Return-Path: X-Original-To: apmail-lucene-lucene-net-commits-archive@www.apache.org Delivered-To: apmail-lucene-lucene-net-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id DDBC49CB6 for ; Tue, 28 Feb 2012 22:44:53 +0000 (UTC) Received: (qmail 25439 invoked by uid 500); 28 Feb 2012 22:44:53 -0000 Delivered-To: apmail-lucene-lucene-net-commits-archive@lucene.apache.org Received: (qmail 25404 invoked by uid 500); 28 Feb 2012 22:44:53 -0000 Mailing-List: contact lucene-net-commits-help@lucene.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: lucene-net-dev@lucene.apache.org Delivered-To: mailing list lucene-net-commits@lucene.apache.org Received: (qmail 25396 invoked by uid 99); 28 Feb 2012 22:44:53 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 28 Feb 2012 22:44:53 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=5.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 28 Feb 2012 22:44:48 +0000 Received: from eris.apache.org (localhost [127.0.0.1]) by eris.apache.org (Postfix) with ESMTP id 111712388BFF; Tue, 28 Feb 2012 22:44:03 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Date: Tue, 28 Feb 2012 22:43:28 -0000 To: lucene-net-commits@lucene.apache.org From: ccurrens@apache.org X-Mailer: svnmailer-1.0.8-patched Message-Id: <20120228224403.111712388BFF@eris.apache.org> X-Virus-Checked: Checked by ClamAV on apache.org Subject: [Lucene.Net] svn commit: r1294875 [12/45] - in /incubator/lucene.net/trunk: ./ build/ build/vs2010/contrib/ build/vs2010/test/ doc/ src/ src/contrib/Analyzers/ src/contrib/Analyzers/AR/ src/contrib/Analyzers/BR/ src/contrib/Analyzers/CJK/ src/contrib/Analyzers/Cn/ ... Modified: incubator/lucene.net/trunk/src/core/Analysis/Tokenattributes/TermAttributeImpl.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Analysis/Tokenattributes/TermAttributeImpl.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Analysis/Tokenattributes/TermAttributeImpl.cs (original) +++ incubator/lucene.net/trunk/src/core/Analysis/Tokenattributes/TermAttributeImpl.cs Tue Feb 28 22:43:08 2012 @@ -16,7 +16,7 @@ */ using System; - +using Lucene.Net.Support; using ArrayUtil = Lucene.Net.Util.ArrayUtil; using AttributeImpl = Lucene.Net.Util.AttributeImpl; @@ -70,7 +70,7 @@ namespace Lucene.Net.Analysis.Tokenattri { int length = buffer.Length; GrowTermBuffer(length); - SupportClass.TextSupport.GetCharsFromString(buffer, 0, length, termBuffer, 0); + TextSupport.GetCharsFromString(buffer, 0, length, termBuffer, 0); termLength = length; } @@ -88,7 +88,7 @@ namespace Lucene.Net.Analysis.Tokenattri System.Diagnostics.Debug.Assert(offset <= buffer.Length); System.Diagnostics.Debug.Assert(offset + length <= buffer.Length); GrowTermBuffer(length); - SupportClass.TextSupport.GetCharsFromString(buffer, offset, offset + length, termBuffer, 0); + TextSupport.GetCharsFromString(buffer, offset, offset + length, termBuffer, 0); termLength = length; } Modified: incubator/lucene.net/trunk/src/core/Analysis/Tokenizer.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Analysis/Tokenizer.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Analysis/Tokenizer.cs (original) +++ incubator/lucene.net/trunk/src/core/Analysis/Tokenizer.cs Tue Feb 28 22:43:08 2012 @@ -26,16 +26,16 @@ namespace Lucene.Net.Analysis ///

/// This is an abstract class; subclasses must override ///

- /// NOTE: Subclasses overriding must call + /// NOTE: Subclasses overriding must call /// before setting attributes. - /// Subclasses overriding must call - /// before setting Token attributes. /// public abstract class Tokenizer:TokenStream { ///

