chardet

Documentation

Overview

Package chardet ports character set detection from ICU.

Index

• Variables
• func DecodeFromCharset(input []byte, charset string) ([]byte, error)
• func EncodeToCharset(input []byte, charset string) ([]byte, error)
• func NewReader(r io.Reader, charset string) io.Reader
• func NewWriter(w io.Writer, charset string) io.Writer
• type Detector
  • func NewHtmlDetector() *Detector
  • func NewTextDetector() *Detector
  • func (d *Detector) DetectAll(b []byte) ([]Result, error)
  • func (d *Detector) DetectBest(b []byte) (r *Result, err error)
• type Result

Variables

var (
	ErrEndOfInputBuffer = errors.New("end of input buffer")
	ErrBadCharDecode    = errors.New("decode a bad char")
)

var (
	ErrNotDetected = errors.New("charset not detected")
)

Functions

func DecodeFromCharset

func DecodeFromCharset(input []byte, charset string) ([]byte, error)

DecodeFromCharset decode input to utf8

func EncodeToCharset

func EncodeToCharset(input []byte, charset string) ([]byte, error)

EncodeToCharset encode input to charset

func NewReader

func NewReader(r io.Reader, charset string) io.Reader

NewReader: convert text from other encodings to UTF-8

func NewWriter

func NewWriter(w io.Writer, charset string) io.Writer

NewWriter: convert UTF-8 encoding to other encodings

Types

type Detector

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

Detector implements charset detection.

func NewHtmlDetector

func NewHtmlDetector() *Detector

NewHtmlDetector creates a Detector for Html.

func NewTextDetector

func NewTextDetector() *Detector

NewTextDetector creates a Detector for plain text.

func (*Detector) DetectAll

func (d *Detector) DetectAll(b []byte) ([]Result, error)

DetectAll returns all Results which have non-zero Confidence. The Results are sorted by Confidence in descending order.

func (*Detector) DetectBest

func (d *Detector) DetectBest(b []byte) (r *Result, err error)

DetectBest returns the Result with highest Confidence.

type Result

type Result struct {
	// IANA name of the detected charset.
	Charset string
	// IANA name of the detected language. It may be empty for some charsets.
	Language string
	// Confidence of the Result. Scale from 1 to 100. The bigger, the more confident.
	Confidence int
}

Result contains all the information that charset detector gives.