Find fuzzy duplicates in a list

fuzzy-file-duplicate-finder

import levenshtein from 'fast-levenshtein';
import { filter, join, isEmpty, sortBy, get, identity, flow, map, toLower } from 'lodash/fp'

// https://stackoverflow.com/questions/43241174/javascript-generating-all-combinations-of-elements-in-a-single-array-in-pairs
function getCombinations(array) {
  var results = [];

  // Since you only want pairs, there's no reason
  // to iterate over the last element directly
  for (var i = 0; i < array.length - 1; i++) {
    // This is where you'll capture that last value
    for (var j = i + 1; j < array.length; j++) {
      results.push([array[i], array[j]]);
    }
  }
  return results
}

const format = flow(
  map( x => `${x[1]} ${x[0][0]} ${x[0][1]}` ),
  join('\n')
)
const process = flow([
  filter(line => !isEmpty(line)),
  getCombinations,
  pairs => pairs.map(processPair),
  sortBy(get('1'))
])

const processPair = (pair) => {
  const score = levenshtein.get(...pair.map(toLower))
  return [pair, score]
}