IAttribute and ICharTermAttribute method changes, #1038 (#1049)

* Remove SetLength and SetEmpty from ICharTermAttribute, add extension methods * Remove CopyTo from IAttribute, add Clear to ICharTermAttribute
apache · Dec 3, 2024 · 5b7d0ac · 5b7d0ac
1 parent d1386d5
commit 5b7d0ac
Show file tree

Hide file tree

Showing 73 changed files with 364 additions and 270 deletions.
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Br/BrazilianStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Br/BrazilianStemFilter.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using System;
 
 namespace Lucene.Net.Analysis.Br
@@ -41,7 +42,7 @@ public sealed class BrazilianStemFilter : TokenFilter
         private readonly IKeywordAttribute keywordAttr;
 
         /// <summary>
-        /// Creates a new <see cref="BrazilianStemFilter"/> 
+        /// Creates a new <see cref="BrazilianStemFilter"/>
         /// </summary>
         /// <param name="in"> the source <see cref="TokenStream"/>  </param>
         public BrazilianStemFilter(TokenStream @in)
@@ -74,4 +75,4 @@ public override bool IncrementToken()
             }
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Compound/CompoundWordTokenFilterBase.cs b/src/Lucene.Net.Analysis.Common/Analysis/Compound/CompoundWordTokenFilterBase.cs
@@ -1,6 +1,7 @@
 // Lucene version compatibility level 4.8.1
 using J2N.Text;
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using Lucene.Net.Analysis.Util;
 using Lucene.Net.Diagnostics;
 using Lucene.Net.Util;

diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilter.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using System;
 
 namespace Lucene.Net.Analysis.De
@@ -22,7 +23,7 @@ namespace Lucene.Net.Analysis.De
      */
 
     /// <summary>
-    /// A <see cref="TokenFilter"/> that stems German words. 
+    /// A <see cref="TokenFilter"/> that stems German words.
     /// <para>
     /// It supports a table of words that should
     /// not be stemmed at all. The stemmer used can be changed at runtime after the
@@ -93,4 +94,4 @@ public GermanStemmer Stemmer
             }
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/En/KStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/En/KStemFilter.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using System.IO;
 
 namespace Lucene.Net.Analysis.En
@@ -30,13 +31,13 @@ namespace Lucene.Net.Analysis.En
     /// Conference on Research and Development in Information Retrieval, 191-203, 1993).
     /// <para/>
     /// All terms must already be lowercased for this filter to work correctly.
-    /// 
+    ///
     /// <para>
     /// Note: This filter is aware of the <see cref="IKeywordAttribute"/>. To prevent
     /// certain terms from being passed to the stemmer
     /// <see cref="IKeywordAttribute.IsKeyword"/> should be set to <code>true</code>
     /// in a previous <see cref="TokenStream"/>.
-    /// 
+    ///
     /// Note: For including the original term as well as the stemmed version, see
     /// <see cref="Miscellaneous.KeywordRepeatFilterFactory"/>
     /// </para>
@@ -47,7 +48,7 @@ public sealed class KStemFilter : TokenFilter
         private readonly ICharTermAttribute termAttribute;
         private readonly IKeywordAttribute keywordAtt;
 
-        public KStemFilter(TokenStream @in) 
+        public KStemFilter(TokenStream @in)
             : base(@in)
         {
             termAttribute = AddAttribute<ICharTermAttribute>();
@@ -75,4 +76,4 @@ public override bool IncrementToken()
             return true;
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Fr/FrenchStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Fr/FrenchStemFilter.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using System;
 
 namespace Lucene.Net.Analysis.Fr
@@ -22,7 +23,7 @@ namespace Lucene.Net.Analysis.Fr
      */
 
