Examples of java.text.CharacterIterator

java.text.CharacterIterator
This interface defines a protocol for bidirectional iteration over text. The iterator iterates over a bounded sequence of characters. Characters are indexed with values beginning with the value returned by getBeginIndex() and continuing through the value returned by getEndIndex()-1.
Iterators maintain a current character index, whose valid range is from getBeginIndex() to getEndIndex(); the value getEndIndex() is included to allow handling of zero-length text ranges and for historical reasons. The current index can be retrieved by calling getIndex() and set directly by calling setIndex(), first(), and last().
The methods previous() and next() are used for iteration. They return DONE if they would move outside the range from getBeginIndex() to getEndIndex() -1, signaling that the iterator has reached the end of the sequence. DONE is also returned by other methods to indicate that the current index is outside this range.
Examples:
Traverse the text from start to finish
```
 public void traverseForward(CharacterIterator iter) { for(char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) { processChar(c); } } 
```
Traverse the text backwards, from end to start
```
 public void traverseBackward(CharacterIterator iter) { for(char c = iter.last(); c != CharacterIterator.DONE; c = iter.previous()) { processChar(c); } } 
```
Traverse both forward and backward from a given position in the text. Calls to notBoundary() in this example represents some additional stopping criteria.
```
 public void traverseOut(CharacterIterator iter, int pos) { for (char c = iter.setIndex(pos); c != CharacterIterator.DONE && notBoundary(c); c = iter.next()) { } int end = iter.getIndex(); for (char c = iter.setIndex(pos); c != CharacterIterator.DONE && notBoundary(c); c = iter.previous()) { } int start = iter.getIndex(); processSection(start, end); } 
```
@see StringCharacterIterator @see AttributedCharacterIterator

        if (null != name) {
            name = name.trim();
        }
          


        CharacterIterator  ci;
        StringBuffer    n = new StringBuffer();
        boolean    up = true;
        boolean    keepCase = false;
        char    c;
        
        ci = new StringCharacterIterator(name);
        c = ci.first();
        
        // If everything is uppercase, we'll lowercase the name.
        while (c != CharacterIterator.DONE)
        {
            if (Character.isLowerCase(c))
            {
                keepCase = true;
                break;
            }
            c = ci.next();
        }
        
        c = ci.first();
        while (c != CharacterIterator.DONE)
        {
            if (c == '-' || c == '_')
                up = true;
            else
            {
                if (up)
                    c = Character.toUpperCase(c);
                else
                    if (!keepCase)
                        c = Character.toLowerCase(c);
                n.append(c);
                up = false;
            }
            c = ci.next();
        }
        return n.toString();
    }

View Full Code Here

     * lower-case (except the characters following - and _)
     * The first letter is always upper-case.
     */
    public static String convertName(String name)
    {
        CharacterIterator  ci;
        StringBuffer    n = new StringBuffer();
        boolean    up = true;
        boolean    keepCase = false;
        char    c;
        
        ci = new StringCharacterIterator(name);
        c = ci.first();
        
        // If everything is uppercase, we'll lowercase the name.
        while (c != CharacterIterator.DONE)
        {
            if (Character.isLowerCase(c))
            {
                keepCase = true;
                break;
            }
            c = ci.next();
        }
        
        c = ci.first();
        while (c != CharacterIterator.DONE)
        {
            if (c == '-' || c == '_')
                up = true;
            else
            {
                if (up)
                    c = Character.toUpperCase(c);
                else
                    if (!keepCase)
                        c = Character.toLowerCase(c);
                n.append(c);
                up = false;
            }
            c = ci.next();
        }
        return n.toString();
    }

View Full Code Here

        if (lineStartPos < fText.length()) {


            if (fLineBreak == null) {
                fLineBreak = BreakIterator.getLineInstance();
            }
            CharacterIterator charIter = fText.createCharacterIterator();
            charIter.setIndex(lineStartPos);
            fLineBreak.setText(charIter);


            firstPossibleBreak = fLineBreak.following(lineStartPos);
        }
        else

View Full Code Here

   * required to encode the string.
   * @param string text to encode
   * @return number of UTF-8 bytes required to encode
   */
  public static int utf8Length(String string) {
    CharacterIterator iter = new StringCharacterIterator(string);
    char ch = iter.first();
    int size = 0;
    while (ch != CharacterIterator.DONE) {
      if ((ch >= 0xD800) && (ch < 0xDC00)) {
        // surrogate pair?
        char trail = iter.next();
        if ((trail > 0xDBFF) && (trail < 0xE000)) {
          // valid pair
          size += 4;
        } else {
          // invalid pair
          size += 3;
          iter.previous(); // rewind one
        }
      } else if (ch < 0x80) {
        size++;
      } else if (ch < 0x800) {
        size += 2;
      } else {
        // ch < 0x10000, that is, the largest char value
        size += 3;
      }
      ch = iter.next();
    }
    return size;
  }

View Full Code Here

        }
    }
    if (canAccessClipboard) {
        String label = "";
        if (o instanceof CharacterIterator) {
      CharacterIterator iter = (CharacterIterator) o;
      char[] cbuff = new char[iter.getEndIndex()-iter.getBeginIndex()];
      if (cbuff.length > 0) {
          cbuff[0] = iter.first();
      }
      for (int i=1; i<cbuff.length;++i) {
          cbuff[i] = iter.next();
      }
      label = new String(cbuff);
        }
        Clipboard clipboard = Toolkit.getDefaultToolkit().getSystemClipboard();
        StringSelection selection = new StringSelection(label);

View Full Code Here

    public static String decodeUri(String uri) throws UnsupportedEncodingException {
        if (uri.indexOf('%') == -1) {
            return uri;
        }
        ByteArrayOutputStream sb = new ByteArrayOutputStream(uri.length());
        CharacterIterator iter = new StringCharacterIterator(uri);
        for (char c = iter.first(); c != CharacterIterator.DONE;
             c = iter.next()) {
            if (c == '%') {
                char c1 = iter.next();
                if (c1 != CharacterIterator.DONE) {
                    int i1 = Character.digit(c1, WORD);
                    char c2 = iter.next();
                    if (c2 != CharacterIterator.DONE) {
                        int i2 = Character.digit(c2, WORD);
                        sb.write((char) ((i1 << NIBBLE) + i2));
                    }
                }

View Full Code Here

            if (!useUnixTextSelection) return;


            Object o = evt.getSelection();
            if (!(o instanceof CharacterIterator))
                return;
            CharacterIterator iter = (CharacterIterator) o;


            // first see if we can access the clipboard
            SecurityManager securityManager;
            securityManager = System.getSecurityManager();
            if (securityManager != null) {
                try {
                    securityManager.checkSystemClipboardAccess();
                } catch (SecurityException e) {
                    return; // Can't access clipboard.
                }
            }


            int sz = iter.getEndIndex()-iter.getBeginIndex();
            if (sz == 0) return;


            char[] cbuff = new char[sz];
            cbuff[0] = iter.first();
            for (int i=1; i<cbuff.length;++i) {
                cbuff[i] = iter.next();
            }
            final String strSel = new String(cbuff);
            // HACK: getSystemClipboard sometimes deadlocks on
            // linux when called from the AWT Thread. The Thread
            // creation prevents that.

View Full Code Here

     * @return -1 when not match; offset of the end of matched string when match.
     */
    private int matchCharacterIterator (Context con, Op op, int offset, int dx, int opts) {




