使用 Lucene.Net 进行全文索引,支持中文

Lucene.Net 对中文的支持不好这是不争的事实,即使能对中文分词也只是两两组合,即比如说一个字符串“我爱博客园,我爱编程”,那么使用 Lucene.Net 分词后变成 下面这些词:

我爱
爱博
博客
客园
我爱
爱编
编程

个人建议还是用 Lucene.Net 搭配 盘古 或其它开源组件来分词,毕竟 Lucene.Net 不懂中文,没有比较全的词库。可惜盘古最近不怎么更新了,最后一次更新还是 2010-08-18 号,也不知道是什么原因,我只知道最新版的 Lucene.Net (版本是:Lucene.Net 3.0.3)不能使用盘古最新的版本,只能用盘古最新版所搭配的 Lucene.Net,具体的可以去下载最新版的盘古,里面有示例代码,自己好好研究一下。

下面我贴出 Lucene.Net 所带的中文 Analysis,不过不是我自己写的,也是网上找的,大家看看就好。

解决方案:

Lucene.Net.Analysis.CJK 项目下的类 CJKAnalyzer.cs 和 CJKTokenizer.cs 代码分别如下:

View Code
using System;
using System.IO;
using System.Collections;
using Lucene.Net.Analysis;

namespace Lucene.Net.Analysis.CJK
{
    /* ====================================================================
     * The Apache Software License, Version 1.1
     *
     * Copyright (c) 2004 The Apache Software Foundation.  All rights
     * reserved.
     *
     * Redistribution and use in source and binary forms, with or without
     * modification, are permitted provided that the following conditions
     * are met:
     *
     * 1. Redistributions of source code must retain the above copyright
     *    notice, this list of conditions and the following disclaimer.
     *
     * 2. Redistributions in binary form must reproduce the above copyright
     *    notice, this list of conditions and the following disclaimer in
     *    the documentation and/or other materials provided with the
     *    distribution.
     *
     * 3. The end-user documentation included with the redistribution,
     *    if any, must include the following acknowledgment:
     *       "This product includes software developed by the
     *        Apache Software Foundation (http://www.apache.org/)."
     *    Alternately, this acknowledgment may appear in the software itself,
     *    if and wherever such third-party acknowledgments normally appear.
     *
     * 4. The names "Apache" and "Apache Software Foundation" and
     *    "Apache Lucene" must not be used to endorse or promote products
     *    derived from this software without prior written permission. For
     *    written permission, please contact apache@apache.org.
     *
     * 5. Products derived from this software may not be called "Apache",
     *    "Apache Lucene", nor may "Apache" appear in their name, without
     *    prior written permission of the Apache Software Foundation.
     *
     * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
     * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
     * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
     * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
     * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
     * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
     * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
     * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
     * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
     * SUCH DAMAGE.
     * ====================================================================
     *
     * This software consists of voluntary contributions made by many
     * individuals on behalf of the Apache Software Foundation.  For more
     * information on the Apache Software Foundation, please see
     * <http://www.apache.org/>.
     *
     * $Id: CJKAnalyzer.java,v 1.2 2004/01/22 20:54:47 ehatcher Exp $
     */

    /// <summary>
    /// Filters CJKTokenizer with StopFilter.
    /// 
    /// @author Che, Dong
    /// </summary>
    public class CJKAnalyzer : Analyzer 
    {
        //~ Static fields/initializers ---------------------------------------------

        /**
          * An array containing some common English words that are not usually
          * useful for searching. and some double-byte interpunctions.....
          */
        private static String[] stopWords = 
        {
            "a", "and", "are", "as", "at", "be",
            "but", "by", "for", "if", "in",
            "into", "is", "it", "no", "not",
            "of", "on", "or", "s", "such", "t",
            "that", "the", "their", "then",
            "there", "these", "they", "this",
            "to", "was", "will", "with", "",
            "www"
        };

        //~ Instance fields --------------------------------------------------------

        /** stop word list */
        private Hashtable stopTable;

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

        /// <summary>
        /// Builds an analyzer which removes words in STOP_WORDS.
        /// </summary>
        public CJKAnalyzer() 
        {
            stopTable = StopFilter.MakeStopTable(stopWords);
        }

