import type { Claims, WrittenFlavour } from '../flavour.ts' import type { InlineReading } from '../inline-content.ts' import type { InlineSource, InlineToken } from '../inline-tokens.ts' import type { LineContainer } from '../line-container.ts' import { delimiterRunToken, inlineSource, readInlineToken } from '../inline-tokens.ts' import { escapesLineClaim, type LinePosition } from '../commonmark/grammar.ts' import { flavourClaims } from '../flavour.ts' import { isBareDelimiterRow } from '../pipe-table-syntax.ts' import { isWordCharacter, runLength } from '../commonmark/emphasis-matching.ts' import { opensLinkDefinition } from '../commonmark/link-reference-definitions.ts' import { readLineBack } from '../inline-content.ts' export type DelimiterRole = 'close' | 'open' // A segment's kind: `backslash` text, `bracketed` text inside `[…]` (link text, alt, a directive's content), `bracketed-link-target` syntax: a link target inside `[…]`, `none` syntax written as is. export type InlineEscaping = (typeof escapingCodes)[number] export type NodeRange = { first: number; last: number } // `depth` is the index into each node's marks array that the run spells. export type MarkRun = NodeRange & { depth: number } export type InlineSegment = | { emphasis: DelimiterRole; escaping: 'none'; highlight?: undefined; nodes: MarkRun; text: string } | { emphasis?: undefined; escaping: 'none'; highlight: DelimiterRole; nodes: MarkRun; text: string } | { emphasis?: undefined; escaping: 'none'; highlight?: undefined; nodes: NodeRange; text: string } | { emphasis?: undefined; escaping: InlineEscaping; highlight?: undefined; nodes?: undefined; text: string } export type AssembledLine = { line: string; openingLinkAsDirective?: true; unspellableRun: MarkRun | undefined } type ScanLine = { position: LinePosition; start: number; text: string } type Escapings = (index: number) => InlineEscaping | undefined // Where a segment's first character landed in the output. type PlacedSegment = { segment: InlineSegment; start: number } // The escaped line once reading it back asks for no further escape. type ReadBack = { output: string; placed: PlacedSegment[]; reading: InlineReading } // Which of a run's characters escape: every escapable one, or every one before `end`. type RunEscapes = { end: number; escapable: false } | { escapable: true } // Which text characters escape wherever they stand: one of them opened a construct when the line was read back. type TextEscapes = { backticks: boolean; brackets: boolean } type EscapeWalk = { readonly claims: Claims readonly container: LineContainer readonly escapings: Escapings readonly headingCloser: number | undefined readonly inline: InlineSource } const escapingCodes: readonly ['backslash', 'bracketed', 'bracketed-link-target', 'none'] = ['backslash', 'bracketed', 'bracketed-link-target', 'none'] const runCharacters = '*_`~' export function assembleInlineLine(segments: readonly InlineSegment[], container: LineContainer, flavour: WrittenFlavour): AssembledLine { return escape(resolveEmphasis(segments), container, flavourClaims[flavour]) } function resolveEmphasis(segments: readonly InlineSegment[]): InlineSegment[] { const resolved = segments.map((segment) => ({ ...segment })) // Offsets index the pre-swap text: every emphasis spelling this swaps between is one character wide. const scan = resolved.map((segment) => segment.text).join('') const offsets: number[] = [] let offset = 0 for (const segment of resolved) { offsets.push(offset) offset += segment.text.length } const open: number[] = [] for (let index = 0; index < resolved.length; index += 1) { const segment = resolved[index] if (segment === undefined) continue if (segment.emphasis === 'open') open.push(index) if (segment.emphasis !== 'close') continue const openerIndex = open.pop() const opener = openerIndex === undefined ? undefined : resolved[openerIndex] if (openerIndex === undefined || opener === undefined) continue const openOffset = offsets[openerIndex] ?? 0 const closeOffset = offsets[index] ?? 0 if (opener.text !== '_') continue if (!isWordCharacter(scan.charAt(openOffset - 1)) && !isWordCharacter(scan.charAt(closeOffset + 1))) continue opener.text = '*' segment.text = '*' } return resolved } function escape(segments: readonly InlineSegment[], container: LineContainer, claims: Claims): AssembledLine { const { output, placed, reading } = readBack(segments, container, claims) return { ...guardLinkDefinition(output, placed, container), unspellableRun: unspellableRun(placed, reading) } } function readBack(segments: readonly InlineSegment[], container: LineContainer, claims: Claims): ReadBack { const scan = segments.map((segment) => segment.text).join('') // One byte a character, never an array element or Set entry: a line may run to hundreds of millions of characters. const codes = new Uint8Array(scan.length) let start = 0 for (const segment of segments) { codes.fill(escapingCodes.indexOf(segment.escaping), start, start + segment.text.length) start += segment.text.length } const escapings: Escapings = (index) => { const code = codes[index] return code === undefined ? undefined : escapingCodes[code] } const claimed = escapeClaims(scan, escapings, container, claims) let escapes: TextEscapes = { backticks: false, brackets: false } // At most three passes: each pass that doesn't return turns on at least one more of the two escape kinds. for (;;) { const { output, placed } = backslashed(segments, scan, withTextEscapes(scan, escapings, claimed, escapes)) const { faulted, reading } = readLineBack(output, container, claims) const shown = textOpeners(placed, output.length, reading) // A text backtick in a directive's slot can open a code span past the slot's `]`: the directive faults before the reader records that span. const opened = faulted && !shown.backticks && !shown.brackets ? { backticks: true, brackets: true } : shown const next = { backticks: escapes.backticks || opened.backticks, brackets: escapes.brackets || opened.brackets } if (next.backticks === escapes.backticks && next.brackets === escapes.brackets) return { output, placed, reading } escapes = next } } // spec/flavour.md, Canonical form. function guardLinkDefinition(output: string, placed: readonly PlacedSegment[], container: LineContainer): { line: string; openingLinkAsDirective?: true } { if (container !== 'paragraph' || !opensLinkDefinition(output)) return { line: output } return opensWithLink(placed) ? { line: output, openingLinkAsDirective: true } : { line: `\\${output}` } } // Only the emitter's link opener is a `[` segment spelling nodes. function opensWithLink([first]: readonly PlacedSegment[]): boolean { return first?.segment.nodes !== undefined && first.segment.text === '[' } function withTextEscapes(scan: string, escapings: Escapings, claimed: Uint8Array, { backticks, brackets }: TextEscapes): Uint8Array { if (!backticks && !brackets) return claimed const escaped = claimed.slice() for (let index = 0; index < scan.length; index += 1) { const character = scan.charAt(index) if (((backticks && character === '`') || (brackets && character === '[')) && isEscapable(escapings(index))) escaped[index] = 1 } return escaped } // A construct the reader opened at a text character is one the line does not mean. function textOpeners(placed: readonly PlacedSegment[], length: number, reading: InlineReading): TextEscapes { const text = new Uint8Array(length) for (const [index, { segment, start }] of placed.entries()) { if (isEscapable(segment.escaping)) text.fill(1, start, placed[index + 1]?.start ?? length) } return { backticks: reading.codeSpans.some((at) => text[at] === 1), brackets: reading.links.some((at) => text[at] === 1) } } function backslashed(segments: readonly InlineSegment[], scan: string, escaped: Uint8Array): { output: string; placed: PlacedSegment[] } { // The output joins 4096 pieces at a time: an array element per escape would cost more than the character it escapes. const chunks: string[] = [] let pieces: string[] = [] let from = 0 for (let index = escaped.indexOf(1); index !== -1; index = escaped.indexOf(1, index + 1)) { pieces.push(scan.slice(from, index), '\\') from = index if (pieces.length < 4096) continue chunks.push(pieces.join('')) pieces = [] } pieces.push(scan.slice(from)) chunks.push(pieces.join('')) const placed: PlacedSegment[] = [] let escapes = 0 let next = escaped.indexOf(1) let start = 0 for (const segment of segments) { while (next !== -1 && next <= start) { escapes += 1 next = escaped.indexOf(1, next + 1) } placed.push({ segment, start: start + escapes }) start += segment.text.length } return { output: chunks.join(''), placed } } function escapeClaims(scan: string, escapings: Escapings, container: LineContainer, claims: Claims): Uint8Array { const walk: EscapeWalk = { claims, container, escapings, headingCloser: container === 'heading' ? closingHashes(scan) : undefined, inline: inlineSource(scan), } const escaped = new Uint8Array(scan.length) let line = scanLine(scan, 0) let index = 0 while (index < scan.length) { while (index > line.start + line.text.length) line = scanLine(scan, line.start + line.text.length + 1) if (runCharacters.includes(scan.charAt(index))) { const end = index + runLength(scan, index) const run = runEscapes(walk, index, end, line) if (!run.escapable) escaped.fill(1, index, run.end) else for (let at = index; at < end; at += 1) if (isEscapable(escapings(at))) escaped[at] = 1 index = end continue } const token = readInlineToken(walk.inline, index, claims) const claimed = claimsCharacter(walk, index, token, line) if (claimed) escaped[index] = 1 // The reader takes a `==` whole, so its second `=` starts nothing unless the first is escaped. index += !claimed && token.kind === 'highlight' ? token.width : 1 } return escaped } // A text character beside one of the emitter's delimiters would lengthen that delimiter's run, so every text character