aalto-xml 1.3.2 · com.fasterxml.aalto.in.XmlScanner

Field Summary

Modifier and Type	Field and Description
protected final AttributeCollector	_attrCollector
protected int	_attrCount
protected final boolean	_cfgCoalescing
protected boolean	_cfgLazyParsing
protected final ReaderConfig	_config
protected ElementScope	_currElem Information about the current element on the stack
protected int	_currNsCount This is a temporary state variable, valid during START_ELEMENT event.
protected int	_currRow The row on which the character to read next is on.
protected int	_currToken
protected NsBinding	_defaultNs Default namespace binding is a per-document singleton, like explicit bindings, and used for elements (never for attributes).
protected int	_depth Number of START_ELEMENT events returned for which no END_ELEMENT has been returned; including current event.
protected boolean	_entityPending Flag set to indicate that an entity is pending
protected boolean	_isEmptyTag Flag that is used if the current state is `START_ELEMENT` or `END_ELEMENT`, to indicate if the underlying physical tag is a so-called empty tag (one ending with "/>")
protected FixedNsContext	_lastNsContext Last returned `NamespaceContext`, created for a call to `getNonTransientNamespaceContext`, iff this would still be a valid context.
protected NsDeclaration	_lastNsDecl Pointer to the last namespace declaration encountered.
protected char[]	_nameBuffer Similarly, need a char buffer for actual String construction (in future, could perhaps use StringBuilder?).
protected PName[]	_nsBindingCache Although unbound pname instances can be easily and safely reused, bound ones are per-document.
protected int	_nsBindingCount
protected NsBinding[]	_nsBindings Array containing all prefix bindings needed within the current document, so far (if any).
protected int	_nsBindMisses
protected long	_pastBytesOrChars Number of bytes that were read and processed before the contents of the current buffer; used for calculating absolute offsets.
protected String	_publicId Public id of the current event (DTD), if any.
protected int	_rowStartOffset Offset used to calculate the column value given current input buffer pointer.
protected long	_startColumn Current column at start of current (last returned) token
protected long	_startRawOffset Offset (in chars or bytes) at start of current token
protected long	_startRow Current row at start of current (last returned) token
protected String	_systemId System id of the current event (DTD), if any.
protected final TextBuilder	_textBuilder Textual content of the current event
protected boolean	_tokenIncomplete
protected PName	_tokenName Current name associated with the token, if any.
protected final boolean	_xml11 Whether validity checks (wrt.
private static final int	BIND_CACHE_MASK
private static final int	BIND_CACHE_SIZE Size of the bind cache can be reasonably small, and should still get high enough hit rate
private static final int	BIND_MISSES_TO_ACTIVATE_CACHE Let's activate cache quite soon, no need to wait for hundreds of misses; just try to avoid cache construction if all we get is soap envelope element or such.
protected final String	CDATA_STR String that identifies CDATA section (after "<![" prefix)
protected static final int	INT_0
protected static final int	INT_9
protected static final int	INT_A
protected static final int	INT_a
protected static final int	INT_AMP
protected static final int	INT_APOS
protected static final int	INT_COLON
protected static final int	INT_CR
protected static final int	INT_EQ
protected static final int	INT_EXCL
protected static final int	INT_F
protected static final int	INT_f
protected static final int	INT_GT
protected static final int	INT_HYPHEN
protected static final int	INT_LBRACKET
protected static final int	INT_LF
protected static final int	INT_LT
protected static final int	INT_NULL
protected static final int	INT_QMARK
protected static final int	INT_QUOTE
protected static final int	INT_RBRACKET
protected static final int	INT_SLASH
protected static final int	INT_SPACE
protected static final int	INT_TAB
protected static final int	INT_z
protected static final int	MAX_UNICODE_CHAR Hides com.fasterxml.aalto.util.XmlConsts.MAX_UNICODE_CHAR. This constant defines the highest Unicode character allowed in XML content.
public static final int	TOKEN_EOI This token type signifies end-of-input, in cases where it can be returned.

Access	Constructor and Description
protected	XmlScanner(ReaderConfig cfg)

