package wal

import (
	"bytes"
	"errors"
	"fmt"
	"os"
)

// TailCorruptionError indicates that the WAL tail contains corrupt data
// (bad CRC, unexpected non-zero padding bytes, etc.). Recovery may safely
// truncate at the last valid record.
type TailCorruptionError struct {
	Offset int
	Err    error
}

func (e *TailCorruptionError) Error() string {
	return fmt.Sprintf("wal: tail corruption at offset %d: %v", e.Offset, e.Err)
}

func (e *TailCorruptionError) Unwrap() error {
	return e.Err
}

// IsTailCorruption reports whether err indicates tail corruption in a WAL
// segment. Callers may safely truncate the segment at the last valid record.
func IsTailCorruption(err error) bool {
	var tce *TailCorruptionError
	return errors.As(err, &tce)
}

// ParseBlock parses physical records from a single block of raw bytes.
// The block is typically WalBlockSize (32 KB) bytes, but the last block of a
// segment may be shorter. Trailing bytes after the last record must be all
// zeros (padding); non-zero trailing bytes produce a TailCorruptionError.
func ParseBlock(data []byte) ([]*PhysicalRecord, error) {
	var records []*PhysicalRecord
	pos := 0

	for pos < len(data) {
		remaining := len(data) - pos

		// If fewer than PhysicalRecordHeaderSize bytes remain, they must be
		// zero-padding.
		if remaining < PhysicalRecordHeaderSize {
			tail := data[pos:]
			if !isAllZeros(tail) {
				return records[:len(records):len(records)], &TailCorruptionError{
					Offset: pos,
					Err:    fmt.Errorf("non-zero padding bytes in tail (%d bytes)", len(tail)),
				}
			}
			break
		}

		// Check for zero-filled header (preallocated / unwritten space).
		if isAllZeros(data[pos : pos+PhysicalRecordHeaderSize]) {
			// Verify rest of block is also zeros.
			if !isAllZeros(data[pos:]) {
				return records[:len(records):len(records)], &TailCorruptionError{
					Offset: pos,
					Err:    errors.New("zero header but non-zero bytes follow"),
				}
			}
			break
		}

		rec, consumed, err := DecodePhysicalRecord(data[pos:])
		if err != nil {
			return records[:len(records):len(records)], &TailCorruptionError{
				Offset: pos,
				Err:    err,
			}
		}
		records = append(records, rec)
		pos += consumed
	}

	return records, nil
}

// ParseRecordsFromFile opens a WAL segment file, skips the file header, reads
// blocks sequentially, and returns all physical records in order. Short final
// blocks are handled correctly.
func ParseRecordsFromFile(filePath string) ([]*PhysicalRecord, error) {
	f, err := os.Open(filePath)
	if err != nil {
		return nil, fmt.Errorf("wal: parse records: %w", err)
	}
	defer f.Close()

	// Skip file header.
	if _, err := f.Seek(WalFileHeaderSize, 0); err != nil {
		return nil, fmt.Errorf("wal: seek past header: %w", err)
	}

	var allRecords []*PhysicalRecord
	buf := make([]byte, WalBlockSize)

	for {
		n, readErr := f.Read(buf)
		if readErr != nil {
			if errors.Is(readErr, os.ErrClosed) {
				return nil, fmt.Errorf("wal: file closed during read: %w", readErr)
			}
			break
		}
		if n == 0 {
			break
		}

		blockData := buf[:n]
		recs, err := ParseBlock(blockData)
		if err != nil {
			// Return records collected so far along with the error.
			return allRecords, err
		}
		allRecords = append(allRecords, recs...)

		// If we got a short block, this was the last one.
		if n < WalBlockSize {
			break
		}
	}

	return allRecords, nil
}

func isAllZeros(data []byte) bool {
	return bytes.Count(data, []byte{0}) == len(data)
}