public StringBuffer Prepare(String src, StringPrepOptions options)
{
int ch;
String mapOut = Map(src, options);
UCharacterIterator iter = UCharacterIterator.GetInstance(mapOut);
UCharacterDirection direction = UCharacterDirectionExtensions.CharDirectionCount,
firstCharDir = UCharacterDirectionExtensions.CharDirectionCount;
int rtlPos = -1, ltrPos = -1;
bool rightToLeft = false, leftToRight = false;
while ((ch = iter.NextCodePoint()) != UCharacterIterator.Done)
{
if (transform.prohibitedSet.Contains(ch) == true && ch != 0x0020)
{
throw new StringPrepParseException("A prohibited code point was found in the input",
StringPrepErrorType.ProhibitedError,
iter.GetText(), iter.Index);
}
direction = UChar.GetDirection(ch);
if (firstCharDir == UCharacterDirectionExtensions.CharDirectionCount)
{
firstCharDir = direction;
}
if (direction == UCharacterDirection.LeftToRight)
{
leftToRight = true;
ltrPos = iter.Index - 1;
}
if (direction == UCharacterDirection.RightToLeft || direction == UCharacterDirection.RightToLeftArabic)
{
rightToLeft = true;
rtlPos = iter.Index - 1;
}
}
// satisfy 2
if (leftToRight == true && rightToLeft == true)
{
throw new StringPrepParseException("The input does not conform to the rules for BiDi code points.",
StringPrepErrorType.CheckBiDiError, iter.GetText(), (rtlPos > ltrPos) ? rtlPos : ltrPos);
}
//satisfy 3
if (rightToLeft == true &&
!((firstCharDir == UCharacterDirection.RightToLeft || firstCharDir == UCharacterDirection.RightToLeftArabic) &&
(direction == UCharacterDirection.RightToLeft || direction == UCharacterDirection.RightToLeftArabic))
)
{
throw new StringPrepParseException("The input does not conform to the rules for BiDi code points.",
StringPrepErrorType.CheckBiDiError, iter.GetText(), (rtlPos > ltrPos) ? rtlPos : ltrPos);
}
return(new StringBuffer(mapOut));
}
// TODO: optimize
public static int Compare(UCharacterIterator i1, UCharacterIterator i2, IDNA2003Options options)
{
if (i1 == null || i2 == null)
{
throw new ArgumentException("One of the source buffers is null");
}
StringBuffer s1Out = ConvertIDNToASCII(i1.GetText(), options);
StringBuffer s2Out = ConvertIDNToASCII(i2.GetText(), options);
return(CompareCaseInsensitiveASCII(s1Out, s2Out));
}
public void getText(UCharacterIterator iterator, String result)
{
/* test getText */
char[] buf = new char[1];
for (; ;)
{
try
{
iterator.GetText(buf);
break;
}
catch (IndexOutOfRangeException e)
{
buf = new char[iterator.Length];
}
}
if (result.CompareToOrdinal(new string(buf, 0, iterator.Length)) != 0)
{
Errln("getText failed for iterator");
}
}
public static StringBuffer ConvertIDNToUnicode(UCharacterIterator iter, IDNA2003Options options)
{
return(ConvertIDNToUnicode(iter.GetText(), options));
}
public static StringBuffer ConvertToUnicode(UCharacterIterator iter, IDNA2003Options options)
{
// the source contains all ascii codepoints
bool srcIsASCII = true;
int ch;
int saveIndex = iter.Index;
// step 1: find out if all the codepoints in src are ASCII
while ((ch = iter.Next()) != UCharacterIterator.DONE)
{
if (ch > 0x7F)
{
srcIsASCII = false;
break;
}
}
// The RFC states that
// <quote>
// ToUnicode never fails. If any step fails, then the original input
// is returned immediately in that step.
