/// <summary> Returns a BitSet with true for documents which should be
/// permitted in search results, and false for those that should
/// not.
/// </summary>
public override System.Collections.BitArray Bits(IndexReader reader)
{
System.Collections.BitArray bits = new System.Collections.BitArray((reader.MaxDoc() % 64 == 0?reader.MaxDoc() / 64:reader.MaxDoc() / 64 + 1) * 64);
TermEnum enumerator = reader.Terms(new Term(field, start));
TermDocs termDocs = reader.TermDocs();
if (enumerator.Term() == null)
{
return(bits);
}
try
{
Term stop = new Term(field, end);
while (enumerator.Term().CompareTo(stop) <= 0)
{
termDocs.Seek(enumerator.Term());
while (termDocs.Next())
{
bits.Set(termDocs.Doc(), true);
}
if (!enumerator.Next())
{
break;
}
}
}
finally
{
enumerator.Close();
termDocs.Close();
}
return(bits);
}
public override Query Rewrite(IndexReader reader)
{
BooleanQuery query = new BooleanQuery(true);
TermEnum enumerator = reader.Terms(prefix);
try
{
System.String prefixText = prefix.Text();
System.String prefixField = prefix.Field();
do
{
Term term = enumerator.Term();
if (term != null && term.Text().StartsWith(prefixText) && term.Field() == prefixField)
{
TermQuery tq = new TermQuery(term); // found a match
tq.SetBoost(GetBoost()); // set the boost
query.Add(tq, BooleanClause.Occur.SHOULD); // add to query
//System.out.println("added " + term);
}
else
{
break;
}
}
while (enumerator.Next());
}
finally
{
enumerator.Close();
}
return query;
}
/// <summary> Constructor for enumeration of all terms from specified <code>reader</code> which share a prefix of
/// length <code>prefixLength</code> with <code>term</code> and which have a fuzzy similarity >
/// <code>minSimilarity</code>.
/// <p/>
/// After calling the constructor the enumeration is already pointing to the first
/// valid term if such a term exists.
///
/// </summary>
/// <param name="reader">Delivers terms.
/// </param>
/// <param name="term">Pattern term.
/// </param>
/// <param name="minSimilarity">Minimum required similarity for terms from the reader. Default value is 0.5f.
/// </param>
/// <param name="prefixLength">Length of required common prefix. Default value is 0.
/// </param>
/// <throws> IOException </throws>
public FuzzyTermEnum(IndexReader reader, Term term, float minSimilarity, int prefixLength) : base()
{
if (minSimilarity >= 1.0f)
{
throw new System.ArgumentException("minimumSimilarity cannot be greater than or equal to 1");
}
else if (minSimilarity < 0.0f)
{
throw new System.ArgumentException("minimumSimilarity cannot be less than 0");
}
if (prefixLength < 0)
{
throw new System.ArgumentException("prefixLength cannot be less than 0");
}
this.minimumSimilarity = minSimilarity;
this.scale_factor = 1.0f / (1.0f - minimumSimilarity);
this.searchTerm = term;
this.field = searchTerm.Field();
//The prefix could be longer than the word.
//It's kind of silly though. It means we must match the entire word.
int fullSearchTermLength = searchTerm.Text().Length;
int realPrefixLength = prefixLength > fullSearchTermLength?fullSearchTermLength:prefixLength;
this.text = searchTerm.Text().Substring(realPrefixLength);
this.prefix = searchTerm.Text().Substring(0, (realPrefixLength) - (0));
InitializeMaxDistances();
this.d = InitDistanceArray();
SetEnum(reader.Terms(new Term(searchTerm.Field(), prefix)));
}
/// <summary>The pattern used to detect integer values in a field </summary>
/// <summary>removed for java 1.3 compatibility
/// protected static final Pattern pIntegers = Pattern.compile ("[0-9\\-]+");
///
/// </summary>
/// <summary>The pattern used to detect float values in a field </summary>
/// <summary> removed for java 1.3 compatibility
/// protected static final Object pFloats = Pattern.compile ("[0-9+\\-\\.eEfFdD]+");
/// </summary>
// inherit javadocs
public virtual System.Object GetAuto(IndexReader reader, System.String field)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, SortField.AUTO, null);
if (ret == null)
{
TermEnum enumerator = reader.Terms(new Term(field, ""));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine sort type");
}
if (term.Field() == field)
{
System.String termtext = term.Text().Trim();
/// <summary> Java 1.4 level code:
/// if (pIntegers.matcher(termtext).matches())
/// return IntegerSortedHitQueue.comparator (reader, enumerator, field);
/// else if (pFloats.matcher(termtext).matches())
/// return FloatSortedHitQueue.comparator (reader, enumerator, field);
/// </summary>
// Java 1.3 level code:
try
{
System.Int32.Parse(termtext);
ret = GetInts(reader, field);
}
catch (System.FormatException nfe1)
{
try
{
System.Single.Parse(termtext);
ret = GetFloats(reader, field);
}
catch (System.FormatException nfe2)
{
ret = GetStringIndex(reader, field);
}
}
if (ret != null)
{
Store(reader, field, SortField.AUTO, null, ret);
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
}
finally
{
enumerator.Close();
}
}
return(ret);
}
public RegexTermEnum(IndexReader reader, Term term)
: base()
{
field = term.Field();
System.String text = term.Text();
pattern = new Pattern(text);
// Find the first regex character position, to find the
// maximum prefix to use for term enumeration
int index = 0;
while (index < text.Length)
{
char c = text[index];
if (!System.Char.IsLetterOrDigit(c))
break;
index++;
}
pre = text.Substring(0, (index) - (0));
SetEnum(reader.Terms(new Term(term.Field(), pre)));
}
public virtual void Generate(IndexReader reader)
{
TermEnum enumerator = reader.Terms(prefix);
TermDocs termDocs = reader.TermDocs();
try
{
System.String prefixText = prefix.Text();
System.String prefixField = prefix.Field();
do
{
Term term = enumerator.Term();
if (term != null && term.Text().StartsWith(prefixText) && (System.Object)term.Field() == (System.Object)prefixField)
{
termDocs.Seek(term);
while (termDocs.Next())
{
HandleDoc(termDocs.Doc());
}
}
else
{
break;
}
}while (enumerator.Next());
}
finally
{
termDocs.Close();
enumerator.Close();
}
}
/* Walk directory hierarchy in uid order, while keeping uid iterator from
* /* existing index in sync. Mismatches indicate one of: (a) old documents to
* /* be deleted; (b) unchanged documents, to be left alone; or (c) new
* /* documents, to be indexed.
*/
private static void IndexDocs(System.IO.FileInfo file, System.IO.FileInfo index, bool create)
{
if (!create)
{
// incrementally update
reader = IndexReader.Open(FSDirectory.Open(index), false); // open existing index
uidIter = reader.Terms(new Term("uid", "")); // init uid iterator
IndexDocs(file);
if (deleting)
{
// delete rest of stale docs
while (uidIter.Term() != null && (System.Object)uidIter.Term().Field() == (System.Object) "uid")
{
System.Console.Out.WriteLine("deleting " + HTMLDocument.Uid2url(uidIter.Term().Text()));
reader.DeleteDocuments(uidIter.Term());
uidIter.Next();
}
deleting = false;
}
uidIter.Close(); // close uid iterator
reader.Close(); // close existing index
}
// don't have exisiting
else
{
IndexDocs(file);
}
}
/// <summary> Enumerates all terms greater/equal than <code>lowerTerm</code>
/// but less/equal than <code>upperTerm</code>.
