private void MyInit()
{
ISimilarity editdistance=new Leven() ;
getSimilarity=new Similarity(editdistance.GetSimilarity) ;
//ISimilarity lexical=new LexicalSimilarity() ;
//getSimilarity=new Similarity(lexical.GetSimilarity) ;
Tokeniser tokeniser=new Tokeniser() ;
_leftTokens=tokeniser.Partition(_lString);
_rightTokens=tokeniser.Partition(_rString);
if (_leftTokens.Length > _rightTokens.Length)
{
string[] tmp=_leftTokens;
_leftTokens=_rightTokens;
_rightTokens=tmp;
string s=_lString; _lString=_rString; _rString=s;
}
leftLen=_leftTokens.Length - 1 ;
rightLen=_rightTokens.Length - 1;
Initialize();
}
/// <summary>
/// Creates a new entity based on the specified mention and its specified gender and number properties.
/// </summary>
/// <param name="mention">
/// The first mention of this entity.
/// </param>
/// <param name="gender">
/// The gender of this entity.
/// </param>
/// <param name="genderProbability">
/// The probability that the specified gender is correct.
/// </param>
/// <param name="number">
/// The number for this entity.
/// </param>
/// <param name="numberProbability">
/// The probability that the specified number is correct.
/// </param>
public DiscourseEntity(Mention.MentionContext mention, Similarity.GenderEnum gender, double genderProbability, Similarity.NumberEnum number, double numberProbability)
: base(mention)
{
mGender = gender;
mGenderProbability = genderProbability;
mNumber = number;
mNumberProbability = numberProbability;
}
public SpanWeight(SpanQuery query, Searcher searcher)
{
this.similarity = query.GetSimilarity(searcher);
this.internalQuery = query;
terms = Lucene.Net.Support.Compatibility.SetFactory.CreateHashSet<Term>();
query.ExtractTerms(terms);
idfExp = similarity.IdfExplain(terms, searcher);
idf = idfExp.Idf;
}
/// <summary> Creates a new instance of DisjunctionMaxScorer
///
/// </summary>
/// <param name="tieBreakerMultiplier">Multiplier applied to non-maximum-scoring subqueries for a
/// document as they are summed into the result.
/// </param>
/// <param name="similarity">-- not used since our definition involves neither coord nor terms
/// directly
/// </param>
/// <param name="subScorers">The sub scorers this Scorer should iterate on
/// </param>
/// <param name="numScorers">The actual number of scorers to iterate on. Note that the array's
/// length may be larger than the actual number of scorers.
/// </param>
public DisjunctionMaxScorer(float tieBreakerMultiplier, Similarity similarity, Scorer[] subScorers, int numScorers):base(similarity)
{
this.tieBreakerMultiplier = tieBreakerMultiplier;
// The passed subScorers array includes only scorers which have documents
// (DisjunctionMaxQuery takes care of that), and their nextDoc() was already
// called.
