I'm trying to index a pdf document with elasticsearch/NEST.
The file is indexed but search results returns with 0 hits.
I need the search result to return only the document Id and the highlight result
(without the base64 content)
Here is the code:
I'll appreciate any help here,
Thanks,
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; }
}