com.sun.org.apache.xerces.internal.util.XMLChar Java Examples

/**
 * Checks that "content" string is valid IDREF value.
 * If invalid a Datatype validation exception is thrown.
 *
 * @param content       the string value that needs to be validated
 * @param context       the validation context
 * @throws InvalidDatatypeException if the content is
 *         invalid according to the rules for the validators
 * @see InvalidDatatypeValueException
 */
public void validate(String content, ValidationContext context) throws InvalidDatatypeValueException {

    //Check if is valid key-[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
    if(context.useNamespaces()) {
        if (!XMLChar.isValidNCName(content)) {
            throw new InvalidDatatypeValueException("IDREFInvalidWithNamespaces", new Object[]{content});
        }
    }
    else {
        if (!XMLChar.isValidName(content)) {
            throw new InvalidDatatypeValueException("IDREFInvalid", new Object[]{content});
        }
    }

    context.addIdRef(content);

}
 

/**
 * Checks that "content" string is valid IDREF value.
 * If invalid a Datatype validation exception is thrown.
 *
 * @param content       the string value that needs to be validated
 * @param context       the validation context
 * @throws InvalidDatatypeException if the content is
 *         invalid according to the rules for the validators
 * @see InvalidDatatypeValueException
 */
public void validate(String content, ValidationContext context) throws InvalidDatatypeValueException {

    //Check if is valid key-[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
    if(context.useNamespaces()) {
        if (!XMLChar.isValidNCName(content)) {
            throw new InvalidDatatypeValueException("IDREFInvalidWithNamespaces", new Object[]{content});
        }
    }
    else {
        if (!XMLChar.isValidName(content)) {
            throw new InvalidDatatypeValueException("IDREFInvalid", new Object[]{content});
        }
    }

    context.addIdRef(content);

}
 

/**
 * Checks that "content" string is valid ID value.
 * If invalid a Datatype validation exception is thrown.
 *
 * @param content       the string value that needs to be validated
 * @param context       the validation context
 * @throws InvalidDatatypeException if the content is
 *         invalid according to the rules for the validators
 * @see InvalidDatatypeValueException
 */
public void validate(String content, ValidationContext context) throws InvalidDatatypeValueException {

    //Check if is valid key-[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
    if(context.useNamespaces()) {
        if (!XMLChar.isValidNCName(content)) {
            throw new InvalidDatatypeValueException("IDInvalidWithNamespaces", new Object[]{content});
        }
    }
    else {
        if (!XMLChar.isValidName(content)) {
            throw new InvalidDatatypeValueException("IDInvalid", new Object[]{content});
        }
    }

    if (context.isIdDeclared(content)) {
        throw new InvalidDatatypeValueException("IDNotUnique", new Object[]{content});
    }

    context.addId(content);
}
 

/**
 * Checks that "content" string is valid ID value.
 * If invalid a Datatype validation exception is thrown.
 *
 * @param content       the string value that needs to be validated
 * @param context       the validation context
 * @throws InvalidDatatypeException if the content is
 *         invalid according to the rules for the validators
 * @see InvalidDatatypeValueException
 */
public void validate(String content, ValidationContext context) throws InvalidDatatypeValueException {

    //Check if is valid key-[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
    if(context.useNamespaces()) {
        if (!XMLChar.isValidNCName(content)) {
            throw new InvalidDatatypeValueException("IDInvalidWithNamespaces", new Object[]{content});
        }
    }
    else {
        if (!XMLChar.isValidName(content)) {
            throw new InvalidDatatypeValueException("IDInvalid", new Object[]{content});
        }
    }

    if (context.isIdDeclared(content)) {
        throw new InvalidDatatypeValueException("IDNotUnique", new Object[]{content});
    }

    context.addId(content);
}
 

/**
 * Checks that "content" string is valid ID value.
 * If invalid a Datatype validation exception is thrown.
 *
 * @param content       the string value that needs to be validated
 * @param context       the validation context
 * @throws InvalidDatatypeException if the content is
 *         invalid according to the rules for the validators
 * @see InvalidDatatypeValueException
 */
public void validate(String content, ValidationContext context) throws InvalidDatatypeValueException {

