Lucene.Net.Analysis.De 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/217f113e Tree: http://git-wip-us.apache.org/repos/asf/lucenenet/tree/217f113e Diff: http://git-wip-us.apache.org/repos/asf/lucenenet/diff/217f113e Branch: refs/heads/api-work Commit: 217f113e91923f846fdd00f2aba403d0a1c59b02 Parents: 31d8cbd Author: Shad Storhaug <[email protected]> Authored: Fri Feb 3 11:08:05 2017 +0700 Committer: Shad Storhaug <[email protected]> Committed: Fri Feb 3 11:08:05 2017 +0700 ---------------------------------------------------------------------- .../Analysis/De/GermanAnalyzer.cs | 49 ++++++++++++-------- .../Analysis/De/GermanLightStemFilter.cs | 2 +- .../Analysis/De/GermanLightStemFilterFactory.cs | 3 +- .../Analysis/De/GermanLightStemmer.cs | 3 +- .../Analysis/De/GermanMinimalStemFilter.cs | 2 +- .../De/GermanMinimalStemFilterFactory.cs | 2 +- .../Analysis/De/GermanMinimalStemmer.cs | 3 +- .../Analysis/De/GermanNormalizationFilter.cs | 16 +++---- .../De/GermanNormalizationFilterFactory.cs | 3 +- .../Analysis/De/GermanStemFilter.cs | 4 +- .../Analysis/De/GermanStemFilterFactory.cs | 6 +-- .../Analysis/De/GermanStemmer.cs | 24 +++++----- 12 files changed, 63 insertions(+), 54 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanAnalyzer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanAnalyzer.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanAnalyzer.cs index eae217f..7eefe2e 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanAnalyzer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanAnalyzer.cs @@ -42,16 +42,15 @@ namespace Lucene.Net.Analysis.De /// exclusion list is empty by default. /// </para> /// - /// <a name="version"/> /// <para>You must specify the required <see cref="LuceneVersion"/> /// compatibility when creating GermanAnalyzer: - /// <ul> - /// <li> As of 3.6, GermanLightStemFilter is used for less aggressive stemming. - /// <li> As of 3.1, Snowball stemming is done with SnowballFilter, and - /// Snowball stopwords are used by default. - /// <li> As of 2.9, StopFilter preserves position - /// increments - /// </ul> + /// <list> + /// <item> As of 3.6, GermanLightStemFilter is used for less aggressive stemming.</item> + /// <item> As of 3.1, Snowball stemming is done with SnowballFilter, and + /// Snowball stopwords are used by default.</item> + /// <item> As of 2.9, StopFilter preserves position + /// increments</item> + /// </list> /// /// </para> /// <para><b>NOTE</b>: This class uses the same <see cref="LuceneVersion"/> @@ -59,10 +58,22 @@ namespace Lucene.Net.Analysis.De /// </summary> public sealed class GermanAnalyzer : StopwordAnalyzerBase { - /// @deprecated in 3.1, remove in Lucene 5.0 (index bw compat) [Obsolete("in 3.1, remove in Lucene 5.0 (index bw compat)")] - private static readonly string[] GERMAN_STOP_WORDS = new string[] { "einer", "eine", "eines", "einem", "einen", "der", "die", "das", "dass", "daÃ", "du", "er", "sie", "es", "was", "wer", "wie", "wir", "und", "oder", "ohne", "mit", "am", "im", "in", "aus", "auf", "ist", "sein", "war", "wird", "ihr", "ihre", "ihres", "als", "für", "von", "mit", "dich", "dir", "mich", "mir", "mein", "sein", "kein", "durch", "wegen", "wird" }; + private static readonly string[] GERMAN_STOP_WORDS = new string[] { + "einer", "eine", "eines", "einem", "einen", + "der", "die", "das", "dass", "daÃ", + "du", "er", "sie", "es", + "was", "wer", "wie", "wir", + "und", "oder", "ohne", "mit", + "am", "im", "in", "aus", "auf", + "ist", "sein", "war", "wird", + "ihr", "ihre", "ihres", + "als", "für", "von", "mit", + "dich", "dir", "mich", "mir", + "mein", "sein", "kein", + "durch", "wegen", "wird" + }; /// <summary> /// File containing default German stopwords. </summary> @@ -105,9 +116,9 @@ namespace Lucene.Net.Analysis.De } } - /// <summary> - /// Contains the stopwords used with the <see cref="StopFilter"/>. - /// </summary> + ///// <summary> + ///// Contains the stopwords used with the <see cref="StopFilter"/>. + ///// </summary> /// <summary> /// Contains words that should be indexed but not stemmed. @@ -116,7 +127,7 @@ namespace Lucene.Net.Analysis.De /// <summary> /// Builds an analyzer with the default stop words: - /// <see cref="#getDefaultStopSet()"/>. + /// <see cref="DefaultStopSet"/>. /// </summary> public GermanAnalyzer(LuceneVersion matchVersion) #pragma warning disable 612, 618 @@ -130,7 +141,7 @@ namespace Lucene.Net.Analysis.De /// Builds an analyzer with the given stop words /// </summary> /// <param name="matchVersion"> - /// lucene compatibility version </param> + /// <see cref="LuceneVersion"/> lucene compatibility version </param> /// <param name="stopwords"> /// a stopword set </param> public GermanAnalyzer(LuceneVersion matchVersion, CharArraySet stopwords) @@ -142,7 +153,7 @@ namespace Lucene.Net.Analysis.De /// Builds an analyzer with the given stop words /// </summary> /// <param name="matchVersion"> - /// lucene compatibility version </param> + /// <see cref="LuceneVersion"/> lucene compatibility version </param> /// <param name="stopwords"> /// a stopword set </param> /// <param name="stemExclusionSet"> @@ -156,12 +167,12 @@ namespace Lucene.Net.Analysis.De /// <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 - /// <see cref="StandardFilter"/>, <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/> - /// , <see cref="SetKeywordMarkerFilter"/> if a stem exclusion set is + /// <see cref="StandardFilter"/>, <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/>, + /// <see cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided, <see cref="GermanNormalizationFilter"/> and <see cref="GermanLightStemFilter"/> </returns> protected override TokenStreamComponents CreateComponents(string fieldName, TextReader reader) { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilter.