Overview  Package   Class  Use  Deprecated  Index
Home >> All >> com >> port80 >> html >> [ tidy overview ]	PREV CLASS  NEXT CLASS
SUMMARY:  JAVADOC |  SOURCE |  DOWNLOAD | NESTED | FIELD | CONSTR | METHOD	DETAIL: FIELD | CONSTR | METHOD

---

com.port80.html.tidy
Class Lexer  

java.lang.Object
  com.port80.html.tidy.Lexer

---

public class Lexer

extends java.lang.Object

---

Nested Class Summary
private static class	Lexer.LexerASPState
private static class	Lexer.LexerCDataState
private static class	Lexer.LexerCommentState
private static class	Lexer.LexerContentState
private static class	Lexer.LexerDocTypeState
private static class	Lexer.LexerEndTagState
private static class	Lexer.LexerJSTEState
private static class	Lexer.LexerPHPState
private static class	Lexer.LexerProcInstState
private static class	Lexer.LexerScriptState
private static class	Lexer.LexerSectionState
private static class	Lexer.LexerStartTagState
private static class	Lexer.LexerState
private static class	Lexer.LexerTagState
private static class	Lexer.W3CVersionInfo

 

Field Summary
short	badAccess
short	badChars
boolean	badDoctype
short	badForm
short	badLayout
private static boolean	CHECK
private  int	column
TidyConfiguration	configuration
private static short	DIGIT
int	doctype
short	errors
boolean	excludeBlocks
boolean	exiled
private  java.lang.String	fInputName
private  char	fInsertSpace
Node	fSavedTextNode
private  Lexer.LexerState	fState
private  TagTable	fTagTable
(package private)  boolean	fWasWhite
private static short	HEXDIGIT
int	insert
(package private)  boolean	isEndWithLineBreak           Text content is ended with a line separator.
(package private)  boolean	isEndWithMultiLineBreak
(package private)  boolean	isStartWithLineBreak
(package private)  boolean	isStartWithMultiLineBreak
java.util.Stack	istack
int	istackbase
IHTMLReader	iStream
boolean	isvoyager
private static short	LETTER
private  CharBuffer	lexbuf
private static short[]	lexmap
private  int	lineno
private static short	LOWERCASE
static short	MODE_ATTR_VALUE
static short	MODE_IGNORE_MARKUP
static short	MODE_IGNORE_WHITESPACE
static short	MODE_JAVASCRIPT
static short	MODE_MIXED_CONTENT
static short	MODE_PREFORMATTED
static short	MODE_SCRIPT
private static java.lang.String	NAME
private static short	NAMECHAR
private static short	NEWLINE
private  boolean	pushed
protected  boolean	seenBodyEndTag
Style	styles
private  Node	token
private static short	UPPERCASE
private static boolean	VERBOSE
short	versions
private static java.lang.String	voyager_frameset
private static java.lang.String	voyager_loose
private static java.lang.String	voyager_strict
private static Lexer.W3CVersionInfo[]	W3CVersion
short	warnings
private static short	WHITE
private static java.lang.String	XHTML_NAMESPACE

 

Constructor Summary

Lexer(IHTMLReader in, java.lang.String inputname, TidyConfiguration configuration)

 

