum>(s: &'s str) -> Result<Self, CheckedHrpstringError> {
let unchecked = UncheckedHrpstring::new(s)?;
let checked = unchecked.validate_and_remove_checksum::<Ck>()?;
Ok(checked)
}
/// Returns the human-readable part.
#[inline]
pub fn hrp(&self) -> Hrp { self.hrp }
/// Returns an iterator that yields the data part of the parsed bech32 encoded string.
///
/// Converts the ASCII bytes representing field elements to the respective field elements, then
/// converts the stream of field elements to a stream of bytes.
#[inline]
pub fn byte_iter(&self) -> ByteIter {
ByteIter { iter: AsciiToFe32Iter { iter: self.data.iter().copied() }.fes_to_bytes() }
}
/// Converts this type to a [`SegwitHrpstring`] after validating the witness and HRP.
#[inline]
pub fn validate_segwit(mut self) -> Result<SegwitHrpstring<'s>, SegwitHrpstringError> {
if self.data.is_empty() {
return Err(SegwitHrpstringError::MissingWitnessVersion);
}
// Unwrap ok since check_characters checked the bech32-ness of this char.
let witness_version = Fe32::from_char(self.data[0].into()).unwrap();
self.data = &self.data[1..]; // Remove the witness version byte from data.
self.validate_padding()?;
self.validate_witness_program_length(witness_version)?;
Ok(SegwitHrpstring { hrp: self.hrp(), witness_version, data: self.data })
}
/// Validates the segwit padding rules.
///
/// Must be called after the witness version byte is removed from the data.
///
/// From BIP-173:
/// > Re-arrange those bits into groups of 8 bits. Any incomplete group at the
/// > end MUST be 4 bits or less, MUST be all zeroes, and is discarded.
fn validate_padding(&self) -> Result<(), PaddingError> {
if self.data.is_empty() {
return Ok(()); // Empty data implies correct padding.
}
let fe_iter = AsciiToFe32Iter { iter: self.data.iter().copied() };
let padding_len = fe_iter.len() * 5 % 8;
if padding_len > 4 {
return Err(PaddingError::TooMuch)?;
}
let last_fe = fe_iter.last().expect("checked above");
let last_byte = last_fe.0;
let padding_contains_non_zero_bits = match padding_len {
0 => false,
1 => last_byte & 0b0001 > 0,
2 => last_byte & 0b0011 > 0,
3 => last_byte & 0b0111 > 0,
4 => last_byte & 0b1111 > 0,
_ => unreachable!("checked above"),
};
if padding_contains_non_zero_bits {
Err(PaddingError::NonZero)
} else {
Ok(())
}
}
/// Validates the segwit witness length rules.
///
/// Must be called after the witness version byte is removed from the data.
fn validate_witness_program_length(
&self,
witness_version: Fe32,
) -> Result<(), WitnessLengthError> {
segwit::validate_witness_program_length(self.byte_iter().len(), witness_version)
}
}
/// An HRP string that has been parsed, had the checksum validated, had the witness version
/// validated, had the witness data length checked, and the had witness version and checksum
/// removed.
///
/// # Examples
///
/// ```
/// use bech32::primitives::decode::SegwitHrpstring;
///
/// // Parse a segwit V0 address.
/// let address = "bc1qar0srrr7xfkvy5l643lydnw9re59gtzzwf5mdq";
/// let segwit = SegwitHrpstring::new(address).expect("valid segwit address");
///
/// // Do something with the encoded data.
/// let _ = segwit.byte_iter();
/// ```
#[derive(Debug)]
pub struct SegwitHrpstring<'s> {
/// The human-readable part, valid for segwit addresses.
hrp: Hrp,
/// The first byte of the parsed data.
witness_version: Fe32,
/// This is ASCII byte values of the parsed string, guaranteed to be valid bech32 characters,
/// with the witness version and checksum removed.
data: &'s [u8],
}
impl<'s> SegwitHrpstring<'s> {
/// Parses an HRP string, treating the first data character as a witness version.