     /// <summary>
-    /// A <see cref="TokenFilter"/> that stems french words. 
+    /// A <see cref="TokenFilter"/> that stems french words.
     /// <para>
     /// The used stemmer can be changed at runtime after the
     /// filter object is created (as long as it is a <see cref="FrenchStemmer"/>).
@@ -33,9 +34,9 @@ namespace Lucene.Net.Analysis.Fr
     /// the <see cref="IKeywordAttribute"/> before this <see cref="TokenStream"/>.
     /// </para> </summary>
     /// <seealso cref="Miscellaneous.KeywordMarkerFilter"/>
-    /// @deprecated (3.1) Use <see cref="Snowball.SnowballFilter"/> with 
+    /// @deprecated (3.1) Use <see cref="Snowball.SnowballFilter"/> with
     /// <see cref="Tartarus.Snowball.Ext.FrenchStemmer"/> instead, which has the
-    /// same functionality. This filter will be removed in Lucene 5.0 
+    /// same functionality. This filter will be removed in Lucene 5.0
     [Obsolete("(3.1) Use SnowballFilter with FrenchStemmer instead, which has the same functionality. This filter will be removed in Lucene 5.0")]
     public sealed class FrenchStemFilter : TokenFilter
     {
@@ -93,4 +94,4 @@ public FrenchStemmer Stemmer
             }
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hunspell/HunspellStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hunspell/HunspellStemFilter.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.10.4
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using Lucene.Net.Util;
 using System.Collections.Generic;
 using JCG = J2N.Collections.Generic;
@@ -24,20 +25,20 @@ namespace Lucene.Net.Analysis.Hunspell
      */
 
     /// <summary>
-    /// <see cref="TokenFilter"/> that uses hunspell affix rules and words to stem tokens.  
-    /// Since hunspell supports a word having multiple stems, this filter can emit 
+    /// <see cref="TokenFilter"/> that uses hunspell affix rules and words to stem tokens.
+    /// Since hunspell supports a word having multiple stems, this filter can emit
     /// multiple tokens for each consumed token
-    /// 
+    ///
     /// <para>
     /// Note: This filter is aware of the <see cref="IKeywordAttribute"/>. To prevent
     /// certain terms from being passed to the stemmer
     /// <see cref="IKeywordAttribute.IsKeyword"/> should be set to <c>true</c>
     /// in a previous <see cref="TokenStream"/>.
-    /// 
+    ///
     /// Note: For including the original term as well as the stemmed version, see
     /// <see cref="Miscellaneous.KeywordRepeatFilterFactory"/>
     /// </para>
-    /// 
+    ///
     /// @lucene.experimental
     /// </summary>
     public sealed class HunspellStemFilter : TokenFilter
@@ -160,4 +161,4 @@ public override void Reset()
             }
         });
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternAnalyzer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/PatternAnalyzer.cs
@@ -1,6 +1,7 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.Core;
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using Lucene.Net.Analysis.Util;
 using Lucene.Net.Support;
 using Lucene.Net.Util;
@@ -38,26 +39,26 @@ namespace Lucene.Net.Analysis.Miscellaneous
     /// <see cref="StopFilter"/> into a single efficient
     /// multi-purpose class.
     /// <para>
-    /// If you are unsure how exactly a regular expression should look like, consider 
+    /// If you are unsure how exactly a regular expression should look like, consider
     /// prototyping by simply trying various expressions on some test texts via
-    /// <see cref="Regex.Split(string)"/>. Once you are satisfied, give that regex to 
-    /// <see cref="PatternAnalyzer"/>. Also see <a target="_blank" 
+    /// <see cref="Regex.Split(string)"/>. Once you are satisfied, give that regex to
+    /// <see cref="PatternAnalyzer"/>. Also see <a target="_blank"
     /// href="http://www.regular-expressions.info/">Regular Expression Tutorial</a>.
     /// </para>
     /// <para>
-    /// This class can be considerably faster than the "normal" Lucene tokenizers. 
+    /// This class can be considerably faster than the "normal" Lucene tokenizers.
     /// It can also serve as a building block in a compound Lucene
-    /// <see cref="TokenFilter"/> chain. For example as in this 
+    /// <see cref="TokenFilter"/> chain. For example as in this
     /// stemming example:
     /// <code>
     /// PatternAnalyzer pat = ...
     /// TokenStream tokenStream = new SnowballFilter(
-    ///     pat.GetTokenStream("content", "James is running round in the woods"), 
+    ///     pat.GetTokenStream("content", "James is running round in the woods"),
     ///     "English"));
     /// </code>
     /// </para>
     /// </summary>
-    /// @deprecated (4.0) use the pattern-based analysis in the analysis/pattern package instead. 
+    /// @deprecated (4.0) use the pattern-based analysis in the analysis/pattern package instead.
     [Obsolete("(4.0) use the pattern-based analysis in the analysis/pattern package instead.")]
     public sealed class PatternAnalyzer : Analyzer
     {
@@ -196,8 +197,8 @@ public PatternAnalyzer(LuceneVersion matchVersion, Regex pattern, bool toLowerCa
         /// <returns> a new token stream </returns>
         public TokenStreamComponents CreateComponents(string fieldName, TextReader reader, string text)
         {
-            // Ideally the Analyzer superclass should have a method with the same signature, 
-            // with a default impl that simply delegates to the StringReader flavour. 
+            // Ideally the Analyzer superclass should have a method with the same signature,
+            // with a default impl that simply delegates to the StringReader flavour.
             if (reader is null)
             {
                 reader = new FastStringReader(text);
@@ -448,9 +449,9 @@ public override void Reset()
 
