Fix roundtripping of attention by encoding surroundings

Related-to: syntax-tree/unist#60.

Author: wooorm

lib/handle/emphasis.js

@@ -4,13 +4,11 @@
  */
 
 import {checkEmphasis} from '../util/check-emphasis.js'
+import {encodeCharacterReference} from '../util/encode-character-reference.js'
+import {encodeInfo} from '../util/encode-info.js'
 
 emphasis.peek = emphasisPeek
 
-// To do: there are cases where emphasis cannot “form” depending on the
-// previous or next character of sequences.
-// There’s no way around that though, except for injecting zero-width stuff.
-// Do we need to safeguard against that?
 /**
  * @param {Emphasis} node
  * @param {Parents | undefined} _
@@ -22,17 +20,42 @@ export function emphasis(node, _, state, info) {
   const marker = checkEmphasis(state)
   const exit = state.enter('emphasis')
   const tracker = state.createTracker(info)
-  let value = tracker.move(marker)
-  value += tracker.move(
+  const before = tracker.move(marker)
+
+  let between = tracker.move(
     state.containerPhrasing(node, {
-      before: value,
       after: marker,
+      before,
       ...tracker.current()
     })
   )
-  value += tracker.move(marker)
+  const betweenHead = between.charCodeAt(0)
+  const open = encodeInfo(
+    info.before.charCodeAt(info.before.length - 1),
+    betweenHead,
+    marker
+  )
+
+  if (open.inside) {
+    between = encodeCharacterReference(betweenHead) + between.slice(1)
+  }
+
+  const betweenTail = between.charCodeAt(between.length - 1)
+  const close = encodeInfo(info.after.charCodeAt(0), betweenTail, marker)
+
+  if (close.inside) {
+    between = between.slice(0, -1) + encodeCharacterReference(betweenTail)
+  }
+
+  const after = tracker.move(marker)
+
   exit()
-  return value
+
+  state.attentionEncodeSurroundingInfo = {
+    after: close.outside,
+    before: open.outside
+  }
+  return before + between + after
 }
 
 /**

lib/handle/heading.js

@@ -3,6 +3,7 @@
  * @import {Heading, Parents} from 'mdast'
  */
 
+import {encodeCharacterReference} from '../util/encode-character-reference.js'
 import {formatHeadingAsSetext} from '../util/format-heading-as-setext.js'
 
 /**
@@ -58,11 +59,7 @@ export function heading(node, _, state, info) {
 
   if (/^[\t ]/.test(value)) {
     // To do: what effect has the character reference on tracking?
-    value =
-      '&#x' +
-      value.charCodeAt(0).toString(16).toUpperCase() +
-      ';' +
-      value.slice(1)
+    value = encodeCharacterReference(value.charCodeAt(0)) + value.slice(1)
   }
 
   value = value ? sequence + ' ' + value : sequence

lib/handle/strong.js

@@ -4,13 +4,11 @@
  */
 
 import {checkStrong} from '../util/check-strong.js'
+import {encodeCharacterReference} from '../util/encode-character-reference.js'
+import {encodeInfo} from '../util/encode-info.js'
 
 strong.peek = strongPeek
 
-// To do: there are cases where emphasis cannot “form” depending on the
-// previous or next character of sequences.
-// There’s no way around that though, except for injecting zero-width stuff.
-// Do we need to safeguard against that?
 /**
  * @param {Strong} node
  * @param {Parents | undefined} _
@@ -22,17 +20,42 @@ export function strong(node, _, state, info) {
   const marker = checkStrong(state)
   const exit = state.enter('strong')
   const tracker = state.createTracker(info)
-  let value = tracker.move(marker + marker)
-  value += tracker.move(
+  const before = tracker.move(marker + marker)
+
+  let between = tracker.move(
     state.containerPhrasing(node, {
-      before: value,
       after: marker,
+      before,
       ...tracker.current()
     })
   )
-  value += tracker.move(marker + marker)
+  const betweenHead = between.charCodeAt(0)
+  const open = encodeInfo(
+    info.before.charCodeAt(info.before.length - 1),
+    betweenHead,
+    marker
+  )
+
+  if (open.inside) {
+    between = encodeCharacterReference(betweenHead) + between.slice(1)
+  }
+
+  const betweenTail = between.charCodeAt(between.length - 1)
+  const close = encodeInfo(info.after.charCodeAt(0), betweenTail, marker)
+
+  if (close.inside) {
+    between = between.slice(0, -1) + encodeCharacterReference(betweenTail)
+  }
+
+  const after = tracker.move(marker + marker)
+
   exit()
-  return value
+
+  state.attentionEncodeSurroundingInfo = {
+    after: close.outside,
+    before: open.outside
+  }
+  return before + between + after
 }
 
