lucenenet-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From nightowl...@apache.org
Subject [41/62] [abbrv] lucenenet git commit: Deleted obsolete Contrib folder
Date Sat, 01 Apr 2017 01:09:34 GMT
Deleted obsolete Contrib folder


Project: http://git-wip-us.apache.org/repos/asf/lucenenet/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucenenet/commit/02362804
Tree: http://git-wip-us.apache.org/repos/asf/lucenenet/tree/02362804
Diff: http://git-wip-us.apache.org/repos/asf/lucenenet/diff/02362804

Branch: refs/heads/api-work
Commit: 023628042cb07a976704ef7663e6be66e7cdfa3e
Parents: 47b6c46
Author: Shad Storhaug <shad@shadstorhaug.com>
Authored: Sat Apr 1 02:00:19 2017 +0700
Committer: Shad Storhaug <shad@shadstorhaug.com>
Committed: Sat Apr 1 07:51:58 2017 +0700

----------------------------------------------------------------------
 src/contrib/Analyzers/AR/ArabicAnalyzer.cs      |  207 --
 .../Analyzers/AR/ArabicLetterTokenizer.cs       |   63 -
 .../Analyzers/AR/ArabicNormalizationFilter.cs   |   58 -
 src/contrib/Analyzers/AR/ArabicNormalizer.cs    |  130 -
 src/contrib/Analyzers/AR/ArabicStemFilter.cs    |   62 -
 src/contrib/Analyzers/AR/ArabicStemmer.cs       |  208 --
 src/contrib/Analyzers/AR/ArabicStopWords.txt    |  162 -
 src/contrib/Analyzers/BR/BrazilianAnalyzer.cs   |  249 --
 src/contrib/Analyzers/BR/BrazilianStemFilter.cs |   79 -
 src/contrib/Analyzers/BR/BrazilianStemmer.cs    | 1264 -------
 src/contrib/Analyzers/CJK/CJKAnalyzer.cs        |  154 -
 src/contrib/Analyzers/CJK/CJKTokenizer.cs       |  399 ---
 src/contrib/Analyzers/Cn/ChineseAnalyzer.cs     |   85 -
 src/contrib/Analyzers/Cn/ChineseFilter.cs       |  100 -
 src/contrib/Analyzers/Cn/ChineseTokenizer.cs    |  191 --
 .../Compound/CompoundWordTokenFilterBase.cs     |  230 --
 .../DictionaryCompoundWordTokenFilter.cs        |  141 -
 .../Compound/Hyphenation/ByteVector.cs          |  148 -
 .../Compound/Hyphenation/CharVector.cs          |  162 -
 .../Analyzers/Compound/Hyphenation/Hyphen.cs    |   78 -
 .../Compound/Hyphenation/Hyphenation.cs         |   59 -
 .../Hyphenation/HyphenationException.cs         |   51 -
 .../Compound/Hyphenation/HyphenationTree.cs     |  480 ---
 .../Compound/Hyphenation/PatternConsumer.cs     |   58 -
 .../Compound/Hyphenation/PatternParser.cs       |  495 ---
 .../Compound/Hyphenation/TernaryTree.cs         |  766 -----
 .../Compound/Hyphenation/hyphenation.dtd        |   68 -
 .../HyphenationCompoundWordTokenFilter.cs       |  230 --
 src/contrib/Analyzers/Contrib.Analyzers.csproj  |  234 --
 src/contrib/Analyzers/Cz/CzechAnalyzer.cs       |  222 --
 src/contrib/Analyzers/De/GermanAnalyzer.cs      |  250 --
 src/contrib/Analyzers/De/GermanDIN2Stemmer.cs   |   55 -
 src/contrib/Analyzers/De/GermanStemFilter.cs    |  123 -
 src/contrib/Analyzers/De/GermanStemmer.cs       |  308 --
 src/contrib/Analyzers/El/GreekAnalyzer.cs       |  174 -
 .../Analyzers/El/GreekLowerCaseFilter.cs        |  123 -
 src/contrib/Analyzers/En/KStemData1.cs          |  758 -----
 src/contrib/Analyzers/En/KStemData2.cs          |  755 -----
 src/contrib/Analyzers/En/KStemData3.cs          |  756 -----
 src/contrib/Analyzers/En/KStemData4.cs          |  757 -----
 src/contrib/Analyzers/En/KStemData5.cs          |  755 -----
 src/contrib/Analyzers/En/KStemData6.cs          |  756 -----
 src/contrib/Analyzers/En/KStemData7.cs          |  756 -----
 src/contrib/Analyzers/En/KStemData8.cs          |  655 ----
 src/contrib/Analyzers/En/KStemFilter.cs         |   48 -
 src/contrib/Analyzers/En/KStemmer.cs            | 1759 ----------
 src/contrib/Analyzers/Fa/PersianAnalyzer.cs     |  234 --
 .../Analyzers/Fa/PersianNormalizationFilter.cs  |   54 -
 src/contrib/Analyzers/Fa/PersianNormalizer.cs   |  108 -
 src/contrib/Analyzers/Filters/ChainedFilter.cs  |  275 --
 src/contrib/Analyzers/Fr/ElisionFilter.cs       |  114 -
 src/contrib/Analyzers/Fr/FrenchAnalyzer.cs      |  262 --
 src/contrib/Analyzers/Fr/FrenchStemFilter.cs    |  113 -
 src/contrib/Analyzers/Fr/FrenchStemmer.cs       |  726 ----
 src/contrib/Analyzers/Hunspell/HunspellAffix.cs |   90 -
 .../Analyzers/Hunspell/HunspellDictionary.cs    |  428 ---
 src/contrib/Analyzers/Hunspell/HunspellStem.cs  |   84 -
 .../Analyzers/Hunspell/HunspellStemFilter.cs    |   92 -
 .../Analyzers/Hunspell/HunspellStemmer.cs       |  201 --
 src/contrib/Analyzers/Hunspell/HunspellWord.cs  |   51 -
 .../Analyzers/Miscellaneous/EmptyTokenStream.cs |   35 -
 .../InjectablePrefixAwareTokenFilter.cs         |   35 -
 .../Analyzers/Miscellaneous/PatternAnalyzer.cs  |  538 ---
 .../PrefixAndSuffixAwareTokenFilter.cs          |   74 -
 .../Miscellaneous/PrefixAwareTokenStream.cs     |  183 --
 .../Miscellaneous/SingleTokenTokenStream.cs     |   78 -
 .../Analyzers/NGram/EdgeNGramTokenFilter.cs     |  189 --
 .../Analyzers/NGram/EdgeNGramTokenizer.cs       |  225 --
 src/contrib/Analyzers/NGram/NGramTokenFilter.cs |  124 -
 src/contrib/Analyzers/NGram/NGramTokenizer.cs   |  161 -
 src/contrib/Analyzers/Nl/DutchAnalyzer.cs       |  288 --
 src/contrib/Analyzers/Nl/DutchStemFilter.cs     |  132 -
 src/contrib/Analyzers/Nl/DutchStemmer.cs        |  462 ---
 .../Analyzers/Payloads/AbstractEncoder.cs       |   34 -
 .../Payloads/DelimitedPayloadTokenFilter.cs     |   90 -
 src/contrib/Analyzers/Payloads/FloatEncoder.cs  |   38 -
 .../Analyzers/Payloads/IdentityEncoder.cs       |   62 -
 .../Analyzers/Payloads/IntegerEncoder.cs        |   38 -
 .../Payloads/NumericPayloadTokenFilter.cs       |   63 -
 .../Analyzers/Payloads/PayloadEncoder.cs        |   37 -
 src/contrib/Analyzers/Payloads/PayloadHelper.cs |   80 -
 .../Payloads/TokenOffsetPayloadTokenFilter.cs   |   61 -
 .../Payloads/TypeAsPayloadTokenFilter.cs        |   62 -
 .../Analyzers/Position/PositionFilter.cs        |   97 -
 .../Analyzers/Properties/AssemblyInfo.cs        |   66 -
 .../Query/QueryAutoStopWordAnalyzer.cs          |  300 --
 .../Analyzers/Reverse/ReverseStringFilter.cs    |  149 -
