org.databene.html
Interface HTMLTokenizer

All Known Implementing Classes:

DefaultHTMLTokenizer, FilteringHTMLTokenizer

public interface HTMLTokenizer

Abstraction of an HTML tokenizer.

Created: 15.06.2007 05:53:19

Author:

Volker Bergmann

Field Summary

static int	CLOSED_TAG
static int	COMMENT
static int	DOCUMENT_TYPE
static int	END
static int	END_TAG
static int	PROCESSING_INSTRUCTION
static int	SCRIPT
static int	START_TAG
static int	TEXT

Method Summary

java.util.Map<java.lang.String,java.lang.String>	attributes()
java.lang.String	name()
int	nextToken()
java.lang.String	text()
int	tokenType()

Field Detail

END

static final int END

See Also:

Constant Field Values

DOCUMENT_TYPE

static final int DOCUMENT_TYPE

See Also:

Constant Field Values

TEXT

static final int TEXT

See Also:

Constant Field Values

START_TAG

static final int START_TAG

See Also:

Constant Field Values

END_TAG

static final int END_TAG

See Also:

Constant Field Values

CLOSED_TAG

static final int CLOSED_TAG

See Also:

Constant Field Values

COMMENT

static final int COMMENT

See Also:

Constant Field Values

PROCESSING_INSTRUCTION

static final int PROCESSING_INSTRUCTION

See Also:

Constant Field Values

SCRIPT

static final int SCRIPT

See Also:

Constant Field Values

Method Detail

nextToken

int nextToken()
              throws java.io.IOException,
                     java.text.ParseException

Throws:

java.io.IOException

java.text.ParseException

tokenType

int tokenType()

name

java.lang.String name()

text

java.lang.String text()

attributes

java.util.Map<java.lang.String,java.lang.String> attributes()