Apache-Lucene.Net-3.0.3-RC2.bin/NET40/doc/Contrib/Lucene.Net.Contrib.Analyzers.XML
<?xml version="1.0"?>
<doc>
<assembly>
<name>Lucene.Net.Contrib.Analyzers</name>
</assembly>
<members>
<member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.GetDefaultStopSet">
<summary>
Returns an unmodifiable instance of the default stop-words set
</summary>
<returns>Returns an unmodifiable instance of the default stop-words set</returns>
</member>
<member name="M:Lucene.Net.Analysis.AR.ArabicAnalyzer.#ctor(Lucene.Net.Util.Version,System.Collections.Generic.ISet{System.String})">
<summary>
Builds an analyzer with the given stop words.
</summary>
<param name="matchVersion">Lucene compatibility version</param>
<param name="stopwords">a stopword set</param>
</member>
<member name="M:Lucene.Net.Analysis.BR.BrazilianAnalyzer.GetDefaultStopSet">
<summary>
Returns an unmodifiable instance of the default stop-words set.
</summary>
<returns>Returns an unmodifiable instance of the default stop-words set.</returns>
</member>
<member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.stoptable">
<summary>
Contains the stopwords used with the StopFilter.
</summary>
</member>
<member name="F:Lucene.Net.Analysis.BR.BrazilianAnalyzer.excltable">
<summary>
Contains words that should be indexed but not stemmed.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.CJK.CJKAnalyzer">
<summary>
Filters CJKTokenizer with StopFilter.
<author>Che, Dong</author>
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKAnalyzer.STOP_WORDS">
<summary>
An array containing some common English words that are not usually
useful for searching. and some double-byte interpunctions.....
</summary>
</member>
<member name="M:Lucene.Net.Analysis.CJK.CJKAnalyzer.GetDefaultStopSet">
<summary>
Returns an unmodifiable instance of the default stop-words set.
</summary>
<returns>Returns an unmodifiable instance of the default stop-words set.</returns>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKAnalyzer.stopTable">
<summary>
stop word list
</summary>
</member>
<member name="M:Lucene.Net.Analysis.CJK.CJKAnalyzer.#ctor(Lucene.Net.Util.Version,System.String[])">
<summary>
Builds an analyzer which removes words in the provided array.
</summary>
<param name="stopWords">stop word array</param>
</member>
<member name="M:Lucene.Net.Analysis.CJK.CJKAnalyzer.TokenStream(System.String,System.IO.TextReader)">
<summary>
get token stream from input
</summary>
<param name="fieldName">lucene field name</param>
<param name="reader">input reader</param>
<returns>Token Stream</returns>
</member>
<member name="T:Lucene.Net.Analysis.CJK.CJKTokenizer">
<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
chars: 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>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.WORD_TYPE">
<summary>
Word token type
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.SINGLE_TOKEN_TYPE">
<summary>
Single byte token type
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.DOUBLE_TOKEN_TYPE">
<summary>
Double byte token type
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.TOKEN_TYPE_NAMES">
<summary>
Names for token types
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.MAX_WORD_LEN">
<summary>
Max word length
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.IO_BUFFER_SIZE">
<summary>
buffer size
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.offset">
<summary>
word offset, used to imply which character(in ) is parsed
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.bufferIndex">
<summary>
the index used only for ioBuffer
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.dataLen">
<summary>
data length
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.buffer">
<summary>
character buffer, store the characters which are used to compose <br/>
the returned Token
</summary>
</member>
<member name="F:Lucene.Net.Analysis.CJK.CJKTokenizer.ioBuffer">
<summary>
I/O buffer, used to store the content of the input(one of the <br/>
members of Tokenizer)
</summary>
</member>
<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="T:Lucene.Net.Analysis.Cn.ChineseAnalyzer">
<summary>
An <see cref="T:Lucene.Net.Analysis.Analyzer"/> that tokenizes text with <see cref="T:Lucene.Net.Analysis.Cn.ChineseTokenizer"/> and
filters with <see cref="T:Lucene.Net.Analysis.Cn.ChineseFilter"/>
</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.
</summary>
<returns>A TokenStream build from a ChineseTokenizer filtered with ChineseFilter.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Cn.ChineseAnalyzer.ReusableTokenStream(System.String,System.IO.TextReader)">
<summary>
Returns a (possibly reused) <see cref="M:Lucene.Net.Analysis.Cn.ChineseAnalyzer.TokenStream(System.String,System.IO.TextReader)"/> which tokenizes all the text in the
provided <see cref="T:System.IO.TextReader"/>.
</summary>
<returns>
A <see cref="M:Lucene.Net.Analysis.Cn.ChineseAnalyzer.TokenStream(System.String,System.IO.TextReader)"/> built from a <see cref="T:Lucene.Net.Analysis.Cn.ChineseTokenizer"/>
filtered with <see cref="T:Lucene.Net.Analysis.Cn.ChineseFilter"/>.
</returns>
</member>
<member name="T:Lucene.Net.Analysis.Cn.ChineseFilter">
<summary>
A {@link TokenFilter} with a stop word table.
<ul>
<li>Numeric tokens are removed.</li>
<li>English tokens must be larger than 1 char.</li>
<li>One Chinese char as one Chinese word.</li>
</ul>
TO DO:
<ol>
<li>Add Chinese stop words, such as \ue400</li>
<li>Dictionary based Chinese word extraction</li>
<li>Intelligent Chinese word extraction</li>
</ol>
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Cn.ChineseTokenizer">
<summary>
Tokenize Chinese text as individual chinese chars.
<p>
The difference between ChineseTokenizer and
CJKTokenizer is that they have different
token parsing logic.
