Add missing Term Vector Filters

Closes #2210

Author: russcam

src/Nest/Document/Single/TermVectors/TermVectorFilter.cs

@@ -4,41 +4,146 @@
 
 namespace Nest
 {
+	/// <summary>
+	/// Filter terms returned based on their TF-IDF scores.
+	/// This can be useful in order find out a good characteristic vector of a document.
+	/// </summary>
 	[JsonObject(MemberSerialization.OptIn)]
 	public interface ITermVectorFilter
 	{
+		/// <summary>
+		/// Maximum number of terms that must be returned per field. Defaults to 25.
+		/// </summary>
 		[JsonProperty("max_num_terms")]
 		int? MaximumNumberOfTerms { get; set; }
 
+		/// <summary>
+		/// Ignore words with less than this frequency in the source doc. Defaults to 1.
+		/// </summary>
 		[JsonProperty("min_term_freq")]
 		int? MinimumTermFrequency { get; set; }
 
+		/// <summary>
+		/// Ignore words with more than this frequency in the source doc. Defaults to unbounded.
+		/// </summary>
+		[JsonProperty("max_term_freq")]
+		int? MaximumTermFrequency { get; set; }
+
+		/// <summary>
+		/// Ignore terms which do not occur in at least this many docs. Defaults to 1.
+		/// </summary>
 		[JsonProperty("min_doc_freq")]
 		int? MinimumDocumentFrequency { get; set; }
+
+		/// <summary>
+		/// Ignore words which occur in more than this many docs. Defaults to unbounded.
+		/// </summary>
+		[JsonProperty("max_doc_freq")]
+		int? MaximumDocumentFrequency { get; set; }
+
+		/// <summary>
+		/// The minimum word length below which words will be ignored. Defaults to 0.
+		/// </summary>
+		[JsonProperty("min_word_length")]
+		int? MinimumWordLength { get; set; }
+
+		/// <summary>
+		/// The maximum word length above which words will be ignored. Defaults to unbounded.
+		/// </summary>
+		[JsonProperty("max_word_length")]
+		int? MaximumWordLength { get; set; }
 	}
 
+	/// <summary>
+	/// Filter terms returned based on their TF-IDF scores.
+	/// This can be useful in order find out a good characteristic vector of a document.
+	/// </summary>
 	public class TermVectorFilter : ITermVectorFilter
 	{
+		/// <summary>
+		/// Maximum number of terms that must be returned per field. Defaults to 25.
+		/// </summary>
 		public int? MaximumNumberOfTerms { get; set; }
 
+		/// <summary>
+		/// Ignore words with less than this frequency in the source doc. Defaults to 1.
+		/// </summary>
 		public int? MinimumTermFrequency { get; set; }
 
+		/// <summary>
+		/// Ignore words with more than this frequency in the source doc. Defaults to unbounded.
+		/// </summary>
+		public int? MaximumTermFrequency { get; set; }
+
+		/// <summary>
+		/// Ignore terms which do not occur in at least this many docs. Defaults to 1.
+		/// </summary>
 		public int? MinimumDocumentFrequency { get; set; }
+
+		/// <summary>
+		/// Ignore words which occur in more than this many docs. Defaults to unbounded.
+		/// </summary>
+		public int? MaximumDocumentFrequency { get; set; }
+
+		/// <summary>
+		/// The minimum word length below which words will be ignored. Defaults to 0.
+		/// </summary>
+		public int? MinimumWordLength { get; set; }
+
+		/// <summary>
+		/// The maximum word length above which words will be ignored. Defaults to unbounded.
+		/// </summary>
+		public int? MaximumWordLength { get; set; }
 	}
 
