You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucenenet.apache.org by sy...@apache.org on 2015/01/25 14:46:36 UTC
[2/2] lucenenet git commit: More porting work
More porting work
Project: http://git-wip-us.apache.org/repos/asf/lucenenet/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucenenet/commit/56bfeaab
Tree: http://git-wip-us.apache.org/repos/asf/lucenenet/tree/56bfeaab
Diff: http://git-wip-us.apache.org/repos/asf/lucenenet/diff/56bfeaab
Branch: refs/heads/master
Commit: 56bfeaab22154916e96433eb91572f26d04d1ef2
Parents: 1b806eb
Author: Itamar Syn-Hershko <it...@code972.com>
Authored: Sun Jan 25 15:46:16 2015 +0200
Committer: Itamar Syn-Hershko <it...@code972.com>
Committed: Sun Jan 25 15:46:16 2015 +0200
----------------------------------------------------------------------
.../CodepointCountFilterFactory.cs | 13 +-
.../Analysis/Miscellaneous/EmptyTokenStream.cs | 6 +-
.../Miscellaneous/HyphenatedWordsFilter.cs | 311 ++++++-----
.../HyphenatedWordsFilterFactory.cs | 11 +-
.../Analysis/Miscellaneous/KeepWordFilter.cs | 5 +-
.../Miscellaneous/KeywordMarkerFilter.cs | 114 ++--
.../Analysis/Miscellaneous/LengthFilter.cs | 20 +-
.../Miscellaneous/LengthFilterFactory.cs | 1 +
.../Analysis/Miscellaneous/PatternAnalyzer.cs | 13 +-
.../Miscellaneous/PatternKeywordMarkerFilter.cs | 4 +-
.../Analysis/Path/PathHierarchyTokenizer.cs | 476 ++++++++---------
.../Path/PathHierarchyTokenizerFactory.cs | 191 ++++---
.../Path/ReversePathHierarchyTokenizer.cs | 421 +++++++--------
.../Analysis/Position/PositionFilterFactory.cs | 7 +-
.../Analysis/Query/QueryAutoStopWordAnalyzer.cs | 10 +-
.../Analysis/Sinks/DateRecognizerSinkFilter.cs | 17 +-
.../Analysis/Sinks/TeeSinkTokenFilter.cs | 521 +++++++++----------
.../Analysis/Sinks/TokenRangeSinkFilter.cs | 127 +++--
.../Analysis/Sinks/TokenTypeSinkFilter.cs | 91 ++--
.../Analysis/Standard/ClassicTokenizerImpl.cs | 16 +-
.../Analysis/Standard/StandardAnalyzer.cs | 11 +-
.../Analysis/Synonym/FSTSynonymFilterFactory.cs | 335 ++++++------
.../Analysis/Util/AbstractAnalysisFactory.cs | 30 +-
.../Analysis/Util/CharArrayMap.cs | 23 +-
.../Analysis/Util/CharArraySet.cs | 17 +-
.../Support/Compatibility/Collections.cs | 7 +
src/Lucene.Net.Core/Util/Version.cs | 2 +-
27 files changed, 1365 insertions(+), 1435 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/CodepointCountFilterFactory.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/CodepointCountFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/CodepointCountFilterFactory.cs
index e85fd1e..bb37bd1 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/CodepointCountFilterFactory.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/CodepointCountFilterFactory.cs
@@ -1,7 +1,8 @@
using System.Collections.Generic;
-using TokenFilterFactory = Lucene.Net.Analysis.Util.TokenFilterFactory;
+using Lucene.Net.Analysis.Util;
+using org.apache.lucene.analysis.miscellaneous;
-namespace org.apache.lucene.analysis.miscellaneous
+namespace Lucene.Net.Analysis.Miscellaneous
{
/*
@@ -20,10 +21,7 @@ namespace org.apache.lucene.analysis.miscellaneous
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-
- using TokenFilterFactory = TokenFilterFactory;
-
- /// <summary>
+ /// <summary>
/// Factory for <seealso cref="CodepointCountFilter"/>.
/// <pre class="prettyprint">
/// <fieldType name="text_lngth" class="solr.TextField" positionIncrementGap="100">
@@ -52,10 +50,9 @@ namespace org.apache.lucene.analysis.miscellaneous
}
}
- public override CodepointCountFilter create(TokenStream input)
+ public override CodepointCountFilter Create(TokenStream input)
{
return new CodepointCountFilter(luceneMatchVersion, input, min, max);
}
}
-
}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/EmptyTokenStream.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/EmptyTokenStream.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/EmptyTokenStream.cs
index 38af481..ef84806 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/EmptyTokenStream.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/EmptyTokenStream.cs
@@ -1,4 +1,4 @@
-namespace org.apache.lucene.analysis.miscellaneous
+namespace Lucene.Net.Analysis.Miscellaneous
{
/*
@@ -24,11 +24,9 @@
public sealed class EmptyTokenStream : TokenStream
{
- public override bool incrementToken()
+ public override bool IncrementToken()
{
return false;
}
-
}
-
}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilter.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilter.cs
index 96a2dfa..022ee31 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilter.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilter.cs
@@ -1,164 +1,159 @@
using System.Text;
+using Lucene.Net.Analysis.Tokenattributes;
-namespace org.apache.lucene.analysis.miscellaneous
+namespace Lucene.Net.Analysis.Miscellaneous
{
- /*
- * 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 org.apache.lucene.analysis;
- using OffsetAttribute = org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
- using CharTermAttribute = org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
-
- /// <summary>
- /// When the plain text is extracted from documents, we will often have many words hyphenated and broken into
- /// two lines. This is often the case with documents where narrow text columns are used, such as newsletters.
- /// In order to increase search efficiency, this filter puts hyphenated words broken into two lines back together.
- /// This filter should be used on indexing time only.
- /// Example field definition in schema.xml:
- /// <pre class="prettyprint">
- /// <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
- /// <analyzer type="index">
- /// <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- /// <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- /// <filter class="solr.StopFilterFactory" ignoreCase="true"/>
- /// <filter class="solr.HyphenatedWordsFilterFactory"/>
- /// <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- /// <filter class="solr.LowerCaseFilterFactory"/>
- /// <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- /// </analyzer>
- /// <analyzer type="query">
- /// <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- /// <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- /// <filter class="solr.StopFilterFactory" ignoreCase="true"/>
- /// <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
- /// <filter class="solr.LowerCaseFilterFactory"/>
- /// <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- /// </analyzer>
- /// </fieldtype>
- /// </pre>
- ///
- /// </summary>
- public sealed class HyphenatedWordsFilter : TokenFilter
- {
-
- private readonly CharTermAttribute termAttribute = addAttribute(typeof(CharTermAttribute));
- private readonly OffsetAttribute offsetAttribute = addAttribute(typeof(OffsetAttribute));
-
- private readonly StringBuilder hyphenated = new StringBuilder();
- private State savedState;
- private bool exhausted = false;
- private int lastEndOffset = 0;
-
- /// <summary>
- /// Creates a new HyphenatedWordsFilter
- /// </summary>
- /// <param name="in"> TokenStream that will be filtered </param>
- public HyphenatedWordsFilter(TokenStream @in) : base(@in)
- {
- }
-
- /// <summary>
- /// {@inheritDoc}
- /// </summary>
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public boolean incrementToken() throws java.io.IOException
- public override bool incrementToken()
- {
- while (!exhausted && input.incrementToken())
- {
- char[] term = termAttribute.buffer();
- int termLength = termAttribute.length();
- lastEndOffset = offsetAttribute.endOffset();
-
- if (termLength > 0 && term[termLength - 1] == '-')
- {
- // a hyphenated word
- // capture the state of the first token only
- if (savedState == null)
- {
- savedState = captureState();
- }
- hyphenated.Append(term, 0, termLength - 1);
- }
- else if (savedState == null)
- {
- // not part of a hyphenated word.
