org.apache.xerces.impl.XML11DTDScannerImpl Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of xercesImpl Show documentation
Show all versions of xercesImpl Show documentation
Xerces2 is the next generation of high performance, fully compliant XML parsers in the Apache Xerces family.
This new version of Xerces introduces the Xerces Native Interface (XNI), a complete framework for building
parser components and configurations that is extremely modular and easy to program. The Apache Xerces2 parser is
the reference implementation of XNI but other parser components, configurations, and parsers can be written
using the Xerces Native Interface. For complete design and implementation documents, refer to the XNI Manual.
Xerces2 is a fully conforming XML Schema 1.0 processor. A partial experimental implementation of the XML Schema
1.1 Structures and Datatypes Working Drafts (December 2009) and an experimental implementation of the XML Schema
Definition Language (XSD): Component Designators (SCD) Candidate Recommendation (January 2010) are provided for
evaluation. For more information, refer to the XML Schema page. Xerces2 also provides a complete implementation
of the Document Object Model Level 3 Core and Load/Save W3C Recommendations and provides a complete
implementation of the XML Inclusions (XInclude) W3C Recommendation. It also provides support for OASIS XML
Catalogs v1.1. Xerces2 is able to parse documents written according to the XML 1.1 Recommendation, except that
it does not yet provide an option to enable normalization checking as described in section 2.13 of this
specification. It also handles namespaces according to the XML Namespaces 1.1 Recommendation, and will correctly
serialize XML 1.1 documents if the DOM level 3 load/save APIs are in use.
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.xerces.impl;
import java.io.IOException;
import org.apache.xerces.util.SymbolTable;
import org.apache.xerces.util.XML11Char;
import org.apache.xerces.util.XMLChar;
import org.apache.xerces.util.XMLStringBuffer;
import org.apache.xerces.xni.XMLString;
import org.apache.xerces.xni.XNIException;
/**
* This class is responsible for scanning the declarations found
* in the internal and external subsets of a DTD in an XML document.
* The scanner acts as the sources for the DTD information which is
* communicated to the DTD handlers.
*
* This component requires the following features and properties from the
* component manager that uses it:
*
* - http://xml.org/sax/features/validation
* - http://apache.org/xml/features/scanner/notify-char-refs
* - http://apache.org/xml/properties/internal/symbol-table
* - http://apache.org/xml/properties/internal/error-reporter
* - http://apache.org/xml/properties/internal/entity-manager
*
*
* @xerces.internal
*
* @author Arnaud Le Hors, IBM
* @author Andy Clark, IBM
* @author Glenn Marcy, IBM
* @author Eric Ye, IBM
*
* @version $Id: XML11DTDScannerImpl.java 572055 2007-09-02 17:55:43Z mrglavas $
*/
public class XML11DTDScannerImpl
extends XMLDTDScannerImpl {
/** String buffer. */
private final XMLStringBuffer fStringBuffer = new XMLStringBuffer();
//
// Constructors
//
/** Default constructor. */
public XML11DTDScannerImpl() {super();} // ()
/** Constructor for he use of non-XMLComponentManagers. */
public XML11DTDScannerImpl(SymbolTable symbolTable,
XMLErrorReporter errorReporter, XMLEntityManager entityManager) {
super(symbolTable, errorReporter, entityManager);
}
//
// XMLDTDScanner methods
//
//
// XMLScanner methods
//
// NOTE: this is a carbon copy of the code in XML11DocumentScannerImpl;
// we need to override these methods in both places. Ah for
// multiple inheritance...
// This needs to be refactored!!! - NG
/**
* Scans public ID literal.
*
* [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"
* [13] PubidChar::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]
*
* The returned string is normalized according to the following rule,
* from http://www.w3.org/TR/REC-xml#dt-pubid:
*
* Before a match is attempted, all strings of white space in the public
* identifier must be normalized to single space characters (#x20), and
* leading and trailing white space must be removed.
*
* @param literal The string to fill in with the public ID literal.
* @return True on success.
*
* Note: This method uses fStringBuffer, anything in it at
* the time of calling is lost.