// </quote>
do
{
StringBuffer processOut;
if (srcIsASCII == false)
{
// step 2: process the string
iter.Index = (saveIndex);
try
{
processOut = transform.Prepare(iter, (StringPrepOptions)options);
}
catch (StringPrepParseException e)
{
break;
}
}
else
{
// just point to source
processOut = new StringBuffer(iter.GetText());
}
// step 3: verify ACE Prefix
if (StartsWithPrefix(processOut))
{
// step 4: Remove the ACE Prefix
String temp = processOut.ToString(ACE_PREFIX_LENGTH, processOut.Length - ACE_PREFIX_LENGTH);
// step 5: Decode using punycode
StringBuffer decodeOut = null;
try
{
decodeOut = PunycodeReference.Decode(new StringBuffer(temp), null);
}
catch (StringPrepParseException e)
{
break;
}
// step 6:Apply toASCII
StringBuffer toASCIIOut = ConvertToASCII(decodeOut, options);
// step 7: verify
if (CompareCaseInsensitiveASCII(processOut, toASCIIOut) != 0)
{
break;
}
// step 8: return output of step 5
return(decodeOut);
}
} while (false);
return(new StringBuffer(iter.GetText()));
}
public static StringBuffer ConvertToASCII(UCharacterIterator srcIter, IDNA2003Options options)
{
char[]
caseFlags = null;
// the source contains all ascii codepoints
bool srcIsASCII = true;
// assume the source contains all LDH codepoints
bool srcIsLDH = true;
//get the options
bool useSTD3ASCIIRules = ((options & USE_STD3_RULES) != 0);
int ch;
// step 1
while ((ch = srcIter.Next()) != UCharacterIterator.DONE)
{
if (ch > 0x7f)
{
srcIsASCII = false;
}
}
int failPos = -1;
srcIter.SetToStart();
StringBuffer processOut = null;
// step 2 is performed only if the source contains non ASCII
if (!srcIsASCII)
{
// step 2
processOut = transform.Prepare(srcIter, (StringPrepOptions)options);
}
else
{
processOut = new StringBuffer(srcIter.GetText());
}
int poLen = processOut.Length;
if (poLen == 0)
{
throw new StringPrepParseException("Found zero length lable after NamePrep.", StringPrepErrorType.ZeroLengthLabel);
}
StringBuffer dest = new StringBuffer();
// reset the variable to verify if output of prepare is ASCII or not
srcIsASCII = true;
// step 3 & 4
for (int j = 0; j < poLen; j++)
{
ch = processOut[j];
if (ch > 0x7F)
{
srcIsASCII = false;
}
else if (IsLDHChar(ch) == false)
{
// here we do not assemble surrogates
// since we know that LDH code points
// are in the ASCII range only
srcIsLDH = false;
failPos = j;
}
}
if (useSTD3ASCIIRules == true)
{
// verify 3a and 3b
if (srcIsLDH == false || /* source contains some non-LDH characters */
processOut[0] == HYPHEN ||
processOut[processOut.Length - 1] == HYPHEN)
{
/* populate the parseError struct */
if (srcIsLDH == false)
{
throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
StringPrepErrorType.STD3ASCIIRulesError,
processOut.ToString(),
(failPos > 0) ? (failPos - 1) : failPos);
}
else if (processOut[0] == HYPHEN)
{
throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
StringPrepErrorType.STD3ASCIIRulesError, processOut.ToString(), 0);
}
else
{
throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
StringPrepErrorType.STD3ASCIIRulesError,
processOut.ToString(),
(poLen > 0) ? poLen - 1 : poLen);
}
}
}
if (srcIsASCII)
{
dest = processOut;
}
else
{
// step 5 : verify the sequence does not begin with ACE prefix
if (!StartsWithPrefix(processOut))
{
