partial reads never cached; extractor version 3 discards 0.0.7 caches

1 files changed, 28 insertions, 0 deletions

diff --git a/internal/engine/exclude_test.go b/internal/engine/exclude_test.go
index 8308a82..5a758bb 100644
--- a/internal/engine/exclude_test.go
+++ b/internal/engine/exclude_test.go
@@ -455,3 +455,31 @@ func TestExplainLeavesTheCacheAlone(t *testing.T) {
 		t.Errorf("explain removed the cache: %v", err)
 	}
 }
+
+// TestPartlyReadableDocumentIsNotCached: a partial read's answers never
+// enter the keyword cache, so a second run with the cache still sets the
+// file aside (plan 11 review M2).
+func TestPartlyReadableDocumentIsNotCached(t *testing.T) {
+	h, dl := excludeTree(t, map[string]string{})
+	os.MkdirAll(dl, 0o755)
+	partDocx(t, filepath.Join(dl, "part.docx"), "good body text")
+	main := writeConfig(t, h, `(include "dl")`, map[string]string{"dl": `
+(path "~/dl")
+(exclude (content "confidential"))
+(rule "all" (move "Out"))
+`})
+	for run := 1; run <= 2; run++ {
+		e, errs := Load(main)
+		if len(errs) > 0 {
+			t.Fatal(errs)
+		}
+		e.CacheDir = filepath.Join(h, "cache")
+		r, err := e.Match(context.Background(), e.Dirs[0])
+		if err != nil {
+			t.Fatal(err)
+		}
+		if len(r.Matched) != 1 || !strings.HasSuffix(r.Matched[0].Excluded, "(content unreadable)") {
+			t.Fatalf("run %d: matched = %+v; want part.docx set aside", run, r.Matched)
+		}
+	}
+}