用Nest Elasticsearch处理文档的术语频率

Question

[ElasticProperty(Type = Nest.FieldType.attachment, TermVector =Nest.TermVectorOption.with_positions_offsets, Store = true)]
    public Attachment File { get; set; }

var searchResults = client.TermVector<Document>(t =>t.Id(ID).TermStatistics().Fields(f => f.File));    

Answer 1

您可以通过client.termvector(..)来实现这一点。下面是一个简单的例子：

文档类：

public class MyDocument
{
    public int Id { get; set; } 
    [ElasticProperty(TermVector = TermVectorOption.WithPositionsOffsets)]
    public string Description { get; set; }
    [ElasticProperty(Type = FieldType.Attachment, TermVector =TermVectorOption.WithPositionsOffsetsPayloads, Store = true, Index = FieldIndexOption.Analyzed)]
    public Attachment File { get; set; }
}

索引一些测试数据：

var indicesOperationResponse = client.CreateIndex(indexName, c => c
    .AddMapping<MyDocument>(m => m.MapFromAttributes()));

var myDocument = new MyDocument {Id = 1, Description = "test cat test"};
client.Index(myDocument);
client.Index(new MyDocument {Id = 2, Description = "river"});
client.Index(new MyDocument {Id = 3, Description = "test"});
client.Index(new MyDocument {Id = 4, Description = "river"});

client.Refresh();

var termVectorResponse = client.TermVector<MyDocument>(t => t
    .Document(myDocument)
    //.Id(1) //you can specify document by id as well
    .TermStatistics()
    .Fields(f => f.Description));

foreach (var item in termVectorResponse.TermVectors)
{
    Console.WriteLine("Field: {0}", item.Key);

    var topTerms = item.Value.Terms.OrderByDescending(x => x.Value.TotalTermFrequency).Take(10);
    foreach (var term in topTerms)
    {
        Console.WriteLine("{0}: {1}", term.Key, term.Value.TermFrequency);
    }
}

Field: description
cat: 1
test: 2

{
    "my_index" : {
        "mappings" : {
            "mydocument" : {
                "properties" : {
                    "file" : {
                        "type" : "attachment",
                        "path" : "full",
                        "fields" : {
                            "file" : {
                                "type" : "string"
                            },
                            "author" : {
                                "type" : "string"
                            },
                            "title" : {
                                "type" : "string"
                            },
                            "name" : {
                                "type" : "string"
                            },
                            "date" : {
                                "type" : "date",
                                "format" : "dateOptionalTime"
                            },
                            "keywords" : {
                                "type" : "string"
                            },
                            "content_type" : {
                                "type" : "string"
                            },
                            "content_length" : {
                                "type" : "integer"
                            },
                            "language" : {
                                "type" : "string"
                            }
                        }
                    },
                    "id" : {
                        "type" : "integer"
                    }
                }
            }
        }
    }
}

当我通过sense创建索引时：

PUT http://localhost:9200/my_index/mydocument/_mapping
{
  "mydocument": {
    "properties": {
      "file": {
        "type": "attachment",
        "path": "full",
        "fields": {
          "file": {
            "type": "string",
            "term_vector":"with_positions_offsets",
            "store": true
          }
        }
      }
    }
  }
}

我能够检索术语统计数据。

希望稍后我会带着通过Nest创建的工作映射回来。

var indicesOperationResponse = client.CreateIndex(indexName, c => c
        .AddMapping<MyDocument>(m => m
            .MapFromAttributes()
            .Properties(ps => ps
                .Attachment(s => s.Name(p => p.File)
                    .FileField(ff => ff.Name(f => f.File).TermVector(TermVectorOption.WithPositionsOffsets)))))
    );