4.2: the review's generator, runner and pattern fixes

corpus/round-trip/combinations/directive-link-colon.json

@@ -0,0 +1,107 @@
+{
+  "content": [
+    {
+      "content": [
+        {
+          "marks": [
+            {
+              "type": "underline"
+            },
+            {
+              "attrs": {
+                "href": ":a{"
+              },
+              "type": "link"
+            }
+          ],
+          "text": "x",
+          "type": "text"
+        }
+      ],
+      "type": "paragraph"
+    },
+    {
+      "content": [
+        {
+          "marks": [
+            {
+              "type": "underline"
+            },
+            {
+              "attrs": {
+                "href": "y",
+                "title": ":a{"
+              },
+              "type": "link"
+            }
+          ],
+          "text": "x",
+          "type": "text"
+        }
+      ],
+      "type": "paragraph"
+    },
+    {
+      "content": [
+        {
+          "marks": [
+            {
+              "type": "underline"
+            },
+            {
+              "attrs": {
+                "href": ":a[]{"
+              },
+              "type": "link"
+            }
+          ],
+          "text": "x",
+          "type": "text"
+        }
+      ],
+      "type": "paragraph"
+    },
+    {
+      "content": [
+        {
+          "marks": [
+            {
+              "type": "underline"
+            },
+            {
+              "attrs": {
+                "href": "https://example.com/?q=:emoji{"
+              },
+              "type": "link"
+            }
+          ],
+          "text": "x",
+          "type": "text"
+        }
+      ],
+      "type": "paragraph"
+    },
+    {
+      "content": [
+        {
+          "marks": [
+            {
+              "type": "underline"
+            },
+            {
+              "attrs": {
+                "href": "ab:c{"
+              },
+              "type": "link"
+            }
+          ],
+          "text": "ab:c{",
+          "type": "text"
+        }
+      ],
+      "type": "paragraph"
+    }
+  ],
+  "type": "doc",
+  "version": 1
+}

corpus/round-trip/combinations/directive-link-colon.md

@@ -0,0 +1,9 @@
+:underline[[x](\:a{)]
+
+:underline[[x](y "\:a{")]
+
+:underline[[x](\:a[]{)]
+
+:underline[[x](https://example.com/?q=\:emoji{)]
+
+:underline[[ab\:c{](ab\:c{)]

docker-runner.sh

@@ -7,7 +7,7 @@ node_image=node:24.19.0-alpine3.24
 in_image() {
   local image=$1 entrypoint=$2
   shift 2
-  docker run --rm -u "$(id -u):$(id -g)" -e HOME=/tmp ${in_image_network:+--network "$in_image_network"} -v "$PWD:/app" -w /app --entrypoint "$entrypoint" "$image" "$@"
+  docker run --rm -u "$(id -u):$(id -g)" -e HOME=/tmp ${PROPERTY_RUNS:+-e PROPERTY_RUNS} ${in_image_network:+--network "$in_image_network"} -v "$PWD:/app" -w /app --entrypoint "$entrypoint" "$image" "$@"
 }
 
 with_firefox() {

spec/flavour.md

@@ -48,8 +48,8 @@ normalizes to it through the round-trip.
   title; title in double quotes. A backslash escapes a parenthesis the destination leaves
   unbalanced, and a quote inside the title; a balanced pair stays bare. `<url>` autolink form only
   when the text equals the destination and the destination is a valid CommonMark autolink
-  (absolute URI) — inside an inline directive's `[content]`, one holding no backtick and no
-  unbalanced bracket.
+  (absolute URI) — inside an inline directive's `[content]`, one holding no backtick, no
+  unbalanced bracket and no inline directive opener.
 - Paragraphs on one line — no soft wrapping; a soft line break in input becomes a single space.
 - Entity references in input decode to their characters; output backslash-escapes only where text
   would otherwise parse as syntax, scanning the assembled line rather than each text node: escape
@@ -132,10 +132,10 @@ each a named error naming the spelling to write instead.
 
 **Escaping**: the emitter backslash-escapes whatever literal text would otherwise parse as
 directive syntax — the leading `:` of a would-be directive, `]` inside content, a bracket a link's
-destination and title inside content leave unbalanced and a backtick there that would open a code
-span, a `{` right after a directive's closing `]`, which would otherwise be read as the attributes
-it has none of; outside code spans and code blocks, a backslash before `:` in input yields a
-literal colon.
+destination and title inside content leave unbalanced, a backtick there that would open a code span
+and a `:` there that would open an inline directive, a `{` right after a directive's closing `]`,
+which would otherwise be read as the attributes it has none of; outside code spans and code blocks,
+a backslash before `:` in input yields a literal colon.
 
