package html

import "github.com/tdewolff/minify/v2/parse/html"

Package html is an HTML5 lexer following the specifications at http://www.w3.org/TR/html5/syntax.html.

Index ¶

• func EscapeAttrVal(buf *[]byte, orig, b []byte, isXML bool) []byte
• type Hash
• func ToHash(s []byte) Hash
• func (i Hash) String() string
• type Lexer
• func NewLexer(r *parse.Input) *Lexer
• func (l *Lexer) AttrVal() []byte
• func (l *Lexer) Err() error
• func (l *Lexer) Next() (TokenType, []byte)
• func (l *Lexer) Text() []byte
• type TokenType
• func (tt TokenType) String() string

Examples ¶

• NewLexer

Functions ¶

func EscapeAttrVal ¶

func EscapeAttrVal(buf *[]byte, orig, b []byte, isXML bool) []byte

EscapeAttrVal returns the escaped attribute value bytes without quotes.

Types ¶

type Hash ¶

type Hash uint32

Hash defines perfect hashes for a predefined list of strings

const (
	Iframe    Hash = 0x6    // iframe
	Math      Hash = 0x604  // math
	Plaintext Hash = 0x1e09 // plaintext
	Script    Hash = 0xa06  // script
	Style     Hash = 0x1405 // style
	Svg       Hash = 0x1903 // svg
	Textarea  Hash = 0x2308 // textarea
	Title     Hash = 0xf05  // title
	Xmp       Hash = 0x1c03 // xmp
)

Unique hash definitions to be used instead of strings

func ToHash ¶

func ToHash(s []byte) Hash

ToHash returns the hash whose name is s. It returns zero if there is no such hash. It is case sensitive.

func (Hash) String ¶

func (i Hash) String() string

String returns the hash' name.

type Lexer ¶

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

Lexer is the state for the lexer.

func NewLexer ¶

func NewLexer(r *parse.Input) *Lexer

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

{
	l := NewLexer(parse.NewInputString("<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) 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
	StartTagToken
	StartTagCloseToken
	StartTagVoidToken
	EndTagToken
	AttributeToken
	TextToken
	SvgToken
	MathToken
)

TokenType values.

func (TokenType) String ¶

func (tt TokenType) String() string

String returns the string representation of a TokenType.

Source Files ¶

hash.go lex.go util.go