nwenc

README

nwenc

Package nwenc is the implementation of encoder and decoder for the nextword data.

OffsetEncoder/OffsetDecoder

The OffsetEncoder and OffsetDecoder can encode/decode between an int64 offset value and a string. There are several implementation for OffsetMapper. They have different performance.

OffsetEncoder/OffsetDecoder example:

f, err := os.Open(filepath.Join("testdata", "words.txt"))
om, err := NewAllReadOffsetMapper(f)

om.OffsetEncode("a")   // 0 ("a" is at 0 byte in testdata/words.txt)
om.OffsetEncode("bcd") // 43 ("bcd" is at 43 bytes in testdata/words.txt)

om.OffsetDecode(0)  // "a"
om.OffsetDecode(43) // "bcd"

Encoder/Decoder

Encoder and Decoder can encode/decode bwtween an int64 offset value and bytes. Encoder/Decoder example:

f, err := os.Open(filepath.Join("testdata", "words.txt"))
om, err := NewAllReadOffsetMapper(f)

buf := new(bytes.Buffer)

byteLen := 3 // It encodes/decodes 3 bytes (24 bits) data.
enc, err := NewEncoder(byteLen)

enc.Encode(buf, 0)               // writes "a" at offset == 0
enc.EncodeString(buf, om, "bcd") // writes "bcd"

dec, err := NewDecoder(byteLen)

dec.Decode(buf)           // 0 ("a")
dec.DecodeString(buf, om) // "bcd"

Documentation

Overview

Package nwenc is the implementation of encoder and decoder for the nextword data.

The OffsetEncoder and OffsetDecoder can encode/decode between an int64 offset value and a string. The offset means the byte offset in a file that the string appears. There are several implementation for OffsetMapper. They have different performance.

Encoder and Decoder can encode/decode between an int64 offset value and bytes.

OffsetEncoder/OffsetDecoder example:

f, err := os.Open(filepath.Join("testdata", "words.txt"))
om, err := NewAllReadOffsetMapper(f)

om.OffsetEncode("a")   // 0 ("a" is at 0 byte in testdata/words.txt)
om.OffsetEncode("bcd") // 43 ("bcd" is at 43 bytes in testdata/words.txt)

om.OffsetDecode(0)  // "a"
om.OffsetDecode(43) // "bcd"

Encoder/Decoder example:

f, err := os.Open(filepath.Join("testdata", "words.txt"))
om, err := NewAllReadOffsetMapper(f)

buf := new(bytes.Buffer)

byteLen := 3 // It encodes/decodes 3 bytes (24 bits) data.
enc, err := NewEncoder(byteLen)

enc.Encode(buf, 0)               // writes "a" at offset == 0
enc.EncodeString(buf, om, "bcd") // writes "bcd"

dec, err := NewDecoder(byteLen)

dec.Decode(buf)           // 0 ("a")
dec.DecodeString(buf, om) // "bcd"

Index

• type AllReadOffsetMapper
  • func NewAllReadOffsetMapper(r io.Reader) (*AllReadOffsetMapper, error)
  • func (m *AllReadOffsetMapper) OffsetDecode(offset int64) (s string, err error)
  • func (m *AllReadOffsetMapper) OffsetEncode(s string) (offset int64, err error)
• type CachedSeekOffsetMapper
  • func NewCachedSeekOffsetMapper(r io.ReaderAt, size int64) *CachedSeekOffsetMapper
  • func (om *CachedSeekOffsetMapper) OffsetDecode(offset int64) (s string, err error)
  • func (om *CachedSeekOffsetMapper) OffsetEncode(s string) (offset int64, err error)
• type Decoder
  • func NewDecoder(byteLen int) (*Decoder, error)
  • func (d *Decoder) Decode(r io.Reader) (offset int64, err error)
  • func (d *Decoder) DecodeString(r io.Reader, od OffsetDecoder) (s string, err error)
• type Encoder
  • func NewEncoder(byteLen int) (*Encoder, error)
  • func (e *Encoder) Encode(w io.Writer, offset int64) error
  • func (e *Encoder) EncodeString(w io.Writer, oe OffsetEncoder, s string) error
• type OffsetDecodeError
  • func (e *OffsetDecodeError) Error() string
• type OffsetDecoder
• type OffsetEncodeError
  • func (e *OffsetEncodeError) Error() string
• type OffsetEncoder
• type OffsetMapper
• type SeekOffsetMapper
  • func NewSeekOffsetMapper(r io.ReaderAt, size int64) *SeekOffsetMapper
  • func (om *SeekOffsetMapper) OffsetDecode(offset int64) (s string, err error)
  • func (om *SeekOffsetMapper) OffsetEncode(s string) (offset int64, err error)

Types

type AllReadOffsetMapper

type AllReadOffsetMapper struct {
	// contains filtered or unexported fields
}

AllReadOffsetMapper is one of the implementation of OffsetMapper. It reads all of io.Reader in advance in order to map fast.

func NewAllReadOffsetMapper

func NewAllReadOffsetMapper(r io.Reader) (*AllReadOffsetMapper, error)

NewAllReadOffsetMapper returns an AllReadOffsetMapper. This function reads all of io.Reader in advance in order to map fast.