- return true;
- }
- else
- {
- // the final portion of a hyphenated word
- hyphenated.Append(term, 0, termLength);
- unhyphenate();
- return true;
- }
- }
-
- exhausted = true;
-
- if (savedState != null)
- {
- // the final term ends with a hyphen
- // add back the hyphen, for backwards compatibility.
- hyphenated.Append('-');
- unhyphenate();
- return true;
- }
-
- return false;
- }
-
- /// <summary>
- /// {@inheritDoc}
- /// </summary>
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public void reset() throws java.io.IOException
- public override void reset()
- {
- base.reset();
- hyphenated.Length = 0;
- savedState = null;
- exhausted = false;
- lastEndOffset = 0;
- }
-
- // ================================================= Helper Methods ================================================
-
- /// <summary>
- /// Writes the joined unhyphenated term
- /// </summary>
- private void unhyphenate()
- {
- restoreState(savedState);
- savedState = null;
-
- char[] term = termAttribute.buffer();
- int length = hyphenated.Length;
- if (length > termAttribute.length())
- {
- term = termAttribute.resizeBuffer(length);
- }
-
- hyphenated.getChars(0, length, term, 0);
- termAttribute.Length = length;
- offsetAttribute.setOffset(offsetAttribute.startOffset(), lastEndOffset);
- hyphenated.Length = 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.
+ */
+ /// <summary>
+ /// When the plain text is extracted from documents, we will often have many words hyphenated and broken into
+ /// two lines. This is often the case with documents where narrow text columns are used, such as newsletters.
+ /// In order to increase search efficiency, this filter puts hyphenated words broken into two lines back together.
+ /// This filter should be used on indexing time only.
+ /// Example field definition in schema.xml:
+ /// <pre class="prettyprint">
+ /// <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
+ /// <analyzer type="index">
+ /// <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ /// <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ /// <filter class="solr.StopFilterFactory" ignoreCase="true"/>
+ /// <filter class="solr.HyphenatedWordsFilterFactory"/>
+ /// <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ /// <filter class="solr.LowerCaseFilterFactory"/>
+ /// <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ /// </analyzer>
+ /// <analyzer type="query">
+ /// <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ /// <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ /// <filter class="solr.StopFilterFactory" ignoreCase="true"/>
+ /// <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ /// <filter class="solr.LowerCaseFilterFactory"/>
+ /// <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ /// </analyzer>
+ /// </fieldtype>
+ /// </pre>
+ ///
+ /// </summary>
+ public sealed class HyphenatedWordsFilter : TokenFilter
+ {
+
+ private readonly ICharTermAttribute termAttribute;
+ private readonly IOffsetAttribute offsetAttribute;
+
+ private readonly StringBuilder hyphenated = new StringBuilder();
+ private State savedState;
+ private bool exhausted = false;
+ private int lastEndOffset = 0;
+
+ /// <summary>
+ /// Creates a new HyphenatedWordsFilter
+ /// </summary>
+ /// <param name="in"> TokenStream that will be filtered </param>
+ public HyphenatedWordsFilter(TokenStream @in)
+ : base(@in)
+ {
+ termAttribute = AddAttribute<ICharTermAttribute>();
+ offsetAttribute = AddAttribute<IOffsetAttribute>();
+ }
+
+ /// <summary>
+ /// {@inheritDoc}
+ /// </summary>
+ public override bool IncrementToken()
+ {
+ while (!exhausted && input.IncrementToken())
+ {
+ char[] term = termAttribute.Buffer();
+ int termLength = termAttribute.Length;
+ lastEndOffset = offsetAttribute.EndOffset();
+
+ if (termLength > 0 && term[termLength - 1] == '-')
+ {
+ // a hyphenated word
+ // capture the state of the first token only
+ if (savedState == null)
+ {
+ savedState = CaptureState();
+ }
+ hyphenated.Append(term, 0, termLength - 1);
+ }
+ else if (savedState == null)
+ {
+ // not part of a hyphenated word.
+ return true;
+ }
+ else
+ {
+ // the final portion of a hyphenated word
+ hyphenated.Append(term, 0, termLength);
+ Unhyphenate();
+ return true;
+ }
+ }
+
+ exhausted = true;
+
+ if (savedState != null)
+ {
+ // the final term ends with a hyphen
+ // add back the hyphen, for backwards compatibility.
+ hyphenated.Append('-');
+ Unhyphenate();
+ return true;
+ }
+
+ return false;
+ }
+
+ /// <summary>
+ /// {@inheritDoc}
+ /// </summary>
+ public override void Reset()
+ {
+ base.Reset();
+ hyphenated.Length = 0;
+ savedState = null;
+ exhausted = false;
+ lastEndOffset = 0;
+ }
+
+ // ================================================= Helper Methods ================================================
+
+ /// <summary>
+ /// Writes the joined unhyphenated term
+ /// </summary>
+ private void Unhyphenate()
+ {
+ RestoreState(savedState);
+ savedState = null;
+
+ char[] term = termAttribute.Buffer();
+ int length = hyphenated.Length;
+ if (length > termAttribute.Length)
+ {
+ term = termAttribute.ResizeBuffer(length);
+ }
+
+ hyphenated.GetChars(0, length, term, 0);
+ termAttribute.Length = length;
+ offsetAttribute.SetOffset(offsetAttribute.StartOffset(), lastEndOffset);
+ hyphenated.Length = 0;
+ }
+ }
}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilterFactory.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilterFactory.cs
index 946cd57..b274564 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilterFactory.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/HyphenatedWordsFilterFactory.cs
@@ -1,7 +1,7 @@
using System.Collections.Generic;
-using TokenFilterFactory = Lucene.Net.Analysis.Util.TokenFilterFactory;
+using Lucene.Net.Analysis.Util;
-namespace org.apache.lucene.analysis.miscellaneous
+namespace Lucene.Net.Analysis.Miscellaneous
{
/*
@@ -20,10 +20,7 @@ namespace org.apache.lucene.analysis.miscellaneous
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-
- using TokenFilterFactory = TokenFilterFactory;
-
- /// <summary>
+ /// <summary>
/// Factory for <seealso cref="HyphenatedWordsFilter"/>.
