[gentoo-commits] gentoo-x86 commit in net-mail/dovecot/files: SnowballFilter.h SnowballAnalyzer.h

[Eray Aslan (eras)]

eras        11/12/04 06:59:13

  Added:                SnowballFilter.h SnowballAnalyzer.h
  Log:
  Add v2.1_rc1 release - bug #392709
  
  (Portage version: 2.1.10.39/cvs/Linux x86_64)

Revision  Changes    Path
1.1                  net-mail/dovecot/files/SnowballFilter.h

file : http://sources.gentoo.org/viewvc.cgi/gentoo-x86/net-mail/dovecot/files/SnowballFilter.h?rev=1.1&view=markup
plain: http://sources.gentoo.org/viewvc.cgi/gentoo-x86/net-mail/dovecot/files/SnowballFilter.h?rev=1.1&content-type=text/plain

Index: SnowballFilter.h
===================================================================
/*------------------------------------------------------------------------------
* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
*
* Distributable under the terms of either the Apache License (Version 2.0) or
* the GNU Lesser General Public License, as specified in the COPYING file.
------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_snowball_filter_
#define _lucene_analysis_snowball_filter_

#include "CLucene/analysis/AnalysisHeader.h"
#include "libstemmer.h"

CL_NS_DEF2(analysis,snowball)

/** A filter that stems words using a Snowball-generated stemmer.
 *
 * Available stemmers are listed in {@link net.sf.snowball.ext}.  The name of a
 * stemmer is the part of the class name before "Stemmer", e.g., the stemmer in
 * {@link EnglishStemmer} is named "English".
 *
 * Note: todo: This is not thread safe...
 */
class CLUCENE_CONTRIBS_EXPORT SnowballFilter: public TokenFilter {
	struct sb_stemmer * stemmer;
public:

  /** Construct the named stemming filter.
   *
   * @param in the input tokens to stem
   * @param name the name of a stemmer
   */
	SnowballFilter(TokenStream* in, const char* language, bool deleteTS);

	~SnowballFilter();

    /** Returns the next input Token, after being stemmed */
    Token* next(Token* token);
};

CL_NS_END2
#endif



1.1                  net-mail/dovecot/files/SnowballAnalyzer.h

file : http://sources.gentoo.org/viewvc.cgi/gentoo-x86/net-mail/dovecot/files/SnowballAnalyzer.h?rev=1.1&view=markup
plain: http://sources.gentoo.org/viewvc.cgi/gentoo-x86/net-mail/dovecot/files/SnowballAnalyzer.h?rev=1.1&content-type=text/plain

Index: SnowballAnalyzer.h
===================================================================
/*------------------------------------------------------------------------------
* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
*
* Distributable under the terms of either the Apache License (Version 2.0) or
* the GNU Lesser General Public License, as specified in the COPYING file.
------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_snowball_analyser_
#define _lucene_analysis_snowball_analyser_

#include "CLucene/analysis/AnalysisHeader.h"

CL_CLASS_DEF(util,BufferedReader)
CL_NS_DEF2(analysis,snowball)

/** Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
 * LowerCaseFilter}, {@link StopFilter} and {@link SnowballFilter}.
 *
 * Available stemmers are listed in {@link net.sf.snowball.ext}.  The name of a
 * stemmer is the part of the class name before "Stemmer", e.g., the stemmer in
 * {@link EnglishStemmer} is named "English".
 */
class CLUCENE_CONTRIBS_EXPORT SnowballAnalyzer: public Analyzer {
  char* language;
  CLTCSetList* stopSet;
  TokenStream *prevstream;

public:
  /** Builds the named analyzer with no stop words. */
  SnowballAnalyzer(const char* language="english");

  /** Builds the named analyzer with the given stop words.
  */
  SnowballAnalyzer(const char* language, const TCHAR** stopWords);

  ~SnowballAnalyzer();

  /** Constructs a {@link StandardTokenizer} filtered by a {@link
      StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. */
  TokenStream* tokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader);
  TokenStream* tokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader, bool deleteReader);
  TokenStream* reusableTokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader);
};

CL_NS_END2
#endif