 src/contrib/Analyzers/Ru/RussianAnalyzer.cs     |  172 -
 .../Analyzers/Ru/RussianLetterTokenizer.cs      |   62 -
 .../Analyzers/Ru/RussianLowerCaseFilter.cs      |   60 -
 src/contrib/Analyzers/Ru/RussianStemFilter.cs   |   85 -
 src/contrib/Analyzers/Ru/RussianStemmer.cs      |  615 ----
 ...eDimensionalNonWeightedTokenSettingsCodec.cs |   46 -
 .../SimpleThreeDimensionalTokenSettingsCodec.cs |   87 -
 .../Shingle/Codec/TokenSettingsCodec.cs         |   54 -
 ...ionalNonWeightedSynonymTokenSettingsCodec.cs |   49 -
 src/contrib/Analyzers/Shingle/Matrix/Column.cs  |   67 -
 src/contrib/Analyzers/Shingle/Matrix/Matrix.cs  |   56 -
 .../Shingle/Matrix/MatrixPermutationIterator.cs |   72 -
 src/contrib/Analyzers/Shingle/Matrix/Row.cs     |   48 -
 .../Analyzers/Shingle/ShingleAnalyzerWrapper.cs |  148 -
 src/contrib/Analyzers/Shingle/ShingleFilter.cs  |  381 ---
 .../Analyzers/Shingle/ShingleMatrixFilter.cs    |  638 ----
 .../Analyzers/Shingle/TokenPositioner.cs        |   33 -
 .../Analyzers/Sinks/DateRecognizerSinkFilter.cs |   81 -
 .../Analyzers/Sinks/TokenRangeSinkFilter.cs     |   63 -
 .../Analyzers/Sinks/TokenTypeSinkFilter.cs      |   51 -
 src/contrib/Analyzers/Th/ThaiAnalyzer.cs        |   94 -
 src/contrib/Analyzers/Th/ThaiWordFilter.cs      |  105 -
 src/contrib/Analyzers/WordlistLoader.cs         |  125 -
 src/contrib/Core/Analysis/Ext/Analysis.Ext.cs   |  166 -
 src/contrib/Core/Contrib.Core.csproj            |  163 -
 src/contrib/Core/Index/FieldEnumerator.cs       |  842 -----
 src/contrib/Core/Index/SegmentsGenCommit.cs     |  162 -
 src/contrib/Core/Index/TermVectorEnumerator.cs  |  194 --
 src/contrib/Core/Properties/AssemblyInfo.cs     |   60 -
 src/contrib/Core/Util/Cache/SegmentCache.cs     |  213 --
 .../Distributed/Configuration/CurrentIndex.cs   |  614 ----
 .../Configuration/DistributedSearcher.cs        |  126 -
 .../DistributedSearcherConfigurationHandler.cs  |   56 -
 .../Configuration/DistributedSearchers.cs       |   82 -
 .../Configuration/LuceneServerIndex.cs          |  175 -
 .../LuceneServerIndexConfigurationHandler.cs    |   43 -
 .../Configuration/LuceneServerIndexes.cs        |  109 -
 .../Distributed/Enumerations.cs                 |   65 -
 .../Distributed/Indexing/DeleteIndexDocument.cs |   35 -
 .../Distributed/Indexing/FileNameComparer.cs    |   44 -
 .../Distributed/Indexing/IndexDocument.cs       |  146 -
 .../Distributed/Indexing/IndexSet.cs            |  363 --
 .../Indexing/IndexSetConfigurationHandler.cs    |   46 -
 .../Distributed/Indexing/IndexSets.cs           |  293 --
 .../Distributed/Search/DistributedSearchable.cs |  100 -
 .../LuceneMonitor/LuceneMonitor.cs              |  184 --
 .../LuceneMonitor/ProjectInstaller.cs           |  141 -
 .../LuceneMonitorSetup.vdproj                   |  948 ------
 .../BaseFragmentsBuilder.cs                     |  201 --
 .../Contrib.FastVectorHighlighter.csproj        |  188 --
 .../FastVectorHighlighter.cs                    |  150 -
 .../FastVectorHighlighter/FieldFragList.cs      |  118 -
 .../FastVectorHighlighter/FieldPhraseList.cs    |  233 --
 src/contrib/FastVectorHighlighter/FieldQuery.cs |  489 ---
 .../FastVectorHighlighter/FieldTermStack.cs     |  245 --
 .../FastVectorHighlighter/FragListBuilder.cs    |   39 -
 .../FastVectorHighlighter/FragmentsBuilder.cs   |   56 -
 .../Properties/AssemblyInfo.cs                  |   59 -
 src/contrib/FastVectorHighlighter/Readme.txt    |    7 -
 .../ScoreOrderFragmentsBuilder.cs               |   76 -
 .../SimpleFragListBuilder.cs                    |   92 -
 .../SimpleFragmentsBuilder.cs                   |   59 -
 .../FastVectorHighlighter/StringUtils.cs        |   56 -
 src/contrib/FastVectorHighlighter/Support.cs    |   73 -
 .../VectorHighlightMapper.cs                    |  134 -
 src/contrib/FastVectorHighlighter/package.html  |  144 -
 src/contrib/Highlighter/ABOUT.txt               |    1 -
 src/contrib/Highlighter/AssemblyInfo.cs         |   85 -
 .../Highlighter/Contrib.Highlighter.csproj      |  266 --
 src/contrib/Highlighter/DefaultEncoder.cs       |   28 -
 src/contrib/Highlighter/GradientFormatter.cs    |  212 --
 src/contrib/Highlighter/HISTORY.txt             |   22 -
 src/contrib/Highlighter/Highlighter.cs          |  477 ---
 src/contrib/Highlighter/IEncoder.cs             |   26 -
 src/contrib/Highlighter/IFormatter.cs           |   29 -
 src/contrib/Highlighter/IFragmenter.cs          |   46 -
 src/contrib/Highlighter/IScorer.cs              |   62 -
 .../Highlighter/InvalidTokenOffsetsException.cs |   51 -
 src/contrib/Highlighter/NullFragmenter.cs       |   36 -
 src/contrib/Highlighter/Package.html            |   81 -
 src/contrib/Highlighter/QueryScorer.cs          |  270 --
 src/contrib/Highlighter/QueryTermExtractor.cs   |  163 -
 src/contrib/Highlighter/QueryTermScorer.cs      |  190 --
 src/contrib/Highlighter/SimpleFragmenter.cs     |   87 -
 src/contrib/Highlighter/SimpleHTMLEncoder.cs    |   85 -
 src/contrib/Highlighter/SimpleHTMLFormatter.cs  |   63 -
 src/contrib/Highlighter/SimpleSpanFragmenter.cs |  112 -
 .../Highlighter/SpanGradientFormatter.cs        |   73 -
 src/contrib/Highlighter/TextFragment.cs         |   73 -
 src/contrib/Highlighter/TokenGroup.cs           |  144 -
 src/contrib/Highlighter/TokenSources.cs         |  267 --
 src/contrib/Highlighter/WeightedSpanTerm.cs     |  104 -
 .../Highlighter/WeightedSpanTermExtractor.cs    |  667 ----
 src/contrib/Highlighter/WeightedTerm.cs         |   44 -
 src/contrib/Memory/CollectionsHelper.cs         |  105 -
 src/contrib/Memory/Contrib.Memory.csproj        |  128 -
 src/contrib/Memory/EmptyCollector.cs            |   65 -
 src/contrib/Memory/KeywordTokenStream.cs        |   68 -
 src/contrib/Memory/MemoryIndex.cs               | 1138 -------
 src/contrib/Memory/MemoryTermEnum.cs            |  105 -
 src/contrib/Memory/MemoryTermPositionVector.cs  |  116 -
 src/contrib/Memory/MemoryTermPositions.cs       |  151 -
 src/contrib/Memory/Properties/AssemblyInfo.cs   |   60 -
