XMLEntityScannerpublic class XMLEntityScanner extends Object implements org.apache.xerces.xni.XMLLocator| Implements the entity scanner methods. |
| Fields Summary |
|---|
| private static final boolean | DEBUG_ENCODINGS | | private static final boolean | DEBUG_BUFFER | | private static final EOFException | END_OF_DOCUMENT_ENTITYTo signal the end of the document entity, this exception will be thrown. | | private XMLEntityManager | fEntityManager | | protected XMLEntityManager.ScannedEntity | fCurrentEntity | | protected org.apache.xerces.util.SymbolTable | fSymbolTable | | protected int | fBufferSize | | protected XMLErrorReporter | fErrorReporterError reporter. This property identifier is:
http://apache.org/xml/properties/internal/error-reporter |
| Constructors Summary |
|---|
public XMLEntityScanner()Default constructor.
//
// Constructors
//
|
| Methods Summary |
|---|
| public final java.lang.String | getBaseSystemId()Returns the base system identifier of the currently scanned
entity, or null if none is available.
return (fCurrentEntity != null && fCurrentEntity.entityLocation != null) ? fCurrentEntity.entityLocation.getExpandedSystemId() : null;
| | public final int | getCharacterOffset()Returns the character offset where the current document event ends.
Warning: The return value from the method
is intended only as an approximation for the sake of error
reporting; it is not intended to provide sufficient information
to edit the character content of the original XML document.
The return value is an approximation of the character offset
in the document entity or external parsed entity where the
markup triggering the event appears.
If possible, the character offset of the first character after the
text associated with the document event should be provided.
if (fCurrentEntity != null) {
if (fCurrentEntity.isExternal()) {
return fCurrentEntity.baseCharOffset + (fCurrentEntity.position - fCurrentEntity.startPosition);
}
else {
// ask current entity to find appropriate character offset
return fCurrentEntity.getCharacterOffset();
}
}
return -1;
| | public final int | getColumnNumber()Returns the column number where the current document event ends.
Warning: The return value from the method
is intended only as an approximation for the sake of error
reporting; it is not intended to provide sufficient information
to edit the character content of the original XML document.
The return value is an approximation of the column number
in the document entity or external parsed entity where the
markup triggering the event appears.
If possible, the line position of the first character after the
text associated with the document event should be provided.
The first column in each line is column 1.
if (fCurrentEntity != null) {
if (fCurrentEntity.isExternal()) {
return fCurrentEntity.columnNumber;
}
else {
// ask current entity to find appropriate column number
return fCurrentEntity.getColumnNumber();
}
}
return -1;
| | public final java.lang.String | getEncoding()Returns the encoding of the current entity.
Note that, for a given entity, this value can only be
considered final once the encoding declaration has been read (or once it
has been determined that there is no such declaration) since, no encoding
having been specified on the XMLInputSource, the parser
will make an initial "guess" which could be in error.
if (fCurrentEntity != null) {
if (fCurrentEntity.isExternal()) {
return fCurrentEntity.encoding;
}
else {
// ask current entity to find appropriate encoding
return fCurrentEntity.getEncoding();
}
}
return null;
| | public final java.lang.String | getExpandedSystemId()Return the expanded system identifier for the current document event.
The return value is the expanded system identifier of the document
entity or of the external parsed entity in which the markup
triggering the event appears.
If the system identifier is a URL, the parser must resolve it
fully before passing it to the application.
if (fCurrentEntity != null) {
if (fCurrentEntity.entityLocation != null &&
fCurrentEntity.entityLocation.getExpandedSystemId() != null ) {
return fCurrentEntity.entityLocation.getExpandedSystemId();
}
else {
// get the current entity to return something appropriate:
return fCurrentEntity.getExpandedSystemId();
}
}
return null;
| | public final int | getLineNumber()Returns the line number where the current document event ends.
Warning: The return value from the method
is intended only as an approximation for the sake of error
reporting; it is not intended to provide sufficient information
to edit the character content of the original XML document.
The return value is an approximation of the line number
in the document entity or external parsed entity where the
markup triggering the event appears.
If possible, the line position of the first character after the
text associated with the document event should be provided.
The first line in the document is line 1.
if (fCurrentEntity != null) {
if (fCurrentEntity.isExternal()) {
return fCurrentEntity.lineNumber;
}
else {
// ask the current entity to return something appropriate:
return fCurrentEntity.getLineNumber();
}
}
return -1;
| | public final java.lang.String | getLiteralSystemId()Return the literal system identifier for the current document event.