this.subScorers = subScorers;
this.numScorers = numScorers;
Heapify();
}
/// <summary>
/// Copies the specified <see cref="ConnectedImage"/> into the new instance
/// </summary>
public ConnectedImage(ConnectedImage image)
: base(image)
{
labelData = image.labelData;
foreach (Similarity similarity in image.labels)
{
Similarity sim = new Similarity();
sim.ID = similarity.ID;
sim.SameAs = similarity.SameAs;
sim.Tag = similarity.Tag;
labels.Add(sim);
}
}
// tries extra hard to cast the sim to TFIDFSimilarity
internal static TFIDFSimilarity AsTFIDF(Similarity sim, string field)
{
while (sim is PerFieldSimilarityWrapper)
{
sim = ((PerFieldSimilarityWrapper)sim).Get(field);
}
if (sim is TFIDFSimilarity)
{
return (TFIDFSimilarity)sim;
}
else
{
return null;
}
}
protected internal SpanScorer(Spans spans, Weight weight, Similarity similarity, byte[] norms):base(similarity)
{
this.spans = spans;
this.norms = norms;
this.weight = weight;
this.value_Renamed = weight.Value;
if (this.spans.Next())
{
doc = - 1;
}
else
{
doc = NO_MORE_DOCS;
more = false;
}
}
protected internal virtual void ProcessPayload(Similarity similarity)
{
if (TermSpans.PayloadAvailable)
{
DocsAndPositionsEnum postings = TermSpans.Postings;
Payload = postings.Payload;
if (Payload != null)
{
PayloadScore_Renamed = OuterInstance.OuterInstance.Function.CurrentScore(Doc, OuterInstance.OuterInstance.Term.Field, Spans.Start(), Spans.End(), PayloadsSeen, PayloadScore_Renamed, DocScorer.ComputePayloadFactor(Doc, Spans.Start(), Spans.End(), Payload));
}
else
{
PayloadScore_Renamed = OuterInstance.OuterInstance.Function.CurrentScore(Doc, OuterInstance.OuterInstance.Term.Field, Spans.Start(), Spans.End(), PayloadsSeen, PayloadScore_Renamed, 1F);
}
PayloadsSeen++;
}
else
{
// zero out the payload?
}
}
public TestRuleSetupAndRestoreClassEnv()
{
/*// if verbose: print some debugging stuff about which codecs are loaded.
if (LuceneTestCase.VERBOSE)
{
ISet<string> codecs = Codec.AvailableCodecs();
foreach (string codec in codecs)
{
Console.WriteLine("Loaded codec: '" + codec + "': " + Codec.ForName(codec).GetType().Name);
}
ISet<string> postingsFormats = PostingsFormat.AvailablePostingsFormats();
foreach (string postingsFormat in postingsFormats)
{
Console.WriteLine("Loaded postingsFormat: '" + postingsFormat + "': " + PostingsFormat.ForName(postingsFormat).GetType().Name);
}
}
SavedInfoStream = InfoStream.Default;
Random random = RandomizedContext.Current.Random;
bool v = random.NextBoolean();
if (LuceneTestCase.INFOSTREAM)
{
InfoStream.Default = new ThreadNameFixingPrintStreamInfoStream(Console.Out);
}
else if (v)
{
InfoStream.Default = new NullInfoStream();
}
Type targetClass = RandomizedContext.Current.GetTargetType;
AvoidCodecs = new HashSet<string>();
// set back to default
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = false;
SavedCodec = Codec.Default;
int randomVal = random.Next(10);
if ("Lucene3x".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 3 && !ShouldAvoidCodec("Lucene3x"))) // preflex-only setup
{
Codec = Codec.ForName("Lucene3x");
Debug.Assert((Codec is PreFlexRWCodec), "fix your classpath to have tests-framework.jar before lucene-core.jar");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
}
else if ("Lucene40".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && randomVal == 0 && !ShouldAvoidCodec("Lucene40"))) // 4.0 setup
{
Codec = Codec.ForName("Lucene40");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert(Codec is Lucene40RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
Debug.Assert((PostingsFormat.ForName("Lucene40") is Lucene40RWPostingsFormat), "fix your classpath to have tests-framework.jar before lucene-core.jar");
}
else if ("Lucene41".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 1 && !ShouldAvoidCodec("Lucene41")))
{
Codec = Codec.ForName("Lucene41");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert(Codec is Lucene41RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
}
else if ("Lucene42".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 2 && !ShouldAvoidCodec("Lucene42")))
{
Codec = Codec.ForName("Lucene42");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert(Codec is Lucene42RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
}
else if ("Lucene45".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 5 && !ShouldAvoidCodec("Lucene45")))
{
Codec = Codec.ForName("Lucene45");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert(Codec is Lucene45RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
}
else if (("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) == false) || ("random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) == false))
{
// the user wired postings or DV: this is messy
// refactor into RandomCodec....
