aalto-xml 1.3.2 · com.fasterxml.aalto.async.AsyncByteScanner

Field Summary

Modifier and Type	Field and Description
protected XmlCharTypes	_charTypes This is a simple container object that is used to access the decoding tables for characters.
protected int	_currQuad Bytes parsed for the current, incomplete, quad
protected int	_currQuadBytes Number of bytes pending/buffered, stored in `_currQuad`
protected boolean	_elemAllNsBound
protected boolean	_elemAttrCount
protected PName	_elemAttrName
protected int	_elemAttrPtr Pointer for the next character of currently being parsed value within attribute value buffer
protected byte	_elemAttrQuote
protected int	_elemNsPtr Pointer for the next character of currently being parsed namespace URI for the current namespace declaration
protected boolean	_endOfInput Flag that is sent when calling application indicates that there will be no more input to parse.
protected int	_entityValue Entity value accumulated so far
protected boolean	_inDtdDeclaration Flag that indicates whether we are inside a declaration during parsing of internal DTD subset.
protected int	_nextEvent Due to asynchronous nature of parsing, we may know what event we are trying to parse, even if it's not yet complete.
protected int	_pendingInput There are some multi-byte combinations that must be handled as a unit: CR+LF linefeeds, multi-byte UTF-8 characters, and multi-character end markers for comments and PIs.
protected int[]	_quadBuffer This buffer is used for name parsing.
protected int	_quadCount Number of complete quads parsed for current name (quads themselves are stored in `_quadBuffer`).
protected int	_state In addition to the event type, there is need for additional state information
protected int	_surroundingEvent For token/state combinations that are 'shared' between events (or embedded in them), this is where the surrounding event state is retained.
protected ByteBasedPNameTable	_symbols For now, symbol table contains prefixed names.
protected static final int	EVENT_INCOMPLETE
protected static final int	PENDING_STATE_ATTR_VALUE_AMP
protected static final int	PENDING_STATE_ATTR_VALUE_AMP_HASH
protected static final int	PENDING_STATE_ATTR_VALUE_AMP_HASH_X
protected static final int	PENDING_STATE_ATTR_VALUE_DEC_DIGIT
protected static final int	PENDING_STATE_ATTR_VALUE_ENTITY_NAME
protected static final int	PENDING_STATE_ATTR_VALUE_HEX_DIGIT
protected static final int	PENDING_STATE_CDATA_BRACKET1
protected static final int	PENDING_STATE_CDATA_BRACKET2
protected static final int	PENDING_STATE_COMMENT_HYPHEN1
protected static final int	PENDING_STATE_COMMENT_HYPHEN2
protected static final int	PENDING_STATE_CR
protected static final int	PENDING_STATE_ENT_IN_DEC_DIGIT
protected static final int	PENDING_STATE_ENT_IN_HEX_DIGIT
protected static final int	PENDING_STATE_ENT_SEEN_HASH
protected static final int	PENDING_STATE_ENT_SEEN_HASH_X
protected static final int	PENDING_STATE_PI_QMARK
protected static final int	PENDING_STATE_TEXT_AMP
protected static final int	PENDING_STATE_TEXT_AMP_HASH
protected static final int	PENDING_STATE_TEXT_BRACKET1
protected static final int	PENDING_STATE_TEXT_BRACKET2
protected static final int	PENDING_STATE_TEXT_DEC_ENTITY
protected static final int	PENDING_STATE_TEXT_HEX_ENTITY
protected static final int	PENDING_STATE_TEXT_IN_ENTITY
protected static final int	PENDING_STATE_XMLDECL_LT
protected static final int	PENDING_STATE_XMLDECL_LTQ
protected static final int	PENDING_STATE_XMLDECL_TARGET
protected static final int	STATE_CDATA_C
protected static final int	STATE_CDATA_CD
protected static final int	STATE_CDATA_CDA
protected static final int	STATE_CDATA_CDAT