                 // LUCENENET: Since we need to "reset" the Match
                 // object, we also need an "isReset" flag to indicate
-                // whether we are at the head of the match and to 
-                // take the appropriate measures to ensure we don't 
-                // overwrite our matcher variable with 
+                // whether we are at the head of the match and to
+                // take the appropriate measures to ensure we don't
+                // overwrite our matcher variable with
                 // matcher = matcher.NextMatch();
                 // before it is time. A string could potentially
                 // match on index 0, so we need another variable to
@@ -528,10 +529,10 @@ public override bool IncrementToken()
                         {
                             text = text.ToLower(); // LUCENENET: Since this class is obsolete, we aren't going to bother with passing culture in the constructor.
                         }
-                        //          if (toLowerCase) {            
+                        //          if (toLowerCase) {
                         ////            use next line once JDK 1.5 String.toLowerCase() performance regression is fixed
                         ////            see http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=6265809
-                        //            text = s.substring(start, i).toLowerCase(); 
+                        //            text = s.substring(start, i).toLowerCase();
                         ////            char[] chars = new char[i-start];
                         ////            for (int j=start; j < i; j++) chars[j-start] = Character.toLowerCase(s.charAt(j));
                         ////            text = new String(chars);
@@ -607,4 +608,4 @@ internal FastStringReader(string s)
             internal string String => s;
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/TrimFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/TrimFilter.cs
@@ -1,6 +1,7 @@
 // Lucene version compatibility level 4.8.1
 using System;
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using Lucene.Net.Util;
 
 namespace Lucene.Net.Analysis.Miscellaneous

diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/TypeAsSynonymFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/TypeAsSynonymFilter.cs
@@ -1,6 +1,7 @@
 // Lucene version compatibility level 8.2.0
 // LUCENENET NOTE: Ported because Lucene.Net.Analysis.OpenNLP requires this to be useful.
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using Lucene.Net.Util;
 #nullable enable
 

diff --git a/src/Lucene.Net.Analysis.Common/Analysis/NGram/Lucene43EdgeNGramTokenizer.cs b/src/Lucene.Net.Analysis.Common/Analysis/NGram/Lucene43EdgeNGramTokenizer.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using Lucene.Net.Util;
 using System;
 using System.IO;
@@ -305,4 +306,4 @@ internal static bool IsDefined(this Lucene43EdgeNGramTokenizer.Side side)
 #pragma warning restore CS0612 // Type or member is obsolete
 
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/NGram/Lucene43NGramTokenizer.cs b/src/Lucene.Net.Analysis.Common/Analysis/NGram/Lucene43NGramTokenizer.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using System;
 using System.IO;
 
