Examples of com.ibm.icu.text.UnicodeSetIterator

com.ibm.icu.text.UnicodeSetIterator
UnicodeSetIterator iterates over the contents of a UnicodeSet. It iterates over either code points or code point ranges. After all code points or ranges have been returned, it returns the multicharacter strings of the UnicodSet, if any.
To iterate over code points and multicharacter strings, use a loop like this:
```
 for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) { processString(it.getString()); } 
```
To iterate over code point ranges, use a loop like this:
```
 for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.nextRange();) { if (it.codepoint != UnicodeSetIterator.IS_STRING) { processCodepointRange(it.codepoint, it.codepointEnd); } else { processString(it.getString()); } } 
```
@author M. Davis @stable ICU 2.0

  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);
      }
    }
  }

View Full Code Here

    if (set.isEmpty()) {
      System.out.println("\t  []");
    }


    HashMap<Character,UnicodeSet> utf16ByLead = new HashMap<Character,UnicodeSet>();
    for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {
      char utf16[] = Character.toChars(it.codepoint);
      UnicodeSet trails = utf16ByLead.get(utf16[0]);
      if (trails == null) {
        trails = new UnicodeSet();
        utf16ByLead.put(utf16[0], trails);

View Full Code Here

    if (set.isEmpty()) {
      System.out.println("\t  []");
    }
    
    HashMap<Character,UnicodeSet> utf16ByLead = new HashMap<Character,UnicodeSet>();
    for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {    
      char utf16[] = Character.toChars(it.codepoint);
      UnicodeSet trails = utf16ByLead.get(utf16[0]);
      if (trails == null) {
        trails = new UnicodeSet();
        utf16ByLead.put(utf16[0], trails);

View Full Code Here

    if (set.isEmpty()) {
      System.out.println("\t  []");
    }
    
    HashMap<Character,UnicodeSet> utf16ByLead = new HashMap<Character,UnicodeSet>();
    for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {    
      char utf16[] = Character.toChars(it.codepoint);
      UnicodeSet trails = utf16ByLead.get(utf16[0]);
      if (trails == null) {
        trails = new UnicodeSet();
        utf16ByLead.put(utf16[0], trails);

View Full Code Here

  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);
      }
    }
  }

View Full Code Here

    if (set.isEmpty()) {
      System.out.println("\t  []");
    }


    HashMap<Character,UnicodeSet> utf16ByLead = new HashMap<Character,UnicodeSet>();
    for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {
      char utf16[] = Character.toChars(it.codepoint);
      UnicodeSet trails = utf16ByLead.get(utf16[0]);
      if (trails == null) {
        trails = new UnicodeSet();
        utf16ByLead.put(utf16[0], trails);

View Full Code Here

    if (set.isEmpty()) {
      System.out.println("\t  []");
    }
    
    HashMap<Character,UnicodeSet> utf16ByLead = new HashMap<Character,UnicodeSet>();
    for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {    
      char utf16[] = Character.toChars(it.codepoint);
      UnicodeSet trails = utf16ByLead.get(utf16[0]);
      if (trails == null) {
        trails = new UnicodeSet();
        utf16ByLead.put(utf16[0], trails);

View Full Code Here

            errln("getMirror() does not work correctly");
        }


        /* verify that Bidi_Mirroring_Glyph roundtrips */
        UnicodeSet set=new UnicodeSet("[:Bidi_Mirrored:]");
        UnicodeSetIterator iter=new UnicodeSetIterator(set);
        int start, end, c2, c3;
        while(iter.nextRange() && (start=iter.codepoint)>=0) {
            end=iter.codepointEnd;
            do {
                c2=UCharacter.getMirror(start);
                c3=UCharacter.getMirror(c2);
                if(c3!=start) {

View Full Code Here

     * @param value
     * @return this (for chaining)
     */
    public UnicodeMap putAll(UnicodeSet codepoints, Object value) {
        // TODO optimize
        UnicodeSetIterator it = new UnicodeSetIterator(codepoints);
        while (it.nextRange()) {
            _putAll(it.codepoint, it.codepointEnd, value);
        }
        return this;
    }

View Full Code Here

        }
        return this;
    }
    
    public UnicodeMap composeWith(UnicodeSet set, Object value, Composer composer) {
        for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {
            int i = it.codepoint;
            Object v1 = getValue(i);
            Object v3 = composer.compose(i, v1, value);
            if (v1 != v3 && (v1 == null || !v1.equals(v3))) put(i, v3);
        }

View Full Code Here

0 1 2 3

TOP

Related Classes of com.ibm.icu.text.UnicodeSetIterator

com.ibm.icu.dev.demo.translit.TransliterationChart

com.ibm.icu.dev.test.lang.UCharacterTest

com.ibm.icu.dev.test.normalizer.BasicTest

com.ibm.icu.dev.test.translit.AnyScriptTest

com.ibm.icu.dev.test.translit.UnicodeSetTest

com.ibm.icu.dev.test.util.CollectionUtilities

com.ibm.icu.dev.test.util.LocaleDataTest

com.ibm.icu.dev.test.util.PrettyPrinter

com.ibm.icu.dev.test.util.UnicodeMap

com.ibm.icu.dev.test.util.UnicodePropertySource

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.