Add sfdupes info: show the database's details (closes #117)
check / check (push) Canceled after 0s

info prints the database's path and source, the sizes of the database
file and its -wal file, when the database file last changed, the schema
version and the record counts, one per line as a name, a tab and the
value. It opens the database as report does and shows an open and a
count phase on stderr. The schema version and the counts come from one
read-only transaction, the counts from one query.

seedDatabase now closes test databases out of WAL mode, as scan does;
otherwise info's own connection creates an empty -wal file. The open
phase's name and text became constants for the linter, and the scan
command moved to newScanCommand to keep newRootCommand short enough.

Judgement call: the lines are written after the last display ends, so they skip the display's stdout writer.

Model: opus-5-5
This commit was merged in pull request #123.
This commit is contained in:
2026-10-16 22:41:16 +02:00
parent ebe4d4dbeb
commit e9e09effc6
11 changed files with 540 additions and 89 deletions
+62 -7
View File
@@ -79,7 +79,8 @@ ON CONFLICT (path) DO UPDATE SET
content = excluded.content
`
// errNoDatabase reports a missing database file for report/trees.
// errNoDatabase reports a missing database file for report, trees and
// info.
var errNoDatabase = errors.New(
"no database (run \"sfdupes scan\" first, or set " + databaseEnv + ")")
@@ -131,9 +132,9 @@ const scanParams = "_pragma=busy_timeout(10000)" +
"&_pragma=journal_mode(WAL)" +
"&_pragma=synchronous(NORMAL)"
// reportParams are the connection parameters for report and trees:
// read-only, with the same busy timeout. They set no journal mode,
// because setting one is a write.
// reportParams are the connection parameters for report, trees and
// info: read-only, with the same busy timeout. They set no journal
// mode, because setting one is a write.
const reportParams = "mode=ro" +
"&_pragma=busy_timeout(10000)" +
"&_pragma=query_only(1)"
@@ -262,9 +263,9 @@ func closeScanDatabase(ctx context.Context, db *sql.DB, path string) {
_ = db.Close()
}
// openReportDatabase opens an existing database for the report and
// trees subcommands. A missing database file is an error directing the
// user to run scan first; the schema version must match exactly.
// openReportDatabase opens an existing database for the report, trees
// and info subcommands. A missing database file is an error directing
// the user to run scan first; the schema version must match exactly.
func openReportDatabase(ctx context.Context,
path string,
) (*sql.DB, error) {
@@ -545,6 +546,60 @@ func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
return n, nil
}
// databaseCountsSQL counts the records, those with head and tail
// hashes and those with a content hash, and adds up their sizes, in one
// pass over the table. A SUM over no rows is NULL, so on an empty table
// each SUM falls back to 0.
const databaseCountsSQL = `
SELECT COUNT(*),
COALESCE(SUM(head <> '' AND tail <> ''), 0),
COALESCE(SUM(content <> ''), 0),
COALESCE(SUM(size), 0)
FROM files
`
// databaseCounts is what info reads from the database: its schema
// version and the counts of databaseCountsSQL.
type databaseCounts struct {
schemaVersion int
records int64 // every record
headTail int64 // records with head and tail hashes
content int64 // records with a content hash
size int64 // the sizes of all records added up
}
// readDatabaseCounts reads the schema version, then the counts of
// databaseCountsSQL, in one read-only transaction, so both describe the
// database at one moment while a scan is committing.
func readDatabaseCounts(ctx context.Context,
db *sql.DB,
) (databaseCounts, error) {
var c databaseCounts
// Everything goes through tx: the report connection is the only
// one, so a query on db would wait for tx forever.
tx, err := db.BeginTx(ctx, &sql.TxOptions{ReadOnly: true})
if err != nil {
return c, fmt.Errorf("count records: %w", err)
}
defer func() { _ = tx.Rollback() }()
err = tx.QueryRowContext(ctx, "PRAGMA user_version").
Scan(&c.schemaVersion)
if err != nil {
return c, fmt.Errorf("read schema version: %w", err)
}
err = tx.QueryRowContext(ctx, databaseCountsSQL).
Scan(&c.records, &c.headTail, &c.content, &c.size)
if err != nil {
return c, fmt.Errorf("count records: %w", err)
}
return c, nil
}
// loadFileMeta streams every record's path, size, mtime, and whether
// it carries hashes to fn. Scan change detection needs no hash
// values, and skipping the hash columns keeps the scan's in-memory