@bcts/uniform-resources 1.0.0-alpha.21 → 1.0.0-alpha.23

package/README.md

@@ -14,4 +14,4 @@ The primary specification for URs is [BCR-2020-005: Uniform Resources](https://g
 
 ## Rust Reference Implementation
 
-This TypeScript implementation is based on [bc-ur-rust](https://github.com/BlockchainCommons/bc-ur-rust) **v0.19.0** ([commit](https://github.com/BlockchainCommons/bc-ur-rust/tree/285c849a546e68c5f6b983ee517cb66348fed0a3)).
+This TypeScript implementation is based on [bc-ur-rust](https://github.com/BlockchainCommons/bc-ur-rust) **v0.19.2** ([commit](https://github.com/BlockchainCommons/bc-ur-rust/tree/2f8b4e728945f9dc248eba71911b89371f076924)).

package/dist/index.cjs

@@ -1,7 +1,6 @@
-Object.defineProperty(exports, Symbol.toStringTag, { value: 'Module' });
+Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
 let _bcts_dcbor = require("@bcts/dcbor");
 let _bcts_crypto = require("@bcts/crypto");
-
 //#region src/error.ts
 /**
 * Copyright © 2023-2026 Blockchain Commons, LLC
@@ -95,7 +94,6 @@ var URDecodeError = class extends URError {
 function isError(result) {
 	return result instanceof Error;
 }
-
 //#endregion
 //#region src/utils.ts
 /**
@@ -653,36 +651,102 @@ const BYTEMOJIS = [
 	"🐳"
 ];
 /**
-* Encodes a 4-byte slice as a string of bytewords for identification.
+* Encodes an arbitrary byte slice as a string of space-separated bytewords.
+*
+* Mirrors `bytewords::encode_to_words` in `bc-ur-rust` (≥ v0.19.1). Does not
+* add a CRC32 checksum — use {@link encodeBytewords} for UR-style encoding.
 */
-function encodeBytewordsIdentifier(data) {
-	if (data.length !== 4) throw new Error("Identifier data must be exactly 4 bytes");
+function encodeToWords(data) {
 	const words = [];
-	for (let i = 0; i < 4; i++) {
-		const byte = data[i];
-		if (byte === void 0) throw new Error("Invalid byte");
+	for (const byte of data) {
 		const word = BYTEWORDS[byte];
-		if (word === "" || word === void 0) throw new Error("Invalid byteword mapping");
+		if (word === void 0) throw new Error(`Invalid byte value: ${byte}`);
 		words.push(word);
 	}
 	return words.join(" ");
 }
 /**
-* Encodes a 4-byte slice as a string of bytemojis for identification.
+* Encodes an arbitrary byte slice as a string of space-separated bytemojis.
+*
+* Mirrors `bytewords::encode_to_bytemojis` in `bc-ur-rust` (≥ v0.19.1).
 */
-function encodeBytemojisIdentifier(data) {
-	if (data.length !== 4) throw new Error("Identifier data must be exactly 4 bytes");
+function encodeToBytemojis(data) {
 	const emojis = [];
-	for (let i = 0; i < 4; i++) {
-		const byte = data[i];
-		if (byte === void 0) throw new Error("Invalid byte");
+	for (const byte of data) {
 		const emoji = BYTEMOJIS[byte];
-		if (emoji === "" || emoji === void 0) throw new Error("Invalid bytemoji mapping");
+		if (emoji === void 0) throw new Error(`Invalid byte value: ${byte}`);
 		emojis.push(emoji);
 	}
 	return emojis.join(" ");
 }
 /**
+* Encodes an arbitrary byte slice as minimal bytewords (first + last letter of
+* each word, concatenated with no separator).
+*
+* Mirrors `bytewords::encode_to_minimal_bytewords` in `bc-ur-rust`
+* (≥ v0.19.1). Does not add a CRC32 checksum.
+*/
+function encodeToMinimalBytewords(data) {
+	let out = "";
+	for (const byte of data) {
+		const word = BYTEWORDS[byte];
+		if (word === void 0) throw new Error(`Invalid byte value: ${byte}`);
+		out += word[0] + word[word.length - 1];
+	}
+	return out;
+}
+/**
+* Encodes a 4-byte slice as a string of bytewords for identification.
+*
+* Thin wrapper over {@link encodeToWords} that enforces the 4-byte length
+* contract historically used by `bc-ur-rust`'s `bytewords::identifier`.