protected static final int	STATE_CDATA_CDATA
protected static final int	STATE_CDATA_CONTENT
protected static final int	STATE_COMMENT_CONTENT
protected static final int	STATE_COMMENT_HYPHEN
protected static final int	STATE_COMMENT_HYPHEN2
protected static final int	STATE_DEFAULT Default starting state for many events/contexts -- nothing has been seen so far, no event incomplete.
protected static final int	STATE_DTD_AFTER_DOCTYPE
protected static final int	STATE_DTD_AFTER_PUBLIC
protected static final int	STATE_DTD_AFTER_PUBLIC_ID
protected static final int	STATE_DTD_AFTER_ROOT_NAME
protected static final int	STATE_DTD_AFTER_SYSTEM
protected static final int	STATE_DTD_AFTER_SYSTEM_ID
protected static final int	STATE_DTD_BEFORE_IDS
protected static final int	STATE_DTD_BEFORE_PUBLIC_ID
protected static final int	STATE_DTD_BEFORE_ROOT_NAME
protected static final int	STATE_DTD_BEFORE_SYSTEM_ID
protected static final int	STATE_DTD_DOCTYPE
protected static final int	STATE_DTD_EXPECT_CLOSING_GT
protected static final int	STATE_DTD_INT_SUBSET
protected static final int	STATE_DTD_PUBLIC_ID
protected static final int	STATE_DTD_PUBLIC_OR_SYSTEM
protected static final int	STATE_DTD_ROOT_NAME
protected static final int	STATE_DTD_SYSTEM_ID
protected static final int	STATE_EE_NEED_GT
protected static final int	STATE_PI_AFTER_TARGET
protected static final int	STATE_PI_AFTER_TARGET_QMARK
protected static final int	STATE_PI_AFTER_TARGET_WS
protected static final int	STATE_PI_IN_DATA
protected static final int	STATE_PI_IN_TARGET
protected static final int	STATE_PROLOG_DECL
protected static final int	STATE_PROLOG_INITIAL State in which a less-than sign has been seen
protected static final int	STATE_PROLOG_SEEN_LT
protected static final int	STATE_SE_ATTR_NAME
protected static final int	STATE_SE_ATTR_VALUE_NORMAL
protected static final int	STATE_SE_ATTR_VALUE_NSDECL
protected static final int	STATE_SE_ELEM_NAME
protected static final int	STATE_SE_SEEN_SLASH
protected static final int	STATE_SE_SPACE_OR_ATTRNAME
protected static final int	STATE_SE_SPACE_OR_ATTRVALUE
protected static final int	STATE_SE_SPACE_OR_END
protected static final int	STATE_SE_SPACE_OR_EQ
protected static final int	STATE_TEXT_AMP
protected static final int	STATE_TEXT_AMP_NAME
protected static final int	STATE_TREE_NAMED_ENTITY_START
protected static final int	STATE_TREE_NUMERIC_ENTITY_START
protected static final int	STATE_TREE_SEEN_AMP
protected static final int	STATE_TREE_SEEN_EXCL
protected static final int	STATE_TREE_SEEN_LT
protected static final int	STATE_TREE_SEEN_SLASH
protected static final int	STATE_XMLDECL_AFTER_ENCODING
protected static final int	STATE_XMLDECL_AFTER_ENCODING_VALUE
protected static final int	STATE_XMLDECL_AFTER_STANDALONE
protected static final int	STATE_XMLDECL_AFTER_STANDALONE_VALUE
protected static final int	STATE_XMLDECL_AFTER_VERSION
protected static final int	STATE_XMLDECL_AFTER_VERSION_VALUE
protected static final int	STATE_XMLDECL_AFTER_XML
protected static final int	STATE_XMLDECL_BEFORE_ENCODING
protected static final int	STATE_XMLDECL_BEFORE_STANDALONE
protected static final int	STATE_XMLDECL_BEFORE_VERSION
protected static final int	STATE_XMLDECL_ENCODING
protected static final int	STATE_XMLDECL_ENCODING_EQ
protected static final int	STATE_XMLDECL_ENCODING_VALUE
protected static final int	STATE_XMLDECL_ENDQ
protected static final int	STATE_XMLDECL_STANDALONE
protected static final int	STATE_XMLDECL_STANDALONE_EQ
protected static final int	STATE_XMLDECL_STANDALONE_VALUE
protected static final int	STATE_XMLDECL_VERSION
protected static final int	STATE_XMLDECL_VERSION_EQ
protected static final int	STATE_XMLDECL_VERSION_VALUE

Access	Constructor and Description
protected	AsyncByteScanner(ReaderConfig cfg)

Method Summary

Modifier and Type	Method and Description
protected void	_activateEncoding() Initialization method to call when encoding has been definitely figured out, from XML declarations, or, from lack of one (using defaults).
protected void	_closeSource() Implements abstract com.fasterxml.aalto.in.ByteBasedScanner._closeSource. Since the async scanner has no access to whatever passes content, there is no input source in same sense as with blocking scanner; and there is nothing to close.
protected abstract byte	_currentByte()
protected final PName	_findXmlDeclName(int lastQuad, int lastByteCount)
protected abstract byte	_nextByte()
private final PName	_parseNewXmlDeclName(byte b)
private final PName	_parseXmlDeclName()
protected abstract byte	_prevByte()
protected void	_releaseBuffers() Overrides com.fasterxml.aalto.in.XmlScanner._releaseBuffers.
protected int	_startDocumentNoXmlDecl() Helper method called when it is determined that the document does NOT start with an xml declaration.
protected final PName	addPName(ByteBasedPNameTable symbols, int hash, int[] quads, int qlen, int lastQuadBytes)
protected abstract boolean	asyncSkipSpace()
protected void	checkPITargetName(PName targetName)
protected int	decodeCharForError(byte b) Implements abstract com.fasterxml.aalto.in.ByteBasedScanner.decodeCharForError. Method called by methods when encountering a byte that can not be part of a valid character in the current context.
public void	endOfInput() Implements com.fasterxml.aalto.AsyncInputFeeder.endOfInput. Method that should be called after last chunk of data to parse has been fed.
protected final PName	findPName(int Word with last 0 to 3 bytes of the PName; not included in the quad array lastQuad, int Number of bytes contained in lastQuad; 0 to 3. lastByteCount) Method called to process a sequence of bytes that is likely to be a PName.
protected void	finishCData() Implements abstract com.fasterxml.aalto.in.XmlScanner.finishCData.
protected abstract void	finishCharacters() Implements abstract com.fasterxml.aalto.in.XmlScanner.finishCharacters.
protected void	finishComment() Implements abstract com.fasterxml.aalto.in.XmlScanner.finishComment.
protected void	finishDTD(boolean copyContents) Implements abstract com.fasterxml.aalto.in.XmlScanner.finishDTD.
protected void	finishPI() Implements abstract com.fasterxml.aalto.in.XmlScanner.finishPI.
protected void	finishSpace() Implements abstract com.fasterxml.aalto.in.XmlScanner.finishSpace.
protected final void	finishToken() Implements abstract com.fasterxml.aalto.in.XmlScanner.finishToken. This method is called to ensure that the current token/event has been completely parsed, such that we have all the data needed to return it (textual content, PI data, comment text etc)
protected abstract boolean	handleAttrValue()
protected abstract int	handleComment()
private int	handleDTD()
protected abstract boolean	handleDTDInternalSubset(boolean init)
protected abstract boolean	handleNsDecl()
protected abstract boolean	handlePartialCR()
protected abstract int	handlePI()
private final int	handlePrologDeclStart(boolean isProlog)
protected abstract int	handleStartElement()
protected abstract int	handleStartElementStart(byte b)
private int	Returns: Completed token (START_DOCUMENT), if fully parsed; incomplete (EVENT_INCOMPLETE) otherwise handleXmlDeclaration() Method called to complete parsing of XML declaration, once it has been reliably detected.
protected boolean	loadMore() Implements abstract com.fasterxml.aalto.in.XmlScanner.loadMore.
public final int	nextFromProlog(boolean isProlog) Implements abstract com.fasterxml.aalto.in.XmlScanner.nextFromProlog.
private final boolean	parseDtdId(char[] outputBuffer, int outputPtr, boolean system)
protected abstract PName	parseNewName(byte b)
protected abstract PName	parsePName()
protected boolean	Returns: True if we managed to parse the whole pseudo-attribute parseXmlDeclAttr(char[] outputBuffer, int outputPtr) Method called to try to parse an XML pseudo-attribute value.
protected void	reportInvalidOther(int mask, int ptr)
protected void	skipCData() Implements abstract com.fasterxml.aalto.in.XmlScanner.skipCData.
protected abstract boolean	Returns: True if the whole characters segment was succesfully skipped; false if not skipCharacters() Implements abstract com.fasterxml.aalto.in.XmlScanner.skipCharacters.
protected void	skipComment() Implements abstract com.fasterxml.aalto.in.XmlScanner.skipComment.
protected void	skipPI() Implements abstract com.fasterxml.aalto.in.XmlScanner.skipPI.
protected void	skipSpace() Implements abstract com.fasterxml.aalto.in.XmlScanner.skipSpace.
protected abstract int	Returns: Event type detected; either CHARACTERS, if at least one full character was decoded (and can be returned), EVENT_INCOMPLETE if not (part of a multi-byte character split across input buffer boundary) startCharacters(byte b) Method called to initialize state for CHARACTERS event, after just a single byte has been seen.
private final Boolean	Returns: null if parsing is inconclusive (may or may not be XML declaration); Boolean.TRUE if complete XML declaration, and Boolean.FALSE if something else startXmlDeclaration() Method that deals with recognizing XML declaration, but not with parsing its contents.
protected int	throwInternal()
protected boolean	Returns: true if the character is valid for use in the Public ID of an XML doctype declaration validPublicIdChar(int A character c) Checks that a character for a PublicId
protected void	verifyAndAppendEntityCharacter(int charFromEntity) Method called to verify validity of given character (from entity) and append it to the text buffer
protected void	verifyAndSetPublicId()
protected void	verifyAndSetSystemId()
protected void	verifyAndSetXmlEncoding()
protected void	verifyAndSetXmlStandalone()
protected void	verifyAndSetXmlVersion()

Inherited from com.fasterxml.aalto.in.ByteBasedScanner:: addUTFPName getCurrentColumnNr getCurrentLocation getEndingByteOffset getEndingCharOffset getStartingByteOffset getStartingCharOffset markLF markLF reportInvalidInitial reportInvalidOther setStartLocation

public abstract Class AsyncByteScanner

Field Summary

Constructor Summary

Method Summary