        /// <summary>
        /// Builds an analyzer which removes words in the provided array.
        /// </summary>
        /// <param name="stopWords">stop word array</param>
        public CJKAnalyzer(String[] stopWords) 
        {
            stopTable = StopFilter.MakeStopTable(stopWords);
        }

        //~ Methods ----------------------------------------------------------------

        /// <summary>
        /// get token stream from input
        /// </summary>
        /// <param name="fieldName">lucene field name</param>
        /// <param name="reader">input reader</param>
        /// <returns>Token Stream</returns>
        public override sealed TokenStream TokenStream(String fieldName, TextReader reader) 
        {
            return new StopFilter(new CJKTokenizer(reader), stopTable);
        }
    }
}
View Code
using System;
using System.IO;
using System.Text;
using Lucene.Net.Analysis;

namespace Lucene.Net.Analysis.CJK
{
    /* ====================================================================
     * The Apache Software License, Version 1.1
     *
     * Copyright (c) 2004 The Apache Software Foundation.  All rights
     * reserved.
     *
     * Redistribution and use in source and binary forms, with or without
     * modification, are permitted provided that the following conditions
     * are met:
     *
     * 1. Redistributions of source code must retain the above copyright
     *    notice, this list of conditions and the following disclaimer.
     *
     * 2. Redistributions in binary form must reproduce the above copyright
     *    notice, this list of conditions and the following disclaimer in
     *    the documentation and/or other materials provided with the
     *    distribution.
     *
     * 3. The end-user documentation included with the redistribution,
     *    if any, must include the following acknowledgment:
     *       "This product includes software developed by the
     *        Apache Software Foundation (http://www.apache.org/)."
     *    Alternately, this acknowledgment may appear in the software itself,
     *    if and wherever such third-party acknowledgments normally appear.
     *
     * 4. The names "Apache" and "Apache Software Foundation" and
     *    "Apache Lucene" must not be used to endorse or promote products
     *    derived from this software without prior written permission. For
     *    written permission, please contact apache@apache.org.
     *
     * 5. Products derived from this software may not be called "Apache",
     *    "Apache Lucene", nor may "Apache" appear in their name, without
     *    prior written permission of the Apache Software Foundation.
     *
     * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
     * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
     * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
     * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
     * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
     * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
     * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
     * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
     * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
     * SUCH DAMAGE.
     * ====================================================================
     *
     * This software consists of voluntary contributions made by many
     * individuals on behalf of the Apache Software Foundation.  For more
     * information on the Apache Software Foundation, please see
     * <http://www.apache.org/>.
     */

    /// <summary>
    /// <p>
    /// CJKTokenizer was modified from StopTokenizer which does a decent job for
    /// most European languages. and it perferm other token method for double-byte
    /// Characters: the token will return at each two charactors with overlap match.<br>
    /// Example: "java C1C2C3C4" will be segment to: "java" "C1C2" "C2C3" "C3C4" it
    /// also need filter filter zero length token ""<br>
    /// for Digit: digit, '+', '#' will token as letter<br>
    /// for more info on Asia language(Chinese Japanese Korean) text segmentation:
    /// please search  <a
    /// href="http://www.google.com/search?q=word+chinese+segment">google</a>
    /// </p>
    /// 
    /// @author Che, Dong
    /// @version $Id: CJKTokenizer.java,v 1.3 2003/01/22 20:54:47 otis Exp $
    /// </summary>
    public sealed class CJKTokenizer : Tokenizer 
    {
        //~ Static fields/initializers ---------------------------------------------

        /** Max word length */
        private static int MAX_WORD_LEN = 255;

        /** buffer size: */
        private static int IO_BUFFER_SIZE = 256;

        //~ Instance fields --------------------------------------------------------

        /** word offset, used to imply which character(in ) is parsed */
        private int offset = 0;

        /** the index used only for ioBuffer */
        private int bufferIndex = 0;

        /** data length */
        private int dataLen = 0;

        /**
         * character buffer, store the characters which are used to compose <br>
         * the returned Token
         */
        private char[] buffer = new char[MAX_WORD_LEN];

        /**
         * I/O buffer, used to store the content of the input(one of the <br>
         * members of Tokenizer)
         */
        private char[] ioBuffer = new char[IO_BUFFER_SIZE];

        /** word type: single=>ASCII  double=>non-ASCII word=>default */
        private String tokenType = "word";

        /**
         * 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"
         */
        private bool preIsTokened = false;

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

        /// <summary>
        /// Construct a token stream processing the given input.
        /// </summary>
        /// <param name="_in">I/O reader</param>
        public CJKTokenizer(TextReader _in) 
        {
            input = _in;
        }

        //~ Methods ----------------------------------------------------------------

        /// <summary>
        ///  Returns the next token in the stream, or null at EOS.
        /// </summary>
        /// <returns>Token</returns>
        public override Token Next()
        {
            /** 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, 0, ioBuffer.Length);
                    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 (('\u0000' <= c && c <= '\u007F') || 
                    ('\uFF00' <= c && c <= '\uFFEF')) 
                {
                    if ('\uFF00' <= c && c <= '\uFFEF')
                    {
                        /** 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 (Char.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++] = Char.ToLower(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 (Char.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
                );
        }
    }

}

Lucene.Net.Analysis.Cn 项目下的类 ChineseAnalyzer.cs 和 ChineseFilter.cs 和 ChineseTokenizer.cs 代码分别如下:

View Code
using System;
using System.IO;
using System.Text;
using System.Collections;

using Lucene.Net.Analysis;

namespace Lucene.Net.Analysis.Cn
{
    /* ====================================================================
     * The Apache Software License, Version 1.1
     *
     * Copyright (c) 2004 The Apache Software Foundation.  All rights
     * reserved.
     *
     * Redistribution and use in source and binary forms, with or without
     * modification, are permitted provided that the following conditions
     * are met:
     *
     * 1. Redistributions of source code must retain the above copyright
     *    notice, this list of conditions and the following disclaimer.
     *
     * 2. Redistributions in binary form must reproduce the above copyright
     *    notice, this list of conditions and the following disclaimer in
     *    the documentation and/or other materials provided with the
     *    distribution.
     *
     * 3. The end-user documentation included with the redistribution,
     *    if any, must include the following acknowledgment:
     *       "This product includes software developed by the
     *        Apache Software Foundation (http://www.apache.org/)."
     *    Alternately, this acknowledgment may appear in the software itself,
     *    if and wherever such third-party acknowledgments normally appear.
     *
     * 4. The names "Apache" and "Apache Software Foundation" and
     *    "Apache Lucene" must not be used to endorse or promote products
     *    derived from this software without prior written permission. For
     *    written permission, please contact apache@apache.org.
     *
     * 5. Products derived from this software may not be called "Apache",
     *    "Apache Lucene", nor may "Apache" appear in their name, without
     *    prior written permission of the Apache Software Foundation.
     *
     * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
     * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
     * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
     * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
     * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
     * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
     * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
     * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
     * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
     * SUCH DAMAGE.
     * ====================================================================
     *
     * This software consists of voluntary contributions made by many
     * individuals on behalf of the Apache Software Foundation.  For more
     * information on the Apache Software Foundation, please see
     * <http://www.apache.org/>.
     */

    /// <summary>
    /// Title: ChineseAnalyzer
    /// Description:
    ///   Subclass of org.apache.lucene.analysis.Analyzer
    ///   build from a ChineseTokenizer, filtered with ChineseFilter.
    /// Copyright:   Copyright (c) 2001
    /// Company:
    /// @author Yiyi Sun
    /// @version $Id: ChineseAnalyzer.java, v 1.2 2003/01/22 20:54:47 ehatcher Exp $
    /// </summary>
    public class ChineseAnalyzer : Analyzer 
    {

        public ChineseAnalyzer() 
        {
        }

        /// <summary>
        /// Creates a TokenStream which tokenizes all the text in the provided Reader.
        /// </summary>
        /// <returns>A TokenStream build from a ChineseTokenizer filtered with ChineseFilter.</returns>
        public override sealed TokenStream TokenStream(String fieldName, TextReader reader) 
        {
            TokenStream result = new ChineseTokenizer(reader);
            result = new ChineseFilter(result);
            return result;
        }
    }
}
View Code
using System;
using System.IO;
using System.Collections;
using System.Globalization;

using Lucene.Net.Analysis;

