com.pd4ml.html.parser

Class HtmlParser

java.lang.Object

com.pd4ml.html.parser.HtmlParser

public class HtmlParser
extends Object

Field Summary

Fields

Modifier and Type	Field and Description
boolean	bodyStarted
static String	CHARSET_PREFIX
static String	ENCODING_CHANGE
static String	FILE_ENCODING
static String	IN_BODY_STYLE
boolean	inCDATA

Constructor Summary

Constructors

Constructor and Description
HtmlParser()

Method Summary

Modifier and Type	Method and Description
static String	convertFromUtf32(int codePoint)
Iterator	errors()
String	getEncoding()
void	readDocument(DocBuilder docHandler, InputStream in, String enc, boolean ignoreCharsetDirective, Properties dynamicParams)
int	readersNum()
void	setDebugLevel(int level)
boolean	setReader(InputStream in, String enc, Tag originator)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

FILE_ENCODING

public static final String FILE_ENCODING

See Also:

Constant Field Values

ENCODING_CHANGE

public static final String ENCODING_CHANGE

See Also:

Constant Field Values

IN_BODY_STYLE

public static final String IN_BODY_STYLE

See Also:

Constant Field Values

CHARSET_PREFIX

public static final String CHARSET_PREFIX

See Also:

Constant Field Values

bodyStarted

public boolean bodyStarted

inCDATA

public boolean inCDATA

Constructor Detail

HtmlParser

public HtmlParser()

Method Detail

setDebugLevel

public void setDebugLevel(int level)

readersNum

public int readersNum()

readDocument

public void readDocument(DocBuilder docHandler,
                         InputStream in,
                         String enc,
                         boolean ignoreCharsetDirective,
                         Properties dynamicParams)
                  throws IOException

Throws:

IOException

convertFromUtf32

public static String convertFromUtf32(int codePoint)

errors

public Iterator errors()

getEncoding

public String getEncoding()

setReader

public boolean setReader(InputStream in,
                         String enc,
                         Tag originator)
                  throws IOException

Throws:

IOException