Skip to content

Pdf native ingestion - #7

Merged
aj1126 merged 7 commits into
mainfrom
pdf-native-ingestion
Jun 13, 2026
Merged

Pdf native ingestion#7
aj1126 merged 7 commits into
mainfrom
pdf-native-ingestion

Conversation

@aj1126

@aj1126 aj1126 commented Jun 13, 2026

Copy link
Copy Markdown
Owner

Summary

  • Describe the change.

Checklist

  • I reviewed whether this change affects README, architecture docs, or legacy docs.
  • If commands, supported file types, or layout metadata changed, I ran npm run docs:generate.
  • I ran npm run docs:check.
  • If historical Python prototype guidance changed, I updated docs/legacy-prototype.md.

aj1126 and others added 7 commits June 12, 2026 20:58
- Refactored PDF ingestion to capture structured page text instead of a single flat string.
- Added new Stage 5 goals to ROADMAP.md.
- Updated PDF router to parse page-level text and extract PDF info object.
- Added PDF metadata support to the file record schema.
- Updated ROADMAP.md to track structural analysis completion.
# Note: For real PDF testing, place a small 'test.pdf' in test/fixtures/
Add a test for successful PDF ingestion and parsing.
- Integrated dynamic import of mupdf to handle top-level await boundaries inside a CommonJS runtime.
- Implemented automated fallback to Tesseract.js when digital text extraction yields insufficient characters.
- Scaled rasterized PDF pages to 2x resolution to optimize OCR linguistic accuracy on older documentation.
@aj1126 aj1126 added bug Something isn't working enhancement New feature or request labels Jun 13, 2026
@aj1126
aj1126 merged commit 8de2914 into main Jun 13, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant