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

   * 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

     * @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 isSet(opts, XMLSCHEMA_MODE) && offset != con.limit ? -1 : 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

   * 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

    }


    private String escapeJSON(Object obj) {
        StringBuilder sb = new StringBuilder();


        CharacterIterator it = new StringCharacterIterator(obj.toString());


        for (char c = it.first(); c != CharacterIterator.DONE; c = it.next()) {
            if (c == '"') {
                sb.append("\\\"");
            } else if (c == '\\') {
                sb.append("\\\\");
            } else if (c == '/') {

View Full Code Here

    
    protected static boolean checkPrefixPart(String s)
    {
        if ( s.length() == 0 )
            return true;
        CharacterIterator cIter = new StringCharacterIterator(s) ;
        char ch = cIter.first() ;
        if ( ! checkNameStartChar(ch) )
            return false ;
        if ( ch == '_' )    // Can't start with _ (bnodes labels handled separately) 
            return false ;
        return checkNameTail(cIter) ;

View Full Code Here

    
    protected static boolean checkNamePart(String s)
    {
        if ( s.length() == 0 )
            return true; 
        CharacterIterator cIter = new StringCharacterIterator(s) ;
        char ch = cIter.first() ;
        if ( ! checkNameStartChar(ch) )
            return false ;
        return checkNameTail(cIter) ;
    }

View Full Code Here

     * escape characters
     */
    private void string(Object obj) {
        this.add('"');


        CharacterIterator it = new StringCharacterIterator(obj.toString());


        for (char c = it.first(); c != CharacterIterator.DONE; c = it.next()) {
            if (c == '"') {
                this.add("\\\"");
            } else if (c == '\\') {
                this.add("\\\\");
            } else if (c == '/') {

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 (!buf.characterStyleAt(pos).equals(boldStyle)) {
                errln("Run style is wrong.");
            }


            ts = buf.getTimeStamp();
            CharacterIterator cIter = buf.createCharacterIterator();
            for (char ch = cIter.first(); ch != CharacterIterator.DONE; ch = cIter.next()) {
                if (ch != allBold.at(0)) {
                    errln("Character is wrong.");
                }
            }

View Full Code Here

            // relative path
        }


        path = path.replace('\\', '/');


        CharacterIterator iter = new StringCharacterIterator(path);
        for (char c = iter.first(); c != CharacterIterator.DONE;
             c = iter.next()) {
            if (c < 256 && isSpecial[c]) {
                sb.append('%');
                sb.append(escapedChar1[c]);
                sb.append(escapedChar2[c]);
            } else {

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.