diff --git a/packages/marshal/NEWS.md b/packages/marshal/NEWS.md index 4b4f8d2366..84d8331b55 100644 --- a/packages/marshal/NEWS.md +++ b/packages/marshal/NEWS.md @@ -1,5 +1,13 @@ User-visible changes in `@endo/marshal`: +# Next release + +- JavaScript's relational comparison operators like `<` compare strings by lexicographic UTF16 code unit order, which is exposes an internal representational detail not relevant to the string's meaning as a Unicode string. Previously, `compareRank` and associated functions compared strings using this JavaScript-native comparison. Now `compareRank` and associated functions compare strings by lexicographic Unicode Code Point order. ***This change only affects strings containing so-called supplementary characters, i.e., those whose Unicode character code does not fit in 16 bits***. + - This release does not change the `encodePassable` encoding. But now, when we say it is order preserving, we need to be careful about which order we mean. `encodePassable` is rank-order preserving when the encoded strings are compared using `compareRank`. + - The key order of strings defined by the @endo/patterns module is still defined to be the same as the rank ordering of those strings. So this release changes key order among strings to also be lexicographic comparison of Unicode Code Points. To accommodate this change, you may need to adapt applications that relied on key-order being the same as JS native order. This could include the use of any patterns expressing key inequality tests, like `M.gte(string)`. + - These string ordering changes brings Endo into conformance with any string ordering components of the OCapN standard. + - To accommodate these change, you may need to adapt applications that relied on rank-order or key-order being the same as JS native order. You may need to resort any data that had previously been rank sorted using the prior `compareRank` function. You may need to revisit any use of patterns like `M.gte(string)` expressing inequalities over strings. + # v1.3.0 (2024-02-22) - Sending and receiving extended errors. diff --git a/packages/marshal/index.js b/packages/marshal/index.js index 6973cf84d7..90a66780b6 100644 --- a/packages/marshal/index.js +++ b/packages/marshal/index.js @@ -18,6 +18,7 @@ export { export { trivialComparator, + compareByCodePoints, assertRankSorted, compareRank, isRankSorted, diff --git a/packages/marshal/src/rankOrder.js b/packages/marshal/src/rankOrder.js index cfbb24924f..18f5982585 100644 --- a/packages/marshal/src/rankOrder.js +++ b/packages/marshal/src/rankOrder.js @@ -44,9 +44,46 @@ const { entries, fromEntries, setPrototypeOf, is } = Object; */ const sameValueZero = (x, y) => x === y || is(x, y); +/** + * @param {any} left + * @param {any} right + * @returns {RankComparison} + */ export const trivialComparator = (left, right) => // eslint-disable-next-line no-nested-ternary, @endo/restrict-comparison-operands left < right ? -1 : left === right ? 0 : 1; +harden(trivialComparator); + +// Apparently eslint confused about whether the function can ever exit +// without an explicit return. +// eslint-disable-next-line jsdoc/require-returns-check +/** + * @param {string} left + * @param {string} right + * @returns {RankComparison} + */ +export const compareByCodePoints = (left, right) => { + const leftIter = left[Symbol.iterator](); + const rightIter = right[Symbol.iterator](); + for (;;) { + const { value: leftChar } = leftIter.next(); + const { value: rightChar } = rightIter.next(); + if (leftChar === undefined && rightChar === undefined) { + return 0; + } else if (leftChar === undefined) { + // left is a prefix of right. + return -1; + } else if (rightChar === undefined) { + // right is a prefix of left. + return 1; + } + const leftCodepoint = /** @type {number} */ (leftChar.codePointAt(0)); + const rightCodepoint = /** @type {number} */ (rightChar.codePointAt(0)); + if (leftCodepoint < rightCodepoint) return -1; + if (leftCodepoint > rightCodepoint) return 1; + } +}; +harden(compareByCodePoints); /** * @typedef {Record} PassStyleRanksRecord @@ -138,8 +175,7 @@ export const makeComparatorKit = (compareRemotables = (_x, _y) => 0) => { return 0; } case 'boolean': - case 'bigint': - case 'string': { + case 'bigint': { // Within each of these passStyles, the rank ordering agrees with // JavaScript's relational operators `<` and `>`. if (left < right) { @@ -149,6 +185,9 @@ export const makeComparatorKit = (compareRemotables = (_x, _y) => 0) => { return 1; } } + case 'string': { + return compareByCodePoints(left, right); + } case 'symbol': { return comparator( nameForPassableSymbol(left), diff --git a/packages/marshal/test/test-encodePassable.js b/packages/marshal/test/test-encodePassable.js index 6583479efe..7f964f4fcf 100644 --- a/packages/marshal/test/test-encodePassable.js +++ b/packages/marshal/test/test-encodePassable.js @@ -71,7 +71,7 @@ const encodePassableInternal2 = makeEncodePassable({ format: 'compactOrdered', }); -const encodePassable = passable => { +export const encodePassable = passable => { resetBuffers(); return encodePassableInternal(passable); }; @@ -86,7 +86,7 @@ const decodePassableInternal = makeDecodePassable({ decodeError: e => decodeThing('!', e), }); -const decodePassable = encoded => { +export const decodePassable = encoded => { resetCursors(); return decodePassableInternal(encoded); }; diff --git a/packages/marshal/test/test-string-rank-order.js b/packages/marshal/test/test-string-rank-order.js new file mode 100644 index 0000000000..590b59b0f2 --- /dev/null +++ b/packages/marshal/test/test-string-rank-order.js @@ -0,0 +1,64 @@ +import { test } from './prepare-test-env-ava.js'; + +import { compareRank } from '../src/rankOrder.js'; +import { encodePassable } from './test-encodePassable.js'; + +/** + * Essentially a ponyfill for Array.prototype.toSorted, for use before + * we can always rely on the platform to provide it. + * + * @param {string[]} strings + * @param {( + * left: string, + * right: string + * ) => import('../src/types.js').RankComparison} comp + * @returns {string[]} + */ +const sorted = (strings, comp) => [...strings].sort(comp); + +test('unicode code point order', t => { + // Test case from + // https://icu-project.org/docs/papers/utf16_code_point_order.html + const str0 = '\u{ff61}'; + const str3 = '\u{d800}\u{dc02}'; + + // str1 and str2 become impossible examples once we prohibit + // non - well - formed strings. + // See https://github.com/endojs/endo/pull/2002 + const str1 = '\u{d800}X'; + const str2 = '\u{d800}\u{ff61}'; + + // harden to ensure it is not sorted in place, just for sanity + const strs = harden([str0, str1, str2, str3]); + + /** + * @param {string} left + * @param {string} right + * @returns {import('../src/types.js').RankComparison} + */ + const nativeComp = (left, right) => + // eslint-disable-next-line no-nested-ternary + left < right ? -1 : left > right ? 1 : 0; + + const nativeSorted = sorted(strs, nativeComp); + + t.deepEqual(nativeSorted, [str1, str3, str2, str0]); + + const rankSorted = sorted(strs, compareRank); + + t.deepEqual(rankSorted, [str1, str2, str0, str3]); + + const nativeEncComp = (left, right) => + nativeComp(encodePassable(left), encodePassable(right)); + + const nativeEncSorted = sorted(strs, nativeEncComp); + + t.deepEqual(nativeEncSorted, nativeSorted); + + const rankEncComp = (left, right) => + compareRank(encodePassable(left), encodePassable(right)); + + const rankEncSorted = sorted(strs, rankEncComp); + + t.deepEqual(rankEncSorted, rankSorted); +}); diff --git a/packages/patterns/NEWS.md b/packages/patterns/NEWS.md index 1de20be073..4064edc5e8 100644 --- a/packages/patterns/NEWS.md +++ b/packages/patterns/NEWS.md @@ -1,5 +1,10 @@ User-visible changes in `@endo/patterns`: +# Next release + +- JavaScript's relational comparison operators like `<` compare strings by lexicographic UTF16 code unit order, which is exposes an internal representational detail not relevant to the string's meaning as a Unicode string. Previously, `compareKeys` and associated functions compared strings using this JavaScript-native comparison. Now `compareKeys` and associated functions compare strings by lexicographic Unicode Code Point order. ***This change only affects strings containing so-called supplementary characters, i.e., those whose Unicode character code does not fit in 16 bits***. + - See the NEWS.md of @endo/marshal for more on this change. + # v1.2.0 (2024-02-22) - Add `M.tagged(tagPattern, payloadPattern)` for making patterns that match diff --git a/packages/patterns/test/test-string-key-order.js b/packages/patterns/test/test-string-key-order.js new file mode 100644 index 0000000000..c1a1f3d293 --- /dev/null +++ b/packages/patterns/test/test-string-key-order.js @@ -0,0 +1,55 @@ +// modeled on test-string-rank-order.js + +import { test } from './prepare-test-env-ava.js'; + +import { compareKeys } from '../src/keys/compareKeys.js'; + +/** + * Essentially a ponyfill for Array.prototype.toSorted, for use before + * we can always rely on the platform to provide it. + * + * @param {string[]} strings + * @param {( + * left: string, + * right: string + * ) => import('@endo/marshal').RankComparison} comp + * @returns {string[]} + */ +const sorted = (strings, comp) => [...strings].sort(comp); + +test('unicode code point order', t => { + // Test case from + // https://icu-project.org/docs/papers/utf16_code_point_order.html + const str0 = '\u{ff61}'; + const str3 = '\u{d800}\u{dc02}'; + + // str1 and str2 become impossible examples once we prohibit + // non - well - formed strings. + // See https://github.com/endojs/endo/pull/2002 + const str1 = '\u{d800}X'; + const str2 = '\u{d800}\u{ff61}'; + + // harden to ensure it is not sorted in place, just for sanity + const strs = harden([str0, str1, str2, str3]); + + /** + * @param {string} left + * @param {string} right + * @returns {import('@endo/marshal').RankComparison} + */ + const nativeComp = (left, right) => + // eslint-disable-next-line no-nested-ternary + left < right ? -1 : left > right ? 1 : 0; + + const nativeSorted = sorted(strs, nativeComp); + + t.deepEqual(nativeSorted, [str1, str3, str2, str0]); + + // @ts-expect-error We know that for strings, `compareKeys` never returns + // NaN because it never judges strings to be incomparable. Thus, the + // KeyComparison it returns happens to also be a RankComparison we can + // sort with. + const keySorted = sorted(strs, compareKeys); + + t.deepEqual(keySorted, [str1, str2, str0, str3]); +});