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().
---
 internal/bible/bible.go | 49 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

(limited to 'internal/bible/bible.go')

diff --git a/internal/bible/bible.go b/internal/bible/bible.go
index ac746e1..1fb29f2 100644
--- a/internal/bible/bible.go
+++ b/internal/bible/bible.go
@@ -2,6 +2,7 @@ package bible
 
 import (
 	"embed"
+	"io/fs"
 	"os"
 	"sort"
 	"strconv"
@@ -9,9 +10,55 @@ import (
 	"sync"
 )
 
+// corporaFS embeds only the public-domain Latin Vulgate (vul), which is the
+// sole corpus compiled into the default binary. Every other translation lives
+// in corpora_optional/ and is NOT embedded unless the build carries the
+// "fullbible" tag (see embed_optional.go), keeping the distributed binary free
+// of any third-party scripture text -- bible corpora are not covered by
+// lectio's AGPL licence. Missing corpora resolve gracefully to a "(not in
+// <code>)" note, and users may drop any <code>.tsv/<code>.ini into their
+// corpora dir (SetUserCorporaDir) to add a translation without rebuilding.
+//
 //go:embed corpora
 var corporaFS embed.FS
 
+// optionalFS holds the extra corpora (corpora_optional/) when the "fullbible"
+// build tag is set; it is nil in the default build. Set by embed_optional.go.
+var optionalFS fs.FS
+
+// embReadCorpus returns the bytes of an embedded corpus file (e.g. "vul.tsv",
+// "drb.ini") from the core FS, then the optional FS if present.
+func embReadCorpus(name string) ([]byte, bool) {
+	if b, err := corporaFS.ReadFile("corpora/" + name); err == nil {
+		return b, true
+	}
+	if optionalFS != nil {
+		if b, err := fs.ReadFile(optionalFS, "corpora_optional/"+name); err == nil {
+			return b, true
+		}
+	}
+	return nil, false
+}
+
+// embCorpusFiles lists the base file names of every embedded corpus file across
+// the core and optional FSes.
+func embCorpusFiles() []string {
+	var names []string
+	if ents, err := corporaFS.ReadDir("corpora"); err == nil {
+		for _, e := range ents {
+			names = append(names, e.Name())
+		}
+	}
+	if optionalFS != nil {
+		if ents, err := fs.ReadDir(optionalFS, "corpora_optional"); err == nil {
+			for _, e := range ents {
+				names = append(names, e.Name())
+			}
+		}
+	}
+	return names
+}
+
 // Verse is a single verse.
 type Verse struct {
 	Chapter, Verse int
@@ -38,7 +85,7 @@ func load(version string) *corpus {
 		data, _ = os.ReadFile(p)
 	}
 	if data == nil {
-		data, _ = corporaFS.ReadFile("corpora/" + version + ".tsv")
+		data, _ = embReadCorpus(version + ".tsv")
 	}
 	if data == nil {
 		corpora[version] = &corpus{books: map[string]map[int][]Verse{}}
-- 
cgit v1.3