3
0
mirror of https://github.com/larvit/adf-codec.git synced 2026-11-18 22:25:44 +01:00

Answer architecture round 4: the forecast and the indent leave, a writer refuses a document whose text alone passes the bound, and the joins are the one bound left

This commit is contained in:
2026-10-12 18:03:58 +02:00
committed by Lillem4n
parent ae1a47f1bc
commit a0bb09b80d
17 changed files with 110 additions and 141 deletions
+10 -21
View File
@@ -46,6 +46,11 @@ test('refuses a value that is not an ADF document, naming the check it failed',
const tooLong = 'unsupported-node-shape: spelled as markdown, this would be longer than 536870888 characters, the longest string V8 holds'
// A code block of 300 lines, two of them some 1000 characters short of V8's longest string, so only what their spelling adds passes it.
function nearlyHalfTheBound(): AdfNode {
return { attrs: {}, content: [{ text: `${'a'.repeat(894_782)}\n`.repeat(300), type: 'text' }], type: 'codeBlock' }
}
// About 556 million characters of carry JSON: past V8's longest string, short of JavaScriptCore's and SpiderMonkey's.
test('refuses a carry whose JSON would run past V8\'s longest string, on every engine', () => {
let value: JsonValue = new Array<JsonValue>(560_000).fill(0)
@@ -55,10 +60,8 @@ test('refuses a carry whose JSON would run past V8\'s longest string, on every e
})
test('refuses lines their quotes would prefix past V8\'s longest string', () => {
let quote: AdfNode = { attrs: {}, content: [{ text: 'a\n'.repeat(1_100_000), type: 'text' }], type: 'codeBlock' }
for (let level = 0; level < 245; level += 1) quote = { content: [quote], type: 'blockquote' }
const result = adfToLosslessMarkdown(document(quote))
assert.equal(markdown(result), tooLong)
const code = nearlyHalfTheBound()
assert.equal(markdown(adfToLosslessMarkdown(document({ content: [code, code], type: 'blockquote' }))), tooLong)
})
test('refuses a directive whose opener and body together would pass V8\'s longest string', () => {
@@ -67,23 +70,9 @@ test('refuses a directive whose opener and body together would pass V8\'s longes
assert.equal(markdown(adfToLosslessMarkdown(document(expand))), tooLong)
})
test('refuses a list whose items together would pass V8\'s longest string', () => {
const item: AdfNode = { content: [{ attrs: {}, content: [{ text: 'a'.repeat(2 ** 28), type: 'text' }], type: 'codeBlock' }], type: 'listItem' }
const result = adfToLosslessMarkdown(document({ content: [item, item], type: 'bulletList' }))
assert.equal(markdown(result), tooLong)
})
test('refuses a pipe table whose rows their containers would prefix past V8\'s longest string', () => {
const row: AdfNode = { content: [{ content: [{ type: 'paragraph' }], type: 'tableCell' }], type: 'tableRow' }
const header: AdfNode = { content: [{ content: [{ type: 'paragraph' }], type: 'tableHeader' }], type: 'tableRow' }
let quote: AdfNode = { content: [header, ...Array.from({ length: 1_100_000 }, () => row)], type: 'table' }
for (let level = 0; level < 245; level += 1) quote = { content: [quote], type: 'blockquote' }
assert.equal(markdown(adfToLosslessMarkdown(document(quote))), tooLong)
})
test('refuses a code block whose fences together would pass V8\'s longest string', () => {
const long: AdfNode = { text: 'a'.repeat(2 ** 28), type: 'text' }
assert.equal(markdown(adfToLosslessMarkdown(document({ attrs: {}, content: [long, long, long], type: 'codeBlock' }))), tooLong)
test('refuses a list whose item markers would carry its lines past V8\'s longest string', () => {
const item: AdfNode = { content: [nearlyHalfTheBound()], type: 'listItem' }
assert.equal(markdown(adfToLosslessMarkdown(document({ content: [item, item], type: 'bulletList' }))), tooLong)
})
test('refuses a directive opener whose attributes together would pass V8\'s longest string', () => {
+26 -50
View File
@@ -1,7 +1,7 @@
import type { AdfDocument, AdfNode } from '../../adf/document.ts'
import type { BlockNodeModel } from '../../adf/block-nodes.ts'
import type { WrittenFlavour } from '../portable/conventions.ts'
import { adfDocumentFault, holdsOnlyAttributes, isUnmarkedSpellableText, nodeAttrs, nodeContent } from '../../adf/document.ts'
import { adfDocumentFault, heldTextLength, holdsOnlyAttributes, isUnmarkedSpellableText, nodeAttrs, nodeContent } from '../../adf/document.ts'
import { alertMarker, flavourClaims, foldedAlertMarker, leadingMarker, readAlertMarker, readTaskMarker, taskMarker } from '../portable/conventions.ts'
import { blockDirectiveForm, documentSpelling } from '../block-directive.ts'
import { blockNodeModel, blockNodes, isTaskItem } from '../../adf/block-nodes.ts'
@@ -27,21 +27,17 @@ type PlacedBlock = SpelledBlock & { node: AdfNode }
type PlacedBlocks = { blocks: readonly PlacedBlock[]; headroom: number }
// CommonMark starts a new list where the marker changes, so every second list in a run of one kind takes `alternateText`.