@@ -171,4 +172,4 @@ public override void Reset()
             pos = 0;
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/NGram/NGramTokenFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/NGram/NGramTokenFilter.cs
@@ -121,9 +121,6 @@ public int PositionIncrement
                 get => 0;
                 set => _ = value;
             }
-
-            // LUCENENET specific - The interface requires this to be implemented, since we added it to avoid casts.
-            public void CopyTo(IAttribute target) => _ = target;
         }
 
         private sealed class PositionLengthAttributeAnonymousClass : IPositionLengthAttribute
@@ -133,9 +130,6 @@ public int PositionLength
                 get => 0;
                 set => _ = value;
             }
-
-            // LUCENENET specific - The interface requires this to be implemented, since we added it to avoid casts.
-            public void CopyTo(IAttribute target) => _ = target;
         }
 
         /// <summary>
@@ -233,4 +227,4 @@ public override void Reset()
             curTermBuffer = null;
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Nl/DutchStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Nl/DutchStemFilter.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using Lucene.Net.Analysis.Util;
 using System;
 using System.Collections.Generic;
@@ -24,7 +25,7 @@ namespace Lucene.Net.Analysis.Nl
      */
 
     /// <summary>
-    /// A <see cref="TokenFilter"/> that stems Dutch words. 
+    /// A <see cref="TokenFilter"/> that stems Dutch words.
     /// <para>
     /// It supports a table of words that should
     /// not be stemmed at all. The stemmer used can be changed at runtime after the
@@ -34,12 +35,12 @@ namespace Lucene.Net.Analysis.Nl
     /// To prevent terms from being stemmed use an instance of
     /// <see cref="Miscellaneous.KeywordMarkerFilter"/> or a custom <see cref="TokenFilter"/> that sets
     /// the <see cref="IKeywordAttribute"/> before this <see cref="TokenStream"/>.
-    /// </para> 
+    /// </para>
     /// </summary>
     /// <seealso cref="Miscellaneous.KeywordMarkerFilter"/>
-    /// @deprecated (3.1) Use <see cref="Snowball.SnowballFilter"/> with 
+    /// @deprecated (3.1) Use <see cref="Snowball.SnowballFilter"/> with
     /// <see cref="Tartarus.Snowball.Ext.DutchStemmer"/> instead, which has the
-    /// same functionality. This filter will be removed in Lucene 5.0 
+    /// same functionality. This filter will be removed in Lucene 5.0
     [Obsolete("(3.1) Use Snowball.SnowballFilter with Tartarus.Snowball.Ext.DutchStemmer instead, which has the same functionality. This filter will be removed in Lucene 5.0")]
     public sealed class DutchStemFilter : TokenFilter
     {
@@ -61,7 +62,7 @@ public DutchStemFilter(TokenStream @in)
 
         /// <param name="in"> Input <see cref="TokenStream"/> </param>
         /// <param name="stemdictionary"> Dictionary of word stem pairs, that overrule the algorithm </param>
-        public DutchStemFilter(TokenStream @in, IDictionary<string, string> stemdictionary) 
+        public DutchStemFilter(TokenStream @in, IDictionary<string, string> stemdictionary)
             : this(@in)
         {
             stemmer.StemDictionary = stemdictionary;
@@ -132,4 +133,4 @@ public CharArrayDictionary<string> StemDictionary
             }
         }
     }
-}
+}
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Pattern/PatternReplaceFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Pattern/PatternReplaceFilter.cs
@@ -1,5 +1,6 @@
 // Lucene version compatibility level 4.8.1
 using Lucene.Net.Analysis.TokenAttributes;
+using Lucene.Net.Analysis.TokenAttributes.Extensions;
 using System.Text.RegularExpressions;
 
 namespace Lucene.Net.Analysis.Pattern
@@ -24,7 +25,7 @@ namespace Lucene.Net.Analysis.Pattern
     /// <summary>
     /// A TokenFilter which applies a <see cref="Regex"/> to each token in the stream,
     /// replacing match occurances with the specified replacement string.
-    /// 
+    ///
     /// <para>
     /// <b>Note:</b> Depending on the input and the pattern used and the input
     /// <see cref="TokenStream"/>, this <see cref="TokenFilter"/> may produce <see cref="Token"/>s whose text is the empty
@@ -73,4 +74,4 @@ public override bool IncrementToken()
             return true;
         }
     }
-}
+}