///
/// If an endpoint is null, it is said to be "open". Either or both
/// endpoints may be open. Open endpoints may not be exclusive
/// (you can't select all but the first or last term without
/// explicitly specifying the term to exclude.)
///
/// </summary>
/// <param name="reader">
/// </param>
/// <param name="field">An interned field that holds both lower and upper terms.
/// </param>
/// <param name="lowerTermText">The term text at the lower end of the range
/// </param>
/// <param name="upperTermText">The term text at the upper end of the range
/// </param>
/// <param name="includeLower">If true, the <code>lowerTerm</code> is included in the range.
/// </param>
/// <param name="includeUpper">If true, the <code>upperTerm</code> is included in the range.
/// </param>
/// <param name="collator">The collator to use to collate index Terms, to determine their
/// membership in the range bounded by <code>lowerTerm</code> and
/// <code>upperTerm</code>.
///
/// </param>
/// <throws> IOException </throws>
public TermRangeTermEnum(IndexReader reader, System.String field, System.String lowerTermText, System.String upperTermText, bool includeLower, bool includeUpper, System.Globalization.CompareInfo collator)
{
this.collator = collator;
this.upperTermText = upperTermText;
this.lowerTermText = lowerTermText;
this.includeLower = includeLower;
this.includeUpper = includeUpper;
this.field = StringHelper.Intern(field);
// do a little bit of normalization...
// open ended range queries should always be inclusive.
if (this.lowerTermText == null)
{
this.lowerTermText = "";
this.includeLower = true;
}
if (this.upperTermText == null)
{
this.includeUpper = true;
}
System.String startTermText = collator == null?this.lowerTermText:"";
SetEnum(reader.Terms(new Term(this.field, startTermText)));
}
public override Query Rewrite(IndexReader reader)
{
BooleanQuery query = new BooleanQuery(true);
TermEnum enumerator = reader.Terms(prefix);
try
{
System.String prefixText = prefix.Text();
System.String prefixField = prefix.Field();
do
{
Term term = enumerator.Term();
#if !FRAMEWORK_1_1
if (term != null && term.Text().StartsWith(prefixText, StringComparison.Ordinal) && term.Field() == prefixField)
#else
if (term != null && term.Text().StartsWith(prefixText) && term.Field() == prefixField)
#endif
{
TermQuery tq = new TermQuery(term); // found a match
tq.SetBoost(GetBoost()); // set the boost
query.Add(tq, BooleanClause.Occur.SHOULD); // add to query
//System.out.println("added " + term);
}
else
{
break;
}
}while (enumerator.Next());
}
finally
{
enumerator.Close();
}
return(query);
}
protected internal override System.Object CreateValue(IndexReader reader, System.Object entryKey)
{
Entry entry = (Entry) entryKey;
System.String field = entry.field;
LongParser parser = (LongParser) entry.custom;
long[] retArray = new long[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field, ""));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object) term.Field() != (System.Object) field)
break;
long termval = parser.ParseLong(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
return retArray;
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = (Entry)entryKey;
System.String field = entry.field;
SortComparator comparator = (SortComparator)entry.custom;
System.IComparable[] retArray = new System.IComparable[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object)term.Field() != (System.Object)field)
{
break;
}
System.IComparable termval = comparator.GetComparable(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
return(retArray);
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
System.String field = StringHelper.Intern((System.String)entryKey.field);
System.String[] retArray = new System.String[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object)term.Field() != (System.Object)field)
{
break;
}
System.String termval = term.Text();
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
return(retArray);
}
public RegexTermEnum(IndexReader reader, Term term) : base()
{
field = term.Field();
System.String text = term.Text();
pattern = new Pattern(text);
// Find the first regex character position, to find the
// maximum prefix to use for term enumeration
int index = 0;
while (index < text.Length)
{
char c = text[index];
if (!System.Char.IsLetterOrDigit(c))
{
break;
}
index++;
}
pre = text.Substring(0, (index) - (0));
SetEnum(reader.Terms(new Term(term.Field(), pre)));
}
protected internal override object CreateValue(IndexReader reader, object entryKey)
{
Entry entry = (Entry)entryKey;
System.String field = entry.field;
LongParser parser = (LongParser)entry.custom;
long[] retArray = new long[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (object)term.Field() != (object)field)
{
break;
}
long termval = parser.ParseLong(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
return(retArray);
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey, IState state)
{
Entry entry = entryKey;
System.String field = entry.field;
IntParser parser = (IntParser)entry.custom;
if (parser == null)
{
try
{
return(wrapper.GetInts(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_INT_PARSER, state));
}
catch (System.FormatException)
{
return(wrapper.GetInts(reader, field, Lucene.Net.Search.FieldCache_Fields.NUMERIC_UTILS_INT_PARSER, state));
}
}
int[] retArray = null;
TermDocs termDocs = reader.TermDocs(state);
TermEnum termEnum = reader.Terms(new Term(field), state);
try
{
do
{
Term term = termEnum.Term;
if (term == null || (System.Object)term.Field != (System.Object)field)
{
break;
}
int termval = parser.ParseInt(term.Text);
if (retArray == null)
{
// late init
retArray = new int[reader.MaxDoc];
}
termDocs.Seek(termEnum, state);
while (termDocs.Next(state))
{
retArray[termDocs.Doc] = termval;
}
}while (termEnum.Next(state));
}
catch (StopFillCacheException)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (retArray == null)
{
// no values
retArray = new int[reader.MaxDoc];
}
return(retArray);
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = (Entry)entryKey;
System.String field = entry.field;
FloatParser parser = (FloatParser)entry.custom;
if (parser == null)
{
try
{
return(wrapper.GetFloats(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_FLOAT_PARSER));
}
catch (System.FormatException ne)
{
return(wrapper.GetFloats(reader, field, Lucene.Net.Search.FieldCache_Fields.NUMERIC_UTILS_FLOAT_PARSER));
}
}
float[] retArray = null;
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object)term.Field() != (System.Object)field)
{
break;
}
float termval = parser.ParseFloat(term.Text());
if (retArray == null)
{
// late init
retArray = new float[reader.MaxDoc()];
}
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
catch (StopFillCacheException stop)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (retArray == null)
{
// no values
retArray = new float[reader.MaxDoc()];
}
return(retArray);
}
public virtual void TestPhrasePrefix()
{
RAMDirectory indexStore = new RAMDirectory();
IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc1 = new Document();
Document doc2 = new Document();
Document doc3 = new Document();
Document doc4 = new Document();
Document doc5 = new Document();
doc1.Add(new Field("body", "blueberry pie", Field.Store.YES, Field.Index.ANALYZED));
doc2.Add(new Field("body", "blueberry strudel", Field.Store.YES, Field.Index.ANALYZED));
doc3.Add(new Field("body", "blueberry pizza", Field.Store.YES, Field.Index.ANALYZED));
doc4.Add(new Field("body", "blueberry chewing gum", Field.Store.YES, Field.Index.ANALYZED));
doc5.Add(new Field("body", "piccadilly circus", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc1);
writer.AddDocument(doc2);
writer.AddDocument(doc3);
writer.AddDocument(doc4);
writer.AddDocument(doc5);
writer.Optimize();
writer.Close();
IndexSearcher searcher = new IndexSearcher(indexStore);
//PhrasePrefixQuery query1 = new PhrasePrefixQuery();
MultiPhraseQuery query1 = new MultiPhraseQuery();
//PhrasePrefixQuery query2 = new PhrasePrefixQuery();
MultiPhraseQuery query2 = new MultiPhraseQuery();
query1.Add(new Term("body", "blueberry"));
query2.Add(new Term("body", "strawberry"));
System.Collections.ArrayList termsWithPrefix = new System.Collections.ArrayList();
IndexReader ir = IndexReader.Open(indexStore);
// this TermEnum gives "piccadilly", "pie" and "pizza".
