/// <summary>
/// WARNING this is used for searching in a Vector.
/// Because Vector.indexOf doesn't take a comparator,
/// this method is ill-defined and ignores strength.
/// </summary>
public override bool Equals(Object obj)
{
if (obj == null)
{
return(false);
}
PatternEntry other = (PatternEntry)obj;
bool result = Chars_Renamed.Equals(other.Chars_Renamed);
return(result);
}
private PatternEntry FindLastWithNoExtension(int i)
{
for (--i; i >= 0; --i)
{
PatternEntry entry = Patterns[i];
if (entry.Extension_Renamed.length() == 0)
{
return(entry);
}
}
return(null);
}
internal static void AppendQuoted(String chars, StringBuffer toAddTo)
{
bool inQuote = false;
char ch = chars.CharAt(0);
if (Character.IsSpaceChar(ch))
{
inQuote = true;
toAddTo.Append('\'');
}
else
{
if (PatternEntry.IsSpecialChar(ch))
{
inQuote = true;
toAddTo.Append('\'');
}
else
{
switch (ch)
{
case 0x0010:
case '\f':
case '\r':
case '\t':
case '\n':
case '@':
inQuote = true;
toAddTo.Append('\'');
break;
case '\'':
inQuote = true;
toAddTo.Append('\'');
break;
default:
if (inQuote)
{
inQuote = false;
toAddTo.Append('\'');
}
break;
}
}
}
toAddTo.Append(chars);
if (inQuote)
{
toAddTo.Append('\'');
}
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private final int findLastEntry(PatternEntry entry, StringBuffer excessChars) throws ParseException
private int FindLastEntry(PatternEntry entry, StringBuffer excessChars)
{
if (entry == null)
{
return(0);
}
if (entry.Strength_Renamed != PatternEntry.RESET)
{
// Search backwards for string that contains this one;
// most likely entry is last one
int oldIndex = -1;
if ((entry.Chars_Renamed.length() == 1))
{
int index = entry.Chars_Renamed.charAt(0) >> BYTEPOWER;
if ((StatusArray[index] & (BITARRAYMASK << (entry.Chars_Renamed.charAt(0) & BYTEMASK))) != 0)
{
oldIndex = Patterns.LastIndexOf(entry);
}
}
else
{
oldIndex = Patterns.LastIndexOf(entry);
}
if ((oldIndex == -1))
{
throw new ParseException("couldn't find last entry: " + entry, oldIndex);
}
return(oldIndex + 1);
}
else
{
int i;
for (i = Patterns.Count - 1; i >= 0; --i)
{
PatternEntry e = Patterns[i];
if (e.Chars_Renamed.regionMatches(0, entry.Chars_Renamed, 0, e.Chars_Renamed.length()))
{
excessChars.Append(StringHelperClass.SubstringSpecial(entry.Chars_Renamed, e.Chars_Renamed.length(), entry.Chars_Renamed.length()));
break;
}
}
if (i == -1)
{
throw new ParseException("couldn't find: " + entry, i);
}
return(i + 1);
}
}
/// <summary>
/// emits the pattern for collation builder. </summary>
/// <param name="withWhiteSpace"> puts spacing around the entries, and \n
/// before & and < </param>
/// <returns> emits the string in the format understable to the collation
/// builder. </returns>
public String EmitPattern(bool withWhiteSpace)
{
StringBuffer result = new StringBuffer();
for (int i = 0; i < Patterns.Count; ++i)
{
PatternEntry entry = Patterns[i];
if (entry != null)
{
entry.AddToBuffer(result, true, withWhiteSpace, null);
}
}
return(result.ToString());
}
/// <summary>
/// adds a pattern to the current one. </summary>
/// <param name="pattern"> the new pattern to be added </param>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void addPattern(String pattern) throws ParseException