The return value is the literal system identifier of the document
entity or of the external parsed entity in which the markup
triggering the event appears.
if (fCurrentEntity != null) {
if (fCurrentEntity.entityLocation != null &&
fCurrentEntity.entityLocation.getLiteralSystemId() != null ) {
return fCurrentEntity.entityLocation.getLiteralSystemId();
}
else {
// get the current entity to do it:
return fCurrentEntity.getLiteralSystemId();
}
}
return null;
| | public final java.lang.String | getPublicId()Return the public identifier for the current document event.
The return value is the public identifier of the document
entity or of the external parsed entity in which the markup
triggering the event appears.
return (fCurrentEntity != null && fCurrentEntity.entityLocation != null) ? fCurrentEntity.entityLocation.getPublicId() : null;
| | public final java.lang.String | getXMLVersion()Returns the XML version of the current entity. This will normally be the
value from the XML or text declaration or defaulted by the parser. Note that
that this value may be different than the version of the processing rules
applied to the current entity. For instance, an XML 1.1 document may refer to
XML 1.0 entities. In such a case the rules of XML 1.1 are applied to the entire
document. Also note that, for a given entity, this value can only be considered
final once the XML or text declaration has been read or once it has been
determined that there is no such declaration.
if (fCurrentEntity != null) {
if (fCurrentEntity.isExternal()) {
return fCurrentEntity.xmlVersion;
}
else {
// ask current entity to find the appropriate XML version
return fCurrentEntity.getXMLVersion();
}
}
return null;
| | public final boolean | isExternal()Returns true if the current entity being scanned is external.
return fCurrentEntity.isExternal();
| | final boolean | load(int offset, boolean changeEntity)Loads a chunk of text.
if (DEBUG_BUFFER) {
System.out.print("(load, "+offset+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
// read characters
int length = fCurrentEntity.mayReadChunks?
(fCurrentEntity.ch.length - offset):
(XMLEntityManager.DEFAULT_XMLDECL_BUFFER_SIZE);
if (DEBUG_BUFFER) System.out.println(" length to try to read: "+length);
int count = fCurrentEntity.reader.read(fCurrentEntity.ch, offset, length);
if (DEBUG_BUFFER) System.out.println(" length actually read: "+count);
// reset count and position
boolean entityChanged = false;
if (count != -1) {
if (count != 0) {
fCurrentEntity.count = count + offset;
fCurrentEntity.position = offset;
fCurrentEntity.startPosition = offset;
}
}
// end of this entity
else {
fCurrentEntity.count = offset;
fCurrentEntity.position = offset;
fCurrentEntity.startPosition = offset;
entityChanged = true;
if (changeEntity) {
fEntityManager.endEntity();
if (fCurrentEntity == null) {
throw END_OF_DOCUMENT_ENTITY;
}
// handle the trailing edges
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
}
}
if (DEBUG_BUFFER) {
System.out.print(")load, "+offset+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
return entityChanged;
| | public int | peekChar()Returns the next character on the input.
Note: The character is not consumed.
if (DEBUG_BUFFER) {
System.out.print("(peekChar: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// peek at character
int c = fCurrentEntity.ch[fCurrentEntity.position];
// return peeked character
if (DEBUG_BUFFER) {
System.out.print(")peekChar: ");
XMLEntityManager.print(fCurrentEntity);
if (fCurrentEntity.isExternal()) {
System.out.println(" -> '"+(c!='\r"?(char)c:'\n")+"'");
}
else {
System.out.println(" -> '"+(char)c+"'");
}
}
if (fCurrentEntity.isExternal()) {
return c != '\r" ? c : '\n";
}
else {
return c;
}
| | public final void | reset(org.apache.xerces.util.SymbolTable symbolTable, XMLEntityManager entityManager, XMLErrorReporter reporter)
fCurrentEntity = null;
fSymbolTable = symbolTable;
fEntityManager = entityManager;
fErrorReporter = reporter;
| | public int | scanChar()Returns the next character on the input.
Note: The character is consumed.
if (DEBUG_BUFFER) {
System.out.print("(scanChar: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// scan character
int c = fCurrentEntity.ch[fCurrentEntity.position++];
boolean external = false;
if (c == '\n" ||
(c == '\r" && (external = fCurrentEntity.isExternal()))) {
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.ch[0] = (char)c;
load(1, false);
}
if (c == '\r" && external) {
if (fCurrentEntity.ch[fCurrentEntity.position++] != '\n") {
fCurrentEntity.position--;
}
c = '\n";
}
}
// return character that was scanned
if (DEBUG_BUFFER) {
System.out.print(")scanChar: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> '"+(char)c+"'");
}
fCurrentEntity.columnNumber++;
return c;
| | public int | scanContent(org.apache.xerces.xni.XMLString content)Scans a range of parsed character data, setting the fields of the
XMLString structure, appropriately.
