ElasticSearch和附件类型(NEST C#)

Question

我正在尝试使用elasticsearch/NEST索引pdf文档.

该文件已编制索引,但搜索结果返回0次点击.

我需要搜索结果只返回文档ID和突出显示结果

(没有base64内容)

这是代码:

我会感激任何帮助,

谢谢,

class Program
{
    static void Main(string[] args)
    {
        // create es client
        string index = "myindex";

        var settings = new ConnectionSettings("localhost", 9200)
            .SetDefaultIndex(index);
        var es = new ElasticClient(settings);

        // delete index if any
        es.DeleteIndex(index);

        // index document
        string path = "test.pdf";
        var doc = new Document()
        {
            Id = 1,
            Title = "test",
            Content = Convert.ToBase64String(File.ReadAllBytes(path))
        };

        var parameters = new IndexParameters() { Refresh = true };
        if (es.Index<Document>(doc, parameters).OK)
        {
            // search in document
            string query = "semantic"; // test.pdf contains the string "semantic"

            var result = es.Search<Document>(s => s
                .Query(q =>
                    q.QueryString(qs => qs
                        .Query(query)
                    )
                )
                .Highlight(h => h
                    .PreTags("<b>")
                    .PostTags("</b>")
                    .OnFields(
                      f => f
                        .OnField(e => e.Content)
                        .PreTags("<em>")
                        .PostTags("</em>")
                    )
                )
            );

            if (result.Hits.Total == 0)
            {
            }
        }
    }
}

[ElasticType(
    Name = "document",
    SearchAnalyzer = "standard",
    IndexAnalyzer = "standard"
)]
public class Document
{
    public int Id { get; set; }

    [ElasticProperty(Store = true)]
    public string Title { get; set; }

    [ElasticProperty(Type = FieldType.attachment,
        TermVector = TermVectorOption.with_positions_offsets)]
    public string Content { get; set; }
}

Answer 1

安装Attachment Plugin并重新启动ES

bin/plugin -install elasticsearch/elasticsearch-mapper-attachments/2.3.2

创建一个映射到Attachment Plugin Documentation的Attachment Class

  public class Attachment
  {
      [ElasticProperty(Name = "_content")]
      public string Content { get; set; }

      [ElasticProperty(Name = "_content_type")]
      public string ContentType { get; set; }

      [ElasticProperty(Name = "_name")]
      public string Name { get; set; }
  }

在要使用名称"File"进行索引的Document类上添加属性并更正映射

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

在索引类的任何实例之前,显式创建索引.如果不这样做,它将使用动态映射并忽略您的属性映射.如果将来更改映射,请始终重新创建索引.

  client.CreateIndex("index-name", c => c
     .AddMapping<Document>(m => m.MapFromAttributes())
  );

索引您的项目

  string path = "test.pdf";

  var attachment = new Attachment();
  attachment.Content = Convert.ToBase64String(File.ReadAllBytes(path));
  attachment.ContentType = "application/pdf";
  attachment.Name = "test.pdf";

  var doc = new Document()
  {
      Id = 1,
      Title = "test",
      File = attachment
  };
  client.Index<Document>(item);

在File属性上搜索

  var query = Query<Document>.Term("file", "searchTerm");

  var searchResults = client.Search<Document>(s => s
          .From(start)
          .Size(count)
          .Query(query)
  );

Answer 2

// 我正在使用 FSRiver 插件 - https://github.com/dadoonet/fsriver/

void Main()
{
    // search in document
    string query = "directly"; // test.pdf contains the string "directly"
    var es = new ElasticClient(new ConnectionSettings( new Uri("http://*.*.*.*:9200"))
        .SetDefaultIndex("mydocs")
        .MapDefaultTypeNames(s=>s.Add(typeof(Doc), "doc")));
        var result = es.Search<Doc>(s => s
        .Fields(f => f.Title, f => f.Name)
        .From(0)
        .Size(10000)
            .Query(q => q.QueryString(qs => qs.Query(query)))
            .Highlight(h => h
                .PreTags("<b>")
                .PostTags("</b>")
                .OnFields(
                  f => f
                    .OnField(e => e.File)
                    .PreTags("<em>")
                    .PostTags("</em>")
                )
            )
        );
}

[ElasticType(Name = "doc",  SearchAnalyzer = "standard", IndexAnalyzer = "standard")]
public class Doc
{
    public int Id { get; set; }

     [ElasticProperty(Store = true)]
     public string Title { get; set; }

    [ElasticProperty(Type = FieldType.attachment, TermVector = TermVectorOption.with_positions_offsets)]
    public string File { get; set; }
    public string Name { get; set; }
}