The text source for this Tokenizer. protected internal System.IO.TextReader input; + + private bool isDisposed; /// Construct a tokenizer with null input. protected internal Tokenizer() @@ -70,17 +70,23 @@ namespace Lucene.Net.Analysis this.input = CharReader.Get(input); } - /// By default, closes the input Reader. - public override void Close() - { - if (input != null) { - input.Close(); - // LUCENE-2387: don't hold onto Reader after close, so - // GC can reclaim - input = null; + protected override void Dispose(bool disposing) + { + if (isDisposed) return; + + if (disposing) + { + if (input != null) + { + input.Close(); + } } - } + // LUCENE-2387: don't hold onto Reader after close, so + // GC can reclaim + input = null; + isDisposed = true; + } /// Return the corrected offset. If is a subclass /// this method calls , else returns currentOff. Modified: incubator/lucene.net/trunk/src/core/Analysis/WordlistLoader.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Analysis/WordlistLoader.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Analysis/WordlistLoader.cs (original) +++ incubator/lucene.net/trunk/src/core/Analysis/WordlistLoader.cs Tue Feb 28 22:43:08 2012 @@ -16,16 +16,12 @@ */ using System; +using System.Collections.Generic; namespace Lucene.Net.Analysis { - /// Loader for text files that represent a list of stopwords. - /// - /// - /// - /// $Id: WordlistLoader.java 706342 2008-10-20 17:19:29Z gsingers $ - /// + /// Loader for text files that represent a list of stopwords. public class WordlistLoader { @@ -33,15 +29,12 @@ namespace Lucene.Net.Analysis /// leading and trailing whitespace). Every line of the file should contain only /// one word. The words need to be in lowercase if you make use of an /// Analyzer which uses LowerCaseFilter (like StandardAnalyzer). - /// /// - /// File containing the wordlist - /// - /// A HashSet with the file's words - /// - public static System.Collections.Hashtable GetWordSet(System.IO.FileInfo wordfile) + /// File containing the wordlist + /// A HashSet with the file's words + public static ISet GetWordSet(System.IO.FileInfo wordfile) { - System.Collections.Hashtable result = new System.Collections.Hashtable(); + ISet result = new HashSet(); System.IO.StreamReader reader = null; try { @@ -60,17 +53,13 @@ namespace Lucene.Net.Analysis /// leading and trailing whitespace). Every line of the file should contain only /// one word. The words need to be in lowercase if you make use of an /// Analyzer which uses LowerCaseFilter (like StandardAnalyzer). - /// /// - /// File containing the wordlist - /// - /// The comment string to ignore - /// - /// A HashSet with the file's words - /// - public static System.Collections.Hashtable GetWordSet(System.IO.FileInfo wordfile, System.String comment) + /// File containing the wordlist + /// The comment string to ignore + /// A HashSet with the file's words + public static HashSet GetWordSet(System.IO.FileInfo wordfile, System.String comment) { - System.Collections.Hashtable result = new System.Collections.Hashtable(); + HashSet result = new HashSet(); System.IO.StreamReader reader = null; try { @@ -90,22 +79,19 @@ namespace Lucene.Net.Analysis /// leading and trailing whitespace). Every line of the Reader should contain only /// one word. The words need to be in lowercase if you make use of an /// Analyzer which uses LowerCaseFilter (like StandardAnalyzer). - /// /// - /// Reader containing the wordlist - /// - /// A HashSet with the reader's words - /// - public static System.Collections.Hashtable GetWordSet(System.IO.TextReader reader) + /// Reader containing the wordlist + /// A HashSet with the reader's words + public static HashSet GetWordSet(System.IO.TextReader reader) { - System.Collections.Hashtable result = new System.Collections.Hashtable(); + HashSet result = new HashSet(); System.IO.TextReader br = null; try { System.String word = null; while ((word = reader.ReadLine()) != null) { - SupportClass.CollectionsHelper.Add(result, word.Trim()); + result.Add(word.Trim()); } } finally @@ -128,9 +114,9 @@ namespace Lucene.Net.Analysis /// /// A HashSet with the reader's words /// - public static System.Collections.Hashtable GetWordSet(System.IO.TextReader reader, System.String comment) + public static HashSet GetWordSet(System.IO.TextReader reader, System.String comment) { - System.Collections.Hashtable result = new System.Collections.Hashtable(); + HashSet result = new HashSet(); System.IO.StreamReader br = null; try { @@ -139,7 +125,7 @@ namespace Lucene.Net.Analysis { if (word.StartsWith(comment) == false) { - SupportClass.CollectionsHelper.Add(result, word.Trim()); + result.Add(word.Trim()); } } } @@ -161,11 +147,11 @@ namespace Lucene.Net.Analysis /// stem dictionary that overrules the stemming algorithm /// /// IOException - public static System.Collections.Hashtable GetStemDict(System.IO.FileInfo wordstemfile) + public static Dictionary GetStemDict(System.IO.FileInfo wordstemfile) { if (wordstemfile == null) throw new System.NullReferenceException("wordstemfile may not be null"); - System.Collections.Hashtable result = new System.Collections.Hashtable(); + Dictionary result = new Dictionary(); System.IO.StreamReader br = null; System.IO.StreamReader fr = null; try Modified: incubator/lucene.net/trunk/src/core/AssemblyInfo.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/AssemblyInfo.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/AssemblyInfo.cs (original) +++ incubator/lucene.net/trunk/src/core/AssemblyInfo.cs Tue Feb 28 22:43:08 2012 @@ -36,8 +36,14 @@ using System.Runtime.CompilerServices; [assembly: CLSCompliant(true)] -[assembly: AssemblyInformationalVersionAttribute("2.9.4")] +[assembly: AssemblyInformationalVersionAttribute("3.0.3")] +// for testing +[assembly: InternalsVisibleTo("Lucene.Net.Test, PublicKey=002400000480000094000000060200000024000052534131000400000100010075a07ce602f88e" + + "f263c7db8cb342c58ebd49ecdcc210fac874260b0213fb929ac3dcaf4f5b39744b800f99073eca" + + "72aebfac5f7284e1d5f2c82012a804a140f06d7d043d83e830cdb606a04da2ad5374cc92c0a495" + + "08437802fb4f8fb80a05e59f80afb99f4ccd0dfe44065743543c4b053b669509d29d332cd32a0c" + + "b1e97e84")] // // Version information for an assembly consists of the following four values: @@ -50,7 +56,7 @@ using System.Runtime.CompilerServices; // You can specify all the values or you can default the Revision and Build Numbers // by using the '*' as shown below: -[assembly: AssemblyVersion("2.9.4.001")] +[assembly: AssemblyVersion("3.0.3")] // Modified: incubator/lucene.net/trunk/src/core/Document/AbstractField.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Document/AbstractField.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Document/AbstractField.cs (original) +++ incubator/lucene.net/trunk/src/core/Document/AbstractField.cs Tue Feb 28 22:43:08 2012 @@ -24,8 +24,6 @@ using SpanQuery = Lucene.Net.Search.Span namespace Lucene.Net.Documents { - - /// /// /// @@ -43,7 +41,6 @@ namespace Lucene.Net.Documents protected internal bool isIndexed = true; protected internal bool isTokenized = true; protected internal bool isBinary = false; - protected internal bool isCompressed = false; protected internal bool lazy = false; protected internal bool omitTermFreqAndPositions = false; protected internal float boost = 1.0f; @@ -64,58 +61,11 @@ namespace Lucene.Net.Documents if (name == null) throw new System.NullReferenceException("name cannot be null"); this.name = StringHelper.Intern(name); // field names are interned - - if (store == Field.Store.YES) - { - this.isStored = true; - this.isCompressed = false; - } - else if (store == Field.Store.COMPRESS) - { - this.isStored = true; - this.isCompressed = true; - } - else if (store == Field.Store.NO) - { - this.isStored = false; - this.isCompressed = false; - } - else - { - throw new System.ArgumentException("unknown store parameter " + store); - } - - if (index == Field.Index.NO) - { - this.isIndexed = false; - this.isTokenized = false; - } - else if (index == Field.Index.ANALYZED) - { - this.isIndexed = true; - this.isTokenized = true; - } - else if (index == Field.Index.NOT_ANALYZED) - { - this.isIndexed = true; - this.isTokenized = false; - } - else if (index == Field.Index.NOT_ANALYZED_NO_NORMS) - { - this.isIndexed = true; - this.isTokenized = false; - this.omitNorms = true; - } - else if (index == Field.Index.ANALYZED_NO_NORMS) - { - this.isIndexed = true; - this.isTokenized = true; - this.omitNorms = true; - } - else - { - throw new System.ArgumentException("unknown index parameter " + index); - } + + this.isStored = store.IsStored(); + this.isIndexed = index.IsIndexed(); + this.isTokenized = index.IsAnalyzed(); + this.omitNorms = index.OmitNorms(); this.isBinary = false; @@ -155,7 +105,7 @@ namespace Lucene.Net.Documents /// ///

Note: this value is not stored directly with the document in the index. /// Documents returned from and - /// may thus not have the same value present as when + /// may thus not have the same value present as when /// this field was indexed. /// ///