+	/// <summary>
+	/// Filter terms returned based on their TF-IDF scores.
+	/// This can be useful in order find out a good characteristic vector of a document.
+	/// </summary>
 	public class TermVectorFilterDescriptor
 		: DescriptorBase<TermVectorFilterDescriptor, ITermVectorFilter>, ITermVectorFilter
 	{
 		int? ITermVectorFilter.MaximumNumberOfTerms { get; set; }
-
-		int? ITermVectorFilter.MinimumDocumentFrequency { get; set; }
-
 		int? ITermVectorFilter.MinimumTermFrequency { get; set; }
+		int? ITermVectorFilter.MaximumTermFrequency { get; set; }
+		int? ITermVectorFilter.MinimumDocumentFrequency { get; set; }
+		int? ITermVectorFilter.MaximumDocumentFrequency { get; set; }
+		int? ITermVectorFilter.MinimumWordLength { get; set; }
+		int? ITermVectorFilter.MaximumWordLength { get; set; }
 
+		/// <summary>
+		/// Maximum number of terms that must be returned per field. Defaults to 25.
+		/// </summary>
 		public TermVectorFilterDescriptor MaximimumNumberOfTerms(int maxNumTerms) => Assign(a => a.MaximumNumberOfTerms = maxNumTerms);
 
+		/// <summary>
+		/// Ignore words with less than this frequency in the source doc. Defaults to 1.
+		/// </summary>
+		public TermVectorFilterDescriptor MinimumTermFrequency(int minTermFreq) => Assign(a => a.MinimumTermFrequency = minTermFreq);
+
+		/// <summary>
+		/// Ignore words with more than this frequency in the source doc. Defaults to unbounded.
+		/// </summary>
+		public TermVectorFilterDescriptor MaximumTermFrequency(int maxTermFreq) => Assign(a => a.MaximumTermFrequency = maxTermFreq);
+
+		/// <summary>
+		/// Ignore terms which do not occur in at least this many docs. Defaults to 1.
+		/// </summary>
 		public TermVectorFilterDescriptor MinimumDocumentFrequency(int minDocFreq) => Assign(a => a.MinimumDocumentFrequency = minDocFreq);
 
-		public TermVectorFilterDescriptor MinimumTermFrequency(int minTermFreq) => Assign(a => a.MinimumTermFrequency = minTermFreq);
+		/// <summary>
+		/// Ignore words which occur in more than this many docs. Defaults to unbounded.
+		/// </summary>
+		public TermVectorFilterDescriptor MaximumDocumentFrequency(int maxDocFreq) => Assign(a => a.MaximumDocumentFrequency = maxDocFreq);
+
+		/// <summary>
+		/// The minimum word length below which words will be ignored. Defaults to 0.
+		/// </summary>
+		public TermVectorFilterDescriptor MinimumWordLength(int minWordLength) => Assign(a => a.MinimumWordLength = minWordLength);
+
+		/// <summary>
+		/// The maximum word length above which words will be ignored. Defaults to unbounded.
+		/// </summary>
+		public TermVectorFilterDescriptor MaximumWordLength(int maxWordLength) => Assign(a => a.MaximumWordLength = maxWordLength);
 	}
 }

src/Nest/Document/Single/TermVectors/TermVectorsRequest.cs

@@ -9,14 +9,22 @@ public partial interface ITermVectorsRequest<TDocument>
 		where TDocument : class
 	{
 		/// <summary>
-		/// An optional document to get termvectors for instead of using an already indexed document
+		/// An optional document to get term vectors for instead of using an already indexed document
 		/// </summary>
 		[JsonProperty("doc")]
 		TDocument Document { get; set; }
 
+		/// <summary>
+		/// Provide a different analyzer than the one at the field.
+		/// This is useful in order to generate term vectors in any fashion, especially when using artificial documents.
+		/// </summary>
 		[JsonProperty("per_field_analyzer")]
 		IPerFieldAnalyzer PerFieldAnalyzer { get; set; }
 