///
/// The version byte does not appear in the extracted binary data, but is covered by the
/// checksum. It can be accessed with [`Self::witness_version`].
///
/// NOTE: We do not enforce any restrictions on the HRP, use [`SegwitHrpstring::has_valid_hrp`]
/// to get strict BIP conformance (also [`Hrp::is_valid_on_mainnet`] and friends).
#[inline]
pub fn new(s: &'s str) -> Result<Self, SegwitHrpstringError> {
let unchecked = UncheckedHrpstring::new(s)?;
if unchecked.data.is_empty() {
return Err(SegwitHrpstringError::MissingWitnessVersion);
}
// Unwrap ok since check_characters (in `Self::new`) checked the bech32-ness of this char.
let witness_version = Fe32::from_char(unchecked.data[0].into()).unwrap();
if witness_version.to_u8() > 16 {
return Err(SegwitHrpstringError::InvalidWitnessVersion(witness_version));
}
let checked: CheckedHrpstring<'s> = match witness_version {
VERSION_0 => unchecked.validate_and_remove_checksum::<Bech32>()?,
_ => unchecked.validate_and_remove_checksum::<Bech32m>()?,
};
checked.validate_segwit()
}
/// Parses an HRP string, treating the first data character as a witness version.
///
/// ## WARNING
///
/// You almost certainly do not want to use this function.
///
/// It is provided for backwards comparability to parse addresses that have an non-zero witness
/// version because [BIP-173] explicitly allows using the bech32 checksum with any witness
/// version however [BIP-350] specifies all witness version > 0 now MUST use bech32m.
///
/// [BIP-173]: https://github.com/bitcoin/bips/blob/master/bip-0173.mediawiki
/// [BIP-350]: https://github.com/bitcoin/bips/blob/master/bip-0350.mediawiki
#[inline]
pub fn new_bech32(s: &'s str) -> Result<Self, SegwitHrpstringError> {
let unchecked = UncheckedHrpstring::new(s)?;
// Unwrap ok since check_characters (in `Self::new`) checked the bech32-ness of this char.
let witness_version = Fe32::from_char(unchecked.data[0].into()).unwrap();
if witness_version.to_u8() > 16 {
return Err(SegwitHrpstringError::InvalidWitnessVersion(witness_version));
}
let checked = unchecked.validate_and_remove_checksum::<Bech32>()?;
checked.validate_segwit()
}
/// Returns `true` if the HRP is "bc" or "tb".
///
/// BIP-173 requires that the HRP is "bc" or "tb" but software in the Bitcoin ecosystem uses
/// other HRPs, specifically "bcrt" for regtest addresses. We provide this function in order to
/// be BIP-173 compliant but their are no restrictions on the HRP of [`SegwitHrpstring`].
#[inline]
pub fn has_valid_hrp(&self) -> bool { self.hrp().is_valid_segwit() }
/// Returns the human-readable part.
#[inline]
pub fn hrp(&self) -> Hrp { self.hrp }
/// Returns the witness version.
#[inline]
pub fn witness_version(&self) -> Fe32 { self.witness_version }
/// Returns an iterator that yields the data part, excluding the witness version, of the parsed
/// bech32 encoded string.
///
/// Converts the ASCII bytes representing field elements to the respective field elements, then
/// converts the stream of field elements to a stream of bytes.
///
/// Use `self.witness_version()` to get the witness version.
#[inline]
pub fn byte_iter(&self) -> ByteIter {
ByteIter { iter: AsciiToFe32Iter { iter: self.data.iter().copied() }.fes_to_bytes() }
}
}
/// Checks whether a given HRP string has data characters in the bech32 alphabet (incl. checksum
/// characters), and that the whole string has consistent casing (hrp, data, and checksum).
