Lucene.Net.Analysis.Cz refactor: member accessibility and documentation comments
Project: http://git-wip-us.apache.org/repos/asf/lucenenet/repo Commit: http://git-wip-us.apache.org/repos/asf/lucenenet/commit/816f0c9b Tree: http://git-wip-us.apache.org/repos/asf/lucenenet/tree/816f0c9b Diff: http://git-wip-us.apache.org/repos/asf/lucenenet/diff/816f0c9b Branch: refs/heads/api-work Commit: 816f0c9b4fa6e628f0d405e0c9fb5949e586551b Parents: 695b714 Author: Shad Storhaug <[email protected]> Authored: Fri Feb 3 02:53:37 2017 +0700 Committer: Shad Storhaug <[email protected]> Committed: Fri Feb 3 02:54:25 2017 +0700 ---------------------------------------------------------------------- .../Analysis/Cz/CzechAnalyzer.cs | 51 +++++++++----------- .../Analysis/Cz/CzechStemFilter.cs | 10 ++-- .../Analysis/Cz/CzechStemFilterFactory.cs | 10 ++-- .../Analysis/Cz/CzechStemmer.cs | 11 ++--- 4 files changed, 38 insertions(+), 44 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/lucenenet/blob/816f0c9b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechAnalyzer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechAnalyzer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechAnalyzer.cs index 00add40..25b0b12 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechAnalyzer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechAnalyzer.cs @@ -28,23 +28,21 @@ namespace Lucene.Net.Analysis.Cz */ /// <summary> - /// <seealso cref="Analyzer"/> for Czech language. + /// <see cref="Analyzer"/> for Czech language. /// <para> /// Supports an external list of stopwords (words that will not be indexed at /// all). A default set of stopwords is used unless an alternative list is /// specified. /// </para> - /// - /// <a name="version"/> /// <para> - /// You must specify the required <seealso cref="Version"/> compatibility when creating - /// CzechAnalyzer: - /// <ul> - /// <li>As of 3.1, words are stemmed with <seealso cref="CzechStemFilter"/> - /// <li>As of 2.9, StopFilter preserves position increments - /// <li>As of 2.4, Tokens incorrectly identified as acronyms are corrected (see - /// <a href="https://issues.apache.org/jira/browse/LUCENE-1068";>LUCENE-1068</a>) - /// </ul> + /// You must specify the required <see cref="LuceneVersion"/> compatibility when creating + /// <see cref="CzechAnalyzer"/>: + /// <list type="bullet"> + /// <item>As of 3.1, words are stemmed with <see cref="CzechStemFilter"/></item> + /// <item>As of 2.9, StopFilter preserves position increments</item> + /// <item>As of 2.4, Tokens incorrectly identified as acronyms are corrected (see + /// <a href="https://issues.apache.org/jira/browse/LUCENE-1068";>LUCENE-1068</a>)</item> + /// </list> /// </para> /// </summary> public sealed class CzechAnalyzer : StopwordAnalyzerBase @@ -94,10 +92,9 @@ namespace Lucene.Net.Analysis.Cz private readonly CharArraySet stemExclusionTable; /// <summary> - /// Builds an analyzer with the default stop words (<seealso cref="#getDefaultStopSet()"/>). + /// Builds an analyzer with the default stop words (<see cref="DefaultStopSet"/>). /// </summary> - /// <param name="matchVersion"> Lucene version to match See - /// <seealso cref="<a href="#version">above</a>"/> </param> + /// <param name="matchVersion"> <see cref="LuceneVersion"/> to match </param> public CzechAnalyzer(LuceneVersion matchVersion) : this(matchVersion, DefaultSetHolder.DEFAULT_SET) { @@ -106,8 +103,7 @@ namespace Lucene.Net.Analysis.Cz /// <summary> /// Builds an analyzer with the given stop words. /// </summary> - /// <param name="matchVersion"> Lucene version to match See - /// <seealso cref="<a href="#version">above</a>"/> </param> + /// <param name="matchVersion"> <see cref="LuceneVersion"/> to match </param> /// <param name="stopwords"> a stopword set </param> public CzechAnalyzer(LuceneVersion matchVersion, CharArraySet stopwords) : this(matchVersion, stopwords, CharArraySet.EMPTY_SET) @@ -116,10 +112,9 @@ namespace Lucene.Net.Analysis.Cz /// <summary> /// Builds an analyzer with the given stop words and a set of work to be - /// excluded from the <seealso cref="CzechStemFilter"/>. + /// excluded from the <see cref="CzechStemFilter"/>. /// </summary> - /// <param name="matchVersion"> Lucene version to match See - /// <seealso cref="<a href="#version">above</a>"/> </param> + /// <param name="matchVersion"> <see cref="LuceneVersion"/> to match </param> /// <param name="stopwords"> a stopword set </param> /// <param name="stemExclusionTable"> a stemming exclusion set </param> public CzechAnalyzer(LuceneVersion matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable) @@ -130,17 +125,17 @@ namespace Lucene.Net.Analysis.Cz /// <summary> /// Creates - /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> - /// used to tokenize all the text in the provided <seealso cref="Reader"/>. + /// <see cref="Analyzer.TokenStreamComponents"/> + /// used to tokenize all the text in the provided <see cref="TextReader"/>. /// </summary> - /// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> - /// built from a <seealso cref="StandardTokenizer"/> filtered with - /// <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/> - /// , and <seealso cref="CzechStemFilter"/> (only if version is >= LUCENE_31). If + /// <returns> <see cref="Analyzer.TokenStreamComponents"/> + /// built from a <see cref="StandardTokenizer"/> filtered with + /// <see cref="StandardFilter"/>, <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/>, + /// and <see cref="CzechStemFilter"/> (only if version is >= LUCENE_31). If /// a version is >= LUCENE_31 and a stem exclusion set is provided via - /// <seealso cref="#CzechAnalyzer(Version, CharArraySet, CharArraySet)"/> a - /// <seealso cref="SetKeywordMarkerFilter"/> is added before - /// <seealso cref="CzechStemFilter"/>. </returns> + /// <see cref="CzechAnalyzer(LuceneVersion, CharArraySet, CharArraySet)"/> a + /// <see cref="SetKeywordMarkerFilter"/> is added before + /// <see cref="CzechStemFilter"/>. </returns> protected override TokenStreamComponents CreateComponents(string fieldName, TextReader reader) { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/816f0c9b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilter.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilter.cs index 4bd47e0..a3f77b6 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilter.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilter.cs @@ -20,15 +20,15 @@ namespace Lucene.Net.Analysis.Cz */ /// <summary> - /// A <seealso cref="TokenFilter"/> that applies <seealso cref="CzechStemmer"/> to stem Czech words. + /// A <see cref="TokenFilter"/> that applies <see cref="CzechStemmer"/> to stem Czech words. /// <para> /// To prevent terms from being stemmed use an instance of - /// <seealso cref="SetKeywordMarkerFilter"/> or a custom <seealso cref="TokenFilter"/> that sets - /// the <seealso cref="KeywordAttribute"/> before this <seealso cref="TokenStream"/>. + /// <see cref="Miscellaneous.SetKeywordMarkerFilter"/> or a custom <see cref="TokenFilter"/> that sets + /// the <see cref="KeywordAttribute"/> before this <see cref="TokenStream"/>. /// </para> /// <para><b>NOTE</b>: Input is expected to be in lowercase, /// but with diacritical marks</para> </summary> - /// <seealso cref= SetKeywordMarkerFilter </seealso> + /// <seealso cref="Miscellaneous.SetKeywordMarkerFilter"/> public sealed class CzechStemFilter : TokenFilter { private readonly CzechStemmer stemmer = new CzechStemmer(); @@ -36,7 +36,7 @@ namespace Lucene.Net.Analysis.Cz private readonly IKeywordAttribute keywordAttr; public CzechStemFilter(TokenStream input) - : base(input) + : base(input) { termAtt = AddAttribute<ICharTermAttribute>(); keywordAttr = AddAttribute<IKeywordAttribute>(); http://git-wip-us.apache.org/repos/asf/lucenenet/blob/816f0c9b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilterFactory.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilterFactory.cs index f19b18f..3b3bb84 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilterFactory.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemFilterFactory.cs @@ -21,21 +21,21 @@ namespace Lucene.Net.Analysis.Cz */ /// <summary> - /// Factory for <seealso cref="CzechStemFilter"/>. - /// <pre class="prettyprint"> + /// Factory for <see cref="CzechStemFilter"/>. + /// <code> /// <fieldType name="text_czstem" class="solr.TextField" positionIncrementGap="100"> /// <analyzer> /// <tokenizer class="solr.StandardTokenizerFactory"/> /// <filter class="solr.LowerCaseFilterFactory"/> /// <filter class="solr.CzechStemFilterFactory"/> /// </analyzer> - /// </fieldType></pre> + /// </fieldType> + /// </code> /// </summary> public class CzechStemFilterFactory : TokenFilterFactory { - /// <summary> - /// Creates a new CzechStemFilterFactory </summary> + /// Creates a new <see cref="CzechStemFilterFactory"/> </summary> public CzechStemFilterFactory(IDictionary<string, string> args) : base(args) { if (args.Count > 0) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/816f0c9b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemmer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemmer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemmer.cs index f623a87..d87b843 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemmer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Cz/CzechStemmer.cs @@ -23,9 +23,9 @@ namespace Lucene.Net.Analysis.Cz /// Light Stemmer for Czech. /// <para> /// Implements the algorithm described in: - /// <i> + /// <c> /// Indexing and stemming approaches for the Czech language - /// </i> + /// </c> /// http://portal.acm.org/citation.cfm?id=1598600 /// </para> /// </summary> @@ -33,13 +33,12 @@ namespace Lucene.Net.Analysis.Cz { /// <summary> /// Stem an input buffer of Czech text. + /// <para><b>NOTE</b>: Input is expected to be in lowercase, + /// but with diacritical marks</para> /// </summary> /// <param name="s"> input buffer </param> /// <param name="len"> length of input buffer </param> - /// <returns> length of input buffer after normalization - /// - /// <para><b>NOTE</b>: Input is expected to be in lowercase, - /// but with diacritical marks</para> </returns> + /// <returns> length of input buffer after normalization</returns> public virtual int Stem(char[] s, int len) { len = RemoveCase(s, len);