</p>
<p>
For example, if the Chinese text
"C1C2C3C4" is to be indexed:
<ul>
<li>The tokens returned from ChineseTokenizer are C1, C2, C3, C4</li>
<li>The tokens returned from the CJKTokenizer are C1C2, C2C3, C3C4.</li>
</ul>
</p>
<p>
Therefore the index created by CJKTokenizer is much larger.
</p>
<p>
The problem is that when searching for C1, C1C2, C1C3,
C4C2, C1C2C3 ... the ChineseTokenizer works, but the
CJKTokenizer will not work.
</p>
</summary>
</member>
<member name="T:Lucene.Net.Analysis.De.GermanAnalyzer">
<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).
A default set of stopwords is used unless an alternative list is specified, the
exclusion list is empty by default.
</summary>
</member>
<member name="F:Lucene.Net.Analysis.De.GermanAnalyzer.GERMAN_STOP_WORDS">
<summary>
List of typical german stopwords.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.GetDefaultStopSet">
<summary>
Returns a set of default German-stopwords
</summary>
</member>
<member name="F:Lucene.Net.Analysis.De.GermanAnalyzer.stopSet">
<summary>
Contains the stopwords used with the StopFilter.
</summary>
</member>
<member name="F:Lucene.Net.Analysis.De.GermanAnalyzer.exclusionSet">
<summary>
Contains words that should be indexed but not stemmed.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor">
<summary>
Builds an analyzer with the default stop words:
<see cref="M:Lucene.Net.Analysis.De.GermanAnalyzer.GetDefaultStopSet"/>
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version)">
<summary>
Builds an analyzer with the default stop words:
<see cref="M:Lucene.Net.Analysis.De.GermanAnalyzer.GetDefaultStopSet"/>
</summary>
<param name="matchVersion">Lucene compatibility version</param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version,System.Boolean)">
<summary>
Builds an analyzer with the default stop words:
<see cref="M:Lucene.Net.Analysis.De.GermanAnalyzer.GetDefaultStopSet"/>
</summary>
<param name="matchVersion">Lucene compatibility version</param>
<param name="normalizeDin2">Specifies if the DIN-2007-2 style stemmer should be used in addition to DIN1. This
will cause words with 'ae', 'ue', or 'oe' in them (expanded umlauts) to be first converted to 'a', 'u', and 'o'
respectively, before the DIN1 stemmer is invoked.</param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version,System.Collections.Generic.ISet{System.String})">
<summary>
Builds an analyzer with the given stop words, using the default DIN-5007-1 stemmer
</summary>
<param name="matchVersion">Lucene compatibility version</param>
<param name="stopwords">a stopword set</param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version,System.Collections.Generic.ISet{System.String},System.Boolean)">
<summary>
Builds an analyzer with the given stop words
</summary>
<param name="matchVersion">Lucene compatibility version</param>
<param name="stopwords">a stopword set</param>
<param name="normalizeDin2">Specifies if the DIN-2007-2 style stemmer should be used in addition to DIN1. This
will cause words with 'ae', 'ue', or 'oe' in them (expanded umlauts) to be first converted to 'a', 'u', and 'o'
respectively, before the DIN1 stemmer is invoked.</param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version,System.Collections.Generic.ISet{System.String},System.Collections.Generic.ISet{System.String})">
<summary>
Builds an analyzer with the given stop words, using the default DIN-5007-1 stemmer
</summary>
<param name="matchVersion">lucene compatibility version</param>
<param name="stopwords">a stopword set</param>
<param name="stemExclusionSet">a stemming exclusion set</param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version,System.Collections.Generic.ISet{System.String},System.Collections.Generic.ISet{System.String},System.Boolean)">
<summary>
Builds an analyzer with the given stop words
</summary>
<param name="matchVersion">lucene compatibility version</param>
<param name="stopwords">a stopword set</param>
<param name="stemExclusionSet">a stemming exclusion set</param>
<param name="normalizeDin2">Specifies if the DIN-2007-2 style stemmer should be used in addition to DIN1. This
will cause words with 'ae', 'ue', or 'oe' in them (expanded umlauts) to be first converted to 'a', 'u', and 'o'
respectively, before the DIN1 stemmer is invoked.</param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version,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(Lucene.Net.Util.Version,System.Collections.Generic.IDictionary{System.String,System.String})">
<summary>
Builds an analyzer with the given stop words.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.#ctor(Lucene.Net.Util.Version,System.IO.FileInfo)">
<summary>
Builds an analyzer with the given stop words.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.SetStemExclusionTable(System.String[])">
<summary>
Builds an exclusionlist from an array of Strings.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.SetStemExclusionTable(System.Collections.Generic.IDictionary{System.String,System.String})">
<summary>
Builds an exclusionlist from a IDictionary.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.SetStemExclusionTable(System.IO.FileInfo)">
<summary>
Builds an exclusionlist from the words contained in the given file.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanAnalyzer.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="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.stemmer">
<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.Generic.ISet{System.String})">
<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.#ctor(Lucene.Net.Analysis.TokenStream,System.Collections.Generic.ISet{System.String},System.Boolean)">
<summary>
Builds a GermanStemFilter that uses an exclusiontable.
</summary>
<param name="_in"></param>
<param name="exclusiontable"></param>
<param name="normalizeDin2">Specifies if the DIN-2007-2 style stemmer should be used in addition to DIN1. This
will cause words with 'ae', 'ue', or 'oe' in them (expanded umlauts) to be first converted to 'a', 'u', and 'o'
respectively, before the DIN1 stemmer is invoked.</param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemFilter.IncrementToken">
<returns>
Returns true for next token in the stream, or false 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.Generic.ISet{System.String})">
<summary>
Set an alternative exclusion list for this filter.