PostingsFormat format;
if ("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT))
{
format = PostingsFormat.ForName("Lucene41");
}
else
{
format = PostingsFormat.ForName(LuceneTestCase.TEST_POSTINGSFORMAT);
}
DocValuesFormat dvFormat;
if ("random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT))
{
dvFormat = DocValuesFormat.ForName("Lucene45");
}
else
{
dvFormat = DocValuesFormat.ForName(LuceneTestCase.TEST_DOCVALUESFORMAT);
}
Codec = new Lucene46CodecAnonymousInnerClassHelper(this, format, dvFormat);
}
else if ("Asserting".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && randomVal == 6 && !ShouldAvoidCodec("Asserting")))
{
Codec = new AssertingCodec();
}
else if ("Compressing".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && randomVal == 5 && !ShouldAvoidCodec("Compressing")))
{
Codec = CompressingCodec.RandomInstance(random);
}
else if (!"random".Equals(LuceneTestCase.TEST_CODEC))
{
Codec = Codec.ForName(LuceneTestCase.TEST_CODEC);
}
else if ("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT))
{
Codec = new RandomCodec(random, AvoidCodecs);
}
else
{
Debug.Assert(false);
}
Codec.Default = Codec;
*/
Random random = new Random();
Similarity = random.NextBoolean() ? (Similarity)new DefaultSimilarity() : new RandomSimilarityProvider(new Random());
/*
// Check codec restrictions once at class level.
try
{
CheckCodecRestrictions(Codec);
}
catch (Exception e)
{
Console.Error.WriteLine("NOTE: " + e.Message + " Suppressed codecs: " + Arrays.ToString(AvoidCodecs.ToArray()));
throw e;
}*/
}
private float[] vScores; // reused in score() to avoid allocating this array for each doc
// constructor
internal CustomScorer(CustomScoreQuery enclosingInstance, Similarity similarity, IndexReader reader, CustomWeight w, Scorer subQueryScorer, Scorer[] valSrcScorers):base(similarity)
{
InitBlock(enclosingInstance);
this.qWeight = w.Value;
this.subQueryScorer = subQueryScorer;
this.valSrcScorers = valSrcScorers;
this.reader = reader;
this.vScores = new float[valSrcScorers.Length];
this.provider = this.Enclosing_Instance.GetCustomScoreProvider(reader);
}
public NormsSimilarity(Similarity @in)
{
this.@in = @in;
}
/// <summary>
/// Builder method for <see cref="IndexWriterConfig.Similarity"/>.
/// </summary>
/// <param name="config">this <see cref="IndexWriterConfig"/> instance</param>
/// <param name="similarity"></param>
/// <returns>this <see cref="IndexWriterConfig"/> instance</returns>
public static IndexWriterConfig SetSimilarity(this IndexWriterConfig config, Similarity similarity)
{
config.Similarity = similarity;
return(config);
}
public ValueSourceWeight(ValueSourceQuery enclosingInstance, Searcher searcher)
{
InitBlock(enclosingInstance);
this.similarity = Enclosing_Instance.GetSimilarity(searcher);
}
public override Explanation Explain(IndexReader reader, int doc)
{
ComplexExplanation result = new ComplexExplanation();
result.SetDescription("weight(" + GetQuery() + " in " + doc + "), product of:");
System.String field = ((SpanQuery)GetQuery()).GetField();
Explanation idfExpl = new Explanation(idf, "idf(" + field + ": " + idfExp.Explain() + ")");
// explain query weight
Explanation queryExpl = new Explanation();
queryExpl.SetDescription("queryWeight(" + GetQuery() + "), product of:");
Explanation boostExpl = new Explanation(GetQuery().GetBoost(), "boost");