/// <pre class="prettyprint">
/// <fieldType name="text_hyphn" class="solr.TextField" positionIncrementGap="100">
@@ -46,7 +43,7 @@ namespace org.apache.lucene.analysis.miscellaneous
}
}
- public override HyphenatedWordsFilter create(TokenStream input)
+ public override TokenStream Create(TokenStream input)
{
return new HyphenatedWordsFilter(input);
}
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeepWordFilter.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeepWordFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeepWordFilter.cs
index f9f9a53..b699de1 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeepWordFilter.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeepWordFilter.cs
@@ -30,7 +30,7 @@ namespace Lucene.Net.Analysis.Miscellaneous
public sealed class KeepWordFilter : FilteringTokenFilter
{
private readonly CharArraySet words;
- private readonly CharTermAttribute termAtt = addAttribute(typeof(CharTermAttribute));
+ private readonly ICharTermAttribute termAtt;
/// @deprecated enablePositionIncrements=false is not supported anymore as of Lucene 4.4.
[Obsolete("enablePositionIncrements=false is not supported anymore as of Lucene 4.4.")]
@@ -38,6 +38,7 @@ namespace Lucene.Net.Analysis.Miscellaneous
: base(version, enablePositionIncrements, @in)
{
this.words = words;
+ termAtt = AddAttribute<ICharTermAttribute>();
}
/// <summary>
@@ -55,7 +56,7 @@ namespace Lucene.Net.Analysis.Miscellaneous
this.words = words;
}
- public override bool Accept()
+ protected internal override bool Accept()
{
return words.Contains(termAtt.Buffer(), 0, termAtt.Length);
}
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeywordMarkerFilter.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeywordMarkerFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeywordMarkerFilter.cs
index 8918274..6403e57 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeywordMarkerFilter.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/KeywordMarkerFilter.cs
@@ -1,61 +1,59 @@
-namespace org.apache.lucene.analysis.miscellaneous
-{
-
- /*
- * 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 KeywordAttribute = org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
-
- /// <summary>
- /// Marks terms as keywords via the <seealso cref="KeywordAttribute"/>.
- /// </summary>
- /// <seealso cref= KeywordAttribute </seealso>
- public abstract class KeywordMarkerFilter : TokenFilter
- {
-
- private readonly KeywordAttribute keywordAttr = addAttribute(typeof(KeywordAttribute));
+using Lucene.Net.Analysis.Tokenattributes;
- /// <summary>
- /// Creates a new <seealso cref="KeywordMarkerFilter"/> </summary>
- /// <param name="in"> the input stream </param>
- protected internal KeywordMarkerFilter(TokenStream @in) : base(@in)
- {
- }
-
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public final boolean incrementToken() throws java.io.IOException
- public override bool incrementToken()
- {
- if (input.incrementToken())
- {
- if (Keyword)
- {
- keywordAttr.Keyword = true;
- }
- return true;
- }
- else
- {
- return false;
- }
- }
-
- protected internal abstract bool Keyword {get;}
-
- }
+namespace Lucene.Net.Analysis.Miscellaneous
+{
+ /*
+ * 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.
+ */
+ /// <summary>
+ /// Marks terms as keywords via the <seealso cref="KeywordAttribute"/>.
+ /// </summary>
+ /// <seealso cref= KeywordAttribute </seealso>
+ public abstract class KeywordMarkerFilter : TokenFilter
+ {
+
+ private readonly IKeywordAttribute keywordAttr;
+
+ /// <summary>
+ /// Creates a new <seealso cref="KeywordMarkerFilter"/> </summary>
+ /// <param name="in"> the input stream </param>
+ protected internal KeywordMarkerFilter(TokenStream @in)
+ : base(@in)
+ {
+ keywordAttr = AddAttribute<IKeywordAttribute>();
+ }
+
+ public override bool IncrementToken()
+ {
+ if (input.IncrementToken())
+ {
+ if (Keyword)
+ {
+ keywordAttr.Keyword = true;
+ }
+ return true;
+ }
+ else
+ {
+ return false;
+ }
+ }
+
+ protected internal abstract bool Keyword { get; }
+
+ }
}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilter.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilter.cs
index 802ff26..e0ba510 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilter.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilter.cs
@@ -1,7 +1,8 @@
using System;
-using FilteringTokenFilter = Lucene.Net.Analysis.Util.FilteringTokenFilter;
+using Lucene.Net.Analysis.Tokenattributes;
+using Lucene.Net.Analysis.Util;
-namespace org.apache.lucene.analysis.miscellaneous
+namespace Lucene.Net.Analysis.Miscellaneous
{
/*
@@ -20,12 +21,7 @@ namespace org.apache.lucene.analysis.miscellaneous
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-
- using FilteringTokenFilter = FilteringTokenFilter;
- using CharTermAttribute = org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
- using Version = org.apache.lucene.util.Version;
-
- /// <summary>
+ /// <summary>
/// Removes words that are too long or too short from the stream.
/// <para>
/// Note: Length is calculated as the number of UTF-16 code units.
@@ -37,7 +33,7 @@ namespace org.apache.lucene.analysis.miscellaneous
private readonly int min;
private readonly int max;
- private readonly CharTermAttribute termAtt = addAttribute(typeof(CharTermAttribute));
+ private readonly ICharTermAttribute termAtt = addAttribute(typeof(CharTermAttribute));
/// @deprecated enablePositionIncrements=false is not supported anymore as of Lucene 4.4.
[Obsolete("enablePositionIncrements=false is not supported anymore as of Lucene 4.4.")]
@@ -77,11 +73,9 @@ namespace org.apache.lucene.analysis.miscellaneous
this.max = max;
}
- public override bool accept()
+ public override bool Accept()
{
-//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
-//ORIGINAL LINE: final int len = termAtt.length();
- int len = termAtt.length();
+ int len = termAtt.Length;
return (len >= min && len <= max);
}
}
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilterFactory.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilterFactory.cs
index 6f0e4a3..afdc961 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilterFactory.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/LengthFilterFactory.cs
@@ -1,4 +1,5 @@
using System.Collections.Generic;
+using Lucene.Net.Analysis.Miscellaneous;
using TokenFilterFactory = Lucene.Net.Analysis.Util.TokenFilterFactory;
namespace org.apache.lucene.analysis.miscellaneous
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternAnalyzer.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternAnalyzer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternAnalyzer.cs
index d074038..4fe2822 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternAnalyzer.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternAnalyzer.cs
@@ -2,7 +2,7 @@
using Lucene.Net.Analysis.Core;
using Lucene.Net.Analysis.Util;
-namespace org.apache.lucene.analysis.miscellaneous
+namespace Lucene.Net.Analysis.Miscellaneous
{
/*
@@ -21,16 +21,7 @@ namespace org.apache.lucene.analysis.miscellaneous
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-
-
- using StopAnalyzer = StopAnalyzer;
- using StopFilter = StopFilter;
- using CharTermAttribute = org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
- using OffsetAttribute = org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
- using CharArraySet = CharArraySet;
- using Version = org.apache.lucene.util.Version;
-
- /// <summary>
+ /// <summary>
/// Efficient Lucene analyzer/tokenizer that preferably operates on a String rather than a
/// <seealso cref="java.io.Reader"/>, that can flexibly separate text into terms via a regular expression <seealso cref="Pattern"/>
/// (with behaviour identical to <seealso cref="String#split(String)"/>),
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternKeywordMarkerFilter.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternKeywordMarkerFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternKeywordMarkerFilter.cs
index 4402d5a..3886da0 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternKeywordMarkerFilter.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternKeywordMarkerFilter.cs
@@ -1,4 +1,6 @@
-namespace org.apache.lucene.analysis.miscellaneous
+using Lucene.Net.Analysis.Miscellaneous;
+
+namespace org.apache.lucene.analysis.miscellaneous
{
/*
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizer.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizer.cs
index b826cd6..69cc6c2 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizer.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizer.cs
@@ -1,242 +1,242 @@
using System.Text;
+using Lucene.Net.Analysis.Tokenattributes;
+using Reader = System.IO.TextReader;
-namespace org.apache.lucene.analysis.path
+namespace Lucene.Net.Analysis.Path
{
- /*
- * 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 CharTermAttribute = org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
- using OffsetAttribute = org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
- using PositionIncrementAttribute = org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-
- /// <summary>
- /// Tokenizer for path-like hierarchies.