System.String prefix = "pi";
TermEnum te = ir.Terms(new Term("body", prefix + "*"));
do
{
if (te.Term().Text().StartsWith(prefix))
{
termsWithPrefix.Add(te.Term());
}
}while (te.Next());
query1.Add((Term[])termsWithPrefix.ToArray(typeof(Term)));
query2.Add((Term[])termsWithPrefix.ToArray(typeof(Term)));
ScoreDoc[] result;
result = searcher.Search(query1, null, 1000).scoreDocs;
Assert.AreEqual(2, result.Length);
result = searcher.Search(query2, null, 1000).scoreDocs;
Assert.AreEqual(0, result.Length);
}
protected internal override object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = entryKey;
string field = entry.field;
Lucene.Net.Search.DoubleParser parser = (Lucene.Net.Search.DoubleParser)entry.custom;
if (parser == null)
{
try
{
return(wrapper.GetDoubles(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_DOUBLE_PARSER));
}
catch (System.FormatException)
{
return(wrapper.GetDoubles(reader, field, Lucene.Net.Search.FieldCache_Fields.NUMERIC_UTILS_DOUBLE_PARSER));
}
}
double[] retArray = null;
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term;
if (term == null || (object)term.Field != (object)field)
{
break;
}
double termval = parser.ParseDouble(term.Text);
if (retArray == null)
{
// late init
retArray = new double[reader.MaxDoc];
}
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc] = termval;
}
}while (termEnum.Next());
}
catch (StopFillCacheException)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (retArray == null)
{
// no values
retArray = new double[reader.MaxDoc];
}
return(retArray);
}
protected internal override object CreateValue(IndexReader reader, object fieldKey)
{
System.String field = String.Intern(((System.String)fieldKey));
TermEnum enumerator = reader.Terms(new Term(field));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine sort type");
}
object ret = null;
if ((object)term.Field() == (object)field)
{
System.String termtext = term.Text().Trim();
/**
* Java 1.4 level code:
*
* if (pIntegers.matcher(termtext).matches())
* return IntegerSortedHitQueue.comparator (reader, enumerator, field);
*
* else if (pFloats.matcher(termtext).matches())
* return FloatSortedHitQueue.comparator (reader, enumerator, field);
*/
// Java 1.3 level code:
try
{
System.Int32.Parse(termtext);
ret = Enclosing_Instance.GetInts(reader, field);
}
catch (System.FormatException)
{
try
{
SupportClass.Single.Parse(termtext);
ret = Enclosing_Instance.GetFloats(reader, field);
}
catch (System.FormatException)
{
ret = Enclosing_Instance.GetStringIndex(reader, field);
}
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
return(ret);
}
finally
{
enumerator.Close();
}
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
System.String field = StringHelper.Intern((System.String)entryKey.field);
TermEnum enumerator = reader.Terms(new Term(field));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine type");
}
System.Object ret = null;
if ((System.Object)term.Field() == (System.Object)field)
{
System.String termtext = term.Text().Trim();
try
{
System.Int32.Parse(termtext);
ret = wrapper.GetInts(reader, field);
}
catch (System.FormatException nfe1)
{
try
{
System.Int64.Parse(termtext);
ret = wrapper.GetLongs(reader, field);
}
catch (System.FormatException nfe2)
{
try
{
SupportClass.Single.Parse(termtext);
ret = wrapper.GetFloats(reader, field);
}
catch (System.FormatException nfe3)
{
ret = wrapper.GetStringIndex(reader, field);
}
}
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
return(ret);
}
finally
{
enumerator.Close();
}
}
public override Query Rewrite(IndexReader reader)
{
BooleanQuery query = new BooleanQuery(true);
TermEnum enumerator = reader.Terms(lowerTerm);
try
{
bool checkLower = false;
if (!inclusive)
{
// make adjustments to set to exclusive
checkLower = true;
}
System.String testField = GetField();
do
{
Term term = enumerator.Term();
if (term != null && term.Field() == testField)
{
// interned comparison
if (!checkLower || String.CompareOrdinal(term.Text(), lowerTerm.Text()) > 0)
{
checkLower = false;
if (upperTerm != null)
{
int compare = String.CompareOrdinal(upperTerm.Text(), term.Text());
/* if beyond the upper term, or is exclusive and
* this is equal to the upper term, break out */
if ((compare < 0) || (!inclusive && compare == 0))
{
break;
}
}
TermQuery tq = new TermQuery(term); // found a match
tq.SetBoost(GetBoost()); // set the boost
query.Add(tq, BooleanClause.Occur.SHOULD); // add to query
}
}
else
{
break;
}
}while (enumerator.Next());
}
finally
{
enumerator.Close();
}
return(query);
}
// inherit javadocs
public virtual float[] GetFloats(IndexReader reader, System.String field, FloatParser parser)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, parser);
if (ret == null)
{
float[] retArray = new float[reader.MaxDoc()];
if (retArray.Length > 0)
{
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field, ""));
try
{
if (termEnum.Term() == null)
{
throw new System.SystemException("no terms in field " + field);
}
do
{
Term term = termEnum.Term();
if (term.Field() != field)
{
break;
}
float termval;
try
{
termval = SupportClass.Single.Parse(term.Text());
}
catch (Exception e)
{
termval = 0;
}
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
}
Store(reader, field, parser, retArray);
return(retArray);
}
return((float[])ret);
}
public override Query Rewrite(IndexReader reader)
{
BooleanQuery query = new BooleanQuery(true);
TermEnum enumerator = reader.Terms(lowerTerm);
try
{
bool checkLower = false;
if (!inclusive)
// make adjustments to set to exclusive
checkLower = true;
System.String testField = GetField();
do
{
Term term = enumerator.Term();
if (term != null && term.Field() == testField)
{
if (!checkLower || String.CompareOrdinal(term.Text(), lowerTerm.Text()) > 0)
{
checkLower = false;
if (upperTerm != null)
{
int compare = String.CompareOrdinal(upperTerm.Text(), term.Text());
/* if beyond the upper term, or is exclusive and
* this is equal to the upper term, break out */
if ((compare < 0) || (!inclusive && compare == 0))
break;
}
TermQuery tq = new TermQuery(term); // found a match
tq.SetBoost(GetBoost()); // set the boost
query.Add(tq, BooleanClause.Occur.SHOULD); // add to query
}
}
else
{
break;
}
}
while (enumerator.Next());
}
finally
{
enumerator.Close();
}
return query;
}
public virtual ScoreDocComparator NewComparator(IndexReader reader, System.String fieldname)
{
System.String field = String.Intern(fieldname);
TermEnum enumerator = reader.Terms(new Term(fieldname, ""));
try
{
return(new AnonymousClassScoreDocComparator(reader, enumerator, field, this));
}
finally
{
enumerator.Close();
