From 5e1664b8008675177a551aff1de371f54d4e20e4 Mon Sep 17 00:00:00 2001
From: Lukasz Kasprzak <lukas@labunix.xyz>
Date: Tue, 28 Jul 2026 18:01:33 +0200
Subject: bible: embed only the Vulgate by default; other corpora opt-in

Split the bundled corpora so the default binary carries only the
public-domain Latin Vulgate. wuj/drb/grb move to corpora_optional/ and are
compiled in only with `-tags fullbible`, or dropped into the user corpora
dir at runtime. This keeps the distributed AGPL binary free of third-party
scripture text -- bible corpora are not covered by lectio's licence.

- bible: read corpus files/metadata from core + optional embed FS
  (embReadCorpus/embCorpusFiles); optionalFS is set only under the tag.
- config: default `versions` now reflects corpora actually available in the
  build (Vulgate first), so a vul-only binary offers no absent versions.
- Makefile: `make build` = vul only; `make build-full` embeds the rest;
  `make test` runs with -tags fullbible; check-corpora validates both dirs.
- tests: corpusmeta asserts on vul (the always-embedded corpus); the
  versions-default expectation follows availableVersions().
---
 Makefile | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index 50fcb87..192c591 100644
--- a/Makefile
+++ b/Makefile
@@ -4,13 +4,17 @@ LECTIO_WEB := lectio-web
 PREFIX   ?= $(HOME)/.local
 BINDIR   := $(PREFIX)/bin
 
-.PHONY: help build install uninstall test vet fmt clean cross check-corpora add-corpus
+.PHONY: help build build-full 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
+build: ## build all three binaries (embeds only the Vulgate)
 	go build -o $(LECTIO) ./cmd/lectio
 	go build -o $(LECTIO_UI) ./cmd/lectio-ui
 	go build -o $(LECTIO_WEB) ./cmd/lectio-web
+build-full: ## build all three with the optional corpora (wuj, drb, grb) embedded
+	go build -tags fullbible -o $(LECTIO) ./cmd/lectio
+	go build -tags fullbible -o $(LECTIO_UI) ./cmd/lectio-ui
+	go build -tags fullbible -o $(LECTIO_WEB) ./cmd/lectio-web
 install: ## build and install all three to $(BINDIR)
 	@mkdir -p $(BINDIR)
 	go build -o $(BINDIR)/$(LECTIO) ./cmd/lectio
@@ -19,8 +23,8 @@ 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: check-corpora ## run tests
-	go test ./...
+test: check-corpora ## run tests (with all corpora embedded, so corpus tests can resolve text)
+	go test -tags fullbible ./...
 vet: ## go vet
 	go vet ./...
 fmt: ## gofmt the tree
@@ -43,12 +47,12 @@ cross: ## cross-compile into dist/
 # (…(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 \
+check-corpora: ## validate every bundled corpus, core + optional (skips grb, see comment)
+	@for f in internal/bible/corpora/*.tsv internal/bible/corpora_optional/*.tsv; do \
 		code=$$(basename $$f .tsv); \
 		[ "$$code" = grb ] && { echo "skipping grb (broader LXX canon)"; continue; }; \
 		echo "checking $$code"; \
-		go run ./cmd/lectio --corpus-check $$code || exit 1; \
+		go run -tags fullbible ./cmd/lectio --corpus-check $$code || exit 1; \
 	done
 
 # Validate then embed a corpus pair: make add-corpus CORPUS=fr-crampon SRC=/path/to/dir
-- 
cgit v1.3