        CharacterIterator target = con.ciTarget;












        while (true) {
            if (op == null)
                return offset;
            if (offset > con.limit || offset < con.start)
                return -1;
            switch (op.type) {
            case Op.CHAR:
                if (isSet(opts, IGNORE_CASE)) {
                    int ch = op.getData();
                    if (dx > 0) {
                        if (offset >= con.limit || !matchIgnoreCase(ch,  target .setIndex(  offset ) ))
                            return -1;
                        offset ++;
                    } else {
                        int o1 = offset-1;
                        if (o1 >= con.limit || o1 < 0 || !matchIgnoreCase(ch,  target .setIndex(  o1 ) ))
                            return -1;
                        offset = o1;
                    }
                } else {
                    int ch = op.getData();
                    if (dx > 0) {
                        if (offset >= con.limit || ch !=  target .setIndex(  offset ) )
                            return -1;
                        offset ++;
                    } else {
                        int o1 = offset-1;
                        if (o1 >= con.limit || o1 < 0 || ch !=  target .setIndex(  o1 ) )
                            return -1;
                        offset = o1;
                    }
                }
                op = op.next;
                break;


            case Op.DOT:
                if (dx > 0) {
                    if (offset >= con.limit)
                        return -1;
                    int ch =  target .setIndex(  offset ) ;
                    if (isSet(opts, SINGLE_LINE)) {
                        if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                            offset ++;
                    } else {
                        if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                            ch = REUtil.composeFromSurrogates(ch,  target .setIndex(  ++offset ) );
                        if (isEOLChar(ch))
                            return -1;
                    }
                    offset ++;
                } else {
                    int o1 = offset-1;
                    if (o1 >= con.limit || o1 < 0)
                        return -1;
                    int ch =  target .setIndex(  o1 ) ;
                    if (isSet(opts, SINGLE_LINE)) {
                        if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                            o1 --;
                    } else {
                        if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                            ch = REUtil.composeFromSurrogates( target .setIndex(  --o1 ) , ch);
                        if (!isEOLChar(ch))
                            return -1;
                    }
                    offset = o1;
                }
                op = op.next;
                break;


            case Op.RANGE:
            case Op.NRANGE:
                if (dx > 0) {
                    if (offset >= con.limit)
                        return -1;
                    int ch =  target .setIndex(  offset ) ;
                    if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                        ch = REUtil.composeFromSurrogates(ch,  target .setIndex(  ++offset ) );
                    RangeToken tok = op.getToken();
                    if (isSet(opts, IGNORE_CASE)) {
                        tok = tok.getCaseInsensitiveToken();
                        if (!tok.match(ch)) {
                            if (ch >= 0x10000)  return -1;
                            char uch;
                            if (!tok.match(uch = Character.toUpperCase((char)ch))
                                && !tok.match(Character.toLowerCase(uch)))
                                return -1;
                        }
                    } else {
                        if (!tok.match(ch))  return -1;
                    }
                    offset ++;
                } else {
                    int o1 = offset-1;
                    if (o1 >= con.limit || o1 < 0)
                        return -1;
                    int ch =  target .setIndex(  o1 ) ;
                    if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                        ch = REUtil.composeFromSurrogates( target .setIndex(  --o1 ) , ch);
                    RangeToken tok = op.getToken();
                    if (isSet(opts, IGNORE_CASE)) {
                        tok = tok.getCaseInsensitiveToken();
                        if (!tok.match(ch)) {
                            if (ch >= 0x10000)  return -1;
                            char uch;
                            if (!tok.match(uch = Character.toUpperCase((char)ch))
                                && !tok.match(Character.toLowerCase(uch)))
                                return -1;
                        }
                    } else {
                        if (!tok.match(ch))  return -1;
                    }
                    offset = o1;
                }
                op = op.next;
                break;


            case Op.ANCHOR:
                boolean go = false;
                switch (op.getData()) {
                case '^':
                    if (isSet(opts, MULTIPLE_LINES)) {
                        if (!(offset == con.start
                              || offset > con.start && isEOLChar( target .setIndex(  offset-1 ) )))
                            return -1;
                    } else {
                        if (offset != con.start)
                            return -1;
                    }
                    break;


                case '@':                         // Internal use only.
                    // The @ always matches line beginnings.
                    if (!(offset == con.start
                          || offset > con.start && isEOLChar( target .setIndex(  offset-1 ) )))
                        return -1;
                    break;


