You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucenenet.apache.org by di...@apache.org on 2011/06/02 20:42:41 UTC
[Lucene.Net] svn commit: r1130719 [2/5] - in /incubator/lucene.net/trunk:
build/vs2010/contrib/ build/vs2010/test/ doc/contrib/Analyzers/
doc/contrib/FastVectorHighlighter/ doc/core/ src/core/
Modified: incubator/lucene.net/trunk/doc/contrib/Analyzers/Lucene.Net.Contrib.Analyzers.xml
URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/doc/contrib/Analyzers/Lucene.Net.Contrib.Analyzers.xml?rev=1130719&r1=1130718&r2=1130719&view=diff
==============================================================================
--- incubator/lucene.net/trunk/doc/contrib/Analyzers/Lucene.Net.Contrib.Analyzers.xml (original)
+++ incubator/lucene.net/trunk/doc/contrib/Analyzers/Lucene.Net.Contrib.Analyzers.xml Thu Jun 2 18:42:41 2011
@@ -4,232 +4,219 @@
<name>Lucene.Net.Contrib.Analyzers</name>
</assembly>
<members>
- <member name="T:Lucene.Net.Analysis.WordlistLoader">
- <summary>
- Loads a text file and adds every line as an entry to a Hashtable. Every line
- should contain only one word. If the file is not found or on any error, an
- empty table is returned.
- </summary>
+ <member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.BRAZILIAN_STOP_WORDS">
+ List of typical Brazilian stopwords.
</member>
- <member name="M:Lucene.Net.Analysis.WordlistLoader.GetWordtable(System.String,System.String)">
- <summary>
- Load words table from the file
- </summary>
- <param name="path">Path to the wordlist</param>
- <param name="wordfile">Name of the wordlist</param>
- <returns></returns>
+ <member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.stoptable">
+ Contains the stopwords used with the StopFilter.
</member>
- <member name="M:Lucene.Net.Analysis.WordlistLoader.GetWordtable(System.String)">
- <summary>
- Load words table from the file
- </summary>
- <param name="wordfile">Complete path to the wordlist</param>
- <returns></returns>
+ <member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.excltable">
+ Contains words that should be indexed but not stemmed.
</member>
- <member name="M:Lucene.Net.Analysis.WordlistLoader.GetWordtable(System.IO.FileInfo)">
- <summary>
- Load words table from the file
- </summary>
- <param name="wordfile">File containing the wordlist</param>
- <returns></returns>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor">
+ Builds an analyzer with the default stop words ({@link #BRAZILIAN_STOP_WORDS}).
</member>
- <member name="M:Lucene.Net.Analysis.WordlistLoader.GetWordtable(System.IO.TextReader)">
- <summary>
- Reads lines from a Reader and adds every line as an entry to a HashSet (omitting
- leading and trailing whitespace). Every line of the Reader should contain only
- one word. The words need to be in lowercase if you make use of an
- Analyzer which uses LowerCaseFilter (like StandardAnalyzer).
- </summary>
- <param name="reader">Reader containing the wordlist</param>
- <returns>A Hashtable with the reader's words</returns>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor(System.String[])">
+ Builds an analyzer with the given stop words.
</member>
- <member name="M:Lucene.Net.Analysis.WordlistLoader.MakeWordTable(System.String[],System.Int32)">
- <summary>
- Builds the wordlist table.
- </summary>
- <param name="words">Word that where read</param>
- <param name="length">Amount of words that where read into <tt>words</tt></param>
- <returns></returns>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor(System.Collections.Hashtable)">
+ Builds an analyzer with the given stop words.
</member>
- <member name="T:Lucene.Net.Analysis.Fr.FrenchAnalyzer">
- <summary>
- Analyzer for french language. Supports an external list of stopwords (words that
- will not be indexed at all) and an external list of exclusions (word that will
- not be stemmed, but indexed).
- A default set of stopwords is used unless an other list is specified, the
- exclusionlist is empty by default.
-
- <author>Patrick Talbot (based on Gerhard Schwarz work for German)</author>
- <version>$Id: FrenchAnalyzer.java,v 1.9 2004/10/17 11:41:40 dnaber Exp $</version>
- </summary>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor(System.IO.FileInfo)">
+ Builds an analyzer with the given stop words.
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchAnalyzer.FRENCH_STOP_WORDS">
- <summary>
- Extended list of typical french stopwords.
- </summary>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.SetStemExclusionTable(System.String[])">
+ Builds an exclusionlist from an array of Strings.
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchAnalyzer.stoptable">
- <summary>
- Contains the stopwords used with the StopFilter.
- </summary>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.SetStemExclusionTable(System.Collections.Hashtable)">
+ Builds an exclusionlist from a Hashtable.
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchAnalyzer.excltable">
- <summary>
- Contains words that should be indexed but not stemmed.
- </summary>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.SetStemExclusionTable(System.IO.FileInfo)">
+ Builds an exclusionlist from the words contained in the given file.
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.#ctor">
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.TokenStream(System.String,System.IO.TextReader)">
+ Creates a TokenStream which tokenizes all the text in the provided Reader.
+
+ @return A TokenStream build from a StandardTokenizer filtered with
+ StandardFilter, StopFilter, GermanStemFilter and LowerCaseFilter.
+ </member>
+ <member name="T:Lucene.Net.Analysis.AR.ArabicStemFilter">
+ A {@link TokenFilter} that applies {@link ArabicStemmer} to stem Arabic words..
+
+ </member>
+ <member name="T:Lucene.Net.Analysis.Ru.RussianAnalyzer">
<summary>
- Builds an analyzer.
+ Analyzer for Russian language. Supports an external list of stopwords (words that
+ will not be indexed at all).
+ A default set of stopwords is used unless an alternative list is specified.
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.#ctor(System.String[])">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianAnalyzer.RUSSIAN_STOP_WORDS">
<summary>
- Builds an analyzer with the given stop words.
+ List of typical Russian stopwords.
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.#ctor(System.Collections.Hashtable)">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianAnalyzer.stoptable">
<summary>
- Builds an analyzer with the given stop words.
+ Contains the stopwords used with the StopFilter.
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.#ctor(System.IO.FileInfo)">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianAnalyzer.charset">
<summary>
- Builds an analyzer with the given stop words.
+ Charset for Russian letters.
+ Represents encoding for 32 lowercase Russian letters.
+ Predefined charsets can be taken from RussianCharSets class
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.SetStemExclusionTable(System.String[])">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianAnalyzer.#ctor">
<summary>
- Builds an exclusionlist from an array of Strings.
+ Builds an analyzer.
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.SetStemExclusionTable(System.Collections.Hashtable)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianAnalyzer.#ctor(System.Char[])">
<summary>
- Builds an exclusionlist from a Hashtable.
+ Builds an analyzer.
</summary>
+ <param name="charset"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.SetStemExclusionTable(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianAnalyzer.#ctor(System.Char[],System.String[])">
<summary>
- Builds an exclusionlist from the words contained in the given file.
+ Builds an analyzer with the given stop words.
</summary>
+ <param name="charset"></param>
+ <param name="stopwords"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchAnalyzer.TokenStream(System.String,System.IO.TextReader)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianAnalyzer.MakeStopWords(System.Char[])">
<summary>
- Creates a TokenStream which tokenizes all the text in the provided Reader.