if (GetQuery().GetBoost() != 1.0f)
{
queryExpl.AddDetail(boostExpl);
}
queryExpl.AddDetail(idfExpl);
Explanation queryNormExpl = new Explanation(queryNorm, "queryNorm");
queryExpl.AddDetail(queryNormExpl);
queryExpl.SetValue(boostExpl.GetValue() * idfExpl.GetValue() * queryNormExpl.GetValue());
result.AddDetail(queryExpl);
// explain field weight
ComplexExplanation fieldExpl = new ComplexExplanation();
fieldExpl.SetDescription("fieldWeight(" + field + ":" + query.ToString(field) + " in " + doc + "), product of:");
Explanation tfExpl = Scorer(reader, true, false).Explain(doc);
fieldExpl.AddDetail(tfExpl);
fieldExpl.AddDetail(idfExpl);
Explanation fieldNormExpl = new Explanation();
byte[] fieldNorms = reader.Norms(field);
float fieldNorm = fieldNorms != null?Similarity.DecodeNorm(fieldNorms[doc]) : 1.0f;
fieldNormExpl.SetValue(fieldNorm);
fieldNormExpl.SetDescription("fieldNorm(field=" + field + ", doc=" + doc + ")");
fieldExpl.AddDetail(fieldNormExpl);
fieldExpl.SetMatch(tfExpl.IsMatch());
fieldExpl.SetValue(tfExpl.GetValue() * idfExpl.GetValue() * fieldNormExpl.GetValue());
result.AddDetail(fieldExpl);
System.Boolean?tempAux = fieldExpl.GetMatch();
result.SetMatch(tempAux);
// combine them
result.SetValue(queryExpl.GetValue() * fieldExpl.GetValue());
if (queryExpl.GetValue() == 1.0f)
{
return(fieldExpl);
}
return(result);
}
public PayloadTermSpanScorer(PayloadTermWeight enclosingInstance, TermSpans spans, Weight weight, Similarity similarity, byte[] norms) : base(spans, weight, similarity, norms)
{
InitBlock(enclosingInstance);
positions = spans.Positions;
}
/// <summary>
/// Writes the document to the directory using the analyzer
/// and the similarity score; returns the SegmentInfo
/// describing the new segment
/// </summary>
public static SegmentCommitInfo WriteDoc(Random random, Directory dir, Analyzer analyzer, Similarity similarity, Document doc)
{
IndexWriter writer = new IndexWriter(dir, (new IndexWriterConfig(Util.LuceneTestCase.TEST_VERSION_CURRENT, analyzer)).SetSimilarity(similarity ?? IndexSearcher.DefaultSimilarity)); // LuceneTestCase.newIndexWriterConfig(random,
//writer.SetNoCFSRatio(0.0);
writer.AddDocument(doc);
writer.Commit();
SegmentCommitInfo info = writer.NewestSegment();
writer.Dispose();
return(info);
}
public SectionSearchWeight(SectionSearchQuery parent, Searcher searcher)
{
_parent = parent;
_similarity = _parent.GetSimilarity(searcher);
}
public MatchNoDocsWeight(MatchNoDocsQuery enclosingInstance, Searcher searcher)
{
this.InitBlock(enclosingInstance);
this.similarity = searcher.Similarity;
}
internal MatchNoDocsScorer(MatchNoDocsQuery enclosingInstance, IndexReader reader, Similarity similarity, Weight w, byte[] norms)
: base(similarity)
{
this.InitBlock(enclosingInstance);
this.termDocs = reader.TermDocs((Term)null);
this.score = w.Value;
this.norms = norms;
}
protected internal PayloadNearSpanScorer(PayloadNearQuery outerInstance, Spans spans, Weight weight, Similarity similarity, Similarity.SimScorer docScorer)
: base(spans, weight, docScorer)
{
this.outerInstance = outerInstance;
this.spans = spans;
}
public override void Before(LuceneTestCase testInstance)
{
// LUCENENET specific - SOLR setup code removed
// if verbose: print some debugging stuff about which codecs are loaded.
