Lucene.net返回正确的查询命中数,但不返回正确的文档
我是Lucene的新手,正在努力解决这个问题。我是这样做的:Lucene.net返回正确的查询命中数,但不返回正确的文档,lucene,lucene.net,Lucene,Lucene.net,我是Lucene的新手,正在努力解决这个问题。我是这样做的: Directory dir = FSDirectory.Open(new System.IO.DirectoryInfo(dirIndexDir)); //Create the indexWriter IndexWriter writer = new IndexWriter(dir, new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE
Directory dir = FSDirectory.Open(new System.IO.DirectoryInfo(dirIndexDir));
//Create the indexWriter
IndexWriter writer = new IndexWriter(dir, new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29), true,
IndexWriter.MaxFieldLength.UNLIMITED);
Document doc = new Document();
doc.Add(new Field("keyform_type", entry.keyForm.type, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_lang", entry.keyForm.lang, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_dial", entry.keyForm.dial, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_reg", entry.keyForm.reg, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_term", entry.keyForm.term.Value, Field.Store.YES, Field.Index.ANALYZED));
if(entry.refForm.type!=null)
doc.Add(new Field("refform_type", entry.refForm.type, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.refForm.lang!=null)
doc.Add(new Field("refform_lang", entry.refForm.lang, Field.Store.YES, Field.Index.NOT_ANALYZED));
if (entry.refForm.dial != null)
doc.Add(new Field("refform_dial", entry.refForm.dial, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.refForm.reg!=null)
doc.Add(new Field("refform_reg", entry.refForm.reg, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.refForm.term.Value!=null)
doc.Add(new Field("refform_term", entry.refForm.term.Value, Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("pos", entry.pos, Field.Store.YES, Field.Index.NOT_ANALYZED));
for (int s = 0; s < entry.subject.Count; s++)
{
doc.Add(new Field("subject_"+s, entry.subject[s], Field.Store.YES, Field.Index.NOT_ANALYZED));
}
for (int g = 0; g < entry.sense.gloss.Count; g++)
{
doc.Add(new Field("gloss_"+g, entry.sense.gloss[g], Field.Store.YES, Field.Index.ANALYZED));
}
if (entry.signature.action != null)
doc.Add(new Field("action", entry.signature.action, Field.Store.YES, Field.Index.NOT_ANALYZED));
if (entry.signature.source != null)
doc.Add(new Field("source", entry.signature.source, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.signature.date==0)
doc.Add(new Field("date", entry.signature.date.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
//Add the doc
writer.AddDocument(doc);
writer.Close();
目录dir=FSDirectory.Open(new System.IO.DirectoryInfo(dirIndexDir));
//创建indexWriter
IndexWriter writer=newindexwriter(dir,newstandardAnalyzer(Lucene.Net.Util.Version.Lucene_29)),true,
IndexWriter.MaxFieldLength.UNLIMITED);
单据单据=新单据();
添加单据(新字段(“keyform_type”,entry.keyform.type,Field.Store.YES,Field.Index.NOT_analysis”);
添加文档(新字段(“keyform_lang”,entry.keyform.lang,Field.Store.YES,Field.Index.NOT_analysis”);
添加文档(新字段(“keyform_-dial”,entry.keyform.dial,Field.Store.YES,Field.Index.NOT_-analysis”);
添加文档(新字段(“keyform_reg”,entry.keyform.reg,Field.Store.YES,Field.Index.NOT_analysis”);
添加单据(新字段(“keyform_term”,entry.keyform.term.Value,Field.Store.YES,Field.Index.ANALYZED));
if(entry.refForm.type!=null)
新增单据(新增字段(“refform_type”,entry.refform.type,Field.Store.YES,Field.Index.NOT_analysis”);
if(entry.refForm.lang!=null)
添加文档(新字段(“refform_lang”,entry.refform.lang,Field.Store.YES,Field.Index.NOT_analysis”);
如果(entry.refForm.dial!=null)
添加文档(新字段(“refform_dial”,entry.refform.dial,Field.Store.YES,Field.Index.NOT_analysis”);
if(entry.refForm.reg!=null)
添加文档(新字段(“refform_reg”,entry.refform.reg,Field.Store.YES,Field.Index.NOT_analysis));
if(entry.refForm.term.Value!=null)
新增单据(新增字段(“refform_term”,entry.refform.term.Value,Field.Store.YES,Field.Index.analysis));
新增单据(新增字段(“pos”,entry.pos,Field.Store.YES,Field.Index.NOT_analysis));
对于(int s=0;s //Doesn't matter what term is, same result
string term="workers";
Directory dir = FSDirectory.Open(new System.IO.DirectoryInfo(luceneDir));
IndexSearcher searcher = new IndexSearcher(dir, true);
List<string> b=new List<string>();
b.Add("keyform_gloss");
b.Add("keyform_term");
b.Add("refform_term");
b.Add("refform_gloss");
for (int i = 0; i < nMaxDupes; i++)
b.Add("gloss_" + i.ToString());
MultiFieldQueryParser mfqp = new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_29,
b.ToArray(), new StandardAnalyzer());
Query q = mfqp.Parse(term);
TopDocs td = searcher.Search(q, 300);
for (int i = 0; i < td.totalHits; i++)
{
//Generate a dictionaryEntry for each hit
Document doc = searcher.Doc(i);
//Access the document fields, blah
}
//不管什么术语,结果都一样
字符串term=“workers”;
Directory dir=FSDirectory.Open(new System.IO.DirectoryInfo(luceneDir));
IndexSearcher=newindexSearcher(dir,true);
列表b=新列表();
b、 添加(“keyform_gloss”);
b、 添加(“关键形式”术语);
b、 添加(“参考表格”术语);
b、 添加(“参考表格”);
对于(int i=0;i
不管term的值是什么,Lucene都会返回索引中的前X个文档,其中X=实际匹配term的文档数。当我使用LUKE浏览索引时,一个相同的手写查询(keyform_term:term gloss_0:term等)返回正确数量的结果和与这些结果匹配的正确文档
然而,上面的C#代码总是返回前X个文档,这些文档不一定在任何搜索字段中包含搜索词。他们甚至都不接近
我做错了什么?我知道索引很好,因为我可以在LUKE中搜索它,所以它必须是查询中的某个内容
谢谢 线路:
Document doc = searcher.Doc(i);
应该是
Document doc = searcher.Doc(td.scoreDocs[i].doc);
或者正确的C#语法等价物(对不起,我是Java爱好者)就是这样,谢谢!如果可以的话,我会投票赞成这个答案。