3
0
mirror of https://github.com/larvit/adf-codec.git synced 2026-11-18 22:25:44 +01:00
Files
adf-codec/src/markdown/emit/line-escaping.ts
T

382 lines
17 KiB
TypeScript

import type { Claims, WrittenFlavour } from '../flavour.ts'
import type { InlineSource, InlineToken } from '../inline-tokens.ts'
import type { LineContainer } from '../line-container.ts'
import { delimiterFlags, isWordCharacter, matchEmphasis, runLength } from '../commonmark/emphasis-matching.ts'
import { delimiterRunToken, highlightFlanking, 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 { opensLinkDefinition } from '../commonmark/link-reference-definitions.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; unspellableRuns: MarkRun[] }
type ScanLine = { position: LinePosition; start: number; text: string }
type EmittedDelimiter = { closes: boolean; offset: number; pair: number; width: number }
type EmittedRun = { canClose: boolean; canOpen: boolean; character: string; delimiters: EmittedDelimiter[]; length: number; start: number }
type Escapings = (index: number) => InlineEscaping | undefined
// Where a segment's first character landed in the output.
type PlacedSegment = { segment: InlineSegment; start: number }
// Which of a run's characters escape: every escapable one, or every one before `end`.
type RunEscapes = { end: number; escapable: false } | { escapable: true }
type EscapeWalk = {
readonly claims: Claims
readonly container: LineContainer
readonly escapings: Escapings
readonly headingCloser: number | undefined
readonly inline: InlineSource
readonly linkClose: number
}
const escapingCodes: readonly ['backslash', 'bracketed', 'bracketed-link-target', 'none'] = ['backslash', 'bracketed', 'bracketed-link-target', 'none']
const followsLinkText = /[([]/
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 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 escaped = escapeClosedRuns(scan, escapings, escapeClaims(scan, escapings, container, claims))
const { output, placed } = backslashed(segments, scan, escaped)
if (container === 'paragraph' && opensLinkDefinition(output)) {
if (segments[0]?.nodes !== undefined) return { line: output, openingLinkAsDirective: true, unspellableRuns: [] }
return { line: `\\${output}`, unspellableRuns: unspellableRuns(placed, output) }
}
return { line: output, unspellableRuns: unspellableRuns(placed, output) }
}
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),
linkClose: lastLinkClose(scan, escapings),
}
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 }, linkClose }: 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':
if (token.image) return isSyntax(escapings(index + 1))
return escaping === 'bracketed' || index < linkClose
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))
}
}
}
// CommonMark reads no escape inside a code span, so a backtick string left beside an escape still closes a span that an earlier bare run of its length opens.
function escapeClosedRuns(scan: string, escapings: Escapings, claimed: Uint8Array): Uint8Array {
const escaped = claimed.slice()
// The lengths of the backtick strings escapes leave: a bare run of one of these lengths would open a span one of them closes, so it is escaped too.
const formed = new Set<number>()
let end = scan.length - 1
while (end >= 0) {
if (scan.charAt(end) !== '`') {
end -= 1
continue
}
let start = end
while (scan.charAt(start - 1) === '`') start -= 1
let segmentEnd = end
for (let index = end; index > start; index -= 1) {
if (claimed[index] !== 1) continue
formed.add(segmentEnd - index + 1)
segmentEnd = index - 1
}
if (segmentEnd !== end || claimed[start] === 1) formed.add(segmentEnd - start + 1)
else if (escapings(start) !== 'none' && formed.has(end - start + 1)) {
escaped.fill(1, start, end + 1)
// Each escaped backtick then stands alone, a string of length one.
formed.add(1)
}
end = start - 1
}
return escaped
}
// One emphasis run, the innermost, or every highlight run the line cannot spell.
function unspellableRuns(placed: readonly PlacedSegment[], output: string): MarkRun[] {
const { nodes, runs } = emittedRuns(placed, output)
const pair = misflanked(runs) ?? unpaired(runs)
const run = pair === undefined ? undefined : nodes[pair]
return run === undefined ? unreadHighlights(placed, output) : [run]
}
// No `==` in text can open or close, and highlights never nest, so a pair reads back where each delimiter flanks.
function unreadHighlights(placed: readonly PlacedSegment[], output: string): MarkRun[] {
const unread: MarkRun[] = []
for (const { segment, start } of placed) {
if (segment.highlight === undefined) continue
const flanking = highlightFlanking(output, start)
const flanks = segment.highlight === 'open' ? flanking.opens : flanking.closes
if (!flanks && unread.at(-1) !== segment.nodes) unread.push(segment.nodes)
}
return unread
}
function misflanked(runs: readonly EmittedRun[]): number | undefined {
for (const run of runs) {
for (const delimiter of run.delimiters) {
if (!(delimiter.closes ? run.canClose : run.canOpen)) return delimiter.pair
}
}
return undefined
}
function unpaired(runs: readonly EmittedRun[]): number | undefined {
const matched = new Set<number>()
for (const pairing of matchEmphasis(runs)) {
const opened = delimiterAt(pairing.opener, false, pairing.openerOffset, pairing.used)
const closed = delimiterAt(pairing.closer, true, pairing.closerOffset, pairing.used)
if (opened !== undefined && closed !== undefined && opened.pair === closed.pair) matched.add(opened.pair)
}
// The last opener left unpaired is the innermost: the smallest carry that changes the line.
let innermost: number | undefined
for (const run of runs) {
for (const delimiter of run.delimiters) {
if (!delimiter.closes && !matched.has(delimiter.pair)) innermost = delimiter.pair
}
}
return innermost
}
function delimiterAt(run: EmittedRun, closes: boolean, offset: number, width: number): EmittedDelimiter | undefined {
return run.delimiters.find((delimiter) => delimiter.closes === closes && delimiter.offset === offset && delimiter.width === width)
}
function emittedRuns(placed: readonly PlacedSegment[], output: string): { nodes: MarkRun[]; runs: EmittedRun[] } {
const runs: EmittedRun[] = []
const nodes: MarkRun[] = []
const open: number[] = []
for (const { segment, start } of placed) {
if (segment.emphasis === undefined) continue
const closes = segment.emphasis === 'close'
const pair = closes ? (open.pop() ?? nodes.length) : nodes.length
if (!closes) {
nodes.push(segment.nodes)
open.push(pair)
}
const width = segment.text.length
const previous = runs[runs.length - 1]
if (previous !== undefined && previous.start + previous.length === start && previous.character === segment.text.charAt(0)) {
previous.delimiters.push({ closes, offset: start - previous.start, pair, width })
previous.length += width
continue
}
runs.push({
canClose: false,
canOpen: false,
character: segment.text.charAt(0),
delimiters: [{ closes, offset: 0, pair, width }],
length: width,
start,
})
}
for (const run of runs) {
const flags = delimiterFlags(run.character, output.charAt(run.start - 1), output.charAt(run.start + run.length))
run.canClose = flags.canClose
run.canOpen = flags.canOpen
}
return { nodes, runs }
}
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) }
}
// A `]` the emitter spelled sits inside a construct that binds before link text does.
function lastLinkClose(scan: string, escapings: Escapings): number {
for (let cursor = scan.length - 1; cursor >= 0; cursor -= 1) {
if (scan.charAt(cursor) !== ']' || isSyntax(escapings(cursor))) continue
if (followsLinkText.test(scan.charAt(cursor + 1))) return cursor
}
return -1
}