From ee5f1e21f306d93b82d657917c92cc379c1df285 Mon Sep 17 00:00:00 2001
From: Lukasz Kasprzak <lukas@labunix.xyz>
Date: Mon, 27 Jul 2026 20:43:54 +0200
Subject: build: corpus-validate script + add-corpus/check-corpora make targets

---
 Makefile | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index f5018eb..50fcb87 100644
--- a/Makefile
+++ b/Makefile
@@ -4,7 +4,7 @@ LECTIO_WEB := lectio-web
 PREFIX   ?= $(HOME)/.local
 BINDIR   := $(PREFIX)/bin
 
-.PHONY: help build install uninstall test vet fmt clean cross
+.PHONY: help build install uninstall test vet fmt clean cross check-corpora add-corpus
 help: ## show this help
 	@grep -hE '^[a-z-]+:.*##' $(MAKEFILE_LIST) | sed -E 's/:.*## /\t/' | sort
 build: ## build ./lectio, ./lectio-ui and ./lectio-web
@@ -19,7 +19,7 @@ install: ## build and install all three to $(BINDIR)
 	@echo "installed $(BINDIR)/$(LECTIO), $(BINDIR)/$(LECTIO_UI) and $(BINDIR)/$(LECTIO_WEB)"
 uninstall: ## remove installed binaries
 	rm -f $(BINDIR)/$(LECTIO) $(BINDIR)/$(LECTIO_UI) $(BINDIR)/$(LECTIO_WEB)
-test: ## run tests
+test: check-corpora ## run tests
 	go test ./...
 vet: ## go vet
 	go vet ./...
@@ -36,3 +36,25 @@ cross: ## cross-compile into dist/
 		GOOS=$$os GOARCH=$$arch go build -o dist/$(LECTIO_UI)-$$os-$$arch$$ext ./cmd/lectio-ui; \
 		GOOS=$$os GOARCH=$$arch go build -o dist/$(LECTIO_WEB)-$$os-$$arch$$ext ./cmd/lectio-web; \
 	done
+
+# Validate every embedded corpus (CI gate). grb is EXEMPT: it is a scholarly
+# Septuagint corpus whose Book column intentionally carries Orthodox-canon
+# extras (1-4 Esdras/Maccabees, Odes, Psalms of Solomon) and manuscript variants
+# (…(Theodotion)/(Sinaiticus)/(Vaticanus)) that are not in the 73-key Catholic
+# canon and would collide with canonical keys if renamed. --corpus-check grb
+# correctly reports these; they are by design, not defects to fix here.
+check-corpora: ## validate all embedded bible corpora (skips grb, see comment)
+	@for f in internal/bible/corpora/*.tsv; do \
+		code=$$(basename $$f .tsv); \
+		[ "$$code" = grb ] && { echo "skipping grb (broader LXX canon)"; continue; }; \
+		echo "checking $$code"; \
+		go run ./cmd/lectio --corpus-check $$code || exit 1; \
+	done
+
+# Validate then embed a corpus pair: make add-corpus CORPUS=fr-crampon SRC=/path/to/dir
+add-corpus: ## validate + copy a corpus pair into internal/bible/corpora/, then build
+	@test -n "$(CORPUS)" || { echo "set CORPUS=<code>" >&2; exit 2; }
+	@test -n "$(SRC)" || { echo "set SRC=<dir with $(CORPUS).tsv/.ini>" >&2; exit 2; }
+	go run ./cmd/lectio --corpus-check "$(SRC)/$(CORPUS).tsv"
+	cp "$(SRC)/$(CORPUS).tsv" "$(SRC)/$(CORPUS).ini" internal/bible/corpora/
+	$(MAKE) build
-- 
cgit v1.3