+*/
+function encodeBytewordsIdentifier(data) {
+	if (data.length !== 4) throw new Error("Identifier data must be exactly 4 bytes");
+	return encodeToWords(data);
+}
+/**
+* Encodes a 4-byte slice as a string of bytemojis for identification.
+*
+* Thin wrapper over {@link encodeToBytemojis} that enforces the 4-byte length
+* contract historically used by `bc-ur-rust`'s `bytewords::bytemoji_identifier`.
+*/
+function encodeBytemojisIdentifier(data) {
+	if (data.length !== 4) throw new Error("Identifier data must be exactly 4 bytes");
+	return encodeToBytemojis(data);
+}
+/**
+* Returns `true` if `emoji` is one of the 256 bytemojis.
+*
+* Mirrors `bytewords::is_valid_bytemoji` in `bc-ur-rust` (≥ v0.19.1).
+*/
+function isValidBytemoji(emoji) {
+	return BYTEMOJI_SET.has(emoji);
+}
+/**
+* Canonicalises a byteword token (2–4 ASCII letters, case-insensitive) to its
+* full 4-letter lowercase form. Returns `undefined` if the token is not a
+* valid byteword or any of its short forms.
+*
+* Mirrors `bytewords::canonicalize_byteword` in `bc-ur-rust` (≥ v0.19.1).
+*
+* - 2-letter tokens are matched against the first + last letter of each
+*   byteword (identical to the minimal bytewords encoding).
+* - 3-letter tokens are matched against the first 3 and the last 3 letters of
+*   each byteword; if both match different entries, the first-3 match wins
+*   (matching rust's `or_else` priority).
+* - 4-letter tokens must exactly match a full byteword (after lower-casing).
+*/
+function canonicalizeByteword(token) {
+	const lower = token.toLowerCase();
+	switch (lower.length) {
+		case 4: return BYTEWORDS_MAP.has(lower) ? lower : void 0;
+		case 2: return BYTEWORD_FIRST_LAST_MAP.get(lower);
+		case 3: return BYTEWORD_FIRST_THREE_MAP.get(lower) ?? BYTEWORD_LAST_THREE_MAP.get(lower);
+		default: return;
+	}
+}
+/**
 * Bytewords encoding style.
 */
 let BytewordsStyle = /* @__PURE__ */ function(BytewordsStyle) {
@@ -707,6 +771,38 @@ function createMinimalBytewordsMap() {
 }
 const MINIMAL_BYTEWORDS_MAP = createMinimalBytewordsMap();
 /**
+* Set of all 256 bytemojis for fast membership testing. Backs
+* {@link isValidBytemoji}.
+*/
+const BYTEMOJI_SET = new Set(BYTEMOJIS);
+/**
+* Lookup from a 2-letter (first+last) byteword short-form to its full
+* lowercase 4-letter form. Backs {@link canonicalizeByteword}.
+*/
+const BYTEWORD_FIRST_LAST_MAP = (() => {
+	const map = /* @__PURE__ */ new Map();
+	for (const word of BYTEWORDS) map.set(word[0] + word[word.length - 1], word);
+	return map;
+})();
+/**
+* Lookup from the first 3 letters of a byteword to its full lowercase 4-letter
+* form. Backs {@link canonicalizeByteword}.
+*/
+const BYTEWORD_FIRST_THREE_MAP = (() => {
+	const map = /* @__PURE__ */ new Map();
+	for (const word of BYTEWORDS) map.set(word.slice(0, 3), word);
+	return map;
+})();
+/**
+* Lookup from the last 3 letters of a byteword to its full lowercase 4-letter
+* form. Backs {@link canonicalizeByteword}.
+*/
+const BYTEWORD_LAST_THREE_MAP = (() => {
+	const map = /* @__PURE__ */ new Map();
+	for (const word of BYTEWORDS) map.set(word.slice(1), word);
+	return map;
+})();
+/**
 * CRC32 lookup table (IEEE polynomial).
 */
 const CRC32_TABLE = (() => {
@@ -741,7 +837,7 @@ function uint32ToBytes(value) {
 * Encode data as bytewords with the specified style.
 * Includes CRC32 checksum.