</summary>
<param name="exclusiontable"></param>
</member>
<member name="T:Lucene.Net.Analysis.De.GermanStemmer">
<summary>
A stemmer for German words. The algorithm is based on the report
"A Fast and Simple Stemming Algorithm for German Words" by Jörg
Caumanns (joerg.caumanns@isst.fhg.de).
</summary>
</member>
<member name="F:Lucene.Net.Analysis.De.GermanStemmer.sb">
<summary>
Buffer for the terms while stemming them.
</summary>
</member>
<member name="F:Lucene.Net.Analysis.De.GermanStemmer.substCount">
<summary>
Amount of characters that are removed with <tt>Substitute()</tt> while stemming.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemmer.Stem(System.String)">
<summary>
Stemms the given term to an unique <tt>discriminator</tt>.
</summary>
<param name="term">The term that should be stemmed.</param>
<returns>Discriminator for <tt>term</tt></returns>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemmer.IsStemmable(System.String)">
<summary>
Checks if a term could be stemmed.
</summary>
<param name="term"></param>
<returns>true if, and only if, the given term consists in letters.</returns>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemmer.Strip(System.Text.StringBuilder)">
<summary>
Suffix stripping (stemming) on the current term. The stripping is reduced
to the seven "base" suffixes "e", "s", "n", "t", "em", "er" and * "nd",
from which all regular suffixes are build of. The simplification causes
some overstemming, and way more irregular stems, but still provides unique.
discriminators in the most of those cases.
The algorithm is context free, except of the length restrictions.
</summary>
<param name="buffer"></param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemmer.Optimize(System.Text.StringBuilder)">
<summary>
Does some optimizations on the term. This optimisations are contextual.
</summary>
<param name="buffer"></param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemmer.RemoveParticleDenotion(System.Text.StringBuilder)">
<summary>
Removes a particle denotion ("ge") from a term.
</summary>
<param name="buffer"></param>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemmer.Substitute(System.Text.StringBuilder)">
<summary>
Do some substitutions for the term to reduce overstemming:
- Substitute Umlauts with their corresponding vowel: äöü -> aou,
"ß" is substituted by "ss"
- Substitute a second char of a pair of equal characters with
an asterisk: ?? -> ?*
- Substitute some common character combinations with a token:
sch/ch/ei/ie/ig/st -> $/В§/%/&/#/!
</summary>
</member>
<member name="M:Lucene.Net.Analysis.De.GermanStemmer.Resubstitute(System.Text.StringBuilder)">
<summary>
Undoes the changes made by Substitute(). That are character pairs and
character combinations. Umlauts will remain as their corresponding vowel,
as "?" remains as "ss".
</summary>
<param name="buffer"></param>
</member>
<member name="T:Lucene.Net.Analysis.De.GermanDIN2Stemmer">
<summary>
A stemmer for the german language that uses the
DIN-5007-2 "Phone Book" rules for handling
umlaut characters.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Hunspell.HunspellAffix">
<summary>
Wrapper class representing a hunspell affix.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellAffix.CheckCondition(System.String)">
<summary>
Checks whether the String defined by the provided char array, offset
and length, meets the condition of this affix.
</summary>
<returns>
<c>true</c> if the String meets the condition, <c>false</c> otherwise.
</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellAffix.SetCondition(System.String,System.String)">
<summary>
Sets the condition that must be met before the affix can be applied.
</summary>
<param name="condition">Condition to be met before affix application.</param>
<param name="pattern">Condition as a regular expression pattern.</param>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellAffix.Append">
<summary>
The append defined for the affix.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellAffix.AppendFlags">
<summary>
The flags defined for the affix append.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellAffix.Condition">
<summary>
The condition that must be met before the affix can be applied.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellAffix.Flag">
<summary>
The affix flag.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellAffix.IsCrossProduct">
<summary>
Whether the affix is defined as cross product.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellAffix.Strip">
<summary>
The stripping characters defined for the affix.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.#ctor(System.IO.Stream,System.IO.Stream)">
<summary>
Creates a new HunspellDictionary containing the information read from the provided streams to hunspell affix and dictionary file.
</summary>
<param name="affix">Stream for reading the hunspell affix file.</param>
<param name="dictionary">Stream for reading the hunspell dictionary file.</param>
<exception cref="T:System.IO.IOException">Can be thrown while reading from the streams.</exception>
<exception cref="T:System.IO.InvalidDataException">Can be thrown if the content of the files does not meet expected formats.</exception>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.#ctor(System.IO.Stream,System.Collections.Generic.IEnumerable{System.IO.Stream})">
<summary>
Creates a new HunspellDictionary containing the information read from the provided streams to hunspell affix and dictionary files.
</summary>
<param name="affix">Stream for reading the hunspell affix file.</param>
<param name="dictionaries">Streams for reading the hunspell dictionary file.</param>
<exception cref="T:System.IO.IOException">Can be thrown while reading from the streams.</exception>
<exception cref="T:System.IO.InvalidDataException">Can be thrown if the content of the files does not meet expected formats.</exception>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.LookupWord(System.String)">
<summary>
Looks up HunspellWords that match the String created from the given char array, offset and length.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.LookupPrefix(System.Char[],System.Int32,System.Int32)">
<summary>
Looks up HunspellAffix prefixes that have an append that matches the String created from the given char array, offset and length.
</summary>
<param name="word">Char array to generate the String from.</param>
<param name="offset">Offset in the char array that the String starts at.</param>
<param name="length">Length from the offset that the String is.</param>
<returns>List of HunspellAffix prefixes with an append that matches the String, or <c>null</c> if none are found.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.LookupSuffix(System.Char[],System.Int32,System.Int32)">
<summary>
Looks up HunspellAffix suffixes that have an append that matches the String created from the given char array, offset and length.