 src/contrib/Memory/TermComparer.cs              |   52 -
 src/contrib/Queries/BooleanFilter.cs            |  281 --
 src/contrib/Queries/BoostingQuery.cs            |  153 -
 src/contrib/Queries/Contrib.Queries.csproj      |  168 -
 src/contrib/Queries/DuplicateFilter.cs          |  202 --
 src/contrib/Queries/FilterClause.cs             |   68 -
 src/contrib/Queries/FuzzyLikeThisQuery.cs       |  422 ---
 src/contrib/Queries/Properties/AssemblyInfo.cs  |   60 -
 src/contrib/Queries/README.txt                  |   22 -
 src/contrib/Queries/Similar/MoreLikeThis.cs     |  945 ------
 .../Queries/Similar/MoreLikeThisQuery.cs        |  141 -
 .../Queries/Similar/SimilarityQueries.cs        |  112 -
 src/contrib/Queries/Similar/package.html        |   22 -
 src/contrib/Queries/TermsFilter.cs              |  112 -
 src/contrib/README.txt                          |   22 -
 src/contrib/Regex/CSharpRegexCapabilities.cs    |   91 -
 src/contrib/Regex/Contrib.Regex.csproj          |  124 -
 src/contrib/Regex/IRegexCapabilities.cs         |   48 -
 src/contrib/Regex/IRegexQueryCapable.cs         |   28 -
 src/contrib/Regex/Properties/AssemblyInfo.cs    |   56 -
 src/contrib/Regex/RegexQuery.cs                 |   95 -
 src/contrib/Regex/RegexTermEnum.cs              |   84 -
 src/contrib/Regex/SpanRegexQuery.cs             |  155 -
 src/contrib/SimpleFacetedSearch/Extensions.cs   |   72 -
 src/contrib/SimpleFacetedSearch/FacetName.cs    |   51 -
 .../SimpleFacetedSearch/FieldValuesBitSets.cs   |   75 -
 src/contrib/SimpleFacetedSearch/Hits.cs         |   73 -
 src/contrib/SimpleFacetedSearch/HitsPerFacet.cs |  133 -
 .../Properties/AssemblyInfo.cs                  |   62 -
 src/contrib/SimpleFacetedSearch/README.txt      |   28 -
 .../SimpleFacetedSearch/SimpleFacetedSearch.cs  |  169 -
 .../SimpleFacetedSearch.csproj                  |  130 -
 src/contrib/Snowball/ABOUT.txt                  |    1 -
 src/contrib/Snowball/AssemblyInfo.cs            |   87 -
 src/contrib/Snowball/Contrib.Snowball.csproj    |  280 --
 src/contrib/Snowball/Docs/Index.html            |  169 -
 src/contrib/Snowball/HISTORY.txt                |   10 -
 src/contrib/Snowball/LICENSE.txt                |   46 -
 .../Lucene.Net/Analysis/Snowball/Package.html   |   26 -
 .../Analysis/Snowball/SnowballAnalyzer.cs       |  125 -
 .../Analysis/Snowball/SnowballFilter.cs         |   92 -
 src/contrib/Snowball/README.txt                 |   17 -
 src/contrib/Snowball/SF/Overview.html           |   26 -
 src/contrib/Snowball/SF/Snowball/Among.cs       |   56 -
 .../Snowball/SF/Snowball/Ext/DanishStemmer.cs   |  456 ---
 .../Snowball/SF/Snowball/Ext/DutchStemmer.cs    | 1022 ------
 .../Snowball/SF/Snowball/Ext/EnglishStemmer.cs  | 1481 ---------
 .../Snowball/SF/Snowball/Ext/FinnishStemmer.cs  | 1150 -------
 .../Snowball/SF/Snowball/Ext/FrenchStemmer.cs   | 1724 ----------
 .../Snowball/SF/Snowball/Ext/German2Stemmer.cs  |  887 -----
 .../Snowball/SF/Snowball/Ext/GermanStemmer.cs   |  859 -----
 .../SF/Snowball/Ext/HungarianStemmer.cs         | 1238 -------
 .../Snowball/SF/Snowball/Ext/ItalianStemmer.cs  | 1258 -------
 .../Snowball/SF/Snowball/Ext/KpStemmer.cs       | 2618 ---------------
 .../Snowball/SF/Snowball/Ext/LovinsStemmer.cs   | 1943 -----------
 .../SF/Snowball/Ext/NorwegianStemmer.cs         |  354 --
 .../Snowball/SF/Snowball/Ext/Package.html       |   26 -
 .../Snowball/SF/Snowball/Ext/PorterStemmer.cs   | 1086 ------
 .../SF/Snowball/Ext/PortugueseStemmer.cs        | 1176 -------
 .../Snowball/SF/Snowball/Ext/RomanianStemmer.cs | 1072 ------
 .../Snowball/SF/Snowball/Ext/RussianStemmer.cs  |  775 -----
 .../Snowball/SF/Snowball/Ext/SpanishStemmer.cs  | 1236 -------
 .../Snowball/SF/Snowball/Ext/SwedishStemmer.cs  |  358 --
 .../Snowball/SF/Snowball/Ext/TurkishStemmer.cs  | 3100 ------------------
 src/contrib/Snowball/SF/Snowball/Package.html   |   26 -
 .../Snowball/SF/Snowball/SnowballProgram.cs     |  518 ---
 src/contrib/Snowball/SF/Snowball/TestApp.cs     |   95 -
 src/contrib/Snowball/Xdocs/Index.xml            |   47 -
 .../Snowball/Xdocs/Stylesheets/Project.xml      |   53 -
 src/contrib/SpellChecker/ABOUT.txt              |    1 -
 src/contrib/SpellChecker/AssemblyInfo.cs        |   85 -
 .../SpellChecker/Contrib.SpellChecker.csproj    |  209 --
 src/contrib/SpellChecker/HISTORY.txt            |    8 -
 src/contrib/SpellChecker/Spell/IDictionary.cs   |   30 -
 .../SpellChecker/Spell/JaroWinklerDistance.cs   |  131 -
 .../SpellChecker/Spell/LevenshteinDistance.cs   |  118 -
 .../SpellChecker/Spell/LuceneDictionary.cs      |  134 -
 src/contrib/SpellChecker/Spell/NGramDistance.cs |  159 -
 src/contrib/SpellChecker/Spell/Package.html     |   26 -
 .../SpellChecker/Spell/PlainTextDictionary.cs   |  143 -
 src/contrib/SpellChecker/Spell/SpellChecker.cs  |  614 ----
 .../SpellChecker/Spell/StringDistance.cs        |   39 -
 src/contrib/SpellChecker/Spell/SuggestWord.cs   |   65 -
 .../SpellChecker/Spell/SuggestWordQueue.cs      |   37 -
 .../SpellChecker/Spell/TRStringDistance.cs      |  135 -
 src/contrib/WordNet/ABOUT.txt                   |    1 -
 src/contrib/WordNet/HISTORY.txt                 |    6 -
 src/contrib/WordNet/Package.html                |   49 -
 src/contrib/WordNet/README.txt                  |    5 -
 src/contrib/WordNet/SynExpand/App.ico           |  Bin 1078 -> 0 bytes
 src/contrib/WordNet/SynExpand/AssemblyInfo.cs   |   86 -
 .../SynExpand/Contrib.WordNet.SynExpand.csproj  |  205 --
 src/contrib/WordNet/SynExpand/SynExpand.cs      |  194 --
 src/contrib/WordNet/SynLookup/App.ico           |  Bin 1078 -> 0 bytes
 src/contrib/WordNet/SynLookup/AssemblyInfo.cs   |   86 -
 .../SynLookup/Contrib.WordNet.SynLookup.csproj  |  205 --
 src/contrib/WordNet/SynLookup/SynLookup.cs      |  208 --
 src/contrib/WordNet/Syns2Index/App.ico          |  Bin 1078 -> 0 bytes
 src/contrib/WordNet/Syns2Index/AssemblyInfo.cs  |   86 -
 .../Contrib.WordNet.Syns2Index.csproj           |  205 --