@@ -176,40 +126,9 @@ namespace Lucene.Net.Documents protected internal virtual void SetStoreTermVector(Field.TermVector termVector) { - if (termVector == Field.TermVector.NO) - { - this.storeTermVector = false; - this.storePositionWithTermVector = false; - this.storeOffsetWithTermVector = false; - } - else if (termVector == Field.TermVector.YES) - { - this.storeTermVector = true; - this.storePositionWithTermVector = false; - this.storeOffsetWithTermVector = false; - } - else if (termVector == Field.TermVector.WITH_POSITIONS) - { - this.storeTermVector = true; - this.storePositionWithTermVector = true; - this.storeOffsetWithTermVector = false; - } - else if (termVector == Field.TermVector.WITH_OFFSETS) - { - this.storeTermVector = true; - this.storePositionWithTermVector = false; - this.storeOffsetWithTermVector = true; - } - else if (termVector == Field.TermVector.WITH_POSITIONS_OFFSETS) - { - this.storeTermVector = true; - this.storePositionWithTermVector = true; - this.storeOffsetWithTermVector = true; - } - else - { - throw new System.ArgumentException("unknown termVector parameter " + termVector); - } + this.storeTermVector = termVector.IsStored(); + this.storePositionWithTermVector = termVector.WithPositions(); + this.storeOffsetWithTermVector = termVector.WithOffsets(); } /// True iff the value of the field is to be stored in the index for return @@ -238,12 +157,6 @@ namespace Lucene.Net.Documents return isTokenized; } - /// True if the value of the field is stored and compressed within the index - public bool IsCompressed() - { - return isCompressed; - } - /// True iff the term or terms used to index this field are stored as a term /// vector, available from . /// These methods do not provide access to the original content of the field, @@ -308,10 +221,7 @@ namespace Lucene.Net.Documents { if (isBinary) { - if (!isCompressed) - return binaryLength; - else - return ((byte[]) fieldsData).Length; + return binaryLength; } else if (fieldsData is byte[]) return ((byte[]) fieldsData).Length; @@ -335,14 +245,6 @@ namespace Lucene.Net.Documents return omitNorms; } - /// Renamed to - /// - [Obsolete("Renamed to GetOmitTermFreqAndPositions")] - public virtual bool GetOmitTf() - { - return omitTermFreqAndPositions; - } - /// /// public virtual bool GetOmitTermFreqAndPositions() @@ -360,14 +262,6 @@ namespace Lucene.Net.Documents this.omitNorms = omitNorms; } - /// Renamed to - /// - [Obsolete("Renamed to SetOmitTermFreqAndPositions")] - public virtual void SetOmitTf(bool omitTermFreqAndPositions) - { - this.omitTermFreqAndPositions = omitTermFreqAndPositions; - } - /// Expert: /// /// If set, omit term freq, positions and payloads from @@ -396,10 +290,6 @@ namespace Lucene.Net.Documents if (isStored) { result.Append("stored"); - if (isCompressed) - result.Append("/compressed"); - else - result.Append("/uncompressed"); } if (isIndexed) { @@ -461,9 +351,8 @@ namespace Lucene.Net.Documents result.Append('>'); return result.ToString(); } - public abstract Lucene.Net.Analysis.TokenStream TokenStreamValue(); - public abstract System.IO.TextReader ReaderValue(); - public abstract System.String StringValue(); - public abstract byte[] BinaryValue(); + public abstract Lucene.Net.Analysis.TokenStream TokenStreamValue(); + public abstract System.IO.TextReader ReaderValue(); + public abstract System.String StringValue(); } } \ No newline at end of file Modified: incubator/lucene.net/trunk/src/core/Document/CompressionTools.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Document/CompressionTools.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Document/CompressionTools.cs (original) +++ incubator/lucene.net/trunk/src/core/Document/CompressionTools.cs Tue Feb 28 22:43:08 2012 @@ -22,7 +22,7 @@ // http://www.icsharpcode.net/OpenSource/SharpZipLib/ using System; - +using Lucene.Net.Support; using UnicodeUtil = Lucene.Net.Util.UnicodeUtil; namespace Lucene.Net.Documents @@ -31,9 +31,7 @@ namespace Lucene.Net.Documents /// Simple utility class providing static methods to /// compress and decompress binary data for stored fields. /// This class uses java.util.zip.Deflater and Inflater - /// classes to compress and decompress, which is the same - /// format previously used by the now deprecated - /// Field.Store.COMPRESS. + /// classes to compress and decompress. /// public class CompressionTools @@ -56,7 +54,7 @@ namespace Lucene.Net.Documents * the uncompressed data. */ System.IO.MemoryStream bos = new System.IO.MemoryStream(length); - SupportClass.SharpZipLib.Deflater compressor = SupportClass.SharpZipLib.CreateDeflater(); + Deflater compressor = SharpZipLib.CreateDeflater(); try { @@ -82,19 +80,19 @@ namespace Lucene.Net.Documents /// Compresses the specified byte range, with default BEST_COMPRESSION level public static byte[] Compress(byte[] value_Renamed, int offset, int length) { - return Compress(value_Renamed, offset, length, SupportClass.SharpZipLib.Deflater.BEST_COMPRESSION); + return Compress(value_Renamed, offset, length, Deflater.BEST_COMPRESSION); } /// Compresses all bytes in the array, with default BEST_COMPRESSION level public static byte[] Compress(byte[] value_Renamed) { - return Compress(value_Renamed, 0, value_Renamed.Length, SupportClass.SharpZipLib.Deflater.BEST_COMPRESSION); + return Compress(value_Renamed, 0, value_Renamed.Length, Deflater.BEST_COMPRESSION); } /// Compresses the String value, with default BEST_COMPRESSION level public static byte[] CompressString(System.String value_Renamed) { - return CompressString(value_Renamed, SupportClass.SharpZipLib.Deflater.BEST_COMPRESSION); + return CompressString(value_Renamed, Deflater.BEST_COMPRESSION); } /// Compresses the String value using the specified @@ -116,7 +114,7 @@ namespace Lucene.Net.Documents // Create an expandable byte array to hold the decompressed data System.IO.MemoryStream bos = new System.IO.MemoryStream(value_Renamed.Length); - SupportClass.SharpZipLib.Inflater decompressor = SupportClass.SharpZipLib.CreateInflater(); + Inflater decompressor = SharpZipLib.CreateInflater(); try { Modified: incubator/lucene.net/trunk/src/core/Document/DateField.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Document/DateField.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Document/DateField.cs (original) +++ incubator/lucene.net/trunk/src/core/Document/DateField.cs Tue Feb 28 22:43:08 2012 @@ -16,9 +16,9 @@ */ using System; - +using Lucene.Net.Search; +using Lucene.Net.Support; using NumericUtils = Lucene.Net.Util.NumericUtils; -using NumericRangeQuery = Lucene.Net.Search.NumericRangeQuery; using PrefixQuery = Lucene.Net.Search.PrefixQuery; using TermRangeQuery = Lucene.Net.Search.TermRangeQuery; // for javadoc @@ -51,15 +51,15 @@ namespace Lucene.Net.Documents /// For indexing a , convert it to unix timestamp as /// long and /// index this as a numeric value with - /// and use to query it. + /// and use to query it. /// /// /// If you build a new index, use or /// instead. /// This class is included for use with existing - /// indices and will be removed in a future release. + /// indices and will be removed in a future (possibly Lucene 4.0) /// - [Obsolete("If you build a new index, use DateTools or NumericField instead.This class is included for use with existing indices and will be removed in a future release.")] + [Obsolete("If you build a new index, use DateTools or NumericField instead.This class is included for use with existing indices and will be removed in a future release (possibly Lucene 4.0).")] public class DateField { @@ -68,7 +68,7 @@ namespace Lucene.Net.Documents } // make date strings long enough to last a millenium - private static int DATE_LEN = SupportClass.Number.ToString(1000L * 365 * 24 * 60 * 60 * 1000, SupportClass.Number.MAX_RADIX).Length; + private static int DATE_LEN = Number.ToString(1000L * 365 * 24 * 60 * 60 * 1000, Number.MAX_RADIX).Length; public static System.String MIN_DATE_STRING() { @@ -78,7 +78,7 @@ namespace Lucene.Net.Documents public static System.String MAX_DATE_STRING() { char[] buffer = new char[DATE_LEN]; - char c = SupportClass.Character.ForDigit(SupportClass.Character.MAX_RADIX - 1, SupportClass.Character.MAX_RADIX); + char c = Character.ForDigit(Character.MAX_RADIX - 1, Character.MAX_RADIX); for (int i = 0; i < DATE_LEN; i++) buffer[i] = c; return new System.String(buffer); @@ -103,7 +103,7 @@ namespace Lucene.Net.Documents if (time < 0) throw new System.SystemException("time '" + time + "' is too early, must be >= 0"); - System.String s = SupportClass.Number.ToString(time, SupportClass.Character.MAX_RADIX); + System.String s = Number.ToString(time, Character.MAX_RADIX); if (s.Length > DATE_LEN) throw new System.SystemException("time '" + time + "' is too late, length of string " + "representation must be <= " + DATE_LEN); @@ -123,7 +123,7 @@ namespace Lucene.Net.Documents /// Converts a string-encoded date into a millisecond time. public static long StringToTime(System.String s) { - return SupportClass.Number.Parse(s, SupportClass.Number.MAX_RADIX); + return Number.Parse(s, Number.MAX_RADIX); } /// Converts a string-encoded date into a Date object. public static System.DateTime StringToDate(System.String s) Modified: incubator/lucene.net/trunk/src/core/Document/DateTools.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Document/DateTools.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Document/DateTools.cs (original) +++ incubator/lucene.net/trunk/src/core/Document/DateTools.cs Tue Feb 28 22:43:08 2012 @@ -16,9 +16,8 @@ */ using System; - +using Lucene.Net.Search; using NumericUtils = Lucene.Net.Util.NumericUtils; -using NumericRangeQuery = Lucene.Net.Search.NumericRangeQuery; namespace Lucene.Net.Documents { @@ -43,7 +42,7 @@ namespace Lucene.Net.Documents /// For indexing a , convert it to unix timestamp as /// long and /// index this as a numeric value with - /// and use to query it. + /// and use to query it. /// public class DateTools { Modified: incubator/lucene.net/trunk/src/core/Document/Document.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Document/Document.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Document/Document.cs (original) +++ incubator/lucene.net/trunk/src/core/Document/Document.cs Tue Feb 28 22:43:08 2012 @@ -93,7 +93,7 @@ namespace Lucene.Net.Documents return iter.Current; } } - internal System.Collections.IList fields = new System.Collections.ArrayList(); + internal System.Collections.Generic.IList fields = new System.Collections.Generic.List(); private float boost = 1.0f; /// Constructs a new document with no fields. @@ -162,10 +162,10 @@ namespace Lucene.Net.Documents /// public void RemoveField(System.String name) { - System.Collections.IEnumerator it = fields.GetEnumerator(); + System.Collections.Generic.IEnumerator it = fields.GetEnumerator(); while (it.MoveNext()) { - Fieldable field = (Fieldable) it.Current; + Fieldable field = it.Current; if (field.Name().Equals(name)) { fields.Remove(field); @@ -186,7 +186,7 @@ namespace Lucene.Net.Documents { for (int i = fields.Count - 1; i >= 0; i--) { - Fieldable field = (Fieldable) fields[i]; + Fieldable field = fields[i]; if (field.Name().Equals(name)) { fields.RemoveAt(i); @@ -201,13 +201,7 @@ namespace Lucene.Net.Documents /// public Field GetField(System.String name) { - for (int i = 0; i < fields.Count; i++) - { - Field field = (Field) fields[i]; - if (field.Name().Equals(name)) - return field; - } - return null; + return (Field) GetFieldable(name); } @@ -217,9 +211,8 @@ namespace Lucene.Net.Documents /// public Fieldable GetFieldable(System.String name) { - for (int i = 0; i < fields.Count; i++) - { - Fieldable field = (Fieldable) fields[i]; + foreach(Fieldable field in fields) + { if (field.Name().Equals(name)) return field; } @@ -233,30 +226,20 @@ namespace Lucene.Net.Documents /// public System.String Get(System.String name) { - for (int i = 0; i < fields.Count; i++) + foreach(Fieldable field in fields) { - Fieldable field = (Fieldable) fields[i]; if (field.Name().Equals(name) && (!field.IsBinary())) return field.StringValue(); } return null; } - /// Returns an Enumeration of all the fields in a document. - /// use instead - /// - [Obsolete("Use GetFields() instead")] - public System.Collections.IEnumerator Fields() - { - return new AnonymousClassEnumeration(this); - } - /// Returns a List of all the fields in a document. ///