</summary>
<param name="word">Char array to generate the String from.</param>
<param name="offset">Offset in the char array that the String starts at.</param>
<param name="length">Length from the offset that the String is.</param>
<returns>List of HunspellAffix suffixes with an append that matches the String, or <c>null</c> if none are found</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.ReadAffixFile(System.IO.Stream,System.Text.Encoding)">
<summary>
Reads the affix file through the provided Stream, building up the prefix and suffix maps.
</summary>
<param name="affixStream">Stream to read the content of the affix file from.</param>
<param name="encoding">Encoding to decode the content of the file.</param>
<exception cref="T:System.IO.IOException">IOException Can be thrown while reading from the Stream.</exception>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.ParseAliasFlag(System.String,System.IO.TextReader)">
<summary>
Parse alias flag and put it in hash
</summary>
<param name="line"></param>
<param name="reader"></param>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.ParseAffix(System.Collections.Generic.Dictionary{System.String,System.Collections.Generic.List{Lucene.Net.Analysis.Hunspell.HunspellAffix}},System.String,System.IO.TextReader,System.String)">
<summary>
Parses a specific affix rule putting the result into the provided affix map.
</summary>
<param name="affixes">Map where the result of the parsing will be put.</param>
<param name="header">Header line of the affix rule.</param>
<param name="reader">TextReader to read the content of the rule from.</param>
<param name="conditionPattern">Pattern to be used to generate the condition regex pattern.</param>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.ReadDictionaryEncoding(System.IO.Stream)">
<summary>
Parses the encoding specificed in the affix file readable through the provided Stream.
</summary>
<param name="affix">Stream for reading the affix file.</param>
<returns>Encoding specified in the affix file.</returns>
<exception cref="T:System.IO.InvalidDataException">
Thrown if the first non-empty non-comment line read from the file does not
adhere to the format <c>SET encoding</c>.
</exception>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.GetFlagParsingStrategy(System.String)">
<summary>
Determines the appropriate {@link FlagParsingStrategy} based on the FLAG definiton line taken from the affix file.
</summary>
<param name="flagLine">Line containing the flag information</param>
<returns>FlagParsingStrategy that handles parsing flags in the way specified in the FLAG definition.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.ReadDictionaryFile(System.IO.Stream,System.Text.Encoding)">
<summary>
Reads the dictionary file through the provided Stream, building up the words map.
</summary>
<param name="dictionary">Stream to read the dictionary file through.</param>
<param name="encoding">Encoding used to decode the contents of the file.</param>
<exception cref="T:System.IO.IOException">Can be thrown while reading from the file.</exception>
</member>
<member name="T:Lucene.Net.Analysis.Hunspell.HunspellDictionary.DoubleASCIIFlagParsingStrategy">
<summary>
Implementation of {@link FlagParsingStrategy} that assumes each flag is encoded as
two ASCII characters whose codes must be combined into a single character.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Hunspell.HunspellDictionary.FlagParsingStrategy">
<summary>
Abstraction of the process of parsing flags taken from the affix and dic files
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.FlagParsingStrategy.ParseFlag(System.String)">
<summary>
Parses the given String into a single flag.
</summary>
<param name="rawFlag">String to parse into a flag.</param>
<returns>Parsed flag.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellDictionary.FlagParsingStrategy.ParseFlags(System.String)">
<summary>
Parses the given String into multiple flag.
</summary>
<param name="rawFlags">String to parse into a flags.</param>
<returns>Parsed flags.</returns>
</member>
<member name="T:Lucene.Net.Analysis.Hunspell.HunspellDictionary.NumFlagParsingStrategy">
<summary>
Implementation of {@link FlagParsingStrategy} that assumes each flag is encoded in its
numerical form. In the case of multiple flags, each number is separated by a comma.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Hunspell.HunspellDictionary.SimpleFlagParsingStrategy">
<summary>
Simple implementation of {@link FlagParsingStrategy} that treats the chars in each
String as a individual flags. Can be used with both the ASCII and UTF-8 flag types.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStem.#ctor(System.String)">
<summary>
Creates a new Stem wrapping the given word stem.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStem.AddPrefix(Lucene.Net.Analysis.Hunspell.HunspellAffix)">
<summary>
Adds a prefix to the list of prefixes used to generate this stem. Because it is
assumed that prefixes are added depth first, the prefix is added to the front of
the list.
</summary>
<param name="prefix">Prefix to add to the list of prefixes for this stem.</param>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStem.AddSuffix(Lucene.Net.Analysis.Hunspell.HunspellAffix)">
<summary>
Adds a suffix to the list of suffixes used to generate this stem. Because it
is assumed that suffixes are added depth first, the suffix is added to the end
of the list.
</summary>
<param name="suffix">Suffix to add to the list of suffixes for this stem.</param>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellStem.Stem">
<summary>
the actual word stem itself.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellStem.StemLength">
<summary>
The stem length.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellStem.Prefixes">
<summary>
The list of prefixes used to generate the stem.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Hunspell.HunspellStem.Suffixes">
<summary>
The list of suffixes used to generate the stem.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Hunspell.HunspellStemFilter">
<summary>
TokenFilter that uses hunspell affix rules and words to stem tokens. Since hunspell supports a
word having multiple stems, this filter can emit multiple tokens for each consumed token.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStemFilter.#ctor(Lucene.Net.Analysis.TokenStream,Lucene.Net.Analysis.Hunspell.HunspellDictionary,System.Boolean)">
<summary>
Creates a new HunspellStemFilter that will stem tokens from the given TokenStream using
affix rules in the provided HunspellDictionary.
