/// <summary>
/// Transforms the string into a series of characters that can be compared
/// with CollationKey.compareTo. This overrides java.text.Collator.getCollationKey.
/// It can be overriden in a subclass.
/// </summary>
public override CollationKey GetCollationKey(String source)
{
lock (this)
{
//
// The basic algorithm here is to find all of the collation elements for each
// character in the source string, convert them to a char representation,
// and put them into the collation key. But it's trickier than that.
// Each collation element in a string has three components: primary (A vs B),
// secondary (A vs A-acute), and tertiary (A' vs a); and a primary difference
// at the end of a string takes precedence over a secondary or tertiary
// difference earlier in the string.
//
// To account for this, we put all of the primary orders at the beginning of the
// string, followed by the secondary and tertiary orders, separated by nulls.
//
// Here's a hypothetical example, with the collation element represented as
// a three-digit number, one digit for primary, one for secondary, etc.
//
// String: A a B \u00e9 <--(e-acute)
// Collation Elements: 101 100 201 510
//
// Collation Key: 1125<null>0001<null>1010
//
// To make things even trickier, secondary differences (accent marks) are compared
// starting at the *end* of the string in languages with French secondary ordering.
// But when comparing the accent marks on a single base character, they are compared
// from the beginning. To handle this, we reverse all of the accents that belong
// to each base character, then we reverse the entire string of secondary orderings
// at the end. Taking the same example above, a French collator might return
// this instead:
//
// Collation Key: 1125<null>1000<null>1010
//
if (source == null)
{
return(null);
}
if (PrimResult == null)
{
PrimResult = new StringBuffer();
SecResult = new StringBuffer();
TerResult = new StringBuffer();
}
else
{
PrimResult.Length = 0;
SecResult.Length = 0;
TerResult.Length = 0;
}
int order = 0;
bool compareSec = (Strength >= Collator.SECONDARY);
bool compareTer = (Strength >= Collator.TERTIARY);
int secOrder = CollationElementIterator.NULLORDER;
int terOrder = CollationElementIterator.NULLORDER;
int preSecIgnore = 0;
if (SourceCursor == null)
{
SourceCursor = GetCollationElementIterator(source);
}
else
{
SourceCursor.Text = source;
}
// walk through each character
while ((order = SourceCursor.Next()) != CollationElementIterator.NULLORDER)
{
secOrder = CollationElementIterator.SecondaryOrder(order);
terOrder = CollationElementIterator.TertiaryOrder(order);
if (!CollationElementIterator.IsIgnorable(order))
{
PrimResult.Append((char)(CollationElementIterator.PrimaryOrder(order) + COLLATIONKEYOFFSET));
if (compareSec)
{
//
// accumulate all of the ignorable/secondary characters attached
// to a given base character
//
if (Tables_Renamed.FrenchSec && preSecIgnore < SecResult.Length())
{
//
// We're doing reversed secondary ordering and we've hit a base
// (non-ignorable) character. Reverse any secondary orderings
// that applied to the last base character. (see block comment above.)
//
RBCollationTables.Reverse(SecResult, preSecIgnore, SecResult.Length());
}
// Remember where we are in the secondary orderings - this is how far
// back to go if we need to reverse them later.
SecResult.Append((char)(secOrder + COLLATIONKEYOFFSET));
preSecIgnore = SecResult.Length();
}
if (compareTer)
{
TerResult.Append((char)(terOrder + COLLATIONKEYOFFSET));
}
}
else
{
if (compareSec && secOrder != 0)
{
SecResult.Append((char)(secOrder + Tables_Renamed.MaxSecOrder + COLLATIONKEYOFFSET));
}
if (compareTer && terOrder != 0)
{
TerResult.Append((char)(terOrder + Tables_Renamed.MaxTerOrder + COLLATIONKEYOFFSET));
}
}
}
if (Tables_Renamed.FrenchSec)
{
if (preSecIgnore < SecResult.Length())
{
// If we've accumulated any secondary characters after the last base character,
// reverse them.
RBCollationTables.Reverse(SecResult, preSecIgnore, SecResult.Length());
}
// And now reverse the entire secResult to get French secondary ordering.
RBCollationTables.Reverse(SecResult, 0, SecResult.Length());
}
PrimResult.Append((char)0);
SecResult.Append((char)0);
SecResult.Append(TerResult.ToString());
PrimResult.Append(SecResult.ToString());
if (Strength == IDENTICAL)
{
PrimResult.Append((char)0);
int mode = Decomposition;
if (mode == CANONICAL_DECOMPOSITION)
{
PrimResult.Append(Normalizer.Normalize(source, Normalizer.Form.NFD));
}
else if (mode == FULL_DECOMPOSITION)
{
PrimResult.Append(Normalizer.Normalize(source, Normalizer.Form.NFKD));
}
else
{
PrimResult.Append(source);
}
}
return(new RuleBasedCollationKey(source, PrimResult.ToString()));
}
}
/// <summary>
/// RuleBasedCollator constructor. This takes the table rules and builds
/// a collation table out of them. Please see RuleBasedCollator class
/// description for more details on the collation rule syntax. </summary>
/// <seealso cref= java.util.Locale </seealso>
/// <param name="rules"> the collation rules to build the collation table from. </param>
/// <param name="decomp"> the decomposition strength used to build the
/// collation table and to perform comparisons. </param>
/// <exception cref="ParseException"> A format exception
/// will be thrown if the build process of the rules fails. For
/// example, build rule "a < ? < d" will cause the constructor to
/// throw the ParseException because the '?' is not quoted. </exception>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: RuleBasedCollator(String rules, int decomp) throws ParseException
internal RuleBasedCollator(String rules, int decomp)
{
Strength = Collator.TERTIARY;
Decomposition = decomp;
Tables_Renamed = new RBCollationTables(rules, decomp);
}