Note that fields which are not stored are /// not available in documents retrieved from the /// index, e.g. or . ///

- public System.Collections.IList GetFields() + public System.Collections.Generic.IList GetFields() { return fields; } @@ -275,20 +258,19 @@ namespace Lucene.Net.Documents /// public Field[] GetFields(System.String name) { - System.Collections.ArrayList result = new System.Collections.ArrayList(); - for (int i = 0; i < fields.Count; i++) + var result = new System.Collections.Generic.List(); + foreach(Fieldable field in fields) { - Field field = (Field) fields[i]; if (field.Name().Equals(name)) { - result.Add(field); + result.Add((Field)field); } } if (result.Count == 0) return NO_FIELDS; - return (Field[]) result.ToArray(typeof(Field)); + return result.ToArray(); } @@ -305,10 +287,9 @@ namespace Lucene.Net.Documents /// public Fieldable[] GetFieldables(System.String name) { - System.Collections.ArrayList result = new System.Collections.ArrayList(); - for (int i = 0; i < fields.Count; i++) + var result = new System.Collections.Generic.List(); + foreach(Fieldable field in fields) { - Fieldable field = (Fieldable) fields[i]; if (field.Name().Equals(name)) { result.Add(field); @@ -318,7 +299,7 @@ namespace Lucene.Net.Documents if (result.Count == 0) return NO_FIELDABLES; - return (Fieldable[]) result.ToArray(typeof(Fieldable)); + return result.ToArray(); } @@ -334,10 +315,9 @@ namespace Lucene.Net.Documents /// public System.String[] GetValues(System.String name) { - System.Collections.ArrayList result = new System.Collections.ArrayList(); - for (int i = 0; i < fields.Count; i++) + var result = new System.Collections.Generic.List(); + foreach(Fieldable field in fields) { - Fieldable field = (Fieldable) fields[i]; if (field.Name().Equals(name) && (!field.IsBinary())) result.Add(field.StringValue()); } @@ -345,7 +325,7 @@ namespace Lucene.Net.Documents if (result.Count == 0) return NO_STRINGS; - return (System.String[]) result.ToArray(typeof(System.String)); + return result.ToArray(); } private static readonly byte[][] NO_BYTES = new byte[0][]; @@ -362,34 +342,17 @@ namespace Lucene.Net.Documents /// public byte[][] GetBinaryValues(System.String name) { - System.Collections.IList result = new System.Collections.ArrayList(); - for (int i = 0; i < fields.Count; i++) + var result = new System.Collections.Generic.List(); + foreach(Fieldable field in fields) { - Fieldable field = (Fieldable) fields[i]; if (field.Name().Equals(name) && (field.IsBinary())) - result.Add(field.BinaryValue()); + result.Add(field.GetBinaryValue()); } if (result.Count == 0) return NO_BYTES; - - System.Collections.ICollection c = result; - object[] objects = new byte[result.Count][]; - - System.Type type = objects.GetType().GetElementType(); - object[] objs = (object[])Array.CreateInstance(type, c.Count); - - System.Collections.IEnumerator e = c.GetEnumerator(); - int ii = 0; - while (e.MoveNext()) - objs[ii++] = e.Current; - - // If objects is smaller than c then do not return the new array in the parameter - if (objects.Length >= c.Count) - objs.CopyTo(objects, 0); - - return (byte[][])objs; + return result.ToArray(); } /// Returns an array of bytes for the first (or only) field that has the name @@ -404,11 +367,10 @@ namespace Lucene.Net.Documents /// public byte[] GetBinaryValue(System.String name) { - for (int i = 0; i < fields.Count; i++) + foreach(Fieldable field in fields) { - Fieldable field = (Fieldable) fields[i]; if (field.Name().Equals(name) && (field.IsBinary())) - return field.BinaryValue(); + return field.GetBinaryValue(); } return null; } @@ -420,7 +382,7 @@ namespace Lucene.Net.Documents buffer.Append("Document<"); for (int i = 0; i < fields.Count; i++) { - Fieldable field = (Fieldable) fields[i]; + Fieldable field = fields[i]; buffer.Append(field.ToString()); if (i != fields.Count - 1) buffer.Append(" "); @@ -429,7 +391,7 @@ namespace Lucene.Net.Documents return buffer.ToString(); } - public System.Collections.IList fields_ForNUnit + public System.Collections.Generic.IList fields_ForNUnit { get { return fields; } } Modified: incubator/lucene.net/trunk/src/core/Document/Field.cs URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/src/core/Document/Field.cs?rev=1294875&r1=1294874&r2=1294875&view=diff ============================================================================== --- incubator/lucene.net/trunk/src/core/Document/Field.cs (original) +++ incubator/lucene.net/trunk/src/core/Document/Field.cs Tue Feb 28 22:43:08 2012 @@ -19,630 +19,649 @@ using System; using TokenStream = Lucene.Net.Analysis.TokenStream; using IndexWriter = Lucene.Net.Index.IndexWriter; -using Parameter = Lucene.Net.Util.Parameter; using StringHelper = Lucene.Net.Util.StringHelper; namespace Lucene.Net.Documents { - - /// A field is a section of a Document. Each field has two parts, a name and a - /// value. Values may be free text, provided as a String or as a Reader, or they - /// may be atomic keywords, which are not further processed. Such keywords may - /// be used to represent dates, urls, etc. Fields are optionally stored in the - /// index, so that they may be returned with hits on the document. - /// - - [Serializable] - public sealed class Field:AbstractField, Fieldable - { - - /// Specifies whether and how a field should be stored. - [Serializable] - public sealed class Store:Parameter - { - - internal Store(System.String name):base(name) - { - } - - /// Store the original field value in the index in a compressed form. This is - /// useful for long documents and for binary valued fields. - /// - /// Please use instead. - /// For string fields that were previously indexed and stored using compression, - /// the new way to achieve this is: First add the field indexed-only (no store) - /// and additionally using the same field name as a binary, stored field - /// with . - /// - public static readonly Store COMPRESS = new Store("COMPRESS"); - - /// Store the original field value in the index. This is useful for short texts - /// like a document's title which should be displayed with the results. The - /// value is stored in its original form, i.e. no analyzer is used before it is - /// stored. - /// - public static readonly Store YES = new Store("YES"); - - /// Do not store the field value in the index. - public static readonly Store NO = new Store("NO"); - } - - /// Specifies whether and how a field should be indexed. - [Serializable] - public sealed class Index:Parameter - { - - internal Index(System.String name):base(name) - { - } - - /// Do not index the field value. This field can thus not be searched, - /// but one can still access its contents provided it is - /// stored. - /// - public static readonly Index NO = new Index("NO"); - - /// Index the tokens produced by running the field's - /// value through an Analyzer. This is useful for - /// common text. - /// - public static readonly Index ANALYZED = new Index("ANALYZED"); - - /// this has been renamed to - /// - [Obsolete("this has been renamed to