Method Summary
boolean	addGenerator(Node root)
private  short	apparentVersion()
void	append(char c)
void	append(java.lang.String str)
boolean	canPrune(Node element)
void	changeChar(char c)
boolean	checkDocTypeKeyWords(Node doctype)
AttVal	cloneAttributes(AttVal attrs)
Node	cloneNode(Node node)
(package private)  void	decLength(int n)
void	deferDup()           Defer duplicates when entering a table or other element where the inlines shouldn't be duplicated
static boolean	expectsContent(Node node)
private static boolean	findBadSubString(java.lang.String s, java.lang.String p, int len)
(package private)  short	findGivenVersion(Node doctype)
boolean	fixDocType(Node root)
private  void	fixHTMLNameSpace(Node root, java.lang.String profile)
void	fixId(Node node)
boolean	fixXMLPI(Node root)
(package private)  CharBuffer	getBuffer()
char	getChar(int i)
int	getColumn()
java.lang.String	getInputName()
int	getLineNumber()
int	getPosition()
Node	getScript(Node container)
Lexer.LexerState	getState()
static java.lang.String	getString(CharBuffer buf, int offset, int len)
(package private)  TagTable	getTagTable()
Node	getToken(int mode)
short	HTMLVersion()
java.lang.String	HTMLVersionName()
Node	inferredTag(java.lang.String name)
private  Lexer.LexerState	initState()
int	inlineDup(Node node)
private  Node	insertedToken()
private static boolean	isJavaScript(Node node)
boolean	isPushed(Node node)
static boolean	isValidAttrName(java.lang.String attr)
int	length()
static void	main(java.lang.String[] args)
private static short	MAP(char c)
private static void	mapStr(java.lang.String str, short code)
void	markPosition()
Node	newLineNode()
Node	newNode(int type)
Node	newNode(int type, int start, int end, int srcstart)
Node	newNode(int type, int start, int end, int srcstart, java.lang.String element)
Node	newNode(int type, int start, int end, int srcstart, java.lang.String element, AttVal attributes)
Node	newTextNode(int start, int end, int srcstart, int srcend)
private  Node	parseAttrAsp()
private  java.lang.String	parseAttribute(MutableBoolean isempty, MutableObject asp, MutableObject php)
private  Node	parseAttrPhp()           PHP is like ASP but is based upon XML processing instructions, e.g.
(package private)  AttVal	parseAttrs(MutableBoolean isempty)
(package private)  void	parseEntity(int mode)           No longer attempts to insert missing ';' for unknown enitities unless one was present already, since this gives unexpected results.
private  char	parseServerInstruction()
(package private)  char	parseTagName(char c)           Get tag name.
private  java.lang.String	parseValue(java.lang.String name, boolean foldCase, MutableBoolean isempty, MutableChar pdelim)
void	popInline(Node node)           Pop inline tag stack.
void	pushInline(Node node)
void	setInsertSpace(char c)
(package private)  void	setPosition(int line, int column)
Lexer.LexerState	setState(Lexer.LexerState state)
void	setWasWhite(boolean b)
boolean	setXHTMLDocType(Node root)
void	ungetToken()
static int	wstrcasecmp(java.lang.String s1, java.lang.String s2)
static int	wstrcaselexcmp(java.lang.String s1, java.lang.String s2)

 

Methods inherited from class java.lang.Object

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

 

Field Detail

NAME

private static final java.lang.String NAME

See Also:

Constant Field Values

---

CHECK

private static final boolean CHECK

See Also:

Constant Field Values

---

VERBOSE

private static boolean VERBOSE

---

voyager_loose

private static final java.lang.String voyager_loose

See Also:

Constant Field Values

---

voyager_strict

private static final java.lang.String voyager_strict

See Also:

Constant Field Values

---

voyager_frameset

private static final java.lang.String voyager_frameset

See Also:

Constant Field Values

---

XHTML_NAMESPACE

private static final java.lang.String XHTML_NAMESPACE

See Also:

Constant Field Values

---

W3CVersion

private static Lexer.W3CVersionInfo[] W3CVersion

---

DIGIT

private static final short DIGIT

See Also:

Constant Field Values

---

LETTER

private static final short LETTER

See Also:

Constant Field Values

---

NAMECHAR

private static final short NAMECHAR

See Also:

Constant Field Values

---

WHITE

private static final short WHITE

See Also:

Constant Field Values

---

NEWLINE

private static final short NEWLINE

See Also:

Constant Field Values

---

LOWERCASE

private static final short LOWERCASE

See Also:

Constant Field Values

---

UPPERCASE

private static final short UPPERCASE

See Also:

Constant Field Values

---

HEXDIGIT

private static final short HEXDIGIT

See Also:

Constant Field Values

---

MODE_IGNORE_WHITESPACE

public static final short MODE_IGNORE_WHITESPACE

See Also:

Constant Field Values

---

MODE_MIXED_CONTENT

public static final short MODE_MIXED_CONTENT

See Also:

Constant Field Values

---

MODE_PREFORMATTED

public static final short MODE_PREFORMATTED

See Also:

Constant Field Values

---

MODE_IGNORE_MARKUP

public static final short MODE_IGNORE_MARKUP

See Also:

Constant Field Values

---

MODE_JAVASCRIPT

public static final short MODE_JAVASCRIPT

See Also:

Constant Field Values

---

MODE_SCRIPT

public static final short MODE_SCRIPT

See Also:

Constant Field Values

---

MODE_ATTR_VALUE

public static final short MODE_ATTR_VALUE

See Also:

Constant Field Values

---

lexmap

private static short[] lexmap

---

iStream

public IHTMLReader iStream

---

badAccess

public short badAccess

---

badLayout

public short badLayout

---

badChars

public short badChars

---

badForm

public short badForm

---

warnings

public short warnings

---

errors

public short errors

---

excludeBlocks

public boolean excludeBlocks

---

exiled

public boolean exiled

---

isvoyager

public boolean isvoyager

---

versions

public short versions

---

doctype

public int doctype

---

badDoctype

public boolean badDoctype

---

fInputName

private java.lang.String fInputName

---

lineno

private int lineno

---

column

private int column

---

token

private Node token

---

pushed

private boolean pushed

---

fState

private Lexer.LexerState fState

---

lexbuf

private CharBuffer lexbuf

---

istack

public java.util.Stack istack

---

istackbase

public int istackbase

---

fSavedTextNode

public Node fSavedTextNode

---

insert

public int insert

---

configuration

public TidyConfiguration configuration

---

styles

public Style styles

---

fTagTable

private TagTable fTagTable

---

seenBodyEndTag

protected boolean seenBodyEndTag

---

fInsertSpace

private char fInsertSpace

---

fWasWhite

boolean fWasWhite

---

isEndWithLineBreak

boolean isEndWithLineBreak

Text content is ended with a line separator.

---

isEndWithMultiLineBreak

boolean isEndWithMultiLineBreak

---

isStartWithLineBreak

boolean isStartWithLineBreak

---

isStartWithMultiLineBreak

boolean isStartWithMultiLineBreak

Constructor Detail

Lexer

public Lexer(IHTMLReader in,
             java.lang.String inputname,
             TidyConfiguration configuration)

Method Detail

mapStr

private static void mapStr(java.lang.String str,
                           short code)

---

initState

private Lexer.LexerState initState()

---

isValidAttrName

public static boolean isValidAttrName(java.lang.String attr)

---

getString

public static java.lang.String getString(CharBuffer buf,
                                         int offset,
                                         int len)

---

expectsContent

public static boolean expectsContent(Node node)

---

wstrcasecmp

public static int wstrcasecmp(java.lang.String s1,
                              java.lang.String s2)

---

wstrcaselexcmp

public static int wstrcaselexcmp(java.lang.String s1,
                                 java.lang.String s2)

---

newNode

public Node newNode(int type)

---

newNode

public Node newNode(int type,
                    int start,
                    int end,
                    int srcstart)

---

newNode

public Node newNode(int type,
                    int start,
                    int end,
                    int srcstart,
                    java.lang.String element)

---

newNode

public Node newNode(int type,
                    int start,
                    int end,
                    int srcstart,
                    java.lang.String element,
                    AttVal attributes)

---

newTextNode

public Node newTextNode(int start,
                        int end,
                        int srcstart,
                        int srcend)

---

newLineNode

public Node newLineNode()

---

cloneNode

public Node cloneNode(Node node)

