FileDocCategorySizeDatePackage
CJKTokenizer.javaAPI DocApache Lucene 1.98352Mon Feb 20 09:18:52 GMT 2006org.apache.lucene.analysis.cjk

CJKTokenizer

public final class CJKTokenizer extends Tokenizer
CJKTokenizer was modified from StopTokenizer which does a decent job for most European languages. It performs other token methods for double-byte Characters: the token will return at each two charactors with overlap match.
Example: "java C1C2C3C4" will be segment to: "java" "C1C2" "C2C3" "C3C4" it also need filter filter zero length token ""
for Digit: digit, '+', '#' will token as letter
for more info on Asia language(Chinese Japanese Korean) text segmentation: please search google
author
Che, Dong

Fields Summary
private static final int
MAX_WORD_LEN
Max word length
private static final int
IO_BUFFER_SIZE
buffer size:
private int
offset
word offset, used to imply which character(in ) is parsed
private int
bufferIndex
the index used only for ioBuffer
private int
dataLen
data length
private final char[]
buffer
character buffer, store the characters which are used to compose
the returned Token
private final char[]
ioBuffer
I/O buffer, used to store the content of the input(one of the
members of Tokenizer)
private String
tokenType
word type: single=>ASCII double=>non-ASCII word=>default
private boolean
preIsTokened
tag: previous character is a cached double-byte character "C1C2C3C4" ----(set the C1 isTokened) C1C2 "C2C3C4" ----(set the C2 isTokened) C1C2 C2C3 "C3C4" ----(set the C3 isTokened) "C1C2 C2C3 C3C4"
Constructors Summary
public CJKTokenizer(Reader in)
Construct a token stream processing the given input.

param
in I/O reader


    //~ Constructors -----------------------------------------------------------

                     
       
        input = in;
Methods Summary
public final org.apache.lucene.analysis.Tokennext()
Returns the next token in the stream, or null at EOS. See http://java.sun.com/j2se/1.3/docs/api/java/lang/Character.UnicodeBlock.html for detail.

return
Token
throws
java.io.IOException - throw IOException when read error
hanppened in the InputStream

        /** how many character(s) has been stored in buffer */
        int length = 0;

        /** the position used to create Token */
        int start = offset;

        while (true) {
            /** current charactor */
            char c;

            /** unicode block of current charactor for detail */
            Character.UnicodeBlock ub;

            offset++;

            if (bufferIndex >= dataLen) {
                dataLen = input.read(ioBuffer);
                bufferIndex = 0;
            }

            if (dataLen == -1) {
                if (length > 0) {
                    if (preIsTokened == true) {
                        length = 0;
                        preIsTokened = false;
                    }

                    break;
                } else {
                    return null;
                }
            } else {
                //get current character
                c = ioBuffer[bufferIndex++];

                //get the UnicodeBlock of the current character
                ub = Character.UnicodeBlock.of(c);
            }

            //if the current character is ASCII or Extend ASCII
            if ((ub == Character.UnicodeBlock.BASIC_LATIN)
                    || (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS)
               ) {
                if (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
                    /** convert  HALFWIDTH_AND_FULLWIDTH_FORMS to BASIC_LATIN */
                    int i = (int) c;
                    i = i - 65248;
                    c = (char) i;
                }

                // if the current character is a letter or "_" "+" "#"
                if (Character.isLetterOrDigit(c)
                        || ((c == '_") || (c == '+") || (c == '#"))
                   ) {
                    if (length == 0) {
                        // "javaC1C2C3C4linux" <br>
                        //      ^--: the current character begin to token the ASCII
                        // letter
                        start = offset - 1;
                    } else if (tokenType == "double") {
                        // "javaC1C2C3C4linux" <br>
                        //              ^--: the previous non-ASCII
                        // : the current character
                        offset--;
                        bufferIndex--;
                        tokenType = "single";

                        if (preIsTokened == true) {
                            // there is only one non-ASCII has been stored
                            length = 0;
                            preIsTokened = false;

                            break;
                        } else {
                            break;
                        }
                    }

                    // store the LowerCase(c) in the buffer
                    buffer[length++] = Character.toLowerCase(c);
                    tokenType = "single";

                    // break the procedure if buffer overflowed!
                    if (length == MAX_WORD_LEN) {
                        break;
                    }
                } else if (length > 0) {
                    if (preIsTokened == true) {
                        length = 0;
                        preIsTokened = false;
                    } else {
                        break;
                    }
                }
            } else {
                // non-ASCII letter, eg."C1C2C3C4"
                if (Character.isLetter(c)) {
                    if (length == 0) {
                        start = offset - 1;
                        buffer[length++] = c;
                        tokenType = "double";
                    } else {
                        if (tokenType == "single") {
                            offset--;
                            bufferIndex--;

                            //return the previous ASCII characters
                            break;
                        } else {
                            buffer[length++] = c;
                            tokenType = "double";

                            if (length == 2) {
                                offset--;
                                bufferIndex--;
                                preIsTokened = true;

                                break;
                            }
                        }
                    }
                } else if (length > 0) {
                    if (preIsTokened == true) {
                        // empty the buffer
                        length = 0;
                        preIsTokened = false;
                    } else {
                        break;
                    }
                }
            }
        }

        return new Token(new String(buffer, 0, length), start, start + length,
                         tokenType
                        );