</summary>
<param name="input">TokenStream whose tokens will be stemmed.</param>
<param name="dictionary">HunspellDictionary containing the affix rules and words that will be used to stem the tokens.</param>
<param name="dedup">true if only unique terms should be output.</param>
</member>
<member name="T:Lucene.Net.Analysis.Hunspell.HunspellStemmer">
<summary>
HunspellStemmer uses the affix rules declared in the HunspellDictionary to generate one or
more stems for a word. It conforms to the algorithm in the original hunspell algorithm,
including recursive suffix stripping.
</summary>
<author>Chris Male</author>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStemmer.#ctor(Lucene.Net.Analysis.Hunspell.HunspellDictionary)">
<summary>
Constructs a new HunspellStemmer which will use the provided HunspellDictionary
to create its stems.
</summary>
<param name="dictionary">HunspellDictionary that will be used to create the stems.</param>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStemmer.Stem(System.String)">
<summary>
Find the stem(s) of the provided word.
</summary>
<param name="word">Word to find the stems for.</param>
<returns>List of stems for the word.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStemmer.UniqueStems(System.String)">
<summary>
Find the unique stem(s) of the provided word.
</summary>
<param name="word">Word to find the stems for.</param>
<returns>List of stems for the word.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStemmer.Stem(System.String,System.Char[],System.Int32)">
<summary>
Generates a list of stems for the provided word.
</summary>
<param name="word">Word to generate the stems for.</param>
<param name="flags">Flags from a previous stemming step that need to be cross-checked with any affixes in this recursive step.</param>
<param name="recursionDepth">Level of recursion this stemming step is at.</param>
<returns>List of stems, pr an empty if no stems are found.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStemmer.ApplyAffix(System.String,Lucene.Net.Analysis.Hunspell.HunspellAffix,System.Int32)">
<summary>
Applies the affix rule to the given word, producing a list of stems if any are found.
</summary>
<param name="strippedWord">Word the affix has been removed and the strip added.</param>
<param name="affix">HunspellAffix representing the affix rule itself.</param>
<param name="recursionDepth">Level of recursion this stemming step is at.</param>
<returns>List of stems for the word, or an empty list if none are found.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellStemmer.HasCrossCheckedFlag(System.Char,System.Char[])">
<summary>
Checks if the given flag cross checks with the given array of flags.
</summary>
<param name="flag">Flag to cross check with the array of flags.</param>
<param name="flags">Array of flags to cross check against. Can be <c>null</c>.</param>
<returns><c>true</c> if the flag is found in the array or the array is <c>null</c>, <c>false</c> otherwise.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellWord.#ctor">
<summary>
Creates a new HunspellWord with no associated flags.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellWord.#ctor(System.Char[])">
<summary>
Constructs a new HunspellWord with the given flags.
</summary>
<param name="flags">Flags to associate with the word.</param>
</member>
<member name="M:Lucene.Net.Analysis.Hunspell.HunspellWord.HasFlag(System.Char)">
<summary>
Checks whether the word has the given flag associated with it.
</summary>
<param name="flag">Flag to check whether it is associated with the word.</param>
<returns><c>true</c> if the flag is associated, <c>false</c> otherwise</returns>
</member>
<member name="T:Lucene.Net.Analysis.Miscellaneous.EmptyTokenStream">
<summary>
An always exhausted token stream
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Miscellaneous.PrefixAwareTokenFilter">
<summary>
Joins two token streams and leaves the last token of the first stream available
to be used when updating the token values in the second stream based on that token.
The default implementation adds last prefix token end offset to the suffix token start and end offsets.
<p/>
<b>NOTE:</b> This filter might not behave correctly if used with custom Attributes, i.e. Attributes other than
the ones located in Lucene.Net.Analysis.TokenAttributes.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Miscellaneous.PrefixAwareTokenFilter.UpdateSuffixToken(Lucene.Net.Analysis.Token,Lucene.Net.Analysis.Token)">
<summary>
The default implementation adds last prefix token end offset to the suffix token start and end offsets.
</summary>
<param name="suffixToken">a token from the suffix stream</param>
<param name="lastPrefixToken">the last token from the prefix stream</param>
<returns>consumer token</returns>
</member>
<member name="T:Lucene.Net.Analysis.Miscellaneous.PrefixAndSuffixAwareTokenFilter">
<summary>
Links two PrefixAwareTokenFilter.
<p/>
<b>NOTE:</b> This filter might not behave correctly if used with custom Attributes, i.e. Attributes other than
the ones located in Lucene.Net.Analysis.Tokenattributes.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Miscellaneous.SingleTokenTokenStream">
<summary>
A TokenStream containing a single token.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.NGram.Side">
<summary>
Specifies which side of the input the n-gram should be generated from
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.AbstractEncoder">
<summary>
Base class for payload encoders.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.PayloadEncoder">
<summary>
Mainly for use with the DelimitedPayloadTokenFilter, converts char buffers to Payload
<p/>
NOTE: this interface is subject to change
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Payloads.PayloadEncoder.Encode(System.Char[],System.Int32,System.Int32)">
<summary>
Convert a char array to a <see cref="T:Lucene.Net.Index.Payload"/>
</summary>
<returns>An encoded <see cref="T:Lucene.Net.Index.Payload"/></returns>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.DelimitedPayloadTokenFilter">
<summary>
Characters before the delimiter are the "token", those after are the payload.
<p/>
For example, if the delimiter is '|', then for the string "foo|bar", foo is the token
and "bar" is a payload.
<p/>
Note, you can also include a {@link org.apache.lucene.analysis.payloads.PayloadEncoder} to convert the
payload in an appropriate way (from characters to bytes).
