%HH, where HH is the hex of the byte value.
*
* @param string String to convert to XML format.
* @param doURLEscaping True if we should try to encode as
* per http://www.ietf.org/rfc/rfc2396.txt.
*
* @throws org.xml.sax.SAXException if a bad surrogate pair is detected.
*/
public void writeAttrURI(String string, boolean doURLEscaping)
throws org.xml.sax.SAXException
{
// http://www.ietf.org/rfc/rfc2396.txt says:
// A URI is always in an "escaped" form, since escaping or unescaping a
// completed URI might change its semantics. Normally, the only time
// escape encodings can safely be made is when the URI is being created
// from its component parts; each component may have its own set of
// characters that are reserved, so only the mechanism responsible for
// generating or interpreting that component can determine whether or
// not escaping a character will change its semantics. Likewise, a URI
// must be separated into its components before the escaped characters
// within those components can be safely decoded.
//
// ...So we do our best to do limited escaping of the URL, without
// causing damage. If the URL is already properly escaped, in theory, this
// function should not change the string value.
char[] stringArray = string.toCharArray();
int len = stringArray.length;
for (int i = 0; i < len; i++)
{
char ch = stringArray[i];
if ((ch < 33) || (ch > 126))
{
if (doURLEscaping)
{
// Encode UTF16 to UTF8.
// Reference is Unicode, A Primer, by Tony Graham.
// Page 92.
if(ch <= 0x7F)
{
accum('%');
accum(makeHHString(ch));
}
else if(ch <= 0x7FF)
{
// Clear low 6 bits before rotate, put high 4 bits in low byte,
// and set two high bits.
int high = (ch >> 6) | 0xC0;
int low = (ch & 0x3F) | 0x80; // First 6 bits, + high bit
accum('%');
accum(makeHHString(high));
accum('%');
accum(makeHHString(low));
}
else if( isUTF16Surrogate(ch) ) // high surrogate
{
// I'm sure this can be done in 3 instructions, but I choose
// to try and do it exactly like it is done in the book, at least
// until we are sure this is totally clean. I don't think performance
// is a big issue with this particular function, though I could be
// wrong. Also, the stuff below clearly does more masking than
// it needs to do.
// Clear high 6 bits.
int highSurrogate = ((int) ch) & 0x03FF;
// Middle 4 bits (wwww) + 1
// "Note that the value of wwww from the high surrogate bit pattern
// is incremented to make the uuuuu bit pattern in the scalar value
// so the surrogate pair don't address the BMP."
int wwww = ((highSurrogate & 0x03C0) >> 6);
int uuuuu = wwww+1;
// next 4 bits
int zzzz = (highSurrogate & 0x003C) >> 2;
// low 2 bits
int yyyyyy = ((highSurrogate & 0x0003) << 4) & 0x30;
// Get low surrogate character.
ch = stringArray[++i];
// Clear high 6 bits.
int lowSurrogate = ((int) ch) & 0x03FF;
// put the middle 4 bits into the bottom of yyyyyy (byte 3)
yyyyyy = yyyyyy | ((lowSurrogate & 0x03C0) >> 6);
// bottom 6 bits.
int xxxxxx = (lowSurrogate & 0x003F);
int byte1 = 0xF0 | (uuuuu >> 2); // top 3 bits of uuuuu
int byte2 = 0x80 | (((uuuuu & 0x03) << 4) & 0x30) | zzzz;
int byte3 = 0x80 | yyyyyy;
int byte4 = 0x80 | xxxxxx;
accum('%');
accum(makeHHString(byte1));
accum('%');
accum(makeHHString(byte2));
accum('%');
accum(makeHHString(byte3));
accum('%');
accum(makeHHString(byte4));
}
else
{
int high = (ch >> 12) | 0xE0; // top 4 bits
int middle = ((ch & 0x0FC0) >> 6) | 0x80; // middle 6 bits
int low = (ch & 0x3F) | 0x80; // First 6 bits, + high bit
accum('%');
accum(makeHHString(high));
accum('%');
accum(makeHHString(middle));
accum('%');
accum(makeHHString(low));
}
}
else if (ch < m_maxCharacter)
{
accum(ch);
}
else
{
accum("&#");
accum(Integer.toString(ch));
accum(';');
}
}
else if('%' == ch)
{
// If the character is a '%' number number, try to avoid double-escaping.