    //Check if is valid key-[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
    if(context.useNamespaces()) {
        if (!XMLChar.isValidNCName(content)) {
            throw new InvalidDatatypeValueException("IDInvalidWithNamespaces", new Object[]{content});
        }
    }
    else {
        if (!XMLChar.isValidName(content)) {
            throw new InvalidDatatypeValueException("IDInvalid", new Object[]{content});
        }
    }

    if (context.isIdDeclared(content)) {
        throw new InvalidDatatypeValueException("IDNotUnique", new Object[]{content});
    }

    context.addId(content);
}
 

/**
 * Scans surrogates and append them to the specified buffer.
 * <p>
 * <strong>Note:</strong> This assumes the current char has already been
 * identified as a high surrogate.
 *
 * @param buf The StringBuffer to append the read surrogates to.
 * @return True if it succeeded.
 */
protected boolean scanSurrogates(XMLStringBuffer buf)
throws IOException, XNIException {

    int high = fEntityScanner.scanChar(null);
    int low = fEntityScanner.peekChar();
    if (!XMLChar.isLowSurrogate(low)) {
        reportFatalError("InvalidCharInContent",
                new Object[] {Integer.toString(high, 16)});
                return false;
    }
    fEntityScanner.scanChar(null);

    // convert surrogates to supplemental character
    int c = XMLChar.supplemental((char)high, (char)low);

    // supplemental character must be a valid XML character
    if (isInvalid(c)) {
        reportFatalError("InvalidCharInContent",
                new Object[]{Integer.toString(c, 16)});
                return false;
    }

    // fill in the buffer
    buf.append((char)high);
    buf.append((char)low);

    return true;

}
 

public boolean characterData(String data, Augmentations augs) {

        fSawText = fSawText || data.length() > 0;

        // REVISIT: this methods basically duplicates implementation of
        //          handleCharacters(). We should be able to reuse some code

        // if whitespace == -1 skip normalization, because it is a complexType
        // or a union type.
        if (fNormalizeData && fWhiteSpace != -1 && fWhiteSpace != XSSimpleType.WS_PRESERVE) {
            // normalize data
            normalizeWhitespace(data, fWhiteSpace == XSSimpleType.WS_COLLAPSE);
            fBuffer.append(fNormalizedStr.ch, fNormalizedStr.offset, fNormalizedStr.length);
        } else {
            if (fAppendBuffer)
                fBuffer.append(data);
        }

        // When it's a complex type with element-only content, we need to
        // find out whether the content contains any non-whitespace character.
        boolean allWhiteSpace = true;
        if (fCurrentType != null
            && fCurrentType.getTypeCategory() == XSTypeDefinition.COMPLEX_TYPE) {
            XSComplexTypeDecl ctype = (XSComplexTypeDecl) fCurrentType;
            if (ctype.fContentType == XSComplexTypeDecl.CONTENTTYPE_ELEMENT) {
                // data outside of element content
                for (int i = 0; i < data.length(); i++) {
                    if (!XMLChar.isSpace(data.charAt(i))) {
                        allWhiteSpace = false;
                        fSawCharacters = true;
                        break;
                    }
                }
            }
        }

        return allWhiteSpace;
    }
 

/**
 * 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;
}
 

XMLString handleCharacters(XMLString text) {

        if (fSkipValidationDepth >= 0)
            return text;

        fSawText = fSawText || text.length > 0;

        // Note: data in EntityRef and CDATA is normalized as well
        // if whitespace == -1 skip normalization, because it is a complexType
        // or a union type.
        if (fNormalizeData && fWhiteSpace != -1 && fWhiteSpace != XSSimpleType.WS_PRESERVE) {
            // normalize data
            normalizeWhitespace(text, fWhiteSpace == XSSimpleType.WS_COLLAPSE);
            text = fNormalizedStr;
        }
        if (fAppendBuffer)
            fBuffer.append(text.ch, text.offset, text.length);

        // When it's a complex type with element-only content, we need to
        // find out whether the content contains any non-whitespace character.
        fSawOnlyWhitespaceInElementContent = false;
        if (fCurrentType != null
            && fCurrentType.getTypeCategory() == XSTypeDefinition.COMPLEX_TYPE) {
            XSComplexTypeDecl ctype = (XSComplexTypeDecl) fCurrentType;
            if (ctype.fContentType == XSComplexTypeDecl.CONTENTTYPE_ELEMENT) {
                // data outside of element content
                for (int i = text.offset; i < text.offset + text.length; i++) {
                    if (!XMLChar.isSpace(text.ch[i])) {
                        fSawCharacters = true;
                        break;
                    }
                    fSawOnlyWhitespaceInElementContent = !fSawCharacters;
                }
            }
        }

        return text;
    }
 

/**
 * Checks if the given qualified name is legal with respect
 * to the version of XML to which this document must conform.
 *
 * @param prefix prefix of qualified name
 * @param local local part of qualified name
 */
protected final void checkQName(String prefix, String local) {
    if (!errorChecking) {
        return;
    }

