Stream report and trees instead of loading every record (closes #14)
check / check (push) Successful in 1m49s

report now has SQLite group the records and put the rows in report
order, helped by a new files_signature index on (size, head, tail,
content), and writes each row as it reads it. trees reads the records
in path order, where all the paths under a directory come together, so
it computes each directory's digest as soon as the stream leaves it and
keeps only its path, parent, digest and totals. Output is unchanged.

The tests that called the removed in-memory grouping functions now group
records stored in a database. A new test checks that both commands give
the same output whatever order the records were inserted in.

Model: opus-5-5
This commit is contained in:
2026-10-04 02:04:37 +00:00
parent 2dd1194f33
commit bd8d41b174
9 changed files with 540 additions and 292 deletions
+10 -25
View File
@@ -8,7 +8,6 @@ import (
"os"
"path/filepath"
"slices"
"strings"
"testing"
)
@@ -73,9 +72,8 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
defer func() { _ = db.Close() }()
recs, err := loadFileRows(t.Context(), db)
if err != nil || len(recs) != 0 {
t.Fatalf("loadFileRows = %v, %v; want empty, nil", recs, err)
if recs := dbRecords(t, db); len(recs) != 0 {
t.Fatalf("records = %v, want none", recs)
}
}
@@ -168,7 +166,7 @@ func TestCloseScanDatabaseWhileReportOpen(t *testing.T) {
defer func() { _ = reportDB.Close() }()
_, err = loadFileRows(t.Context(), reportDB)
err = loadFileRows(t.Context(), reportDB, func(scanRec) {})
if err != nil {
t.Fatalf("loadFileRows: %v", err)
}
@@ -196,15 +194,8 @@ func TestApplyChangesRoundTrip(t *testing.T) {
t.Fatalf("applyChanges: %v", err)
}
got, err := loadFileRows(t.Context(), db)
if err != nil {
t.Fatal(err)
}
slices.SortFunc(got, func(a, b scanRec) int {
return strings.Compare(a.path, b.path)
})
// The records come back in path order, which is the order of recs.
got := dbRecords(t, db)
if !slices.Equal(got, recs) {
t.Fatalf("rows = %+v, want %+v", got, recs)
}
@@ -221,11 +212,7 @@ func TestApplyChangesRoundTrip(t *testing.T) {
t.Fatalf("applyChanges: %v", err)
}
got, err = loadFileRows(t.Context(), db)
if err != nil {
t.Fatal(err)
}
got = dbRecords(t, db)
if len(got) != 1 || got[0] != upd {
t.Fatalf("rows = %+v, want just %+v", got, upd)
}
@@ -254,9 +241,8 @@ func TestApplyChangesBatching(t *testing.T) {
t.Fatalf("applyChanges: %v", err)
}
got, err := loadFileRows(t.Context(), db)
if err != nil || len(got) != n {
t.Fatalf("loadFileRows = %d rows, %v; want %d", len(got), err, n)
if got := dbRecords(t, db); len(got) != n {
t.Fatalf("records = %d, want %d", len(got), n)
}
deletes := make([]string, 0, n)
@@ -270,8 +256,7 @@ func TestApplyChangesBatching(t *testing.T) {
t.Fatalf("applyChanges deletes: %v", err)
}
got, err = loadFileRows(t.Context(), db)
if err != nil || len(got) != 0 {
t.Fatalf("loadFileRows = %d rows, %v; want 0", len(got), err)
if got := dbRecords(t, db); len(got) != 0 {
t.Fatalf("records = %d, want 0", len(got))
}
}