Matt 501004ecf1 Filter non-English articles from ZIM ingestion ... Skip articles with MediaWiki translation suffixes (/es, /fr, /pl, etc.) before text extraction to avoid wasting Gemini enrichment on translations. Uses path-based regex matching against ISO 639 language codes. ~5,276 non-English articles already ingested from Appropedia (top: es=837, zh=765, ru=475, fr=433, ko=407). Purge decision deferred.		2026-04-17 07:30:30 +00:00
..
__init__.py	Phase 3: dispatcher, transcript processor, text_dir resolution	2026-04-14 15:39:42 +00:00
pdf_processor.py	Fix: Gemini "null" string bug in pdf_processor metadata voting	2026-04-15 23:30:59 +00:00
text_processor.py	Phase 6f: text processor for .txt file ingestion	2026-04-15 22:39:31 +00:00
transcript_processor.py	Phase 6a: transcripts mark organized in-place, skip filing	2026-04-14 22:49:21 +00:00
zim_processor.py	Filter non-English articles from ZIM ingestion	2026-04-17 07:30:30 +00:00