}
}
internal static int DetectFieldType(IndexReader reader, System.String fieldKey)
{
System.String field = StringHelper.Intern(fieldKey);
TermEnum enumerator = reader.Terms(new Term(field));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine sort type");
}
int ret = 0;
if ((System.Object)term.Field() == (System.Object)field)
{
System.String termtext = term.Text().Trim();
int tmpI32; long tmpI64; float tmpF;
if (System.Int32.TryParse(termtext, out tmpI32))
{
ret = SortField.INT;
}
else if (System.Int64.TryParse(termtext, out tmpI64))
{
ret = SortField.LONG;
}
else if (SupportClass.Single.TryParse(termtext, out tmpF))
{
ret = SortField.FLOAT;
}
else
{
ret = SortField.STRING;
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
return(ret);
}
finally
{
enumerator.Close();
}
}
/// <summary>Increments the enumeration to the next element. True if one exists. </summary>
//@Override
public override bool Next()
{
// if a current term exists, the actual enum is initialized:
// try change to next term, if no such term exists, fall-through
if (currentTerm != null)
{
System.Diagnostics.Debug.Assert(actualEnum != null);
if (actualEnum.Next())
{
currentTerm = actualEnum.Term();
if (TermCompare(currentTerm))
{
return(true);
}
}
}
// if all above fails, we go forward to the next enum,
// if one is available
currentTerm = null;
if (rangeBounds.Count < 2)
{
return(false);
}
// close the current enum and read next bounds
if (actualEnum != null)
{
actualEnum.Close();
actualEnum = null;
}
string tempObject;
tempObject = rangeBounds.First.Value;
rangeBounds.RemoveFirst();
string lowerBound = tempObject;
string tempObject2;
tempObject2 = rangeBounds.First.Value;
rangeBounds.RemoveFirst();
this.currentUpperBound = tempObject2;
// this call recursively uses next(), if no valid term in
// next enum found.
// if this behavior is changed/modified in the superclass,
// this enum will not work anymore!
SetEnum(reader.Terms(new Term(Enclosing_Instance.field, lowerBound)));
return(currentTerm != null);
}
// inherit javadocs
public virtual System.IComparable[] GetCustom(IndexReader reader, System.String field, SortComparator comparator)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, comparator);
if (ret == null)
{
System.IComparable[] retArray = new System.IComparable[reader.MaxDoc()];
if (retArray.Length > 0)
{
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field, ""));
try
{
if (termEnum.Term() == null)
{
throw new System.SystemException("no terms in field " + field);
}
do
{
Term term = termEnum.Term();
if (term.Field() != field)
{
break;
}
System.IComparable termval = comparator.GetComparable(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
}
Store(reader, field, comparator, retArray);
return(retArray);
}
return((System.IComparable[])ret);
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey, IState state)
{
Entry entry = entryKey;
System.String field = entry.field;
ByteParser parser = (ByteParser)entry.custom;
if (parser == null)
{
return(wrapper.GetBytes(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_BYTE_PARSER, state));
}
sbyte[] retArray = new sbyte[reader.MaxDoc];
TermDocs termDocs = reader.TermDocs(state);
TermEnum termEnum = reader.Terms(new Term(field), state);
try
{
do
{
Term term = termEnum.Term;
if (term == null || (System.Object)term.Field != (System.Object)field)
{
break;
}
sbyte termval = parser.ParseByte(term.Text);
termDocs.Seek(termEnum, state);
while (termDocs.Next(state))
{
retArray[termDocs.Doc] = termval;
}
}while (termEnum.Next(state));
}
catch (StopFillCacheException)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
return(retArray);
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = (Entry)entryKey;
System.String field = entry.field;
ShortParser parser = (ShortParser)entry.custom;
if (parser == null)
{
return(wrapper.GetShorts(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_SHORT_PARSER));
}
short[] retArray = new short[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object)term.Field() != (System.Object)field)
{
break;
}
short termval = parser.ParseShort(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
catch (StopFillCacheException stop)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
return(retArray);
}
/// <summary> Creates a new <c>WildcardTermEnum</c>.
/// <p/>
/// After calling the constructor the enumeration is already pointing to the first
/// valid term if such a term exists.
/// </summary>
public WildcardTermEnum(IndexReader reader, Term term):base()
{
searchTerm = term;
field = searchTerm.Field;
System.String searchTermText = searchTerm.Text;
int sidx = searchTermText.IndexOf((System.Char) WILDCARD_STRING);
int cidx = searchTermText.IndexOf((System.Char) WILDCARD_CHAR);
int idx = sidx;
if (idx == - 1)
{
idx = cidx;
}
else if (cidx >= 0)
{
idx = System.Math.Min(idx, cidx);
}
pre = idx != - 1?searchTerm.Text.Substring(0, (idx) - (0)):"";
preLen = pre.Length;
text = searchTermText.Substring(preLen);
SetEnum(reader.Terms(new Term(searchTerm.Field, pre)));
}
// inherit javadocs
public virtual int[] GetInts(IndexReader reader, System.String field, IntParser parser)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, parser);
if (ret == null)
{
int[] retArray = new int[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field, ""));
try
{
do
{
Term term = termEnum.Term();
if (term == null || term.Field() != field)
{
break;
}
int termval = parser.ParseInt(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
Store(reader, field, parser, retArray);
return(retArray);
}
return((int[])ret);
}
/// <summary> Creates a new <c>WildcardTermEnum</c>.
/// <p/>
/// After calling the constructor the enumeration is already pointing to the first
/// valid term if such a term exists.
/// </summary>
public WildcardTermEnum(IndexReader reader, Term term, IState state) : base()
{
searchTerm = term;
field = searchTerm.Field;
System.String searchTermText = searchTerm.Text;
int sidx = searchTermText.IndexOf((System.Char)WILDCARD_STRING);
int cidx = searchTermText.IndexOf((System.Char)WILDCARD_CHAR);
int idx = sidx;
if (idx == -1)
{
idx = cidx;
}
else if (cidx >= 0)
{
idx = System.Math.Min(idx, cidx);
}
pre = idx != -1?searchTerm.Text.Substring(0, (idx) - (0)):"";
preLen = pre.Length;
text = searchTermText.Substring(preLen);
SetEnum(reader.Terms(new Term(searchTerm.Field, pre), state), state);
}
/// <summary> Creates a new <code>WildcardTermEnum</code>. Passing in a
/// {@link Lucene.Net.Index.Term Term} that does not contain a
/// <code>WILDCARD_CHAR</code> will cause an exception to be thrown.