                case '$':
                    if (isSet(opts, MULTIPLE_LINES)) {
                        if (!(offset == con.limit
                              || offset < con.limit && isEOLChar( target .setIndex(  offset ) )))
                            return -1;
                    } else {
                        if (!(offset == con.limit
                              || offset+1 == con.limit && isEOLChar( target .setIndex(  offset ) )
                              || offset+2 == con.limit &&  target .setIndex(  offset )  == CARRIAGE_RETURN
                              &&  target .setIndex(  offset+1 )  == LINE_FEED))
                            return -1;
                    }
                    break;


                case 'A':
                    if (offset != con.start)  return -1;
                    break;


                case 'Z':
                    if (!(offset == con.limit
                          || offset+1 == con.limit && isEOLChar( target .setIndex(  offset ) )
                          || offset+2 == con.limit &&  target .setIndex(  offset )  == CARRIAGE_RETURN
                          &&  target .setIndex(  offset+1 )  == LINE_FEED))
                        return -1;
                    break;


                case 'z':
                    if (offset != con.limit)  return -1;

View Full Code Here

            if (!useUnixTextSelection) return;


            Object o = evt.getSelection();
            if (!(o instanceof CharacterIterator))
                return;
            CharacterIterator iter = (CharacterIterator) o;


            // first see if we can access the clipboard
            SecurityManager securityManager;
            securityManager = System.getSecurityManager();
            if (securityManager != null) {
                try {
                    securityManager.checkSystemClipboardAccess();
                } catch (SecurityException e) {
                    return; // Can't access clipboard.
                }
            }


            int sz = iter.getEndIndex()-iter.getBeginIndex();
            if (sz == 0) return;


            char[] cbuff = new char[sz];
            cbuff[0] = iter.first();
            for (int i=1; i<cbuff.length;++i) {
                cbuff[i] = iter.next();
            }
            final String strSel = new String(cbuff);
            // HACK: getSystemClipboard sometimes deadlocks on
            // linux when called from the AWT Thread. The Thread
            // creation prevents that.

View Full Code Here

     * @return -1 when not match; offset of the end of matched string when match.
     */
    private int matchCharacterIterator (Context con, Op op, int offset, int dx, int opts) {




        CharacterIterator target = con.ciTarget;












        while (true) {
            if (op == null)
                return offset;
            if (offset > con.limit || offset < con.start)
                return -1;
            switch (op.type) {
            case Op.CHAR:
                if (isSet(opts, IGNORE_CASE)) {
                    int ch = op.getData();
                    if (dx > 0) {
                        if (offset >= con.limit || !matchIgnoreCase(ch,  target .setIndex(  offset ) ))
                            return -1;
                        offset ++;
                    } else {
                        int o1 = offset-1;
                        if (o1 >= con.limit || o1 < 0 || !matchIgnoreCase(ch,  target .setIndex(  o1 ) ))
                            return -1;
                        offset = o1;
                    }
                } else {
                    int ch = op.getData();
                    if (dx > 0) {
                        if (offset >= con.limit || ch !=  target .setIndex(  offset ) )
                            return -1;
                        offset ++;
                    } else {
                        int o1 = offset-1;
                        if (o1 >= con.limit || o1 < 0 || ch !=  target .setIndex(  o1 ) )
                            return -1;
                        offset = o1;
                    }
                }
                op = op.next;
                break;


            case Op.DOT:
                if (dx > 0) {
                    if (offset >= con.limit)
                        return -1;
                    int ch =  target .setIndex(  offset ) ;
                    if (isSet(opts, SINGLE_LINE)) {
                        if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                            offset ++;
                    } else {
                        if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                            ch = REUtil.composeFromSurrogates(ch,  target .setIndex(  ++offset ) );
                        if (isEOLChar(ch))
                            return -1;
                    }
                    offset ++;
                } else {
                    int o1 = offset-1;
                    if (o1 >= con.limit || o1 < 0)
                        return -1;
                    int ch =  target .setIndex(  o1 ) ;
                    if (isSet(opts, SINGLE_LINE)) {
                        if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                            o1 --;
                    } else {
                        if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                            ch = REUtil.composeFromSurrogates( target .setIndex(  --o1 ) , ch);
                        if (!isEOLChar(ch))
                            return -1;
                    }
                    offset = o1;
                }
                op = op.next;
                break;