+ Takes russian stop words and translates them to a String array, using
+ the given charset
</summary>
- <returns>
- A TokenStream build from a StandardTokenizer filtered with
- StandardFilter, StopFilter, FrenchStemFilter and LowerCaseFilter
- </returns>
+ <param name="charset"></param>
+ <returns></returns>
</member>
- <member name="T:Lucene.Net.Analysis.Cz.CzechAnalyzer">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianAnalyzer.#ctor(System.Char[],System.Collections.Hashtable)">
<summary>
- Analyzer for Czech language. Supports an external list of stopwords (words that
- will not be indexed at all).
- A default set of stopwords is used unless an alternative list is specified, the
- exclusion list is empty by default.
-
- <author>Lukas Zapletal [lzap@root.cz]</author>
- <version>$Id: CzechAnalyzer.java,v 1.2 2003/01/22 20:54:47 ehatcher Exp $</version>
+ Builds an analyzer with the given stop words.
</summary>
+ <param name="charset"></param>
+ <param name="stopwords"></param>
</member>
- <member name="F:Lucene.Net.Analysis.Cz.CzechAnalyzer.STOP_WORDS">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianAnalyzer.TokenStream(System.String,System.IO.TextReader)">
<summary>
- List of typical stopwords.
+ Creates a TokenStream which tokenizes all the text in the provided TextReader.
</summary>
+ <param name="fieldName"></param>
+ <param name="reader"></param>
+ <returns>
+ A TokenStream build from a RussianLetterTokenizer filtered with
+ RussianLowerCaseFilter, StopFilter, and RussianStemFilter
+ </returns>
</member>
- <member name="F:Lucene.Net.Analysis.Cz.CzechAnalyzer.stoptable">
+ <member name="T:Lucene.Net.Analysis.De.GermanStemFilter">
<summary>
- Contains the stopwords used with the StopFilter.
+ A filter that stems German words. It supports a table of words that should
+ not be stemmed at all. The stemmer used can be changed at runtime after the
+ filter object is created (as long as it is a GermanStemmer).
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Cz.CzechAnalyzer.#ctor">
+ <member name="F:Lucene.Net.Analysis.De.GermanStemFilter.token">
<summary>
- Builds an analyzer.
+ The actual token in the input stream.
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Cz.CzechAnalyzer.#ctor(System.String[])">
+ <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Collections.Hashtable)">
<summary>
- Builds an analyzer with the given stop words.
+ Builds a GermanStemFilter that uses an exclusiontable.
</summary>
+ <param name="_in"></param>
+ <param name="exclusiontable"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Cz.CzechAnalyzer.#ctor(System.Collections.Hashtable)">
+ <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.Next">
<summary>
- Builds an analyzer with the given stop words.
</summary>
+ <returns>Returns the next token in the stream, or null at EOS</returns>
</member>
- <member name="M:Lucene.Net.Analysis.Cz.CzechAnalyzer.#ctor(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.SetStemmer(Lucene.Net.Analysis.De.GermanStemmer)">
<summary>
- Builds an analyzer with the given stop words.
+ Set a alternative/custom GermanStemmer for this filter.
</summary>
+ <param name="stemmer"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Cz.CzechAnalyzer.LoadStopWords(System.IO.Stream,System.String)">
+ <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.SetExclusionTable(System.Collections.Hashtable)">
<summary>
- Loads stopwords hash from resource stream (file, database...).
+ Set an alternative exclusion list for this filter.
</summary>
- <param name="wordfile">File containing the wordlist</param>
- <param name="encoding">Encoding used (win-1250, iso-8859-2, ...}, null for default system encoding</param>
- </member>
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Cz.CzechAnalyzer.TokenStream(System.String,System.IO.TextReader)" -->
- <member name="F:Lucene.Net.Analysis.BR.BrazilianStemFilter.stemmer">
- The actual token in the input stream.
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemFilter.Next(Lucene.Net.Analysis.Token)">
- @return Returns the next token in the stream, or null at EOS.
+ <param name="exclusiontable"></param>
</member>
- <member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.BRAZILIAN_STOP_WORDS">
- List of typical Brazilian stopwords.
+ <!-- Badly formed XML comment ignored for member "T:Lucene.Net.Analysis.AR.ArabicAnalyzer" -->
+ <member name="F:Lucene.Net.Analysis.AR.ArabicAnalyzer.DEFAULT_STOPWORD_FILE">
+ File containing default Arabic stopwords.
+
+ Default stopword list is from http://members.unine.ch/jacques.savoy/clef/index.html
+ The stopword list is BSD-Licensed.
</member>
- <member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.stoptable">
+ <member name="F:Lucene.Net.Analysis.AR.ArabicAnalyzer.stoptable">
Contains the stopwords used with the StopFilter.
</member>
- <member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.excltable">
- Contains words that should be indexed but not stemmed.
+ <member name="F:Lucene.Net.Analysis.AR.ArabicAnalyzer.STOPWORDS_COMMENT">
+ The comment character in the stopwords file. All lines prefixed with this will be ignored
</member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor">
- Builds an analyzer with the default stop words ({@link #BRAZILIAN_STOP_WORDS}).
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor">
+ Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
+
+ @deprecated Use {@link #ArabicAnalyzer(Version)} instead
</member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor(System.String[])">
- Builds an analyzer with the given stop words.
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(Lucene.Net.Util.Version)">
+ Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
</member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor(System.Collections.Hashtable)">
- Builds an analyzer with the given stop words.
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(System.String[])">
+ Builds an analyzer with the given stop words.
+
+ @deprecated Use {@link #ArabicAnalyzer(Version, String[])} instead
</member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.#ctor(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(Lucene.Net.Util.Version,System.String[])">
Builds an analyzer with the given stop words.
</member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.SetStemExclusionTable(System.String[])">
- Builds an exclusionlist from an array of Strings.
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.SetStemExclusionTable(System.Collections.Hashtable)">
- Builds an exclusionlist from a Hashtable.
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(System.Collections.Hashtable)">
+ Builds an analyzer with the given stop words.
+
+ @deprecated Use {@link #ArabicAnalyzer(Version, Hashtable)} instead
</member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.SetStemExclusionTable(System.IO.FileInfo)">
- Builds an exclusionlist from the words contained in the given file.
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(Lucene.Net.Util.Version,System.Collections.Hashtable)">
+ Builds an analyzer with the given stop words.
</member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.TokenStream(System.String,System.IO.TextReader)">
- Creates a TokenStream which tokenizes all the text in the provided Reader.
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.TokenStream(System.String,System.IO.TextReader)">
+ Creates a {@link TokenStream} which tokenizes all the text in the provided {@link Reader}.
- @return A TokenStream build from a StandardTokenizer filtered with
- StandardFilter, StopFilter, GermanStemFilter and LowerCaseFilter.
+ @return A {@link TokenStream} built from an {@link ArabicLetterTokenizer} filtered with
+ {@link LowerCaseFilter}, {@link StopFilter}, {@link ArabicNormalizationFilter}
+ and {@link ArabicStemFilter}.
</member>
- <member name="T:Lucene.Net.Analysis.Cn.ChineseAnalyzer">
+ <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.ReusableTokenStream(System.String,System.IO.TextReader)">
+ Returns a (possibly reused) {@link TokenStream} which tokenizes all the text
+ in the provided {@link Reader}.