in such a run escapes. function runEscapes(walk: EscapeWalk, start: number, end: number, line: ScanLine): RunEscapes { const { escapings, inline: { text: scan } } = walk if (runHolds(escapings, start, end, isSyntax) && runHolds(escapings, start, end, isEscapable)) return { escapable: true } let index = start // A backtick run escapes whole: a bare rest would be a shorter backtick string, which can close a span an earlier run opens. while (index < end && ((index > start && scan.charAt(index) === '`') || claimsRunRest(walk, index, end, line))) index += 1 return { end: index, escapable: false } } function runHolds(escapings: Escapings, start: number, end: number, kind: (escaping: InlineEscaping | undefined) => boolean): boolean { for (let index = start; index < end; index += 1) if (kind(escapings(index))) return true return false } function claimsRunRest({ claims, container, escapings, inline }: EscapeWalk, index: number, end: number, line: ScanLine): boolean { const scan = inline.text const escaping = escapings(index) if (escaping === 'bracketed-link-target') return readInlineToken(inline, index, claims).kind === 'code-span' if (!isEscapable(escaping)) return false if (claimsLineStart(line, index, container)) return true const token = scan.charAt(index) === '`' ? readInlineToken(inline, index, claims) : delimiterRunToken(scan, index, end - index, claims) return token.kind !== 'text' } function claimsCharacter({ container, escapings, headingCloser, inline: { text: scan } }: EscapeWalk, index: number, token: InlineToken, line: ScanLine): boolean { const escaping = escapings(index) if (escaping === 'bracketed-link-target') return token.kind === 'directive' if (!isEscapable(escaping)) return false if (index === headingCloser || claimsLineStart(line, index, container)) return true switch (token.kind) { case 'autolink': case 'code-span': case 'delimiter-run': case 'directive': case 'entity': case 'escape': case 'hard-break': case 'html': return true case 'bracket': return token.image ? isSyntax(escapings(index + 1)) : escaping === 'bracketed' case 'bracket-close': return escaping === 'bracketed' case 'highlight': return token.opens || token.closes // A backslash before a line ending reads as a hard break, so no line ending escapes. case 'line-ending': case 'text': { const character = scan.charAt(index) if (character === '|') return container === 'table-cell' return character === '{' && scan.charAt(index - 1) === ']' && isSyntax(escapings(index - 1)) } } } // Of the runs the line does not read back as written, the first emphasis run to close, else the first highlight run: one misread pair can re-pair the delimiters after it. function unspellableRun(placed: readonly PlacedSegment[], reading: InlineReading): MarkRun | undefined { const openers: { nodes: MarkRun; start: number }[] = [] let highlight: { nodes: MarkRun; start: number } | undefined let unreadHighlight: MarkRun | undefined for (const { segment, start } of placed) { if (segment.emphasis === 'open') openers.push({ nodes: segment.nodes, start }) if (segment.highlight === 'open') highlight = { nodes: segment.nodes, start } if (segment.emphasis === 'close') { const opener = openers.pop() if (opener !== undefined && !readAsWritten(reading, opener.start, start, segment.text.length)) return opener.nodes } if (segment.highlight === 'close' && highlight !== undefined && reading.highlights.get(highlight.start) !== start) unreadHighlight ??= highlight.nodes } return unreadHighlight } function readAsWritten(reading: InlineReading, opener: number, closer: number, width: number): boolean { const read = reading.emphasis.get(opener) return read?.closer === closer && read.width === width } function isEscapable(escaping: InlineEscaping | undefined): boolean { return escaping === 'backslash' || escaping === 'bracketed' } export function isSyntax(escaping: InlineEscaping | undefined): boolean { return escaping === 'none' || escaping === 'bracketed-link-target' } // A hard break is the one spelling that puts a delimiter row under a row of its own, so only a later line claims. function claimsLineStart(line: ScanLine, index: number, container: LineContainer): boolean { if (container !== 'paragraph') return false if (index === line.start && line.position === 'later' && isBareDelimiterRow(line.text)) return true return escapesLineClaim(line.text, index - line.start, line.position) } // The start of the closing sequence an ATX heading would read at the text's end. function closingHashes(scan: string): number | undefined { let start = scan.length while (scan.charAt(start - 1) === '#') start -= 1 if (start === scan.length) return undefined return start === 0 || /[ \t]/.test(scan.charAt(start - 1)) ? start : undefined } function scanLine(scan: string, start: number): ScanLine { const end = scan.indexOf('\n', start) return { position: start === 0 ? 'first' : 'later', start, text: scan.slice(start, end === -1 ? undefined : end) } }