///
/// # Returns
///
/// The byte-index into the string where the '1' separator occurs, or an error if it does not.
fn check_characters(s: &str) -> Result<usize, CharError> {
use CharError::*;
let mut has_upper = false;
let mut has_lower = false;
let mut req_bech32 = true;
let mut sep_pos = None;
for (n, ch) in s.char_indices().rev() {
if ch == SEP && sep_pos.is_none() {
req_bech32 = false;
sep_pos = Some(n);
}
if req_bech32 {
Fe32::from_char(ch).map_err(|_| InvalidChar(ch))?;
}
if ch.is_ascii_uppercase() {
has_upper = true;
} else if ch.is_ascii_lowercase() {
has_lower = true;
}
}
if has_upper && has_lower {
Err(MixedCase)
} else if let Some(pos) = sep_pos {
Ok(pos)
} else {
Err(MissingSeparator)
}
}
/// An iterator over a parsed HRP string data as bytes.
pub struct ByteIter<'s> {
iter: FesToBytes<AsciiToFe32Iter<iter::Copied<slice::Iter<'s, u8>>>>,
}
impl<'s> Iterator for ByteIter<'s> {
type Item = u8;
#[inline]
fn next(&mut self) -> Option<u8> { self.iter.next() }
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) { self.iter.size_hint() }
}
impl<'s> ExactSizeIterator for ByteIter<'s> {
#[inline]
fn len(&self) -> usize { self.iter.len() }
}
/// An iterator over a parsed HRP string data as field elements.
pub struct Fe32Iter<'s> {
iter: AsciiToFe32Iter<iter::Copied<slice::Iter<'s, u8>>>,
}
impl<'s> Iterator for Fe32Iter<'s> {
type Item = Fe32;
#[inline]
fn next(&mut self) -> Option<Fe32> { self.iter.next() }
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) { self.iter.size_hint() }
}
/// Helper iterator adaptor that maps an iterator of valid bech32 character ASCII bytes to an
/// iterator of field elements.
///
/// # Panics
///
/// If any `u8` in the input iterator is out of range for an [`Fe32`]. Should only be used on data
/// that has already been checked for validity (eg, by using `check_characters`).
struct AsciiToFe32Iter<I: Iterator<Item = u8>> {
iter: I,
}
impl<I> Iterator for AsciiToFe32Iter<I>
where
I: Iterator<Item = u8>,
{
type Item = Fe32;
#[inline]
fn next(&mut self) -> Option<Fe32> { self.iter.next().map(Fe32::from_char_unchecked) }
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
// Each ASCII character is an fe32 so iterators are the same size.
self.iter.size_hint()
}
}
impl<I> ExactSizeIterator for AsciiToFe32Iter<I>
where
I: Iterator<Item = u8> + ExactSizeIterator,
{
#[inline]
fn len(&self) -> usize { self.iter.len() }
}
/// An error while constructing a [`SegwitHrpstring`] type.
#[derive(Debug, Clone, PartialEq, Eq)]
#[non_exhaustive]
pub enum SegwitHrpstringError {
/// Error while parsing the encoded address string.
Unchecked(UncheckedHrpstringError),
/// The witness version byte is missing.
MissingWitnessVersion,
/// Invalid witness version (must be 0-16 inclusive).
InvalidWitnessVersion(Fe32),
/// Invalid padding on the witness data.
Padding(PaddingError),
/// Invalid witness length.
WitnessLength(WitnessLengthError),
/// Invalid checksum.
Checksum(ChecksumError),
}
impl fmt::Display for SegwitHrpstringError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use SegwitHrpstringError::*;
match *self {
Unchecked(ref e) => write_err!(f, "parsing unchecked hrpstring failed"; e),
MissingWitnessVersion => write!(f, "the witness version byte is missing"),
InvalidWitnessVersion(fe) => write!(f, "invalid segwit witness version: {}", fe),
Padding(ref e) => write_err!(f, "invalid padding on the witness data"; e),
WitnessLength(ref e) => write_err!(f, "invalid witness length"; e),
Checksum(ref e) => write_err!(f, "invalid checksum"; e),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for SegwitHrpstringError {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
use SegwitHrpstringError::*;
match *self {
Unchecked(ref e) => Some(e),
Padding(ref e) => Some(e),
WitnessLength(ref e) => Some(e),
Checksum(ref e) => Some(e),
MissingWitnessVersion | InvalidWitnessVersion(_) => None,
}
}
}
impl From<UncheckedHrpstringError> for SegwitHrpstringError {
#[inline]
fn from(e: UncheckedHrpstringError) -> Self { Self::Unchecked(e) }
}
impl From<WitnessLengthError> for SegwitHrpstringError {
#[inline]
fn from(e: WitnessLengthError) -> Self { Self::WitnessLength(e) }
}
impl From<PaddingError> for SegwitHrpstringError {
#[inline]
fn from(e: PaddingError) -> Self { Self::Padding(e) }
}
impl From<ChecksumError> for SegwitHrpstringError {
#[inline]
fn from(e: ChecksumError) -> Self { Self::Checksum(e) }
}
/// An error while constructing a [`CheckedHrpstring`] type.