 src/contrib/WordNet/Syns2Index/Syns2Index.cs    |  292 --
 291 files changed, 72146 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/AR/ArabicAnalyzer.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/AR/ArabicAnalyzer.cs b/src/contrib/Analyzers/AR/ArabicAnalyzer.cs
deleted file mode 100644
index 88e9736..0000000
--- a/src/contrib/Analyzers/AR/ArabicAnalyzer.cs
+++ /dev/null
@@ -1,207 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System;
-using System.Collections.Generic;
-using System.IO;
-using System.Collections;
-using System.Linq;
-using Lucene.Net.Analysis;
-using Version = Lucene.Net.Util.Version;
-using Lucene.Net.Support.Compatibility;
-
-namespace Lucene.Net.Analysis.AR
-{
-    /*
-     * <see cref="Analyzer"/> for Arabic. 
-     * <p/>
-     * This analyzer implements light-stemming as specified by:
-     * <i>
-     * Light Stemming for Arabic Information Retrieval
-     * </i>    
-     * http://www.mtholyoke.edu/~lballest/Pubs/arab_stem05.pdf
-     * <p/>
-     * The analysis package contains three primary components:
-     * <ul>
-     *  <li><see cref="ArabicNormalizationFilter"/>: Arabic orthographic normalization.</li>
-     *  <li><see cref="ArabicStemFilter"/>: Arabic light stemming</li>
-     *  <li>Arabic stop words file: a set of default Arabic stop words.</li>
-     * </ul>
-     * 
-     */
-    public class ArabicAnalyzer : Analyzer
-    {
-
-        /*
-         * 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.
-         */
-        public static string DEFAULT_STOPWORD_FILE = "ArabicStopWords.txt";
-
-        /*
-         * Contains the stopwords used with the StopFilter.
-         */
-        private readonly ISet<string> stoptable;
-        /*<summary>
-         * The comment character in the stopwords file.  All lines prefixed with this will be ignored  
-         * </summary>
-         */
-        [Obsolete("Use WordListLoader.GetWordSet(FileInfo, string) directly")]
-        public static string STOPWORDS_COMMENT = "#";
-
-        /// <summary>
-        /// Returns an unmodifiable instance of the default stop-words set
-        /// </summary>
-        /// <returns>Returns an unmodifiable instance of the default stop-words set</returns>
-        public static ISet<string>  GetDefaultStopSet()
-        {
-            return DefaultSetHolder.DEFAULT_STOP_SET;
-        }
-
-        private static class DefaultSetHolder
-        {
-            internal static ISet<string> DEFAULT_STOP_SET;
-
-            static DefaultSetHolder()
-            {
-                try
-                {
-                    DEFAULT_STOP_SET = LoadDefaultStopWordSet();
-                }
-                catch (System.IO.IOException)
-                {
-                    // default set should always be present as it is part of the
-                    // distribution (JAR)
-                    throw new Exception("Unable to load default stopword set");
-                }
-            }
-
-            internal static ISet<string> LoadDefaultStopWordSet()
-            {
-                using (StreamReader reader = new StreamReader(System.Reflection.Assembly.GetAssembly(typeof(ArabicAnalyzer)).GetManifestResourceStream("Lucene.Net.Analysis.AR." + DEFAULT_STOPWORD_FILE)))
-                {
-                    return CharArraySet.UnmodifiableSet(CharArraySet.Copy(WordlistLoader.GetWordSet(reader, STOPWORDS_COMMENT)));
-                }
-            }
-        }
-
-        private Version matchVersion;
-
-        /*
-         * Builds an analyzer with the default stop words: <see cref="DEFAULT_STOPWORD_FILE"/>.
-         */
-        public ArabicAnalyzer(Version matchVersion)
-            : this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET)
-        {
-        }
-
-        /// <summary>
-        /// Builds an analyzer with the given stop words.
-        /// </summary>
-        /// <param name="matchVersion">Lucene compatibility version</param>
-        /// <param name="stopwords">a stopword set</param>
-        public ArabicAnalyzer(Version matchVersion, ISet<string> stopwords)
-        {
-            stoptable = CharArraySet.UnmodifiableSet(CharArraySet.Copy(stopwords));
-            this.matchVersion = matchVersion;
-        }
-
-        /*
-         * Builds an analyzer with the given stop words.
-         */
-        [Obsolete("Use ArabicAnalyzer(Version, Set) instead")]
-        public ArabicAnalyzer(Version matchVersion, params string[] stopwords)
-            : this(matchVersion, StopFilter.MakeStopSet(stopwords))
-        {
-        }
-
-        /*
-         * Builds an analyzer with the given stop words.
-         */
-        [Obsolete("Use ArabicAnalyzer(Version, Set) instead")]
-        public ArabicAnalyzer(Version matchVersion, IDictionary<string, string> stopwords)
-            : this(matchVersion, stopwords.Keys.ToArray())
-        {
-        }
-
-        /*
-         * Builds an analyzer with the given stop words.  Lines can be commented out using <see cref="STOPWORDS_COMMENT"/>
-         */
-        public ArabicAnalyzer(Version matchVersion, FileInfo stopwords)
-            : this(matchVersion, WordlistLoader.GetWordSet(stopwords, STOPWORDS_COMMENT))
-        {
-        }
-
-
-        /*
-         * Creates a <see cref="TokenStream"/> which tokenizes all the text in the provided <see cref="TextReader"/>.
-         *
-         * <returns>A <see cref="TokenStream"/> built from an <see cref="ArabicLetterTokenizer"/> filtered with
-         *             <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/>, <see cref="ArabicNormalizationFilter"/>
-         *            and <see cref="ArabicStemFilter"/>.</returns>
-         */
-        public override TokenStream TokenStream(string fieldName, TextReader reader)
-        {
-            TokenStream result = new ArabicLetterTokenizer(reader);
-            result = new LowerCaseFilter(result);
-            // the order here is important: the stopword list is not normalized!