Note: The characters are consumed.
Note: This method does not guarantee to return
the longest run of parsed character data. This method may return
before markup due to reaching the end of the input buffer or any
other reason.
Note: The fields contained in the XMLString
structure are not guaranteed to remain valid upon subsequent calls
to the entity scanner. Therefore, the caller is responsible for
immediately using the returned character data or making a copy of
the character data.
if (DEBUG_BUFFER) {
System.out.print("(scanContent: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
else if (fCurrentEntity.position == fCurrentEntity.count - 1) {
fCurrentEntity.ch[0] = fCurrentEntity.ch[fCurrentEntity.count - 1];
load(1, false);
fCurrentEntity.position = 0;
fCurrentEntity.startPosition = 0;
}
// normalize newlines
int offset = fCurrentEntity.position;
int c = fCurrentEntity.ch[offset];
int newlines = 0;
boolean external = fCurrentEntity.isExternal();
if (c == '\n" || (c == '\r" && external)) {
if (DEBUG_BUFFER) {
System.out.print("[newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
do {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c == '\r" && external) {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
fCurrentEntity.position = newlines;
fCurrentEntity.startPosition = newlines;
if (load(newlines, false)) {
break;
}
}
if (fCurrentEntity.ch[fCurrentEntity.position] == '\n") {
fCurrentEntity.position++;
offset++;
}
/*** NEWLINE NORMALIZATION ***/
else {
newlines++;
}
}
else if (c == '\n") {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
fCurrentEntity.position = newlines;
fCurrentEntity.startPosition = newlines;
if (load(newlines, false)) {
break;
}
}
}
else {
fCurrentEntity.position--;
break;
}
} while (fCurrentEntity.position < fCurrentEntity.count - 1);
for (int i = offset; i < fCurrentEntity.position; i++) {
fCurrentEntity.ch[i] = '\n";
}
int length = fCurrentEntity.position - offset;
if (fCurrentEntity.position == fCurrentEntity.count - 1) {
content.setValues(fCurrentEntity.ch, offset, length);
if (DEBUG_BUFFER) {
System.out.print("]newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
return -1;
}
if (DEBUG_BUFFER) {
System.out.print("]newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
}
// inner loop, scanning for content
while (fCurrentEntity.position < fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (!XMLChar.isContent(c)) {
fCurrentEntity.position--;
break;
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length - newlines;
content.setValues(fCurrentEntity.ch, offset, length);
// return next character
if (fCurrentEntity.position != fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position];
// REVISIT: Does this need to be updated to fix the
// #x0D ^#x0A newline normalization problem? -Ac
if (c == '\r" && external) {
c = '\n";
}
}
else {
c = -1;
}
if (DEBUG_BUFFER) {
System.out.print(")scanContent: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> '"+(char)c+"'");
}
return c;
| | public boolean | scanData(java.lang.String delimiter, org.apache.xerces.util.XMLStringBuffer buffer)Scans a range of character data up to the specified delimiter,
setting the fields of the XMLString structure, appropriately.
Note: The characters are consumed.
Note: This assumes that the internal buffer is
at least the same size, or bigger, than the length of the delimiter
and that the delimiter contains at least one character.
Note: This method does not guarantee to return
the longest run of character data. This method may return before
the delimiter due to reaching the end of the input buffer or any
other reason.
Note: The fields contained in the XMLString
structure are not guaranteed to remain valid upon subsequent calls
to the entity scanner. Therefore, the caller is responsible for
immediately using the returned character data or making a copy of
the character data.
// REVISIT: This method does not need to use a string buffer.
// The change would avoid the array copies and increase
// performance. -Ac
//
// Currently, this method is called for scanning CDATA
// sections, comments, and processing instruction data.
