3
0
mirror of https://github.com/larvit/adf-codec.git synced 2026-11-19 06:35:44 +01:00

Answer stability round 1: 0 🔴, 5 🟡 (0 misread); derive the entity tables from one map, drop a dead branch, pin two refusals' places

This commit is contained in:
2026-10-31 02:13:10 +01:00
parent 0579c1d4ab
commit 0ee700c04d
5 changed files with 25 additions and 27 deletions
+11 -14
View File
@@ -1,14 +1,5 @@
export type Spelling = 'attribute' | 'text'
const escapable = /[&<>"]/g
const escapes: ReadonlyMap<string, string> = new Map([
['"', '&quot;'],
['&', '&amp;'],
['<', '&lt;'],
['>', '&gt;'],
])
const writtenEntities = [...escapes.values()]
const entity = /&(?:amp|gt|lt|nbsp|quot);/g
const entityValues: ReadonlyMap<string, string> = new Map([
['&amp;', '&'],
['&gt;', '>'],
@@ -16,16 +7,22 @@ const entityValues: ReadonlyMap<string, string> = new Map([
['&nbsp;', '\u00a0'],
['&quot;', '"'],
])
const entityNames = [...entityValues.keys()].map((spelled) => spelled.slice(1, -1)).join('|')
const entity = new RegExp(`&(?:${entityNames});`, 'g')
// `adfToHtml` writes every character of `entityValues` as its entity but the no-break space.
const escapes: ReadonlyMap<string, string> = new Map([...entityValues].filter(([, character]) => character !== '\u00a0').map(([spelled, character]): [string, string] => [character, spelled]))
const escapable = new RegExp(`[${[...escapes.keys()].join('')}]`, 'g')
const writtenEntities = [...escapes.values()]
// What HTML text and attribute values cannot hold (WHATWG HTML §13.1.3): any control but a tab, line feed or form feed, a carriage return among them, since a parser reads it as a line feed; a noncharacter; and a lone surrogate, which UTF-8 cannot encode.
const unwritable = /(?![\t\n\f ])[\p{Cc}\p{Cs}\p{Noncharacter_Code_Point}]/u
const unwritables = new RegExp(unwritable.source, 'gu')
const strayAmpersand = '&(?!(?:amp|gt|lt|nbsp|quot);)'
// What reads wrongly in a value: `&` outside an entity, a character HTML cannot hold, and in text a `<` or `>`. An attribute value may hold `<` and `>` raw, as older browsers write it, and text may hold `"`.
const strayAmpersand = `&(?!(?:${entityNames});)`
// An attribute value may hold a raw `<` or `>`, as older browsers write them; text may hold a raw `"`.
const misspellings: Readonly<Record<Spelling, RegExp>> = {
attribute: new RegExp(`${strayAmpersand}|${unwritable.source}`, 'u'),
text: new RegExp(`${strayAmpersand}|[<>]|${unwritable.source}`, 'u'),
}
// What `adfToHtml` spells with an entity, a browser (WHATWG HTML §13.3) spells raw in text, or in an attribute; a no-break space it spells `&nbsp;` in both.
// For each spelling, the other way a browser writes what `adfToHtml` writes as the key (WHATWG HTML §13.3).
const browserSpellings: Readonly<Record<Spelling, ReadonlyMap<string, string>>> = {
attribute: new Map([['&gt;', '>'], ['&lt;', '<'], ['\u00a0', '&nbsp;']]),
text: new Map([['&quot;', '"'], ['\u00a0', '&nbsp;']]),
@@ -56,14 +53,14 @@ export function shownValue(value: string, lineFeed: string): string {
return escapeHtml(value.replace(unwritables, '')).replaceAll('\n', lineFeed)
}
// Where `html` reads as `shown` from `index`: `whole`, and the index after it, or where it first reads otherwise. `shown` is spelled as `adfToHtml` writes it, `html` as a browser may too.
// Whether `html` holds `shown` from `index` (`whole`), and the index where the match ends or first fails. `shown` is as `adfToHtml` writes it; `html` may spell it as a browser does.
export function readsAsShown(html: string, index: number, shown: string): { at: number; whole: boolean } {
if (html.startsWith(shown, index)) return { at: index + shown.length, whole: true }
let at = index
let spelling: Spelling = 'text'
for (let next = 0; next < shown.length; ) {
const token = writtenEntities.find((spelled) => shown.startsWith(spelled, next)) ?? shown.charAt(next)
// Only a tag holds a raw `<` or `>`, and only its attribute values an escape.
// A shown `<` opens a tag, whose attribute values may spell `<` and `>` raw; a shown `>` ends it.
if (token === '<') spelling = 'attribute'
if (token === '>') spelling = 'text'
const read = [token, browserSpellings[spelling].get(token)].find((spelled) => spelled !== undefined && html.startsWith(spelled, at))