+
+ @return A {@link TokenStream} built from an {@link ArabicLetterTokenizer} filtered with
+ {@link LowerCaseFilter}, {@link StopFilter}, {@link ArabicNormalizationFilter}
+ and {@link ArabicStemFilter}.
+ </member>
+ <member name="T:Lucene.Net.Analysis.Cn.ChineseFilter">
<summary>
- Title: ChineseAnalyzer
- Description:
- Subclass of org.apache.lucene.analysis.Analyzer
- build from a ChineseTokenizer, filtered with ChineseFilter.
- Copyright: Copyright (c) 2001
+ 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</author>
- <version>$Id: ChineseAnalyzer.java, v 1.2 2003/01/22 20:54:47 ehatcher Exp $</version>
- </summary>
- </member>
- <member name="M:Lucene.Net.Analysis.Cn.ChineseAnalyzer.TokenStream(System.String,System.IO.TextReader)">
- <summary>
- Creates a TokenStream which tokenizes all the text in the provided Reader.
+ <version>$Id: ChineseFilter.java, v 1.4 2003/01/23 12:49:33 ehatcher Exp $</version>
</summary>
- <returns>A TokenStream build from a ChineseTokenizer filtered with ChineseFilter.</returns>
</member>
<member name="T:Lucene.Net.Analysis.Ru.RussianStemFilter">
<summary>
@@ -255,145 +242,248 @@
</summary>
<param name="stemmer"></param>
</member>
- <member name="T:Lucene.Net.Analysis.Fr.FrenchStemFilter">
+ <member name="T:Lucene.Net.Analysis.Nl.WordlistLoader">
<summary>
- A filter that stemms french words. It supports a table of words that should
- not be stemmed at all. The used stemmer can be changed at runtime after the
- filter object is created (as long as it is a FrenchStemmer).
+ Loads a text file and adds every line as an entry to a Hashtable. Every line
+ should contain only one word. If the file is not found or on any error, an
+ empty table is returned.
- <author>Patrick Talbot (based on Gerhard Schwarz work for German)</author>
- <version>$Id: FrenchAnalyzer.java,v 1.2 2004/01/23 20:54:47 ehatcher Exp $</version>
+ <version>$Id: WordListLoader.java,v 1.1 2004/03/09 14:55:08 otis Exp $</version>
</summary>
+ <author>Gerhard Schwarz</author>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemFilter.token">
+ <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetWordtable(System.String,System.String)">
+ <param name="path">Path to the wordlist</param>
+ <param name="wordfile">Name of the wordlist</param>
+ <returns></returns>
+ </member>
+ <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetWordtable(System.String)">
+ <param name="wordfile">Complete path to the wordlist</param>
+ </member>
+ <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetStemDict(System.IO.FileInfo)">
<summary>
- The actual token in the input stream.
+ Reads a stemsdictionary. Each line contains:
+ word \t stem
+ (i.e. tab seperated)
</summary>
+ <param name="wordstemfile"></param>
+ <returns>Stem dictionary that overrules, the stemming algorithm</returns>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Collections.Hashtable)">
+ <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetWordtable(System.IO.FileInfo)">
<summary>
- Builds a FrenchStemFilter that uses an exclusiontable.
+
</summary>
+ <param name="wordfile">File containing the wordlist</param>
+ <returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemFilter.Next">
+ <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.MakeWordTable(System.String[],System.Int32)">
<summary>
- Returns the next token in the stream, or null at EOS
+ Builds the wordlist table.
</summary>
- <returns>
- Returns the next token in the stream, or null at EOS
- </returns>
+ <param name="words">Word that where read</param>
+ <param name="length">Amount of words that where read into <tt>words</tt></param>
+ <returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemFilter.SetStemmer(Lucene.Net.Analysis.Fr.FrenchStemmer)">
+ <member name="T:Lucene.Net.Analysis.Cn.ChineseTokenizer">
<summary>
- Set a alternative/custom FrenchStemmer for this filter.
+ 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</author>
+ <version>$Id: ChineseTokenizer.java, v 1.4 2003/03/02 13:56:03 otis Exp $</version>
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemFilter.SetExclusionTable(System.Collections.Hashtable)">
+ <member name="T:Lucene.Net.Analysis.Cn.ChineseAnalyzer">
<summary>
- Set an alternative exclusion list for this filter.
+ Title: ChineseAnalyzer
+ Description:
+ Subclass of org.apache.lucene.analysis.Analyzer
+ build from a ChineseTokenizer, filtered with ChineseFilter.
+ Copyright: Copyright (c) 2001
+ Company:
+ <author>Yiyi Sun</author>
+ <version>$Id: ChineseAnalyzer.java, v 1.2 2003/01/22 20:54:47 ehatcher Exp $</version>
</summary>
</member>
- <member name="T:Lucene.Net.Analysis.De.WordlistLoader">
+ <member name="M:Lucene.Net.Analysis.Cn.ChineseAnalyzer.TokenStream(System.String,System.IO.TextReader)">
<summary>
- Loads a text file and adds every line as an entry to a Hashtable. Every line
- should contain only one word. If the file is not found or on any error, an
- empty table is returned.
+ Creates a TokenStream which tokenizes all the text in the provided Reader.
</summary>
+ <returns>A TokenStream build from a ChineseTokenizer filtered with ChineseFilter.</returns>
</member>
- <member name="M:Lucene.Net.Analysis.De.WordlistLoader.GetWordtable(System.String,System.String)">
+ <!-- Badly formed XML comment ignored for member "T:Lucene.Net.Analysis.CJK.CJKTokenizer" -->
+ <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.MAX_WORD_LEN">
<summary>
+ Max word length
</summary>
- <param name="path">Path to the wordlist</param>
- <param name="wordfile">Name of the wordlist</param>
- <returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.De.WordlistLoader.GetWordtable(System.String)">
+ <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.IO_BUFFER_SIZE">
<summary>
+ buffer size
</summary>
- <param name="wordfile">Complete path to the wordlist</param>
- <returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.De.WordlistLoader.GetWordtable(System.IO.FileInfo)">
+ <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.offset">
<summary>
-
+ word offset, used to imply which character(in ) is parsed
</summary>
- <param name="wordfile">File containing the wordlist</param>
- <returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.De.WordlistLoader.MakeWordTable(System.String[],System.Int32)">
+ <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.bufferIndex">
<summary>
- Builds the wordlist table.
+ the index used only for ioBuffer
</summary>
- <param name="words">Word that where read</param>
- <param name="length">Amount of words that where read into <tt>words</tt></param>
- <returns></returns>
</member>
- <member name="T:Lucene.Net.Analysis.De.GermanAnalyzer">
+ <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.dataLen">
<summary>
- Analyzer for German language. Supports an external list of stopwords (words that
- will not be indexed at all) and an external list of exclusions (word that will
- not be stemmed, but indexed).
+ data length
+ </summary>
+ </member>
+ <!-- Badly formed XML comment ignored for member "F:Lucene.Net.Analysis.CJK.CJKTokenizer.buffer" -->
+ <!-- Badly formed XML comment ignored for member "F:Lucene.Net.Analysis.CJK.CJKTokenizer.ioBuffer" -->
+ <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.tokenType">
+ <summary>
+ word type: single=>ASCII double=>non-ASCII word=>default
+ </summary>
+ </member>
+ <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.preIsTokened">
+ <summary>
+ 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"
+ </summary>
+ </member>
+ <member name="M:Lucene.Net.Analysis.CJK.CJKTokenizer.#ctor(System.IO.TextReader)">
+ <summary>
+ Construct a token stream processing the given input.