// So if this code is updated to NOT buffer, the scanning
// code for comments and processing instructions will
// need to be updated to do its own buffering. The code
// for CDATA sections is safe as-is. -Ac
boolean found = false;
int delimLen = delimiter.length();
char charAt0 = delimiter.charAt(0);
boolean external = fCurrentEntity.isExternal();
if (DEBUG_BUFFER) {
System.out.print("(scanData: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
boolean bNextEntity = false;
while ((fCurrentEntity.position > fCurrentEntity.count - delimLen)
&& (!bNextEntity))
{
System.arraycopy(fCurrentEntity.ch,
fCurrentEntity.position,
fCurrentEntity.ch,
0,
fCurrentEntity.count - fCurrentEntity.position);
bNextEntity = load(fCurrentEntity.count - fCurrentEntity.position, false);
fCurrentEntity.position = 0;
fCurrentEntity.startPosition = 0;
}
if (fCurrentEntity.position > fCurrentEntity.count - delimLen) {
// something must be wrong with the input: e.g., file ends in an unterminated comment
int length = fCurrentEntity.count - fCurrentEntity.position;
buffer.append (fCurrentEntity.ch, fCurrentEntity.position, length);
fCurrentEntity.columnNumber += fCurrentEntity.count;
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
fCurrentEntity.position = fCurrentEntity.count;
fCurrentEntity.startPosition = fCurrentEntity.count;
load(0,true);
return false;
}
// normalize newlines
int offset = fCurrentEntity.position;
int c = fCurrentEntity.ch[offset];
int newlines = 0;
if (c == '\n" || (c == '\r" && external)) {
if (DEBUG_BUFFER) {
System.out.print("[newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
do {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c == '\r" && external) {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
fCurrentEntity.position = newlines;
fCurrentEntity.startPosition = newlines;
if (load(newlines, false)) {
break;
}
}
if (fCurrentEntity.ch[fCurrentEntity.position] == '\n") {
fCurrentEntity.position++;
offset++;
}
/*** NEWLINE NORMALIZATION ***/
else {
newlines++;
}
}
else if (c == '\n") {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
fCurrentEntity.position = newlines;
fCurrentEntity.startPosition = newlines;
fCurrentEntity.count = newlines;
if (load(newlines, false)) {
break;
}
}
}
else {
fCurrentEntity.position--;
break;
}
} while (fCurrentEntity.position < fCurrentEntity.count - 1);
for (int i = offset; i < fCurrentEntity.position; i++) {
fCurrentEntity.ch[i] = '\n";
}
int length = fCurrentEntity.position - offset;
if (fCurrentEntity.position == fCurrentEntity.count - 1) {
buffer.append(fCurrentEntity.ch, offset, length);
if (DEBUG_BUFFER) {
System.out.print("]newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
return true;
}
if (DEBUG_BUFFER) {
System.out.print("]newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
}
// iterate over buffer looking for delimiter
OUTER: while (fCurrentEntity.position < fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c == charAt0) {
// looks like we just hit the delimiter
int delimOffset = fCurrentEntity.position - 1;
for (int i = 1; i < delimLen; i++) {
if (fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.position -= i;
break OUTER;
}
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (delimiter.charAt(i) != c) {
fCurrentEntity.position--;
break;
}
}
if (fCurrentEntity.position == delimOffset + delimLen) {
found = true;
break;
}
}
else if (c == '\n" || (external && c == '\r")) {
fCurrentEntity.position--;
break;
}
else if (XMLChar.isInvalid(c)) {
fCurrentEntity.position--;
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length - newlines;
buffer.append(fCurrentEntity.ch, offset, length);
return true;
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length - newlines;
if (found) {
length -= delimLen;
}
buffer.append (fCurrentEntity.ch, offset, length);
// return true if string was skipped
if (DEBUG_BUFFER) {
System.out.print(")scanData: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> " + !found);
}
return !found;
| | public int | scanLiteral(int quote, org.apache.xerces.xni.XMLString content)Scans a range of attribute value data, setting the fields of the
XMLString structure, appropriately.
Note: The characters are consumed.
Note: This method does not guarantee to return
the longest run of attribute value data. This method may return
before the quote character due to reaching the end of the input
buffer or any other reason.
Note: The fields contained in the XMLString
structure are not guaranteed to remain valid upon subsequent calls
to the entity scanner. Therefore, the caller is responsible for
immediately using the returned character data or making a copy of
the character data.
