Ship htmlToAdf: read back exactly the HTML adfToHtml writes, a carry element from its data-adf alone, any other HTML refused

src/html/parse/source.ts

@@ -0,0 +1,55 @@
+import type { ConvertErrorCode, ConvertErrorPath, ParseError, Result, SourcePosition } from '../../result.ts'
+import { unescapedValue } from '../escaping.ts'
+
+// A node's place among its parent's content, the document's own content where `parent` is undefined; a path is built only for a refusal.
+export type Place = { index: number; parent: Place | undefined }
+
+// A start tag as `adfToHtml` writes it, its attributes' values unescaped.
+export type StartTag = { attributes: (readonly [string, string])[]; end: number; name: string; start: number }
+
+const attribute = / ([a-z][a-z0-9-]*)="([^"]*)"/g
+const lineEnding = /\r\n?|\n/g
+const startTag = /<([a-z][a-z0-9]*)((?: [a-z][a-z0-9-]*="[^"]*")*)>/y
+
+// `undefined` where no start tag stands at `index`, or one of its values is not escaped as the dialect escapes it.
+export function readStartTag(html: string, index: number): StartTag | undefined {
+  startTag.lastIndex = index
+  const match = startTag.exec(html)
+  if (match === null) return undefined
+  const attributes: (readonly [string, string])[] = []
+  for (const [, name = '', spelled = ''] of (match[2] ?? '').matchAll(attribute)) {
+    const value = unescapedValue(spelled)
+    if (value === undefined) return undefined
+    attributes.push([name, value])
+  }
+  return { attributes, end: index + match[0].length, name: match[1] ?? '', start: index }
+}
+
+// What stands at `index`, for a refusal's message.
+export function foundAt(html: string, index: number): string {
+  if (index >= html.length) return 'found the end of the HTML'
+  const found = html.slice(index, index + 24)
+  return `found ${JSON.stringify(found)}${index + found.length < html.length ? '…' : ''}`
+}
+
+// At the start of the line `index` stands on.
+export function refused<T>(code: ConvertErrorCode, message: string, html: string, index: number, place: Place | undefined): Result<T, ParseError> {
+  return { error: { code, message, path: pathOf(place), position: lineStart(html, index) }, ok: false }
+}
+
+// A line ends at a line feed, a carriage return or both, as an HTML parser reads it.
+function lineStart(html: string, index: number): SourcePosition {
+  let line = 1
+  let offset = 0
+  for (const ending of html.slice(0, index).matchAll(lineEnding)) {
+    line += 1
+    offset = ending.index + ending[0].length
+  }
+  return { line, offset }
+}
+
+function pathOf(place: Place | undefined): ConvertErrorPath {
+  const steps: (number | string)[] = []
+  for (let at = place; at !== undefined; at = at.parent) steps.push(at.index, 'content')
+  return steps.reverse()
+}