-            result = new StopFilter(StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion), result, stoptable);
-            result = new ArabicNormalizationFilter(result);
-            result = new ArabicStemFilter(result);
-
-            return result;
-        }
-
-        private class SavedStreams
-        {
-            internal Tokenizer Source;
-            internal TokenStream Result;
-        };
-
-        /*
-         * Returns a (possibly reused) <see cref="TokenStream"/> which tokenizes all the text 
-         * in the provided <see cref="TextReader"/>.
-         *
-         * <returns>A <see cref="TokenStream"/> built from an <see cref="ArabicLetterTokenizer"/> filtered with
-         *            <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/>, <see cref="ArabicNormalizationFilter"/>
-         *            and <see cref="ArabicStemFilter"/>.</returns>
-         */
-        public override TokenStream ReusableTokenStream(string fieldName, TextReader reader)
-        {
-            SavedStreams streams = (SavedStreams)PreviousTokenStream;
-            if (streams == null)
-            {
-                streams = new SavedStreams();
-                streams.Source = new ArabicLetterTokenizer(reader);
-                streams.Result = new LowerCaseFilter(streams.Source);
-                // the order here is important: the stopword list is not normalized!
-                streams.Result = new StopFilter(StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion),
-                                                streams.Result, stoptable);
-                streams.Result = new ArabicNormalizationFilter(streams.Result);
-                streams.Result = new ArabicStemFilter(streams.Result);
-                PreviousTokenStream = streams;
-            }
-            else
-            {
-                streams.Source.Reset(reader);
-            }
-            return streams.Result;
-        }
-    }
-}
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/AR/ArabicLetterTokenizer.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/AR/ArabicLetterTokenizer.cs b/src/contrib/Analyzers/AR/ArabicLetterTokenizer.cs
deleted file mode 100644
index 780d8aa..0000000
--- a/src/contrib/Analyzers/AR/ArabicLetterTokenizer.cs
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System.IO;
-using System.Collections;
-
-using Lucene.Net.Analysis;
-using Lucene.Net.Util;
-
-namespace Lucene.Net.Analysis.AR
-{
-
-    /*
-     * 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>
-     *
-     */
-    public class ArabicLetterTokenizer : LetterTokenizer
-    {
-
-        public ArabicLetterTokenizer(TextReader @in): base(@in)
-        {
-            
-        }
-
-        public ArabicLetterTokenizer(AttributeSource source, TextReader @in) : base(source, @in)
-        {
-            
-        }
-
-        public ArabicLetterTokenizer(AttributeFactory factory, TextReader @in) : base(factory, @in)
-        {
-            
-        }
-
-        /* 
-         * Allows for Letter category or NonspacingMark category
-         * <see cref="LetterTokenizer.IsTokenChar(char)"/>
-         */
-        protected override bool IsTokenChar(char c)
-        {
-            return base.IsTokenChar(c) || char.GetUnicodeCategory(c)==System.Globalization.UnicodeCategory.NonSpacingMark ;
-        }
-
-    }
-}
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/AR/ArabicNormalizationFilter.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/AR/ArabicNormalizationFilter.cs b/src/contrib/Analyzers/AR/ArabicNormalizationFilter.cs
deleted file mode 100644
index 28b7044..0000000
--- a/src/contrib/Analyzers/AR/ArabicNormalizationFilter.cs
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System.IO;
-using System.Collections;
-
-using Lucene.Net.Analysis;
-using Lucene.Net.Analysis.Tokenattributes;
-using Lucene.Net.Util;
-
-
-namespace Lucene.Net.Analysis.AR
-{
-
-    /*
-     * A <see cref="TokenFilter"/> that applies <see cref="ArabicNormalizer"/> to normalize the orthography.
-     * 
-     */
-
-    public class ArabicNormalizationFilter : TokenFilter
-    {
-
-        protected ArabicNormalizer normalizer = null;
-        private ITermAttribute termAtt;
-
-        public ArabicNormalizationFilter(TokenStream input) : base(input)
-        {
-            
-            normalizer = new ArabicNormalizer();
-            termAtt = AddAttribute<ITermAttribute>();
-        }
-
-        public override bool IncrementToken()
-        {
-            if (input.IncrementToken())
-            {
-                int newlen = normalizer.Normalize(termAtt.TermBuffer(), termAtt.TermLength());
-                termAtt.SetTermLength(newlen);
-                return true;
-            }
-            return false;
-        }
-    }
-}

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/AR/ArabicNormalizer.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/AR/ArabicNormalizer.cs b/src/contrib/Analyzers/AR/ArabicNormalizer.cs
deleted file mode 100644
index da8c8af..0000000
--- a/src/contrib/Analyzers/AR/ArabicNormalizer.cs
+++ /dev/null
@@ -1,130 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System;
-using System.IO;
-using System.Collections;
-
-using Lucene.Net.Analysis;
-using Lucene.Net.Analysis.Tokenattributes;
-using Lucene.Net.Util;
-
-
-namespace Lucene.Net.Analysis.AR
-{
-    /*
-     *  Normalizer for Arabic.
-     *  <p/>
-     *  Normalization is done in-place for efficiency, operating on a termbuffer.
-     *  <p/>
-     *  Normalization is defined as:
-     *  <ul>
-     *  <li> Normalization of hamza with alef seat to a bare alef.</li>
-     *  <li> Normalization of teh marbuta to heh</li>
-     *  <li> Normalization of dotless yeh (alef maksura) to yeh.</li>
-     *  <li> Removal of Arabic diacritics (the harakat)</li>
-     *  <li> Removal of tatweel (stretching character).</li>
-     * </ul>
-     *
-     */
-    public class ArabicNormalizer
-    {
-        public const char ALEF = '\u0627';
-        public const char ALEF_MADDA = '\u0622';
-        public const char ALEF_HAMZA_ABOVE = '\u0623';
-        public const char ALEF_HAMZA_BELOW = '\u0625';
-
-        public const char YEH = '\u064A';
-        public const char DOTLESS_YEH = '\u0649';
-
-        public const char TEH_MARBUTA = '\u0629';
-        public const char HEH = '\u0647';
-
-        public const char TATWEEL = '\u0640';
-
-        public const char FATHATAN = '\u064B';
-        public const char DAMMATAN = '\u064C';
-        public const char KASRATAN = '\u064D';
-        public const char FATHA = '\u064E';
-        public const char DAMMA = '\u064F';
-        public const char KASRA = '\u0650';
-        public const char SHADDA = '\u0651';
-        public const char SUKUN = '\u0652';
-
-        /*
-         * Normalize an input buffer of Arabic text
-         * 
-         * <param name="s">input buffer</param>
-         * <param name="len">length of input buffer</param>
-         * <returns>length of input buffer after normalization</returns>
-         */
-        public int Normalize(char[] s, int len)
-        {
-
-            for (int i = 0; i < len; i++)
-            {
-                switch (s[i])
-                {
-                    case ALEF_MADDA:
-                    case ALEF_HAMZA_ABOVE:
-                    case ALEF_HAMZA_BELOW:
-                        s[i] = ALEF;
-                        break;
-                    case DOTLESS_YEH:
-                        s[i] = YEH;
-                        break;
-                    case TEH_MARBUTA:
-                        s[i] = HEH;
-                        break;
-                    case TATWEEL:
-                    case KASRATAN:
-                    case DAMMATAN:
-                    case FATHATAN:
-                    case FATHA:
-                    case DAMMA:
-                    case KASRA:
-                    case SHADDA:
-                    case SUKUN:
-                        len = Delete(s, i, len);
-                        i--;
-                        break;
-                    default:
-                        break;
-                }
-            }
-
-            return len;
-        }
-
-        /*
-         * Delete a character in-place
-         * 
-         * <param name="s">Input Buffer</param>
-         * <param name="pos">Position of character to delete</param>
-         * <param name="len">length of input buffer</param>
-         * <returns>length of input buffer after deletion</returns>
-         */
-        protected int Delete(char[] s, int pos, int len)
-        {
-            if (pos < len)
-                Array.Copy(s, pos + 1, s, pos, len - pos - 1); 
-
-            return len - 1;
-        }
-
-    }
-}
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/AR/ArabicStemFilter.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/AR/ArabicStemFilter.cs b/src/contrib/Analyzers/AR/ArabicStemFilter.cs
deleted file mode 100644
index b3e89c1..0000000
--- a/src/contrib/Analyzers/AR/ArabicStemFilter.cs
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System;
-using System.IO;
-using System.Collections;
-
-using Lucene.Net.Analysis;
-using Lucene.Net.Analysis.Tokenattributes;
-using Lucene.Net.Util;
-
-
-namespace Lucene.Net.Analysis.AR
-{
-
-
-    /*
-     * A <see cref="TokenFilter"/> that applies <see cref="ArabicStemmer"/> to stem Arabic words..