/// <p>
/// After calling the constructor the enumeration is already pointing to the first
/// valid term if such a term exists.
/// </summary>
public WildcardTermEnum(IndexReader reader, Term term) : base()
{
searchTerm = term;
field = searchTerm.Field();
text = searchTerm.Text();
int sidx = text.IndexOf((System.Char)WILDCARD_STRING);
int cidx = text.IndexOf((System.Char)WILDCARD_CHAR);
int idx = sidx;
if (idx == -1)
{
idx = cidx;
}
else if (cidx >= 0)
{
idx = System.Math.Min(idx, cidx);
}
pre = searchTerm.Text().Substring(0, (idx) - (0));
preLen = pre.Length;
text = text.Substring(preLen);
SetEnum(reader.Terms(new Term(searchTerm.Field(), pre)));
}
// inherit javadocs
public virtual System.String[] GetStrings(IndexReader reader, System.String field)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, SortField.STRING, null);
if (ret == null)
{
System.String[] retArray = new System.String[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field, ""));
try
{
do
{
Term term = termEnum.Term();
if (term == null || term.Field() != field)
{
break;
}
System.String termval = term.Text();
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
Store(reader, field, SortField.STRING, null, retArray);
return(retArray);
}
return((System.String[])ret);
}
protected internal override object CreateValue(IndexReader reader, object fieldKey)
{
System.String field = String.Intern(((System.String) fieldKey));
System.String[] retArray = new System.String[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (object) term.Field() != (object) field)
break;
System.String termval = term.Text();
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
return retArray;
}
internal static int DetectFieldType(IndexReader reader, System.String fieldKey)
{
System.String field = StringHelper.Intern(fieldKey);
TermEnum enumerator = reader.Terms(new Term(field));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine sort type");
}
int ret = 0;
if ((System.Object) term.Field() == (System.Object) field)
{
System.String termtext = term.Text().Trim();
int tmpI32; long tmpI64; float tmpF;
if (System.Int32.TryParse(termtext, out tmpI32)) ret = SortField.INT;
else if (System.Int64.TryParse(termtext, out tmpI64)) ret = SortField.LONG;
else if (SupportClass.Single.TryParse(termtext, out tmpF)) ret = SortField.FLOAT;
else ret = SortField.STRING;
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
return ret;
}
finally
{
enumerator.Close();
}
}
/// <summary> Constructor for enumeration of all terms from specified <c>reader</c> which share a prefix of
/// length <c>prefixLength</c> with <c>term</c> and which have a fuzzy similarity >
/// <c>minSimilarity</c>.
/// <p/>
/// After calling the constructor the enumeration is already pointing to the first
/// valid term if such a term exists.
///
/// </summary>
/// <param name="reader">Delivers terms.
/// </param>
/// <param name="term">Pattern term.
/// </param>
/// <param name="minSimilarity">Minimum required similarity for terms from the reader. Default value is 0.5f.
/// </param>
/// <param name="prefixLength">Length of required common prefix. Default value is 0.
/// </param>
/// <throws> IOException </throws>
public FuzzyTermEnum(IndexReader reader, Term term, float minSimilarity, int prefixLength):base()
{
if (minSimilarity >= 1.0f)
throw new System.ArgumentException("minimumSimilarity cannot be greater than or equal to 1");
else if (minSimilarity < 0.0f)
throw new System.ArgumentException("minimumSimilarity cannot be less than 0");
if (prefixLength < 0)
throw new System.ArgumentException("prefixLength cannot be less than 0");
this.minimumSimilarity = minSimilarity;
this.scale_factor = 1.0f / (1.0f - minimumSimilarity);
this.searchTerm = term;
this.field = searchTerm.Field;
//The prefix could be longer than the word.
//It's kind of silly though. It means we must match the entire word.
int fullSearchTermLength = searchTerm.Text.Length;
int realPrefixLength = prefixLength > fullSearchTermLength?fullSearchTermLength:prefixLength;
this.text = searchTerm.Text.Substring(realPrefixLength);
this.prefix = searchTerm.Text.Substring(0, (realPrefixLength) - (0));
this.p = new int[this.text.Length + 1];
this.d = new int[this.text.Length + 1];
SetEnum(reader.Terms(new Term(searchTerm.Field, prefix)));
}
/// <summary> Returns a DocIdSet with documents that should be
/// permitted in search results.
/// </summary>
public override DocIdSet GetDocIdSet(IndexReader reader)
{
OpenBitSet bits = new OpenBitSet(reader.MaxDoc());
TermEnum enumerator = (null != lowerTerm && collator == null ?
reader.Terms(new Term(fieldName, lowerTerm)) :
reader.Terms(new Term(fieldName)));
try
{
if (enumerator.Term() == null)
{
return bits;
}
TermDocs termDocs = reader.TermDocs();
try
{
if (collator != null)
{
do
{
Term term = enumerator.Term();
if (term != null && term.Field().Equals(fieldName))
{
if ((lowerTerm == null ||
(includeLower ? collator.Compare(term.Text(), lowerTerm) >= 0 : collator.Compare(term.Text(), lowerTerm) > 0)) &&
(upperTerm == null ||
(includeUpper ? collator.Compare(term.Text(), upperTerm) <= 0 : collator.Compare(term.Text(), upperTerm) < 0)))
{
// term in range, lookup docs
termDocs.Seek(enumerator.Term());
while (termDocs.Next())
{
bits.Set(termDocs.Doc());
}
}
}
}
while (enumerator.Next());
}
else // null collator; using Unicode code point ordering
{
bool checkLower = false;
if (!includeLower) // make adjustments to set to exclusive
checkLower = true;
do
{
Term term = enumerator.Term();
if (term != null && term.Field().Equals(fieldName))
{
if (!checkLower || null == lowerTerm || String.CompareOrdinal(term.Text(), lowerTerm) > 0)
{
checkLower = false;
if (upperTerm != null)
{
int compare = String.CompareOrdinal(upperTerm, term.Text());
/* if beyond the upper term, or is exclusive and
* this is equal to the upper term, break out */
if ((compare < 0) || (!includeUpper && compare == 0))
{
break;
}
}
/* we have a good term, find the docs */
termDocs.Seek(enumerator.Term());
while (termDocs.Next())
{
bits.Set(termDocs.Doc());
}
}
}
else
{
break;
}
}
while (enumerator.Next());
}
}
finally
{
termDocs.Close();
}
}
finally
{
enumerator.Close();
}
return bits;
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = (Entry) entryKey;
System.String field = entry.field;
SortComparator comparator = (SortComparator) entry.custom;
System.IComparable[] retArray = new System.IComparable[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object) term.Field() != (System.Object) field)
break;
System.IComparable termval = comparator.GetComparable(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
return retArray;
}
/// <summary>The pattern used to detect integer values in a field </summary>
/// <summary>removed for java 1.3 compatibility
