Discussion Show HN: Document parsing 5B tokens on a single CPU thread mit license: https://github.com/john-friedman/doc2structdoc2struct 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 2 points jgfriedman1999 6 days ago 0 comments
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