if (DEBUG_BUFFER) {
System.out.print("(scanLiteral, '"+(char)quote+"': ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
else if (fCurrentEntity.position == fCurrentEntity.count - 1) {
fCurrentEntity.ch[0] = fCurrentEntity.ch[fCurrentEntity.count - 1];
load(1, false);
fCurrentEntity.position = 0;
fCurrentEntity.startPosition = 0;
}
// normalize newlines
int offset = fCurrentEntity.position;
int c = fCurrentEntity.ch[offset];
int newlines = 0;
boolean external = fCurrentEntity.isExternal();
if (c == '\n" || (c == '\r" && external)) {
if (DEBUG_BUFFER) {
System.out.print("[newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
do {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c == '\r" && external) {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
fCurrentEntity.position = newlines;
fCurrentEntity.startPosition = newlines;
if (load(newlines, false)) {
break;
}
}
if (fCurrentEntity.ch[fCurrentEntity.position] == '\n") {
fCurrentEntity.position++;
offset++;
}
/*** NEWLINE NORMALIZATION ***/
else {
newlines++;
}
/***/
}
else if (c == '\n") {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition);
fCurrentEntity.position = newlines;
fCurrentEntity.startPosition = newlines;
if (load(newlines, false)) {
break;
}
}
}
else {
fCurrentEntity.position--;
break;
}
} while (fCurrentEntity.position < fCurrentEntity.count - 1);
for (int i = offset; i < fCurrentEntity.position; i++) {
fCurrentEntity.ch[i] = '\n";
}
int length = fCurrentEntity.position - offset;
if (fCurrentEntity.position == fCurrentEntity.count - 1) {
content.setValues(fCurrentEntity.ch, offset, length);
if (DEBUG_BUFFER) {
System.out.print("]newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
return -1;
}
if (DEBUG_BUFFER) {
System.out.print("]newline, "+offset+", "+fCurrentEntity.position+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
}
// scan literal value
while (fCurrentEntity.position < fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if ((c == quote &&
(!fCurrentEntity.literal || external))
|| c == '%" || !XMLChar.isContent(c)) {
fCurrentEntity.position--;
break;
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length - newlines;
content.setValues(fCurrentEntity.ch, offset, length);
// return next character
if (fCurrentEntity.position != fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position];
// NOTE: We don't want to accidentally signal the
// end of the literal if we're expanding an
// entity appearing in the literal. -Ac
if (c == quote && fCurrentEntity.literal) {
c = -1;
}
}
else {
c = -1;
}
if (DEBUG_BUFFER) {
System.out.print(")scanLiteral, '"+(char)quote+"': ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> '"+(char)c+"'");
}
return c;
| | public java.lang.String | scanNCName()Returns a string matching the NCName production appearing immediately
on the input as a symbol, or null if no NCName string is present.
Note: The NCName characters are consumed.
Note: The string returned must be a symbol. The
SymbolTable can be used for this purpose.
if (DEBUG_BUFFER) {
System.out.print("(scanNCName: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// scan name
int offset = fCurrentEntity.position;
if (XMLChar.isNCNameStart(fCurrentEntity.ch[offset])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.ch[0] = fCurrentEntity.ch[offset];
offset = 0;
if (load(1, false)) {
fCurrentEntity.columnNumber++;
String symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 1);
if (DEBUG_BUFFER) {
System.out.print(")scanNCName: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> "+String.valueOf(symbol));
}
return symbol;
}
}
while (XMLChar.isNCName(fCurrentEntity.ch[fCurrentEntity.position])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
int length = fCurrentEntity.position - offset;
if (length == fCurrentEntity.ch.length) {
// bad luck we have to resize our buffer
char[] tmp = new char[fCurrentEntity.ch.length << 1];
System.arraycopy(fCurrentEntity.ch, offset,
tmp, 0, length);
fCurrentEntity.ch = tmp;
}
else {
System.arraycopy(fCurrentEntity.ch, offset,
fCurrentEntity.ch, 0, length);
}
offset = 0;
if (load(length, false)) {
break;
}
}
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length;
// return name
String symbol = null;
if (length > 0) {
symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length);
}
if (DEBUG_BUFFER) {
System.out.print(")scanNCName: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> "+String.valueOf(symbol));
}
return symbol;
| | public java.lang.String | scanName()Returns a string matching the Name production appearing immediately
on the input as a symbol, or null if no Name string is present.
Note: The Name characters are consumed.
Note: The string returned must be a symbol. The
SymbolTable can be used for this purpose.
if (DEBUG_BUFFER) {
System.out.print("(scanName: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// scan name
int offset = fCurrentEntity.position;
if (XMLChar.isNameStart(fCurrentEntity.ch[offset])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.ch[0] = fCurrentEntity.ch[offset];
offset = 0;
if (load(1, false)) {
fCurrentEntity.columnNumber++;
String symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 1);
if (DEBUG_BUFFER) {
System.out.print(")scanName: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> "+String.valueOf(symbol));
}
return symbol;
}
}
while (XMLChar.isName(fCurrentEntity.ch[fCurrentEntity.position])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
int length = fCurrentEntity.position - offset;
if (length == fCurrentEntity.ch.length) {
// bad luck we have to resize our buffer
char[] tmp = new char[fCurrentEntity.ch.length << 1];
System.arraycopy(fCurrentEntity.ch, offset,
tmp, 0, length);
fCurrentEntity.ch = tmp;
}
else {
System.arraycopy(fCurrentEntity.ch, offset,
fCurrentEntity.ch, 0, length);
}
offset = 0;
if (load(length, false)) {
break;
}
}
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length;
// return name
String symbol = null;
if (length > 0) {
symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length);
}
if (DEBUG_BUFFER) {
System.out.print(")scanName: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> "+String.valueOf(symbol));
}
return symbol;
| | public java.lang.String | scanNmtoken()Returns a string matching the NMTOKEN production appearing immediately
on the input as a symbol, or null if NMTOKEN Name string is present.
