lucenenet-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From asmcad <asm...@gmail.com>
Subject Re: need some help =)
Date Wed, 17 Nov 2010 21:58:46 GMT
i don't have any ide writing custom analyzer... so i'll stick with 
SnowballAnalyzer for now.

On 17.11.2010 21:53, Digy wrote:
> UnaccentedWordAnalyzer doesn't make use of stemming.
>
> If you really need it;
> a) SnowballAnalyzer is not good in turkish stemming.
> b) It is better to write a custom analyzer using Zemberek or its .NET
> version NZemberek.
>
> DIGY
>
>
>
> -----Original Message-----
> From: asmcad [mailto:asmcad@gmail.com]
> Sent: Wednesday, November 17, 2010 11:24 PM
> To: lucene-net-dev@lucene.apache.org
> Subject: Re: need some help =)
>
> i need turkish analyzer. my lucene book says i need to use
> SnowballAnalyzer but i can't access to it as
> Lucene.Net.Analysis.Snowball should i install another library to use it?
>
> On 17.11.2010 21:12, Granroth, Neal V. wrote:
>> You need to pick a suitable analyzer for use during indexing and for
> queries.  The StandardAnalyzer you are using will most likely break the
> words apart at the non-english characters.
>> You might want to consider using the Luke tool to inspect the index you've
> created and see who the words in your documents were split and indexed.
>>
>> - Neal
>>
>> -----Original Message-----
>> From: asmcad [mailto:asmcad@gmail.com]
>> Sent: Wednesday, November 17, 2010 3:06 PM
>> To: lucene-net-dev@lucene.apache.org
>> Subject: Re: need some help =)
>>
>>
>> i solved the problem . now i have non-english character problem.
>> when i search like something "çşğuı"(i'm not sure you can see this)
>> characters. i don't get any results.
>> how can i solve this ?
>>
>> by the way sorry about the "content" messing =)
>>
>> thanks  for the  previous help  =)
>>
>> On 17.11.2010 20:16, Digy wrote:
>>>       1.
>>>          using System;
>>>       2.
>>>          using System.Collections.Generic;
>>>       3.
>>>          using System.ComponentModel;
>>>       4.
>>>          using System.Data;
>>>       5.
>>>          using System.Drawing;
>>>       6.
>>>          using System.Linq;
>>>       7.
>>>          using System.Text;
>>>       8.
>>>          using System.Windows.Forms;
>>>       9.
>>>          using Lucene.Net;
>>>      10.
>>>          using Lucene.Net.Analysis.Standard;
>>>      11.
>>>          using Lucene.Net.Documents;
>>>      12.
>>>          using Lucene.Net.Index;
>>>      13.
>>>          using Lucene.Net.QueryParsers;
>>>      14.
>>>          using Lucene.Net.Search;
>>>      15.
>>>          using System.IO;
>>>      16.
>>>      17.
>>>          namespace newLucene
>>>      18.
>>>          {
>>>      19.
>>>          public partial class Form1 : Form
>>>      20.
>>>          {
>>>      21.
>>>          public Form1()
>>>      22.
>>>          {
>>>      23.
>>>                       InitializeComponent();
>>>      24.
>>>          }
>>>      25.
>>>      26.
>>>          private void buttonIndex_Click(object sender, EventArgs e)
>>>      27.
>>>          {
>>>      28.
>>>                       IndexWriter indexwrtr = new
>>>          IndexWriter(@"c:\index\",new StandardAnalyzer() , true);
>>>      29.
>>>                       Document doc = new Document();
>>>      30.
>>>          string filename = @"fer.txt";
>>>      31.
>>>                       Lucene.Net.QueryParsers.QueryParser df;
>>>      32.
>>>      33.
>>>      34.
>>>      35.
>>>          System.IO.StreamReader local_StreamReader = new
>>>          System.IO.StreamReader(@"C:\z\fer.txt");
>>>      36.
>>>          string  file_text = local_StreamReader.ReadToEnd();
>>>      37.
>>>      38.
>>>          System.Text.UTF8Encoding encoding = new
> System.Text.UTF8Encoding();
>>>      39.
>>>                       doc.Add(new
>>>          Field("text",encoding.GetBytes(file_text),Field.Store.YES));
>>>      40.
>>>                       doc.Add(new
>>>          Field("path",encoding.GetBytes(@"C:\z\"),Field.Store.YES));
>>>      41.
>>>                       doc.Add(new Field("title",
>>>          encoding.GetBytes(filename), Field.Store.YES));
>>>      42.
>>>                       indexwrtr.AddDocument(doc);
>>>      43.
>>>      44.
>>>                       indexwrtr.Optimize();
>>>      45.
>>>                       indexwrtr.Close();
>>>      46.
>>>      47.
>>>          }
>>>      48.
>>>      49.
>>>          private void buttonSearch_Click(object sender, EventArgs e)
>>>      50.
>>>          {
>>>      51.
>>>                       IndexSearcher indxsearcher = new
>>>          IndexSearcher(@"C:\index\");
>>>      52.
>>>      53.
>>>                       QueryParser parser = new QueryParser("contents", new
>>>          StandardAnalyzer());
>>>      54.
>>>                       Query query = parser.Parse(textBoxQuery.Text);
>>>      55.
>>>      56.
>>>          //Lucene.Net.QueryParsers.QueryParser qp = new
>>>          QueryParser(Lucene.Net.QueryParsers.CharStream
>>>          s).Parse(textBoxQuery.Text);
>>>      57.
>>>                       Hits hits = indxsearcher.Search(query);
>>>      58.
>>>      59.
>>>      60.
>>>          for (int i = 0; i<    hits.Length(); i++)
>>>      61.
>>>          {
>>>      62.
>>>      63.
>>>                           Document doc = hits.Doc(i);
>>>      64.
>>>      65.
>>>      66.
>>>          string filename = doc.Get("title");
>>>      67.
>>>          string path = doc.Get("path");
>>>      68.
>>>          string folder = Path.GetDirectoryName(path);
>>>      69.
>>>      70.
>>>      71.
>>>                           ListViewItem item = new ListViewItem(new
> string[]
>>>          { null, filename, "asd", hits.Score(i).ToString() });
>>>      72.
>>>                           item.Tag = path;
>>>      73.
>>>      74.
>>>          this.listViewResults.Items.Add(item);
>>>      75.
>>>                           Application.DoEvents();
>>>      76.
>>>          }
>>>      77.
>>>      78.
>>>                       indxsearcher.Close();
>>>      79.
>>>      80.
>>>      81.
>>>      82.
>>>      83.
>>>          }
>>>      84.
>>>          }
>>>      85.
>>>          }
>>>
>>>
>>> thanks
>>>
>


Mime
View raw message