type SpelledBlock = { spelling: 'commonmark' | 'directive'; text: string } | { alternateText: string; spelling: 'list'; text: string }
// joined: each item's text; start: the first item's number.
type SpelledItems = { joined: readonly string[]; start: number; walked: readonly WalkedItem[] }
// Keyed by reference: only a caller building one object per position (the parse, the portable reduction) passes one; a consumer's document may share a node.
export type SpellingMemo = Map<AdfNode, KeptSpelling>
type WalkedItem = { node: AdfNode; walk: PlacedBlocks }
// indent: the characters the containers around a block surely prefix each of its lines with.
export type Writing = { flavour: WrittenFlavour; indent: number; memo: SpellingMemo | undefined }
// inner: the item's blocks joined, for the list form; walk: the blocks themselves, for the directive form.
type WalkedItem = { inner: string; node: AdfNode; walk: PlacedBlocks }
export type Writing = { flavour: WrittenFlavour; memo: SpellingMemo | undefined }
const bulletDelimiters: Delimiters = ['-', '*']
const bulletWidth = '- '.length
export const largestListMarker = 999999999
// Bare because tryList admits no item carrying attributes, marks or text.
const listItemOpener = spellDirectiveOpener('listItem', undefined, '')
const orderedDelimiters: Delimiters = ['.', ')']
const quoteWidth = '> '.length
export function adfToLosslessMarkdown(document: AdfDocument): Result<string> {
return withinEngineLimits(() => writeMarkdown(document, 'lossless'))
@@ -52,7 +48,9 @@ export function writeMarkdown(document: AdfDocument, flavour: WrittenFlavour): R
if (fault !== undefined) return faulted(fault, [])
if (document.version !== 1) return failure('unsupported-document-version', `no markdown spelling carries ADF version ${document.version}`, [])
if (document.content === undefined) return success(`${documentSpelling}\n`)
const walk = walkBlocks(document.content, [], 0, { flavour, indent: 0, memo: undefined })
// Every character of text is spelled at least once, so this much text cannot fit, and none of it is spelled.
if (heldTextLength(document.content) > longestMarkdown) return tooLong()
const walk = walkBlocks(document.content, [], 0, { flavour, memo: undefined })
if (!walk.ok) return walk
const text = joinedWithin(walk.value.blocks.length === 0 ? [] : [...blockPieces(walk.value.blocks, 'document'), '\n'])
return boundedThen(text, success)
@@ -62,35 +60,15 @@ function walkBlocks(nodes: readonly AdfNode[], path: ConvertErrorPath, depth: nu
let headroom = largestNesting - depth
if (headroom < 0) return tooDeep(path)
const blocks: PlacedBlock[] = []
// A forecast that never overcounts, so a deep subtree refuses where its containers would prefix its lines past the bound, before any of them copies those lines.
let forecast = 0
for (const [index, node] of nodes.entries()) {
const block = emitBlock(node, [...path, 'content', index], depth, writing)
if (!block.ok) return block
forecast += prefixedLength(block.value.text, writing.indent)
if (forecast > longestMarkdown) return tooLong()
headroom = Math.min(headroom, block.value.headroom)
blocks.push({ ...block.value, node })
}
return success({ blocks, headroom })
}
// A blank line takes no indent in a list item and one `>` in a quote, so only the others are charged it.