-     * 
-     */
-
-    public class ArabicStemFilter : TokenFilter
-    {
-
-        private readonly ArabicStemmer stemmer;
-        private readonly ITermAttribute termAtt;
-
-        public ArabicStemFilter(TokenStream input) : base(input)
-        {
-            stemmer = new ArabicStemmer();
-            termAtt = AddAttribute<ITermAttribute>();
-        }
-
-        public override bool IncrementToken()
-        {
-            if (input.IncrementToken())
-            {
-                int newlen = stemmer.Stem(termAtt.TermBuffer(), termAtt.TermLength());
-                termAtt.SetTermLength(newlen);
-                return true;
-            }
-            else
-            {
-                return false;
-            }
-        }
-    }
-}
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/AR/ArabicStemmer.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/AR/ArabicStemmer.cs b/src/contrib/Analyzers/AR/ArabicStemmer.cs
deleted file mode 100644
index 7ee08bb..0000000
--- a/src/contrib/Analyzers/AR/ArabicStemmer.cs
+++ /dev/null
@@ -1,208 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System;
-using System.IO;
-using System.Collections;
-
-using Lucene.Net.Analysis;
-using Lucene.Net.Analysis.Tokenattributes;
-using Lucene.Net.Util;
-
-
-namespace Lucene.Net.Analysis.AR
-{
-
-
-    /*
-     *  Stemmer for Arabic.
-     *  <p/>
-     *  Stemming  is done in-place for efficiency, operating on a termbuffer.
-     *  <p/>
-     *  Stemming is defined as:
-     *  <ul>
-     *  <li> Removal of attached definite article, conjunction, and prepositions.</li>
-     *  <li> Stemming of common suffixes.</li>
-     * </ul>
-     *
-     */
-    public class ArabicStemmer
-    {
-        public const char ALEF = '\u0627';
-        public const char BEH = '\u0628';
-        public const char TEH_MARBUTA = '\u0629';
-        public const char TEH = '\u062A';
-        public const char FEH = '\u0641';
-        public const char KAF = '\u0643';
-        public const char LAM = '\u0644';
-        public const char NOON = '\u0646';
-        public const char HEH = '\u0647';
-        public const char WAW = '\u0648';
-        public const char YEH = '\u064A';
-
-        public static readonly char[][] prefixes = {
-            ("" + ALEF + LAM).ToCharArray(), 
-            ("" + WAW + ALEF + LAM).ToCharArray(), 
-            ("" + BEH + ALEF + LAM).ToCharArray(),
-            ("" + KAF + ALEF + LAM).ToCharArray(),
-            ("" + FEH + ALEF + LAM).ToCharArray(),
-            ("" + LAM + LAM).ToCharArray(),
-            ("" + WAW).ToCharArray(),
-        };
-
-        public static readonly char[][] suffixes = {
-            ("" + HEH + ALEF).ToCharArray(), 
-            ("" + ALEF + NOON).ToCharArray(), 
-            ("" + ALEF + TEH).ToCharArray(), 
-            ("" + WAW + NOON).ToCharArray(), 
-            ("" + YEH + NOON).ToCharArray(), 
-            ("" + YEH + HEH).ToCharArray(),
-            ("" + YEH + TEH_MARBUTA).ToCharArray(),
-            ("" + HEH).ToCharArray(),
-            ("" + TEH_MARBUTA).ToCharArray(),
-            ("" + YEH).ToCharArray(),
-        };
-
-
-        /*
-         * Stem an input buffer of Arabic text.
-         * 
-         * <param name="s">input buffer</param>
-         * <param name="len">length of input buffer</param>
-         * <returns>length of input buffer after normalization</returns>
-         */
-        public int Stem(char[] s, int len)
-        {
-            len = StemPrefix(s, len);
-            len = StemSuffix(s, len);
-
-            return len;
-        }
-
-        /*
-         * Stem a prefix off an Arabic word.
-         * <param name="s">input buffer</param>
-         * <param name="len">length of input buffer</param>
-         * <returns>new length of input buffer after stemming.</returns>
-         */
-        public int StemPrefix(char[] s, int len)
-        {
-            for (int i = 0; i < prefixes.Length; i++)
-                if (StartsWith(s, len, prefixes[i]))
-                    return DeleteN(s, 0, len, prefixes[i].Length);
-            return len;
-        }
-
-        /*
-         * Stem suffix(es) off an Arabic word.
-         * <param name="s">input buffer</param>
-         * <param name="len">length of input buffer</param>
-         * <returns>new length of input buffer after stemming</returns>
-         */
-        public int StemSuffix(char[] s, int len)
-        {
-            for (int i = 0; i < suffixes.Length; i++)
-                if (EndsWith(s, len, suffixes[i]))
-                    len = DeleteN(s, len - suffixes[i].Length, len, suffixes[i].Length);
-            return len;
-        }
-
-        /*
-         * Returns true if the prefix matches and can be stemmed
-         * <param name="s">input buffer</param>
-         * <param name="len">length of input buffer</param>
-         * <param name="prefix">prefix to check</param>
-         * <returns>true if the prefix matches and can be stemmed</returns>
-         */
-        bool StartsWith(char[] s, int len, char[] prefix)
-        {
-            if (prefix.Length == 1 && len < 4)
-            { // wa- prefix requires at least 3 characters
-                return false;
-            }
-            else if (len < prefix.Length + 2)
-            { // other prefixes require only 2.