namespace Lucene.Net.Analysis.Cn
{
    /* ====================================================================
     * The Apache Software License, Version 1.1
     *
     * Copyright (c) 2004 The Apache Software Foundation.  All rights
     * reserved.
     *
     * Redistribution and use in source and binary forms, with or without
     * modification, are permitted provided that the following conditions
     * are met:
     *
     * 1. Redistributions of source code must retain the above copyright
     *    notice, this list of conditions and the following disclaimer.
     *
     * 2. Redistributions in binary form must reproduce the above copyright
     *    notice, this list of conditions and the following disclaimer in
     *    the documentation and/or other materials provided with the
     *    distribution.
     *
     * 3. The end-user documentation included with the redistribution,
     *    if any, must include the following acknowledgment:
     *       "This product includes software developed by the
     *        Apache Software Foundation (http://www.apache.org/)."
     *    Alternately, this acknowledgment may appear in the software itself,
     *    if and wherever such third-party acknowledgments normally appear.
     *
     * 4. The names "Apache" and "Apache Software Foundation" and
     *    "Apache Lucene" must not be used to endorse or promote products
     *    derived from this software without prior written permission. For
     *    written permission, please contact apache@apache.org.
     *
     * 5. Products derived from this software may not be called "Apache",
     *    "Apache Lucene", nor may "Apache" appear in their name, without
     *    prior written permission of the Apache Software Foundation.
     *
     * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
     * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
     * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
     * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
     * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
     * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
     * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
     * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
     * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
     * SUCH DAMAGE.
     * ====================================================================
     *
     * This software consists of voluntary contributions made by many
     * individuals on behalf of the Apache Software Foundation.  For more
     * information on the Apache Software Foundation, please see
     * <http://www.apache.org/>.
     */

    /// <summary>
    /// Title: ChineseFilter
    /// Description: Filter with a stop word table
    ///              Rule: No digital is allowed.
    ///                    English word/token should larger than 1 character.
    ///                    One Chinese character as one Chinese word.
    /// TO DO:
    ///   1. Add Chinese stop words, such as \ue400
    ///   2. Dictionary based Chinese word extraction
    ///   3. Intelligent Chinese word extraction
    /// 
    /// Copyright:    Copyright (c) 2001
    /// Company:
    /// @author Yiyi Sun
    /// @version $Id: ChineseFilter.java, v 1.4 2003/01/23 12:49:33 ehatcher Exp $
    /// </summary>
    public sealed class ChineseFilter : TokenFilter 
    {
        // Only English now, Chinese to be added later.
        public static String[] STOP_WORDS = 
                 {
                     "and", "are", "as", "at", "be", "but", "by",
                     "for", "if", "in", "into", "is", "it",
                     "no", "not", "of", "on", "or", "such",
                     "that", "the", "their", "then", "there", "these",
                     "they", "this", "to", "was", "will", "with"
                 };

        private Hashtable stopTable;

        public ChineseFilter(TokenStream _in) : base (_in)
        {
            stopTable = new Hashtable(STOP_WORDS.Length);

            for (int i = 0; i < STOP_WORDS.Length; i++)
                stopTable[STOP_WORDS[i]] = STOP_WORDS[i];
        }

        public override Token Next()
        {

            for (Token token = input.Next(); token != null; token = input.Next()) 
            {
                String text = token.TermText();

                // why not key off token type here assuming ChineseTokenizer comes first?
                if (stopTable[text] == null) 
                {
                    switch (Char.GetUnicodeCategory(text[0])) 
                    {

                        case UnicodeCategory.LowercaseLetter:
                        case UnicodeCategory.UppercaseLetter:

                            // English word/token should larger than 1 character.
                            if (text.Length > 1) 
                            {
                                return token;
                            }
                            break;
                        case UnicodeCategory.OtherLetter:

                            // One Chinese character as one Chinese word.
                            // Chinese word extraction to be added later here.