ANALYZED")] - public static readonly Index TOKENIZED; - - /// Index the field's value without using an Analyzer, so it can be searched. - /// As no analyzer is used the value will be stored as a single term. This is - /// useful for unique Ids like product numbers. - /// - public static readonly Index NOT_ANALYZED = new Index("NOT_ANALYZED"); - - /// This has been renamed to - /// - [Obsolete("This has been renamed to NOT_ANALYZED")] - public static readonly Index UN_TOKENIZED; - - /// Expert: Index the field's value without an Analyzer, - /// and also disable the storing of norms. Note that you - /// can also separately enable/disable norms by calling + + /// A field is a section of a Document. Each field has two parts, a name and a + /// value. Values may be free text, provided as a String or as a Reader, or they + /// may be atomic keywords, which are not further processed. Such keywords may + /// be used to represent dates, urls, etc. Fields are optionally stored in the + /// index, so that they may be returned with hits on the document. + /// + + [Serializable] + public sealed class Field:AbstractField, Fieldable + { + /// Specifies whether and how a field should be stored. + public enum Store + { + /// Store the original field value in the index. This is useful for short texts + /// like a document's title which should be displayed with the results. The + /// value is stored in its original form, i.e. no analyzer is used before it is + /// stored. + /// + YES, + + /// Do not store the field value in the index. + NO + } + + /// Specifies whether and how a field should be indexed. + + public enum Index + { + /// Do not index the field value. This field can thus not be searched, + /// but one can still access its contents provided it is + /// stored. + /// + NO, + + /// Index the tokens produced by running the field's + /// value through an Analyzer. This is useful for + /// common text. + /// + ANALYZED, + + /// Index the field's value without using an Analyzer, so it can be searched. + /// As no analyzer is used the value will be stored as a single term. This is + /// useful for unique Ids like product numbers. + /// + NOT_ANALYZED, + + /// Expert: Index the field's value without an Analyzer, + /// and also disable the storing of norms. Note that you + /// can also separately enable/disable norms by calling /// . No norms means that - /// index-time field and document boosting and field - /// length normalization are disabled. The benefit is - /// less memory usage as norms take up one byte of RAM - /// per indexed field for every document in the index, - /// during searching. Note that once you index a given - /// field with norms enabled, disabling norms will - /// have no effect. In other words, for this to have the - /// above described effect on a field, all instances of - /// that field must be indexed with NOT_ANALYZED_NO_NORMS - /// from the beginning. - /// - public static readonly Index NOT_ANALYZED_NO_NORMS = new Index("NOT_ANALYZED_NO_NORMS"); - - /// This has been renamed to - /// - /// - [Obsolete("This has been renamed to NOT_ANALYZED_NO_NORMS")] - public static readonly Index NO_NORMS; - - /// Expert: Index the tokens produced by running the - /// field's value through an Analyzer, and also - /// separately disable the storing of norms. See - /// for what norms are - /// and why you may want to disable them. - /// - public static readonly Index ANALYZED_NO_NORMS = new Index("ANALYZED_NO_NORMS"); - static Index() - { - TOKENIZED = ANALYZED; - UN_TOKENIZED = NOT_ANALYZED; - NO_NORMS = NOT_ANALYZED_NO_NORMS; - } - } - - /// Specifies whether and how a field should have term vectors. - [Serializable] - public sealed class TermVector:Parameter - { - - internal TermVector(System.String name):base(name) - { - } - - /// Do not store term vectors. - public static readonly TermVector NO = new TermVector("NO"); - - /// Store the term vectors of each document. A term vector is a list - /// of the document's terms and their number of occurrences in that document. - /// - public static readonly TermVector YES = new TermVector("YES"); - - /// Store the term vector + token position information - /// - /// - /// - /// - public static readonly TermVector WITH_POSITIONS = new TermVector("WITH_POSITIONS"); - - /// Store the term vector + Token offset information - /// - /// - /// - /// - public static readonly TermVector WITH_OFFSETS = new TermVector("WITH_OFFSETS"); - - /// Store the term vector + Token position and offset information - /// - /// - /// - /// - /// - /// - /// - /// - public static readonly TermVector WITH_POSITIONS_OFFSETS = new TermVector("WITH_POSITIONS_OFFSETS"); - } - - - /// The value of the field as a String, or null. If null, the Reader value or - /// binary value is used. Exactly one of stringValue(), - /// readerValue(), and getBinaryValue() must be set. - /// - public override System.String StringValue() - { - return fieldsData is System.String?(System.String) fieldsData:null; - } - - /// The value of the field as a Reader, or null. If null, the String value or - /// binary value is used. Exactly one of stringValue(), - /// readerValue(), and getBinaryValue() must be set. - /// - public override System.IO.TextReader ReaderValue() - { - return fieldsData is System.IO.TextReader?(System.IO.TextReader) fieldsData:null; - } - - /// The value of the field in Binary, or null. If null, the Reader value, - /// or String value is used. Exactly one of stringValue(), - /// readerValue(), and getBinaryValue() must be set. - /// - /// This method must allocate a new byte[] if - /// the is non-zero - /// or is not the - /// full length of the byte[]. Please use - /// instead, which simply - /// returns the byte[]. - /// - [Obsolete("This method must allocate a new byte[] if the AbstractField.GetBinaryOffset() is non-zero or AbstractField.GetBinaryLength() is not the full length of the byte[]. Please use AbstractField.GetBinaryValue() instead, which simply returns the byte[].")] - public override byte[] BinaryValue() - { - if (!isBinary) - return null; - byte[] data = (byte[]) fieldsData; - if (binaryOffset == 0 && data.Length == binaryLength) - return data; //Optimization - - byte[] ret = new byte[binaryLength]; - Array.Copy(data, binaryOffset, ret, 0, binaryLength); - return ret; - } - - /// The TokesStream for this field to be used when indexing, or null. If null, the Reader value - /// or String value is analyzed to produce the indexed tokens. - /// - public override TokenStream TokenStreamValue() - { - return tokenStream; - } - - - ///

Expert: change the value of this field. This can - /// be used during indexing to re-use a single Field - /// instance to improve indexing speed by avoiding GC cost - /// of new'ing and reclaiming Field instances. Typically - /// a single instance is re-used as - /// well. This helps most on small documents.

- /// - ///

Each Field instance should only be used once - /// within a single instance. See ImproveIndexingSpeed - /// for details.

