import { describe, it, expect } from 'vitest'
import { Schema, type Node as PMNode } from '@tiptap/pm/model'
import { wordAt } from './SpellCheck'

// Same minimal schema the suggestion-anchoring tests use: enough of a document
// to walk textblocks, none of the editor.
const schema = new Schema({
  nodes: {
    doc: { content: 'block+' },
    paragraph: { group: 'block', content: 'inline*', toDOM: () => ['p', 0] },
    text: { group: 'inline' },
  },
})

const para = (text: string): PMNode =>
  schema.node('doc', null, [schema.node('paragraph', null, text ? [schema.text(text)] : [])])

// posOf turns a plain-text offset into a ProseMirror position inside the single
// paragraph (+1 for the paragraph's opening token).
const posOf = (offset: number) => offset + 1

describe('wordAt and the pair alphabet', () => {
  it('keeps English-only tokenizing when no accented dictionary is loaded', () => {
    const doc = para('the river runs')
    expect(wordAt(doc, posOf(5))?.word).toBe('river')
  })

  it('cuts an accented word into fragments on the narrow alphabet', () => {
    // Not a hypothetical: this is what every surface did before the pt-PT pair,
    // and it is why the alphabet had to become a property of the checker rather
    // than a constant. "coração" tokenized as A-Z yields "cora" — a definition
    // of which would be worse than no popover.
    const doc = para('o coração dela')
    expect(wordAt(doc, posOf(3))?.word).toBe('cora')
  })

  it('resolves the whole word once the pair widens the alphabet', () => {
    const doc = para('o coração dela')
    expect(wordAt(doc, posOf(3), true)?.word).toBe('coração')
    // …from either side of the accented letters, not just before them.
    expect(wordAt(doc, posOf(9), true)?.word).toBe('coração')
  })

  it('never tokenizes CJK, whichever alphabet is in force', () => {
    // The zh pair's guarantee, and it must survive a change made for another
    // pair entirely: Chinese is the source language, not something to spellcheck.
    const doc = para('我在写作 today')
    expect(wordAt(doc, posOf(1))).toBeNull()
    expect(wordAt(doc, posOf(1), true)).toBeNull()
    expect(wordAt(doc, posOf(6), true)?.word).toBe('today')
  })

  it('stops the wide alphabet at the maths symbols hiding in Latin-1', () => {
    // × (U+00D7) and ÷ (U+00F7) sit inside the accented-letter block. A range
    // written À-ÿ would swallow them and glue "3×4" into one token.
    const doc = para('3×4 é isso')
    expect(wordAt(doc, posOf(4), true)?.word).toBe('é')
  })
})