Show HN: Document parsing 5B tokens on a single CPU thread
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
Read original source
Source record
Recorded metrics
points · 1 votes
2026-11-06 09:45:15.073Z
cumulative since publication
Research analysis
What changed
Source account: 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
Version & cost evidence
Source votes: 1 votes (Nov 6, 2026 UTC; cumulative since publication) Recent records to compare: “Show HN: Models[.]Dev Index on a Globe” (Show HN, Nov 7, 2026); “Show HN: NLP capabilities of Opus, Astra, Argon measured by Codenames skills” (Show HN, Nov 7, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Who is affected
Identify the existing workflow this change affects before recommending an upgrade. Launch attention does not establish improvement; an API, pricing or availability change may instead create migration work.
Missing comparison points
Missing checks: old versus new behavior, affected plans and regions, availability date, compatibility, rollback path and cost under the same workload.
Migration check
Save the release or policy notice, run the same task on the old and new option, and compare outputs and the full bill. For retirement notices, verify the deadline before scheduling migration.