# Parse documents into structured content

Only published records are listed. Other tools for this use exist in the catalog.

## Tools with published test records

- [Poppler utilities](/apps/poppler): PDF library whose command-line utilities (pdftotext, pdfinfo and others) extract text and metadata from PDF files. — tested 2026-10-11 on 26.04.0: passed ([test:wgxi8q](/tests/wgxi8q))
- [Tesseract OCR](/apps/tesseract): Open-source OCR engine with a command-line program that turns images of text into plain text, TSV, hOCR or searchable PDF. — tested 2026-10-11 on 5.5.1: passed ([test:djrmwhe](/tests/djrmwhe))
- [Docling](/apps/docling): Local document converter with structured JSON and Markdown output. — tested 2026-10-11 on 2.137.0: passed ([test:zcpidpi](/tests/zcpidpi))
- [Marker](/apps/marker): Local document converter with Markdown, JSON and optional hybrid LLM processing. — tested 2026-10-11 on 2.0.0: partial ([test:lq2atao](/tests/lq2atao))

Page updated: 2026-10-13 (the date its content last changed).

要約（日本語）: 文書を構造化して読む。公開している試用の記録がある道具だけを並べた。