Created
August 22, 2016 05:55
-
-
Save imarban/9bc43f6c2cf33eddd208bdce0ad4a53a to your computer and use it in GitHub Desktop.
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
| class TextProcessor: | |
| def __init__(self, text, tokenizer_module, sanitizer_module): | |
| self.text = text | |
| self.tokenizer = tokenizer_module | |
| self.sanitizer = sanitizer_module | |
| def get_tokens(): | |
| sanitized = self.sanitizer.sanitize(self.text) | |
| tokens = self.tokenizer.tokenize(sanitized) | |
| return tokens | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment