/* 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> Returns an array of objects which represent that natural order /// of the term values in the given Field. /// /// </summary> /// <param name="reader"> Terms are in this index. /// </param> /// <param name="enumerator">Use this to get the term values and TermDocs. /// </param> /// <param name="fieldname"> Comparables should be for this Field. /// </param> /// <returns> Array of objects representing natural order of terms in Field. /// </returns> /// <throws> IOException If an error occurs reading the index. </throws> protected internal virtual System.IComparable[] FillCache(IndexReader reader, TermEnum enumerator, System.String fieldname) { System.String field = String.Intern(fieldname); System.IComparable[] retArray = new System.IComparable[reader.MaxDoc()]; if (retArray.Length > 0) { TermDocs termDocs = reader.TermDocs(); try { if (enumerator.Term() == null) { throw new System.SystemException("no terms in Field " + field); } do { Term term = enumerator.Term(); if ((System.Object)term.Field() != (System.Object)field) { break; } System.IComparable termval = GetComparable(term.Text()); termDocs.Seek(enumerator); while (termDocs.Next()) { retArray[termDocs.Doc()] = termval; } }while (enumerator.Next()); } finally { termDocs.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); }
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); }
private static void IndexDocs(System.IO.FileInfo file) { if (System.IO.Directory.Exists(file.FullName)) { // if a directory System.String[] files = System.IO.Directory.GetFileSystemEntries(file.FullName); // list its files System.Array.Sort(files); // sort the files for (int i = 0; i < files.Length; i++) { // recursively index them IndexDocs(new System.IO.FileInfo(System.IO.Path.Combine(file.FullName, files[i]))); } } else if (file.FullName.EndsWith(".html") || file.FullName.EndsWith(".htm") || file.FullName.EndsWith(".txt")) { // index .txt files if (uidIter != null) { System.String uid = HTMLDocument.Uid(file); // construct uid for doc while (uidIter.Term() != null && (System.Object)uidIter.Term().Field() == (System.Object) "uid" && String.CompareOrdinal(uidIter.Term().Text(), uid) < 0) { if (deleting) { // delete stale docs System.Console.Out.WriteLine("deleting " + HTMLDocument.Uid2url(uidIter.Term().Text())); reader.DeleteDocuments(uidIter.Term()); } uidIter.Next(); } if (uidIter.Term() != null && (System.Object)uidIter.Term().Field() == (System.Object) "uid" && String.CompareOrdinal(uidIter.Term().Text(), uid) == 0) { uidIter.Next(); // keep matching docs } else if (!deleting) { // add new docs Document doc = HTMLDocument.Document(file); System.Console.Out.WriteLine("adding " + doc.Get("path")); writer.AddDocument(doc); } } else { // creating a new index Document doc = HTMLDocument.Document(file); System.Console.Out.WriteLine("adding " + doc.Get("path")); writer.AddDocument(doc); // add docs unconditionally } } }
// 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 bool MoveNext() { has_next_called = true; try { // if there is still words if (!termEnum.Next()) { actualTerm = null; return(false); } // if the next word are in the field actualTerm = termEnum.Term(); System.String fieldt = actualTerm.Field(); if (fieldt != Enclosing_Instance.field) { actualTerm = null; return(false); } return(true); } catch (System.IO.IOException ex) { System.Console.Error.WriteLine(ex.StackTrace); return(false); } }
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); }
/// <summary>Increments the enumeration to the next element. True if one exists. </summary> public override bool Next() { if (actualEnum == null) { return(false); // the actual enumerator is not initialized! } currentTerm = null; while (currentTerm == null) { if (EndEnum()) { return(false); } if (actualEnum.Next()) { Term term = actualEnum.Term(); if (TermCompare(term)) { currentTerm = term; return(true); } } else { return(false); } } currentTerm = null; return(false); }
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); }
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(); } }
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); }
/// <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); }
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) { 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); }
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(); } }
// 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); }
