chunking_strategies_evaluation/backlog/multi-column-layout.md

Multi-column layout reading order

Why deferred

Many Text PDFs are single-column policies. Multi-column (or sidebar) layouts can make naive top-to-bottom extraction interleave columns.

Trigger

Chunk Preview shows sentences from column A mixed with column B; Experiment Faithfulness drops on those docs only.

Approach to try

1. Use PyMuPDF block/bbox clustering to detect columns
2. Read column-by-column (right-to-left for Farsi multi-column if applicable)
3. Add a fixture PDF with known two-column layout to regression tests

Success criteria

• Reading order matches human reading on the fixture
• No regression on single-column Farsi docs