| // Package zstd provides decompression of zstandard files. |
| // |
| // For advanced usage and examples, go to the README: https://github.com/klauspost/compress/tree/master/zstd#zstd |
| package zstd |
| |
| import ( |
| "errors" |
| "log" |
| "math/bits" |
| ) |
| |
| const debug = false |
| const debugSequences = false |
| const debugMatches = false |
| |
| // force encoder to use predefined tables. |
| const forcePreDef = false |
| |
| // zstdMinMatch is the minimum zstd match length. |
| const zstdMinMatch = 3 |
| |
| var ( |
| // ErrReservedBlockType is returned when a reserved block type is found. |
| // Typically this indicates wrong or corrupted input. |
| ErrReservedBlockType = errors.New("invalid input: reserved block type encountered") |
| |
| // ErrCompressedSizeTooBig is returned when a block is bigger than allowed. |
| // Typically this indicates wrong or corrupted input. |
| ErrCompressedSizeTooBig = errors.New("invalid input: compressed size too big") |
| |
| // ErrBlockTooSmall is returned when a block is too small to be decoded. |
| // Typically returned on invalid input. |
| ErrBlockTooSmall = errors.New("block too small") |
| |
| // ErrMagicMismatch is returned when a "magic" number isn't what is expected. |
| // Typically this indicates wrong or corrupted input. |
| ErrMagicMismatch = errors.New("invalid input: magic number mismatch") |
| |
| // ErrWindowSizeExceeded is returned when a reference exceeds the valid window size. |
| // Typically this indicates wrong or corrupted input. |
| ErrWindowSizeExceeded = errors.New("window size exceeded") |
| |
| // ErrWindowSizeTooSmall is returned when no window size is specified. |
| // Typically this indicates wrong or corrupted input. |
| ErrWindowSizeTooSmall = errors.New("invalid input: window size was too small") |
| |
| // ErrDecoderSizeExceeded is returned if decompressed size exceeds the configured limit. |
| ErrDecoderSizeExceeded = errors.New("decompressed size exceeds configured limit") |
| |
| // ErrUnknownDictionary is returned if the dictionary ID is unknown. |
| // For the time being dictionaries are not supported. |
| ErrUnknownDictionary = errors.New("unknown dictionary") |
| |
| // ErrFrameSizeExceeded is returned if the stated frame size is exceeded. |
| // This is only returned if SingleSegment is specified on the frame. |
| ErrFrameSizeExceeded = errors.New("frame size exceeded") |
| |
| // ErrCRCMismatch is returned if CRC mismatches. |
| ErrCRCMismatch = errors.New("CRC check failed") |
| |
| // ErrDecoderClosed will be returned if the Decoder was used after |
| // Close has been called. |
| ErrDecoderClosed = errors.New("decoder used after Close") |
| ) |
| |
| func println(a ...interface{}) { |
| if debug { |
| log.Println(a...) |
| } |
| } |
| |
| func printf(format string, a ...interface{}) { |
| if debug { |
| log.Printf(format, a...) |
| } |
| } |
| |
| // matchLen returns the maximum length. |
| // a must be the shortest of the two. |
| // The function also returns whether all bytes matched. |
| func matchLen(a, b []byte) int { |
| b = b[:len(a)] |
| for i := 0; i < len(a)-7; i += 8 { |
| if diff := load64(a, i) ^ load64(b, i); diff != 0 { |
| return i + (bits.TrailingZeros64(diff) >> 3) |
| } |
| } |
| checked := (len(a) >> 3) << 3 |
| a = a[checked:] |
| b = b[checked:] |
| // TODO: We could do a 4 check. |
| for i := range a { |
| if a[i] != b[i] { |
| return int(i) + checked |
| } |
| } |
| return len(a) + checked |
| } |
| |
| // matchLen returns a match length in src between index s and t |
| func matchLenIn(src []byte, s, t int32) int32 { |
| s1 := len(src) |
| b := src[t:] |
| a := src[s:s1] |
| b = b[:len(a)] |
| // Extend the match to be as long as possible. |
| for i := range a { |
| if a[i] != b[i] { |
| return int32(i) |
| } |
| } |
| return int32(len(a)) |
| } |
| |
| func load3232(b []byte, i int32) uint32 { |
| // Help the compiler eliminate bounds checks on the read so it can be done in a single read. |
| b = b[i:] |
| b = b[:4] |
| return uint32(b[0]) | uint32(b[1])<<8 | uint32(b[2])<<16 | uint32(b[3])<<24 |
| } |
| |
| func load6432(b []byte, i int32) uint64 { |
| // Help the compiler eliminate bounds checks on the read so it can be done in a single read. |
| b = b[i:] |
| b = b[:8] |
| return uint64(b[0]) | uint64(b[1])<<8 | uint64(b[2])<<16 | uint64(b[3])<<24 | |
| uint64(b[4])<<32 | uint64(b[5])<<40 | uint64(b[6])<<48 | uint64(b[7])<<56 |
| } |
| |
| func load64(b []byte, i int) uint64 { |
| // Help the compiler eliminate bounds checks on the read so it can be done in a single read. |
| b = b[i:] |
| b = b[:8] |
| return uint64(b[0]) | uint64(b[1])<<8 | uint64(b[2])<<16 | uint64(b[3])<<24 | |
| uint64(b[4])<<32 | uint64(b[5])<<40 | uint64(b[6])<<48 | uint64(b[7])<<56 |
| } |