// There is a question if this is legal behavior.
// Dmitri Ilyin: to check if '%' number number is invalid. It must be checked if %xx is a sign, that would be encoded
// The encoded signes are in Hex form. So %xx my be in form %3C that is "<" sign. I will try to change here a little.
// if( ((i+2) < len) && isASCIIDigit(stringArray[i+1]) && isASCIIDigit(stringArray[i+2]) )
if ( ((i+2) < len) && isHHSign(new String(stringArray,i+1,2)) )
{
accum(ch);
}
else
{
if (doURLEscaping)
{
accum('%');
accum(makeHHString(ch));
}
else
accum(ch);
}
}
// Since http://www.ietf.org/rfc/rfc2396.txt refers to the URI grammar as
// not allowing quotes in the URI proper syntax, nor in the fragment
// identifier, we believe that it's OK to double escape quotes.
else if (ch == '"')
{
// Mike Kay encodes this as ", so he may know something I don't?
if (doURLEscaping)
accum("%22");
else
accum("""); // we have to escape this, I guess.
}
else
{
accum(ch);
}
}
}
/**
* Writes the specified string after substituting specials,
* and UTF-16 surrogates for character references &#xnn.
*
* @param string String to convert to XML format.
* @param encoding CURRENTLY NOT IMPLEMENTED.
*
* @throws org.xml.sax.SAXException
*/
public void writeAttrString(String string, String encoding)
throws org.xml.sax.SAXException
{
final char chars[] = string.toCharArray();
final int strLen = chars.length;
for (int i = 0; i < strLen; i++)
{
char ch = chars[i];
// System.out.println("SPECIALSSIZE: "+SPECIALSSIZE);
// System.out.println("ch: "+(int)ch);
// System.out.println("m_maxCharacter: "+(int)m_maxCharacter);
// System.out.println("m_attrCharsMap[ch]: "+(int)m_attrCharsMap[ch]);
if ((ch < m_maxCharacter) && (!m_charInfo.isSpecial(ch)))
{
accum(ch);
}
else if ('<' == ch || '>' == ch)
{
accum(ch); // no escaping in this case, as specified in 15.2
}
else if (('&' == ch) && ((i + 1) < strLen) && ('{' == chars[i + 1]))
{
accum(ch); // no escaping in this case, as specified in 15.2
}
else
{
int pos = accumDefaultEntity(ch, i, chars, strLen, false);
if (i != pos)
{
i = pos - 1;
}
else
{
if (isUTF16Surrogate(ch))
{
try
{
i = writeUTF16Surrogate(ch, chars, i, strLen);
}
catch(IOException ioe)
{
throw new SAXException(ioe);
}
}
// The next is kind of a hack to keep from escaping in the case
// of Shift_JIS and the like.
/*
else if ((ch < m_maxCharacter) && (m_maxCharacter == 0xFFFF)
&& (ch != 160))
{
accum(ch); // no escaping in this case
}
else
*/
String entityName = m_charInfo.getEntityNameForChar(ch);
if (null != entityName)
{
accum('&');
accum(entityName);
accum(';');
}
else if (ch < m_maxCharacter)
{
accum(ch); // no escaping in this case
}
else
{
if (ch < m_maxCharacter)
{
accum(ch); // no escaping in this case
}
else
{
accum("&#");
accum(Integer.toString(ch));
accum(';');
}
}
}
}
}
}
/**
* Copy an entity into the accumulation buffer.
*
* @param s The name of the entity.
* @param pos unused.
*
* @return The pos argument.
*
* @throws org.xml.sax.SAXException
*/
private int copyEntityIntoBuf(String s, int pos)
throws org.xml.sax.SAXException
{
int l = s.length();
accum('&');
for (int i = 0; i < l; i++)
{
accum(s.charAt(i));
}
accum(';');
return pos;
}
/**
* Receive notification of character data.
*
* The Parser will call this method to report each chunk of * character data. SAX parsers may return all contiguous character * data in a single chunk, or they may split it into several * chunks; however, all of the characters in any single event * must come from the same external entity, so that the Locator * provides useful information.
