Implement persistent SQLite scan database
All checks were successful
check / check (push) Successful in 3s

scan now synchronizes a database that survives between runs
(SFDUPES_DATABASE, default /var/lib/sfdupes/db.sqlite) instead of
emitting a stream: operands are resolved to absolute paths, unchanged
files (same size, mtime not newer than recorded) are never re-read, new
and changed files are hashed, and records under the scanned operands
that were not verified this run are deleted; records outside the
operands are untouched. All changes commit in a single transaction, and
WAL journaling with a busy timeout keeps a report run during a cron
scan safe.

report and trees read the database (no positional arguments); the
NUL-terminated stream format, its parser, and the malformed-record
handling are gone. The driver is modernc.org/sqlite (pure Go), so
builds keep cgo disabled.
This commit is contained in:
2026-07-24 03:08:49 +07:00
parent e0d578a707
commit d8fbcb32c2
12 changed files with 1229 additions and 379 deletions

153
report.go
View File

@@ -2,106 +2,49 @@ package main
import (
"bufio"
"bytes"
"fmt"
"io"
"os"
"slices"
"strconv"
"strings"
)
// ioBufSize is the buffer size for the buffered scan-stream reader and
// the buffered stdout writers.
// ioBufSize is the buffer size for the buffered stdout writers.
const ioBufSize = 1 << 20
// recordFieldCount is the number of tab-separated fields in a scan
// record: size, mtime, head hash, tail hash, path.
const recordFieldCount = 5
// scanInitBufSize and scanMaxRecordSize bound the scanner buffer used
// to read scan records; a record longer than scanMaxRecordSize is a
// fatal read error.
const (
scanInitBufSize = 64 << 10
scanMaxRecordSize = 4 << 20
)
// minGroupSize is the smallest number of members that makes a
// duplicate group.
const minGroupSize = 2
// scanRec is one well-formed record parsed from a scan stream. The
// signature (size, head, tail) is the duplicate key; mtime is
// informational and not retained.
// scanRec is one file record from the database. The signature (size,
// head, tail) is the duplicate key; mtime is informational only and
// used by scan for change detection.
type scanRec struct {
size int64
head string
tail string
path string
size int64
mtime int64
head string
tail string
path string
}
// openScanInput resolves the analysis-mode input: the file named by the
// single optional positional argument, or stdin when it is absent or
// "-". The returned closer must be called when reading is done.
func openScanInput(args []string) (io.Reader, string, func()) {
if len(args) == 1 && args[0] != "-" {
f, err := os.Open(args[0])
if err != nil {
fatalf("open %s: %v", args[0], err)
}
// loadRecords opens the database and reads every file record for the
// report and trees subcommands. Any database problem — including a
// missing database — is fatal.
func loadRecords() []scanRec {
dbPath := databasePath()
return f, args[0], func() { _ = f.Close() }
}
return os.Stdin, "stdin", func() {}
}
// parseScanStream reads every NUL-terminated record from in. A record
// that does not have exactly 5 fields or whose size is non-numeric is
// counted as malformed and skipped. Total records read is
// len(recs) + malformed.
func parseScanStream(in io.Reader, name string) ([]scanRec, int) {
sc := bufio.NewScanner(bufio.NewReaderSize(in, ioBufSize))
sc.Buffer(make([]byte, 0, scanInitBufSize), scanMaxRecordSize)
sc.Split(splitNUL)
var (
recs []scanRec
malformed int
)
for sc.Scan() {
// The path is the last field and may itself contain tabs,
// so split into at most recordFieldCount fields.
fields := strings.SplitN(sc.Text(), "\t", recordFieldCount)
if len(fields) != recordFieldCount {
malformed++
continue
}
size, err := strconv.ParseInt(fields[0], 10, 64)
if err != nil {
malformed++
continue
}
recs = append(recs, scanRec{
size: size,
head: fields[2],
tail: fields[3],
path: fields[4],
})
}
err := sc.Err()
db, err := openReportDatabase(dbPath)
if err != nil {
fatalf("read %s: %v", name, err)
fatalf("%v", err)
}
return recs, malformed
defer func() { _ = db.Close() }()
recs, err := loadFileRows(db)
if err != nil {
fatalf("database %s: %v", dbPath, err)
}
return recs
}
// dupeGroup is one set of candidate-duplicate files: identical size,
@@ -112,18 +55,12 @@ type dupeGroup struct {
paths []string
}
// runReport implements the report subcommand: it reads a scan stream
// from the named file (or stdin when absent or "-") and prints the
// file-level duplicates report as TSV on stdout. It never touches the
// scanned filesystem; its only I/O is the scan input, stdout, and
// stderr. args holds the positional arguments already validated by
// cobra (at most one).
func runReport(args []string) {
in, name, closer := openScanInput(args)
defer closer()
recs, malformed := parseScanStream(in, name)
records := len(recs) + malformed
// runReport implements the report subcommand: it reads every record
// from the database and prints the file-level duplicates report as TSV
// on stdout. It never touches the scanned filesystem; its only I/O is
// the database, stdout, and stderr.
func runReport() {
recs := loadRecords()
dupes := collectDupeGroups(recs)
out := bufio.NewWriterSize(os.Stdout, ioBufSize)
@@ -156,9 +93,9 @@ func runReport(args []string) {
}
fmt.Fprintf(os.Stderr,
"report: %d records read%s, %d duplicate groups, %d dupe files, %s reclaimable\n",
records, malformedNote(malformed), len(dupes), dupeFiles,
humanBytes(reclaimable))
"report: %d records read, %d duplicate groups, %d dupe files, "+
"%s reclaimable\n",
len(recs), len(dupes), dupeFiles, humanBytes(reclaimable))
}
// collectDupeGroups groups records by signature and returns every group
@@ -199,30 +136,6 @@ func collectDupeGroups(recs []scanRec) []dupeGroup {
return dupes
}
// malformedNote formats the optional malformed-record note for the
// stderr summaries.
func malformedNote(malformed int) string {
if malformed == 0 {
return ""
}
return fmt.Sprintf(" (%d malformed, skipped)", malformed)
}
// splitNUL is a bufio.SplitFunc for NUL-terminated records. Trailing
// data without a terminator at EOF is returned as a final record.
func splitNUL(data []byte, atEOF bool) (int, []byte, error) {
if i := bytes.IndexByte(data, 0); i >= 0 {
return i + 1, data[:i], nil
}
if atEOF && len(data) > 0 {
return len(data), data, nil
}
return 0, nil, nil
}
// humanBytes formats a byte count in human units (binary prefixes).
func humanBytes(n int64) string {
const unit = 1024