How to use the attachment processor within an array of attachments?

Elastic Stack Elasticsearch
6

I answered your original question on Stack Overflow; I'll post here for posterity

Your code is missing the ForeachProcessor; the NEST implementation for this is pretty much a direct translation of the Elasticsearch JSON example that you've posted in your question. It's a little easier using the Attachment type available in NEST too, which the attachment object that the data is extracted into will deserialize into.

void Main()
{
    var pool = new SingleNodeConnectionPool(new Uri("http://localhost:9200"));
    var defaultIndex = "default-index";
    var connectionSettings = new ConnectionSettings(pool)
        .DefaultIndex(defaultIndex);

    var client = new ElasticClient(connectionSettings);

        if (client.IndexExists(defaultIndex).Exists)
            client.DeleteIndex(defaultIndex);

    client.PutPipeline("attachments", p => p
        .Processors(pp => pp
            .Description("Document attachment pipeline")
            .Foreach<Document>(fe => fe
                .Field(f => f.Attachments)
                .Processor(fep => fep
                    .Attachment<Attachment>(a => a
                        .Field("_ingest._value.data")
                        .TargetField("_ingest._value.attachment")
                    )
                )
            )
        )
    );

    var indexResponse = client.Index(new Document
        {
            Attachments = new List<DocumentAttachment>
            {
                new DocumentAttachment { Data = "dGhpcyBpcwpqdXN0IHNvbWUgdGV4dAo=" },
                new DocumentAttachment { Data = "VGhpcyBpcyBhIHRlc3QK" }
            }
        },
        i => i.Pipeline("attachments")
    );

    var getResponse = client.Get<Document>(indexResponse.Id);
}

public class Document
{
    public List<DocumentAttachment> Attachments { get; set; }
}

public class DocumentAttachment
{
    public string Data { get; set; }

    public Attachment Attachment { get; set; }
}

returns

{
  "_index" : "default-index",
  "_type" : "document",
  "_id" : "AVrOVuC1vjcwkxZzCHYS",
  "_version" : 1,
  "found" : true,
  "_source" : {
    "attachments" : [
      {
        "data" : "dGhpcyBpcwpqdXN0IHNvbWUgdGV4dAo=",
        "attachment" : {
          "content_type" : "text/plain; charset=ISO-8859-1",
          "language" : "en",
          "content" : "this is\njust some text",
          "content_length" : 24
        }
      },
      {
        "data" : "VGhpcyBpcyBhIHRlc3QK",
        "attachment" : {
          "content_type" : "text/plain; charset=ISO-8859-1",
          "language" : "en",
          "content" : "This is a test",
          "content_length" : 16
        }
      }
    ]
  }
}

You can chain the RemoveProcessor on to remove the data field from _source too, just specify another ForeachProcessor after the current ForeachProcessor that contains the RemoveProcessor, targeting the data field. Take a look at this answer for what the json would look like.