<p/>
Note make sure your Tokenizer doesn't split on the delimiter, or this won't work
</summary>
<seealso cref="T:Lucene.Net.Analysis.Payloads.PayloadEncoder"/>
</member>
<member name="M:Lucene.Net.Analysis.Payloads.DelimitedPayloadTokenFilter.#ctor(Lucene.Net.Analysis.TokenStream)">
<summary>
Construct a token stream filtering the given input.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.FloatEncoder">
<summary>
Encode a character array Float as a {@link org.apache.lucene.index.Payload}.
</summary>
<seealso cref="M:Lucene.Net.Analysis.Payloads.PayloadHelper.EncodeFloat(System.Single,System.Byte[],System.Int32)"/>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.IdentityEncoder">
<summary>
Does nothing other than convert the char array to a byte array using the specified encoding.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.IntegerEncoder">
<summary>
Encode a character array Integer as a {@link org.apache.lucene.index.Payload}.
</summary>
<seealso cref="M:Lucene.Net.Analysis.Payloads.PayloadHelper.EncodeInt(System.Int32,System.Byte[],System.Int32)"/>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.NumericPayloadTokenFilter">
<summary>
Assigns a payload to a token based on the <see cref="P:Lucene.Net.Analysis.Token.Type"/>
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.PayloadHelper">
<summary>
Utility methods for encoding payloads.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Payloads.PayloadHelper.DecodeFloat(System.Byte[])">
<summary>
<p>Decode the payload that was encoded using encodeFloat(float)</p>
<p>NOTE: the length of the array must be at least offset + 4 long.</p>
</summary>
<param name="bytes">The bytes to decode</param>
<returns>the decoded float</returns>
</member>
<member name="M:Lucene.Net.Analysis.Payloads.PayloadHelper.DecodeFloat(System.Byte[],System.Int32)">
<summary>
<p>Decode the payload that was encoded using encodeFloat(float)</p>
<p>NOTE: the length of the array must be at least offset + 4 long.</p>
</summary>
<param name="bytes">The bytes to decode</param>
<param name="offset">The offset into the array.</param>
<returns>The float that was encoded</returns>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.TokenOffsetPayloadTokenFilter">
<summary>
Adds the <see cref="P:Lucene.Net.Analysis.Token.StartOffset"/>
and <see cref="P:Lucene.Net.Analysis.Token.EndOffset"/>
First 4 bytes are the start
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Payloads.TypeAsPayloadTokenFilter">
<summary>
Makes the Token.Type() a payload.
Encodes the type using <see cref="P:System.Text.Encoding.UTF8"/> as the encoding
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Ru.RussianAnalyzer">
<summary>
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="F:Lucene.Net.Analysis.Ru.RussianAnalyzer.RUSSIAN_STOP_WORDS">
<summary>
List of typical Russian stopwords.
</summary>
</member>
<member name="F:Lucene.Net.Analysis.Ru.RussianAnalyzer.stopSet">
<summary>
Contains the stopwords used with the StopFilter.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Ru.RussianLetterTokenizer">
<summary>
A RussianLetterTokenizer is a {@link Tokenizer} that extends {@link LetterTokenizer}
by also allowing the basic latin digits 0-9.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Ru.RussianLowerCaseFilter">
<summary>
Normalizes token text to lower case.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Shingle.Matrix.Matrix">
<summary>
A column focused matrix in three dimensions:
<pre>
Token[column][row][z-axis] {
{{hello}, {greetings, and, salutations}},
{{world}, {earth}, {tellus}}
};
</pre>
todo consider row groups
to indicate that shingles is only to contain permutations with texts in that same row group.
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Shingle.ShingleAnalyzerWrapper.MaxShingleSize">
<summary>
Gets or sets the max shingle (ngram) size
</summary>
</member>
<member name="P:Lucene.Net.Analysis.Shingle.ShingleAnalyzerWrapper.IsOutputUnigrams">
<summary>
Gets or sets whether or not to have the filter pass the original tokens
(the "unigrams") to the output stream
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter">
<summary>
<p>A ShingleMatrixFilter constructs shingles (token n-grams) from a token stream.
In other words, it creates combinations of tokens as a single token.</p>
<p>For example, the sentence "please divide this sentence into shingles"
might be tokenized into shingles "please divide", "divide this",
"this sentence", "sentence into", and "into shingles".</p>
<p>Using a shingle filter at index and query time can in some instances
be used to replace phrase queries, especially them with 0 slop.</p>
<p>Without a spacer character
it can be used to handle composition and decomposition of words
such as searching for "multi dimensional" instead of "multidimensional".
It is a rather common human problem at query time
in several languages, notably the northern Germanic branch.</p>
<p>Shingles are amongst many things also known to solve problems
in spell checking, language detection and document clustering.</p>
<p>This filter is backed by a three dimensional column oriented matrix
used to create permutations of the second dimension, the rows,
and leaves the third, the z-axis, for for multi token synonyms.</p>
<p>In order to use this filter you need to define a way of positioning
the input stream tokens in the matrix. This is done using a
ShingleMatrixFilter.TokenSettingsCodec.