/// <summary> use this method to set the actual TermEnum (e.g. in ctor), /// it will be automatically positioned on the first matching term. /// </summary> protected internal virtual void SetEnum(TermEnum actualEnum) { this.actualEnum = actualEnum; // Find the first term that matches Term term = actualEnum.Term(); if (term != null && TermCompare(term)) currentTerm = term; else Next(); }
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); }
/// <summary> use this method to set the actual TermEnum (e.g. in ctor), /// it will be automatically positioned on the first matching term. /// </summary> protected internal virtual void SetEnum(TermEnum actualEnum) { this.actualEnum = actualEnum; // Find the first term that matches Term term = actualEnum.Term(); if (term != null && TermCompare(term)) { currentTerm = term; } else { Next(); } }
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(); } }
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); }
public virtual void Generate(MultiTermQuery query, IndexReader reader, TermEnum enumerator) { int[] docs = new int[32]; int[] freqs = new int[32]; TermDocs termDocs = reader.TermDocs(); try { int termCount = 0; do { Term term = enumerator.Term(); if (term == null) { break; } termCount++; termDocs.Seek(term); while (true) { int count = termDocs.Read(docs, freqs); if (count != 0) { for (int i = 0; i < count; i++) { HandleDoc(docs[i]); } } else { break; } } }while (enumerator.Next()); query.IncTotalNumberOfTerms(termCount); // {{Aroush-2.9}} is the use of 'temp' as is right? } finally { termDocs.Close(); } }
/// <summary> Returns a DocIdSet with documents that should be /// permitted in search results. /// </summary> //@Override public override DocIdSet GetDocIdSet(IndexReader reader) { TermEnum enumerator = query.GetEnum(reader); try { // if current term in enum is null, the enum is empty -> shortcut if (enumerator.Term() == null) { return(DocIdSet.EMPTY_DOCIDSET); } // else fill into a OpenBitSet OpenBitSet bitSet = new OpenBitSet(reader.MaxDoc()); new AnonymousClassTermGenerator1(bitSet, this).Generate(query, reader, enumerator); return(bitSet); } finally { enumerator.Close(); } }
//hasNext() public bool MoveNext() { hasNextCalled = true; actualTerm = termEnum.Term(); // if there are no words return false if (actualTerm == null) { return(false); } System.String fieldt = actualTerm.Field(); termEnum.Next(); // if the next word doesn't have the same field return false if (fieldt != enclosingInstance.field) { actualTerm = null; return(false); } return(true); }
// 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); }
// 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 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); }
public virtual void Generate(MultiTermQuery query, IndexReader reader, TermEnum enumerator) { int[] docs = new int[32]; int[] freqs = new int[32]; TermDocs termDocs = reader.TermDocs(); try { int termCount = 0; do { Term term = enumerator.Term(); if (term == null) break; termCount++; termDocs.Seek(term); while (true) { int count = termDocs.Read(docs, freqs); if (count != 0) { for (int i = 0; i < count; i++) { HandleDoc(docs[i]); } } else { break; } } } while (enumerator.Next()); query.IncTotalNumberOfTerms(termCount); // {{Aroush-2.9}} is the use of 'temp' as is right? } finally { termDocs.Close(); } }
// 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); }
/// <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); }
/// <summary> Returns an array of objects which represent that natural order /// of the term values in the given field. /// /// </summary> /// <param name="reader"> Terms are in this index. /// </param> /// <param name="enumerator">Use this to get the term values and TermDocs. /// </param> /// <param name="fieldname"> Comparables should be for this field. /// </param> /// <returns> Array of objects representing natural order of terms in field. /// </returns> /// <throws> IOException If an error occurs reading the index. </throws> public static System.IComparable[] FillCache(IndexReader reader, TermEnum enumerator, System.String fieldname) { System.String field = String.Intern(fieldname); System.IComparable[] retArray = new System.IComparable[reader.MaxDoc()]; if (retArray.Length > 0) { TermDocs termDocs = reader.TermDocs(); try { if (enumerator.Term() == null) { throw new System.SystemException("no terms in field " + field); } do { Term term = enumerator.Term(); if (term.Field() != field) break; System.IComparable termval = GetComparable(term.Text()); termDocs.Seek(enumerator); while (termDocs.Next()) { retArray[termDocs.Doc()] = termval; } } while (enumerator.Next()); } finally { termDocs.Close(); } } return retArray; }
/* 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); }