                            return token;
                    }

                }

            }
            return null;
        }
    }
}
View Code
using System;
using System.IO;
using System.Text;
using System.Collections;
using System.Globalization;

using Lucene.Net.Analysis;

namespace Lucene.Net.Analysis.Cn
{
    /* ====================================================================
     * The Apache Software License, Version 1.1
     *
     * Copyright (c) 2004 The Apache Software Foundation.  All rights
     * reserved.
     *
     * Redistribution and use in source and binary forms, with or without
     * modification, are permitted provided that the following conditions
     * are met:
     *
     * 1. Redistributions of source code must retain the above copyright
     *    notice, this list of conditions and the following disclaimer.
     *
     * 2. Redistributions in binary form must reproduce the above copyright
     *    notice, this list of conditions and the following disclaimer in
     *    the documentation and/or other materials provided with the
     *    distribution.
     *
     * 3. The end-user documentation included with the redistribution,
     *    if any, must include the following acknowledgment:
     *       "This product includes software developed by the
     *        Apache Software Foundation (http://www.apache.org/)."
     *    Alternately, this acknowledgment may appear in the software itself,
     *    if and wherever such third-party acknowledgments normally appear.
     *
     * 4. The names "Apache" and "Apache Software Foundation" and
     *    "Apache Lucene" must not be used to endorse or promote products
     *    derived from this software without prior written permission. For
     *    written permission, please contact apache@apache.org.
     *
     * 5. Products derived from this software may not be called "Apache",
     *    "Apache Lucene", nor may "Apache" appear in their name, without
     *    prior written permission of the Apache Software Foundation.
     *
     * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
     * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
     * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
     * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
     * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
     * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
     * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
     * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
     * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
     * SUCH DAMAGE.
     * ====================================================================
     *
     * This software consists of voluntary contributions made by many
     * individuals on behalf of the Apache Software Foundation.  For more
     * information on the Apache Software Foundation, please see
     * <http://www.apache.org/>.
     */

    /**
     * Title: ChineseTokenizer
     * Description: Extract tokens from the Stream using Character.getType()
     *              Rule: A Chinese character as a single token
     * Copyright:   Copyright (c) 2001
     * Company:
     *
     * The difference between thr ChineseTokenizer and the
     * CJKTokenizer (id=23545) is that they have different
     * token parsing logic.
     * 
     * Let me use an example. If having a Chinese text
     * "C1C2C3C4" to be indexed, the tokens returned from the
     * ChineseTokenizer are C1, C2, C3, C4. And the tokens
     * returned from the CJKTokenizer are C1C2, C2C3, C3C4.
     *
     * Therefore the index the CJKTokenizer created is much
     * larger.
     *
     * The problem is that when searching for C1, C1C2, C1C3,
     * C4C2, C1C2C3 ... the ChineseTokenizer works, but the
     * CJKTokenizer will not work.
     *
     * @author Yiyi Sun
     * @version $Id: ChineseTokenizer.java, v 1.4 2003/03/02 13:56:03 otis Exp $
     *
     */

    public sealed class ChineseTokenizer : Tokenizer 
    {


        public ChineseTokenizer(TextReader _in) 
        {
            input = _in;
        }

        private int offset = 0, bufferIndex=0, dataLen=0;
        private static int MAX_WORD_LEN = 255;
        private static int IO_BUFFER_SIZE = 1024;
        private char[] buffer = new char[MAX_WORD_LEN];
        private char[] ioBuffer = new char[IO_BUFFER_SIZE];

        private int length;
        private int start;

        private void Push(char c) 
        {

            if (length == 0) start = offset-1;            // start of token
            buffer[length++] = Char.ToLower(c);  // buffer it

        }

        private Token Flush() 
        {

            if (length > 0) 
            {
                //System.out.println(new String(buffer, 0, length));
                return new Token(new String(buffer, 0, length), start, start+length);
            }
            else
                return null;
        }

        public override Token Next()
        {

            length = 0;
            start = offset;


            while (true) 
            {

                char c;
                offset++;

                if (bufferIndex >= dataLen) 
                {
                    dataLen = input.Read(ioBuffer, 0, ioBuffer.Length);
                    bufferIndex = 0;
                };

                if (dataLen == -1) return Flush();
                else
                    c = ioBuffer[bufferIndex++];


                switch(Char.GetUnicodeCategory(c)) 
                {

                    case UnicodeCategory.DecimalDigitNumber:
                    case UnicodeCategory.LowercaseLetter:
                    case UnicodeCategory.UppercaseLetter:
                        Push(c);
                        if (length == MAX_WORD_LEN) return Flush();
                        break;

                    case UnicodeCategory.OtherLetter:
                        if (length>0) 
                        {
                            bufferIndex--;
                            return Flush();
                        }
                        Push(c);
                        return Flush();

                    default:
                        if (length>0) return Flush();
                        break;
                }
            }