*/
protected boolean scanPubidLiteral(XMLString literal)
throws IOException, XNIException
{
int quote = fEntityScanner.scanChar();
if (quote != '\'' && quote != '"') {
reportFatalError("QuoteRequiredInPublicID", null);
return false;
}
fStringBuffer.clear();
// skip leading whitespace
boolean skipSpace = true;
boolean dataok = true;
while (true) {
int c = fEntityScanner.scanChar();
// REVISIT: it could really only be \n or 0x20; all else is normalized, no? - neilg
if (c == ' ' || c == '\n' || c == '\r' || c == 0x85 || c == 0x2028) {
if (!skipSpace) {
// take the first whitespace as a space and skip the others
fStringBuffer.append(' ');
skipSpace = true;
}
}
else if (c == quote) {
if (skipSpace) {
// if we finished on a space let's trim it
fStringBuffer.length--;
}
literal.setValues(fStringBuffer);
break;
}
else if (XMLChar.isPubid(c)) {
fStringBuffer.append((char)c);
skipSpace = false;
}
else if (c == -1) {
reportFatalError("PublicIDUnterminated", null);
return false;
}
else {
dataok = false;
reportFatalError("InvalidCharInPublicID",
new Object[]{Integer.toHexString(c)});
}
}
return dataok;
}
/**
* Normalize whitespace in an XMLString converting all whitespace
* characters to space characters.
*/
protected void normalizeWhitespace(XMLString value) {
int end = value.offset + value.length;
for (int i = value.offset; i < end; ++i) {
int c = value.ch[i];
if (XMLChar.isSpace(c)) {
value.ch[i] = ' ';
}
}
}
/**
* Normalize whitespace in an XMLString converting all whitespace
* characters to space characters.
*/
protected void normalizeWhitespace(XMLString value, int fromIndex) {
int end = value.offset + value.length;
for (int i = value.offset + fromIndex; i < end; ++i) {
int c = value.ch[i];
if (XMLChar.isSpace(c)) {
value.ch[i] = ' ';
}
}
}
/**
* Checks whether this string would be unchanged by normalization.
*
* @return -1 if the value would be unchanged by normalization,
* otherwise the index of the first whitespace character which
* would be transformed.
*/
protected int isUnchangedByNormalization(XMLString value) {
int end = value.offset + value.length;
for (int i = value.offset; i < end; ++i) {
int c = value.ch[i];
if (XMLChar.isSpace(c)) {
return i - value.offset;
}
}
return -1;
}
// returns true if the given character is not
// valid with respect to the version of
// XML understood by this scanner.
protected boolean isInvalid(int value) {
return (!XML11Char.isXML11Valid(value));
} // isInvalid(int): boolean
// returns true if the given character is not
// valid or may not be used outside a character reference
// with respect to the version of XML understood by this scanner.
protected boolean isInvalidLiteral(int value) {
return (!XML11Char.isXML11ValidLiteral(value));
} // isInvalidLiteral(int): boolean
// returns true if the given character is
// a valid nameChar with respect to the version of
// XML understood by this scanner.
protected boolean isValidNameChar(int value) {
return (XML11Char.isXML11Name(value));
} // isValidNameChar(int): boolean
// returns true if the given character is
// a valid nameStartChar with respect to the version of
// XML understood by this scanner.
protected boolean isValidNameStartChar(int value) {
return (XML11Char.isXML11NameStart(value));
} // isValidNameStartChar(int): boolean
// returns true if the given character is
// a valid NCName character with respect to the version of
// XML understood by this scanner.
protected boolean isValidNCName(int value) {
return (XML11Char.isXML11NCName(value));
} // isValidNCName(int): boolean
// returns true if the given character is
// a valid high surrogate for a nameStartChar
// with respect to the version of XML understood
// by this scanner.
protected boolean isValidNameStartHighSurrogate(int value) {
return XML11Char.isXML11NameHighSurrogate(value);
} // isValidNameStartHighSurrogate(int): boolean
// note that, according to 4.3.4 of the XML 1.1 spec, XML 1.1
// documents may invoke 1.0 entities; thus either version decl (or none!)
// is allowed to appear in this context
protected boolean versionSupported(String version) {
return version.equals("1.1") || version.equals ("1.0");
} // versionSupported(String): boolean
// returns the error message key for unsupported
// versions of XML with respect to the version of
// XML understood by this scanner.
protected String getVersionNotSupportedKey () {
return "VersionNotSupported11";
} // getVersionNotSupportedKey: String
} // class XML11DTDScannerImpl