Leave empty files out of report and trees (closes #178) (#183)

internal/sfdupes/trees_test.go

@@ -2,6 +2,7 @@ package sfdupes //nolint:testpackage // checks the unexported treeNode results
 
 import (
 	"bytes"
+	"crypto/sha256"
 	"database/sql"
 	"os"
 	"slices"
@@ -435,6 +436,35 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 	}
 }
 
+// TestCollectTreeGroupsLeavesOutEmptyTrees checks that directories
+// holding only empty files form no group, and that an empty file still
+// counts toward the digest of a tree that holds other files.
+func TestCollectTreeGroupsLeavesOutEmptyTrees(t *testing.T) {
+	t.Parallel()
+
+	h, tl, c, e := testHash("h"), testHash("t"), testHash("c"),
+		sha256.Sum256(nil)
+	recs := []scanRec{
+		{size: 0, head: e, tail: e, content: e, path: "/e/a/.gitkeep"},
+		{size: 0, head: e, tail: e, content: e, path: "/e/b/.gitkeep"},
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x1/f"},
+		{size: 0, head: e, tail: e, content: e, path: "/p/x1/.gitkeep"},
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x2/f"},
+		{size: 0, head: e, tail: e, content: e, path: "/p/x2/.gitkeep"},
+		// Without the empty file, /p/x3 is no copy of /p/x1.
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x3/f"},
+	}
+
+	super, dirs := treeOf(t, recs)
+
+	got := groupPaths(collectTreeGroups(dirs, super, nil))
+
+	want := [][]string{{"/p/x1", "/p/x2"}}
+	if !slices.EqualFunc(got, want, slices.Equal) {
+		t.Fatalf("groups = %v, want %v", got, want)
+	}
+}
+
 func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 	t.Parallel()