        }
    }
}

Program.cs 的代码如下:

View Code
using System;
using System.Collections.Generic;
using System.Text;
using Lucene.Net.Analysis.Standard;
using Lucene.Net.Analysis;
using Lucene.Net.Index;
using Lucene.Net.Documents;
using System.IO;
using Lucene.Net.Analysis.Cn;
using Lucene.Net.Analysis.CJK;
//date:11-02-2007
//home page:http://www.cnblogs.com/xuanfeng
//author:peizunyou
namespace DearBruce.LuceneSimpleChineses.ConApp
{
    class TokenizerTest
    {
        static void Main(string[] args)
        {
            string testText = "我们是中国人; 我们 是 人;we are chiness; 172.16.34.172;youpeizun@126.com;#$*;85*34;58 69";
            Console.WriteLine("测试文字:"+testText);
            Console.WriteLine("测试StandardTokenizer的分词情况如下:");
            TestStandardTokenizer(testText);
            
            
            Console.WriteLine("测试CJKTokenizer的分词情况如下:");
            TestCJKTokenizer(testText);
            
            
            Console.WriteLine("测试ChinessTokenizer的分词情况如下:");
            TestChinessTokenizer(testText);
            
            
            Console.WriteLine("测试LowerCaseTokenizer的分词情况如下:");
            TestLowerCaseTokenizer(testText);
            
            
            Console.WriteLine("测试WhitespaceTokenizer的分词情况如下:");
            TestWhitespaceTokenizer(testText);
            Console.Read();
        }
        static  void TestStandardTokenizer(string text)
        {
            TextReader tr = new StringReader(text);

            StandardTokenizer st = new StandardTokenizer(tr);
         
            while (st.Next() != null)
            {

                Console.Write(st.token.ToString()+"/ ");
            }
            Console.WriteLine();
        }
        static void TestCJKTokenizer(string text)
        {
            TextReader tr = new StringReader(text);
            int end = 0;
            CJKAnalyzer cjkA = new CJKAnalyzer();
            TokenStream ts = cjkA.TokenStream(tr);
            while(end<text.Length)
            {
                Lucene.Net.Analysis.Token t = ts.Next();
                end = t.EndOffset();
                Console.Write(t.TermText()+"/ ");
            }
            Console.WriteLine();
        }
        static void TestChinessTokenizer(string text)
        {
            TextReader tr = new StringReader(text);
            ChineseTokenizer ct = new ChineseTokenizer(tr);
            int end = 0;
            Lucene.Net.Analysis.Token t;
            while(end<text.Length)
            {
                t = ct.Next();
                end = t.EndOffset();
                Console.Write(t.TermText()+"/ ");
            }
            Console.WriteLine();
        
        }
        
        static void TestLowerCaseTokenizer(string text)
        {
            TextReader tr = new StringReader(text);
            SimpleAnalyzer sA = new SimpleAnalyzer();
            //SimpleAnalyzer使用了LowerCaseTokenizer分词器
            TokenStream ts = sA.TokenStream(tr);
            Lucene.Net.Analysis.Token t;
            while((t=ts.Next())!=null)
            {
                Console.Write(t.TermText()+"/");
            }
            Console.WriteLine();
        }
        static void TestWhitespaceTokenizer(string text)
        {
            TextReader tr = new StringReader(text);
   
            WhitespaceAnalyzer sA = new WhitespaceAnalyzer();
            TokenStream ts = sA.TokenStream(tr);
            Lucene.Net.Analysis.Token t;
            while ((t = ts.Next()) != null)
            {
                Console.Write(t.TermText() + "/");
            }
            Console.WriteLine();
        }
    }
}

运行结果如下:

代码下载:下载

谢谢浏览!

转载于:https://www.cnblogs.com/Music/archive/2013/04/19/lucene-net-CJKAnalyzer-and-ChineseAnalyzer.html

评论将由博主筛选后显示,对所有人可见 | 还能输入1000个字符 “速评一下”
©️2020 CSDN 皮肤主题: 编程工作室 设计师:CSDN官方博客 返回首页