#[derive(Debug, Clone, PartialEq, Eq)]
#[non_exhaustive]
pub enum CheckedHrpstringError {
/// Error while parsing the encoded address string.
Parse(UncheckedHrpstringError),
/// Invalid checksum.
Checksum(ChecksumError),
}
impl fmt::Display for CheckedHrpstringError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use CheckedHrpstringError::*;
match *self {
Parse(ref e) => write_err!(f, "parse failed"; e),
Checksum(ref e) => write_err!(f, "invalid checksum"; e),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for CheckedHrpstringError {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
use CheckedHrpstringError::*;
match *self {
Parse(ref e) => Some(e),
Checksum(ref e) => Some(e),
}
}
}
impl From<UncheckedHrpstringError> for CheckedHrpstringError {
#[inline]
fn from(e: UncheckedHrpstringError) -> Self { Self::Parse(e) }
}
impl From<ChecksumError> for CheckedHrpstringError {
#[inline]
fn from(e: ChecksumError) -> Self { Self::Checksum(e) }
}
/// Errors when parsing a bech32 encoded string.
#[derive(Debug, Clone, PartialEq, Eq)]
#[non_exhaustive]
pub enum UncheckedHrpstringError {
/// An error with the characters of the input string.
Char(CharError),
/// The human-readable part is invalid.
Hrp(hrp::Error),
}
impl fmt::Display for UncheckedHrpstringError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use UncheckedHrpstringError::*;
match *self {
Char(ref e) => write_err!(f, "character error"; e),
Hrp(ref e) => write_err!(f, "invalid human-readable part"; e),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for UncheckedHrpstringError {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
use UncheckedHrpstringError::*;
match *self {
Char(ref e) => Some(e),
Hrp(ref e) => Some(e),
}
}
}
impl From<CharError> for UncheckedHrpstringError {
#[inline]
fn from(e: CharError) -> Self { Self::Char(e) }
}
impl From<hrp::Error> for UncheckedHrpstringError {
#[inline]
fn from(e: hrp::Error) -> Self { Self::Hrp(e) }
}
/// Character errors in a bech32 encoded string.
#[derive(Debug, Clone, PartialEq, Eq)]
#[non_exhaustive]
pub enum CharError {
/// String does not contain the separator character.
MissingSeparator,
/// No characters after the separator.
NothingAfterSeparator,
/// The checksum does not match the rest of the data.
InvalidChecksum,
/// The checksum is not a valid length.
InvalidChecksumLength,
/// Some part of the string contains an invalid character.
InvalidChar(char),
/// The whole string must be of one case.
MixedCase,
}
impl fmt::Display for CharError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use CharError::*;
match *self {
MissingSeparator => write!(f, "missing human-readable separator, \"{}\"", SEP),
NothingAfterSeparator => write!(f, "invalid data - no characters after the separator"),
InvalidChecksum => write!(f, "invalid checksum"),
InvalidChecksumLength => write!(f, "the checksum is not a valid length"),
InvalidChar(n) => write!(f, "invalid character (code={})", n),
MixedCase => write!(f, "mixed-case strings not allowed"),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for CharError {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
use CharError::*;
match *self {
MissingSeparator
| NothingAfterSeparator
| InvalidChecksum
| InvalidChecksumLength
| InvalidChar(_)
| MixedCase => None,
}
}
}
/// Errors in the checksum of a bech32 encoded string.