- /// <para>
- /// Take something like:
- ///
- /// <pre>
- /// /something/something/else
- /// </pre>
- ///
- /// and make:
- ///
- /// <pre>
- /// /something
- /// /something/something
- /// /something/something/else
- /// </pre>
- /// </para>
- /// </summary>
- public class PathHierarchyTokenizer : Tokenizer
- {
-
- public PathHierarchyTokenizer(Reader input) : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, DEFAULT_SKIP)
- {
- }
-
- public PathHierarchyTokenizer(Reader input, int skip) : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, skip)
- {
- }
-
- public PathHierarchyTokenizer(Reader input, int bufferSize, char delimiter) : this(input, bufferSize, delimiter, delimiter, DEFAULT_SKIP)
- {
- }
-
- public PathHierarchyTokenizer(Reader input, char delimiter, char replacement) : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, DEFAULT_SKIP)
- {
- }
-
- public PathHierarchyTokenizer(Reader input, char delimiter, char replacement, int skip) : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
- {
- }
-
- public PathHierarchyTokenizer(AttributeFactory factory, Reader input, char delimiter, char replacement, int skip) : this(factory, input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
- {
- }
-
- public PathHierarchyTokenizer(Reader input, int bufferSize, char delimiter, char replacement, int skip) : this(AttributeFactory.DEFAULT_ATTRIBUTE_FACTORY, input, bufferSize, delimiter, replacement, skip)
- {
- }
-
- public PathHierarchyTokenizer(AttributeFactory factory, Reader input, int bufferSize, char delimiter, char replacement, int skip) : base(factory, input)
- {
- if (bufferSize < 0)
- {
- throw new System.ArgumentException("bufferSize cannot be negative");
- }
- if (skip < 0)
- {
- throw new System.ArgumentException("skip cannot be negative");
- }
- termAtt.resizeBuffer(bufferSize);
-
- this.delimiter = delimiter;
- this.replacement = replacement;
- this.skip = skip;
- resultToken = new StringBuilder(bufferSize);
- }
-
- private const int DEFAULT_BUFFER_SIZE = 1024;
- public const char DEFAULT_DELIMITER = '/';
- public const int DEFAULT_SKIP = 0;
-
- private readonly char delimiter;
- private readonly char replacement;
- private readonly int skip;
-
- private readonly CharTermAttribute termAtt = addAttribute(typeof(CharTermAttribute));
- private readonly OffsetAttribute offsetAtt = addAttribute(typeof(OffsetAttribute));
- private readonly PositionIncrementAttribute posAtt = addAttribute(typeof(PositionIncrementAttribute));
- private int startPosition = 0;
- private int skipped = 0;
- private bool endDelimiter = false;
- private StringBuilder resultToken;
-
- private int charsRead = 0;
-
-
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public final boolean incrementToken() throws java.io.IOException
- public override bool incrementToken()
- {
- clearAttributes();
- termAtt.append(resultToken);
- if (resultToken.Length == 0)
- {
- posAtt.PositionIncrement = 1;
- }
- else
- {
- posAtt.PositionIncrement = 0;
- }
- int length = 0;
- bool added = false;
- if (endDelimiter)
- {
- termAtt.append(replacement);
- length++;
- endDelimiter = false;
- added = true;
- }
-
- while (true)
- {
- int c = input.read();
- if (c >= 0)
- {
- charsRead++;
- }
- else
- {
- if (skipped > skip)
- {
- length += resultToken.Length;
- termAtt.Length = length;
- offsetAtt.setOffset(correctOffset(startPosition), correctOffset(startPosition + length));
- if (added)
- {
- resultToken.Length = 0;
- resultToken.Append(termAtt.buffer(), 0, length);
- }
- return added;
- }
- else
- {
- return false;
- }
- }
- if (!added)
- {
- added = true;
- skipped++;
- if (skipped > skip)
- {
- termAtt.append(c == delimiter ? replacement : (char)c);
- length++;
- }
- else
- {
- startPosition++;
- }
- }
- else
- {
- if (c == delimiter)
- {
- if (skipped > skip)
- {
- endDelimiter = true;
- break;
- }
- skipped++;
- if (skipped > skip)
- {
- termAtt.append(replacement);
- length++;
- }
- else
- {
- startPosition++;
- }
- }
- else
- {
- if (skipped > skip)
- {
- termAtt.append((char)c);
- length++;
- }
- else
- {
- startPosition++;
- }
- }
- }
- }
- length += resultToken.Length;
- termAtt.Length = length;
- offsetAtt.setOffset(correctOffset(startPosition), correctOffset(startPosition + length));
- resultToken.Length = 0;
- resultToken.Append(termAtt.buffer(), 0, length);
- return true;
- }
-
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public final void end() throws java.io.IOException
- public override void end()
- {
- base.end();
- // set final offset
- int finalOffset = correctOffset(charsRead);
- offsetAtt.setOffset(finalOffset, finalOffset);
- }
-
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public void reset() throws java.io.IOException
- public override void reset()
- {
- base.reset();
- resultToken.Length = 0;
- charsRead = 0;
- endDelimiter = false;
- skipped = 0;
- startPosition = 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.
+ */
+ /// <summary>
+ /// Tokenizer for path-like hierarchies.
