feat(pipeline): add POST /backfill-refs endpoint to retroactively inject source back-references

This commit is contained in:
Mathias Bergqvist
2026-04-23 16:50:00 +02:00
parent 55fa0b503a
commit 1605624668
4 changed files with 211 additions and 0 deletions

View File

@@ -0,0 +1,107 @@
// ingestion/internal/pipeline/backfill_test.go
package pipeline
import (
"context"
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func setupBrainDir(t *testing.T) string {
t.Helper()
dir := t.TempDir()
for _, sub := range []string{"wiki/sources", "wiki/concepts", "wiki/entities"} {
require.NoError(t, os.MkdirAll(filepath.Join(dir, sub), 0o755))
}
return dir
}
func writeFile(t *testing.T, path, content string) {
t.Helper()
require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, os.WriteFile(path, []byte(content), 0o644))
}
func TestBackfillRefs_UpdatesConcept(t *testing.T) {
dir := setupBrainDir(t)
writeFile(t, filepath.Join(dir, "wiki/sources/shape-up.md"),
"---\ntitle: Shape Up\n---\n\n## Summary\n\nSee [[betting|Betting]].\n")
writeFile(t, filepath.Join(dir, "wiki/concepts/betting.md"),
"---\ntitle: Betting\n---\n\n## Definition\n\nA resource allocation technique.\n")
n, err := BackfillRefs(context.Background(), dir)
require.NoError(t, err)
assert.Equal(t, 1, n)
got, err := os.ReadFile(filepath.Join(dir, "wiki/concepts/betting.md"))
require.NoError(t, err)
assert.Contains(t, string(got), "## Sources")
assert.Contains(t, string(got), "[[shape-up|Shape Up]]")
assert.Contains(t, string(got), "## Definition") // original content preserved
}
func TestBackfillRefs_Deduplication(t *testing.T) {
dir := setupBrainDir(t)
writeFile(t, filepath.Join(dir, "wiki/sources/shape-up.md"),
"---\ntitle: Shape Up\n---\n\n## Summary\n\nSee [[betting|Betting]].\n")
writeFile(t, filepath.Join(dir, "wiki/concepts/betting.md"),
"---\ntitle: Betting\n---\n\n## Definition\n\nA technique.\n")
// Run twice — should not duplicate the ref.
_, err := BackfillRefs(context.Background(), dir)
require.NoError(t, err)
_, err = BackfillRefs(context.Background(), dir)
require.NoError(t, err)
got, err := os.ReadFile(filepath.Join(dir, "wiki/concepts/betting.md"))
require.NoError(t, err)
count := 0
for _, line := range splitLines(string(got)) {
if line == "- [[shape-up|Shape Up]]" {
count++
}
}
assert.Equal(t, 1, count, "ref should appear exactly once after two runs")
}
func TestBackfillRefs_MultipleSources(t *testing.T) {
dir := setupBrainDir(t)
writeFile(t, filepath.Join(dir, "wiki/sources/book-a.md"),
"---\ntitle: Book A\n---\n\n## Summary\n\nSee [[shaping|Shaping]].\n")
writeFile(t, filepath.Join(dir, "wiki/sources/book-b.md"),
"---\ntitle: Book B\n---\n\n## Summary\n\nAlso [[shaping|Shaping]].\n")
writeFile(t, filepath.Join(dir, "wiki/concepts/shaping.md"),
"---\ntitle: Shaping\n---\n\n## Definition\n\nA design activity.\n")
n, err := BackfillRefs(context.Background(), dir)
require.NoError(t, err)
assert.Equal(t, 1, n) // one concept page written
got, err := os.ReadFile(filepath.Join(dir, "wiki/concepts/shaping.md"))
require.NoError(t, err)
assert.Contains(t, string(got), "[[book-a|Book A]]")
assert.Contains(t, string(got), "[[book-b|Book B]]")
}
func TestBackfillRefs_NoSourcesDir(t *testing.T) {
dir := t.TempDir() // no wiki/sources subdir
n, err := BackfillRefs(context.Background(), dir)
require.NoError(t, err)
assert.Equal(t, 0, n)
}
func TestBackfillRefs_SkipsUnknownSlugs(t *testing.T) {
dir := setupBrainDir(t)
// Source links to a slug not in inventory and not on disk.
writeFile(t, filepath.Join(dir, "wiki/sources/article.md"),
"---\ntitle: Article\n---\n\n## Summary\n\nSee [[ghost-slug|Ghost]].\n")
n, err := BackfillRefs(context.Background(), dir)
require.NoError(t, err)
assert.Equal(t, 0, n)
}