//step 6: encode the sequence with punycode
StringBuffer punyout = PunycodeReference.Encode(processOut, caseFlags);
// convert all codepoints to lower case ASCII
StringBuffer lowerOut = ToASCIILower(punyout);
//Step 7: prepend the ACE prefix
dest.Append(ACE_PREFIX, 0, ACE_PREFIX_LENGTH - 0); // ICU4N: Checked 3rd parameter
//Step 6: copy the contents in b2 into dest
dest.Append(lowerOut);
}
else
{
throw new StringPrepParseException("The input does not start with the ACE Prefix.",
StringPrepErrorType.AcePrefixError, processOut.ToString(), 0);
}
}
if (dest.Length > MAX_LABEL_LENGTH)
{
throw new StringPrepParseException("The labels in the input are too long. Length > 64.",
StringPrepErrorType.LabelTooLongError, dest.ToString(), 0);
}
return(dest);
}
public static StringBuffer ConvertToUnicode(UCharacterIterator src, IDNA2003Options options)
{
bool[] caseFlags = null;
// the source contains all ascii codepoints
bool srcIsASCII = true;
// assume the source contains all LDH codepoints
//bool srcIsLDH = true;
//get the options
//bool useSTD3ASCIIRules = ((options & USE_STD3_RULES) != 0);
//int failPos = -1;
int ch;
int saveIndex = src.Index;
// step 1: find out if all the codepoints in src are ASCII
while ((ch = src.Next()) != UCharacterIterator.DONE)
{
if (ch > 0x7F)
{
srcIsASCII = false;
}/*else if((srcIsLDH = isLDHChar(ch))==false){
* failPos = src.getIndex();
* }*/
}
StringBuffer processOut;
if (srcIsASCII == false)
{
try
{
// step 2: process the string
src.Index = saveIndex;
processOut = namePrep.Prepare(src, (StringPrepOptions)options);
}
catch (StringPrepParseException ex)
{
return(new StringBuffer(src.GetText()));
}
}
else
{
//just point to source
processOut = new StringBuffer(src.GetText());
}
// TODO:
// The RFC states that
// <quote>
// ToUnicode never fails. If any step fails, then the original input
// is returned immediately in that step.
// </quote>
//step 3: verify ACE Prefix
if (StartsWithPrefix(processOut))
{
StringBuffer decodeOut = null;
//step 4: Remove the ACE Prefix
string temp = processOut.ToString(ACE_PREFIX.Length, processOut.Length - ACE_PREFIX.Length);
//step 5: Decode using punycode
try
{
decodeOut = new StringBuffer(Punycode.Decode(temp, caseFlags).ToString());
}
catch (StringPrepParseException e)
{
decodeOut = null;
}
//step 6:Apply toASCII
if (decodeOut != null)
{
StringBuffer toASCIIOut = ConvertToASCII(UCharacterIterator.GetInstance(decodeOut), options);
//step 7: verify
if (CompareCaseInsensitiveASCII(processOut, toASCIIOut) != 0)
{
// throw new StringPrepParseException("The verification step prescribed by the RFC 3491 failed",
// StringPrepParseException.VERIFICATION_ERROR);
decodeOut = null;
}
}
//step 8: return output of step 5
if (decodeOut != null)
{
return(decodeOut);
}
}
// }else{
// // verify that STD3 ASCII rules are satisfied
// if(useSTD3ASCIIRules == true){
// if( srcIsLDH == false /* source contains some non-LDH characters */
// || processOut.charAt(0) == HYPHEN
// || processOut.charAt(processOut.Length-1) == HYPHEN){
//
// if(srcIsLDH==false){
// throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
// StringPrepParseException.STD3_ASCII_RULES_ERROR,processOut.toString(),
// (failPos>0) ? (failPos-1) : failPos);
// }else if(processOut.charAt(0) == HYPHEN){
// throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
// StringPrepParseException.STD3_ASCII_RULES_ERROR,
// processOut.toString(),0);
//
// }else{
// throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
// StringPrepParseException.STD3_ASCII_RULES_ERROR,
// processOut.toString(),
// processOut.Length);
//
// }
// }
// }
// // just return the source
// return new StringBuffer(src.getText());
// }
return(new StringBuffer(src.GetText()));
}
public StringBuffer Prepare(UCharacterIterator src,
StringPrepOptions options)
{
return(Prepare(src.GetText(), options));
}
public void TestIterationUChar32()
{
String text = "\u0061\u0062\ud841\udc02\u20ac\ud7ff\ud842\udc06\ud801\udc00\u0061";
int c;
int i;
{
UCharacterIterator iter = UCharacterIterator.GetInstance(text);
String iterText = iter.GetText();
if (!iterText.Equals(text))
{
Errln("iter.getText() failed");
}
iter.Index = (1);
if (iter.CurrentCodePoint != UTF16.CharAt(text, 1))
{
Errln("Iterator didn't start out in the right place.");
}
iter.SetToStart();
c = iter.CurrentCodePoint;
i = 0;
i = iter.MoveCodePointIndex(1);
c = iter.CurrentCodePoint;
if (c != UTF16.CharAt(text, 1) || i != 1)
{
Errln("moveCodePointIndex(1) didn't work correctly expected " + Hex(c) + " got " + Hex(UTF16.CharAt(text, 1)) + " i= " + i);
}
i = iter.MoveCodePointIndex(2);
c = iter.CurrentCodePoint;
if (c != UTF16.CharAt(text, 4) || i != 4)
{
Errln("moveCodePointIndex(2) didn't work correctly expected " + Hex(c) + " got " + Hex(UTF16.CharAt(text, 4)) + " i= " + i);
}
i = iter.MoveCodePointIndex(-2);
c = iter.CurrentCodePoint;
if (c != UTF16.CharAt(text, 1) || i != 1)
{
Errln("moveCodePointIndex(-2) didn't work correctly expected " + Hex(c) + " got " + Hex(UTF16.CharAt(text, 1)) + " i= " + i);
}
iter.SetToLimit();
i = iter.MoveCodePointIndex(-2);
c = iter.CurrentCodePoint;
if (c != UTF16.CharAt(text, (text.Length - 3)) || i != (text.Length - 3))
{
Errln("moveCodePointIndex(-2) didn't work correctly expected " + Hex(c) + " got " + Hex(UTF16.CharAt(text, (text.Length - 3))) + " i= " + i);
}
iter.SetToStart();
c = iter.CurrentCodePoint;
i = 0;
//testing first32PostInc, nextCodePointPostInc, setTostart
i = 0;
iter.SetToStart();
c = iter.Next();
if (c != UTF16.CharAt(text, i))
{
Errln("first32PostInc failed. Expected->" + Hex(UTF16.CharAt(text, i)) + " Got-> " + Hex(c));
}
if (iter.Index != UTF16.GetCharCount(c) + i)
{
Errln("getIndex() after first32PostInc() failed");
}
iter.SetToStart();
i = 0;
if (iter.Index != 0)
{
Errln("setToStart failed");
}
Logln("Testing forward iteration...");
do
{
if (c != UCharacterIterator.DONE)
{
c = iter.NextCodePoint();
}
if (c != UTF16.CharAt(text, i))
{
Errln("Character mismatch at position " + i + ", iterator has " + Hex(c) + ", string has " + Hex(UTF16.CharAt(text, i)));
}
i += UTF16.GetCharCount(c);
if (iter.Index != i)
{
Errln("getIndex() aftr nextCodePointPostInc() isn't working right");
}
c = iter.CurrentCodePoint;
if (c != UCharacterIterator.DONE && c != UTF16.CharAt(text, i))
{
Errln("current() after nextCodePointPostInc() isn't working right");
}
} while (c != UCharacterIterator.DONE);
c = iter.NextCodePoint();
if (c != UCharacterIterator.DONE)
{
Errln("nextCodePointPostInc() didn't return DONE at the beginning");
}
}
}