Store each hash as its raw 32 bytes in a BLOB column (closes #134)

The head, tail and content columns of the files table are BLOB NOT
NULL and hold the raw 32-byte SHA-256, half the size of the hex text,
in the table and in the files_signature index. The hash phase, the
records, report and trees carry each hash as a [sha256.Size]byte and
compare it with ==; nothing is hex-encoded. Reading a record whose
hash column is not 32 bytes is an error naming its path.

In the tests, testHash is a stand-in hash: a string's bytes padded
with zeros, so fixtures keep the sort order their strings give.

Judgement call: a hash of the wrong length is refused on reading,
not copied silently.

Model: opus-5-5

db.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"crypto/sha256"
 	"database/sql"
 	"errors"
 	"fmt"
@@ -48,16 +49,17 @@ const lockFilePerm = 0o600
 // createTableSQL is the schema applied to a fresh database. Paths are
 // BLOBs because Unix paths are raw bytes, not guaranteed UTF-8. mtime
 // holds whole Unix seconds and mtime_nsec the nanoseconds within that
-// second.
+// second. head, tail and content each hold the raw 32 bytes of a
+// SHA-256.
 const createTableSQL = `
 CREATE TABLE files (
     path       BLOB PRIMARY KEY,
     size       INTEGER NOT NULL,
     mtime      INTEGER NOT NULL,
     mtime_nsec INTEGER NOT NULL,
-    head       TEXT NOT NULL,
-    tail       TEXT NOT NULL,
-    content    TEXT NOT NULL
+    head       BLOB NOT NULL,
+    tail       BLOB NOT NULL,
+    content    BLOB NOT NULL
 ) WITHOUT ROWID
 `
 
@@ -92,6 +94,10 @@ var errSchemaVersion = errors.New("unsupported database schema version")
 // database.
 var errScanRunning = errors.New("another scan is running")
 
+// errHashSize reports a record whose head, tail or content is not the
+// 32 bytes of a SHA-256.
+var errHashSize = errors.New("hash is not 32 bytes")
+
 // databasePath resolves the database location: SFDUPES_DATABASE when
 // set and non-empty, the compiled-in default otherwise. It returns the
 // path, with the working directory, its symlinks resolved, put in front
@@ -492,19 +498,24 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 
 	for rows.Next() {
 		var (
-			path      []byte
-			sec, nsec int64
-			r         scanRec
+			path, head, tail, content []byte
+			sec, nsec                 int64
+			r                         scanRec
 		)
 
-		err = rows.Scan(&path, &r.size, &sec, &nsec, &r.head, &r.tail,
-			&r.content)
+		err = rows.Scan(&path, &r.size, &sec, &nsec, &head, &tail, &content)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
 		r.path = string(path)
 		r.mtime = time.Unix(sec, nsec)
+
+		err = r.setHashes(head, tail, content)
+		if err != nil {
+			return fmt.Errorf("read record %s: %w", escapePath(r.path), err)
+		}
+
 		fn(r)
 	}
 
@@ -561,17 +572,22 @@ func loadSignatureRows(ctx context.Context, db *sql.DB,
 
 	for rows.Next() {
 		var (
-			path []byte
-			r    scanRec
+			path, head, tail, content []byte
+			r                         scanRec
 		)
 
-		err = rows.Scan(&r.size, &r.head, &r.tail, &r.content, &path)
+		err = rows.Scan(&r.size, &head, &tail, &content, &path)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
 		r.path = string(path)
 
+		err = r.setHashes(head, tail, content)
+		if err != nil {
+			return fmt.Errorf("read record %s: %w", escapePath(r.path), err)
+		}
+
 		err = fn(r)
 		if err != nil {
 			return err
@@ -586,6 +602,22 @@ func loadSignatureRows(ctx context.Context, db *sql.DB,
 	return nil
 }
 
+// setHashes sets r's head, tail and content to the values read from
+// those columns. Each must be the raw 32 bytes of a SHA-256.
+func (r *scanRec) setHashes(head, tail, content []byte) error {
+	for _, b := range [][]byte{head, tail, content} {
+		if len(b) != sha256.Size {
+			return fmt.Errorf("%w: found %d bytes", errHashSize, len(b))
+		}
+	}
+
+	r.head = [sha256.Size]byte(head)
+	r.tail = [sha256.Size]byte(tail)
+	r.content = [sha256.Size]byte(content)
+
+	return nil
+}
+
 // countRecords returns the number of records in the database.
 func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
 	var n int64
@@ -756,7 +788,8 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
 
 	for _, r := range upserts {
 		_, err = st.ExecContext(ctx, []byte(r.path), r.size,
-			r.mtime.Unix(), r.mtime.Nanosecond(), r.head, r.tail, r.content)
+			r.mtime.Unix(), r.mtime.Nanosecond(),
+			r.head[:], r.tail[:], r.content[:])
 		if err != nil {
 			return fmt.Errorf("upsert %s: %w", r.path, err)
 		}