Note: The NMTOKEN characters are consumed.
Note: The string returned must be a symbol. The
SymbolTable can be used for this purpose.
if (DEBUG_BUFFER) {
System.out.print("(scanNmtoken: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// scan nmtoken
int offset = fCurrentEntity.position;
while (XMLChar.isName(fCurrentEntity.ch[fCurrentEntity.position])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
int length = fCurrentEntity.position - offset;
if (length == fCurrentEntity.ch.length) {
// bad luck we have to resize our buffer
char[] tmp = new char[fCurrentEntity.ch.length << 1];
System.arraycopy(fCurrentEntity.ch, offset,
tmp, 0, length);
fCurrentEntity.ch = tmp;
}
else {
System.arraycopy(fCurrentEntity.ch, offset,
fCurrentEntity.ch, 0, length);
}
offset = 0;
if (load(length, false)) {
break;
}
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length;
// return nmtoken
String symbol = null;
if (length > 0) {
symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length);
}
if (DEBUG_BUFFER) {
System.out.print(")scanNmtoken: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> "+String.valueOf(symbol));
}
return symbol;
| | public boolean | scanQName(org.apache.xerces.xni.QName qname)Scans a qualified name from the input, setting the fields of the
QName structure appropriately.
Note: The qualified name characters are consumed.
Note: The strings used to set the values of the
QName structure must be symbols. The SymbolTable can be used for
this purpose.
if (DEBUG_BUFFER) {
System.out.print("(scanQName, "+qname+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// scan qualified name
int offset = fCurrentEntity.position;
if (XMLChar.isNCNameStart(fCurrentEntity.ch[offset])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.ch[0] = fCurrentEntity.ch[offset];
offset = 0;
if (load(1, false)) {
fCurrentEntity.columnNumber++;
String name =
fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 1);
qname.setValues(null, name, name, null);
if (DEBUG_BUFFER) {
System.out.print(")scanQName, "+qname+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> true");
}
return true;
}
}
int index = -1;
while (XMLChar.isName(fCurrentEntity.ch[fCurrentEntity.position])) {
char c = fCurrentEntity.ch[fCurrentEntity.position];
if (c == ':") {
if (index != -1) {
break;
}
index = fCurrentEntity.position;
}
if (++fCurrentEntity.position == fCurrentEntity.count) {
int length = fCurrentEntity.position - offset;
if (length == fCurrentEntity.ch.length) {
// bad luck we have to resize our buffer
char[] tmp = new char[fCurrentEntity.ch.length << 1];
System.arraycopy(fCurrentEntity.ch, offset,
tmp, 0, length);
fCurrentEntity.ch = tmp;
}
else {
System.arraycopy(fCurrentEntity.ch, offset,
fCurrentEntity.ch, 0, length);
}
if (index != -1) {
index = index - offset;
}
offset = 0;
if (load(length, false)) {
break;
}
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length;
if (length > 0) {
String prefix = null;
String localpart = null;
String rawname = fSymbolTable.addSymbol(fCurrentEntity.ch,
offset, length);
if (index != -1) {
int prefixLength = index - offset;
prefix = fSymbolTable.addSymbol(fCurrentEntity.ch,
offset, prefixLength);
int len = length - prefixLength - 1;
int startLocal = index +1;
if (!XMLChar.isNCNameStart(fCurrentEntity.ch[startLocal])){
fErrorReporter.reportError(XMLMessageFormatter.XML_DOMAIN,
"IllegalQName",
null,
XMLErrorReporter.SEVERITY_FATAL_ERROR);
}
localpart = fSymbolTable.addSymbol(fCurrentEntity.ch,
startLocal, len);
}
else {
localpart = rawname;
}
qname.setValues(prefix, localpart, rawname, null);
if (DEBUG_BUFFER) {
System.out.print(")scanQName, "+qname+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> true");
}
return true;
}
}
// no qualified name found
if (DEBUG_BUFFER) {
System.out.print(")scanQName, "+qname+": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> false");
}
return false;
| | public final void | setBufferSize(int size)
// REVISIT: Buffer size passed to entity scanner
// was not being kept in synch with the actual size
// of the buffers in each scanned entity. If any
// of the buffers were actually resized, it was possible
// that the parser would throw an ArrayIndexOutOfBoundsException
// for documents which contained names which are longer than
// the current buffer size. Conceivably the buffer size passed
// to entity scanner could be used to determine a minimum size
// for resizing, if doubling its size is smaller than this
// minimum. -- mrglavas
fBufferSize = size;
| | public final void | setCurrentEntity(XMLEntityManager.ScannedEntity ent)
fCurrentEntity = ent;
| | public final void | setEncoding(java.lang.String encoding)Sets the encoding of the scanner. This method is used by the
scanners if the XMLDecl or TextDecl line contains an encoding
pseudo-attribute.