 **Malformed directives are error results**, named: an unclosed container at end of input, a body
 fence line of the container's length or longer, a bare colon-run line outside any container or

src/adf-property.test.ts

@@ -18,17 +18,21 @@ import { toEditorNormal } from './adf/editor-normal.ts'
 type Positions = { block: AdfNode; inline: AdfNode }
 
 const deepRunsVariable = 'PROPERTY_RUNS'
-const gateRuns = 3000
+const gateRuns = 1600
 const gateSeed = 20260914
+// Bun's test runner stops a test after five seconds unless the test sets its own timeout.
+const propertyTimeout = 600000
 
 const depthIdentifier = fc.createDepthIdentifier()
 const emptyCell: AdfNode = { content: [{ type: 'paragraph' }], type: 'tableCell' }
-const markdownCharacters = fc.constantFrom(...'aZ09 \t\n!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~é\xa0🎉')
+const flatCommonMarkShapeWeight = 4
+const markdownPieces = fc.constantFrom(...'aZ09 \t\n!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~é\xa0🎉', ':a[', ':a{', 'ab:', 'http://')
+const nestingCommonMarkShapeWeight = 21
 const spelledTypes = new Set(['text', ...Object.keys(blockDirectives), ...Object.keys(inlineDirectives), ...Object.keys(markAttributes)])
 
 function textOf(minLength: number): Arbitrary<string> {
   return fc.oneof(
-    { arbitrary: fc.string({ maxLength: 12, minLength, unit: markdownCharacters }), weight: 4 },
+    { arbitrary: fc.string({ maxLength: 12, minLength, unit: markdownPieces }), weight: 4 },
     { arbitrary: fc.string({ maxLength: 6, minLength, unit: 'grapheme' }), weight: 1 },
   )
 }
@@ -37,11 +41,11 @@ const text = textOf(1)
 const unknownType = fc.oneof(fc.stringMatching(/^[a-z][A-Za-z0-9]{0,7}$/), text).filter((type) => !spelledTypes.has(type))
 const numberValue = fc.oneof({ arbitrary: fc.integer({ max: 10, min: -1 }), weight: 3 }, { arbitrary: fc.double({ noDefaultInfinity: true, noNaN: true }), weight: 1 })
 
-// V8's JSON.parse returns a wrong key after parsing a key holding an escaped backslash; Bun is unaffected.
-const keyCharacter = fc
-  .oneof({ arbitrary: markdownCharacters, weight: 4 }, { arbitrary: fc.string({ maxLength: 1, minLength: 1, unit: 'grapheme' }), weight: 1 })
-  .filter((character) => !/[\\"\x00-\x1f]/.test(character))
-const jsonKey = fc.string({ maxLength: 8, unit: keyCharacter })
+// V8's JSON.parse returns a wrong key after parsing a key holding an escaped backslash (https://issues.chromium.org/issues/521080746); Bun is unaffected.
+const keyPiece = fc
+  .oneof({ arbitrary: markdownPieces, weight: 4 }, { arbitrary: fc.string({ maxLength: 1, minLength: 1, unit: 'grapheme' }), weight: 1 })
+  .filter((piece) => !/[\\"\x00-\x1f]/.test(piece))
+const jsonKey = fc.string({ maxLength: 8, unit: keyPiece })
 
 const { jsonValue } = fc.letrec<{ jsonValue: JsonValue }>((tie) => ({
   jsonValue: fc.oneof(
@@ -85,10 +89,18 @@ const marks = fc.uniqueArray(mark, { maxLength: 3, selector: (held) => held.type
 
 const textNode = fc.record({ marks, text }).map((held): AdfNode => ({ ...held, type: 'text' }))
 
+const autolinkTextNode = fc
+  .record({ href: fc.tuple(fc.constantFrom('ab:', 'http://'), textOf(0)).map(([scheme, rest]) => `${scheme}${rest}`), marks })
+  .map(({ href, marks: held }): AdfNode => ({ marks: [...held.filter((outer) => outer.type !== 'link'), { attrs: { href }, type: 'link' }], text: href, type: 'text' }))
+
 const inlineNodes = Object.entries(inlineDirectives).map(([type, directive]) =>
   fc.record({ attrs: attributes(directive.attributes), marks }).map((held): AdfNode => ({ ...held, type })),
 )
 
