Ruslan Gainanov GRomR1
GRomR1
/ regex_tokenizer.js
Last active
March 18, 2016 12:47
— forked from raisch/regex_tokenizer.js
Regular Expression Sentence Tokenizer (English)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // tokenize(str) | |
| // extracts semantically useful tokens from a string containing English-language sentences | |
| // @param {String} the string to tokenize | |
| // @returns {Array} containing extracted tokens | |
| function tokenize(str) { | |
| var punct = '\\[' + '\\!' + '\\"' + '\\#' + '\\$' + // since javascript does not | |
| '\\%' + '\\&' + '\\\'' + '\\(' + '\\)' + // support POSIX character | |
| '\\*' + '\\+' + '\\,' + '\\\\' + '\\-' + // classes, we'll need our |