public void TestDefaultFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
Hashtable results = new Hashtable();
Hits h = searcher.Search(tq, df);
for (int i = 0; i < h.Length(); i++)
{
Document d = h.Doc(i);
String url = d.Get(KEY_FIELD);
Assert.IsFalse(results.Contains(url), "No duplicate urls should be returned");
results.Add(url,url);
}
}
public void TestDefaultFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
Hashtable results = new Hashtable();
Hits h = searcher.Search(tq, df);
for (int i = 0; i < h.Length(); i++)
{
Document d = h.Doc(i);
String url = d.Get(KEY_FIELD);
Assert.IsFalse(results.Contains(url), "No duplicate urls should be returned");
results.Add(url,url);
}
}
public override bool Equals(Object obj)
{
if (this == obj)
{
return(true);
}
if ((obj == null) || (obj.GetType() != this.GetType()))
{
return(false);
}
DuplicateFilter other = (DuplicateFilter)obj;
return(keepMode == other.keepMode &&
processingMode == other.processingMode &&
(fieldName == other.fieldName || (fieldName != null && fieldName.Equals(other.fieldName))));
}
public void TestFastFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
df.SetProcessingMode(DuplicateFilter.PM_FAST_INVALIDATION);
Hashtable results = new Hashtable();
Hits h = searcher.Search(tq, df);
Assert.IsTrue(h.Length() > 0, "Filtered searching should have found some matches");
for (int i = 0; i < h.Length(); i++)
{
Document d = h.Doc(i);
String url = d.Get(KEY_FIELD);
Assert.IsFalse(results.Contains(url), "No duplicate urls should be returned");
results.Add(url,url);
}
Assert.AreEqual(2, results.Count, "Two urls found");
}
public void TestKeepsFirstFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
df.SetKeepMode(DuplicateFilter.KM_USE_FIRST_OCCURRENCE);
Hits h = searcher.Search(tq, df);
Assert.IsTrue(h.Length() > 0, "Filtered searching should have found some matches");
for (int i = 0; i < h.Length(); i++)
{
Document d = h.Doc(i);
String url = d.Get(KEY_FIELD);
TermDocs td = reader.TermDocs(new Term(KEY_FIELD, url));
int lastDoc = 0;
td.Next();
lastDoc = td.Doc();
Assert.AreEqual(lastDoc, h.Id((i)), "Duplicate urls should return first doc");
}
}
public void TestKeepsFirstFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
df.KeepMode = DuplicateFilter.KM_USE_FIRST_OCCURRENCE;
ScoreDoc[] h = searcher.Search(tq, df, 1000).ScoreDocs;
Assert.IsTrue(h.Length > 0, "Filtered searching should have found some matches");
for (int i = 0; i < h.Length; i++)
{
Document d = searcher.Doc(h[i].Doc);
String url = d.Get(KEY_FIELD);
TermDocs td = reader.TermDocs(new Term(KEY_FIELD, url));
int lastDoc = 0;
td.Next();
lastDoc = td.Doc;
Assert.AreEqual(lastDoc, h[i].Doc, "Duplicate urls should return first doc");
}
}
public void TestKeepsFirstFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
df.SetKeepMode(DuplicateFilter.KM_USE_FIRST_OCCURRENCE);
Hits h = searcher.Search(tq, df);
Assert.IsTrue(h.Length() > 0, "Filtered searching should have found some matches");
for (int i = 0; i < h.Length(); i++)
{
Document d = h.Doc(i);
String url = d.Get(KEY_FIELD);
TermDocs td = reader.TermDocs(new Term(KEY_FIELD, url));
int lastDoc = 0;
td.Next();
lastDoc = td.Doc();
Assert.AreEqual(lastDoc, h.Id((i)), "Duplicate urls should return first doc");
}
}
public void TestFastFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
df.SetProcessingMode(DuplicateFilter.PM_FAST_INVALIDATION);
Hashtable results = new Hashtable();
Hits h = searcher.Search(tq, df);
Assert.IsTrue(h.Length() > 0, "Filtered searching should have found some matches");
for (int i = 0; i < h.Length(); i++)
{
Document d = h.Doc(i);
String url = d.Get(KEY_FIELD);
Assert.IsFalse(results.Contains(url), "No duplicate urls should be returned");
results.Add(url,url);
}
Assert.AreEqual(2, results.Count, "Two urls found");
}
public void TestKeepsFirstFilter()
{
DuplicateFilter df = new DuplicateFilter(KEY_FIELD);
df.KeepMode = DuplicateFilter.KM_USE_FIRST_OCCURRENCE;
ScoreDoc[] h = searcher.Search(tq, df, 1000).ScoreDocs;
Assert.IsTrue(h.Length > 0, "Filtered searching should have found some matches");
for (int i = 0; i < h.Length; i++)
{
Document d = searcher.Doc(h[i].Doc);
String url = d.Get(KEY_FIELD);
TermDocs td = reader.TermDocs(new Term(KEY_FIELD, url));
int lastDoc = 0;
td.Next();
lastDoc = td.Doc;
Assert.AreEqual(lastDoc, h[i].Doc, "Duplicate urls should return first doc");
}
}