There are three simple implementations for demonstrational purposes,
see ShingleMatrixFilter.OneDimensionalNonWeightedTokenSettingsCodec,
ShingleMatrixFilter.TwoDimensionalNonWeightedSynonymTokenSettingsCodec
and ShingleMatrixFilter.SimpleThreeDimensionalTokenSettingsCodec.</p>
<p>Consider this token matrix:</p>
<pre>
Token[column][row][z-axis]{
{{hello}, {greetings, and, salutations}},
{{world}, {earth}, {tellus}}
};
</pre>
It would produce the following 2-3 gram sized shingles:
<pre>
"hello_world"
"greetings_and"
"greetings_and_salutations"
"and_salutations"
"and_salutations_world"
"salutations_world"
"hello_earth"
"and_salutations_earth"
"salutations_earth"
"hello_tellus"
"and_salutations_tellus"
"salutations_tellus"
</pre>
<p>This implementation can be rather heap demanding
if (maximum shingle size - minimum shingle size) is a great number and the stream contains many columns,
or if each column contains a great number of rows.</p>
<p>The problem is that in order avoid producing duplicates
the filter needs to keep track of any shingle already produced and returned to the consumer.</p>
<p>There is a bit of resource management to handle this
but it would of course be much better if the filter was written
so it never created the same shingle more than once in the first place.</p>
<p>The filter also has basic support for calculating weights for the shingles
based on the weights of the tokens from the input stream, output shingle size, etc.
See CalculateShingleWeight.
<p/>
<b>NOTE:</b> This filter might not behave correctly if used with custom Attributes, i.e. Attributes other than
the ones located in org.apache.lucene.analysis.tokenattributes.</p>
</summary>
</member>
<member name="F:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter._shinglesSeen">
<summary>
A set containing shingles that has been the result of a call to Next(Token),
used to avoid producing the same shingle more than once.
<p>
NOTE: The Java List implementation uses a different equality comparison scheme
than .NET's Generic List. So We have to use a custom IEqualityComparer implementation
to get the same behaviour.
</p>
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.#ctor(Lucene.Net.Analysis.Shingle.Matrix.Matrix,System.Int32,System.Int32,System.Char,System.Boolean,Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec)">
<summary>
Creates a shingle filter based on a user defined matrix.
The filter /will/ delete columns from the input matrix! You will not be able to reset the filter if you used this constructor.
todo: don't touch the matrix! use a bool, set the input stream to null or something, and keep track of where in the matrix we are at.
</summary>
<param name="matrix">the input based for creating shingles. Does not need to contain any information until ShingleMatrixFilter.IncrementToken() is called the first time.</param>
<param name="minimumShingleSize">minimum number of tokens in any shingle.</param>
<param name="maximumShingleSize">maximum number of tokens in any shingle.</param>
<param name="spacerCharacter">character to use between texts of the token parts in a shingle. null for none.</param>
<param name="ignoringSinglePrefixOrSuffixShingle">if true, shingles that only contains permutation of the first of the last column will not be produced as shingles. Useful when adding boundary marker tokens such as '^' and '$'.</param>
<param name="settingsCodec">codec used to read input token weight and matrix positioning.</param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Int32,System.Int32)">
<summary>
Creates a shingle filter using default settings.
See ShingleMatrixFilter.DefaultSpacerCharacter,
ShingleMatrixFilter.IgnoringSinglePrefixOrSuffixShingleByDefault,
and ShingleMatrixFilter.DefaultSettingsCodec
</summary>
<param name="input">stream from which to construct the matrix</param>
<param name="minimumShingleSize">minimum number of tokens in any shingle.</param>
<param name="maximumShingleSize">maximum number of tokens in any shingle.</param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Int32,System.Int32,System.Nullable{System.Char})">
<summary>
Creates a shingle filter using default settings.
See IgnoringSinglePrefixOrSuffixShingleByDefault, and DefaultSettingsCodec
</summary>
<param name="input">stream from which to construct the matrix</param>
<param name="minimumShingleSize">minimum number of tokens in any shingle.</param>
<param name="maximumShingleSize">maximum number of tokens in any shingle.</param>
<param name="spacerCharacter">character to use between texts of the token parts in a shingle. null for none. </param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Int32,System.Int32,System.Nullable{System.Char},System.Boolean)">
<summary>
Creates a shingle filter using the default <see cref="T:Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec"/>.
See DefaultSettingsCodec
</summary>
<param name="input">stream from which to construct the matrix</param>
<param name="minimumShingleSize">minimum number of tokens in any shingle.</param>
<param name="maximumShingleSize">maximum number of tokens in any shingle.</param>
<param name="spacerCharacter">character to use between texts of the token parts in a shingle. null for none.</param>
<param name="ignoringSinglePrefixOrSuffixShingle">if true, shingles that only contains permutation of the first of the last column will not be produced as shingles. Useful when adding boundary marker tokens such as '^' and '$'.</param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.#ctor(Lucene.Net.Analysis.TokenStream,System.Int32,System.Int32,System.Nullable{System.Char},System.Boolean,Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec)">
<summary>
Creates a shingle filter with ad hoc parameter settings.
</summary>
<param name="input">stream from which to construct the matrix</param>
<param name="minimumShingleSize">minimum number of tokens in any shingle.</param>
<param name="maximumShingleSize">maximum number of tokens in any shingle.</param>
<param name="spacerCharacter">character to use between texts of the token parts in a shingle. null for none.</param>
<param name="ignoringSinglePrefixOrSuffixShingle">if true, shingles that only contains permutation of the first of the last column will not be produced as shingles. Useful when adding boundary marker tokens such as '^' and '$'.</param>
<param name="settingsCodec">codec used to read input token weight and matrix positioning.</param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.ProduceNextToken(Lucene.Net.Analysis.Token)">
<summary>
This method exists in order to avoid recursive calls to the method
as the complexity of a fairly small matrix then easily would require
a gigabyte sized stack per thread.