-                return false;
-            }
-            else
-            {
-                for (int i = 0; i < prefix.Length; i++)
-                    if (s[i] != prefix[i])
-                        return false;
-
-                return true;
-            }
-        }
-
-        /*
-         * Returns true if the suffix matches and can be stemmed
-         * <param name="s">input buffer</param>
-         * <param name="len">length of input buffer</param>
-         * <param name="suffix">suffix to check</param>
-         * <returns>true if the suffix matches and can be stemmed</returns>
-         */
-        bool EndsWith(char[] s, int len, char[] suffix)
-        {
-            if (len < suffix.Length + 2)
-            { // all suffixes require at least 2 characters after stemming
-                return false;
-            }
-            else
-            {
-                for (int i = 0; i < suffix.Length; i++)
-                    if (s[len - suffix.Length + i] != suffix[i])
-                        return false;
-
-                return true;
-            }
-        }
-
-
-        /*
-         * Delete n characters in-place
-         * 
-         * <param name="s">Input Buffer</param>
-         * <param name="pos">Position of character to delete</param>
-         * <param name="len">Length of input buffer</param>
-         * <param name="nChars">number of characters to delete</param>
-         * <returns>length of input buffer after deletion</returns>
-         */
-        protected int DeleteN(char[] s, int pos, int len, int nChars)
-        {
-            for (int i = 0; i < nChars; i++)
-                len = Delete(s, pos, len);
-            return len;
-        }
-
-        /*
-         * Delete a character in-place
-         * 
-         * <param name="s">Input Buffer</param>
-         * <param name="pos">Position of character to delete</param>
-         * <param name="len">length of input buffer</param>
-         * <returns>length of input buffer after deletion</returns>
-         */
-        protected int Delete(char[] s, int pos, int len)
-        {
-            if (pos < len)
-                Array.Copy(s, pos + 1, s, pos, len - pos - 1); 
-
-            return len - 1;
-        }
-
-    }
-}
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/AR/ArabicStopWords.txt
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/AR/ArabicStopWords.txt b/src/contrib/Analyzers/AR/ArabicStopWords.txt
deleted file mode 100644
index b7d2956..0000000
--- a/src/contrib/Analyzers/AR/ArabicStopWords.txt
+++ /dev/null
@@ -1,162 +0,0 @@
-ب
-ا
-أ
-،
-عشر
-عدد
-عدة
-عشرة
-عدم
-عام
-عاما
-عن
-عند
-عندما
-على
-عليه
-عليها
-زيارة
-سنة
-سنوات
-تم
-ضد
-بعد
-بعض
-اعادة
-اعلنت
-بسبب
-حتى
-اذا
-احد
-اثر
-برس
-باسم
-غدا
-شخصا
-صباح
-اطار
-اربعة
-اخرى
-بان
-اجل
-غير
-بشكل
-حاليا
-بن
-به
-ثم
-اف
-ان
-او
-اي
-بها
-صفر
-حيث
-اكد
-الا
-اما
-امس
-السابق
-التى
-التي
-اكثر
-ايار
-ايضا
-ثلاثة
-الذاتي
-الاخيرة
-الثاني
-الثانية
-الذى
-الذي
-الان
-امام
-ايام
-خلال
-حوالى
-الذين
-الاول
-الاولى
-بين
-ذلك
-دون
-حول
-حين
-الف
-الى
-انه
-اول
-ضمن
-انها
-جميع
-الماضي
-الوقت
-المقبل
-اليوم
-ـ
-ف
-و
-و6
-قد
-لا
-ما
-مع
-مساء
-هذا
-واحد
-واضاف
-واضافت
-فان
-قبل
-قال
-كان
-لدى
-نحو
-هذه
-وان
-واكد
-كانت
-واوضح
-مايو
-فى
-في
-كل
-لم
-لن
-له
-من
-هو
-هي
-قوة
-كما
-لها
-منذ
-وقد
-ولا
-نفسه
-لقاء
-مقابل
-هناك
-وقال
-وكان
-نهاية
-وقالت
-وكانت
-للامم
-فيه
-كلم
-لكن
-وفي
-وقف
-ولم
-ومن
-وهو
-وهي
-يوم
-فيها
-منها
-مليار
-لوكالة
-يكون
-يمكن
-مليون

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/BR/BrazilianAnalyzer.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/BR/BrazilianAnalyzer.cs b/src/contrib/Analyzers/BR/BrazilianAnalyzer.cs
deleted file mode 100644
index 6e6ee25..0000000
--- a/src/contrib/Analyzers/BR/BrazilianAnalyzer.cs
+++ /dev/null
@@ -1,249 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System;
-using System.Collections;
-using System.Collections.Generic;
-using System.Linq;
-using Lucene.Net.Analysis;
-using Lucene.Net.Analysis.Standard;
-using System.IO;
-using Version = Lucene.Net.Util.Version;
-
-/*
- * Analyzer for Brazilian 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).
- *
- */
-namespace Lucene.Net.Analysis.BR
-{
-    public sealed class BrazilianAnalyzer : Analyzer
-    {
-        /*
-         * List of typical Brazilian stopwords.
-         */
-        //TODO: Make this private in 3.1
-        public static string[] BRAZILIAN_STOP_WORDS = {
-                                                          "a", "ainda", "alem", "ambas", "ambos", "antes",
-                                                          "ao", "aonde", "aos", "apos", "aquele", "aqueles",
-                                                          "as", "assim", "com", "como", "contra", "contudo",
-                                                          "cuja", "cujas", "cujo", "cujos", "da", "das", "de",
-                                                          "dela", "dele", "deles", "demais", "depois", "desde",
-                                                          "desta", "deste", "dispoe", "dispoem", "diversa",
-                                                          "diversas", "diversos", "do", "dos", "durante", "e",
-                                                          "ela", "elas", "ele", "eles", "em", "entao", "entre",
-                                                          "essa", "essas", "esse", "esses", "esta", "estas",
-                                                          "este", "estes", "ha", "isso", "isto", "logo", "mais",
-                                                          "mas", "mediante", "menos", "mesma", "mesmas", "mesmo",
-                                                          "mesmos", "na", "nas", "nao", "nas", "nem", "nesse", "neste",
-                                                          "nos", "o", "os", "ou", "outra", "outras", "outro", "outros",
-                                                          "pelas", "pelas", "pelo", "pelos", "perante", "pois", "por",
-                                                          "porque", "portanto", "proprio", "propios", "quais", "qual",
-                                                          "qualquer", "quando", "quanto", "que", "quem", "quer", "se",
-                                                          "seja", "sem", "sendo", "seu", "seus", "sob", "sobre", "sua",
-                                                          "suas", "tal", "tambem", "teu", "teus", "toda", "todas",
-                                                          "todo",
-                                                          "todos", "tua", "tuas", "tudo", "um", "uma", "umas", "uns"
-                                                      };
-
-        /// <summary>
-        /// Returns an unmodifiable instance of the default stop-words set.
-        /// </summary>
-        /// <returns>Returns an unmodifiable instance of the default stop-words set.</returns>
-        public static ISet<string> GetDefaultStopSet()
-        {
-            return DefaultSetHolder.DEFAULT_STOP_SET;
-        }
-
-        private static class DefaultSetHolder
-        {
-            internal static ISet<string> DEFAULT_STOP_SET =
-                CharArraySet.UnmodifiableSet(new CharArraySet((IEnumerable<string>)BRAZILIAN_STOP_WORDS, false));
-        }
-
-        /// <summary>
-        /// Contains the stopwords used with the StopFilter.
-        /// </summary>
-        private ISet<string> stoptable = Support.Compatibility.SetFactory.CreateHashSet<string>();
-
-        private readonly Version matchVersion;
-
-        // TODO: make this private in 3.1
-        /// <summary>
-        /// Contains words that should be indexed but not stemmed.
