string-punctuation-tokenizer
Version:
Small library that provides functions to tokenize a string into an array of words with or without punctuation
43 lines (38 loc) • 675 B
JavaScript
import {
tokenize,
tokenizeOrigLang,
word,
punctuation,
whitespace,
number_ as number,
} from './tokenizers';
import {
normalizer,
normalizerDestructive,
normalizationsDestructive,
} from './normalizers';
import {
occurrenceInString,
occurrencesInString,
} from './occurrences';
import {
selectionArray,
spliceStringOnRanges,
selectionsToRanges,
} from './selectionHelpers';
export {
tokenize,
tokenizeOrigLang,
normalizer,
normalizerDestructive,
normalizationsDestructive,
occurrenceInString,
occurrencesInString,
selectionArray,
spliceStringOnRanges,
selectionsToRanges,
word,
punctuation,
whitespace,
number,
};