    // check that both prefix and local part match NCName
    boolean validNCName = false;
    if (!xml11Version) {
        validNCName = (prefix == null || XMLChar.isValidNCName(prefix))
                && XMLChar.isValidNCName(local);
    }
    else {
        validNCName = (prefix == null || XML11Char.isXML11ValidNCName(prefix))
                && XML11Char.isXML11ValidNCName(local);
    }

    if (!validNCName) {
        // REVISIT: add qname parameter to the message
        String msg =
        DOMMessageFormatter.formatMessage(
                        DOMMessageFormatter.DOM_DOMAIN,
                        "INVALID_CHARACTER_ERR",
                        null);
        throw new DOMException(DOMException.INVALID_CHARACTER_ERR, msg);
    }
}
 

boolean skipQElement(String rawname) throws IOException{

        final int c = fEntityScanner.getChar(rawname.length());
        //if this character is still valid element name -- this means string can't match
        if(XMLChar.isName(c)){
            return false;
        }else{
            return fEntityScanner.skipString(rawname);
        }
    }
 

/**
 * Scans a comment.
 * <p>
 * <pre>
 * [15] Comment ::= '&lt!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
 * </pre>
 * <p>
 * <strong>Note:</strong> Called after scanning past '&lt;!--'
 * <strong>Note:</strong> This method uses fString, anything in it
 * at the time of calling is lost.
 *
 * @param text The buffer to fill in with the text.
 */
protected void scanComment(XMLStringBuffer text)
throws IOException, XNIException {

    //System.out.println( "XMLScanner#scanComment# In Scan Comment" );
    // text
    // REVISIT: handle invalid character, eof
    text.clear();
    while (fEntityScanner.scanData("--", text, 0)) {
        int c = fEntityScanner.peekChar();

        //System.out.println( "XMLScanner#scanComment#text.toString() == " + text.toString() );
        //System.out.println( "XMLScanner#scanComment#c == " + c );

        if (c != -1) {
            if (XMLChar.isHighSurrogate(c)) {
                scanSurrogates(text);
            }
            else if (isInvalidLiteral(c)) {
                reportFatalError("InvalidCharInComment",
                        new Object[] { Integer.toHexString(c) });
                        fEntityScanner.scanChar(NameType.COMMENT);
            }
        }
    }
    if (!fEntityScanner.skipChar('>', NameType.COMMENT)) {
        reportFatalError("DashDashInComment", null);
    }

}
 

/**
 * 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] = ' ';
        }
    }
}
 

/**
 * Check the string against XML's definition of acceptable names for
 * elements and attributes and so on using the XMLCharacterProperties
 * utility class
 */

public static final boolean isXMLName(String s, boolean xml11Version) {

    if (s == null) {
        return false;
    }
    if(!xml11Version)
        return XMLChar.isValidName(s);
    else
        return XML11Char.isXML11ValidName(s);

}
 

/**
 * 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] = ' ';
        }
    }
}
 

protected void surrogates(int high, int low) throws IOException{
    if (XMLChar.isHighSurrogate(high)) {
        if (!XMLChar.isLowSurrogate(low)) {
            //Invalid XML
            fatalError("The character '"+(char)low+"' is an invalid XML character");
        }
        else {
            int supplemental = XMLChar.supplemental((char)high, (char)low);
            if (!XMLChar.isValid(supplemental)) {
                //Invalid XML
                fatalError("The character '"+(char)supplemental+"' is an invalid XML character");
            }
            else {
                if (content().inCData ) {
                    _printer.printText("]]>&#x");
                    _printer.printText(Integer.toHexString(supplemental));
                    _printer.printText(";<![CDATA[");
                }
                else {
                    printHex(supplemental);
                }
            }
        }
    } else {
        fatalError("The character '"+(char)high+"' is an invalid XML character");
    }

}
 

private void normalizeWhitespace(String value, boolean collapse) {
    boolean skipSpace = collapse;
    char c;
    int size = value.length();

    // ensure the ch array is big enough
    if (fNormalizedStr.ch == null || fNormalizedStr.ch.length < size) {
        fNormalizedStr.ch = new char[size];
    }
    fNormalizedStr.offset = 0;
    fNormalizedStr.length = 0;

    for (int i = 0; i < size; i++) {
        c = value.charAt(i);
        if (XMLChar.isSpace(c)) {
            if (!skipSpace) {
                // take the first whitespace as a space and skip the others
                fNormalizedStr.ch[fNormalizedStr.length++] = ' ';
                skipSpace = collapse;
            }
        } else {
            fNormalizedStr.ch[fNormalizedStr.length++] = c;
            skipSpace = false;
        }
    }
    if (skipSpace) {
        if (fNormalizedStr.length != 0)
            // if we finished on a space trim it but also record it
            fNormalizedStr.length--;
    }
}
 

public Object getActualValue(String content, ValidationContext context)
    throws InvalidDatatypeValueException {