+ /// <para>
+ /// Take something like:
+ ///
+ /// <pre>
+ /// /something/something/else
+ /// </pre>
+ ///
+ /// and make:
+ ///
+ /// <pre>
+ /// /something
+ /// /something/something
+ /// /something/something/else
+ /// </pre>
+ /// </para>
+ /// </summary>
+ public class PathHierarchyTokenizer : Tokenizer
+ {
+
+ public PathHierarchyTokenizer(Reader input)
+ : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, DEFAULT_SKIP)
+ {
+ }
+
+ public PathHierarchyTokenizer(Reader input, int skip)
+ : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, skip)
+ {
+ }
+
+ public PathHierarchyTokenizer(Reader input, int bufferSize, char delimiter)
+ : this(input, bufferSize, delimiter, delimiter, DEFAULT_SKIP)
+ {
+ }
+
+ public PathHierarchyTokenizer(Reader input, char delimiter, char replacement)
+ : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, DEFAULT_SKIP)
+ {
+ }
+
+ public PathHierarchyTokenizer(Reader input, char delimiter, char replacement, int skip)
+ : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
+ {
+ }
+
+ public PathHierarchyTokenizer(AttributeFactory factory, Reader input, char delimiter, char replacement, int skip)
+ : this(factory, input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
+ {
+ }
+
+ public PathHierarchyTokenizer(Reader input, int bufferSize, char delimiter, char replacement, int skip)
+ : this(AttributeFactory.DEFAULT_ATTRIBUTE_FACTORY, input, bufferSize, delimiter, replacement, skip)
+ {
+ }
+
+ public PathHierarchyTokenizer(AttributeFactory factory, Reader input, int bufferSize, char delimiter, char replacement, int skip)
+ : base(factory, input)
+ {
+ if (bufferSize < 0)
+ {
+ throw new System.ArgumentException("bufferSize cannot be negative");
+ }
+ if (skip < 0)
+ {
+ throw new System.ArgumentException("skip cannot be negative");
+ }
+
+ offsetAtt = AddAttribute<IOffsetAttribute>();
+ posAtt = AddAttribute<IPositionIncrementAttribute>();
+ termAtt = AddAttribute<ICharTermAttribute>();
+ termAtt.ResizeBuffer(bufferSize);
+
+ this.delimiter = delimiter;
+ this.replacement = replacement;
+ this.skip = skip;
+ resultToken = new StringBuilder(bufferSize);
+ }
+
+ private const int DEFAULT_BUFFER_SIZE = 1024;
+ public const char DEFAULT_DELIMITER = '/';
+ public const int DEFAULT_SKIP = 0;
+
+ private readonly char delimiter;
+ private readonly char replacement;
+ private readonly int skip;
+
+ private readonly ICharTermAttribute termAtt;
+ private readonly IOffsetAttribute offsetAtt;
+ private readonly IPositionIncrementAttribute posAtt;
+ private int startPosition = 0;
+ private int skipped = 0;
+ private bool endDelimiter = false;
+ private readonly StringBuilder resultToken;
+
+ private int charsRead = 0;
+
+ public override bool IncrementToken()
+ {
+ ClearAttributes();
+ termAtt.Append(resultToken);
+ if (resultToken.Length == 0)
+ {
+ posAtt.PositionIncrement = 1;
+ }
+ else
+ {
+ posAtt.PositionIncrement = 0;
+ }
+ int length = 0;
+ bool added = false;
+ if (endDelimiter)
+ {
+ termAtt.Append(replacement);
+ length++;
+ endDelimiter = false;
+ added = true;
+ }
+
+ while (true)
+ {
+ int c = input.Read();
+ if (c >= 0)
+ {
+ charsRead++;
+ }
+ else
+ {
+ if (skipped > skip)
+ {
+ length += resultToken.Length;
+ termAtt.Length = length;
+ offsetAtt.SetOffset(CorrectOffset(startPosition), CorrectOffset(startPosition + length));
+ if (added)
+ {
+ resultToken.Length = 0;
+ resultToken.Append(termAtt.Buffer(), 0, length);
+ }
+ return added;
+ }
+ else
+ {
+ return false;
+ }
+ }
+ if (!added)
+ {
+ added = true;
+ skipped++;
+ if (skipped > skip)
+ {
+ termAtt.Append(c == delimiter ? replacement : (char)c);
+ length++;
+ }
+ else
+ {
+ startPosition++;
+ }
+ }
+ else
+ {
+ if (c == delimiter)
+ {
+ if (skipped > skip)
+ {
+ endDelimiter = true;
+ break;
+ }
+ skipped++;
+ if (skipped > skip)
+ {
+ termAtt.Append(replacement);
+ length++;
+ }
+ else
+ {
+ startPosition++;
+ }
+ }
+ else
+ {
+ if (skipped > skip)
+ {
+ termAtt.Append((char)c);
+ length++;
+ }
+ else
+ {
+ startPosition++;
+ }
+ }
+ }
+ }
+ length += resultToken.Length;
+ termAtt.Length = length;
+ offsetAtt.SetOffset(CorrectOffset(startPosition), CorrectOffset(startPosition + length));
+ resultToken.Length = 0;
+ resultToken.Append(termAtt.Buffer(), 0, length);
+ return true;
+ }
+
+ public override void End()
+ {
+ base.End();
+ // set final offset
+ int finalOffset = CorrectOffset(charsRead);
+ offsetAtt.SetOffset(finalOffset, finalOffset);
+ }
+
+ public override void Reset()
+ {
+ base.Reset();
+ resultToken.Length = 0;
+ charsRead = 0;
+ endDelimiter = false;
+ skipped = 0;
+ startPosition = 0;
+ }
+ }
}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizerFactory.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizerFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizerFactory.cs
index 7dd1e62..f43772c 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizerFactory.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Path/PathHierarchyTokenizerFactory.cs
@@ -1,105 +1,100 @@
using System.Collections.Generic;
-using TokenizerFactory = Lucene.Net.Analysis.Util.TokenizerFactory;
+using System.IO;
+using Lucene.Net.Analysis.Util;
+using Lucene.Net.Util;
-namespace org.apache.lucene.analysis.path
+namespace Lucene.Net.Analysis.Path
{
- /*
- * 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 TokenizerFactory = TokenizerFactory;
- using AttributeFactory = org.apache.lucene.util.AttributeSource.AttributeFactory;
-
- /// <summary>
- /// Factory for <seealso cref="PathHierarchyTokenizer"/>.
- /// <para>
- /// This factory is typically configured for use only in the <code>index</code>
- /// Analyzer (or only in the <code>query</code> Analyzer, but never both).
- /// </para>
- /// <para>
- /// For example, in the configuration below a query for
- /// <code>Books/NonFic</code> will match documents indexed with values like
- /// <code>Books/NonFic</code>, <code>Books/NonFic/Law</code>,
- /// <code>Books/NonFic/Science/Physics</code>, etc. But it will not match
- /// documents indexed with values like <code>Books</code>, or
- /// <code>Books/Fic</code>...
- /// </para>
- ///
- /// <pre class="prettyprint">
- /// <fieldType name="descendent_path" class="solr.TextField">
- /// <analyzer type="index">
- /// <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- /// </analyzer>
- /// <analyzer type="query">
- /// <tokenizer class="solr.KeywordTokenizerFactory" />
- /// </analyzer>
- /// </fieldType>
- /// </pre>
- /// <para>
- /// In this example however we see the oposite configuration, so that a query
- /// for <code>Books/NonFic/Science/Physics</code> would match documents
- /// containing <code>Books/NonFic</code>, <code>Books/NonFic/Science</code>,
- /// or <code>Books/NonFic/Science/Physics</code>, but not
- /// <code>Books/NonFic/Science/Physics/Theory</code> or
- /// <code>Books/NonFic/Law</code>.