function prefixedLength(text: string, indent: number): number {
let length = text.length
for (let start = 0; start <= text.length; ) {
const end = text.indexOf('\n', start)
const stop = end === -1 ? text.length : end
if (stop > start) length += indent
start = stop + 1
}
return length
}
function indented(writing: Writing, width: number): Writing {
return { ...writing, indent: writing.indent + width }
}
function tooDeep(path: ConvertErrorPath): Result<never> {
return failure('unsupported-nesting-depth', `the document nests deeper than the ${largestNesting} levels the emitter carries`, path)
}
@@ -185,18 +163,17 @@ function spellPortableBlock(node: AdfNode, path: ConvertErrorPath, depth: number
}
function quotedUnder(head: string, node: AdfNode, path: ConvertErrorPath, depth: number, writing: Writing): Result<EmittedBlock> {
const inner = walkBlocks(nodeContent(node), path, depth + 1, indented(writing, quoteWidth))
const inner = walkBlocks(nodeContent(node), path, depth + 1, writing)
if (!inner.ok) return inner
const text = joinedWithin(inner.value.blocks.length === 0 ? [head] : [head, '\n\n', ...blockPieces(inner.value.blocks, 'document')])
return quotedBlock(text, inner.value.headroom)
}
function quotedBlock(text: string | undefined, headroom: number): Result<EmittedBlock> {
const quoted = (whole: string): Result<EmittedBlock> => boundedThen(joinedWithin(quotedPieces(whole)), (quotedText) => success(commonMarkText(quotedText, headroom)))
return boundedThen(text, quoted)
const quoted = text === undefined ? undefined : joinedWithin(quotedPieces(text))
return boundedThen(quoted, (spelled) => success(commonMarkText(spelled, headroom)))
}
function* quotedPieces(text: string): Generator<string> {
for (let start = 0; ; ) {
const end = text.indexOf('\n', start)
@@ -215,8 +192,7 @@ function tryTaskList(node: AdfNode, path: ConvertErrorPath, depth: number, writi
// A child other than a task nests in the task before it.
for (const [index, child] of nodeContent(node).entries()) {
const task = isTaskItem(child)
const itemWriting = indented(writing, bulletWidth)
const walk = task ? taskBlocks(child, [...path, 'content', index], depth + 1, itemWriting) : placedBlock(child, [...path, 'content', index], depth + 1, itemWriting)
const walk = task ? taskBlocks(child, [...path, 'content', index], depth + 1, writing) : placedBlock(child, [...path, 'content', index], depth + 1, writing)
if (!walk.ok) return walk
headroom = Math.min(headroom, walk.value.headroom)
const previous = items.at(-1)
@@ -229,15 +205,12 @@ function tryTaskList(node: AdfNode, path: ConvertErrorPath, depth: number, writi
return boundedThen(inners, (spelled) => spelledList(spelled, () => '', bulletDelimiters, headroom) ?? unspellable)
}
// Each item's text, or `undefined` where one, or all of them together, would pass the bound: every item is joined before the list is.
// Each item's text, or `undefined` where one would pass the bound.
function joinedItems(items: readonly Iterable<string>[]): string[] | undefined {
const inners: string[] = []
let length = 0
for (const pieces of items) {
const inner = joinedWithin(pieces)
if (inner === undefined) return undefined
length += inner.length
if (length > longestMarkdown) return undefined
inners.push(inner)
}
return inners
@@ -311,7 +284,7 @@ function emitDirectiveBody(node: AdfNode, model: BlockNodeModel, opener: string,
function tryBlockquote(node: AdfNode, path: ConvertErrorPath, depth: number, writing: Writing): Result<EmittedBlock> | undefined {
if (!holdsOnlyAttributes(node, [])) return undefined
const inner = walkBlocks(nodeContent(node), path, depth + 1, indented(writing, quoteWidth))
const inner = walkBlocks(nodeContent(node), path, depth + 1, writing)
if (!inner.ok) return inner
const text = joinBlocks(inner.value.blocks, 'document')
const alert = text !== undefined && flavourClaims[writing.flavour].alerts && leadingMarker(text, readAlertMarker) !== undefined
@@ -374,33 +347,36 @@ function tryList(node: AdfNode, path: ConvertErrorPath, depth: number, writing:
const walked: WalkedItem[] = []
let headroom = Number.POSITIVE_INFINITY
for (const [offset, item] of items.entries()) {
// Unindented: the list may give way to the directive form, which prefixes nothing, and the forecast must not overcount.