-        /// </summary>
-        private ISet<string> excltable = Support.Compatibility.SetFactory.CreateHashSet<string>();
-
-        public BrazilianAnalyzer(Version matchVersion)
-            : this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET)
-        {
-        }
-
-        /*
-           * Builds an analyzer with the given stop words
-           * 
-           * @param matchVersion
-           *          lucene compatibility version
-           * @param stopwords
-           *          a stopword set
-           */
-
-        public BrazilianAnalyzer(Version matchVersion, ISet<string> stopwords)
-        {
-            stoptable = CharArraySet.UnmodifiableSet(CharArraySet.Copy(stopwords));
-            this.matchVersion = matchVersion;
-        }
-
-        /*
-         * Builds an analyzer with the given stop words and stemming exclusion words
-         * 
-         * @param matchVersion
-         *          lucene compatibility version
-         * @param stopwords
-         *          a stopword set
-         */
-
-        public BrazilianAnalyzer(Version matchVersion, ISet<string> stopwords,
-                                 ISet<string> stemExclusionSet)
-            : this(matchVersion, stopwords)
-        {
-
-            excltable = CharArraySet.UnmodifiableSet(CharArraySet
-                                                         .Copy(stemExclusionSet));
-        }
-
-        /*
-         * Builds an analyzer with the given stop words.
-         * @deprecated use {@link #BrazilianAnalyzer(Version, Set)} instead
-         */
-
-        public BrazilianAnalyzer(Version matchVersion, params string[] stopwords)
-            : this(matchVersion, StopFilter.MakeStopSet(stopwords))
-        {
-
-        }
-
-        /*
-   * Builds an analyzer with the given stop words. 
-   * @deprecated use {@link #BrazilianAnalyzer(Version, Set)} instead
-   */
-
-        public BrazilianAnalyzer(Version matchVersion, IDictionary<string, string> stopwords)
-            : this(matchVersion, stopwords.Keys.ToArray())
-        {
-
-        }
-
-        /*
-   * Builds an analyzer with the given stop words.
-   * @deprecated use {@link #BrazilianAnalyzer(Version, Set)} instead
-   */
-
-        public BrazilianAnalyzer(Version matchVersion, FileInfo stopwords)
-            : this(matchVersion, WordlistLoader.GetWordSet(stopwords))
-        {
-        }
-
-        /*
-         * Builds an exclusionlist from an array of Strings.
-         * @deprecated use {@link #BrazilianAnalyzer(Version, Set, Set)} instead
-         */
-
-        public void SetStemExclusionTable(params string[] exclusionlist)
-        {
-            excltable = StopFilter.MakeStopSet(exclusionlist);
-            PreviousTokenStream = null; // force a new stemmer to be created
-        }
-
-        /*
-         * Builds an exclusionlist from a {@link Map}.
-         * @deprecated use {@link #BrazilianAnalyzer(Version, Set, Set)} instead
-         */
-
-        public void SetStemExclusionTable(IDictionary<string, string> exclusionlist)
-        {
-            excltable = Support.Compatibility.SetFactory.CreateHashSet(exclusionlist.Keys);
-            PreviousTokenStream = null; // force a new stemmer to be created
-        }
-
-        /*
-         * Builds an exclusionlist from the words contained in the given file.
-         * @deprecated use {@link #BrazilianAnalyzer(Version, Set, Set)} instead
-         */
-
-        public void SetStemExclusionTable(FileInfo exclusionlist)
-        {
-            excltable = WordlistLoader.GetWordSet(exclusionlist);
-            PreviousTokenStream = null; // force a new stemmer to be created
-        }
-
-        /*
-         * Creates a {@link TokenStream} which tokenizes all the text in the provided {@link Reader}.
-         *
-         * @return  A {@link TokenStream} built from a {@link StandardTokenizer} filtered with
-         *             {@link LowerCaseFilter}, {@link StandardFilter}, {@link StopFilter}, and 
-         *          {@link BrazilianStemFilter}.
-         */
-        public override TokenStream TokenStream(String fieldName, TextReader reader)
-        {
-            TokenStream result = new StandardTokenizer(matchVersion, reader);
-            result = new LowerCaseFilter(result);
-            result = new StandardFilter(result);
-            result = new StopFilter(StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion),
-                                    result, stoptable);
-            result = new BrazilianStemFilter(result, excltable);
-            return result;
-        }
-
-        private class SavedStreams
-        {
-            protected internal Tokenizer source;
-            protected internal TokenStream result;
-        };
-
-        /*
-         * Returns a (possibly reused) {@link TokenStream} which tokenizes all the text 
-         * in the provided {@link Reader}.
-         *
-         * @return  A {@link TokenStream} built from a {@link StandardTokenizer} filtered with
-         *          {@link LowerCaseFilter}, {@link StandardFilter}, {@link StopFilter}, and 
-         *          {@link BrazilianStemFilter}.
-         */
-
-        public override TokenStream ReusableTokenStream(String fieldName, TextReader reader)
-        {
-            SavedStreams streams = (SavedStreams) PreviousTokenStream;
-            if (streams == null)
-            {
-                streams = new SavedStreams();
-                streams.source = new StandardTokenizer(matchVersion, reader);
-                streams.result = new LowerCaseFilter(streams.source);
-                streams.result = new StandardFilter(streams.result);
-                streams.result = new StopFilter(StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion),
-                                                streams.result, stoptable);
-                streams.result = new BrazilianStemFilter(streams.result, excltable);
-                PreviousTokenStream = streams;
-            }
-            else
-            {
-                streams.source.Reset(reader);
-            }
-            return streams.result;
-        }
-    }
-}

http://git-wip-us.apache.org/repos/asf/lucenenet/blob/02362804/src/contrib/Analyzers/BR/BrazilianStemFilter.cs
----------------------------------------------------------------------
diff --git a/src/contrib/Analyzers/BR/BrazilianStemFilter.cs b/src/contrib/Analyzers/BR/BrazilianStemFilter.cs
deleted file mode 100644
index 892e5ab..0000000
--- a/src/contrib/Analyzers/BR/BrazilianStemFilter.cs
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements.  See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-using System.Collections.Generic;
-using Lucene.Net.Analysis;
-using System.Collections;
-using Lucene.Net.Analysis.Tokenattributes;
-using Version = Lucene.Net.Util.Version;
-
-
-/*
- * Based on GermanStemFilter
- *
- */
-namespace Lucene.Net.Analysis.BR
-{
-
-    public sealed class BrazilianStemFilter : TokenFilter
-    {
-
-        /*
-         * The actual token in the input stream.
-         */
-        private BrazilianStemmer stemmer = null;
-        private ISet<string> exclusions = null;
-        private ITermAttribute termAtt;
-
-        public BrazilianStemFilter(TokenStream input)
-            : base(input)
-        {
-            stemmer = new BrazilianStemmer();
-            termAtt = AddAttribute<ITermAttribute>();
-        }
-
-        public BrazilianStemFilter(TokenStream input, ISet<string> exclusiontable)
-            : this(input)
-        {
-            this.exclusions = exclusiontable;
-        }
-
-        /*
-         * <returns>Returns the next token in the stream, or null at EOS.</returns>
-         */
-        public override bool IncrementToken()
-        {
-            if (input.IncrementToken())
-            {
-                string term = termAtt.Term;
-                // Check the exclusion table.
-                if (exclusions == null || !exclusions.Contains(term))
-                {
-                    string s = stemmer.Stem(term);
-                    // If not stemmed, don't waste the time adjusting the token.
-                    if ((s != null) && !s.Equals(term))
-                        termAtt.SetTermBuffer(s);
-                }
-                return true;
-            }
-            else
-            {
-                return false;
-            }
-        }
-    }
-}


Mime
View raw message