- /// </para>
- /// <pre class="prettyprint">
- /// <fieldType name="descendent_path" class="solr.TextField">
- /// <analyzer type="index">
- /// <tokenizer class="solr.KeywordTokenizerFactory" />
- /// </analyzer>
- /// <analyzer type="query">
- /// <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- /// </analyzer>
- /// </fieldType>
- /// </pre>
- /// </summary>
- public class PathHierarchyTokenizerFactory : TokenizerFactory
- {
- private readonly char delimiter;
- private readonly char replacement;
- private readonly bool reverse;
- private readonly int skip;
-
- /// <summary>
- /// Creates a new PathHierarchyTokenizerFactory </summary>
- public PathHierarchyTokenizerFactory(IDictionary<string, string> args) : base(args)
- {
- delimiter = getChar(args, "delimiter", PathHierarchyTokenizer.DEFAULT_DELIMITER);
- replacement = getChar(args, "replace", delimiter);
- reverse = getBoolean(args, "reverse", false);
- skip = getInt(args, "skip", PathHierarchyTokenizer.DEFAULT_SKIP);
- if (args.Count > 0)
- {
- throw new System.ArgumentException("Unknown parameters: " + args);
- }
- }
-
- public override Tokenizer create(AttributeFactory factory, Reader input)
- {
- if (reverse)
- {
- return new ReversePathHierarchyTokenizer(factory, input, delimiter, replacement, skip);
- }
- return new PathHierarchyTokenizer(factory, input, delimiter, replacement, skip);
- }
- }
-
+ /*
+ * 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.
+ */
+ /// <summary>
+ /// Factory for <seealso cref="PathHierarchyTokenizer"/>.
+ /// <para>
+ /// This factory is typically configured for use only in the <code>index</code>
+ /// Analyzer (or only in the <code>query</code> Analyzer, but never both).
+ /// </para>
+ /// <para>
+ /// For example, in the configuration below a query for
+ /// <code>Books/NonFic</code> will match documents indexed with values like
+ /// <code>Books/NonFic</code>, <code>Books/NonFic/Law</code>,
+ /// <code>Books/NonFic/Science/Physics</code>, etc. But it will not match
+ /// documents indexed with values like <code>Books</code>, or
+ /// <code>Books/Fic</code>...
+ /// </para>
+ ///
+ /// <pre class="prettyprint">
+ /// <fieldType name="descendent_path" class="solr.TextField">
+ /// <analyzer type="index">
+ /// <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ /// </analyzer>
+ /// <analyzer type="query">
+ /// <tokenizer class="solr.KeywordTokenizerFactory" />
+ /// </analyzer>
+ /// </fieldType>
+ /// </pre>
+ /// <para>
+ /// In this example however we see the oposite configuration, so that a query
+ /// for <code>Books/NonFic/Science/Physics</code> would match documents
+ /// containing <code>Books/NonFic</code>, <code>Books/NonFic/Science</code>,
+ /// or <code>Books/NonFic/Science/Physics</code>, but not
+ /// <code>Books/NonFic/Science/Physics/Theory</code> or
+ /// <code>Books/NonFic/Law</code>.
+ /// </para>
+ /// <pre class="prettyprint">
+ /// <fieldType name="descendent_path" class="solr.TextField">
+ /// <analyzer type="index">
+ /// <tokenizer class="solr.KeywordTokenizerFactory" />
+ /// </analyzer>
+ /// <analyzer type="query">
+ /// <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ /// </analyzer>
+ /// </fieldType>
+ /// </pre>
+ /// </summary>
+ public class PathHierarchyTokenizerFactory : TokenizerFactory
+ {
+ private readonly char delimiter;
+ private readonly char replacement;
+ private readonly bool reverse;
+ private readonly int skip;
+ /// <summary>
+ /// Creates a new PathHierarchyTokenizerFactory </summary>
+ public PathHierarchyTokenizerFactory(IDictionary<string, string> args)
+ : base(args)
+ {
+ delimiter = getChar(args, "delimiter", PathHierarchyTokenizer.DEFAULT_DELIMITER);
+ replacement = getChar(args, "replace", delimiter);
+ reverse = getBoolean(args, "reverse", false);
+ skip = getInt(args, "skip", PathHierarchyTokenizer.DEFAULT_SKIP);
+ if (args.Count > 0)
+ {
+ throw new System.ArgumentException("Unknown parameters: " + args);
+ }
+ }
+ public override Tokenizer Create(AttributeSource.AttributeFactory factory, TextReader input)
+ {
+ if (reverse)
+ {
+ return new ReversePathHierarchyTokenizer(factory, input, delimiter, replacement, skip);
+ }
+ return new PathHierarchyTokenizer(factory, input, delimiter, replacement, skip);
+ }
+ }
}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Path/ReversePathHierarchyTokenizer.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Path/ReversePathHierarchyTokenizer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Path/ReversePathHierarchyTokenizer.cs
index 00b5880..47a5d0f 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Path/ReversePathHierarchyTokenizer.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Path/ReversePathHierarchyTokenizer.cs
@@ -1,214 +1,217 @@
using System.Collections.Generic;
using System.Text;
+using Lucene.Net.Analysis.Tokenattributes;
+using Reader = System.IO.TextReader;
-namespace org.apache.lucene.analysis.path
+namespace Lucene.Net.Analysis.Path
{
- /*
- * 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 CharTermAttribute = org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
- using OffsetAttribute = org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
- using PositionIncrementAttribute = org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-
- /// <summary>
- /// Tokenizer for domain-like hierarchies.