/// protected static final Pattern pIntegers = Pattern.compile ("[0-9\\-]+");
///
/// </summary>
/// <summary>The pattern used to detect float values in a field </summary>
/// <summary> removed for java 1.3 compatibility
/// protected static final Object pFloats = Pattern.compile ("[0-9+\\-\\.eEfFdD]+");
/// </summary>
// inherit javadocs
public virtual System.Object GetAuto(IndexReader reader, System.String field)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, SortField.AUTO);
if (ret == null)
{
TermEnum enumerator = reader.Terms(new Term(field, ""));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine sort type");
}
if (term.Field() == field)
{
System.String termtext = term.Text().Trim();
/**
* Java 1.4 level code:
if (pIntegers.matcher(termtext).matches())
return IntegerSortedHitQueue.comparator (reader, enumerator, field);
else if (pFloats.matcher(termtext).matches())
return FloatSortedHitQueue.comparator (reader, enumerator, field);
*/
// Java 1.3 level code:
try
{
System.Int32.Parse(termtext);
ret = GetInts(reader, field);
}
catch (System.FormatException nfe1)
{
try
{
System.Single.Parse(termtext);
ret = GetFloats(reader, field);
}
catch (System.FormatException nfe2)
{
ret = GetStringIndex(reader, field);
}
}
if (ret != null)
{
Store(reader, field, SortField.AUTO, ret);
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
}
finally
{
enumerator.Close();
}
}
return ret;
}
// inherit javadocs
public virtual System.IComparable[] GetCustom(IndexReader reader, System.String field, SortComparator comparator)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, comparator);
if (ret == null)
{
System.IComparable[] retArray = new System.IComparable[reader.MaxDoc()];
if (retArray.Length > 0)
{
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field, ""));
try
{
if (termEnum.Term() == null)
{
throw new System.SystemException("no terms in field " + field);
}
do
{
Term term = termEnum.Term();
if (term.Field() != field)
break;
System.IComparable termval = comparator.GetComparable(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
}
Store(reader, field, comparator, retArray);
return retArray;
}
return (System.IComparable[]) ret;
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
System.String field = StringHelper.Intern((System.String)entryKey.field);
int[] retArray = new int[reader.MaxDoc()];
System.String[] mterms = new System.String[reader.MaxDoc() + 1];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
int t = 0; // current term number
// an entry for documents that have no terms in this field
// should a document with no terms be at top or bottom?
// this puts them at the top - if it is changed, FieldDocSortedHitQueue
// needs to change as well.
mterms[t++] = null;
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object)term.Field() != (System.Object)field)
{
break;
}
// store term text
// we expect that there is at most one term per document
if (t >= mterms.Length)
{
throw new System.SystemException("there are more terms than " + "documents in field \"" + field + "\", but it's impossible to sort on " + "tokenized fields");
}
mterms[t] = term.Text();
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = t;
}
t++;
}while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (t == 0)
{
// if there are no terms, make the term array
// have a single null entry
mterms = new System.String[1];
}
else if (t < mterms.Length)
{
// if there are less terms than documents,
// trim off the dead array space
System.String[] terms = new System.String[t];
Array.Copy(mterms, 0, terms, 0, t);
mterms = terms;
}
StringIndex value_Renamed = new StringIndex(retArray, mterms);
return(value_Renamed);
}
/* Walk directory hierarchy in uid order, while keeping uid iterator from
/* existing index in sync. Mismatches indicate one of: (a) old documents to
/* be deleted; (b) unchanged documents, to be left alone; or (c) new
/* documents, to be indexed.
*/
private static void IndexDocs(System.IO.DirectoryInfo file, System.IO.DirectoryInfo index, bool create)
{
if (!create)
{
// incrementally update
reader = IndexReader.Open(FSDirectory.Open(index), false); // open existing index
uidIter = reader.Terms(new Term("uid", "")); // init uid iterator
IndexDocs(file);
if (deleting)
{
// delete rest of stale docs
while (uidIter.Term() != null && (System.Object) uidIter.Term().Field == (System.Object) "uid")
{
System.Console.Out.WriteLine("deleting " + HTMLDocument.Uid2url(uidIter.Term().Text));
reader.DeleteDocuments(uidIter.Term());
uidIter.Next();
}
deleting = false;
}
uidIter.Close(); // close uid iterator
reader.Close(); // close existing index
}
// don't have exisiting
else
IndexDocs(file);
}
public virtual void Generate(IndexReader reader)
{
TermEnum enumerator = reader.Terms(prefix);
TermDocs termDocs = reader.TermDocs();
try
{
System.String prefixText = prefix.Text();
System.String prefixField = prefix.Field();
do
{
Term term = enumerator.Term();
if (term != null && term.Text().StartsWith(prefixText) && (System.Object) term.Field() == (System.Object) prefixField)
{
termDocs.Seek(term);
while (termDocs.Next())
{
HandleDoc(termDocs.Doc());
}
}
else
{
break;
}
}
while (enumerator.Next());
}
finally
{
termDocs.Close();
enumerator.Close();
}
}
/// <summary> Enumerates all terms greater/equal than <c>lowerTerm</c>
/// but less/equal than <c>upperTerm</c>.
///
/// If an endpoint is null, it is said to be "open". Either or both
/// endpoints may be open. Open endpoints may not be exclusive
/// (you can't select all but the first or last term without
/// explicitly specifying the term to exclude.)
///
/// </summary>
/// <param name="reader">
/// </param>
/// <param name="field">An interned field that holds both lower and upper terms.
/// </param>
/// <param name="lowerTermText">The term text at the lower end of the range
/// </param>
/// <param name="upperTermText">The term text at the upper end of the range
/// </param>
/// <param name="includeLower">If true, the <c>lowerTerm</c> is included in the range.
/// </param>
/// <param name="includeUpper">If true, the <c>upperTerm</c> is included in the range.
/// </param>
/// <param name="collator">The collator to use to collate index Terms, to determine their
/// membership in the range bounded by <c>lowerTerm</c> and
/// <c>upperTerm</c>.
///
/// </param>
/// <throws> IOException </throws>
public TermRangeTermEnum(IndexReader reader, System.String field, System.String lowerTermText, System.String upperTermText, bool includeLower, bool includeUpper, System.Globalization.CompareInfo collator)
{
this.collator = collator;
this.upperTermText = upperTermText;
this.lowerTermText = lowerTermText;
this.includeLower = includeLower;
this.includeUpper = includeUpper;
this.field = StringHelper.Intern(field);
// do a little bit of normalization...