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilter.cs index a58138c..1bce56b 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilter.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilter.cs @@ -24,7 +24,7 @@ namespace Lucene.Net.Analysis.De /// words. /// <para> /// To prevent terms from being stemmed 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> http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilterFactory.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilterFactory.cs index f16956c..207b788 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilterFactory.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemFilterFactory.cs @@ -33,9 +33,8 @@ namespace Lucene.Net.Analysis.De /// </summary> public class GermanLightStemFilterFactory : TokenFilterFactory { - /// <summary> - /// Creates a new GermanLightStemFilterFactory </summary> + /// Creates a new <see cref="GermanLightStemFilterFactory"/> </summary> public GermanLightStemFilterFactory(IDictionary<string, string> args) : base(args) { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemmer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemmer.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemmer.cs index 96ce9ac..c1940d2 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemmer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanLightStemmer.cs @@ -56,13 +56,12 @@ /// Light Stemmer for German. /// <para> /// This stemmer implements the "UniNE" algorithm in: - /// <i>Light Stemming Approaches for the French, Portuguese, German and Hungarian Languages</i> + /// <c>Light Stemming Approaches for the French, Portuguese, German and Hungarian Languages</c> /// Jacques Savoy /// </para> /// </summary> public class GermanLightStemmer { - public virtual int Stem(char[] s, int len) { for (int i = 0; i < len; i++) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilter.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilter.cs index 84f1f4b..094a6fc 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilter.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilter.cs @@ -24,7 +24,7 @@ namespace Lucene.Net.Analysis.De /// words. /// <para> /// To prevent terms from being stemmed 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> http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilterFactory.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilterFactory.cs index 25c6cb1..cdf77e7 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilterFactory.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemFilterFactory.cs @@ -35,7 +35,7 @@ namespace Lucene.Net.Analysis.De { /// <summary> - /// Creates a new GermanMinimalStemFilterFactory </summary> + /// Creates a new <see cref="GermanMinimalStemFilterFactory"/> </summary> public GermanMinimalStemFilterFactory(IDictionary<string, string> args) : base(args) { if (args.Count > 0) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemmer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemmer.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemmer.cs index 05b2d9a..6e01384 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemmer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanMinimalStemmer.cs @@ -56,13 +56,12 @@ /// Minimal Stemmer for German. /// <para> /// This stemmer implements the following algorithm: - /// <i>Morphologie et recherche d'information</i> + /// <c>Morphologie et recherche d'information</c> /// Jacques Savoy. /// </para> /// </summary> public class GermanMinimalStemmer { - public virtual int Stem(char[] s, int len) { if (len < 5) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilter.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilter.cs index 025c674..7160e1c 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilter.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilter.cs @@ -23,16 +23,16 @@ namespace Lucene.Net.Analysis.De /// <summary> /// Normalizes German characters according to the heuristics - /// of the <a href="http://snowball.tartarus.org/algorithms/german2/stemmer.html";> - /// German2 snowball algorithm</a>. + /// of the <c>http://snowball.tartarus.org/algorithms/german2/stemmer.html + /// German2 snowball algorithm</c>. /// It allows for the fact that ä, ö and ü are sometimes written as ae, oe and ue. /// <para> - /// <ul> - /// <li> 'Ã' is replaced by 'ss' - /// <li> 'ä', 'ö', 'ü' are replaced by 'a', 'o', 'u', respectively. - /// <li> 'ae' and 'oe' are replaced by 'a', and 'o', respectively. - /// <li> 'ue' is replaced by 'u', when not following a vowel or q. - /// </ul> + /// <list> + /// <item> 'Ã' is replaced by 'ss'</item> + /// <item> 'ä', 'ö', 'ü' are replaced by 'a', 'o', 'u', respectively.