* *The application must not attempt to read from the array * outside of the specified range.
* *Note that some parsers will report whitespace using the * ignorableWhitespace() method rather than this one (validating * parsers must do so).
* * @param chars The characters from the XML document. * @param start The start position in the array. * @param length The number of characters to read from the array. * @throws org.xml.sax.SAXException Any SAX exception, possibly * wrapping another exception. * @see #ignorableWhitespace * @see org.xml.sax.Locator * * @throws org.xml.sax.SAXException */ public void characters(char chars[], int start, int length) throws org.xml.sax.SAXException { if (m_isRawStack.peekOrFalse()) { try { writeParentTagEnd(); m_ispreserve = true; if (shouldIndent()) indent(m_currentIndent); // this.accum(""); return; } catch (IOException ioe) { throw new org.xml.sax.SAXException( XSLMessages.createXPATHMessage( XPATHErrorResources.ER_OIERROR, null), ioe); //"IO error", ioe); } } else { super.characters(chars, start, length); } } /** * Receive notification of cdata. * *The Parser will call this method to report each chunk of * character data. SAX parsers may return all contiguous character * data in a single chunk, or they may split it into several * chunks; however, all of the characters in any single event * must come from the same external entity, so that the Locator * provides useful information.
* *The application must not attempt to read from the array * outside of the specified range.
* *Note that some parsers will report whitespace using the * ignorableWhitespace() method rather than this one (validating * parsers must do so).
* * @param ch The characters from the XML document. * @param start The start position in the array. * @param length The number of characters to read from the array. * @throws org.xml.sax.SAXException Any SAX exception, possibly * wrapping another exception. * @see #ignorableWhitespace * @see org.xml.sax.Locator * * @throws org.xml.sax.SAXException */ public void cdata(char ch[], int start, int length) throws org.xml.sax.SAXException { if ((null != m_currentElementName) && (m_currentElementName.equalsIgnoreCase("SCRIPT") || m_currentElementName.equalsIgnoreCase("STYLE"))) { try { writeParentTagEnd(); m_ispreserve = true; if (shouldIndent()) indent(m_currentIndent); // this.accum(ch, start, length); writeNormalizedChars(ch, start, length, true); } catch (IOException ioe) { throw new org.xml.sax.SAXException( XSLMessages.createXPATHMessage( XPATHErrorResources.ER_OIERROR, null), ioe); //"IO error", ioe); } } /* else if(m_stripCData) // should normally always be false { try { writeParentTagEnd(); m_ispreserve = true; if (shouldIndent()) indent(m_currentIndent); // this.accum(""); } catch(IOException ioe) { throw new org.xml.sax.SAXException(XSLMessages.createXPATHMessage(XPATHErrorResources.ER_OIERROR, null),ioe); //"IO error", ioe); } } */ else { super.cdata(ch, start, length); } } /** * Receive notification of a processing instruction. * * @param target The processing instruction target. * @param data The processing instruction data, or null if * none was supplied. * @throws org.xml.sax.SAXException Any SAX exception, possibly * wrapping another exception. * * @throws org.xml.sax.SAXException */ public void processingInstruction(String target, String data) throws org.xml.sax.SAXException { // Use a fairly nasty hack to tell if the next node is supposed to be // unescaped text. if (target.equals(Result.PI_DISABLE_OUTPUT_ESCAPING)) { startNonEscaping(); } else if (target.equals(Result.PI_ENABLE_OUTPUT_ESCAPING)) { endNonEscaping(); } else { writeParentTagEnd(); if (shouldIndent()) indent(m_currentIndent); this.accum(" 0 &&!Character.isSpaceChar(data.charAt(0))) this.accum(" "); this.accum(data + ">"); // different from XML // Always output a newline char if not inside of an // element. The whitespace is not significant in that // case. if (m_elemStack.isEmpty()) outputLineSep(); m_startNewLine = true; } } /** * Receive notivication of a entityReference. * * @param name non-null reference to entity name string. * * @throws org.xml.sax.SAXException */ public void entityReference(String name) throws org.xml.sax.SAXException { this.accum("&"); this.accum(name); this.accum(";"); } }