const walk = walkBlocks(nodeContent(item), [...path, 'content', offset], depth + 1, writing)
if (!walk.ok) return walk
const inner = joinBlocks(walk.value.blocks, 'list-item')
if (inner === undefined) return tooLong()
headroom = Math.min(headroom, walk.value.headroom)
walked.push({ node: item, walk: walk.value })
walked.push({ inner, node: item, walk: walk.value })
}
return boundedThen(joinedItems(walked.map((item) => blockPieces(item.walk.blocks, 'list-item'))), (joined) => spelledOrDirectiveList(node, { joined, start, walked }, path, depth, headroom, writing))
const number = ordered ? (offset: number): string => `${start + offset}` : (): string => ''
return spelledOrDirectiveList(node, walked, number, { depth, headroom, path, writing })
}
// The list spelling where every item holds lines a list item spells, else the directive form.
function spelledOrDirectiveList(node: AdfNode, { joined, start, walked }: SpelledItems, path: ConvertErrorPath, depth: number, headroom: number, writing: Writing): Result<EmittedBlock> {
function spelledOrDirectiveList(node: AdfNode, walked: readonly WalkedItem[], number: (offset: number) => string, at: { depth: number; headroom: number; path: ConvertErrorPath; writing: Writing }): Result<EmittedBlock> {
const ordered = node.type === 'orderedList'
// GitHub reads a task marker opening any item's first paragraph as a checkbox, whatever its siblings hold.
const inners = joined.map((inner) => (flavourClaims[writing.flavour].taskMarkers && leadingMarker(inner, readTaskMarker) !== undefined ? `\\${inner}` : inner))
const list = ordered ? spelledList(inners, (offset) => `${start + offset}`, orderedDelimiters, headroom) : spelledList(inners, () => '', bulletDelimiters, headroom)
const escapesMarker = (inner: string): boolean => flavourClaims[at.writing.flavour].taskMarkers && leadingMarker(inner, readTaskMarker) !== undefined
const inners = walked.map(({ inner }) => (escapesMarker(inner) ? `\\${inner}` : inner))
const list = spelledList(inners, number, ordered ? orderedDelimiters : bulletDelimiters, at.headroom)
if (list !== undefined) return list
// The directive form spends a level the walk did not count.
if (headroom < 1) return tooDeep(path)
return emitDirectiveBlock(node, ordered ? blockNodes.orderedList : blockNodes.bulletList, path, depth, () => directiveItems(walked, headroom - 1))
if (at.headroom < 1) return tooDeep(at.path)
return emitDirectiveBlock(node, ordered ? blockNodes.orderedList : blockNodes.bulletList, at.path, at.depth, () => directiveItems(walked, at.headroom - 1))
}
function spelledList(inners: readonly string[], number: (offset: number) => string, [usual, alternate]: Delimiters, headroom: number): Result<EmittedBlock> | undefined {
const pieces = listLines(inners, number, usual)
const alternatePieces = listLines(inners, number, alternate)
if (pieces === undefined || alternatePieces === undefined) return undefined
const spelled = (text: string, alternateText: string): Result<EmittedBlock> => success({ alternateText, headroom, spelling: 'list', text })
return boundedThen(joinedWithin(pieces), (text) => boundedThen(joinedWithin(alternatePieces), (alternateText) => spelled(text, alternateText)))
const withAlternate = (text: string): Result<EmittedBlock> => boundedThen(joinedWithin(alternatePieces), (alternateText) => success({ alternateText, headroom, spelling: 'list', text }))
return boundedThen(joinedWithin(pieces), withAlternate)
}
// `undefined` where an item holds a line no list item spells.