Note: The underlying character reader on the
current entity will be changed to accomodate the new encoding.
However, the new encoding is ignored if the current reader was
not constructed from an input stream (e.g. an external entity
that is resolved directly to the appropriate java.io.Reader
object).
if (DEBUG_ENCODINGS) {
System.out.println("$$$ setEncoding: "+encoding);
}
if (fCurrentEntity.stream != null) {
// if the encoding is the same, don't change the reader and
// re-use the original reader used by the OneCharReader
// NOTE: Besides saving an object, this overcomes deficiencies
// in the UTF-16 reader supplied with the standard Java
// distribution (up to and including 1.3). The UTF-16
// decoder buffers 8K blocks even when only asked to read
// a single char! -Ac
if (fCurrentEntity.encoding == null ||
!fCurrentEntity.encoding.equals(encoding)) {
// UTF-16 is a bit of a special case. If the encoding is UTF-16,
// and we know the endian-ness, we shouldn't change readers.
// If it's ISO-10646-UCS-(2|4), then we'll have to deduce
// the endian-ness from the encoding we presently have.
if(fCurrentEntity.encoding != null && fCurrentEntity.encoding.startsWith("UTF-16")) {
String ENCODING = encoding.toUpperCase(Locale.ENGLISH);
if(ENCODING.equals("UTF-16")) return;
if(ENCODING.equals("ISO-10646-UCS-4")) {
if(fCurrentEntity.encoding.equals("UTF-16BE")) {
fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS4BE);
} else {
fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS4LE);
}
return;
}
if(ENCODING.equals("ISO-10646-UCS-2")) {
if(fCurrentEntity.encoding.equals("UTF-16BE")) {
fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS2BE);
} else {
fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS2LE);
}
return;
}
}
// wrap a new reader around the input stream, changing
// the encoding
if (DEBUG_ENCODINGS) {
System.out.println("$$$ creating new reader from stream: "+
fCurrentEntity.stream);
}
//fCurrentEntity.stream.reset();
fCurrentEntity.setReader(fCurrentEntity.stream, encoding, null);
fCurrentEntity.encoding = encoding;
} else {
if (DEBUG_ENCODINGS)
System.out.println("$$$ reusing old reader on stream");
}
}
| | public final void | setXMLVersion(java.lang.String xmlVersion)Sets the XML version. This method is used by the
scanners to report the value of the version pseudo-attribute
in an XML or text declaration.
fCurrentEntity.xmlVersion = xmlVersion;
| | public boolean | skipChar(int c)Skips a character appearing immediately on the input.
Note: The character is consumed only if it matches
the specified character.
if (DEBUG_BUFFER) {
System.out.print("(skipChar, '"+(char)c+"': ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// skip character
int cc = fCurrentEntity.ch[fCurrentEntity.position];
if (cc == c) {
fCurrentEntity.position++;
if (c == '\n") {
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
}
else {
fCurrentEntity.columnNumber++;
}
if (DEBUG_BUFFER) {
System.out.print(")skipChar, '"+(char)c+"': ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> true");
}
return true;
}
else if (c == '\n" && cc == '\r" && fCurrentEntity.isExternal()) {
// handle newlines
if (fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.ch[0] = (char)cc;
load(1, false);
}
fCurrentEntity.position++;
if (fCurrentEntity.ch[fCurrentEntity.position] == '\n") {
fCurrentEntity.position++;
}
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (DEBUG_BUFFER) {
System.out.print(")skipChar, '"+(char)c+"': ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> true");
}
return true;
}
// character was not skipped
if (DEBUG_BUFFER) {
System.out.print(")skipChar, '"+(char)c+"': ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> false");
}
return false;
| | public final boolean | skipDeclSpaces()Skips space characters appearing immediately on the input that would
match non-terminal S (0x09, 0x0A, 0x0D, 0x20) before end of line
normalization is performed. This is useful when scanning structures
such as the XMLDecl and TextDecl that can only contain US-ASCII
characters.