            case Op.RANGE:
            case Op.NRANGE:
                if (dx > 0) {
                    if (offset >= con.limit)
                        return -1;
                    int ch =  target .setIndex(  offset ) ;
                    if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                        ch = REUtil.composeFromSurrogates(ch,  target .setIndex(  ++offset ) );
                    RangeToken tok = op.getToken();
                    if (isSet(opts, IGNORE_CASE)) {
                        tok = tok.getCaseInsensitiveToken();
                        if (!tok.match(ch)) {
                            if (ch >= 0x10000)  return -1;
                            char uch;
                            if (!tok.match(uch = Character.toUpperCase((char)ch))
                                && !tok.match(Character.toLowerCase(uch)))
                                return -1;
                        }
                    } else {
                        if (!tok.match(ch))  return -1;
                    }
                    offset ++;
                } else {
                    int o1 = offset-1;
                    if (o1 >= con.limit || o1 < 0)
                        return -1;
                    int ch =  target .setIndex(  o1 ) ;
                    if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                        ch = REUtil.composeFromSurrogates( target .setIndex(  --o1 ) , ch);
                    RangeToken tok = op.getToken();
                    if (isSet(opts, IGNORE_CASE)) {
                        tok = tok.getCaseInsensitiveToken();
                        if (!tok.match(ch)) {
                            if (ch >= 0x10000)  return -1;
                            char uch;
                            if (!tok.match(uch = Character.toUpperCase((char)ch))
                                && !tok.match(Character.toLowerCase(uch)))
                                return -1;
                        }
                    } else {
                        if (!tok.match(ch))  return -1;
                    }
                    offset = o1;
                }
                op = op.next;
                break;


            case Op.ANCHOR:
                boolean go = false;
                switch (op.getData()) {
                case '^':
                    if (isSet(opts, MULTIPLE_LINES)) {
                        if (!(offset == con.start
                              || offset > con.start && isEOLChar( target .setIndex(  offset-1 ) )))
                            return -1;
                    } else {
                        if (offset != con.start)
                            return -1;
                    }
                    break;


                case '@':                         // Internal use only.
                    // The @ always matches line beginnings.
                    if (!(offset == con.start
                          || offset > con.start && isEOLChar( target .setIndex(  offset-1 ) )))
                        return -1;
                    break;


                case '$':
                    if (isSet(opts, MULTIPLE_LINES)) {
                        if (!(offset == con.limit
                              || offset < con.limit && isEOLChar( target .setIndex(  offset ) )))
                            return -1;
                    } else {
                        if (!(offset == con.limit
                              || offset+1 == con.limit && isEOLChar( target .setIndex(  offset ) )
                              || offset+2 == con.limit &&  target .setIndex(  offset )  == CARRIAGE_RETURN
                              &&  target .setIndex(  offset+1 )  == LINE_FEED))
                            return -1;
                    }
                    break;


                case 'A':
                    if (offset != con.start)  return -1;
                    break;


                case 'Z':
                    if (!(offset == con.limit
                          || offset+1 == con.limit && isEOLChar( target .setIndex(  offset ) )
                          || offset+2 == con.limit &&  target .setIndex(  offset )  == CARRIAGE_RETURN
                          &&  target .setIndex(  offset+1 )  == LINE_FEED))
                        return -1;
                    break;


                case 'z':
                    if (offset != con.limit)  return -1;

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of java.text.CharacterIterator

avrora.util.StringUtil

cn.bran.japid.util.DirUtil

com.hp.hpl.jena.n3.N3JenaWriterCommon

com.ibm.icu.dev.test.iterator.TestUCharacterIterator

com.ibm.icu.tests.BreakIteratorTest

com.ibm.icu.text.DictionaryBasedBreakIterator

com.ibm.icu.text.RuleBasedBreakIterator

com.ibm.icu.text.RuleBasedCollator

com.ibm.icu.text.ThaiBreakIterator

com.rabbitmq.tools.json.JSONWriter

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.