package xml

import "github.com/tdewolff/parse/v2/xml"

Package xml is an XML1.0 lexer following the specifications at http://www.w3.org/TR/xml/.

Index ¶

• Variables
• func EscapeAttrVal(buf *[]byte, b []byte) []byte
• func EscapeCDATAVal(buf *[]byte, b []byte) ([]byte, bool)
• type Lexer
• func NewLexer(r io.Reader) *Lexer
• func (l *Lexer) AttrVal() []byte
• func (l *Lexer) Err() error
• func (l *Lexer) Next() (TokenType, []byte)
• func (l *Lexer) Offset() int
• func (l *Lexer) Restore()
• func (l *Lexer) Text() []byte
• type TokenType
• func (tt TokenType) String() string

Examples ¶

• NewLexer

Variables ¶

var EntitiesMap = map[string][]byte{
	"apos": []byte("'"),
	"gt":   []byte(">"),
	"quot": []byte("\""),
}

Entities are all named character entities.

Functions ¶

func EscapeAttrVal ¶

func EscapeAttrVal(buf *[]byte, b []byte) []byte

EscapeAttrVal returns the escape attribute value bytes without quotes.

func EscapeCDATAVal ¶

func EscapeCDATAVal(buf *[]byte, b []byte) ([]byte, bool)

EscapeCDATAVal returns the escaped text bytes.

Types ¶

type Lexer ¶

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

Lexer is the state for the lexer.

func NewLexer ¶

func NewLexer(r io.Reader) *Lexer

NewLexer returns a new Lexer for a given io.Reader.

{
	l := NewLexer(bytes.NewBufferString("<span class='user'>John Doe</span>"))
	out := ""
	for {
		tt, data := l.Next()
		if tt == ErrorToken {
			break
		}
		out += string(data)
	}
	fmt.Println(out)
	// Output: <span class='user'>John Doe</span>
}

<span class='user'>John Doe</span>

func (*Lexer) AttrVal ¶

func (l *Lexer) AttrVal() []byte

AttrVal returns the attribute value when an AttributeToken was returned from Next.

func (*Lexer) Err ¶

func (l *Lexer) Err() error

Err returns the error encountered during lexing, this is often io.EOF but also other errors can be returned.

func (*Lexer) Next ¶

func (l *Lexer) Next() (TokenType, []byte)

Next returns the next Token. It returns ErrorToken when an error was encountered. Using Err() one can retrieve the error message.

func (*Lexer) Offset ¶

func (l *Lexer) Offset() int

Offset returns the current position in the input stream.

func (*Lexer) Restore ¶

func (l *Lexer) Restore()

Restore restores the NULL byte at the end of the buffer.

func (*Lexer) Text ¶

func (l *Lexer) Text() []byte

Text returns the textual representation of a token. This excludes delimiters and additional leading/trailing characters.

type TokenType ¶

type TokenType uint32

TokenType determines the type of token, eg. a number or a semicolon.

const (
	ErrorToken TokenType = iota // extra token when errors occur
	CommentToken
	DOCTYPEToken
	CDATAToken
	StartTagToken
	StartTagPIToken
	StartTagCloseToken
	StartTagCloseVoidToken
	StartTagClosePIToken
	EndTagToken
	AttributeToken
	TextToken
)

TokenType values.

func (TokenType) String ¶

func (tt TokenType) String() string

String returns the string representation of a TokenType.

Source Files ¶

lex.go util.go