public void AddPattern(String pattern)
{
if (pattern == null)
{
return;
}
PatternEntry.Parser parser = new PatternEntry.Parser(pattern);
PatternEntry entry = parser.Next();
while (entry != null)
{
FixEntry(entry);
entry = parser.Next();
}
}
/// <summary>
/// recovers current pattern. </summary>
/// <param name="withWhiteSpace"> puts spacing around the entries, and \n
/// before & and < </param>
public String GetPattern(bool withWhiteSpace)
{
StringBuffer result = new StringBuffer();
PatternEntry tmp = null;
List <PatternEntry> extList = null;
int i;
for (i = 0; i < Patterns.Count; ++i)
{
PatternEntry entry = Patterns[i];
if (entry.Extension_Renamed.length() != 0)
{
if (extList == null)
{
extList = new List <>();
}
extList.Add(entry);
}
else
{
if (extList != null)
{
PatternEntry last = FindLastWithNoExtension(i - 1);
for (int j = extList.Count - 1; j >= 0; j--)
{
tmp = extList[j];
tmp.AddToBuffer(result, false, withWhiteSpace, last);
}
extList = null;
}
entry.AddToBuffer(result, false, withWhiteSpace, null);
}
}
if (extList != null)
{
PatternEntry last = FindLastWithNoExtension(i - 1);
for (int j = extList.Count - 1; j >= 0; j--)
{
tmp = extList[j];
tmp.AddToBuffer(result, false, withWhiteSpace, last);
}
extList = null;
}
return(result.ToString());
}
/*
* If the strength is RESET, then just change the lastEntry to
* be the current. (If the current is not in patterns, signal an error).
* If not, then remove the current entry, and add it after lastEntry
* (which is usually at the end).
*/
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private final void fixEntry(PatternEntry newEntry) throws ParseException
private void FixEntry(PatternEntry newEntry)
{
// check to see whether the new entry has the same characters as the previous
// entry did (this can happen when a pattern declaring a difference between two
// strings that are canonically equivalent is normalized). If so, and the strength
// is anything other than IDENTICAL or RESET, throw an exception (you can't
// declare a string to be unequal to itself). --rtg 5/24/99
if (LastEntry != null && newEntry.Chars_Renamed.Equals(LastEntry.Chars_Renamed) && newEntry.Extension_Renamed.Equals(LastEntry.Extension_Renamed))
{
if (newEntry.Strength_Renamed != Collator.IDENTICAL && newEntry.Strength_Renamed != PatternEntry.RESET)
{
throw new ParseException("The entries " + LastEntry + " and " + newEntry + " are adjacent in the rules, but have conflicting " + "strengths: A character can't be unequal to itself.", -1);
}
else
{
// otherwise, just skip this entry and behave as though you never saw it
return;
}
}
bool changeLastEntry = true;
if (newEntry.Strength_Renamed != PatternEntry.RESET)
{
int oldIndex = -1;
if ((newEntry.Chars_Renamed.length() == 1))
{
char c = newEntry.Chars_Renamed.charAt(0);
int statusIndex = c >> BYTEPOWER;
sbyte bitClump = StatusArray[statusIndex];
sbyte setBit = (sbyte)(BITARRAYMASK << (c & BYTEMASK));
if (bitClump != 0 && (bitClump & setBit) != 0)
{
oldIndex = Patterns.LastIndexOf(newEntry);
}
else
{
// We're going to add an element that starts with this
// character, so go ahead and set its bit.