- ///

- public void SetValue(System.String value_Renamed) - { - if (isBinary) - { - throw new System.ArgumentException("cannot set a String value on a binary field"); - } - fieldsData = value_Renamed; - } - - /// Expert: change the value of this field. See setValue(String). - public void SetValue(System.IO.TextReader value_Renamed) - { - if (isBinary) - { - throw new System.ArgumentException("cannot set a Reader value on a binary field"); - } - if (isStored) - { - throw new System.ArgumentException("cannot set a Reader value on a stored field"); - } - fieldsData = value_Renamed; - } - - /// Expert: change the value of this field. See setValue(String). - public void SetValue(byte[] value_Renamed) - { - if (!isBinary) - { - throw new System.ArgumentException("cannot set a byte[] value on a non-binary field"); - } - fieldsData = value_Renamed; - binaryLength = value_Renamed.Length; - binaryOffset = 0; - } - - /// Expert: change the value of this field. See setValue(String). - public void SetValue(byte[] value_Renamed, int offset, int length) - { - if (!isBinary) - { - throw new System.ArgumentException("cannot set a byte[] value on a non-binary field"); - } - fieldsData = value_Renamed; - binaryLength = length; - binaryOffset = offset; - } - - - /// Expert: change the value of this field. See setValue(String). - /// use - /// - [Obsolete("use SetTokenStream ")] - public void SetValue(TokenStream value_Renamed) - { - if (isBinary) - { - throw new System.ArgumentException("cannot set a TokenStream value on a binary field"); - } - if (isStored) - { - throw new System.ArgumentException("cannot set a TokenStream value on a stored field"); - } - fieldsData = null; - tokenStream = value_Renamed; - } - - /// Expert: sets the token stream to be used for indexing and causes isIndexed() and isTokenized() to return true. - /// May be combined with stored values from stringValue() or binaryValue() - /// - public void SetTokenStream(TokenStream tokenStream) - { - this.isIndexed = true; - this.isTokenized = true; - this.tokenStream = tokenStream; - } - - /// Create a field by specifying its name, value and how it will - /// be saved in the index. Term vectors will not be stored in the index. - /// - /// - /// The name of the field - /// - /// The string to process - /// - /// Whether value should be stored in the index - /// - /// Whether the field should be indexed, and if so, if it should - /// be tokenized before indexing - /// - /// NullPointerException if name or value is null - /// IllegalArgumentException if the field is neither stored nor indexed - public Field(System.String name, System.String value_Renamed, Store store, Index index):this(name, value_Renamed, store, index, TermVector.NO) - { - } - - /// Create a field by specifying its name, value and how it will - /// be saved in the index. - /// - /// - /// The name of the field - /// - /// The string to process - /// - /// Whether value should be stored in the index - /// - /// Whether the field should be indexed, and if so, if it should - /// be tokenized before indexing - /// - /// Whether term vector should be stored - /// - /// NullPointerException if name or value is null - /// IllegalArgumentException in any of the following situations: - /// - /// the field is neither stored nor indexed - /// the field is not indexed but termVector is TermVector.YES - /// - /// - public Field(System.String name, System.String value_Renamed, Store store, Index index, TermVector termVector):this(name, true, value_Renamed, store, index, termVector) - { - } - - /// Create a field by specifying its name, value and how it will - /// be saved in the index. - /// - /// - /// The name of the field - /// - /// Whether to .intern() name or not - /// - /// The string to process - /// - /// Whether value should be stored in the index - /// - /// Whether the field should be indexed, and if so, if it should - /// be tokenized before indexing - /// - /// Whether term vector should be stored - /// - /// NullPointerException if name or value is null - /// IllegalArgumentException in any of the following situations: - /// - /// the field is neither stored nor indexed - /// the field is not indexed but termVector is TermVector.YES - /// - /// - public Field(System.String name, bool internName, System.String value_Renamed, Store store, Index index, TermVector termVector) - { - if (name == null) - throw new System.NullReferenceException("name cannot be null"); - if (value_Renamed == null) - throw new System.NullReferenceException("value cannot be null"); - if (name.Length == 0 && value_Renamed.Length == 0) - throw new System.ArgumentException("name and value cannot both be empty"); - if (index == Index.NO && store == Store.NO) - throw new System.ArgumentException("it doesn't make sense to have a field that " + "is neither indexed nor stored"); - if (index == Index.NO && termVector != TermVector.NO) - throw new System.ArgumentException("cannot store term vector information " + "for a field that is not indexed"); - - if (internName) - // field names are optionally interned - name = StringHelper.Intern(name); - - this.name = name; - - this.fieldsData = value_Renamed; - - if (store == Store.YES) - { - this.isStored = true; - this.isCompressed = false; - } - else if (store == Store.COMPRESS) - { - this.isStored = true; - this.isCompressed = true; - } - else if (store == Store.NO) - { - this.isStored = false; - this.isCompressed = false; - } - else - { - throw new System.ArgumentException("unknown store parameter " + store); - } - - if (index == Index.NO) - { - this.isIndexed = false; - this.isTokenized = false; - this.omitTermFreqAndPositions = false; - this.omitNorms = true; - } - else if (index == Index.ANALYZED) - { - this.isIndexed = true; - this.isTokenized = true; - } - else if (index == Index.NOT_ANALYZED) - { - this.isIndexed = true; - this.isTokenized = false; - } - else if (index == Index.NOT_ANALYZED_NO_NORMS) - { - this.isIndexed = true; - this.isTokenized = false; - this.omitNorms = true; - } - else if (index == Index.ANALYZED_NO_NORMS) - { - this.isIndexed = true; - this.isTokenized = true; - this.omitNorms = true; - } - else - { - throw new System.ArgumentException("unknown index parameter " + index); - } - - this.isBinary = false; - - SetStoreTermVector(termVector); - } - - /// Create a tokenized and indexed field that is not stored. Term vectors will - /// not be stored. The Reader is read only when the Document is added to the index, - /// i.e. you may not close the Reader until - /// has been called. - /// - /// - /// The name of the field - /// - /// The reader with the content - /// - /// NullPointerException if name or reader is null - public Field(System.String name, System.IO.TextReader reader):this(name, reader, TermVector.NO) - { - } - - /// Create a tokenized and indexed field that is not stored, optionally with - /// storing term vectors. The Reader is read only when the Document is added to the index, - /// i.e. you may not close the Reader until - /// has been called. - /// - /// - /// The name of the field - /// - /// The reader with the content - /// - /// Whether term vector should be stored - /// - /// NullPointerException if name or reader is null - public Field(System.String name, System.IO.TextReader reader, TermVector termVector) - { - if (name == null) - throw new System.NullReferenceException("name cannot be null"); - if (reader == null) - throw new System.NullReferenceException("reader cannot be null"); - - this.name = StringHelper.Intern(name); // field names are interned - this.fieldsData = reader; - - this.isStored = false; - this.isCompressed = false; - - this.isIndexed = true; - this.isTokenized = true; - - this.isBinary = false; - - SetStoreTermVector(termVector); - } - - /// Create a tokenized and indexed field that is not stored. Term vectors will - /// not be stored. This is useful for pre-analyzed fields. - /// The TokenStream is read only when the Document is added to the index, - /// i.e. you may not close the TokenStream until - /// has been called. - /// - /// - /// The name of the field - /// - /// The TokenStream with the content - /// - /// NullPointerException if name or tokenStream is null - public Field(System.String name, TokenStream tokenStream):this(name, tokenStream, TermVector.NO) - { - } - - /// Create a tokenized and indexed field that is not stored, optionally with - /// storing term vectors. This is useful for pre-analyzed fields. - /// The TokenStream is read only when the Document is added to the index, - /// i.e. you may not close the TokenStream until - /// has been called. - /// - /// - /// The name of the field - /// - /// The TokenStream with the content - /// - /// Whether term vector should be stored - /// - /// NullPointerException if name or tokenStream is null - public Field(System.String name, TokenStream tokenStream, TermVector termVector) - { - if (name == null) - throw new System.NullReferenceException("name cannot be null"); - if (tokenStream == null) - throw new System.NullReferenceException("tokenStream cannot be null"); - - this.name = StringHelper.Intern(name); // field names are interned - this.fieldsData = null; - this.tokenStream = tokenStream; - - this.isStored = false; - this.isCompressed = false; - - this.isIndexed = true; - this.isTokenized = true; - - this.isBinary = false; - - SetStoreTermVector(termVector); - } - - - /// Create a stored field with binary value. Optionally the value may be compressed. - /// - /// - /// The name of the field - /// - /// The binary value - /// - /// How value should be stored (compressed or not) - /// - /// IllegalArgumentException if store is Store.NO - public Field(System.String name, byte[] value_Renamed, Store store):this(name, value_Renamed, 0, value_Renamed.Length, store) - { - } - - /// Create a stored field with binary value. Optionally the value may be compressed. - /// - /// - /// The name of the field - /// - /// The binary value - /// - /// Starting offset in value where this Field's bytes are - /// - /// Number of bytes to use for this Field, starting at offset - /// - /// How value should be stored (compressed or not) - /// - /// IllegalArgumentException if store is Store.NO - public Field(System.String name, byte[] value_Renamed, int offset, int length, Store store) - { - - if (name == null) - throw new System.ArgumentException("name cannot be null"); - if (value_Renamed == null) - throw new System.ArgumentException("value cannot be null"); - - this.name = StringHelper.Intern(name); // field names are interned - fieldsData = value_Renamed; - - if (store == Store.YES) - { - isStored = true; - isCompressed = false; - } - else if (store == Store.COMPRESS) - { - isStored = true; - isCompressed = true; - } - else if (store == Store.NO) - throw new System.ArgumentException("binary values can't be unstored"); - else - { - throw new System.ArgumentException("unknown store parameter " + store); - } - - isIndexed = false; - isTokenized = false; - omitTermFreqAndPositions = false; - omitNorms = true; - - isBinary = true; - binaryLength = length; - binaryOffset = offset; - - SetStoreTermVector(TermVector.NO); - } - } + /// index-time field and document boosting and field + /// length normalization are disabled. The benefit is + /// less memory usage as norms take up one byte of RAM + /// per indexed field for every document in the index, + /// during searching. Note that once you index a given + /// field with norms enabled, disabling norms will + /// have no effect. In other words, for this to have the + /// above described effect on a field, all instances of + /// that field must be indexed with NOT_ANALYZED_NO_NORMS + /// from the beginning. + /// + NOT_ANALYZED_NO_NORMS, + + /// Expert: Index the tokens produced by running the + /// field's value through an Analyzer, and also + /// separately disable the storing of norms. See + /// for what norms are + /// and why you may want to disable them. + /// + ANALYZED_NO_NORMS, + } + + /// Specifies whether and how a field should have term vectors. + public enum TermVector + { + /// Do not store term vectors. + NO, + + /// Store the term vectors of each document. A term vector is a list + /// of the document's terms and their number of occurrences in that document. + /// + YES, + + /// Store the term vector + token position information + /// + /// + /// + /// + WITH_POSITIONS, + + /// Store the term vector + Token offset information + /// + /// + /// + /// + WITH_OFFSETS, + + /// Store the term vector + Token position and offset information + /// + /// + /// + /// + /// + /// + /// + /// + WITH_POSITIONS_OFFSETS, + } + + + /// The value of the field as a String, or null. If null, the Reader value or + /// binary value is used. Exactly one of stringValue(), + /// readerValue(), and getBinaryValue() must be set. + /// + public override System.String StringValue() + { + return fieldsData is System.String?(System.String) fieldsData:null; + } + + /// The value of the field as a Reader, or null. If null, the String value or + /// binary value is used. Exactly one of stringValue(), + /// readerValue(), and getBinaryValue() must be set. + /// + public override System.IO.TextReader ReaderValue() + { + return fieldsData is System.IO.TextReader?(System.IO.TextReader) fieldsData:null; + } + + /// The TokesStream for this field to be used when indexing, or null. If null, the Reader value + /// or String value is analyzed to produce the indexed tokens. + /// + public override TokenStream TokenStreamValue() + { + return tokenStream; + } + + + ///