func (*AllReadOffsetMapper) OffsetDecode

func (m *AllReadOffsetMapper) OffsetDecode(offset int64) (s string, err error)

OffsetDecode is the implementation of OffsetDecode. It works fast. When offset is not found, it will return OffsetDecodeError.

func (*AllReadOffsetMapper) OffsetEncode

func (m *AllReadOffsetMapper) OffsetEncode(s string) (offset int64, err error)

OffsetEncode is the implementation of OffsetEncoder. It works fast. When s is not found, it will return OffsetEncodeError.

type CachedSeekOffsetMapper

type CachedSeekOffsetMapper struct {
	// contains filtered or unexported fields
}

CachedSeekOffsetMapper is the implementation of OffsetMapper. It seeks io.ReaderAt when methods are called, but caches the results. It's takes shorter time rather than SeekOffsetMapper.

func NewCachedSeekOffsetMapper

func NewCachedSeekOffsetMapper(r io.ReaderAt, size int64) *CachedSeekOffsetMapper

NewCachedSeekOffsetMapper returns a CachedSeekOffsetMapper. The size is total bytes of r. It seeks io.ReaderAt when methods are called, but caches the results. It's takes shorter time rather than SeekOffsetMapper.

func (*CachedSeekOffsetMapper) OffsetDecode

func (om *CachedSeekOffsetMapper) OffsetDecode(offset int64) (s string, err error)

OffsetDecode is the implementation of OffsetDecoder.

func (*CachedSeekOffsetMapper) OffsetEncode

func (om *CachedSeekOffsetMapper) OffsetEncode(s string) (offset int64, err error)

OffsetEncode is the implementation of OffsetEncoder. This method makes cache when it is called.

type Decoder

type Decoder struct {
	// contains filtered or unexported fields
}

Decoder decodes bytes to an int64 or a string.

func NewDecoder

func NewDecoder(byteLen int) (*Decoder, error)

NewDecoder returns Decoder. The byteLen is the length of bytes. The byteLen must be 1 <= bytelen <= 8.

func (*Decoder) Decode

func (d *Decoder) Decode(r io.Reader) (offset int64, err error)

Decode reads r and decodes to the offset.

func (*Decoder) DecodeString

func (d *Decoder) DecodeString(r io.Reader, od OffsetDecoder) (s string, err error)

DecodeString reads r and decodes to s.

type Encoder

type Encoder struct {
	// contains filtered or unexported fields
}

Encoder encodes an int64 to bytes.

func NewEncoder

func NewEncoder(byteLen int) (*Encoder, error)

NewEncoder returns an Encoder. The byteLen is the length of encoded bytes. The byteLen must be 1 <= byteLen <= 8.

func (*Encoder) Encode

func (e *Encoder) Encode(w io.Writer, offset int64) error

Encode encodes offset to bytes and writes it to w.

func (*Encoder) EncodeString

func (e *Encoder) EncodeString(w io.Writer, oe OffsetEncoder, s string) error

EncodeString encodes s to bytes and writes it to w.

type OffsetDecodeError

type OffsetDecodeError struct {
	// contains filtered or unexported fields
}

OffsetDecodeError is returned when OffsetDecode fails.

func (*OffsetDecodeError) Error

func (e *OffsetDecodeError) Error() string

type OffsetDecoder

type OffsetDecoder interface {
	OffsetDecode(offset int64) (s string, err error)
}

OffsetDecoder is the interface which can map an int64 offset to a string. The offset is the offset where the string appears in a text file.

type OffsetEncodeError

type OffsetEncodeError struct {
	// contains filtered or unexported fields
}

OffsetEncodeError is returned when OffsetEncode fails.

func (*OffsetEncodeError) Error

func (e *OffsetEncodeError) Error() string

type OffsetEncoder

type OffsetEncoder interface {
	OffsetEncode(s string) (offset int64, err error)
}

OffsetEncoder is the interface which can map a string to an int64 offset. The offset is the offset where the string appears in a text file.

type OffsetMapper

type OffsetMapper interface {
	OffsetEncoder
	OffsetDecoder
}

OffsetMapper implements both OffsetEncoder and OffsetDecoder.

type SeekOffsetMapper

type SeekOffsetMapper struct {
	// contains filtered or unexported fields
}

SeekOffsetMapper is the implementation of OffsetMapper. It seeks file each time when OffsetEncode or OffsetDecode are called, so it works slowly.

func NewSeekOffsetMapper

func NewSeekOffsetMapper(r io.ReaderAt, size int64) *SeekOffsetMapper

NewSeekOffsetMapper returns an NewSeekOffsetMapper. The size is the total bytes of r. It seeks file each time when OffsetEncode or OffsetDecode are called, so it works slowly.

func (*SeekOffsetMapper) OffsetDecode

func (om *SeekOffsetMapper) OffsetDecode(offset int64) (s string, err error)

OffsetDecode is the implementation of OffsetDecoder. This function works slow because it needs io.ReadAt seeking each time.

func (*SeekOffsetMapper) OffsetEncode

func (om *SeekOffsetMapper) OffsetEncode(s string) (offset int64, err error)

OffsetEncode is the implementation of OffsetEncoder. This function works slow because it needs io.ReadAt seeking each time.