    // "prefix:localpart" or "localpart"
    // get prefix and local part out of content
    String prefix, localpart;
    int colonptr = content.indexOf(":");
    if (colonptr > 0) {
        prefix = context.getSymbol(content.substring(0,colonptr));
        localpart = content.substring(colonptr+1);
    } else {
        prefix = EMPTY_STRING;
        localpart = content;
    }

    // both prefix (if any) a nd localpart must be valid NCName
    if (prefix.length() > 0 && !XMLChar.isValidNCName(prefix))
        throw new InvalidDatatypeValueException("cvc-datatype-valid.1.2.1", new Object[]{content, "QName"});

    if(!XMLChar.isValidNCName(localpart))
        throw new InvalidDatatypeValueException("cvc-datatype-valid.1.2.1", new Object[]{content, "QName"});

    // resove prefix to a uri, report an error if failed
    String uri = context.getURI(prefix);
    if (prefix.length() > 0 && uri == null)
        throw new InvalidDatatypeValueException("UndeclaredPrefix", new Object[]{content, prefix});

    return new XQName(prefix, context.getSymbol(localpart), context.getSymbol(content), uri);

}
 

/**
 * Checks if the given qualified name is legal with respect
 * to the version of XML to which this document must conform.
 *
 * @param prefix prefix of qualified name
 * @param local local part of qualified name
 */
protected final void checkQName(String prefix, String local) {
    if (!errorChecking) {
        return;
    }

    // check that both prefix and local part match NCName
    boolean validNCName = false;
    if (!xml11Version) {
        validNCName = (prefix == null || XMLChar.isValidNCName(prefix))
                && XMLChar.isValidNCName(local);
    }
    else {
        validNCName = (prefix == null || XML11Char.isXML11ValidNCName(prefix))
                && XML11Char.isXML11ValidNCName(local);
    }

    if (!validNCName) {
        // REVISIT: add qname parameter to the message
        String msg =
        DOMMessageFormatter.formatMessage(
                        DOMMessageFormatter.DOM_DOMAIN,
                        "INVALID_CHARACTER_ERR",
                        null);
        throw new DOMException(DOMException.INVALID_CHARACTER_ERR, msg);
    }
}
 

public boolean isIgnorableWhiteSpace(XMLString text) {
    if (isInElementContent()) {
        for (int i = text.offset; i < text.offset + text.length; i++) {
            if (!XMLChar.isSpace(text.ch[i])) {
                return false;
            }
        }
        return true;
    }
    return false;
}
 

protected final void surrogates(int high, int low) throws IOException{
    if (XMLChar.isHighSurrogate(high)) {
        if (!XMLChar.isLowSurrogate(low)) {
            //Invalid XML
            fatalError("The character '"+(char)low+"' is an invalid XML character");
        }
        else {
            int supplemental = XMLChar.supplemental((char)high, (char)low);
            if (!XML11Char.isXML11Valid(supplemental)) {
                //Invalid XML
                fatalError("The character '"+(char)supplemental+"' is an invalid XML character");
            }
            else {
                if (content().inCData ) {
                    _printer.printText("]]>&#x");
                    _printer.printText(Integer.toHexString(supplemental));
                    _printer.printText(";<![CDATA[");
                }
                else {
                                            printHex(supplemental);
                }
            }
        }
    } else {
        fatalError("The character '"+(char)high+"' is an invalid XML character");
    }

}
 

/**
 * Character content.
 *
 * @param text   The content.
 * @param augs   Additional information that may include infoset augmentations
 *
 * @exception XNIException
 *                   Thrown by handler to signal an error.
 */
public void characters(XMLString text, Augmentations augs) throws XNIException {
    // when it's not within xs:appinfo or xs:documentation
    if (fInnerAnnotationDepth == -1 ) {
        for (int i=text.offset; i<text.offset+text.length; i++) {
            // and there is a non-whitespace character
            if (!XMLChar.isSpace(text.ch[i])) {
                // the string we saw: starting from the first non-whitespace character.
                String txt = new String(text.ch, i, text.length+text.offset-i);
                // report an error
                fErrorReporter.reportError(fLocator,
                        XSMessageFormatter.SCHEMA_DOMAIN,
                        "s4s-elt-character",
                        new Object[]{txt},
                        XMLErrorReporter.SEVERITY_ERROR);
                break;
            }
        }
        // don't call super.characters() when it's not within one of the 2
        // annotation elements: the traversers ignore them anyway. We can
        // save time/memory creating the text nodes.
    }
    // when it's within either of the 2 elements, characters are allowed
    // and we need to store them.
    else {
        schemaDOM.characters(text);
    }

