Show HN: Document parsing 5B tokens on a single CPU thread

2026-11-06来源 Hacker News ShowEnglish

mit license: https://github.com/john-friedman/doc2struct

doc2struct is an algorithm that can parse documents fast on one thread. For example it can parse every every 2025 annual report 19GB in 40s.

It preserves nesting, does mild table cleaning, among other things.

It succeeds my earlier document parser https://github.com/john-friedman/doc2dict

Comments URL: https://news.ycombinator.com/item?id=50388374

Points: 1

# Comments: 0

原文：https://www.a8q9.cn/en/article/show-hn-document-parsing-5b-tokens-on-a-single-cpu-thread-8fc2ca.html

相关文章