public override Query Rewrite(Monodoc.Lucene.Net.Index.IndexReader reader)
{
BooleanQuery query = new BooleanQuery();
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) && (System.Object)term.Field() == (System.Object)prefixField)
{
TermQuery tq = new TermQuery(term); // found a match
tq.SetBoost(GetBoost()); // set the boost
query.Add(tq, false, false); // add to query
//System.out.println("added " + term);
}
else
{
break;
}
}while (enumerator.Next());
}
finally
{
enumerator.Close();
}
return(query);
}
/// <summary> Adds a term to the end of the query phrase.
/// The relative position of the term within the phrase is specified explicitly.
/// This allows e.g. phrases with more than one term at the same position
/// or phrases with gaps (e.g. in connection with stopwords).
///
/// </summary>
/// <param name="">term
/// </param>
/// <param name="">position
/// </param>
public virtual void Add(Term term, int position)
{
if (terms.Count == 0)
{
field = term.Field();
}
else if ((System.Object)term.Field() != (System.Object)field)
{
throw new System.ArgumentException("All phrase terms must be in the same field: " + term);
}
terms.Add(term);
positions.Add((System.Int32)position);
}
/// <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(Monodoc.Lucene.Net.Index.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 ((System.Object)term.Field() == (System.Object)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, ret);
}
}
else
{
throw new System.SystemException("Field \"" + field + "\" does not appear to be indexed");
}
}
finally
{
enumerator.Close();
}
}
return(ret);
}
/// <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>.
///
/// </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(Monodoc.Lucene.Net.Index.IndexReader reader, Term term, float minSimilarity, int prefixLength) : base()
{
InitBlock();
minimumSimilarity = minSimilarity;
scale_factor = 1.0f / (1.0f - minimumSimilarity);
searchTerm = term;
field = searchTerm.Field();
text = searchTerm.Text();
textlen = text.Length;
if (prefixLength > 0 && prefixLength < textlen)
{
this.prefixLength = prefixLength;
prefix = text.Substring(0, (prefixLength) - (0));
text = text.Substring(prefixLength);
textlen = text.Length;
}
SetEnum(reader.Terms(new Term(searchTerm.Field(), prefix)));
}
/// <summary>Prints a user-readable version of this query. </summary>
public override System.String ToString(System.String field)
{
System.Text.StringBuilder buffer = new System.Text.StringBuilder();
if (!term.Field().Equals(field))
{
buffer.Append(term.Field());
buffer.Append(":");
}
buffer.Append(term.Text());
if (GetBoost() != 1.0f)
{
System.Globalization.NumberFormatInfo nfi = new System.Globalization.CultureInfo("en-US", false).NumberFormat;
nfi.NumberDecimalDigits = 1;
buffer.Append("^");
buffer.Append(GetBoost().ToString("N", nfi));
}
return(buffer.ToString());
}
/// <summary> Adds a term to the end of the query phrase.
/// The relative position of the term within the phrase is specified explicitly.
/// This allows e.g. phrases with more than one term at the same position
/// or phrases with gaps (e.g. in connection with stopwords).
///
/// </summary>
/// <param name="">term
/// </param>
/// <param name="">position
/// </param>
public virtual void Add(Term term, int position)
{
if (terms.Count == 0)
field = term.Field();
else if ((System.Object) term.Field() != (System.Object) field)
{
throw new System.ArgumentException("All phrase terms must be in the same field: " + term);
}
terms.Add(term);
positions.Add((System.Int32) position);
}
/// <summary> FIXME: Describe <code>rewrite</code> method here.
///
/// </summary>
/// <param name="reader">an <code>Monodoc.Lucene.Net.Index.IndexReader</code> value
/// </param>
/// <returns> a <code>Query</code> value
/// </returns>
/// <exception cref=""> IOException if an error occurs
/// </exception>
public override Query Rewrite(Monodoc.Lucene.Net.Index.IndexReader reader)
{
BooleanQuery query = new BooleanQuery();
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 && (System.Object)term.Field() == (System.Object)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, false, false); // add to query
}
}
else
{
break;
}
}while (enumerator.Next());
}
finally
{
enumerator.Close();
}
return(query);
}
protected internal override bool TermCompare(Term term)
{
if ((System.Object) field == (System.Object) term.Field())
{
System.String searchText = term.Text();
if (searchText.StartsWith(pre))
{
return WildcardEquals(text, 0, searchText, preLen);
}
}
endEnum = true;
return false;
}
protected internal override bool TermCompare(Term term)
{
if ((System.Object)field == (System.Object)term.Field())
{
System.String searchText = term.Text();
if (searchText.StartsWith(pre))
{
return(WildcardEquals(text, 0, searchText, preLen));
}
}
endEnum = true;
return(false);
}
// inherit javadocs
public virtual float[] GetFloats(Monodoc.Lucene.Net.Index.IndexReader reader, System.String field)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, SortField.FLOAT);
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 ((System.Object)term.Field() != (System.Object)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, SortField.FLOAT, retArray);
return(retArray);
}
return((float[])ret);
}
/// <summary>The termCompare method in FuzzyTermEnum uses Levenshtein distance to
/// calculate the distance between the given term and the comparing term.