Note: The characters are consumed only if they would
match non-terminal S before end of line normalization is performed.
if (DEBUG_BUFFER) {
System.out.print("(skipDeclSpaces: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// skip spaces
int c = fCurrentEntity.ch[fCurrentEntity.position];
if (XMLChar.isSpace(c)) {
boolean external = fCurrentEntity.isExternal();
do {
boolean entityChanged = false;
// handle newlines
if (c == '\n" || (external && c == '\r")) {
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count - 1) {
fCurrentEntity.ch[0] = (char)c;
entityChanged = load(1, true);
if (!entityChanged) {
// the load change the position to be 1,
// need to restore it when entity not changed
fCurrentEntity.position = 0;
fCurrentEntity.startPosition = 0;
}
}
if (c == '\r" && external) {
// REVISIT: Does this need to be updated to fix the
// #x0D ^#x0A newline normalization problem? -Ac
if (fCurrentEntity.ch[++fCurrentEntity.position] != '\n") {
fCurrentEntity.position--;
}
}
/*** NEWLINE NORMALIZATION ***
else {
if (fCurrentEntity.ch[fCurrentEntity.position + 1] == '\r'
&& external) {
fCurrentEntity.position++;
}
}
/***/
}
else {
fCurrentEntity.columnNumber++;
}
// load more characters, if needed
if (!entityChanged)
fCurrentEntity.position++;
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
} while (XMLChar.isSpace(c = fCurrentEntity.ch[fCurrentEntity.position]));
if (DEBUG_BUFFER) {
System.out.print(")skipDeclSpaces: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> true");
}
return true;
}
// no spaces were found
if (DEBUG_BUFFER) {
System.out.print(")skipDeclSpaces: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> false");
}
return false;
| | public boolean | skipSpaces()Skips space characters appearing immediately on the input.
Note: The characters are consumed only if they are
space characters.
if (DEBUG_BUFFER) {
System.out.print("(skipSpaces: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// skip spaces
int c = fCurrentEntity.ch[fCurrentEntity.position];
if (XMLChar.isSpace(c)) {
boolean external = fCurrentEntity.isExternal();
do {
boolean entityChanged = false;
// handle newlines
if (c == '\n" || (external && c == '\r")) {
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count - 1) {
fCurrentEntity.ch[0] = (char)c;
entityChanged = load(1, true);
if (!entityChanged) {
// the load change the position to be 1,
// need to restore it when entity not changed
fCurrentEntity.position = 0;
fCurrentEntity.startPosition = 0;
}
}
if (c == '\r" && external) {
// REVISIT: Does this need to be updated to fix the
// #x0D ^#x0A newline normalization problem? -Ac
if (fCurrentEntity.ch[++fCurrentEntity.position] != '\n") {
fCurrentEntity.position--;
}
}
/*** NEWLINE NORMALIZATION ***
else {
if (fCurrentEntity.ch[fCurrentEntity.position + 1] == '\r'
&& external) {
fCurrentEntity.position++;
}
}
/***/
}
else {
fCurrentEntity.columnNumber++;
}
// load more characters, if needed
if (!entityChanged)
fCurrentEntity.position++;
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
} while (XMLChar.isSpace(c = fCurrentEntity.ch[fCurrentEntity.position]));
if (DEBUG_BUFFER) {
System.out.print(")skipSpaces: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> true");
}
return true;
}
// no spaces were found
if (DEBUG_BUFFER) {
System.out.print(")skipSpaces: ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> false");
}
return false;
| | public boolean | skipString(java.lang.String s)Skips the specified string appearing immediately on the input.
Note: The characters are consumed only if they are
space characters.
if (DEBUG_BUFFER) {
System.out.print("(skipString, \""+s+"\": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println();
}
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// skip string
final int length = s.length();
for (int i = 0; i < length; i++) {
char c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c != s.charAt(i)) {
fCurrentEntity.position -= i + 1;
if (DEBUG_BUFFER) {
System.out.print(")skipString, \""+s+"\": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> false");
}
return false;
}
if (i < length - 1 && fCurrentEntity.position == fCurrentEntity.count) {
System.arraycopy(fCurrentEntity.ch, fCurrentEntity.count - i - 1, fCurrentEntity.ch, 0, i + 1);
// REVISIT: Can a string to be skipped cross an
// entity boundary? -Ac
if (load(i + 1, false)) {
fCurrentEntity.startPosition -= i + 1;
fCurrentEntity.position -= i + 1;
if (DEBUG_BUFFER) {
System.out.print(")skipString, \""+s+"\": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> false");
}
return false;
}
}
}
if (DEBUG_BUFFER) {
System.out.print(")skipString, \""+s+"\": ");
XMLEntityManager.print(fCurrentEntity);
System.out.println(" -> true");
}
fCurrentEntity.columnNumber += length;
return true;
|
|
