# aborist — Makefile entry points
# Every workflow lives behind a `make` target. Bare python commands are not
# the user interface.

# Tools and config
PYTHON       ?= python3
VENV         ?= .venv
PIP          := $(VENV)/bin/pip
PY           := $(VENV)/bin/python
ABORIST      := $(VENV)/bin/aborist

# Data + DB
DATA_DIR     ?= data
WP_DUMP_URL  ?= https://dumps.wikimedia.org/archive/2003/2003-05-16/en/20030516_cur_tablesql.bz2
WP_DUMP      := $(DATA_DIR)/20030516_cur_tablesql.bz2
DB           ?= $(HOME)/.aborist/aborist.db

# Smoke-test caps so make all stays fast
INGEST_LIMIT ?= 500
VERIFY_N     ?= 10
SEARCH_Q     ?= computer

.PHONY: all bootstrap fetch ingest verify search stats test clean clean-db clean-data help

all: bootstrap fetch ingest verify stats ## bootstrap → fetch → ingest → verify → stats

help: ## show this help
	@awk 'BEGIN{FS=":.*##"} /^[a-zA-Z0-9_-]+:.*##/{printf "  %-14s %s\n", $$1, $$2}' $(MAKEFILE_LIST)

$(VENV)/bin/activate: pyproject.toml
	$(PYTHON) -m venv $(VENV)
	$(PIP) install --upgrade pip wheel
	$(PIP) install -e '.[dev]'
	@touch $(VENV)/bin/activate

bootstrap: $(VENV)/bin/activate ## create venv and install editable package

$(WP_DUMP): | $(DATA_DIR)
	@echo ">> fetching $(WP_DUMP_URL)"
	curl -fL --retry 3 -o $@ "$(WP_DUMP_URL)"

$(DATA_DIR):
	mkdir -p $(DATA_DIR)

fetch: $(WP_DUMP) ## download Wikipedia 2003-05-16 cur dump (cached)

ingest: bootstrap fetch ## ingest INGEST_LIMIT articles into $(DB)
	$(ABORIST) --db $(DB) ingest --source wikipedia_cur --path $(WP_DUMP) --limit $(INGEST_LIMIT)

verify: bootstrap ## round-trip Merkle proofs for VERIFY_N random documents
	$(ABORIST) --db $(DB) verify -n $(VERIFY_N)

search: bootstrap ## keyword search; override SEARCH_Q (or pass Q=...)
	$(ABORIST) --db $(DB) search '$(if $(Q),$(Q),$(SEARCH_Q))'

stats: bootstrap ## counts: documents, chunks, edges, audit chain
	$(ABORIST) --db $(DB) stats

test: bootstrap ## run pytest suite
	$(VENV)/bin/pytest -q

clean: ## remove venv + caches (keeps fetched data and db)
	rm -rf $(VENV) .pytest_cache **/__pycache__ aborist.egg-info
	find . -type d -name __pycache__ -prune -exec rm -rf {} +

clean-db: ## drop the aborist db (keeps fetched data and venv)
	rm -f $(DB) $(DB)-journal $(DB)-wal $(DB)-shm

clean-data: ## remove fetched dumps
	rm -rf $(DATA_DIR)