Method Summary

Modifier and Type	Method and Description
protected abstract void	_closeSource()
protected void	_releaseBuffers()
protected final PName	bindName(PName name, String prefix) This method is called to find/create a fully qualified (bound) name (element / attribute), for a name with prefix.
protected final void	bindNs(PName name, String uri) Method called when we are ready to bind a declared namespace.
protected final void	checkImmutableBinding(String prefix, String uri) Method called when an immutable ns prefix (xml, xmlns) is encountered.
public final void	close(boolean True if the underlying input source is to be closed, independent of whether auto-close has been set to true via configuration (or if the scanner manages the input source) forceCloseSource) Method called at point when the parsing process has ended (either by encountering end of the input, or via explicit close), and buffers can and should be released.
public final byte[]	decodeAttrBinaryValue(int index, Base64Variant v, CharArrayBase64Decoder dec)
public final void	decodeAttrValue(int index, TypedValueDecoder tvd)
public final int	Returns: Number of tokens decoded decodeAttrValues(int index, TypedArrayDecoder tad) Method called to decode the attribute value that consists of zero or more space-separated tokens.
public final int	decodeElements(TypedArrayDecoder tad, boolean If true, need to tell text buffer to reset its decoding state; if false, shouldn't reset) Method called by the stream reader to decode space-separated tokens that are part of the current text event, using given decoder.
public final int	findAttrIndex(String nsURI, String localName)
private NsDeclaration	findCurrNsDecl(int index)
protected final NsBinding	findOrCreateBinding(String prefix) Method called when a namespace declaration needs to find the binding object (essentially a per-prefix-per-document canonical container object)
protected abstract void	finishCData()
protected abstract void	finishCharacters()
protected abstract void	finishComment()
protected abstract void	finishDTD(boolean copyContents)
protected abstract void	finishPI()
protected abstract void	finishSpace()
protected abstract void	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)
public void	fireSaxCharacterEvents(ContentHandler h)
public void	fireSaxCommentEvent(LexicalHandler h)
public void	fireSaxEndElement(ContentHandler h)
public void	fireSaxPIEvent(ContentHandler h)
public void	fireSaxSpaceEvents(ContentHandler h)
public void	fireSaxStartElement(ContentHandler h, Attributes attrs)
public AttributeCollector	getAttrCollector()
public final int	getAttrCount()
public final String	getAttrLocalName(int index)
public final String	getAttrNsURI(int index)
public final String	getAttrPrefix(int index)
public final String	getAttrPrefixedName(int index)
public final QName	getAttrQName(int index)
public final String	getAttrType(int index)
public final String	getAttrValue(int index)
public final String	getAttrValue(String nsURI, String localName)
public ReaderConfig	getConfig()
public abstract int	getCurrentColumnNr()
public final int	getCurrentLineNr()
public abstract XMLStreamLocation2	Returns: Current input location getCurrentLocation()
public final int	getDepth()
public final String	getDTDPublicId()
public final String	getDTDSystemId()
public abstract long	getEndingByteOffset()
public abstract long	getEndingCharOffset()
public XMLStreamLocation2	getEndLocation()
public final String	getInputPublicId()
public final String	getInputSystemId()
public final PName	getName()
public final String	getNamespacePrefix(int index)
public final String	getNamespaceURI(int index)
public final String	getNamespaceURI()
public String	getNamespaceURI(String prefix to look up prefix) Implements javax.xml.namespace.NamespaceContext.getNamespaceURI. Get Namespace URI bound to a prefix in the current scope.
public final NamespaceContext	getNonTransientNamespaceContext()
public final int	getNsCount()
public String	getPrefix(String URI of Namespace to lookup nsURI) Implements javax.xml.namespace.NamespaceContext.getPrefix. Get prefix bound to Namespace URI in the current scope.
public Iterator<String>	getPrefixes(String URI of Namespace to lookup nsURI) Implements javax.xml.namespace.NamespaceContext.getPrefixes. Get all prefixes bound to a Namespace URI in the current scope.
public final QName	getQName()
public abstract long	getStartingByteOffset()
public abstract long	getStartingCharOffset()
public final XMLStreamLocation2	getStartLocation()
public final String	getText()
public final int	getText(Writer w, boolean preserveContents)
public final char[]	getTextCharacters()
public final int	getTextCharacters(int srcStart, char[] target, int targetStart, int len)
public final int	getTextLength()
protected char	handleInvalidXmlChar(int i)
public final boolean	hasEmptyStack()
public final boolean	isAttrSpecified(int index)
public final boolean	isEmptyTag()
public final boolean	isTextWhitespace()
protected abstract boolean	loadMore()
protected final void	loadMoreGuaranteed() Method that tries to load at least one more byte into buffer; and if that fails, throws an appropriate EOI exception.
protected final void	loadMoreGuaranteed(int tt)
public abstract int	nextFromProlog(boolean isProlog)
public abstract int	nextFromTree()
protected void	reportDoubleHyphenInComments()
protected void	reportDuplicateNsDecl(String prefix)
protected void	reportEntityOverflow()
protected void	reportEofInName(char[] cbuf, int clen)
protected void	reportIllegalCDataEnd()
protected void	reportIllegalNsDecl(String prefix)
protected void	reportIllegalNsDecl(String prefix, String uri)
protected void	reportInputProblem(String msg)
protected void	reportInvalidNameChar(int ch, int index)
protected void	reportInvalidNsIndex(int index)
protected void	reportInvalidXmlChar(int ch)
protected void	reportMissingPISpace(int ch) Called when there's an unexpected char after PI target (non-ws, not part of `'?`
protected void	reportMultipleColonsInName()
protected void	reportPrologProblem(boolean isProlog, String msg)
protected void	reportPrologUnexpChar(boolean isProlog, int ch, String msg)
protected void	reportPrologUnexpElement(boolean isProlog, int ch)
protected void	reportTreeUnexpChar(int ch, String msg)
protected void	reportUnboundPrefix(PName name, boolean isAttr)
protected void	reportUnexpandedEntityInAttr(PName name, boolean isNsDecl) Method called when a call to expand an entity within attribute value fails to expand it.
protected void	reportUnexpectedEndTag(String expName)
public final void	resetForDecoding(Base64Variant v, CharArrayBase64Decoder dec, boolean firstChunk) Method called by the stream reader to reset given base64 decoder with data from the current text event.
protected abstract void	skipCData()
protected abstract boolean	Returns: True, if an unexpanded entity was encountered (and is now pending) skipCharacters()
protected abstract boolean	Returns: True, if an unexpanded entity was encountered (and is now pending) skipCoalescedText() Secondary skip method called after primary text segment has been skipped, and we are in coalescing mode.
protected abstract void	skipComment()
protected abstract void	skipPI()
protected abstract void	skipSpace()
protected final boolean	Returns: True If by skipping we also figured out following event type (and assigned its type to _currToken); false if that remains to be done skipToken() This method is called to essentially skip remaining of the current token (data of PI etc)
protected void	throwInvalidSpace(int i)
protected void	throwNullChar()
protected void	throwUnexpectedChar(int i, String msg)
protected final void	verifyXmlChar(int value)

Inherited from java.lang.Object:: clone equals finalize getClass hashCode notify notifyAll toString wait wait wait

public abstract Class XmlScanner

Field Summary

Constructor Summary

Method Summary