@@ -1,10 +1,10 @@
import type { AdfNode } from '../../adf/document.ts'
import type { BlockNodeModel } from '../../adf/block-nodes.ts'
import { attributeNestingMessage, nodeAttrs, nodeMarks } from '../../adf/document.ts'
import { attributePieces, directiveOpenerPieces, isBareToken, spellJsonAttribute, spellVocabulary } from '../directive-syntax.ts'
import { attributePieces, isBareToken, spellDirectiveOpener, spellJsonAttribute, spellVocabulary } from '../directive-syntax.ts'
import { blockArgument, markValues, marksAttribute } from '../block-directive.ts'
import { failure, success, type ConvertErrorPath, type Result } from '../../result.ts'
import { boundedThen, joinedWithin } from '../length-bound.ts'
import { failure, success, type ConvertErrorPath, type Result } from '../../result.ts'
import { overNested } from '../../json-value.ts'
import { spellEmptyKeys } from '../empty-keys.ts'
import { vocabularyPairs } from '../../adf/attribute-vocabulary.ts'
@@ -23,7 +23,8 @@ export function spellBlockDirectiveOpener(node: AdfNode, model: BlockNodeModel,
if (overNested(values)) return failure('unsupported-nesting-depth', attributeNestingMessage(marksAttribute, node.type), path)
spelledPairs.push([marksAttribute, spellJsonAttribute(values)])
}
const opener = joinedWithin(directiveOpenerPieces(node.type, slot.argument, attributePieces(spelledPairs)))
const head = spellDirectiveOpener(node.type, slot.argument, '')
const opener = joinedWithin(spelledPairs.length === 0 ? [head] : [head, ' ', ...attributePieces(spelledPairs)])
return boundedThen(opener, success)
}
+1 -3
View File
@@ -9,13 +9,12 @@ import { commonMarkLink, linkHref, markSpelling, spellMarkAttributes } from '../
import { escapeUnbalanced, spellDestination, spellLinkTarget } from '../commonmark/link-syntax.ts'
import { failure, success, type ConvertErrorPath, type Result } from '../../result.ts'
import { flavourClaims, highlightDelimiter } from '../portable/conventions.ts'
import { heldTextLength, identicalMark, isSpellableText, nodeAttrs, nodeContent, nodeMarks } from '../../adf/document.ts'
import { holdsNullCharacter, trimTrailingSpace } from '../commonmark/grammar.ts'
import { identicalMark, isSpellableText, nodeAttrs, nodeContent, nodeMarks } from '../../adf/document.ts'
import { inlineNodeModel } from '../../adf/inline-nodes.ts'
import { joinsWhenRead, textBreakSpelling } from '../adjacent-text.ts'
import { largestNesting } from '../../nesting.ts'
import { longestBacktickRun } from '../commonmark/backtick-runs.ts'
import { longestMarkdown, tooLong } from '../length-bound.ts'
import { slotFault, spellInlineDirectiveOpener, spellInlineLeafDirective } from '../directive-syntax.ts'
import { spellInlineNodeAttributes } from './inline-directive-spelling.ts'
import { spellTextDirective } from '../text-directive.ts'
@@ -81,7 +80,6 @@ export function tryImageLine(alt: string | undefined, url: string, link?: LinkDe
}
function emitLine(nodes: readonly AdfNode[], container: LineContainer, path: ConvertErrorPath, flavour: WrittenFlavour): Result<EmittedLine> {
if (heldTextLength(nodes) > longestMarkdown) return tooLong()
const fallbacks: LineFallbacks = { carried: new Set(), flavour, openingLinkAsDirective: false }
// Terminates because takeFallback refuses a pass that took no new fallback.
for (;;) {
+1 -5
View File
@@ -1,6 +1,6 @@
import type { AdfNode } from '../../adf/document.ts'
import type { WrittenFlavour } from '../portable/conventions.ts'
import { boundedThen, joinedWithin, longestMarkdown, separatedBy, tooLong } from '../length-bound.ts'
import { boundedThen, joinedWithin, separatedBy } from '../length-bound.ts'
import { delimiterCells, pipeRowPieces } from '../pipe-table-syntax.ts'
import { holdsOnlyAttributes, nodeContent } from '../../adf/document.ts'
import { success, type ConvertErrorPath, type Result } from '../../result.ts'
@@ -10,16 +10,12 @@ export function tryPipeTable(node: AdfNode, path: ConvertErrorPath, flavour: Wri
const rows = pipeRows(node)
if (rows === undefined) return undefined
const spelled: string[][] = []
// Every cell is spelled before the rows join, so the cells together are held to the bound as they come.
let length = 0
for (const [rowIndex, row] of rows.entries()) {
const cells: string[] = []
for (const [cellIndex, paragraph] of row.entries()) {
const content = nodeContent(paragraph)
const line = content.length === 0 ? '' : tryPipeCell(content, [...path, 'content', rowIndex, 'content', cellIndex, 'content', 0], flavour)
if (line === undefined) return undefined
length += line.length
if (length > longestMarkdown) return tooLong()
cells.push(line)
}
spelled.push(cells)