+ </summary>
+ <param name="_in">I/O reader</param>
+ </member>
+ <member name="M:Lucene.Net.Analysis.CJK.CJKTokenizer.Next">
+ <summary>
+ Returns the next token in the stream, or null at EOS.
+ </summary>
+ <returns>Token</returns>
+ </member>
+ <member name="F:Lucene.Net.Analysis.BR.BrazilianStemFilter.stemmer">
+ The actual token in the input stream.
+ </member>
+ <member name="M:Lucene.Net.Analysis.BR.BrazilianStemFilter.Next(Lucene.Net.Analysis.Token)">
+ @return Returns the next token in the stream, or null at EOS.
+ </member>
+ <!-- Badly formed XML comment ignored for member "T:Lucene.Net.Analysis.AR.ArabicNormalizer" -->
+ <member name="M:Lucene.Net.Analysis.AR.ArabicNormalizer.Normalize(System.Char[],System.Int32)">
+ Normalize an input buffer of Arabic text
+
+ @param s input buffer
+ @param len length of input buffer
+ @return length of input buffer after normalization
+ </member>
+ <member name="M:Lucene.Net.Analysis.AR.ArabicNormalizer.Delete(System.Char[],System.Int32,System.Int32)">
+ Delete a character in-place
+
+ @param s Input Buffer
+ @param pos Position of character to delete
+ @param len length of input buffer
+ @return length of input buffer after deletion
+ </member>
+ <member name="T:Lucene.Net.Analysis.Nl.DutchAnalyzer">
+ <summary>
+ Analyzer for Dutch language. Supports an external list of stopwords (words that
+ will not be indexed at all), an external list of exclusions (word that will
+ not be stemmed, but indexed) and an external list of word-stem pairs that overrule
+ the algorithm (dictionary stemming).
A default set of stopwords is used unless an alternative list is specified, the
exclusion list is empty by default.
+ As start for the Analyzer the German Analyzer was used. The stemming algorithm
+ implemented can be found at <c cref="!:"></c>
+
+ <version>$Id: DutchAnalyzer.java,v 1.1 2004/03/09 14:55:08 otis Exp $</version>
</summary>
+ <author>Edwin de Jonge</author>
</member>
- <member name="F:Lucene.Net.Analysis.De.GermanAnalyzer.GERMAN_STOP_WORDS">
+ <member name="F:Lucene.Net.Analysis.Nl.DutchAnalyzer.DUTCH_STOP_WORDS">
<summary>
List of typical german stopwords.
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.De.GermanAnalyzer.stoptable">
+ <member name="F:Lucene.Net.Analysis.Nl.DutchAnalyzer.stoptable">
<summary>
Contains the stopwords used with the StopFilter.
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.De.GermanAnalyzer.excltable">
+ <member name="F:Lucene.Net.Analysis.Nl.DutchAnalyzer.excltable">
<summary>
Contains words that should be indexed but not stemmed.
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor">
<summary>
Builds an analyzer.
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(System.String[])">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor(System.String[])">
<summary>
Builds an analyzer with the given stop words.
</summary>
<param name="stopwords"></param>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(System.Collections.Hashtable)">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor(System.Collections.Hashtable)">
<summary>
Builds an analyzer with the given stop words.
</summary>
<param name="stopwords"></param>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor(System.IO.FileInfo)">
<summary>
Builds an analyzer with the given stop words.
</summary>
<param name="stopwords"></param>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.SetStemExclusionTable(System.String[])">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemExclusionTable(System.String[])">
<summary>
Builds an exclusionlist from an array of Strings.
</summary>
<param name="exclusionlist"></param>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.SetStemExclusionTable(System.Collections.Hashtable)">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemExclusionTable(System.Collections.Hashtable)">
<summary>
Builds an exclusionlist from a Hashtable.
</summary>
<param name="exclusionlist"></param>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.SetStemExclusionTable(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemExclusionTable(System.IO.FileInfo)">
<summary>
Builds an exclusionlist from the words contained in the given file.
</summary>
<param name="exclusionlist"></param>
</member>
- <member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.TokenStream(System.String,System.IO.TextReader)">
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemDictionary(System.IO.FileInfo)">
+ <summary>
+ Reads a stemdictionary file , that overrules the stemming algorithm
+ This is a textfile that contains per line
+ word\tstem
+ i.e: tabseperated
+ </summary>
+ <param name="stemdict"></param>
+ </member>
+ <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.TokenStream(System.String,System.IO.TextReader)">
<summary>
Creates a TokenStream which tokenizes all the text in the provided TextReader.
</summary>
@@ -401,615 +491,367 @@
<param name="reader"></param>
<returns>A TokenStream build from a StandardTokenizer filtered with StandardFilter, StopFilter, GermanStemFilter</returns>
</member>
- <member name="T:Lucene.Net.Analysis.Cn.ChineseFilter">
+ <member name="T:Lucene.Net.Analysis.AR.ArabicNormalizationFilter">
+ A {@link TokenFilter} that applies {@link ArabicNormalizer} to normalize the orthography.
+
+ </member>
+ <member name="T:Lucene.Net.Analysis.Fr.FrenchStemmer">
<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
+ A stemmer for French words. The algorithm is based on the work of
+ Dr Martin Porter on his snowball project<br/>
+ refer to http://snowball.sourceforge.net/french/stemmer.html<br/>
+ (French stemming algorithm) for details
- Copyright: Copyright (c) 2001
- Company:
- <author>Yiyi Sun</author>
- <version>$Id: ChineseFilter.java, v 1.4 2003/01/23 12:49:33 ehatcher Exp $</version>
+ <author>Patrick Talbot (based on Gerhard Schwarz work for German)</author>
+ <version>$Id: FrenchStemmer.java,v 1.2 2004/01/22 20:54:47 ehatcher Exp $</version>
</summary>
</member>
- <member name="T:Lucene.Net.Analysis.Ru.RussianCharsets">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.sb">
<summary>
- RussianCharsets class contains encodings schemes (charsets) and ToLowerCase() method implementation
- for russian characters in Unicode, KOI8 and CP1252.
- Each encoding scheme contains lowercase (positions 0-31) and uppercase (position 32-63) characters.
- One should be able to add other encoding schemes (like ISO-8859-5 or customized) by adding a new charset
- and adding logic to ToLowerCase() method for that charset.
+ Buffer for the terms while stemming them.
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.Ru.RussianCharsets.UnicodeRussian">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.tb">
<summary>
- Unicode Russian charset (lowercase letters only)
+ A temporary buffer, used to reconstruct R2
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.Ru.RussianCharsets.KOI8">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.R0">
<summary>
- KOI8 charset
+ Region R0 is equal to the whole buffer
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.Ru.RussianCharsets.CP1251">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.RV">
<summary>
- CP1251 Charset
+ Region RV
+ "If the word begins with two vowels, RV is the region after the third letter,
+ otherwise the region after the first vowel not at the beginning of the word,
+ or the end of the word if these positions cannot be found."