 */
-function encodeBytewords(data, style = BytewordsStyle.Minimal) {
+function encodeBytewords(data, style = "minimal") {
 	const checksumBytes = uint32ToBytes(crc32(data));
 	const dataWithChecksum = new Uint8Array(data.length + 4);
 	dataWithChecksum.set(data);
@@ -751,46 +847,46 @@ function encodeBytewords(data, style = BytewordsStyle.Minimal) {
 		const word = BYTEWORDS[byte];
 		if (word === void 0) throw new Error(`Invalid byte value: ${byte}`);
 		switch (style) {
-			case BytewordsStyle.Standard:
+			case "standard":
 				words.push(word);
 				break;
-			case BytewordsStyle.Uri:
+			case "uri":
 				words.push(word);
 				break;
-			case BytewordsStyle.Minimal:
+			case "minimal":
 				words.push(word[0] + word[3]);
 				break;
 		}
 	}
 	switch (style) {
-		case BytewordsStyle.Standard: return words.join(" ");
-		case BytewordsStyle.Uri: return words.join("-");
-		case BytewordsStyle.Minimal: return words.join("");
+		case "standard": return words.join(" ");
+		case "uri": return words.join("-");
+		case "minimal": return words.join("");
 	}
 }
 /**
 * Decode bytewords string back to data.
 * Validates and removes CRC32 checksum.
 */
-function decodeBytewords(encoded, style = BytewordsStyle.Minimal) {
+function decodeBytewords(encoded, style = "minimal") {
 	const lowercased = encoded.toLowerCase();
 	let bytes;
 	switch (style) {
-		case BytewordsStyle.Standard:
+		case "standard":
 			bytes = lowercased.split(" ").map((word) => {
 				const index = BYTEWORDS_MAP.get(word);
 				if (index === void 0) throw new Error(`Invalid byteword: ${word}`);
 				return index;
 			});
 			break;
-		case BytewordsStyle.Uri:
+		case "uri":
 			bytes = lowercased.split("-").map((word) => {
 				const index = BYTEWORDS_MAP.get(word);
 				if (index === void 0) throw new Error(`Invalid byteword: ${word}`);
 				return index;
 			});
 			break;
-		case BytewordsStyle.Minimal:
+		case "minimal":
 			if (lowercased.length % 2 !== 0) throw new Error("Invalid minimal bytewords length");
 			bytes = [];
 			for (let i = 0; i < lowercased.length; i += 2) {
@@ -810,7 +906,6 @@ function decodeBytewords(encoded, style = BytewordsStyle.Minimal) {
 	if (expectedChecksum !== actualChecksum) throw new Error(`Bytewords checksum mismatch: expected ${expectedChecksum.toString(16)}, got ${actualChecksum.toString(16)}`);
 	return data;
 }
-
 //#endregion
 //#region src/ur-type.ts
 /**
@@ -894,7 +989,6 @@ var URType = class URType {
 		}
 	}
 };
-
 //#endregion
 //#region src/ur.ts
 /**
@@ -1037,7 +1131,7 @@ var UR = class UR {
 */
 var URStringEncoder = class {
 	static encode(urType, cborData) {
-		return `ur:${urType}/${encodeBytewords(cborData, BytewordsStyle.Minimal)}`;
+		return `ur:${urType}/${encodeBytewords(cborData, "minimal")}`;
 	}
 };
 /**
@@ -1054,14 +1148,13 @@ var URStringDecoder = class {
 		try {
 			return {
 				urType,
-				cbor: (0, _bcts_dcbor.decodeCbor)(decodeBytewords(data, BytewordsStyle.Minimal))
+				cbor: (0, _bcts_dcbor.decodeCbor)(decodeBytewords(data, "minimal"))
 			};
 		} catch (error) {
 			throw new URError(`Failed to decode UR: ${error instanceof Error ? error.message : String(error)}`);
 		}
 	}
 };
-
 //#endregion
 //#region src/ur-encodable.ts
 /**
@@ -1070,7 +1163,6 @@ var URStringDecoder = class {
 function isUREncodable(obj) {
 	return typeof obj === "object" && obj !== null && "ur" in obj && "urString" in obj && typeof obj["ur"] === "function" && typeof obj["urString"] === "function";
 }
-
 //#endregion
 //#region src/ur-decodable.ts
 /**