+function weighted(arbitraries: readonly Arbitrary<AdfNode>[], weight: number): { arbitrary: Arbitrary<AdfNode>; weight: number }[] {
+  return arbitraries.map((arbitrary) => ({ arbitrary, weight }))
+}
+
 const positions = fc.letrec<Positions>((tie) => {
   const blockContent = fc.array(tie('block'), { depthIdentifier, maxLength: 3 })
   const inlineContent = fc.array(tie('inline'), { depthIdentifier, maxLength: 4 })
@@ -117,27 +129,33 @@ const positions = fc.letrec<Positions>((tie) => {
     blockContent.map((content): AdfNode => ({ content, type: 'listItem' })),
     { depthIdentifier, maxLength: 3, minLength: 1 },
   )
-  const commonMarkShapes = [
+  const flatCommonMarkShapes = [
+    fc.record({ content: inlineContent, level: fc.integer({ max: 6, min: 1 }) }).map(({ content, level }): AdfNode => ({ attrs: { level }, content, type: 'heading' })),
+    paragraph,
+    fc.record({ body: fc.array(fc.array(cell('tableCell'), { maxLength: 3 }), { maxLength: 2 }), header: fc.array(cell('tableHeader'), { maxLength: 3, minLength: 1 }) }).map(pipeTable),
+  ]
+  const nestingCommonMarkShapes = [
     blockContent.map((content): AdfNode => ({ content, type: 'blockquote' })),
     listItems.map((content): AdfNode => ({ content, type: 'bulletList' })),
-    fc.record({ content: inlineContent, level: fc.integer({ max: 6, min: 1 }) }).map(({ content, level }): AdfNode => ({ attrs: { level }, content, type: 'heading' })),
     fc
       .record({ content: listItems, order: fc.oneof({ arbitrary: fc.integer({ max: 3, min: 0 }), weight: 4 }, { arbitrary: fc.integer({ max: 999999999, min: 0 }), weight: 1 }) })
       .map(({ content, order }): AdfNode => ({ attrs: { order }, content, type: 'orderedList' })),
-    paragraph,
-    fc.record({ body: fc.array(fc.array(cell('tableCell'), { maxLength: 3 }), { maxLength: 2 }), header: fc.array(cell('tableHeader'), { maxLength: 3, minLength: 1 }) }).map(pipeTable),
   ]
   return {
     block: fc.oneof(
       { depthIdentifier, depthSize: 'small', maxDepth: 4 },
-      { arbitrary: fc.oneof(...leafBlocks), weight: leafBlocks.length * 2 },
+      {
+        arbitrary: fc.oneof(...weighted(leafBlocks, 2), ...weighted(flatCommonMarkShapes, flatCommonMarkShapeWeight)),
+        weight: leafBlocks.length * 2 + flatCommonMarkShapes.length * flatCommonMarkShapeWeight,
+      },
       { arbitrary: fc.oneof(...containerBlocks), weight: containerBlocks.length * 2 },
       { arbitrary: fc.oneof(textNode, ...inlineNodes, unknownNode), weight: misplacedWeight },
-      { arbitrary: fc.oneof(...commonMarkShapes), weight: blockNodes.length * 2 + misplacedWeight },
+      { arbitrary: fc.oneof(...nestingCommonMarkShapes), weight: nestingCommonMarkShapes.length * nestingCommonMarkShapeWeight },
     ),
     inline: fc.oneof(
       { depthIdentifier, depthSize: 'small', maxDepth: 4 },
       { arbitrary: textNode, weight: 12 },
+      { arbitrary: autolinkTextNode, weight: 2 },
       { arbitrary: fc.oneof(...inlineNodes), weight: 7 },
       { arbitrary: fc.oneof(...blockNodes.map((entry) => entry.node), unknownNode), weight: 2 },
     ),
@@ -149,12 +167,11 @@ const adfDocument = fc.array(positions.block, { depthIdentifier, maxLength: 4, m
 function runParameters(): { numRuns: number; seed?: number } {
   const deepRuns = env[deepRunsVariable]
   if (deepRuns === undefined) return { numRuns: gateRuns, seed: gateSeed }
-  const numRuns = Number(deepRuns)
-  assert.ok(Number.isSafeInteger(numRuns) && numRuns > 0, `${deepRunsVariable} holds a whole number of runs: found ${deepRuns}`)
-  return { numRuns }
+  assert.ok(/^[1-9]\d*$/.test(deepRuns), `${deepRunsVariable} is a run count in digits, such as ${deepRunsVariable}=10000: found ${JSON.stringify(deepRuns)}`)
+  return { numRuns: Number(deepRuns) }
 }
 
-test('a generated document refuses to emit, or its markdown reads back to it', () => {
+test('a generated document refuses to emit, or its markdown reads back to it', { timeout: propertyTimeout }, () => {
   fc.assert(
     fc.property(adfDocument, (document) => {
       const emitted = adfToMarkdown(document)

src/markdown/commonmark-grammar.ts

@@ -51,6 +51,7 @@ const htmlBlockConditions: HtmlBlockCondition[] = [
 ]
 const asciiPunctuation = /[!"#$%&'()*+,\-./:;<=>?@[\\\]^_`{|}~]/
 const atxHeadingOpener = /^(#{1,6})(?:[ \t]|$)/
+const blankLine = /^[ \t]*$/
 const codeFenceOpener = /^(`{3,}|~{3,})/
 const directiveClaim = /^:{2,}(?:[A-Za-z0-9]|[ \t]*$)/
 const pipeClaim = /^\|/
@@ -168,7 +169,7 @@ export function isAutolink(text: string): boolean {
 }
 
 export function isBlankLine(line: string): boolean {
-  return /^[ \t]*$/.test(line)
+  return blankLine.test(line)
 }
 
 export function isThematicBreak(line: string): boolean {

src/markdown/directive-syntax.ts

@@ -56,6 +56,11 @@ export function attributeValue(text: string, kind: AttributeKind): AttributeRead
   return overNested(parsed) ? { refusal: 'nesting' } : { value: { kind, value: parsed } }
 }
 
+export function holdsInlineDirectiveOpener(text: string): boolean {
+  for (let index = text.indexOf(':'); index !== -1; index = text.indexOf(':', index + 1)) if (opensInlineDirective(text, index)) return true
+  return false
+}
+
 export function isBareToken(text: string): boolean {
   return bareToken.test(text)
 }

src/markdown/emit/inline-line.ts

@@ -6,13 +6,13 @@ import { claimsLine, holdsNullCharacter, isAutolink } from '../commonmark-gramma
 import { escapeUnbalanced, spellDestination, spellLinkTarget } from '../link-syntax.ts'
 import { failure, faulted, success, type ConvertErrorPath, type Result } from '../../result.ts'
 import { holdsEntityReference } from '../entity-references.ts'
+import { holdsInlineDirectiveOpener, slotLineEndingFault, spellLeafDirective } from '../directive-syntax.ts'
 import { inlineDirective } from '../../adf/inline-directives.ts'
 import { largestNesting } from '../../nesting.ts'
 import { longestBacktickRun } from '../backtick-runs.ts'
 import { markSpelling, spellMarkAttributes } from '../mark-spellings.ts'
 import { nodeAttrs, nodeContent, nodeMarks } from '../../adf/document.ts'
 import { sameMark } from '../../adf/editor-normal.ts'
-import { slotLineEndingFault, spellLeafDirective } from '../directive-syntax.ts'
 import { spellInlineNodeAttributes } from './inline-directive-spelling.ts'
 import { spellTextDirective } from '../text-directive.ts'
 
@@ -284,7 +284,7 @@ function emitLink(nodes: readonly AdfNode[], mark: AdfMark, depth: number, range
   if (typeof href !== 'string') return success({ carry: range })
   const node = nodes[0]
   const bare = nodes.length === 1 && node !== undefined && node.type === 'text' && node.text === href && nodeMarks(node).length === depth + 1
-  const autolinkHolds = !context.bracketed || (!href.includes('`') && escapeUnbalanced(href, '[', ']') === href)
+  const autolinkHolds = !context.bracketed || (!href.includes('`') && !holdsInlineDirectiveOpener(href) && escapeUnbalanced(href, '[', ']') === href)
   if (bare && autolinkHolds && title === undefined && isAutolink(href) && !holdsEntityReference(href)) return success({ segments: [syntax(`<${href}>`)] })
   const target = spellLinkTarget(href, typeof title === 'string' ? title : undefined, path)
   if (!target.ok) return target

src/markdown/emit/line-escaping.ts

@@ -81,7 +81,8 @@ function escape(segments: readonly InlineSegment[], container: LineContainer): A
         (claimsLineStart(line, index, container) ||
           mergesWithSyntax(scan, escapings, index) ||
           opensConstruct(scan, linkClose, index, escaping === 'bracketed', container, escaped))) ||
-      (escaping === 'bracketed-link-target' && scan.charAt(index) === '`' && opensCodeSpan(scan, index, escaped))
+      (escaping === 'bracketed-link-target' &&
+        ((scan.charAt(index) === '`' && opensCodeSpan(scan, index, escaped)) || (scan.charAt(index) === ':' && opensInlineDirective(scan, index))))
     ) {
       output += '\\'
       escaped.add(index)