}
 

/**
 * 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;
}
 

/**
 * 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;
}
 

/**
 * Check the string against XML's definition of acceptable names for
 * elements and attributes and so on using the XMLCharacterProperties
 * utility class
 */

public static final boolean isXMLName(String s, boolean xml11Version) {

    if (s == null) {
        return false;
    }
    if(!xml11Version)
        return XMLChar.isValidName(s);
    else
        return XML11Char.isXML11ValidName(s);

}
 

/**
 *  Returns true if the cursor points to a character data event that consists of all whitespace
 *  Application calling this method needs to cache the value and avoid calling this method again
 *  for the same event.
 * @return
 */
public boolean isWhiteSpace() {
    if(isCharacters() || (fEventType == XMLStreamConstants.CDATA)){
        char [] ch = this.getTextCharacters();
        final int start = this.getTextStart();
        final int end = start + this.getTextLength();
        for (int i = start; i < end; i++){
            if(!XMLChar.isSpace(ch[i])){
                return false;
            }
        }
        return true;
    }
    return false;
}
 

/**
 * 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 the string only contains white space characters.
 *
 * @param value the text to check
 */
private void checkWhitespace(XMLString value) {
    int end = value.offset + value.length;
    for (int i = value.offset; i < end; ++i) {
        if (!XMLChar.isSpace(value.ch[i])) {
            reportFatalError("ContentIllegalAtTopLevel");
            return;
        }
    }
}
 

/**
 * Scans surrogates and append them to the specified buffer.
 * <p>
 * <strong>Note:</strong> This assumes the current char has already been
 * identified as a high surrogate.
 *
 * @param buf The StringBuffer to append the read surrogates to.
 * @return True if it succeeded.
 */
protected boolean scanSurrogates(XMLStringBuffer buf)
throws IOException, XNIException {

    int high = fEntityScanner.scanChar(null);
    int low = fEntityScanner.peekChar();
    if (!XMLChar.isLowSurrogate(low)) {
        reportFatalError("InvalidCharInContent",
                new Object[] {Integer.toString(high, 16)});
                return false;
    }
    fEntityScanner.scanChar(null);

    // convert surrogates to supplemental character
    int c = XMLChar.supplemental((char)high, (char)low);

    // supplemental character must be a valid XML character
    if (isInvalid(c)) {
        reportFatalError("InvalidCharInContent",
                new Object[]{Integer.toString(c, 16)});
                return false;
    }

    // fill in the buffer
    buf.append((char)high);
    buf.append((char)low);

    return true;

}
 

public boolean characterData(String data, Augmentations augs) {

        fSawText = fSawText || data.length() > 0;

        // REVISIT: this methods basically duplicates implementation of
        //          handleCharacters(). We should be able to reuse some code

        // if whitespace == -1 skip normalization, because it is a complexType
        // or a union type.
        if (fNormalizeData && fWhiteSpace != -1 && fWhiteSpace != XSSimpleType.WS_PRESERVE) {
            // normalize data
            normalizeWhitespace(data, fWhiteSpace == XSSimpleType.WS_COLLAPSE);
            fBuffer.append(fNormalizedStr.ch, fNormalizedStr.offset, fNormalizedStr.length);
        } else {
            if (fAppendBuffer)
                fBuffer.append(data);
        }

        // When it's a complex type with element-only content, we need to
        // find out whether the content contains any non-whitespace character.
        boolean allWhiteSpace = true;
        if (fCurrentType != null
            && fCurrentType.getTypeCategory() == XSTypeDefinition.COMPLEX_TYPE) {
            XSComplexTypeDecl ctype = (XSComplexTypeDecl) fCurrentType;
            if (ctype.fContentType == XSComplexTypeDecl.CONTENTTYPE_ELEMENT) {
                // data outside of element content
                for (int i = 0; i < data.length(); i++) {
                    if (!XMLChar.isSpace(data.charAt(i))) {
                        allWhiteSpace = false;
                        fSawCharacters = true;
                        break;
                    }
                }
            }
        }

        return allWhiteSpace;
    }