@@ -1079,7 +1171,6 @@ function isUREncodable(obj) {
 function isURDecodable(obj) {
 	return typeof obj === "object" && obj !== null && "fromUR" in obj && typeof obj["fromUR"] === "function";
 }
-
 //#endregion
 //#region src/ur-codable.ts
 /**
@@ -1088,7 +1179,6 @@ function isURDecodable(obj) {
 function isURCodable(obj) {
 	return typeof obj === "object" && obj !== null && "ur" in obj && "urString" in obj && "fromUR" in obj && typeof obj["ur"] === "function" && typeof obj["urString"] === "function" && typeof obj["fromUR"] === "function";
 }
-
 //#endregion
 //#region src/xoshiro.ts
 /**
@@ -1300,7 +1390,6 @@ function createSeed(checksum, seqNum) {
 	seed8[7] = checksum & 255;
 	return (0, _bcts_crypto.sha256)(seed8);
 }
-
 //#endregion
 //#region src/fountain.ts
 /**
@@ -1553,7 +1642,6 @@ var FountainDecoder = class {
 		this.mixedParts.clear();
 	}
 };
-
 //#endregion
 //#region src/multipart-encoder.ts
 /**
@@ -1602,7 +1690,8 @@ var MultipartEncoder = class {
 	constructor(ur, maxFragmentLen) {
 		if (maxFragmentLen < 1) throw new URError("Max fragment length must be at least 1");
 		this._ur = ur;
-		this._fountainEncoder = new FountainEncoder(ur.cbor().toData(), maxFragmentLen);
+		const cborData = ur.cbor().toData();
+		this._fountainEncoder = new FountainEncoder(cborData, maxFragmentLen);
 	}
 	/**
 	* Gets the next part of the encoding.
@@ -1628,7 +1717,7 @@ var MultipartEncoder = class {
 	*/
 	_encodePart(part) {
 		if (part.seqLen === 1) return this._ur.string();
-		const encoded = encodeBytewords(this._encodePartData(part), BytewordsStyle.Minimal);
+		const encoded = encodeBytewords(this._encodePartData(part), "minimal");
 		return `ur:${this._ur.urTypeStr()}/${part.seqNum}-${part.seqLen}/${encoded}`;
 	}
 	/**
@@ -1660,7 +1749,6 @@ var MultipartEncoder = class {
 		return this._fountainEncoder.seqLen;
 	}
 };
-
 //#endregion
 //#region src/multipart-decoder.ts
 /**
@@ -1749,7 +1837,7 @@ var MultipartDecoder = class {
 	* The multipart body is a CBOR array: [seqNum, seqLen, messageLen, checksum, data]
 	*/
 	_decodeFountainPart(partInfo) {
-		const decoded = (0, _bcts_dcbor.decodeCbor)(decodeBytewords(partInfo.encodedData, BytewordsStyle.Minimal));
+		const decoded = (0, _bcts_dcbor.decodeCbor)(decodeBytewords(partInfo.encodedData, "minimal"));
 		if (decoded.type !== _bcts_dcbor.MajorType.Array) throw new URError("Invalid multipart data: expected CBOR array");
 		const items = decoded.value;
 		if (items.length !== 5) throw new URError(`Invalid multipart data: expected 5 elements, got ${items.length}`);
@@ -1782,7 +1870,6 @@ var MultipartDecoder = class {
 		return this._decodedMessage;
 	}
 };
-
 //#endregion
 exports.BYTEMOJIS = BYTEMOJIS;
 exports.BYTEWORDS = BYTEWORDS;
@@ -1800,12 +1887,18 @@ exports.URDecodeError = URDecodeError;
 exports.URError = URError;
 exports.URType = URType;
 exports.UnexpectedTypeError = UnexpectedTypeError;
+exports.canonicalizeByteword = canonicalizeByteword;
 exports.decodeBytewords = decodeBytewords;
 exports.encodeBytemojisIdentifier = encodeBytemojisIdentifier;
 exports.encodeBytewords = encodeBytewords;
 exports.encodeBytewordsIdentifier = encodeBytewordsIdentifier;
+exports.encodeToBytemojis = encodeToBytemojis;
+exports.encodeToMinimalBytewords = encodeToMinimalBytewords;
+exports.encodeToWords = encodeToWords;
 exports.isError = isError;
 exports.isURCodable = isURCodable;
 exports.isURDecodable = isURDecodable;
 exports.isUREncodable = isUREncodable;
+exports.isValidBytemoji = isValidBytemoji;
+
 //# sourceMappingURL=index.cjs.map