Expert: change the value of this field. This can + /// be used during indexing to re-use a single Field + /// instance to improve indexing speed by avoiding GC cost + /// of new'ing and reclaiming Field instances. Typically + /// a single instance is re-used as + /// well. This helps most on small documents.

+ /// + ///

Each Field instance should only be used once + /// within a single instance. See ImproveIndexingSpeed + /// for details.

+ ///

+ public void SetValue(System.String value_Renamed) + { + if (isBinary) + { + throw new System.ArgumentException("cannot set a String value on a binary field"); + } + fieldsData = value_Renamed; + } + + /// Expert: change the value of this field. See setValue(String). + public void SetValue(System.IO.TextReader value_Renamed) + { + if (isBinary) + { + throw new System.ArgumentException("cannot set a Reader value on a binary field"); + } + if (isStored) + { + throw new System.ArgumentException("cannot set a Reader value on a stored field"); + } + fieldsData = value_Renamed; + } + + /// Expert: change the value of this field. See setValue(String). + public void SetValue(byte[] value_Renamed) + { + if (!isBinary) + { + throw new System.ArgumentException("cannot set a byte[] value on a non-binary field"); + } + fieldsData = value_Renamed; + binaryLength = value_Renamed.Length; + binaryOffset = 0; + } + + /// Expert: change the value of this field. See setValue(String). + public void SetValue(byte[] value_Renamed, int offset, int length) + { + if (!isBinary) + { + throw new System.ArgumentException("cannot set a byte[] value on a non-binary field"); + } + fieldsData = value_Renamed; + binaryLength = length; + binaryOffset = offset; + } + + /// Expert: sets the token stream to be used for indexing and causes isIndexed() and isTokenized() to return true. + /// May be combined with stored values from stringValue() or GetBinaryValue() + /// + public void SetTokenStream(TokenStream tokenStream) + { + this.isIndexed = true; + this.isTokenized = true; + this.tokenStream = tokenStream; + } + + /// Create a field by specifying its name, value and how it will + /// be saved in the index. Term vectors will not be stored in the index. + /// + /// + /// The name of the field + /// + /// The string to process + /// + /// Whether value should be stored in the index + /// + /// Whether the field should be indexed, and if so, if it should + /// be tokenized before indexing + /// + /// NullPointerException if name or value is null + /// IllegalArgumentException if the field is neither stored nor indexed + public Field(System.String name, System.String value_Renamed, Store store, Index index) + : this(name, value_Renamed, store, index, TermVector.NO) + { + } + + /// Create a field by specifying its name, value and how it will + /// be saved in the index. + /// + /// + /// The name of the field + /// + /// The string to process + /// + /// Whether value should be stored in the index + /// + /// Whether the field should be indexed, and if so, if it should + /// be tokenized before indexing + /// + /// Whether term vector should be stored + /// + /// NullPointerException if name or value is null + /// IllegalArgumentException in any of the following situations: + /// + /// the field is neither stored nor indexed + /// the field is not indexed but termVector is TermVector.YES + /// + /// + public Field(System.String name, System.String value_Renamed, Store store, Index index, TermVector termVector) + : this(name, true, value_Renamed, store, index, termVector) + { + } + + /// Create a field by specifying its name, value and how it will + /// be saved in the index. + /// + /// + /// The name of the field + /// + /// Whether to .intern() name or not + /// + /// The string to process + /// + /// Whether value should be stored in the index + /// + /// Whether the field should be indexed, and if so, if it should + /// be tokenized before indexing + /// + /// Whether term vector should be stored + /// + /// NullPointerException if name or value is null + /// IllegalArgumentException in any of the following situations: + /// + /// the field is neither stored nor indexed + /// the field is not indexed but termVector is TermVector.YES + /// + /// + public Field(System.String name, bool internName, System.String value_Renamed, Store store, Index index, TermVector termVector) + { + if (name == null) + throw new System.NullReferenceException("name cannot be null"); + if (value_Renamed == null) + throw new System.NullReferenceException("value cannot be null"); + if (name.Length == 0 && value_Renamed.Length == 0) + throw new System.ArgumentException("name and value cannot both be empty"); + if (index == Index.NO && store == Store.NO) + throw new System.ArgumentException("it doesn't make sense to have a field that " + "is neither indexed nor stored"); + if (index == Index.NO && termVector != TermVector.NO) + throw new System.ArgumentException("cannot store term vector information " + "for a field that is not indexed"); + + if (internName) + // field names are optionally interned + name = StringHelper.Intern(name); + + this.name = name; + + this.fieldsData = value_Renamed; + + this.isStored = store.IsStored(); + + this.isIndexed = index.IsIndexed(); + this.isTokenized = index.IsAnalyzed(); + this.omitNorms = index.OmitNorms(); + + if (index == Index.NO) + { + this.omitTermFreqAndPositions = false; + } + + this.isBinary = false; + + SetStoreTermVector(termVector); + } + + /// Create a tokenized and indexed field that is not stored. Term vectors will + /// not be stored. The Reader is read only when the Document is added to the index, + /// i.e. you may not close the Reader until + /// has been called. + /// + /// + /// The name of the field + /// + /// The reader with the content + /// + /// NullPointerException if name or reader is null + public Field(System.String name, System.IO.TextReader reader):this(name, reader, TermVector.NO) + { + } + + /// Create a tokenized and indexed field that is not stored, optionally with + /// storing term vectors. The Reader is read only when the Document is added to the index, + /// i.e. you may not close the Reader until + /// has been called. + /// + /// + /// The name of the field + /// + /// The reader with the content + /// + /// Whether term vector should be stored + /// + /// NullPointerException if name or reader is null + public Field(System.String name, System.IO.TextReader reader, TermVector termVector) + { + if (name == null) + throw new System.NullReferenceException("name cannot be null"); + if (reader == null) + throw new System.NullReferenceException("reader cannot be null"); + + this.name = StringHelper.Intern(name); // field names are interned + this.fieldsData = reader; + + this.isStored = false; + + this.isIndexed = true; + this.isTokenized = true; + + this.isBinary = false; + + SetStoreTermVector(termVector); + } + + /// Create a tokenized