- /// <para>
- /// Take something like:
- ///
- /// <pre>
- /// www.site.co.uk
- /// </pre>
- ///
- /// and make:
- ///
- /// <pre>
- /// www.site.co.uk
- /// site.co.uk
- /// co.uk
- /// uk
- /// </pre>
- ///
- /// </para>
- /// </summary>
- public class ReversePathHierarchyTokenizer : Tokenizer
- {
-
- public ReversePathHierarchyTokenizer(Reader input) : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, DEFAULT_SKIP)
- {
- }
-
- public ReversePathHierarchyTokenizer(Reader input, int skip) : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, skip)
- {
- }
-
- public ReversePathHierarchyTokenizer(Reader input, int bufferSize, char delimiter) : this(input, bufferSize, delimiter, delimiter, DEFAULT_SKIP)
- {
- }
-
- public ReversePathHierarchyTokenizer(Reader input, char delimiter, char replacement) : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, DEFAULT_SKIP)
- {
- }
-
- public ReversePathHierarchyTokenizer(Reader input, int bufferSize, char delimiter, char replacement) : this(input, bufferSize, delimiter, replacement, DEFAULT_SKIP)
- {
- }
-
- public ReversePathHierarchyTokenizer(Reader input, char delimiter, int skip) : this(input, DEFAULT_BUFFER_SIZE, delimiter, delimiter, skip)
- {
- }
-
- public ReversePathHierarchyTokenizer(Reader input, char delimiter, char replacement, int skip) : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
- {
- }
-
- public ReversePathHierarchyTokenizer(AttributeFactory factory, Reader input, char delimiter, char replacement, int skip) : this(factory, input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
- {
- }
-
- public ReversePathHierarchyTokenizer(Reader input, int bufferSize, char delimiter, char replacement, int skip) : this(AttributeFactory.DEFAULT_ATTRIBUTE_FACTORY, input, bufferSize, delimiter, replacement, skip)
- {
- }
- public ReversePathHierarchyTokenizer(AttributeFactory factory, Reader input, int bufferSize, char delimiter, char replacement, int skip) : base(factory, input)
- {
- if (bufferSize < 0)
- {
- throw new System.ArgumentException("bufferSize cannot be negative");
- }
- if (skip < 0)
- {
- throw new System.ArgumentException("skip cannot be negative");
- }
- termAtt.resizeBuffer(bufferSize);
- this.delimiter = delimiter;
- this.replacement = replacement;
- this.skip = skip;
- resultToken = new StringBuilder(bufferSize);
- resultTokenBuffer = new char[bufferSize];
- delimiterPositions = new List<>(bufferSize / 10);
- }
-
- private const int DEFAULT_BUFFER_SIZE = 1024;
- public const char DEFAULT_DELIMITER = '/';
- public const int DEFAULT_SKIP = 0;
-
- private readonly char delimiter;
- private readonly char replacement;
- private readonly int skip;
-
- private readonly CharTermAttribute termAtt = addAttribute(typeof(CharTermAttribute));
- private readonly OffsetAttribute offsetAtt = addAttribute(typeof(OffsetAttribute));
- private readonly PositionIncrementAttribute posAtt = addAttribute(typeof(PositionIncrementAttribute));
-
- private int endPosition = 0;
- private int finalOffset = 0;
- private int skipped = 0;
- private StringBuilder resultToken;
-
- private IList<int?> delimiterPositions;
- private int delimitersCount = -1;
- private char[] resultTokenBuffer;
-
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public final boolean incrementToken() throws java.io.IOException
- public override bool incrementToken()
- {
- clearAttributes();
- if (delimitersCount == -1)
- {
- int length = 0;
- delimiterPositions.Add(0);
- while (true)
- {
- int c = input.read();
- if (c < 0)
- {
- break;
- }
- length++;
- if (c == delimiter)
- {
- delimiterPositions.Add(length);
- resultToken.Append(replacement);
- }
- else
- {
- resultToken.Append((char)c);
- }
- }
- delimitersCount = delimiterPositions.Count;
- if (delimiterPositions[delimitersCount - 1] < length)
- {
- delimiterPositions.Add(length);
- delimitersCount++;
- }
- if (resultTokenBuffer.Length < resultToken.Length)
- {
- resultTokenBuffer = new char[resultToken.Length];
- }
- resultToken.getChars(0, resultToken.Length, resultTokenBuffer, 0);
- resultToken.Length = 0;
- int idx = delimitersCount - 1 - skip;
- if (idx >= 0)
- {
- // otherwise its ok, because we will skip and return false
- endPosition = delimiterPositions[idx];
- }
- finalOffset = correctOffset(length);
- posAtt.PositionIncrement = 1;
- }
- else
- {
- posAtt.PositionIncrement = 0;
- }
-
- while (skipped < delimitersCount - skip - 1)
- {
- int start = delimiterPositions[skipped];
- termAtt.copyBuffer(resultTokenBuffer, start, endPosition - start);
- offsetAtt.setOffset(correctOffset(start), correctOffset(endPosition));
- skipped++;
- return true;
- }
-
- return false;
- }
-
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public final void end() throws java.io.IOException
- public override void end()
- {
- base.end();
- // set final offset
- offsetAtt.setOffset(finalOffset, finalOffset);
- }
-
-//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
-//ORIGINAL LINE: @Override public void reset() throws java.io.IOException
- public override void reset()
- {
- base.reset();
- resultToken.Length = 0;
- finalOffset = 0;
- endPosition = 0;
- skipped = 0;
- delimitersCount = -1;
- delimiterPositions.Clear();
- }
- }
-
+ /*
+ * 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.
+ */
+ /// <summary>
+ /// Tokenizer for domain-like hierarchies.
+ /// <para>
+ /// Take something like:
+ ///
+ /// <pre>
+ /// www.site.co.uk
+ /// </pre>
+ ///
+ /// and make:
+ ///
+ /// <pre>
+ /// www.site.co.uk
+ /// site.co.uk
+ /// co.uk
+ /// uk
+ /// </pre>
+ ///
+ /// </para>
+ /// </summary>
+ public class ReversePathHierarchyTokenizer : Tokenizer
+ {
+
+ public ReversePathHierarchyTokenizer(Reader input)
+ : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, DEFAULT_SKIP)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(Reader input, int skip)
+ : this(input, DEFAULT_BUFFER_SIZE, DEFAULT_DELIMITER, DEFAULT_DELIMITER, skip)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(Reader input, int bufferSize, char delimiter)
+ : this(input, bufferSize, delimiter, delimiter, DEFAULT_SKIP)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(Reader input, char delimiter, char replacement)
+ : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, DEFAULT_SKIP)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(Reader input, int bufferSize, char delimiter, char replacement)
+ : this(input, bufferSize, delimiter, replacement, DEFAULT_SKIP)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(Reader input, char delimiter, int skip)
+ : this(input, DEFAULT_BUFFER_SIZE, delimiter, delimiter, skip)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(Reader input, char delimiter, char replacement, int skip)
+ : this(input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(AttributeFactory factory, Reader input, char delimiter, char replacement, int skip)
+ : this(factory, input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
+ {
+ }
+
+ public ReversePathHierarchyTokenizer(Reader input, int bufferSize, char delimiter, char replacement, int skip)
+ : this(AttributeFactory.DEFAULT_ATTRIBUTE_FACTORY, input, bufferSize, delimiter, replacement, skip)
+ {
+ termAtt = AddAttribute<ICharTermAttribute>();
+ offsetAtt = AddAttribute<IOffsetAttribute>();
+ posAtt = AddAttribute<IPositionIncrementAttribute>();
+ }
+
+ public ReversePathHierarchyTokenizer(AttributeFactory factory, Reader input, int bufferSize, char delimiter, char replacement, int skip)
+ : base(factory, input)
+ {
+ if (bufferSize < 0)
+ {
+ throw new System.ArgumentException("bufferSize cannot be negative");
