use of com.ibm.icu.text.UnicodeSetIterator in project lucene-solr by apache.
the class GenerateUTR30DataFiles method expandSingleRule.
private static void expandSingleRule(StringBuilder builder, String leftHandSide, String rightHandSide) throws IllegalArgumentException {
UnicodeSet set = new UnicodeSet(leftHandSide, UnicodeSet.IGNORE_SPACE);
boolean numericValue = NUMERIC_VALUE_PATTERN.matcher(rightHandSide).matches();
for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.nextRange(); ) {
if (it.codepoint != UnicodeSetIterator.IS_STRING) {
if (numericValue) {
for (int cp = it.codepoint; cp <= it.codepointEnd; ++cp) {
builder.append(String.format(Locale.ROOT, "%04X", cp)).append('>');
builder.append(String.format(Locale.ROOT, "%04X", 0x30 + UCharacter.getNumericValue(cp)));
builder.append(" # ").append(UCharacter.getName(cp));
builder.append("\n");
}
} else {
builder.append(String.format(Locale.ROOT, "%04X", it.codepoint));
if (it.codepointEnd > it.codepoint) {
builder.append("..").append(String.format(Locale.ROOT, "%04X", it.codepointEnd));
}
builder.append('>').append(rightHandSide).append("\n");
}
} else {
System.err.println("ERROR: String '" + it.getString() + "' found in UnicodeSet");
System.exit(1);
}
}
}
Aggregations