</summary>
</member>
- <!-- Badly formed XML comment ignored for member "T:Lucene.Net.Analysis.CJK.CJKTokenizer" -->
- <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.MAX_WORD_LEN">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.R1">
<summary>
- Max word length
+ Region R1
+ "R1 is the region after the first non-vowel following a vowel
+ or is the null region at the end of the word if there is no such non-vowel"
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.IO_BUFFER_SIZE">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.R2">
<summary>
- buffer size
+ Region R2
+ "R2 is the region after the first non-vowel in R1 following a vowel
+ or is the null region at the end of the word if there is no such non-vowel"
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.offset">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.suite">
<summary>
- word offset, used to imply which character(in ) is parsed
+ Set to true if we need to perform step 2
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.bufferIndex">
+ <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.modified">
<summary>
- the index used only for ioBuffer
+ Set to true if the buffer was modified
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.dataLen">
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.Stem(System.String)">
<summary>
- data length
+ Stemms the given term to a unique <tt>discriminator</tt>.
</summary>
+ <param name="term">
+ java.langString The term that should be stemmed
+ </param>
+ <returns>
+ Discriminator for <tt>term</tt>
+ </returns>
</member>
- <!-- Badly formed XML comment ignored for member "F:Lucene.Net.Analysis.CJK.CJKTokenizer.buffer" -->
- <!-- Badly formed XML comment ignored for member "F:Lucene.Net.Analysis.CJK.CJKTokenizer.ioBuffer" -->
- <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.tokenType">
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.SetStrings" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step1" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step2a" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step2b" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step3" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step4" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step5" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step6" -->
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteFromIfPrecededIn(System.String,System.String[],System.String,System.String)">
<summary>
- word type: single=>ASCII double=>non-ASCII word=>default
+ Delete a suffix searched in zone "source" if zone "from" contains prefix + search string
</summary>
+ <param name="source">the primary source zone for search</param>
+ <param name="search">the strings to search for suppression</param>
+ <param name="from">the secondary source zone for search</param>
+ <param name="prefix">the prefix to add to the search string to test</param>
+ <returns>true if modified</returns>
</member>
- <member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.preIsTokened">
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteFromIfTestVowelBeforeIn(System.String,System.String[],System.Boolean,System.String)">
<summary>
- 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"
+ Delete a suffix searched in zone "source" if the preceding letter is (or isn't) a vowel
</summary>
+ <param name="source">the primary source zone for search</param>
+ <param name="search">the strings to search for suppression</param>
+ <param name="vowel">true if we need a vowel before the search string</param>
+ <param name="from">the secondary source zone for search (where vowel could be)</param>
+ <returns>true if modified</returns>
</member>
- <member name="M:Lucene.Net.Analysis.CJK.CJKTokenizer.#ctor(System.IO.TextReader)">
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteButSuffixFrom(System.String,System.String[],System.String,System.Boolean)">
<summary>
- Construct a token stream processing the given input.
+ Delete a suffix searched in zone "source" if preceded by the prefix
</summary>
- <param name="_in">I/O reader</param>
+ <param name="source">the primary source zone for search</param>
+ <param name="search">the strings to search for suppression</param>
+ <param name="prefix">the prefix to add to the search string to test</param>
+ <param name="without">true if it will be deleted even without prefix found</param>
</member>
- <member name="M:Lucene.Net.Analysis.CJK.CJKTokenizer.Next">
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteButSuffixFromElseReplace(System.String,System.String[],System.String,System.Boolean,System.String,System.String)" -->
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.ReplaceFrom(System.String,System.String[],System.String)">
<summary>
- Returns the next token in the stream, or null at EOS.
+ Replace a search string with another within the source zone
</summary>
- <returns>Token</returns>
- </member>
- <member name="T:Lucene.Net.Analysis.AR.ArabicLetterTokenizer">
- Tokenizer that breaks text into runs of letters and diacritics.
- <p>
- The problem with the standard Letter tokenizer is that it fails on diacritics.
- Handling similar to this is necessary for Indic Scripts, Hebrew, Thaana, etc.
- </p>
-
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicLetterTokenizer.IsTokenChar(System.Char)">
- Allows for Letter category or NonspacingMark category
- @see org.apache.lucene.analysis.LetterTokenizer#isTokenChar(char)
- </member>
- <!-- Badly formed XML comment ignored for member "T:Lucene.Net.Analysis.AR.ArabicAnalyzer" -->
- <member name="F:Lucene.Net.Analysis.AR.ArabicAnalyzer.DEFAULT_STOPWORD_FILE">
- File containing default Arabic stopwords.
-
- Default stopword list is from http://members.unine.ch/jacques.savoy/clef/index.html
- The stopword list is BSD-Licensed.
- </member>
- <member name="F:Lucene.Net.Analysis.AR.ArabicAnalyzer.stoptable">
- Contains the stopwords used with the StopFilter.
- </member>
- <member name="F:Lucene.Net.Analysis.AR.ArabicAnalyzer.STOPWORDS_COMMENT">
- The comment character in the stopwords file. All lines prefixed with this will be ignored
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor">
- Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
-
- @deprecated Use {@link #ArabicAnalyzer(Version)} instead
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(Lucene.Net.Util.Version)">
- Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(System.String[])">
- Builds an analyzer with the given stop words.
-
- @deprecated Use {@link #ArabicAnalyzer(Version, String[])} instead
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(Lucene.Net.Util.Version,System.String[])">
- Builds an analyzer with the given stop words.
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(System.Collections.Hashtable)">
- Builds an analyzer with the given stop words.
-
- @deprecated Use {@link #ArabicAnalyzer(Version, Hashtable)} instead
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(Lucene.Net.Util.Version,System.Collections.Hashtable)">
- Builds an analyzer with the given stop words.
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.TokenStream(System.String,System.IO.TextReader)">
- Creates a {@link TokenStream} which tokenizes all the text in the provided {@link Reader}.
-
- @return A {@link TokenStream} built from an {@link ArabicLetterTokenizer} filtered with
- {@link LowerCaseFilter}, {@link StopFilter}, {@link ArabicNormalizationFilter}
- and {@link ArabicStemFilter}.
- </member>
- <member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.ReusableTokenStream(System.String,System.IO.TextReader)">
- Returns a (possibly reused) {@link TokenStream} which tokenizes all the text
- in the provided {@link Reader}.
-
- @return A {@link TokenStream} built from an {@link ArabicLetterTokenizer} filtered with
- {@link LowerCaseFilter}, {@link StopFilter}, {@link ArabicNormalizationFilter}
- and {@link ArabicStemFilter}.
+ <param name="source">the source zone for search</param>
+ <param name="search">the strings to search for replacement</param>
+ <param name="replace">the replacement string</param>
+ <returns></returns>
</member>
- <member name="T:Lucene.Net.Analysis.Nl.DutchAnalyzer">
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteFrom(System.String,System.String[])">
<summary>
- Analyzer for Dutch language. Supports an external list of stopwords (words that
- will not be indexed at all), an external list of exclusions (word that will
- not be stemmed, but indexed) and an external list of word-stem pairs that overrule
- the algorithm (dictionary stemming).
- A default set of stopwords is used unless an alternative list is specified, the
- exclusion list is empty by default.