+		/// <summary>
+		/// Filter the terms returned based on their TF-IDF scores.
+		/// This can be useful in order find out a good characteristic vector of a document.
+		/// </summary>
 		[JsonProperty("filter")]
 		ITermVectorFilter Filter { get; set; }
 	}
@@ -26,10 +34,21 @@ public partial class TermVectorsRequest<TDocument>
 	{
 		HttpMethod IRequest.HttpMethod => (this.Document != null || this.Filter != null) ? HttpMethod.POST : HttpMethod.GET;
 
+		/// <summary>
+		/// An optional document to get term vectors for instead of using an already indexed document
+		/// </summary>
 		public TDocument Document { get; set; }
 
+		/// <summary>
+		/// Provide a different analyzer than the one at the field.
+		/// This is useful in order to generate term vectors in any fashion, especially when using artificial documents.
+		/// </summary>
 		public IPerFieldAnalyzer PerFieldAnalyzer { get; set; }
 
+		/// <summary>
+		/// Filter the terms returned based on their TF-IDF scores.
+		/// This can be useful in order find out a good characteristic vector of a document.
+		/// </summary>
 		public ITermVectorFilter Filter { get; set; }
 
 		partial void DocumentFromPath(TDocument document)
@@ -51,11 +70,22 @@ public partial class TermVectorsDescriptor<TDocument> where TDocument : class
 
 		ITermVectorFilter ITermVectorsRequest<TDocument>.Filter { get; set; }
 
+		/// <summary>
+		/// An optional document to get term vectors for instead of using an already indexed document
+		/// </summary>
 		public TermVectorsDescriptor<TDocument> Document(TDocument document) => Assign(a => a.Document = document);
 
+		/// <summary>
+		/// Provide a different analyzer than the one at the field.
+		/// This is useful in order to generate term vectors in any fashion, especially when using artificial documents.
+		/// </summary>
 		public TermVectorsDescriptor<TDocument> PerFieldAnalyzer(Func<PerFieldAnalyzerDescriptor<TDocument>, IPromise<IPerFieldAnalyzer>> analyzerSelector) =>
 			Assign(a => a.PerFieldAnalyzer = analyzerSelector?.Invoke(new PerFieldAnalyzerDescriptor<TDocument>())?.Value);
 
+		/// <summary>
+		/// Filter the terms returned based on their TF-IDF scores.
+		/// This can be useful in order find out a good characteristic vector of a document.
+		/// </summary>
 		public TermVectorsDescriptor<TDocument> Filter(Func<TermVectorFilterDescriptor, ITermVectorFilter> filterSelector) =>
 			Assign(a => a.Filter = filterSelector?.Invoke(new TermVectorFilterDescriptor()));
 	}

src/Tests/Document/Single/TermVectors/TermVectorsApiTests.cs

@@ -33,7 +33,11 @@ protected override LazyResponses ClientUsage() => Calls(
 			{
 				max_num_terms = 3,
 				min_term_freq = 1,
-				min_doc_freq = 1
+				max_term_freq = 10,
+				min_doc_freq = 1,
+				max_doc_freq = int.MaxValue,
+				min_word_length = 0,
+				max_word_length = 200
 			}
 		};
 
@@ -45,7 +49,11 @@ protected override LazyResponses ClientUsage() => Calls(
 			.Filter(f => f
 				.MaximimumNumberOfTerms(3)
 				.MinimumTermFrequency(1)
+				.MaximumTermFrequency(10)
 				.MinimumDocumentFrequency(1)
+				.MaximumDocumentFrequency(int.MaxValue)
+				.MinimumWordLength(0)
+				.MaximumWordLength(200)
 			)
 		;
 
@@ -56,7 +64,11 @@ protected override LazyResponses ClientUsage() => Calls(
 			{
 				MaximumNumberOfTerms = 3,
 				MinimumTermFrequency = 1,
-				MinimumDocumentFrequency = 1
+				MaximumTermFrequency = 10,
+				MinimumDocumentFrequency = 1,
+				MaximumDocumentFrequency = int.MaxValue,
+				MinimumWordLength = 0,
+				MaximumWordLength = 200
 			}
 		};
 	}