+ }
+ if (skip < 0)
+ {
+ throw new System.ArgumentException("skip cannot be negative");
+ }
+ termAtt.ResizeBuffer(bufferSize);
+ this.delimiter = delimiter;
+ this.replacement = replacement;
+ this.skip = skip;
+ resultToken = new StringBuilder(bufferSize);
+ resultTokenBuffer = new char[bufferSize];
+ delimiterPositions = new List<int?>(bufferSize / 10);
+ }
+
+ private const int DEFAULT_BUFFER_SIZE = 1024;
+ public const char DEFAULT_DELIMITER = '/';
+ public const int DEFAULT_SKIP = 0;
+
+ private readonly char delimiter;
+ private readonly char replacement;
+ private readonly int skip;
+
+ private readonly ICharTermAttribute termAtt;
+ private readonly IOffsetAttribute offsetAtt;
+ private readonly IPositionIncrementAttribute posAtt;
+
+ private int endPosition = 0;
+ private int finalOffset = 0;
+ private int skipped = 0;
+ private readonly StringBuilder resultToken;
+
+ private readonly IList<int?> delimiterPositions;
+ private int delimitersCount = -1;
+ private char[] resultTokenBuffer;
+
+ public override bool IncrementToken()
+ {
+ ClearAttributes();
+ if (delimitersCount == -1)
+ {
+ int length = 0;
+ delimiterPositions.Add(0);
+ while (true)
+ {
+ int c = input.Read();
+ if (c < 0)
+ {
+ break;
+ }
+ length++;
+ if (c == delimiter)
+ {
+ delimiterPositions.Add(length);
+ resultToken.Append(replacement);
+ }
+ else
+ {
+ resultToken.Append((char)c);
+ }
+ }
+ delimitersCount = delimiterPositions.Count;
+ if (delimiterPositions[delimitersCount - 1] < length)
+ {
+ delimiterPositions.Add(length);
+ delimitersCount++;
+ }
+ if (resultTokenBuffer.Length < resultToken.Length)
+ {
+ resultTokenBuffer = new char[resultToken.Length];
+ }
+ resultToken.GetChars(0, resultToken.Length, resultTokenBuffer, 0);
+ resultToken.Length = 0;
+ int idx = delimitersCount - 1 - skip;
+ if (idx >= 0)
+ {
+ // otherwise its ok, because we will skip and return false
+ endPosition = delimiterPositions[idx];
+ }
+ finalOffset = CorrectOffset(length);
+ posAtt.PositionIncrement = 1;
+ }
+ else
+ {
+ posAtt.PositionIncrement = 0;
+ }
+
+ while (skipped < delimitersCount - skip - 1)
+ {
+ var start = delimiterPositions[skipped] ?? 0;
+ termAtt.CopyBuffer(resultTokenBuffer, start, endPosition - start);
+ offsetAtt.SetOffset(CorrectOffset(start), CorrectOffset(endPosition));
+ skipped++;
+ return true;
+ }
+
+ return false;
+ }
+
+ public override void End()
+ {
+ base.End();
+ // set final offset
+ offsetAtt.SetOffset(finalOffset, finalOffset);
+ }
+
+ public override void Reset()
+ {
+ base.Reset();
+ resultToken.Length = 0;
+ finalOffset = 0;
+ endPosition = 0;
+ skipped = 0;
+ delimitersCount = -1;
+ delimiterPositions.Clear();
+ }
+ }
}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Position/PositionFilterFactory.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Position/PositionFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Position/PositionFilterFactory.cs
index cc65164..476c7fe 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Position/PositionFilterFactory.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Position/PositionFilterFactory.cs
@@ -1,6 +1,7 @@
using System;
using System.Collections.Generic;
using Lucene.Net.Analysis.Util;
+using Lucene.Net.Util;
namespace Lucene.Net.Analysis.Position
{
@@ -33,9 +34,7 @@ namespace Lucene.Net.Analysis.Position
/// </analyzer>
/// </fieldType></pre>
/// </summary>
- /// <seealso cref= org.apache.lucene.analysis.position.PositionFilter
- /// @since solr 1.4 </seealso>
- /// @deprecated (4.4)
+ /// <seealso cref=PositionFilter/>
[Obsolete("(4.4)")]
public class PositionFilterFactory : TokenFilterFactory
{
@@ -51,7 +50,7 @@ namespace Lucene.Net.Analysis.Position
{
throw new System.ArgumentException("Unknown parameters: " + args);
}
- if (luceneMatchVersion != null && luceneMatchVersion.onOrAfter(Version.LUCENE_44))
+ if (luceneMatchVersion != null && luceneMatchVersion.OnOrAfter(Lucene.Net.Util.Version.LUCENE_44))
{
throw new System.ArgumentException("PositionFilter is deprecated as of Lucene 4.4. You should either fix your code to not use it or use Lucene 4.3 version compatibility");
}
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Query/QueryAutoStopWordAnalyzer.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Query/QueryAutoStopWordAnalyzer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Query/QueryAutoStopWordAnalyzer.cs
index be73228..548b7f6 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Query/QueryAutoStopWordAnalyzer.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Query/QueryAutoStopWordAnalyzer.cs
@@ -152,12 +152,12 @@ namespace Lucene.Net.Analysis.Query
protected override TokenStreamComponents WrapComponents(string fieldName, TokenStreamComponents components)
{
- HashSet<string> stopWords = stopWordsPerField[fieldName];
+ var stopWords = stopWordsPerField[fieldName];
if (stopWords == null)
{
return components;
}
- StopFilter stopFilter = new StopFilter(matchVersion, components.TokenStream, new CharArraySet(matchVersion, stopWords, false));
+ var stopFilter = new StopFilter(matchVersion, components.TokenStream, new CharArraySet(matchVersion, stopWords, false));
return new TokenStreamComponents(components.Tokenizer, stopFilter);
}
@@ -168,9 +168,9 @@ namespace Lucene.Net.Analysis.Query
/// method calls will be returned </param>
/// <returns> the stop words identified for a field </returns>
public string[] GetStopWords(string fieldName)
- {
- HashSet<string> stopWords = stopWordsPerField[fieldName];
- return stopWords != null ? stopWords.ToArray(new string[stopWords.Count]) : new string[0];
+ {
+ var stopWords = stopWordsPerField[fieldName];
+ return stopWords != null ? stopWords.ToArray() : new string[0];
}
/// <summary>
http://git-wip-us.apache.org/repos/asf/lucenenet/blob/56bfeaab/src/Lucene.Net.Analysis.Common/Analysis/Sinks/DateRecognizerSinkFilter.cs
----------------------------------------------------------------------
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Sinks/DateRecognizerSinkFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Sinks/DateRecognizerSinkFilter.cs
index a04fd51..dc080a6 100644
--- a/src/Lucene.Net.Analysis.Common/Analysis/Sinks/DateRecognizerSinkFilter.cs
+++ b/src/Lucene.Net.Analysis.Common/Analysis/Sinks/DateRecognizerSinkFilter.cs
@@ -1,6 +1,8 @@
using System;
+using Lucene.Net.Analysis.Tokenattributes;
+using Lucene.Net.Util;
-namespace org.apache.lucene.analysis.sinks
+namespace Lucene.Net.Analysis.Sinks
{
/*
@@ -19,12 +21,7 @@ namespace org.apache.lucene.analysis.sinks
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-
-
- using CharTermAttribute = org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
- using AttributeSource = org.apache.lucene.util.AttributeSource;
-
- /// <summary>
+ /// <summary>
/// Attempts to parse the <seealso cref="CharTermAttribute#buffer()"/> as a Date using a <seealso cref="java.text.DateFormat"/>.
/// If the value is a Date, it will add it to the sink.
/// <p/>
@@ -52,15 +49,15 @@ namespace org.apache.lucene.analysis.sinks
this.dateFormat = dateFormat;
}
- public override bool accept(AttributeSource source)
+ public override bool Accept(AttributeSource source)
{
if (termAtt == null)
{
- termAtt = source.addAttribute(typeof(CharTermAttribute));
+ termAtt = source.AddAttribute <ICharTermAttribute>();
}
try
{
- DateTime date = dateFormat.parse(termAtt.ToString()); //We don't care about the date, just that we can parse it as a date
+ DateTime date = dateFormat.Parse(termAtt.ToString()); //We don't care about the date, just that we can parse it as a date
if (date != null)
{
return true;