.gitignore

# Dependencies
node_modules/
npm-debug.log*
yarn-debug.log*
yarn-error.log*

# Python
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
env/
venv/
.venv/
.env
*.egg-info/
dist/
build/
.pytest_cache/
.mypy_cache/
.coverage
htmlcov/

# IDE
.vscode/
.idea/
*.swp
*.swo
*~
.project
.settings/

# OS
.DS_Store
Thumbs.db
Desktop.ini

# Build outputs
/build
/dist
/out
*.log

# Testing
coverage/
.nyc_output/

# Temporary files
*.tmp
*.temp
*.bak
*.backup
*.old
.cache/

# React/Next.js specific
viewer/.next/
viewer/out/
viewer/build/

# Timeline specific
timeline_data/events/index.json
timeline_data/reports/date_validation_*.json
timeline_data/reports/temp_*.json

# Archives (if they get large)
timeline_data/archive/temp/
timeline_data/archive/*.zip
timeline_data/archive/*.tar.gz

# Local environment
.env.local
.env.development.local
.env.test.local
.env.production.local

# Debug
debug.log
npm-debug.log*
yarn-debug.log*
yarn-error.log*
lerna-debug.log*

# Cache
.eslintcache
.cache/
.parcel-cache/

# Generated files
*.generated.*
timeline_data/timeline_complete.json
timeline_data/COMPLETE_TIMELINE.md
timeline_data/validation_status.json
timeline_data/archive_progress_slow.json
importance_distribution.json

# Script-generated exports
timeline_events.csv
timeline_events.json
timeline_events.yaml
timeline_events_minimal.yaml
duplicates.json
duplicates_to_remove.txt
/viewer/public/timeline_events.csv
/viewer/public/timeline_events.json  
/viewer/public/timeline_events.yaml
/viewer/public/timeline_events_minimal.yaml

# Temporary processing files
process_*.py
*_temp.py
*_backup.py
events_to_process.txt
missing_events.txt

# Database
*.sqlite
*.sqlite3
*.db

# Documentation build
# NOTE: docs/ folder is NOT ignored - it contains GitHub Pages site
docs/_build/
site/

# Jupyter Notebook
.ipynb_checkpoints/

# macOS
.AppleDouble
.LSOverride
Icon
._*
.DocumentRevisions-V100
.fseventsd
.Spotlight-V100
.TemporaryItems
.Trashes
.VolumeIcon.icns
.com.apple.timemachine.donotpresent

# Viewer specific
viewer/node_modules/
viewer/build/
viewer/.env.local

# API specific
api/__pycache__/
api/*.pyc
api/static_api/

# Archive downloads (temporary)
tools/archiving/downloads/
tools/archiving/temp/

# Reports (keep only permanent ones)
timeline_data/reports/daily_*.json
timeline_data/reports/weekly_*.json
!timeline_data/reports/final_*.json

# RAG System artifacts
rag/chroma_db/
rag/.chroma/
rag/embeddings/
rag/*.pkl
rag/*.npy
rag/*.npz
rag/vector_store/
rag/cache/
*.faiss
*.ann
*.hnsw

# Model downloads
models/
*.bin
*.onnx
*.pt
*.pth
*.safetensors

# QA artifacts
timeline_data/qa_reports/temp_*.json
timeline_data/.qa_cache/

# Source archives (hidden folder with scraped sources)
timeline_data/events/.sources/

# Archive folder (old files - generally ignored)
archive/

# Except for important cleanup documentation
!archive/CLEANUP-2025-10-21.md
!archive/development-process-docs-20251021/
!archive/one-time-scripts-20251021/
!archive/experimental-research-20251021/

# AI notes and internal documentation (not part of core timeline)
ai_notes/

# Flask app files
timeline_data/static/logs/
*.log
coverage_html/
.coverage
coverage.json

# Hugo build artifacts
timeline/.hugo_build.lock
timeline/public/
timeline/archetypes/
timeline/resources/

# Database WAL files (write-ahead log and shared memory)
*.db-wal
*.db-shm

# Legacy directories (superseded by research-server/)
research_monitor/
api/
research_api.py

# Backup files
*.backup
*.bak
*.old
*-backup-*.tar.gz
timeline/data/events/malformed_backup/

# Experimental research (keep in archive only)
research-server/ai-analysis/

# Development process docs (keep in archive only)
SPEC-*.md
CLEANUP-*.md
ARCHITECTURE_REVIEW.md
IMPROVEMENTS_SUMMARY.md
specs/

# One-time manifests
*_manifest.json
*_files_manifest.json

# Scraped source cache (should not be in git)
timeline/data/events/.sources/

# React viewer coverage and build
timeline/viewer/coverage/
timeline/viewer/build/
hugo-site/public/
hugo-site/.hugo_build.lock

# Cleanup scripts (not for public repo)
scripts/