 /**

lib/index.js

@@ -22,35 +22,36 @@ import {track} from './util/track.js'
  *
  * @param {Nodes} tree
  *   Tree to serialize.
- * @param {Options} [options]
+ * @param {Options | null | undefined} [options]
  *   Configuration (optional).
  * @returns {string}
  *   Serialized markdown representing `tree`.
  */
-export function toMarkdown(tree, options = {}) {
+export function toMarkdown(tree, options) {
+  const settings = options || {}
   /** @type {State} */
   const state = {
-    enter,
-    indentLines,
     associationId: association,
     containerPhrasing: containerPhrasingBound,
     containerFlow: containerFlowBound,
     createTracker: track,
     compilePattern,
-    safe: safeBound,
-    stack: [],
-    unsafe: [...unsafe],
-    join: [...join],
+    enter,
     // @ts-expect-error: GFM / frontmatter are typed in `mdast` but not defined
     // here.
     handlers: {...handlers},
-    options: {},
-    indexStack: [],
     // @ts-expect-error: add `handle` in a second.
-    handle: undefined
+    handle: undefined,
+    indentLines,
+    indexStack: [],
+    join: [...join],
+    options: {},
+    safe: safeBound,
+    stack: [],
+    unsafe: [...unsafe]
   }
 
-  configure(state, options)
+  configure(state, settings)
 
   if (state.options.tightDefinitions) {
     state.join.push(joinDefinition)

lib/types.d.ts

@@ -392,6 +392,38 @@ export type ContainerPhrasing = (parent: PhrasingParents, info: Info) => string
  */
 export type CreateTracker = (info: TrackFields) => Tracker
 
+/**
+ * Whether to encode things — with fields representing the surrounding of a
+ * whole.
+ */
+export interface EncodeSurrounding {
+  /**
+   * Whether to encode after.
+   */
+  after: boolean
+
+  /**
+   * Whether to encode before.
+   */
+  before: boolean
+}
+
+/**
+ * Whether to encode things — with fields representing the relationship to a
+ * whole.
+ */
+export interface EncodeSides {
+  /**
+   * Whether to encode inside.
+   */
+  inside: boolean
+
+  /**
+   * Whether to encode before.
+   */
+  outside: boolean
+}
+
 /**
  * Enter something.
  *
@@ -754,6 +786,18 @@ export interface State {
    * Get an identifier from an association to match it to others.
    */
   associationId: AssociationId
+  /**
+   * Info on whether to encode the surrounding of *attention*.
+   *
+   * Whether attention (emphasis, strong, strikethrough) forms
+   * depends on the characters inside and outside them.
+   * The characters inside can be handled by *attention* itself.
+   * However the outside characters are already handled.
+   * Or handled afterwards.
+   * This field can be used to signal from *attention* that some parent
+   * function (practically `containerPhrasing`) has to handle the surrounding.
+   */
+  attentionEncodeSurroundingInfo: EncodeSurrounding | undefined
   /**
    * List marker currently in use.
    */

lib/util/container-phrasing.js

@@ -3,6 +3,8 @@
  * @import {PhrasingParents} from '../types.js'
  */
 
+import {encodeCharacterReference} from './encode-character-reference.js'
+
 /**
  * Serialize the children of a parent that contains phrasing children.
  *
@@ -24,6 +26,8 @@ export function containerPhrasing(parent, state, info) {
   const results = []
   let index = -1
   let before = info.before
+  /** @type {string | undefined} */
+  let encodeAfter
 
   indexStack.push(-1)
   let tracker = state.createTracker(info)
@@ -75,17 +79,43 @@ export function containerPhrasing(parent, state, info) {
       tracker.move(results.join(''))
     }
 
-    results.push(
-      tracker.move(
-        state.handle(child, parent, state, {
-          ...tracker.current(),
-          before,
-          after
-        })
-      )
-    )
+    let value = state.handle(child, parent, state, {
+      ...tracker.current(),
+      after,
+      before
+    })
+
+    // If we had to encode the first character after the previous node and it’s
+    // still the same character,
+    // encode it.
+    if (encodeAfter && encodeAfter === value.slice(0, 1)) {
+      value =
+        encodeCharacterReference(encodeAfter.charCodeAt(0)) + value.slice(1)
+    }
+
+    const encodingInfo = state.attentionEncodeSurroundingInfo
+    state.attentionEncodeSurroundingInfo = undefined
+    encodeAfter = undefined
+
+    // If we have to encode the first character before the current node and
+    // it’s still the same character,
+    // encode it.
+    if (encodingInfo) {
+      if (
+        encodingInfo.before &&
+        before === results[results.length - 1].slice(-1)
+      ) {
+        results[results.length - 1] =
+          results[results.length - 1].slice(0, -1) +
+          encodeCharacterReference(before.charCodeAt(0))
+      }
+
+      if (encodingInfo.after) encodeAfter = after
+    }
 
-    before = results[results.length - 1].slice(-1)
+    tracker.move(value)
+    results.push(value)
+    before = value.slice(-1)
   }
 
   indexStack.pop()

lib/util/encode-character-reference.js

@@ -0,0 +1,11 @@
+/**
+ * Encode a code point as a character reference.
+ *
+ * @param {number} code
+ *   Code point to encode.
+ * @returns {string}
+ *   Encoded character reference.
+ */
+export function encodeCharacterReference(code) {
+  return '&#x' + code.toString(16).toUpperCase() + ';'
+}