</summary>
<param name="reusableToken"></param>
<returns>null if exhausted, instance request_next_token if one more call is required for an answer,
or instance parameter resuableToken.</returns>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.NextTokensPermutation">
<summary>
Get next permutation of row combinations,
creates list of all tokens in the row and
an index from each such token to what row they exist in.
finally resets the current (next) shingle size and offset.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.UpdateToken(Lucene.Net.Analysis.Token,System.Collections.Generic.List{Lucene.Net.Analysis.Token},System.Int32,System.Collections.Generic.List{Lucene.Net.Analysis.Shingle.Matrix.Row},System.Collections.Generic.List{Lucene.Net.Analysis.Token})">
<summary>
Final touch of a shingle token before it is passed on to the consumer from method <see cref="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.IncrementToken"/>.
Calculates and sets type, flags, position increment, start/end offsets and weight.
</summary>
<param name="token">Shingle Token</param>
<param name="shingle">Tokens used to produce the shingle token.</param>
<param name="currentPermutationStartOffset">Start offset in parameter currentPermutationTokens</param>
<param name="currentPermutationRows">index to Matrix.Column.Row from the position of tokens in parameter currentPermutationTokens</param>
<param name="currentPermuationTokens">tokens of the current permutation of rows in the matrix. </param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.CalculateShingleWeight(Lucene.Net.Analysis.Token,System.Collections.Generic.List{Lucene.Net.Analysis.Token},System.Int32,System.Collections.Generic.List{Lucene.Net.Analysis.Shingle.Matrix.Row},System.Collections.Generic.List{Lucene.Net.Analysis.Token})">
<summary>
Evaluates the new shingle token weight.
for (shingle part token in shingle)
weight += shingle part token weight * (1 / sqrt(all shingle part token weights summed))
This algorithm gives a slightly greater score for longer shingles
and is rather penalising to great shingle token part weights.
</summary>
<param name="shingleToken">token returned to consumer</param>
<param name="shingle">tokens the tokens used to produce the shingle token.</param>
<param name="currentPermutationStartOffset">start offset in parameter currentPermutationRows and currentPermutationTokens.</param>
<param name="currentPermutationRows">an index to what matrix row a token in parameter currentPermutationTokens exist.</param>
<param name="currentPermuationTokens">all tokens in the current row permutation of the matrix. A sub list (parameter offset, parameter shingle.size) equals parameter shingle.</param>
<returns>weight to be set for parameter shingleToken </returns>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.ShingleMatrixFilter.ReadColumn">
<summary>
Loads one column from the token stream.
When the last token is read from the token stream it will column.setLast(true);
</summary>
<returns>true if it manage to read one more column from the input token stream</returns>
</member>
<member name="T:Lucene.Net.Analysis.Shingle.Codec.OneDimensionalNonWeightedTokenSettingsCodec">
<summary>
Using this codec makes a ShingleMatrixFilter act like ShingleFilter.
It produces the most simple sort of shingles, ignoring token position increments, etc.
It adds each token as a new column.
</summary>
</member>
<member name="T:Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec">
<summary>
Strategy used to code and decode meta data of the tokens from the input stream
regarding how to position the tokens in the matrix, set and retreive weight, etc.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec.GetTokenPositioner(Lucene.Net.Analysis.Token)">
<summary>
Retrieves information on how a Token is to be inserted to a ShingleMatrixFilter.Matrix.
</summary>
<param name="token"></param>
<returns></returns>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec.SetTokenPositioner(Lucene.Net.Analysis.Token,Lucene.Net.Analysis.Shingle.TokenPositioner)">
<summary>
Sets information on how a Token is to be inserted to a ShingleMatrixFilter.Matrix.
</summary>
<param name="token"></param>
<param name="tokenPositioner"></param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec.GetWeight(Lucene.Net.Analysis.Token)">
<summary>
Have this method return 1f in order to 'disable' weights.
</summary>
<param name="token"></param>
<returns></returns>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.TokenSettingsCodec.SetWeight(Lucene.Net.Analysis.Token,System.Single)">
<summary>
Have this method do nothing in order to 'disable' weights.
</summary>
<param name="token"></param>
<param name="weight"></param>
</member>
<member name="T:Lucene.Net.Analysis.Shingle.Codec.SimpleThreeDimensionalTokenSettingsCodec">
<summary>
A full featured codec not to be used for something serious.
It takes complete control of
payload for weight
and the bit flags for positioning in the matrix.
Mainly exist for demonstrational purposes.
</summary>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.SimpleThreeDimensionalTokenSettingsCodec.GetTokenPositioner(Lucene.Net.Analysis.Token)">
<summary>
</summary>
<param name="token"></param>
<returns>the token flags int value as TokenPosition</returns>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.SimpleThreeDimensionalTokenSettingsCodec.SetTokenPositioner(Lucene.Net.Analysis.Token,Lucene.Net.Analysis.Shingle.TokenPositioner)">
<summary>
Sets the TokenPositioner as token flags int value.
</summary>
<param name="token"></param>
<param name="tokenPositioner"></param>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.SimpleThreeDimensionalTokenSettingsCodec.GetWeight(Lucene.Net.Analysis.Token)">
<summary>
Returns a 32 bit float from the payload, or 1f it null.
</summary>
<param name="token"></param>
<returns></returns>
</member>
<member name="M:Lucene.Net.Analysis.Shingle.Codec.SimpleThreeDimensionalTokenSettingsCodec.SetWeight(Lucene.Net.Analysis.Token,System.Single)">
<summary>
Stores a 32 bit float in the payload, or set it to null if 1f;
</summary>
<param name="token"></param>
<param name="weight"></param>
</member>
<member name="T:Lucene.Net.Analysis.Shingle.Codec.TwoDimensionalNonWeightedSynonymTokenSettingsCodec">
<summary>
A codec that creates a two dimensional matrix
by treating tokens from the input stream with 0 position increment
as new rows to the current column.
</summary>
</member>
</members>
</doc>