- As start for the Analyzer the German Analyzer was used. The stemming algorithm
- implemented can be found at <c cref="!:"></c>
-
- <version>$Id: DutchAnalyzer.java,v 1.1 2004/03/09 14:55:08 otis Exp $</version>
+ Delete a search string within the source zone
</summary>
- <author>Edwin de Jonge</author>
+ <param name="source">the source zone for search</param>
+ <param name="suffix">the strings to search for suppression</param>
</member>
- <member name="F:Lucene.Net.Analysis.Nl.DutchAnalyzer.DUTCH_STOP_WORDS">
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.IsVowel(System.Char)">
<summary>
- List of typical german stopwords.
+ Test if a char is a french vowel, including accentuated ones
</summary>
+ <param name="ch">the char to test</param>
+ <returns>true if the char is a vowel</returns>
</member>
- <member name="F:Lucene.Net.Analysis.Nl.DutchAnalyzer.stoptable">
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.RetrieveR(System.Text.StringBuilder)" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.RetrieveRV(System.Text.StringBuilder)" -->
+ <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.TreatVowels(System.Text.StringBuilder)" -->
+ <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.IsStemmable(System.String)">
<summary>
- Contains the stopwords used with the StopFilter.
+ Checks a term if it can be processed correctly.
</summary>
+ <returns>true if, and only if, the given term consists in letters.</returns>
</member>
- <member name="F:Lucene.Net.Analysis.Nl.DutchAnalyzer.excltable">
+ <member name="T:Lucene.Net.Analysis.Ru.RussianStemmer">
<summary>
- Contains words that should be indexed but not stemmed.
+ Russian stemming algorithm implementation (see http://snowball.sourceforge.net for detailed description).
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.RV">
<summary>
- Builds an analyzer.
+ positions of RV, R1 and R2 respectively
</summary>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor(System.String[])">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.R1">
<summary>
- Builds an analyzer with the given stop words.
+ positions of RV, R1 and R2 respectively
</summary>
- <param name="stopwords"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor(System.Collections.Hashtable)">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.R2">
<summary>
- Builds an analyzer with the given stop words.
+ positions of RV, R1 and R2 respectively
</summary>
- <param name="stopwords"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.#ctor(System.IO.FileInfo)">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.A">
<summary>
- Builds an analyzer with the given stop words.
+ letters
</summary>
- <param name="stopwords"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemExclusionTable(System.String[])">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.vowels">
<summary>
- Builds an exclusionlist from an array of Strings.
+ stem definitions
</summary>
- <param name="exclusionlist"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemExclusionTable(System.Collections.Hashtable)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.#ctor">
<summary>
- Builds an exclusionlist from a Hashtable.
+ RussianStemmer constructor comment.
</summary>
- <param name="exclusionlist"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemExclusionTable(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.#ctor(System.Char[])">
<summary>
- Builds an exclusionlist from the words contained in the given file.
+ RussianStemmer constructor comment.
</summary>
- <param name="exclusionlist"></param>
+ <param name="charset"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.SetStemDictionary(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Adjectival(System.Text.StringBuilder)">
<summary>
- Reads a stemdictionary file , that overrules the stemming algorithm
- This is a textfile that contains per line
- word\tstem
- i.e: tabseperated
- </summary>
- <param name="stemdict"></param>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchAnalyzer.TokenStream(System.String,System.IO.TextReader)">
- <summary>
- Creates a TokenStream which tokenizes all the text in the provided TextReader.
- </summary>
- <param name="fieldName"></param>
- <param name="reader"></param>
- <returns>A TokenStream build from a StandardTokenizer filtered with StandardFilter, StopFilter, GermanStemFilter</returns>
- </member>
- <member name="F:Lucene.Net.Analysis.BR.BrazilianStemmer.TERM">
- Changed term
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.Stem(System.String)">
- Stemms the given term to an unique <tt>discriminator</tt>.
-
- @param term The term that should be stemmed.
- @return Discriminator for <tt>term</tt>
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.isStemmable(System.String)">
- Checks a term if it can be processed correctly.
-
- @return true if, and only if, the given term consists in letters.
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.isIndexable(System.String)">
- Checks a term if it can be processed indexed.
-
- @return true if it can be indexed
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.isVowel(System.Char)">
- * See if string is 'a','e','i','o','u'
- *
- * @return true if is vowel
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.getR1(System.String)">
- * Gets R1
- *
- * R1 - is the region after the first non-vowel follwing a vowel,
- * or is the null region at the end of the word if there is
- * no such non-vowel.
- *
- * @return null or a string representing R1
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.getRV(System.String)">
- * Gets RV
- *
- * RV - IF the second letter is a consoant, RV is the region after
- * the next following vowel,
- *
- * OR if the first two letters are vowels, RV is the region
- * after the next consoant,
- *
- * AND otherwise (consoant-vowel case) RV is the region after
- * the third letter.
- *
- * BUT RV is the end of the word if this positions cannot be
- * found.
- *
- * @return null or a string representing RV
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.changeTerm(System.String)">
- 1) Turn to lowercase
- 2) Remove accents
- 3) ã -> a ; õ -> o
- 4) ç -> c
-
- @return null or a string transformed
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.suffix(System.String,System.String)">
- Check if a string ends with a suffix
-
- @return true if the string ends with the specified suffix
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.replaceSuffix(System.String,System.String,System.String)">
- Replace a string suffix by another
-
- @return the replaced string
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.removeSuffix(System.String,System.String)">
- Remove a string suffix
-
- @return the string without the suffix
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.suffixPreceded(System.String,System.String,System.String)">
- See if a suffix is preceded by a string
-
- @return true if the suffix is preceded
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.createCT(System.String)">
- Creates CT (changed term) , substituting * 'ã' and 'õ' for 'a~' and 'o~'.
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.step1">
- * Standart suffix removal.
- * Search for the longest among the following suffixes, and perform
- * the following actions:
- *
- * @return false if no ending was removed
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.step2">
- * Verb suffixes.
- *
- * Search for the longest among the following suffixes in RV,
- * and if found, delete.
- *
- * @return false if no ending was removed
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.step3">
- * Delete suffix 'i' if in RV and preceded by 'c'
- *
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.step4">
- * Residual suffix
- *
- * If the word ends with one of the suffixes (os a i o á à ó)
- * in RV, delete it
- *
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.step5">
- * If the word ends with one of ( e é ê) in RV,delete it,
- * and if preceded by 'gu' (or 'ci') with the 'u' (or 'i') in RV,
- * delete the 'u' (or 'i')
- *
- * Or if the word ends ç remove the cedilha
- *
- </member>
- <member name="M:Lucene.Net.Analysis.BR.BrazilianStemmer.Log">
- For log and debug purpose
-
- @return TERM, CT, RV, R1 and R2
- </member>
- <member name="T:Lucene.Net.Analysis.Nl.WordlistLoader">
- <summary>
- Loads a text file and adds every line as an entry to a Hashtable. Every line
- should contain only one word. If the file is not found or on any error, an
- empty table is returned.