StatusArray[statusIndex] = (sbyte)(bitClump | setBit);
}
}
else
{
oldIndex = Patterns.LastIndexOf(newEntry);
}
if (oldIndex != -1)
{
Patterns.RemoveAt(oldIndex);
}
Excess.Length = 0;
int lastIndex = FindLastEntry(LastEntry, Excess);
if (Excess.Length() != 0)
{
newEntry.Extension_Renamed = Excess + newEntry.Extension_Renamed;
if (lastIndex != Patterns.Count)
{
LastEntry = SaveEntry;
changeLastEntry = false;
}
}
if (lastIndex == Patterns.Count)
{
Patterns.Add(newEntry);
SaveEntry = newEntry;
}
else
{
Patterns.Insert(lastIndex, newEntry);
}
}
if (changeLastEntry)
{
LastEntry = newEntry;
}
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public PatternEntry next() throws ParseException
public virtual PatternEntry Next()
{
int newStrength = UNSET;
NewChars.Length = 0;
NewExtension.Length = 0;
bool inChars = true;
bool inQuote = false;
while (i < Pattern.Length())
{
char ch = Pattern.CharAt(i);
if (inQuote)
{
if (ch == '\'')
{
inQuote = false;
}
else
{
if (NewChars.Length() == 0)
{
NewChars.Append(ch);
}
else if (inChars)
{
NewChars.Append(ch);
}
else
{
NewExtension.Append(ch);
}
}
}
else
{
switch (ch)
{
case '=':
if (newStrength != UNSET)
{
goto mainLoopBreak;
}
newStrength = Collator.IDENTICAL;
break;
case ',':
if (newStrength != UNSET)
{
goto mainLoopBreak;
}
newStrength = Collator.TERTIARY;
break;
case ';':
if (newStrength != UNSET)
{
goto mainLoopBreak;
}
newStrength = Collator.SECONDARY;
break;
case '<':
if (newStrength != UNSET)
{
goto mainLoopBreak;
}
newStrength = Collator.PRIMARY;
break;
case '&':
if (newStrength != UNSET)
{
goto mainLoopBreak;
}
newStrength = RESET;
break;
case '\t':
case '\n':
case '\f':
case '\r':
case ' ': // skip whitespace TODO use Character
break;
case '/':
inChars = false;
break;
case '\'':
inQuote = true;
ch = Pattern.CharAt(++i);
if (NewChars.Length() == 0)
{
NewChars.Append(ch);
}
else if (inChars)
{
NewChars.Append(ch);
}
else
{
NewExtension.Append(ch);
}
break;
default:
if (newStrength == UNSET)
{
throw new ParseException("missing char (=,;<&) : " + Pattern.Substring(i, (10 < Pattern.Length()) ? i + 10 : Pattern.Length()), i);
}
if (PatternEntry.IsSpecialChar(ch) && (inQuote == false))
{
throw new ParseException("Unquoted punctuation character : " + Convert.ToString(ch, 16), i);
}
if (inChars)
{
NewChars.Append(ch);
}
else
{
NewExtension.Append(ch);
}
break;
}
}
i++;
mainLoopContinue :;
}
mainLoopBreak :
if (newStrength == UNSET)
{
return(null);
}
if (NewChars.Length() == 0)
{
throw new ParseException("missing chars (=,;<&): " + Pattern.Substring(i, (10 < Pattern.Length()) ? i + 10 : Pattern.Length()), i);
}
return(new PatternEntry(newStrength, NewChars, NewExtension));
}
// ===== privates =====
internal virtual void AddToBuffer(StringBuffer toAddTo, bool showExtension, bool showWhiteSpace, PatternEntry lastEntry)
{
if (showWhiteSpace && toAddTo.Length() > 0)
{
if (Strength_Renamed == Collator.PRIMARY || lastEntry != null)
{
toAddTo.Append('\n');
}
else
{
toAddTo.Append(' ');
}
}
if (lastEntry != null)
{
toAddTo.Append('&');
if (showWhiteSpace)
{
toAddTo.Append(' ');
}
lastEntry.AppendQuotedChars(toAddTo);
AppendQuotedExtension(toAddTo);
if (showWhiteSpace)
{
toAddTo.Append(' ');
}
}
switch (Strength_Renamed)
{
case Collator.IDENTICAL:
toAddTo.Append('=');
break;
case Collator.TERTIARY:
toAddTo.Append(',');
break;
case Collator.SECONDARY:
toAddTo.Append(';');
break;
case Collator.PRIMARY:
toAddTo.Append('<');
break;
case RESET:
toAddTo.Append('&');
break;
case UNSET:
toAddTo.Append('?');
break;
}
if (showWhiteSpace)
{
toAddTo.Append(' ');
}
AppendQuoted(Chars_Renamed, toAddTo);
if (showExtension && Extension_Renamed.Length() != 0)
{
toAddTo.Append('/');
AppendQuoted(Extension_Renamed, toAddTo);
}
}
/// <summary>
/// Create a table-based collation object with the given rules.