// open ended range queries should always be inclusive.
if (this.lowerTermText == null)
{
this.lowerTermText = "";
this.includeLower = true;
}
if (this.upperTermText == null)
{
this.includeUpper = true;
}
System.String startTermText = collator == null?this.lowerTermText:"";
SetEnum(reader.Terms(new Term(this.field, startTermText)));
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = (Entry) entryKey;
System.String field = entry.field;
FloatParser parser = (FloatParser) entry.custom;
if (parser == null)
{
try
{
return wrapper.GetFloats(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_FLOAT_PARSER);
}
catch (System.FormatException ne)
{
return wrapper.GetFloats(reader, field, Lucene.Net.Search.FieldCache_Fields.NUMERIC_UTILS_FLOAT_PARSER);
}
}
float[] retArray = null;
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object) term.Field() != (System.Object) field)
break;
float termval = parser.ParseFloat(term.Text());
if (retArray == null)
// late init
retArray = new float[reader.MaxDoc()];
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}
while (termEnum.Next());
}
catch (StopFillCacheException stop)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (retArray == null)
// no values
retArray = new float[reader.MaxDoc()];
return retArray;
}
public PrefixTermEnum(IndexReader reader, Term prefix)
{
this.prefix = prefix;
SetEnum(reader.Terms(new Term(prefix.Field, prefix.Text)));
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = entryKey;
System.String field = entry.field;
ShortParser parser = (ShortParser) entry.custom;
if (parser == null)
{
return wrapper.GetShorts(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_SHORT_PARSER);
}
short[] retArray = new short[reader.MaxDoc];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term;
if (term == null || (System.Object) term.Field != (System.Object) field)
break;
short termval = parser.ParseShort(term.Text);
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc] = termval;
}
}
while (termEnum.Next());
}
catch (StopFillCacheException)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
return retArray;
}
/// <summary> Returns a BitSet with true for documents which should be
/// permitted in search results, and false for those that should
/// not.
/// </summary>
public override System.Collections.BitArray Bits(IndexReader reader)
{
System.Collections.BitArray bits = new System.Collections.BitArray((reader.MaxDoc() % 64 == 0?reader.MaxDoc() / 64:reader.MaxDoc() / 64 + 1) * 64);
TermEnum enumerator = reader.Terms(new Term(field, start));
TermDocs termDocs = reader.TermDocs();
if (enumerator.Term() == null)
{
return bits;
}
try
{
Term stop = new Term(field, end);
while (enumerator.Term().CompareTo(stop) <= 0)
{
termDocs.Seek(enumerator.Term());
while (termDocs.Next())
{
bits.Set(termDocs.Doc(), true);
}
if (!enumerator.Next())
{
break;
}
}
}
finally
{
enumerator.Close();
termDocs.Close();
}
return bits;
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
System.String field = StringHelper.Intern(entryKey.field);
System.String[] retArray = new System.String[reader.MaxDoc];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term;
if (term == null || (System.Object) term.Field != (System.Object) field)
break;
System.String termval = term.Text;
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc] = termval;
}
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
return retArray;
}
protected internal override System.Object CreateValue(IndexReader reader, System.Object fieldKey)
{
System.String field = String.Intern(((System.String) fieldKey));
TermEnum enumerator = reader.Terms(new Term(field, ""));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine sort type");
}
System.Object ret = null;
if ((System.Object) term.Field() == (System.Object) field)
{
System.String termtext = term.Text().Trim();
/**
* Java 1.4 level code:
if (pIntegers.matcher(termtext).matches())
return IntegerSortedHitQueue.comparator (reader, enumerator, field);
else if (pFloats.matcher(termtext).matches())
return FloatSortedHitQueue.comparator (reader, enumerator, field);
*/
// Java 1.3 level code:
try
{
int parsedIntValue;
long parsedLongValue;
if (int.TryParse(termtext, out parsedIntValue))
{
ret = Enclosing_Instance.GetInts(reader, field);
}
else if (long.TryParse(termtext, out parsedLongValue))
{
ret = ((ExtendedFieldCacheImpl)Enclosing_Instance).GetLongs(reader, field);
}
else
{
float f = 0.0f;
if (SupportClass.Single.TryParse(termtext, out f))
{
ret = Enclosing_Instance.GetFloats(reader, field);
}
else
{
ret = Enclosing_Instance.GetStringIndex(reader, field);
}
}
}
catch (System.Exception)
{
ret = Enclosing_Instance.GetStringIndex(reader, field);
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
return ret;
}
finally
{
enumerator.Close();
}
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
System.String field = StringHelper.Intern((System.String) entryKey.field);
int[] retArray = new int[reader.MaxDoc()];
System.String[] mterms = new System.String[reader.MaxDoc() + 1];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
int t = 0; // current term number
// an entry for documents that have no terms in this field
// should a document with no terms be at top or bottom?
// this puts them at the top - if it is changed, FieldDocSortedHitQueue
// needs to change as well.
mterms[t++] = null;
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object) term.Field() != (System.Object) field)
break;
// store term text
// we expect that there is at most one term per document
if (t >= mterms.Length)
throw new System.SystemException("there are more terms than " + "documents in field \"" + field + "\", but it's impossible to sort on " + "tokenized fields");
mterms[t] = term.Text();
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = t;
}
t++;
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (t == 0)
{
// if there are no terms, make the term array
// have a single null entry
mterms = new System.String[1];
}
else if (t < mterms.Length)
{
// if there are less terms than documents,
// trim off the dead array space
System.String[] terms = new System.String[t];
Array.Copy(mterms, 0, terms, 0, t);
mterms = terms;
}
StringIndex value_Renamed = new StringIndex(retArray, mterms);
return value_Renamed;
}
// inherit javadocs
public virtual StringIndex GetStringIndex(IndexReader reader, System.String field)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, Lucene.Net.Search.FieldCache_Fields.STRING_INDEX);
if (ret == null)
{
int[] retArray = new int[reader.MaxDoc()];
System.String[] mterms = new System.String[reader.MaxDoc() + 1];
if (retArray.Length > 0)
{
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field, ""));
int t = 0; // current term number
// an entry for documents that have no terms in this field
// should a document with no terms be at top or bottom?
// this puts them at the top - if it is changed, FieldDocSortedHitQueue
// needs to change as well.