and indexed field that is not stored. Term vectors will + /// not be stored. This is useful for pre-analyzed fields. + /// The TokenStream is read only when the Document is added to the index, + /// i.e. you may not close the TokenStream until + /// has been called. + /// + /// + /// The name of the field + /// + /// The TokenStream with the content + /// + /// NullPointerException if name or tokenStream is null + public Field(System.String name, TokenStream tokenStream):this(name, tokenStream, TermVector.NO) + { + } + + /// Create a tokenized and indexed field that is not stored, optionally with + /// storing term vectors. This is useful for pre-analyzed fields. + /// The TokenStream is read only when the Document is added to the index, + /// i.e. you may not close the TokenStream until + /// has been called. + /// + /// + /// The name of the field + /// + /// The TokenStream with the content + /// + /// Whether term vector should be stored + /// + /// NullPointerException if name or tokenStream is null + public Field(System.String name, TokenStream tokenStream, TermVector termVector) + { + if (name == null) + throw new System.NullReferenceException("name cannot be null"); + if (tokenStream == null) + throw new System.NullReferenceException("tokenStream cannot be null"); + + this.name = StringHelper.Intern(name); // field names are interned + this.fieldsData = null; + this.tokenStream = tokenStream; + + this.isStored = false; + + this.isIndexed = true; + this.isTokenized = true; + + this.isBinary = false; + + SetStoreTermVector(termVector); + } + + + /// Create a stored field with binary value. Optionally the value may be compressed. + /// + /// + /// The name of the field + /// + /// The binary value + /// + /// How value should be stored (compressed or not) + /// + /// IllegalArgumentException if store is Store.NO + public Field(System.String name, byte[] value_Renamed, Store store):this(name, value_Renamed, 0, value_Renamed.Length, store) + { + } + + /// Create a stored field with binary value. Optionally the value may be compressed. + /// + /// + /// The name of the field + /// + /// The binary value + /// + /// Starting offset in value where this Field's bytes are + /// + /// Number of bytes to use for this Field, starting at offset + /// + /// How value should be stored (compressed or not) + /// + /// IllegalArgumentException if store is Store.NO + public Field(System.String name, byte[] value_Renamed, int offset, int length, Store store) + { + + if (name == null) + throw new System.ArgumentException("name cannot be null"); + if (value_Renamed == null) + throw new System.ArgumentException("value cannot be null"); + + this.name = StringHelper.Intern(name); // field names are interned + fieldsData = value_Renamed; + + if (store == Store.NO) + throw new System.ArgumentException("binary values can't be unstored"); + + isStored = store.IsStored(); + isIndexed = false; + isTokenized = false; + omitTermFreqAndPositions = false; + omitNorms = true; + + isBinary = true; + binaryLength = length; + binaryOffset = offset; + + SetStoreTermVector(TermVector.NO); + } + } + + public static class FieldExtensions + { + public static bool IsStored(this Field.Store store) + { + switch(store) + { + case Field.Store.YES: + return true; + case Field.Store.NO: + return false; + default: + throw new ArgumentOutOfRangeException("store", "Invalid value for Field.Store"); + } + } + + public static bool IsIndexed(this Field.Index index) + { + switch(index) + { + case Field.Index.NO: + return false; + case Field.Index.ANALYZED: + case Field.Index.NOT_ANALYZED: + case Field.Index.NOT_ANALYZED_NO_NORMS: + case Field.Index.ANALYZED_NO_NORMS: + return true; + default: + throw new ArgumentOutOfRangeException("index", "Invalid value for Field.Index"); + } + } + + public static bool IsAnalyzed(this Field.Index index) + { + switch (index) + { + case Field.Index.NO: + case Field.Index.NOT_ANALYZED: + case Field.Index.NOT_ANALYZED_NO_NORMS: + return false; + case Field.Index.ANALYZED: + case Field.Index.ANALYZED_NO_NORMS: + return true; + default: + throw new ArgumentOutOfRangeException("index", "Invalid value for Field.Index"); + } + } + + public static bool OmitNorms(this Field.Index index) + { + switch (index) + { + case Field.Index.ANALYZED: + case Field.Index.NOT_ANALYZED: + return false; + case Field.Index.NO: + case Field.Index.NOT_ANALYZED_NO_NORMS: + case Field.Index.ANALYZED_NO_NORMS: + return true; + default: + throw new ArgumentOutOfRangeException("index", "Invalid value for Field.Index"); + } + } + + public static bool IsStored(this Field.TermVector tv) + { + switch(tv) + { + case Field.TermVector.NO: + return false; + case Field.TermVector.YES: + case Field.TermVector.WITH_OFFSETS: + case Field.TermVector.WITH_POSITIONS: + case Field.TermVector.WITH_POSITIONS_OFFSETS: + return true; + default: + throw new ArgumentOutOfRangeException("tv", "Invalid value for Field.TermVector"); + } + } + + public static bool WithPositions(this Field.TermVector tv) + { + switch (tv) + { + case Field.TermVector.NO: + case Field.TermVector.YES: + case Field.TermVector.WITH_OFFSETS: + return false; + case Field.TermVector.WITH_POSITIONS: + case Field.TermVector.WITH_POSITIONS_OFFSETS: + return true; + default: + throw new ArgumentOutOfRangeException("tv", "Invalid value for Field.TermVector"); + } + } + + public static bool WithOffsets(this Field.TermVector tv) + { + switch (tv) + { + case Field.TermVector.NO: + case Field.TermVector.YES: + case Field.TermVector.WITH_POSITIONS: + return false; + case Field.TermVector.WITH_OFFSETS: + case Field.TermVector.WITH_POSITIONS_OFFSETS: + return true; + default: + throw new ArgumentOutOfRangeException("tv", "Invalid value for Field.TermVector"); + } + } + + public static Field.Index ToIndex(bool indexed, bool analyed) + { + return ToIndex(indexed, analyed, false); + } + + public static Field.Index ToIndex(bool indexed, bool analyzed, bool omitNorms) + { + + // If it is not indexed nothing else matters + if (!indexed) + { + return Field.Index.NO; + } + + // typical, non-expert + if (!omitNorms) + { + if (analyzed) + { + return Field.Index.ANALYZED; + } + return Field.Index.NOT_ANALYZED; + } + + // Expert: Norms omitted + if (analyzed) + { + return Field.Index.ANALYZED_NO_NORMS; + } + return Field.Index.NOT_ANALYZED_NO_NORMS; + } + + /// + /// Get the best representation of a TermVector given the flags. + /// + public static Field.TermVector ToTermVector(bool stored, bool withOffsets, bool withPositions) + { + // If it is not stored, nothing else matters. + if (!stored) + { + return Field.TermVector.NO; + } + + if (withOffsets) + { + if (withPositions) + { + return Field.TermVector.WITH_POSITIONS_OFFSETS; + } + return Field.TermVector.WITH_OFFSETS; + } + + if (withPositions) + { + return Field.TermVector.WITH_POSITIONS; + } + return Field.TermVector.YES; + } + } } \ No newline at end of file