#[derive(Debug, Clone, PartialEq, Eq)]
#[non_exhaustive]
pub enum ChecksumError {
/// The checksum does not match the rest of the data.
InvalidChecksum,
/// The checksum is not a valid length.
InvalidChecksumLength,
}
impl fmt::Display for ChecksumError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use ChecksumError::*;
match *self {
InvalidChecksum => write!(f, "invalid checksum"),
InvalidChecksumLength => write!(f, "the checksum is not a valid length"),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for ChecksumError {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
use ChecksumError::*;
match *self {
InvalidChecksum | InvalidChecksumLength => None,
}
}
}
/// Error validating the padding bits on the witness data.
#[derive(Debug, Clone, PartialEq, Eq)]
#[non_exhaustive]
pub enum PaddingError {
/// The data payload has too many bits of padding.
TooMuch,
/// The data payload is padded with non-zero bits.
NonZero,
}
impl fmt::Display for PaddingError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use PaddingError::*;
match *self {
TooMuch => write!(f, "the data payload has too many bits of padding"),
NonZero => write!(f, "the data payload is padded with non-zero bits"),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for PaddingError {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
use PaddingError::*;
match *self {
TooMuch | NonZero => None,
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn bip_173_invalid_parsing_fails() {
use UncheckedHrpstringError::*;
let invalid: Vec<(&str, UncheckedHrpstringError)> = vec!(
("\u{20}1nwldj5",
// TODO: Rust >= 1.59.0 use Hrp(hrp::Error::InvalidAsciiByte('\u{20}'.try_into().unwrap()))),
Hrp(hrp::Error::InvalidAsciiByte(32))),
("\u{7F}1axkwrx",
Hrp(hrp::Error::InvalidAsciiByte(127))),
("\u{80}1eym55h",
Hrp(hrp::Error::NonAsciiChar('\u{80}'))),
("an84characterslonghumanreadablepartthatcontainsthetheexcludedcharactersbioandnumber11d6pts4",
Hrp(hrp::Error::TooLong(84))),
("pzry9x0s0muk",
Char(CharError::MissingSeparator)),
("1pzry9x0s0muk",
Hrp(hrp::Error::Empty)),
("x1b4n0q5v",
Char(CharError::InvalidChar('b'))),
// "li1dgmt3" in separate test because error is a checksum error.
("de1lg7wt\u{ff}",
Char(CharError::InvalidChar('\u{ff}'))),
// "A1G7SGD8" in separate test because error is a checksum error.
("10a06t8",
Hrp(hrp::Error::Empty)),
("1qzzfhee",
Hrp(hrp::Error::Empty)),
);
for (s, want) in invalid {
let got = UncheckedHrpstring::new(s).unwrap_err();
assert_eq!(got, want);
}
}
#[test]
fn bip_173_invalid_parsing_fails_invalid_checksum() {
use ChecksumError::*;
let err = UncheckedHrpstring::new("li1dgmt3")
.expect("string parses correctly")
.validate_checksum::<Bech32>()
.unwrap_err();
assert_eq!(err, InvalidChecksumLength);
let err = UncheckedHrpstring::new("A1G7SGD8")
.expect("string parses correctly")
.validate_checksum::<Bech32>()
.unwrap_err();
assert_eq!(err, InvalidChecksum);
}
#[test]
fn bip_350_invalid_parsing_fails() {
use UncheckedHrpstringError::*;
let invalid: Vec<(&str, UncheckedHrpstringError)> = vec!(
("\u{20}1xj0phk",
// TODO: Rust >= 1.59.0 use Hrp(hrp::Error::InvalidAsciiByte('\u{20}'.try_into().unwrap()))),
Hrp(hrp::Error::InvalidAsciiByte(32))),
("\u{7F}1g6xzxy",
Hrp(hrp::Error::InvalidAsciiByte(127))),
("\u{80}1g6xzxy",
Hrp(hrp::Error::NonAsciiChar('\u{80}'))),
("an84characterslonghumanreadablepartthatcontainsthenumber1andtheexcludedcharactersbio1569pvx",
Hrp(hrp::Error::TooLong(84))),
("qyrz8wqd2c9m",
Char(CharError::MissingSeparator)),
("1qyrz8wqd2c9m",
Hrp(hrp::Error::Empty)),
("y1b0jsk6g",
Char(CharError::InvalidChar('b'))),
("lt1igcx5c0",
Char(CharError::InvalidChar('i'))),
// "in1muywd" in separate test because error is a checksum error.