/// This is the main function that actually builds the tables and
/// stores them back in the RBCollationTables object. It is called
/// ONLY by the RBCollationTables constructor. </summary>
/// <seealso cref= RuleBasedCollator#RuleBasedCollator </seealso>
/// <exception cref="ParseException"> If the rules format is incorrect. </exception>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void build(String pattern, int decmp) throws ParseException
public void Build(String pattern, int decmp)
{
bool isSource = true;
int i = 0;
String expChars;
String groupChars;
if (pattern.Length() == 0)
{
throw new ParseException("Build rules empty.", 0);
}
// This array maps Unicode characters to their collation ordering
Mapping = new UCompactIntArray(RBCollationTables.UNMAPPED);
// Normalize the build rules. Find occurances of all decomposed characters
// and normalize the rules before feeding into the builder. By "normalize",
// we mean that all precomposed Unicode characters must be converted into
// a base character and one or more combining characters (such as accents).
// When there are multiple combining characters attached to a base character,
// the combining characters must be in their canonical order
//
// sherman/Note:
//(1)decmp will be NO_DECOMPOSITION only in ko locale to prevent decompose
//hangual syllables to jamos, so we can actually just call decompose with
//normalizer's IGNORE_HANGUL option turned on
//
//(2)just call the "special version" in NormalizerImpl directly
//pattern = Normalizer.decompose(pattern, false, Normalizer.IGNORE_HANGUL, true);
//
//Normalizer.Mode mode = CollatorUtilities.toNormalizerMode(decmp);
//pattern = Normalizer.normalize(pattern, mode, 0, true);
pattern = NormalizerImpl.canonicalDecomposeWithSingleQuotation(pattern);
// Build the merged collation entries
// Since rules can be specified in any order in the string
// (e.g. "c , C < d , D < e , E .... C < CH")
// this splits all of the rules in the string out into separate
// objects and then sorts them. In the above example, it merges the
// "C < CH" rule in just before the "C < D" rule.
//
MPattern = new MergeCollation(pattern);
int order = 0;
// Now walk though each entry and add it to my own tables
for (i = 0; i < MPattern.Count; ++i)
{
PatternEntry entry = MPattern.GetItemAt(i);
if (entry != null)
{
groupChars = entry.Chars;
if (groupChars.Length() > 1)
{
switch (groupChars.CharAt(groupChars.Length() - 1))
{
case '@':
FrenchSec = true;
groupChars = groupChars.Substring(0, groupChars.Length() - 1);
break;
case '!':
SeAsianSwapping = true;
groupChars = groupChars.Substring(0, groupChars.Length() - 1);
break;
}
}
order = Increment(entry.Strength, order);
expChars = entry.Extension;
if (expChars.Length() != 0)
{
AddExpandOrder(groupChars, expChars, order);
}
else if (groupChars.Length() > 1)
{
char ch = groupChars.CharAt(0);
if (char.IsHighSurrogate(ch) && groupChars.Length() == 2)
{
AddOrder(Character.ToCodePoint(ch, groupChars.CharAt(1)), order);
}
else
{
AddContractOrder(groupChars, order);
}
}
else
{
char ch = groupChars.CharAt(0);
AddOrder(ch, order);
}
}
}
AddComposedChars();
Commit();
Mapping.compact();
/*
* System.out.println("mappingSize=" + mapping.getKSize());
* for (int j = 0; j < 0xffff; j++) {
* int value = mapping.elementAt(j);
* if (value != RBCollationTables.UNMAPPED)
* System.out.println("index=" + Integer.toString(j, 16)
+ ", value=" + Integer.toString(value, 16));
+ }
*/
Tables.FillInTables(FrenchSec, SeAsianSwapping, Mapping, ContractTable, ExpandTable, ContractFlags, MaxSecOrder, MaxTerOrder);
}