-
- <version>$Id: WordListLoader.java,v 1.1 2004/03/09 14:55:08 otis Exp $</version>
+ Adjectival ending is an adjective ending,
+ optionally preceded by participle ending.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
- <author>Gerhard Schwarz</author>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetWordtable(System.String,System.String)">
- <param name="path">Path to the wordlist</param>
- <param name="wordfile">Name of the wordlist</param>
+ <param name="stemmingZone">StringBuilder</param>
<returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetWordtable(System.String)">
- <param name="wordfile">Complete path to the wordlist</param>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetStemDict(System.IO.FileInfo)">
- <summary>
- Reads a stemsdictionary. Each line contains:
- word \t stem
- (i.e. tab seperated)
- </summary>
- <param name="wordstemfile"></param>
- <returns>Stem dictionary that overrules, the stemming algorithm</returns>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.GetWordtable(System.IO.FileInfo)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Derivational(System.Text.StringBuilder)">
<summary>
-
+ Derivational endings
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
- <param name="wordfile">File containing the wordlist</param>
+ <param name="stemmingZone">StringBuilder</param>
<returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.Nl.WordlistLoader.MakeWordTable(System.String[],System.Int32)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.FindEnding(System.Text.StringBuilder,System.Int32,System.Char[][])">
<summary>
- Builds the wordlist table.
+ Finds ending among given ending class and returns the length of ending found(0, if not found).
+ Creation date: (17/03/2002 8:18:34 PM)
</summary>
- <param name="words">Word that where read</param>
- <param name="length">Amount of words that where read into <tt>words</tt></param>
+ <param name="stemmingZone"></param>
+ <param name="startIndex"></param>
+ <param name="theEndingClass"></param>
<returns></returns>
</member>
- <member name="T:Lucene.Net.Analysis.Nl.DutchStemFilter">
- <summary>
- A filter that stems Dutch words. It supports a table of words that should
- not be stemmed at all. The stemmer used can be changed at runtime after the
- filter object is created (as long as it is a DutchStemmer).
-
- <version>$Id: DutchStemFilter.java,v 1.1 2004/03/09 14:55:08 otis Exp $</version>
- </summary>
- <author>Edwin de Jonge</author>
- </member>
- <member name="F:Lucene.Net.Analysis.Nl.DutchStemFilter.token">
- <summary>
- The actual token in the input stream.
- </summary>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchStemFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Collections.Hashtable)">
- <summary>
- Builds a DutchStemFilter that uses an exclusiontable.
- </summary>
- <param name="_in"></param>
- <param name="exclusiontable"></param>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchStemFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Collections.Hashtable,System.Collections.Hashtable)">
- <summary>
-
- </summary>
- <param name="_in"></param>
- <param name="exclusiontable"></param>
- <param name="stemdictionary">Dictionary of word stem pairs, that overrule the algorithm</param>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchStemFilter.Next">
- <summary>
- </summary>
- <returns>Returns the next token in the stream, or null at EOS</returns>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchStemFilter.SetStemmer(Lucene.Net.Analysis.Nl.DutchStemmer)">
- <summary>
- Set a alternative/custom DutchStemmer for this filter.
- </summary>
- <param name="stemmer"></param>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchStemFilter.SetExclusionTable(System.Collections.Hashtable)">
- <summary>
- Set an alternative exclusion list for this filter.
- </summary>
- <param name="exclusiontable"></param>
- </member>
- <member name="M:Lucene.Net.Analysis.Nl.DutchStemFilter.SetStemDictionary(System.Collections.Hashtable)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.FindAndRemoveEnding(System.Text.StringBuilder,System.Char[][])">
<summary>
- Set dictionary for stemming, this dictionary overrules the algorithm,
- so you can correct for a particular unwanted word-stem pair.
+ Finds the ending among the given class of endings and removes it from stemming zone.
+ Creation date: (17/03/2002 8:18:34 PM)
</summary>
- <param name="dict"></param>
+ <param name="stemmingZone"></param>
+ <param name="theEndingClass"></param>
+ <returns></returns>
</member>
- <member name="T:Lucene.Net.Analysis.Fr.FrenchStemmer">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.FindAndRemoveEnding(System.Text.StringBuilder,System.Char[][],System.Char[][])">
<summary>
- A stemmer for French words. The algorithm is based on the work of
- Dr Martin Porter on his snowball project<br/>
- refer to http://snowball.sourceforge.net/french/stemmer.html<br/>
- (French stemming algorithm) for details
-
- <author>Patrick Talbot (based on Gerhard Schwarz work for German)</author>
- <version>$Id: FrenchStemmer.java,v 1.2 2004/01/22 20:54:47 ehatcher Exp $</version>
+ Finds the ending among the given class of endings, then checks if this ending was
+ preceded by any of given predessors, and if so, removes it from stemming zone.
+ Creation date: (17/03/2002 8:18:34 PM)
</summary>
+ <param name="stemmingZone"></param>
+ <param name="theEndingClass"></param>
+ <param name="thePredessors"></param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.sb">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.MarkPositions(System.String)">
<summary>
- Buffer for the terms while stemming them.
+ Marks positions of RV, R1 and R2 in a given word.
+ Creation date: (16/03/2002 3:40:11 PM)
</summary>
+ <param name="word"></param>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.tb">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.IsVowel(System.Char)">
<summary>
- A temporary buffer, used to reconstruct R2
+ Checks if character is a vowel..
+ Creation date: (16/03/2002 10:47:03 PM)
</summary>
+ <param name="letter"></param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.R0">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Noun(System.Text.StringBuilder)">
<summary>
- Region R0 is equal to the whole buffer
+ Noun endings.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.RV">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.PerfectiveGerund(System.Text.StringBuilder)">
<summary>
- Region RV
- "If the word begins with two vowels, RV is the region after the third letter,
- otherwise the region after the first vowel not at the beginning of the word,
- or the end of the word if these positions cannot be found."
+ Perfective gerund endings.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.R1">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Reflexive(System.Text.StringBuilder)">
<summary>
- Region R1
- "R1 is the region after the first non-vowel following a vowel
- or is the null region at the end of the word if there is no such non-vowel"
+ Reflexive endings.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.R2">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.RemoveI(System.Text.StringBuilder)">
<summary>
- Region R2
- "R2 is the region after the first non-vowel in R1 following a vowel
- or is the null region at the end of the word if there is no such non-vowel"
+ Insert the method's description here.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.suite">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.RemoveSoft(System.Text.StringBuilder)">
<summary>
- Set to true if we need to perform step 2
+ Insert the method's description here.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Fr.FrenchStemmer.modified">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.SetCharset(System.Char[])">
<summary>
- Set to true if the buffer was modified
+ Insert the method's description here.
+ Creation date: (16/03/2002 10:58:42 PM)
</summary>
+ <param name="newCharset"></param>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.Stem(System.String)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Stem(System.String)">
<summary>
- Stemms the given term to a unique <tt>discriminator</tt>.
+ Finds the stem for given Russian word.
+ Creation date: (16/03/2002 3:36:48 PM)
</summary>
- <param name="term">
- java.langString The term that should be stemmed
- </param>
- <returns>
- Discriminator for <tt>term</tt>
- </returns>
+ <param name="input"></param>
+ <returns></returns>
</member>
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.SetStrings" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step1" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step2a" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step2b" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step3" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step4" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step5" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.Step6" -->
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteFromIfPrecededIn(System.String,System.String[],System.String,System.String)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Superlative(System.Text.StringBuilder)">
<summary>
- Delete a suffix searched in zone "source" if zone "from" contains prefix + search string
+ Superlative endings.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
- <param name="source">the primary source zone for search</param>
- <param name="search">the strings to search for suppression</param>
- <param name="from">the secondary source zone for search</param>
- <param name="prefix">the prefix to add to the search string to test</param>
- <returns>true if modified</returns>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteFromIfTestVowelBeforeIn(System.String,System.String[],System.Boolean,System.String)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.UndoubleN(System.Text.StringBuilder)">
<summary>
- Delete a suffix searched in zone "source" if the preceding letter is (or isn't) a vowel
+ Undoubles N.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
- <param name="source">the primary source zone for search</param>
- <param name="search">the strings to search for suppression</param>
- <param name="vowel">true if we need a vowel before the search string</param>
- <param name="from">the secondary source zone for search (where vowel could be)</param>
- <returns>true if modified</returns>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteButSuffixFrom(System.String,System.String[],System.String,System.Boolean)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Verb(System.Text.StringBuilder)">
<summary>
- Delete a suffix searched in zone "source" if preceded by the prefix
+ Verb endings.