</item> + /// <item> 'ae' and 'oe' are replaced by 'a', and 'o', respectively.</item> + /// <item> 'ue' is replaced by 'u', when not following a vowel or q.</item> + /// </list> /// </para> /// <para> /// This is useful if you want this normalization without using http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilterFactory.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilterFactory.cs index 85cd62d..5afe9be 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilterFactory.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanNormalizationFilterFactory.cs @@ -33,9 +33,8 @@ namespace Lucene.Net.Analysis.De /// </summary> public class GermanNormalizationFilterFactory : TokenFilterFactory, IMultiTermAwareComponent { - /// <summary> - /// Creates a new GermanNormalizationFilterFactory </summary> + /// Creates a new <see cref="GermanNormalizationFilterFactory"/> </summary> public GermanNormalizationFilterFactory(IDictionary<string, string> args) : base(args) { if (args.Count > 0) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilter.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilter.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilter.cs index 542c6a7..cd4291c 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilter.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilter.cs @@ -28,10 +28,10 @@ namespace Lucene.Net.Analysis.De /// </para> /// <para> /// To prevent terms from being stemmed 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= SetKeywordMarkerFilter </seealso> + /// <seealso cref="Miscellaneous.SetKeywordMarkerFilter"/> public sealed class GermanStemFilter : TokenFilter { /// <summary> http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilterFactory.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilterFactory.cs index d182b4a..7176d90 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilterFactory.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemFilterFactory.cs @@ -33,10 +33,10 @@ namespace Lucene.Net.Analysis.De /// </summary> public class GermanStemFilterFactory : TokenFilterFactory { - /// <summary> - /// Creates a new GermanStemFilterFactory </summary> - public GermanStemFilterFactory(IDictionary<string, string> args) : base(args) + /// Creates a new <see cref="GermanStemFilterFactory"/> </summary> + public GermanStemFilterFactory(IDictionary<string, string> args) + : base(args) { if (args.Count > 0) { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/217f113e/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemmer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemmer.cs b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemmer.cs index 93a759e..99f2455 100644 --- a/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemmer.cs +++ b/src/Lucene.Net.Analysis.Common/Analysis/De/GermanStemmer.cs @@ -26,7 +26,7 @@ namespace Lucene.Net.Analysis.De /// A stemmer for German words. /// <para> /// The algorithm is based on the report - /// "A Fast and Simple Stemming Algorithm for German Words" by Jörg + /// "A Fast and Simple Stemming Algorithm for German Words" by Jörg /// Caumanns (joerg.caumanns at isst.fhg.de). /// </para> /// </summary> @@ -38,17 +38,17 @@ namespace Lucene.Net.Analysis.De private StringBuilder sb = new StringBuilder(); /// <summary> - /// Amount of characters that are removed with <tt>substitute()</tt> while stemming. + /// Amount of characters that are removed with <see cref="Substitute"/> while stemming. /// </summary> private int substCount = 0; private static readonly CultureInfo locale = new CultureInfo("de-DE"); /// <summary> - /// Stemms the given term to an unique <tt>discriminator</tt>. + /// Stemms the given term to an unique <c>discriminator</c>. /// </summary> /// <param name="term"> The term that should be stemmed. </param> - /// <returns> Discriminator for <tt>term</tt> </returns> + /// <returns> Discriminator for <paramref name="term"/> </returns> protected internal virtual string Stem(string term) { // Use lowercase for medium stemming. @@ -175,12 +175,14 @@ namespace Lucene.Net.Analysis.De /// <summary> /// Do some substitutions for the term to reduce overstemming: /// - /// - Substitute Umlauts with their corresponding vowel: äöü -> aou, - /// "Ã" is substituted by "ss" - /// - Substitute a second char of a pair of equal characters with - /// an asterisk: ?? -> ?* - /// - Substitute some common character combinations with a token: - /// sch/ch/ei/ie/ig/st -> $/§/%/&/#/! + /// <list type="bullet"> + /// <item>Substitute Umlauts with their corresponding vowel: äöü -> aou, + /// "Ã" is substituted by "ss"</item> + /// <item>Substitute a second char of a pair of equal characters with + /// an asterisk: ?? -> ?*</item> + /// <item>Substitute some common character combinations with a token: + /// sch/ch/ei/ie/ig/st -> $/§/%/&/#/!</item> + /// </list> /// </summary> private void Substitute(StringBuilder buffer) { @@ -257,7 +259,7 @@ namespace Lucene.Net.Analysis.De } /// <summary> - /// Undoes the changes made by substitute(). That are character pairs and + /// Undoes the changes made by <see cref="Substitute"/>. That are character pairs and /// character combinations. Umlauts will remain as their corresponding vowel, /// as "Ã" remains as "ss". /// </summary>
