vaultik/internal/database/file_chunks.go

package database

import (
	"context"
	"database/sql"
	"fmt"
	"strings"

	"sneak.berlin/go/vaultik/internal/types"
)

// FileChunkRepository provides access to the file_chunks table, which maps
// files to their ordered constituent chunks.
type FileChunkRepository struct {
	db *DB
}

// NewFileChunkRepository creates a FileChunkRepository backed by db.
func NewFileChunkRepository(db *DB) *FileChunkRepository {
	return &FileChunkRepository{db: db}
}

// Create inserts a file_chunks row (idempotently), using tx when non-nil.
func (r *FileChunkRepository) Create(
	ctx context.Context, tx *sql.Tx, fc *FileChunk,
) error {
	query := `
		INSERT INTO file_chunks (file_id, idx, chunk_hash)
		VALUES (?, ?, ?)
		ON CONFLICT(file_id, idx) DO NOTHING
	`

	var err error
	if tx != nil {
		_, err = tx.ExecContext(ctx, query, fc.FileID.String(), fc.Idx, fc.ChunkHash.String())
	} else {
		_, err = r.db.ExecWithLog(ctx, query,
			fc.FileID.String(), fc.Idx, fc.ChunkHash.String())
	}

	if err != nil {
		return fmt.Errorf("inserting file_chunk: %w", err)
	}

	return nil
}

// GetByPath returns the ordered chunks of the file at the given path.
func (r *FileChunkRepository) GetByPath(
	ctx context.Context, path string,
) ([]*FileChunk, error) {
	query := `
		SELECT fc.file_id, fc.idx, fc.chunk_hash
		FROM file_chunks fc
		JOIN files f ON fc.file_id = f.id
		WHERE f.path = ?
		ORDER BY fc.idx
	`

	rows, err := r.db.conn.QueryContext(ctx, query, path)
	if err != nil {
		return nil, fmt.Errorf("querying file chunks: %w", err)
	}

	defer func() { _ = rows.Close() }()

	return r.scanFileChunks(rows)
}

// GetByFileID retrieves file chunks by file ID
func (r *FileChunkRepository) GetByFileID(
	ctx context.Context, fileID types.FileID,
) ([]*FileChunk, error) {
	query := `
		SELECT file_id, idx, chunk_hash
		FROM file_chunks
		WHERE file_id = ?
		ORDER BY idx
	`

	rows, err := r.db.conn.QueryContext(ctx, query, fileID.String())
	if err != nil {
		return nil, fmt.Errorf("querying file chunks: %w", err)
	}

	defer func() { _ = rows.Close() }()

	return r.scanFileChunks(rows)
}

// GetByPathTx retrieves file chunks within a transaction
func (r *FileChunkRepository) GetByPathTx(
	ctx context.Context, tx *sql.Tx, path string,
) ([]*FileChunk, error) {
	query := `
		SELECT fc.file_id, fc.idx, fc.chunk_hash
		FROM file_chunks fc
		JOIN files f ON fc.file_id = f.id
		WHERE f.path = ?
		ORDER BY fc.idx
	`

	LogSQL("GetByPathTx", query, path)

	rows, err := tx.QueryContext(ctx, query, path)
	if err != nil {
		return nil, fmt.Errorf("querying file chunks: %w", err)
	}

	defer func() { _ = rows.Close() }()

	fileChunks, err := r.scanFileChunks(rows)
	LogSQL("GetByPathTx", "Complete", path, "count", len(fileChunks))

	return fileChunks, err
}

// DeleteByPath deletes all file_chunks rows for the file at the given path.
func (r *FileChunkRepository) DeleteByPath(
	ctx context.Context, tx *sql.Tx, path string,
) error {
	query := `
		DELETE FROM file_chunks
		WHERE file_id = (SELECT id FROM files WHERE path = ?)
	`

	var err error
	if tx != nil {
		_, err = tx.ExecContext(ctx, query, path)
	} else {
		_, err = r.db.ExecWithLog(ctx, query, path)
	}

	if err != nil {
		return fmt.Errorf("deleting file chunks: %w", err)
	}

	return nil
}

// DeleteByFileID deletes all chunks for a file by its UUID
func (r *FileChunkRepository) DeleteByFileID(
	ctx context.Context, tx *sql.Tx, fileID types.FileID,
) error {
	query := `DELETE FROM file_chunks WHERE file_id = ?`

	var err error
	if tx != nil {
		_, err = tx.ExecContext(ctx, query, fileID.String())
	} else {
		_, err = r.db.ExecWithLog(ctx, query, fileID.String())
	}

	if err != nil {
		return fmt.Errorf("deleting file chunks: %w", err)
	}

	return nil
}

// DeleteByFileIDs deletes all chunks for multiple files in a single statement.
//
//nolint:dupl // symmetric implementation for a parallel association table
func (r *FileChunkRepository) DeleteByFileIDs(
	ctx context.Context, tx *sql.Tx, fileIDs []types.FileID,
) error {
	if len(fileIDs) == 0 {
		return nil
	}