/// </summary>
protected internal override bool TermCompare(Term term)
{
System.String termText = term.Text();
if ((System.Object)field == (System.Object)term.Field() && termText.StartsWith(prefix))
{
System.String target = termText.Substring(prefixLength);
int targetlen = target.Length;
int dist = EditDistance(text, target, textlen, targetlen);
distance = 1 - ((double)dist / (double)System.Math.Min(textlen, targetlen));
return(distance > minimumSimilarity);
}
endEnum = true;
return(false);
}
/// <summary> Creates a new <code>WildcardTermEnum</code>. Passing in a
/// {@link Monodoc.Lucene.Net.Index.Term Term} that does not contain a
/// <code>WILDCARD_CHAR</code> will cause an exception to be thrown.
/// </summary>
public WildcardTermEnum(Monodoc.Lucene.Net.Index.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)));
}
/// <summary> Creates a new <code>WildcardTermEnum</code>. Passing in a
/// {@link Monodoc.Lucene.Net.Index.Term Term} that does not contain a
/// <code>WILDCARD_CHAR</code> will cause an exception to be thrown.
/// </summary>
public WildcardTermEnum(Monodoc.Lucene.Net.Index.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)));
}
/// <summary>Constructs a query selecting all terms greater than
/// <code>lowerTerm</code> but less than <code>upperTerm</code>.
/// There must be at least one term and either term may be null,
/// in which case there is no bound on that side, but if there are
/// two terms, both terms <b>must</b> be for the same Field.
/// </summary>
public RangeQuery(Term lowerTerm, Term upperTerm, bool inclusive)
{
if (lowerTerm == null && upperTerm == null)
{
throw new System.ArgumentException("At least one term must be non-null");
}
if (lowerTerm != null && upperTerm != null && (System.Object) lowerTerm.Field() != (System.Object) upperTerm.Field())
{
throw new System.ArgumentException("Both terms must be for the same Field");
}
// if we have a lowerTerm, start there. otherwise, start at beginning
if (lowerTerm != null)
{
this.lowerTerm = lowerTerm;
}
else
{
this.lowerTerm = new Term(upperTerm.Field(), "");
}
this.upperTerm = upperTerm;
this.inclusive = inclusive;
}
// inherit javadocs
public virtual System.IComparable[] GetCustom(Monodoc.Lucene.Net.Index.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 ((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();
}
}
Store(reader, field, SortField.CUSTOM, retArray);
return(retArray);
}
return((System.IComparable[])ret);
}
/// <summary>Constructs a query selecting all terms greater than
/// <code>lowerTerm</code> but less than <code>upperTerm</code>.
/// There must be at least one term and either term may be null,
/// in which case there is no bound on that side, but if there are
/// two terms, both terms <b>must</b> be for the same Field.
/// </summary>
public RangeQuery(Term lowerTerm, Term upperTerm, bool inclusive)
{
if (lowerTerm == null && upperTerm == null)
{
throw new System.ArgumentException("At least one term must be non-null");
}
if (lowerTerm != null && upperTerm != null && (System.Object)lowerTerm.Field() != (System.Object)upperTerm.Field())
{
throw new System.ArgumentException("Both terms must be for the same Field");
}
// if we have a lowerTerm, start there. otherwise, start at beginning
if (lowerTerm != null)
{
this.lowerTerm = lowerTerm;
}
else
{
this.lowerTerm = new Term(upperTerm.Field(), "");
}
this.upperTerm = upperTerm;
this.inclusive = inclusive;
}
/// <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>.
///
/// </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(Monodoc.Lucene.Net.Index.IndexReader reader, Term term, float minSimilarity, int prefixLength):base()
{
InitBlock();
minimumSimilarity = minSimilarity;
scale_factor = 1.0f / (1.0f - minimumSimilarity);
searchTerm = term;
field = searchTerm.Field();
text = searchTerm.Text();
textlen = text.Length;
if (prefixLength > 0 && prefixLength < textlen)
{
this.prefixLength = prefixLength;
prefix = text.Substring(0, (prefixLength) - (0));
text = text.Substring(prefixLength);
textlen = text.Length;
}
SetEnum(reader.Terms(new Term(searchTerm.Field(), prefix)));
}
/// <summary>The termCompare method in FuzzyTermEnum uses Levenshtein distance to
/// calculate the distance between the given term and the comparing term.
/// </summary>
protected internal override bool TermCompare(Term term)
{
System.String termText = term.Text();
if ((System.Object) field == (System.Object) term.Field() && termText.StartsWith(prefix))
{
System.String target = termText.Substring(prefixLength);
int targetlen = target.Length;
int dist = EditDistance(text, target, textlen, targetlen);
distance = 1 - ((double) dist / (double) System.Math.Min(textlen, targetlen));
return (distance > minimumSimilarity);
}
endEnum = true;
return false;
}
/// <summary>Returns the Field name for this query </summary>
public virtual System.String GetField()
{
return(lowerTerm != null?lowerTerm.Field():upperTerm.Field());
}
public override System.String GetField()
{
return(term.Field());
}
// inherit javadocs
public virtual StringIndex GetStringIndex(Monodoc.Lucene.Net.Index.IndexReader reader, System.String field)
{
field = String.Intern(field);
System.Object ret = Lookup(reader, field, Monodoc.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 ((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 + "\"");
}
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, Monodoc.Lucene.Net.Search.FieldCache_Fields.STRING_INDEX, value_Renamed);
return(value_Renamed);
}
return((StringIndex)ret);
}
