@thi.ng/text-analysis/replace.js

Text tokenization, transformation & analysis transducers, utilities, stop words, porter stemming, vector encodings, similarities

import { mapcat } from "@thi.ng/transducers/mapcat";
const DEFAULT_REPLACEMENTS_EN = {
  "can't": ["can", "not"],
  "couldn't": ["could", "not"],
  "didn't": ["did", "not"],
  "doesn't": ["does", "not"],
  "don't": ["do", "not"],
  "hadn't": ["had", "not"],
  "hasn't": ["has", "not"],
  "haven't": ["has", "not"],
  "he'd": ["he", "would"],
  "he'll": ["he", "will"],
  "he's": ["he", "is"],
  "how'd": ["how", "would"],
  "how're": ["how", "are"],
  "how's": ["how", "is"],
  "i'd": ["i", "would"],
  "i'll": ["i", "will"],
  "i'm": ["i", "am"],
  "i've": ["i", "have"],
  "isn't": ["is", "not"],
  "it'd": ["it", "would"],
  "it'll": ["it", "will"],
  "it's": ["it", "is"],
  "she'd": ["she", "would"],
  "she'll": ["she", "would"],
  "she's": ["she", "is"],
  "should've'": ["should", "have"],
  "shouldn't": ["should", "not"],
  "they'd": ["they", "would"],
  "they'll": ["they", "will"],
  "they're": ["they", "are"],
  "they've": ["they", "have"],
  "wasn't": ["was", "not"],
  "we'd": ["we", "would"],
  "we'll": ["we", "will"],
  "we're": ["we", "are"],
  "we've": ["we", "have"],
  "weren't": ["were", "not"],
  "what'd": ["what", "would"],
  "what're": ["what", "are"],
  "what's": ["what", "is"],
  "who'd": ["who", "would"],
  "who're": ["who", "are"],
  "who's": ["who", "is"],
  "why'd": ["why", "would"],
  "why're": ["why", "are"],
  "why's": ["why", "is"],
  "won't": ["will", "not"],
  "wouldn't": ["would", "not"],
  "you'd": ["you", "would"],
  "you'll": ["you", "will"],
  "you're": ["you", "are"],
  "you've": ["you", "have"]
};
const replaceWith = (dict = DEFAULT_REPLACEMENTS_EN) => mapcat((x) => dict[x] ?? [x]);
export {
  DEFAULT_REPLACEMENTS_EN,
  replaceWith
};