import Diff from './base';

import {generateOptions} from '../util/params';

// Based on https://en.wikipedia.org/wiki/Latin_script_in_Unicode

//

// Ranges and exceptions:

// Latin-1 Supplement, 0080–00FF

// - U+00D7 × Multiplication sign

// - U+00F7 ÷ Division sign

// Latin Extended-A, 0100–017F

// Latin Extended-B, 0180–024F

// IPA Extensions, 0250–02AF

// Spacing Modifier Letters, 02B0–02FF

// - U+02C7 ˇ ˇ Caron

// - U+02D8 ˘ ˘ Breve

// - U+02D9 ˙ ˙ Dot Above

// - U+02DA ˚ ˚ Ring Above

// - U+02DB ˛ ˛ Ogonek

// - U+02DC ˜ ˜ Small Tilde

// - U+02DD ˝ ˝ Double Acute Accent

// Latin Extended Additional, 1E00–1EFF

const extendedWordChars = /^[a-zA-Z\u{C0}-\u{FF}\u{D8}-\u{F6}\u{F8}-\u{2C6}\u{2C8}-\u{2D7}\u{2DE}-\u{2FF}\u{1E00}-\u{1EFF}]+$/u;

const reWhitespace = /\S/;

export const wordDiff = new Diff();

wordDiff.equals = function(left, right) {

return left === right || (this.options.ignoreWhitespace && !reWhitespace.test(left) && !reWhitespace.test(right));

};

wordDiff.tokenize = function(value) {

let tokens = value.split(/(\s+|\b)/);

// Join the boundary splits that we do not consider to be boundaries. This is primarily the extended Latin character set.

for (let i = 0; i < tokens.length - 1; i++) {

// If we have an empty string in the next field and we have only word chars before and after, merge

if (!tokens[i + 1] && tokens[i + 2]

&& extendedWordChars.test(tokens[i])

&& extendedWordChars.test(tokens[i + 2])) {

tokens[i] += tokens[i + 2];

tokens.splice(i + 1, 2);

i--;

}

}

return tokens;

};

export function diffWords(oldStr, newStr, callback) {

let options = generateOptions(callback, {ignoreWhitespace: true});

return wordDiff.diff(oldStr, newStr, options);

}

export function diffWordsWithSpace(oldStr, newStr, callback) {

return wordDiff.diff(oldStr, newStr, callback);

}