mterms[t++] = null;
try
{
if (termEnum.Term() == null)
{
throw new System.SystemException("no terms in field " + field);
}
do
{
Term term = termEnum.Term();
if (term.Field() != field)
break;
// store term text
// we expect that there is at most one term per document
if (t >= mterms.Length)
throw new System.SystemException("there are more terms than " + "documents in field \"" + field + "\", but it's impossible to sort on " + "tokenized fields");
mterms[t] = term.Text();
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = t;
}
t++;
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (t == 0)
{
// if there are no terms, make the term array
// have a single null entry
mterms = new System.String[1];
}
else if (t < mterms.Length)
{
// if there are less terms than documents,
// trim off the dead array space
System.String[] terms = new System.String[t];
Array.Copy(mterms, 0, terms, 0, t);
mterms = terms;
}
}
StringIndex value_Renamed = new StringIndex(retArray, mterms);
Store(reader, field, Lucene.Net.Search.FieldCache_Fields.STRING_INDEX, value_Renamed);
return value_Renamed;
}
return (StringIndex) ret;
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
System.String field = StringHelper.Intern((System.String) entryKey.field);
TermEnum enumerator = reader.Terms(new Term(field));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine type");
}
System.Object ret = null;
if ((System.Object) term.Field() == (System.Object) field)
{
System.String termtext = term.Text().Trim();
try
{
System.Int32.Parse(termtext);
ret = wrapper.GetInts(reader, field);
}
catch (System.FormatException nfe1)
{
try
{
System.Int64.Parse(termtext);
ret = wrapper.GetLongs(reader, field);
}
catch (System.FormatException nfe2)
{
try
{
SupportClass.Single.Parse(termtext);
ret = wrapper.GetFloats(reader, field);
}
catch (System.FormatException nfe3)
{
ret = wrapper.GetStringIndex(reader, field);
}
}
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
return ret;
}
finally
{
enumerator.Close();
}
}
public override Query Rewrite(IndexReader reader)
{
BooleanQuery query = new BooleanQuery(true);
string testField = GetField();
if (collator != null)
{
TermEnum enumerator = reader.Terms(new Term(testField, ""));
string lowerTermText = lowerTerm != null ? lowerTerm.Text() : null;
string upperTermText = upperTerm != null ? upperTerm.Text() : null;
try
{
do
{
Term term = enumerator.Term();
if (term != null && term.Field() == testField) // interned comparison
{
if ((lowerTermText == null ||
(inclusive ? collator.Compare(term.Text(), lowerTermText) >= 0 : collator.Compare(term.Text(), lowerTermText) > 0))
&&
(upperTermText == null ||
(inclusive ? collator.Compare(term.Text(), upperTermText) <= 0 : collator.Compare(term.Text(), upperTermText) < 0))
)
{
AddTermToQuery(term, query);
}
}
}
while (enumerator.Next());
}
finally
{
enumerator.Close();
}
}
else
{
TermEnum enumerator = reader.Terms(lowerTerm);
try
{
bool checkLower = false;
if (!inclusive)
// make adjustments to set to exclusive
checkLower = true;
do
{
Term term = enumerator.Term();
if (term != null && term.Field() == testField)
{
// interned comparison
if (!checkLower || String.CompareOrdinal(term.Text(), lowerTerm.Text()) > 0)
{
checkLower = false;
if (upperTerm != null)
{
int compare = String.CompareOrdinal(upperTerm.Text(), term.Text());
/* if beyond the upper term, or is exclusive and
* this is equal to the upper term, break out */
if ((compare < 0) || (!inclusive && compare == 0))
break;
}
AddTermToQuery(term, query); // Found a match
}
}
else
{
break;
}
}
while (enumerator.Next());
}
finally
{
enumerator.Close();
}
}
return query;
}
public virtual ScoreDocComparator NewComparator(IndexReader reader, System.String fieldname)
{
System.String field = String.Intern(fieldname);
TermEnum enumerator = reader.Terms(new Term(fieldname, ""));
try
{
return new AnonymousClassScoreDocComparator(reader, enumerator, field, this);
}
finally
{
enumerator.Close();
}
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = entryKey;
System.String field = entry.field;
Lucene.Net.Search.DoubleParser parser = (Lucene.Net.Search.DoubleParser) entry.custom;
if (parser == null)
{
try
{
return wrapper.GetDoubles(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_DOUBLE_PARSER);
}
catch (System.FormatException)
{
return wrapper.GetDoubles(reader, field, Lucene.Net.Search.FieldCache_Fields.NUMERIC_UTILS_DOUBLE_PARSER);
}
}
double[] retArray = null;
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term;
if (term == null || (System.Object) term.Field != (System.Object) field)
break;
double termval = parser.ParseDouble(term.Text);
if (retArray == null)
// late init
retArray = new double[reader.MaxDoc];
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc] = termval;
}
}
while (termEnum.Next());
}
catch (StopFillCacheException)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (retArray == null)
// no values
retArray = new double[reader.MaxDoc];
return retArray;
}
protected internal override object CreateValue(IndexReader reader, object fieldKey)
{
System.String field = String.Intern(((System.String) fieldKey));
TermEnum enumerator = reader.Terms(new Term(field));
try
{
Term term = enumerator.Term();
if (term == null)
{
throw new System.SystemException("no terms in field " + field + " - cannot determine sort type");
}
object ret = null;
if ((object) term.Field() == (object) field)
{
System.String termtext = term.Text().Trim();
/**
* Java 1.4 level code:
if (pIntegers.matcher(termtext).matches())
return IntegerSortedHitQueue.comparator (reader, enumerator, field);
else if (pFloats.matcher(termtext).matches())
return FloatSortedHitQueue.comparator (reader, enumerator, field);
*/
// Java 1.3 level code:
try
{
System.Int32.Parse(termtext);
ret = Enclosing_Instance.GetInts(reader, field);
}
catch (System.FormatException)
{
try
{
SupportClass.Single.Parse(termtext);
ret = Enclosing_Instance.GetFloats(reader, field);
}
catch (System.FormatException)
{
ret = Enclosing_Instance.GetStringIndex(reader, field);
}
}
}
else
{
throw new System.SystemException("field \"" + field + "\" does not appear to be indexed");
}
return ret;
}
finally
{
enumerator.Close();
}
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
System.String field = StringHelper.Intern(entryKey.field);
int[] retArray = new int[reader.MaxDoc];
System.String[] mterms = new System.String[reader.MaxDoc + 1];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
int t = 0; // current term number
// an entry for documents that have no terms in this field
// should a document with no terms be at top or bottom?
// this puts them at the top - if it is changed, FieldDocSortedHitQueue
// needs to change as well.
mterms[t++] = null;
try
{
do
{
Term term = termEnum.Term;
if (term == null || term.Field != field || t >= mterms.Length) break;
// store term text
mterms[t] = term.Text;
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc] = t;
}
t++;
}
while (termEnum.Next());
}
finally
{
termDocs.Close();
termEnum.Close();
}
if (t == 0)
{
// if there are no terms, make the term array
// have a single null entry
mterms = new System.String[1];
}
else if (t < mterms.Length)
{
// if there are less terms than documents,
// trim off the dead array space
System.String[] terms = new System.String[t];
Array.Copy(mterms, 0, terms, 0, t);
mterms = terms;
}
StringIndex value_Renamed = new StringIndex(retArray, mterms);
return value_Renamed;
}
protected internal override System.Object CreateValue(IndexReader reader, Entry entryKey)
{
Entry entry = (Entry) entryKey;
System.String field = entry.field;
ByteParser parser = (ByteParser) entry.custom;
if (parser == null)
{
return wrapper.GetBytes(reader, field, Lucene.Net.Search.FieldCache_Fields.DEFAULT_BYTE_PARSER);
}
byte[] retArray = new byte[reader.MaxDoc()];
TermDocs termDocs = reader.TermDocs();
TermEnum termEnum = reader.Terms(new Term(field));
try
{
do
{
Term term = termEnum.Term();
if (term == null || (System.Object) term.Field() != (System.Object) field)
break;
byte termval = parser.ParseByte(term.Text());
termDocs.Seek(termEnum);
while (termDocs.Next())
{
retArray[termDocs.Doc()] = termval;
}
}
while (termEnum.Next());
}
catch (StopFillCacheException stop)
{
}
finally
{
termDocs.Close();
termEnum.Close();
}
return retArray;
}
