Lucene.Net.Analysis.Hi 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/ce43351e Tree: http://git-wip-us.apache.org/repos/asf/lucenenet/tree/ce43351e Diff: http://git-wip-us.apache.org/repos/asf/lucenenet/diff/ce43351e Branch: refs/heads/api-work Commit: ce43351eb840f3bc48db8b4fb1cc97ad0692de3e Parents: ed446d2 Author: Shad Storhaug <[email protected]> Authored: Fri Feb 3 15:36:07 2017 +0700 Committer: Shad Storhaug <[email protected]> Committed: Fri Feb 3 15:36:07 2017 +0700 ---------------------------------------------------------------------- .../Analysis/Hi/HindiAnalyzer.cs | 23 +++++++++----------- .../Analysis/Hi/HindiNormalizationFilter.cs | 9 ++++---- .../Hi/HindiNormalizationFilterFactory.cs | 4 +--- .../Analysis/Hi/HindiNormalizer.cs | 14 +++++------- .../Analysis/Hi/HindiStemFilter.cs | 1 - .../Analysis/Hi/HindiStemFilterFactory.cs | 3 +-- .../Analysis/Hi/HindiStemmer.cs | 2 +- 7 files changed, 23 insertions(+), 33 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/lucenenet/blob/ce43351e/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiAnalyzer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiAnalyzer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiAnalyzer.cs index 49a1d01..2025cac 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiAnalyzer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiAnalyzer.cs @@ -28,14 +28,11 @@ namespace Lucene.Net.Analysis.Hi /// <summary> /// Analyzer for Hindi. - /// <para> - /// <a name="version"/> - /// </para> /// <para>You must specify the required <see cref="LuceneVersion"/> /// compatibility when creating HindiAnalyzer: - /// <ul> - /// <li> As of 3.6, StandardTokenizer is used for tokenization - /// </ul> + /// <list type="bullet"> + /// <item> As of 3.6, StandardTokenizer is used for tokenization</item> + /// </list> /// </para> /// </summary> public sealed class HindiAnalyzer : StopwordAnalyzerBase @@ -44,7 +41,7 @@ namespace Lucene.Net.Analysis.Hi /// <summary> /// File containing default Hindi stopwords. - /// + /// <para/> /// Default stopword list is from http://members.unine.ch/jacques.savoy/clef/index.html /// The stopword list is BSD-Licensed. /// </summary> @@ -63,7 +60,7 @@ namespace Lucene.Net.Analysis.Hi } /// <summary> - /// Atomically loads the DEFAULT_STOP_SET in a lazy fashion once the outer class + /// Atomically loads the <see cref="DEFAULT_STOP_SET"/> in a lazy fashion once the outer class /// accesses the static final set the first time.; /// </summary> private class DefaultSetHolder @@ -93,7 +90,7 @@ namespace Lucene.Net.Analysis.Hi /// <param name="stopwords"> a stopword set </param> /// <param name="stemExclusionSet"> a stemming exclusion set </param> public HindiAnalyzer(LuceneVersion version, CharArraySet stopwords, CharArraySet stemExclusionSet) - : base(version, stopwords) + : base(version, stopwords) { this.stemExclusionSet = CharArraySet.UnmodifiableSet(CharArraySet.Copy(m_matchVersion, stemExclusionSet)); } @@ -104,23 +101,23 @@ namespace Lucene.Net.Analysis.Hi /// <param name="version"> lucene compatibility version </param> /// <param name="stopwords"> a stopword set </param> public HindiAnalyzer(LuceneVersion version, CharArraySet stopwords) - : this(version, stopwords, CharArraySet.EMPTY_SET) + : this(version, stopwords, CharArraySet.EMPTY_SET) { } /// <summary> /// Builds an analyzer with the default stop words: - /// <see cref="#DEFAULT_STOPWORD_FILE"/>. + /// <see cref="DEFAULT_STOPWORD_FILE"/>. /// </summary> public HindiAnalyzer(LuceneVersion version) - : this(version, DefaultSetHolder.DEFAULT_STOP_SET) + : this(version, DefaultSetHolder.DEFAULT_STOP_SET) { } /// <summary> /// Creates /// <see cref="Analyzer.TokenStreamComponents"/> - /// used to tokenize all the text in the provided <see cref="Reader"/>. + /// used to tokenize all the text in the provided <see cref="TextReader"/>. /// </summary> /// <returns> <see cref="Analyzer.TokenStreamComponents"/> /// built from a <see cref="StandardTokenizer"/> filtered with http://git-wip-us.apache.org/repos/asf/lucenenet/blob/ce43351e/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilter.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilter.cs index 8600e0d..25fc39c 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilter.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilter.cs @@ -1,5 +1,4 @@ using Lucene.Net.Analysis.TokenAttributes; -using System.IO; namespace Lucene.Net.Analysis.Hi { @@ -26,13 +25,13 @@ namespace Lucene.Net.Analysis.Hi /// <para> /// In some cases the normalization may cause unrelated terms to conflate, so /// to prevent terms from being normalized use an instance of - /// <see cref="SetKeywordMarkerFilter"/> or a custom <see cref="TokenFilter"/> that sets + /// <see cref="Miscellaneous.SetKeywordMarkerFilter"/> or a custom <see cref="TokenFilter"/> that sets /// the <see cref="KeywordAttribute"/> before this <see cref="TokenStream"/>. - /// </para> </summary> - /// <seealso cref= HindiNormalizer </seealso> + /// </para> + /// </summary> + /// <seealso cref="HindiNormalizer"/> public sealed class HindiNormalizationFilter : TokenFilter { - private readonly HindiNormalizer normalizer = new HindiNormalizer(); private readonly ICharTermAttribute termAtt; private readonly IKeywordAttribute keywordAtt; http://git-wip-us.apache.org/repos/asf/lucenenet/blob/ce43351e/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilterFactory.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilterFactory.cs index 70f7175..4cad89e 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilterFactory.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizationFilterFactory.cs @@ -1,6 +1,5 @@ using Lucene.Net.Analysis.Util; using System.Collections.Generic; -using System.IO; namespace Lucene.Net.Analysis.Hi { @@ -33,9 +32,8 @@ namespace Lucene.Net.Analysis.Hi /// </summary> public class HindiNormalizationFilterFactory : TokenFilterFactory, IMultiTermAwareComponent { - /// <summary> - /// Creates a new HindiNormalizationFilterFactory </summary> + /// Creates a new <see cref="HindiNormalizationFilterFactory"/> </summary> public HindiNormalizationFilterFactory(IDictionary<string, string> args) : base(args) { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/ce43351e/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizer.cs index b1a1271..45144a6 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiNormalizer.cs @@ -27,19 +27,18 @@ namespace Lucene.Net.Analysis.Hi /// </para> /// <para> /// Implements the Hindi-language specific algorithm specified in: - /// <i>Word normalization in Indian languages</i> + /// <c>Word normalization in Indian languages</c> /// Prasad Pingali and Vasudeva Varma. /// http://web2py.iiit.ac.in/publications/default/download/inproceedings.pdf.3fe5b38c-02ee-41ce-9a8f-3e745670be32.pdf /// </para> /// <para> - /// with the following additions from <i>Hindi CLIR in Thirty Days</i> + /// with the following additions from <c>Hindi CLIR in Thirty Days</c> /// Leah S. Larkey, Margaret E. Connell, and Nasreen AbdulJaleel. /// http://maroo.cs.umass.edu/pub/web/getpdf.php?id=454: - /// <ul> - /// <li>Internal Zero-width joiner and Zero-width non-joiners are removed - /// <li>In addition to chandrabindu, NA+halant is normalized to anusvara - /// </ul> - /// + /// <list type="bullet"> + /// <item>Internal Zero-width joiner and Zero-width non-joiners are removed</item> + /// <item>In addition to chandrabindu, NA+halant is normalized to anusvara</item> + /// </list> /// </para> /// </summary> public class HindiNormalizer @@ -52,7 +51,6 @@ namespace Lucene.Net.Analysis.Hi /// <returns> length of input buffer after normalization </returns> public virtual int Normalize(char[] s, int len) { - for (int i = 0; i < len; i++) { switch (s[i]) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/ce43351e/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilter.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilter.cs index ac11063..dced8e8 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilter.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilter.cs @@ -1,5 +1,4 @@ using Lucene.Net.Analysis.TokenAttributes; -using System.IO; namespace Lucene.Net.Analysis.Hi { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/ce43351e/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilterFactory.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilterFactory.cs index cdd897e..2427506 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilterFactory.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemFilterFactory.cs @@ -33,9 +33,8 @@ namespace Lucene.Net.Analysis.Hi /// </summary> public class HindiStemFilterFactory : TokenFilterFactory { - /// <summary> - /// Creates a new HindiStemFilterFactory </summary> + /// Creates a new <see cref="HindiStemFilterFactory"/> </summary> public HindiStemFilterFactory(IDictionary<string, string> args) : base(args) { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/ce43351e/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemmer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemmer.cs b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemmer.cs index c356553..35dfd91 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemmer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/Hi/HindiStemmer.cs @@ -24,7 +24,7 @@ namespace Lucene.Net.Analysis.Hi /// Light Stemmer for Hindi. /// <para> /// Implements the algorithm specified in: - /// <i>A Lightweight Stemmer for Hindi</i> + /// <c>A Lightweight Stemmer for Hindi</c> /// Ananthakrishnan Ramanathan and Durgesh D Rao. /// http://computing.open.ac.uk/Sites/EACLSouthAsia/Papers/p6-Ramanathan.pdf /// </para>