("mm1crxm3i",
Char(CharError::InvalidChar('i'))),
("au1s5cgom",
Char(CharError::InvalidChar('o'))),
// "M1VUXWEZ" in separate test because error is a checksum error.
("16plkw9",
Hrp(hrp::Error::Empty)),
("1p2gdwpf",
Hrp(hrp::Error::Empty)),
);
for (s, want) in invalid {
let got = UncheckedHrpstring::new(s).unwrap_err();
assert_eq!(got, want);
}
}
#[test]
fn bip_350_invalid_because_of_invalid_checksum() {
use ChecksumError::*;
// Note the "bc1p2" test case is not from the bip test vectors.
let invalid: Vec<&str> = vec!["in1muywd", "bc1p2"];
for s in invalid {
let err =
UncheckedHrpstring::new(s).unwrap().validate_checksum::<Bech32m>().unwrap_err();
assert_eq!(err, InvalidChecksumLength);
}
let err = UncheckedHrpstring::new("M1VUXWEZ")
.unwrap()
.validate_checksum::<Bech32m>()
.unwrap_err();
assert_eq!(err, InvalidChecksum);
}
#[test]
fn check_hrp_uppercase_returns_lower() {
let addr = "BC1QW508D6QEJXTDG4Y5R3ZARVARY0C5XW7KV8F3T4";
let unchecked = UncheckedHrpstring::new(addr).expect("failed to parse address");
assert_eq!(unchecked.hrp(), Hrp::parse_unchecked("bc"));
}
#[test]
#[cfg(feature = "alloc")]
fn check_hrp_max_length() {
let hrps =
"an83characterlonghumanreadablepartthatcontainsthenumber1andtheexcludedcharactersbio";
let hrp = Hrp::parse_unchecked(hrps);
let s = crate::encode::<Bech32>(hrp, &[]).expect("failed to encode empty buffer");
let unchecked = UncheckedHrpstring::new(&s).expect("failed to parse address");
assert_eq!(unchecked.hrp(), hrp);
}
#[test]
fn mainnet_valid_addresses() {
let addresses = vec![
"bc1qar0srrr7xfkvy5l643lydnw9re59gtzzwf5mdq",
"23451QAR0SRRR7XFKVY5L643LYDNW9RE59GTZZLKULZK",
];
for valid in addresses {
assert!(CheckedHrpstring::new::<Bech32>(valid).is_ok())
}
}
macro_rules! check_invalid_segwit_addresses {
($($test_name:ident, $reason:literal, $address:literal);* $(;)?) => {
$(
#[test]
fn $test_name() {
let res = SegwitHrpstring::new($address);
if res.is_ok() {
panic!("{} sting should not be valid: {}", $address, $reason);
}
}
)*
}
}
check_invalid_segwit_addresses! {
invalid_segwit_address_0, "missing hrp", "1qar0srrr7xfkvy5l643lydnw9re59gtzzwf5mdq";
invalid_segwit_address_1, "missing data-checksum", "91111";
invalid_segwit_address_2, "invalid witness version", "bc14r0srrr7xfkvy5l643lydnw9re59gtzzwf5mdq";
invalid_segwit_address_3, "invalid checksum length", "bc1q5mdq";
invalid_segwit_address_4, "missing data", "bc1qwf5mdq";
invalid_segwit_address_5, "invalid program length", "bc14r0srrr7xfkvy5l643lydnw9rewf5mdq";
}
}