---

cloneAttributes

public AttVal cloneAttributes(AttVal attrs)

---

changeChar

public void changeChar(char c)

---

append

public final void append(char c)

---

append

public final void append(java.lang.String str)

---

decLength

final void decLength(int n)

---

getBuffer

final CharBuffer getBuffer()

---

getTagTable

final TagTable getTagTable()

---

setPosition

final void setPosition(int line,
                       int column)

---

getInputName

public java.lang.String getInputName()

---

setState

public Lexer.LexerState setState(Lexer.LexerState state)

---

getState

public Lexer.LexerState getState()

---

ungetToken

public void ungetToken()

---

getToken

public Node getToken(int mode)

---

getScript

public Node getScript(Node container)

---

pushInline

public void pushInline(Node node)

---

popInline

public void popInline(Node node)

Pop inline tag stack.

---

isPushed

public boolean isPushed(Node node)

---

inlineDup

public int inlineDup(Node node)

---

HTMLVersion

public short HTMLVersion()

---

HTMLVersionName

public java.lang.String HTMLVersionName()

---

addGenerator

public boolean addGenerator(Node root)

---

checkDocTypeKeyWords

public boolean checkDocTypeKeyWords(Node doctype)

---

setXHTMLDocType

public boolean setXHTMLDocType(Node root)

---

fixDocType

public boolean fixDocType(Node root)

---

fixXMLPI

public boolean fixXMLPI(Node root)

---

inferredTag

public Node inferredTag(java.lang.String name)

---

fixId

public void fixId(Node node)

---

deferDup

public void deferDup()

Defer duplicates when entering a table or other element where the inlines shouldn't be duplicated

---

canPrune

public boolean canPrune(Node element)

---

length

public final int length()

---

getChar

public final char getChar(int i)

---

getLineNumber

public final int getLineNumber()

---

getColumn

public final int getColumn()

---

getPosition

public final int getPosition()

---

setInsertSpace

public final void setInsertSpace(char c)

---

setWasWhite

public final void setWasWhite(boolean b)

---

markPosition

public void markPosition()

---

findBadSubString

private static boolean findBadSubString(java.lang.String s,
                                        java.lang.String p,
                                        int len)

---

MAP

private static short MAP(char c)

---

isJavaScript

private static boolean isJavaScript(Node node)

---

findGivenVersion

short findGivenVersion(Node doctype)

---

fixHTMLNameSpace

private void fixHTMLNameSpace(Node root,
                              java.lang.String profile)

---

apparentVersion

private short apparentVersion()

---

parseTagName

char parseTagName(char c)

Get tag name.

---

parseEntity

void parseEntity(int mode)

No longer attempts to insert missing ';' for unknown enitities unless one was present already, since this gives unexpected results. For example: was tidied to: rather than: My thanks for Maurice Buxton for spotting this.

---

parseAttrAsp

private Node parseAttrAsp()

---

parseAttrPhp

private Node parseAttrPhp()

PHP is like ASP but is based upon XML processing instructions, e.g. <?php ... ?>

---

parseAttribute

private java.lang.String parseAttribute(MutableBoolean isempty,
                                        MutableObject asp,
                                        MutableObject php)

---

parseServerInstruction

private char parseServerInstruction()

---

parseValue

private java.lang.String parseValue(java.lang.String name,
                                    boolean foldCase,
                                    MutableBoolean isempty,
                                    MutableChar pdelim)

---

parseAttrs

AttVal parseAttrs(MutableBoolean isempty)

---

insertedToken

private Node insertedToken()

---

main

public static void main(java.lang.String[] args)

---

Overview  Package   Class  Use  Deprecated  Index
Home >> All >> com >> port80 >> html >> [ tidy overview ]	PREV CLASS  NEXT CLASS
SUMMARY:  JAVADOC |  SOURCE |  DOWNLOAD | NESTED | FIELD | CONSTR | METHOD	DETAIL: FIELD | CONSTR | METHOD

---