axhiao
/ testRegex.js
Created
August 16, 2024 06:37
— forked from hanxiao/testRegex.js
Regex for chunking by using all semantic cues
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
| // Updated: Aug. 15, 2024 | |
| // Run: node testRegex.js testText.txt | |
| // Used in https://jina.ai/tokenizer | |
| const fs = require('fs'); | |
| const util = require('util'); | |
| // Define variables for magic numbers | |
| const MAX_HEADING_LENGTH = 7; | |
| const MAX_HEADING_CONTENT_LENGTH = 200; | |
| const MAX_HEADING_UNDERLINE_LENGTH = 200; |