+ Creation date: (17/03/2002 12:14:58 AM)
</summary>
- <param name="source">the primary source zone for search</param>
- <param name="search">the strings to search for suppression</param>
- <param name="prefix">the prefix to add to the search string to test</param>
- <param name="without">true if it will be deleted even without prefix found</param>
+ <param name="stemmingZone"></param>
+ <returns></returns>
</member>
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteButSuffixFromElseReplace(System.String,System.String[],System.String,System.Boolean,System.String,System.String)" -->
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.ReplaceFrom(System.String,System.String[],System.String)">
+ <member name="M:Lucene.Net.Analysis.Ru.RussianStemmer.Stem(System.String,System.Char[])">
<summary>
- Replace a search string with another within the source zone
+ Static method for stemming with different charsets
</summary>
- <param name="source">the source zone for search</param>
- <param name="search">the strings to search for replacement</param>
- <param name="replace">the replacement string</param>
+ <param name="theWord"></param>
+ <param name="charset"></param>
<returns></returns>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.DeleteFrom(System.String,System.String[])">
+ <member name="T:Lucene.Net.Analysis.Ru.RussianLowerCaseFilter">
<summary>
- Delete a search string within the source zone
+ Normalizes token text to lower case, analyzing given ("russian") charset.
</summary>
- <param name="source">the source zone for search</param>
- <param name="suffix">the strings to search for suppression</param>
</member>
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.IsVowel(System.Char)">
+ <member name="T:Lucene.Net.Analysis.Ru.RussianCharsets">
<summary>
- Test if a char is a french vowel, including accentuated ones
+ RussianCharsets class contains encodings schemes (charsets) and ToLowerCase() method implementation
+ for russian characters in Unicode, KOI8 and CP1252.
+ Each encoding scheme contains lowercase (positions 0-31) and uppercase (position 32-63) characters.
+ One should be able to add other encoding schemes (like ISO-8859-5 or customized) by adding a new charset
+ and adding logic to ToLowerCase() method for that charset.
</summary>
- <param name="ch">the char to test</param>
- <returns>true if the char is a vowel</returns>
</member>
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.RetrieveR(System.Text.StringBuilder)" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.RetrieveRV(System.Text.StringBuilder)" -->
- <!-- Badly formed XML comment ignored for member "M:Lucene.Net.Analysis.Fr.FrenchStemmer.TreatVowels(System.Text.StringBuilder)" -->
- <member name="M:Lucene.Net.Analysis.Fr.FrenchStemmer.IsStemmable(System.String)">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianCharsets.UnicodeRussian">
<summary>
- Checks a term if it can be processed correctly.
+ Unicode Russian charset (lowercase letters only)
</summary>
- <returns>true if, and only if, the given term consists in letters.</returns>
</member>
- <member name="T:Lucene.Net.Analysis.Ru.RussianLowerCaseFilter">
+ <member name="F:Lucene.Net.Analysis.Ru.RussianCharsets.KOI8">
<summary>
- Normalizes token text to lower case, analyzing given ("russian") charset.
+ KOI8 charset
</summary>
</member>
- <member name="T:Lucene.Net.Analysis.AR.ArabicStemFilter">
- A {@link TokenFilter} that applies {@link ArabicStemmer} to stem Arabic words..
-
+ <member name="F:Lucene.Net.Analysis.Ru.RussianCharsets.CP1251">
+ <summary>
+ CP1251 Charset
+ </summary>
</member>
<member name="T:Lucene.Net.Analysis.Nl.DutchStemmer">
<summary>
@@ -1081,42 +923,6 @@
</summary>
<param name="buffer"></param>
</member>
- <member name="T:Lucene.Net.Analysis.De.GermanStemFilter">
- <summary>
- A filter that stems German words. It supports a table of words that should
- not be stemmed at all. The stemmer used can be changed at runtime after the
- filter object is created (as long as it is a GermanStemmer).
- </summary>
- </member>
- <member name="F:Lucene.Net.Analysis.De.GermanStemFilter.token">
- <summary>
- The actual token in the input stream.
- </summary>
- </member>
- <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Collections.Hashtable)">
- <summary>
- Builds a GermanStemFilter that uses an exclusiontable.
- </summary>
- <param name="_in"></param>
- <param name="exclusiontable"></param>
- </member>
- <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.Next">
- <summary>
- </summary>
- <returns>Returns the next token in the stream, or null at EOS</returns>
- </member>
- <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.SetStemmer(Lucene.Net.Analysis.De.GermanStemmer)">
- <summary>
- Set a alternative/custom GermanStemmer for this filter.
- </summary>
- <param name="stemmer"></param>
- </member>
- <member name="M:Lucene.Net.Analysis.De.GermanStemFilter.SetExclusionTable(System.Collections.Hashtable)">
- <summary>
- Set an alternative exclusion list for this filter.
- </summary>
- <param name="exclusiontable"></param>
- </member>
<!-- Badly formed XML comment ignored for member "T:Lucene.Net.Analysis.AR.ArabicStemmer" -->
<member name="M:Lucene.Net.Analysis.AR.ArabicStemmer.Stem(System.Char[],System.Int32)">
Stem an input buffer of Arabic text.
@@ -1168,430 +974,804 @@
@param len length of input buffer
@return length of input buffer after deletion
</member>
- <member name="T:Lucene.Net.Analysis.Ru.RussianStemmer">
+ <member name="T:Lucene.Net.Analysis.WordlistLoader">
<summary>
- Russian stemming algorithm implementation (see http://snowball.sourceforge.net for detailed description).
+ Loads a text file and adds every line as an entry to a Hashtable. Every line
+ should contain only one word. If the file is not found or on any error, an
+ empty table is returned.
</summary>
</member>
- <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.RV">
+ <member name="M:Lucene.Net.Analysis.WordlistLoader.GetWordtable(System.String,System.String)">
<summary>
- positions of RV, R1 and R2 respectively
+ Load words table from the file
</summary>
+ <param name="path">Path to the wordlist</param>
+ <param name="wordfile">Name of the wordlist</param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.R1">
+ <member name="M:Lucene.Net.Analysis.WordlistLoader.GetWordtable(System.String)">
<summary>
- positions of RV, R1 and R2 respectively
+ Load words table from the file
</summary>
+ <param name="wordfile">Complete path to the wordlist</param>
+ <returns></returns>
</member>
- <member name="F:Lucene.Net.Analysis.Ru.RussianStemmer.R2">
+ <member name="M:Lucene.Net.Analysis.WordlistLoader.GetWordtable(System.IO.FileInfo)">
<summary>
[... 1036 lines stripped ...]