9bac0f3009
- Add validate-corpus target to Makefile (calls scripts/validate-corpus.sh) - Regenerate corpus manifest with 1000 synthetic PDF entries - Validate corpus integrity: 1000 files, 10,590 pages, ~6.9 MB - Update tests/fixtures/grep-corpus/README.md with complete workflow documentation - Document Makefile targets (validate-corpus, download-grep-corpus) - Add manual usage instructions for advanced users - Verify complete end-to-end workflow: generation → manifest → validation Acceptance criteria: - ✓ make validate-corpus runs successfully - ✓ Manifest contains 1000 entries with all required fields - ✓ Validation confirms corpus meets size/count targets - ✓ README.md documents workflow - ✓ All child beads' outputs integrated Closes bf-2kre2
37 lines
1.1 KiB
Makefile
37 lines
1.1 KiB
Makefile
# pdftract Makefile
|
|
# Top-level build automation for pdftract project
|
|
|
|
.PHONY: help validate-corpus download-grep-corpus test clean
|
|
|
|
# Default target
|
|
help:
|
|
@echo "pdftract Makefile targets:"
|
|
@echo ""
|
|
@echo " validate-corpus - Verify grep-corpus integrity against manifest"
|
|
@echo " download-grep-corpus - Download/generate PDFs for grep-corpus"
|
|
@echo " test - Run all tests"
|
|
@echo " clean - Clean build artifacts"
|
|
@echo ""
|
|
@echo "Corpus management:"
|
|
@echo " make validate-corpus # Validate existing corpus"
|
|
@echo " make download-grep-corpus # Generate corpus (default: 1000 PDFs)"
|
|
@echo " make download-grep-corpus COUNT=500 # Generate specific count"
|
|
@echo ""
|
|
|
|
# Validate corpus integrity against manifest.csv
|
|
validate-corpus:
|
|
@echo "Validating grep-corpus..."
|
|
@bash scripts/validate-corpus.sh tests/fixtures/grep-corpus
|
|
|
|
# Download/generate PDFs for grep-corpus
|
|
download-grep-corpus:
|
|
@echo "Generating grep-corpus ($(COUNT) PDFs)..."
|
|
@bash scripts/download-grep-corpus.sh $(COUNT)
|
|
|
|
# Run tests
|
|
test:
|
|
cargo test --all-targets
|
|
|
|
# Clean build artifacts
|
|
clean:
|
|
cargo clean
|