	// Batch at 500 to stay within SQLite's variable limit
	const batchSize = 500

	for i := 0; i < len(fileIDs); i += batchSize {
		end := min(i+batchSize, len(fileIDs))

		batch := fileIDs[i:end]

		//nolint:gosec // G202: concatenates constant SQL and "?" placeholders only
		query := "DELETE FROM file_chunks WHERE file_id IN (?" +
			repeatPlaceholder(len(batch)-1) + ")"

		args := make([]any, len(batch))
		for j, id := range batch {
			args[j] = id.String()
		}

		var err error
		if tx != nil {
			_, err = tx.ExecContext(ctx, query, args...)
		} else {
			_, err = r.db.ExecWithLog(ctx, query, args...)
		}

		if err != nil {
			return fmt.Errorf("batch deleting file_chunks: %w", err)
		}
	}

	return nil
}

// CreateBatch inserts multiple file_chunks in a single statement for efficiency.
// Batches are automatically split to stay within SQLite's variable limit.
func (r *FileChunkRepository) CreateBatch(
	ctx context.Context, tx *sql.Tx, fcs []FileChunk,
) error {
	if len(fcs) == 0 {
		return nil
	}

	// Each file_chunks row binds this many SQL variables.
	const fileChunkCols = 3

	// SQLite has a limit on variables (typically 999 or 32766), so batch
	// at 300 rows to be safe.
	const batchSize = 300

	for i := 0; i < len(fcs); i += batchSize {
		end := min(i+batchSize, len(fcs))

		batch := fcs[i:end]

		// Build the query with multiple value sets
		query := "INSERT INTO file_chunks (file_id, idx, chunk_hash) VALUES "

		args := make([]any, 0, len(batch)*fileChunkCols)

		var querySb211 strings.Builder

		for j, fc := range batch {
			if j > 0 {
				querySb211.WriteString(", ")
			}

			querySb211.WriteString("(?, ?, ?)")

			args = append(args, fc.FileID.String(), fc.Idx, fc.ChunkHash.String())
		}

		query += querySb211.String()

		query += " ON CONFLICT(file_id, idx) DO NOTHING"

		var err error
		if tx != nil {
			_, err = tx.ExecContext(ctx, query, args...)
		} else {
			_, err = r.db.ExecWithLog(ctx, query, args...)
		}

		if err != nil {
			return fmt.Errorf("batch inserting file_chunks: %w", err)
		}
	}

	return nil
}

// GetByFile is an alias for GetByPath for compatibility
func (r *FileChunkRepository) GetByFile(
	ctx context.Context, path string,
) ([]*FileChunk, error) {
	LogSQL("GetByFile", "Starting", path)
	result, err := r.GetByPath(ctx, path)
	LogSQL("GetByFile", "Complete", path, "count", len(result))

	return result, err
}

// GetByFileTx retrieves file chunks within a transaction
func (r *FileChunkRepository) GetByFileTx(
	ctx context.Context, tx *sql.Tx, path string,
) ([]*FileChunk, error) {
	LogSQL("GetByFileTx", "Starting", path)
	result, err := r.GetByPathTx(ctx, tx, path)
	LogSQL("GetByFileTx", "Complete", path, "count", len(result))

	return result, err
}

// scanFileChunks is a helper that scans file chunk rows
func (r *FileChunkRepository) scanFileChunks(rows *sql.Rows) ([]*FileChunk, error) {
	var fileChunks []*FileChunk

	for rows.Next() {
		var (
			fc                      FileChunk
			fileIDStr, chunkHashStr string
		)

		err := rows.Scan(&fileIDStr, &fc.Idx, &chunkHashStr)
		if err != nil {
			return nil, fmt.Errorf("scanning file chunk: %w", err)
		}

		fc.FileID, err = types.ParseFileID(fileIDStr)
		if err != nil {
			return nil, fmt.Errorf("parsing file ID: %w", err)
		}

		fc.ChunkHash = types.ChunkHash(chunkHashStr)
		fileChunks = append(fileChunks, &fc)
	}

	return fileChunks, rows.Err()
}