if (LuceneTestCase.VERBOSE)
{
ICollection <string> codecs = Codec.AvailableCodecs();
foreach (string codec in codecs)
{
Console.WriteLine("Loaded codec: '" + codec + "': " + Codec.ForName(codec).GetType().Name);
}
ICollection <string> postingsFormats = PostingsFormat.AvailablePostingsFormats();
foreach (string postingsFormat in postingsFormats)
{
Console.WriteLine("Loaded postingsFormat: '" + postingsFormat + "': " + PostingsFormat.ForName(postingsFormat).GetType().Name);
}
}
savedInfoStream = InfoStream.Default;
Random random = LuceneTestCase.Random;
bool v = random.NextBoolean();
if (LuceneTestCase.INFOSTREAM)
{
InfoStream.Default = new ThreadNameFixingPrintStreamInfoStream(Console.Out);
}
else if (v)
{
InfoStream.Default = new NullInfoStream();
}
Type targetClass = testInstance.GetType();
avoidCodecs = new HashSet <string>();
var suppressCodecsAttribute = targetClass.GetTypeInfo().GetCustomAttribute <LuceneTestCase.SuppressCodecsAttribute>();
if (suppressCodecsAttribute != null)
{
avoidCodecs.AddAll(suppressCodecsAttribute.Value);
}
// set back to default
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = false;
savedCodec = Codec.Default;
int randomVal = random.Next(10);
if ("Lucene3x".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) || ("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT, StringComparison.Ordinal) &&
randomVal == 3 &&
!ShouldAvoidCodec("Lucene3x"))) // preflex-only setup
{
codec = Codec.ForName("Lucene3x");
Debug.Assert((codec is PreFlexRWCodec), "fix your ICodecFactory to scan Lucene.Net.Tests before Lucene.Net.TestFramework");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
}
else if ("Lucene40".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) || ("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal) &&
randomVal == 0 &&
!ShouldAvoidCodec("Lucene40"))) // 4.0 setup
{
codec = Codec.ForName("Lucene40");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert((codec is Lucene40RWCodec), "fix your ICodecFactory to scan Lucene.Net.Tests before Lucene.Net.TestFramework");
Debug.Assert((PostingsFormat.ForName("Lucene40") is Lucene40RWPostingsFormat), "fix your IPostingsFormatFactory to scan Lucene.Net.Tests before Lucene.Net.TestFramework");
}
else if ("Lucene41".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) || ("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT, StringComparison.Ordinal) &&
randomVal == 1 &&
!ShouldAvoidCodec("Lucene41")))
{
codec = Codec.ForName("Lucene41");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert((codec is Lucene41RWCodec), "fix your ICodecFactory to scan Lucene.Net.Tests before Lucene.Net.TestFramework");
}
else if ("Lucene42".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) || ("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT, StringComparison.Ordinal) &&
randomVal == 2 &&
!ShouldAvoidCodec("Lucene42")))
{
codec = Codec.ForName("Lucene42");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert((codec is Lucene42RWCodec), "fix your ICodecFactory to scan Lucene.Net.Tests before Lucene.Net.TestFramework");
}
else if ("Lucene45".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) || ("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal) &&
"random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT, StringComparison.Ordinal) &&
randomVal == 5 &&
!ShouldAvoidCodec("Lucene45")))
{
codec = Codec.ForName("Lucene45");
LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
Debug.Assert((codec is Lucene45RWCodec), "fix your ICodecFactory to scan Lucene.Net.Tests before Lucene.Net.TestFramework");
}
else if (("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal) == false) ||
("random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT, StringComparison.Ordinal) == false))
{
// the user wired postings or DV: this is messy
// refactor into RandomCodec....
PostingsFormat format;
if ("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal))
{
format = PostingsFormat.ForName("Lucene41");
}
else if ("MockRandom".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal))
{
format = new MockRandomPostingsFormat(new Random(random.Next()));
}
else
{
format = PostingsFormat.ForName(LuceneTestCase.TEST_POSTINGSFORMAT);
}
DocValuesFormat dvFormat;
if ("random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT, StringComparison.Ordinal))
{
dvFormat = DocValuesFormat.ForName("Lucene45");
}
else
{
dvFormat = DocValuesFormat.ForName(LuceneTestCase.TEST_DOCVALUESFORMAT);
}
codec = new Lucene46CodecAnonymousInnerClassHelper(this, format, dvFormat);
}
else if ("SimpleText".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) ||
("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) && randomVal == 9 && LuceneTestCase.Rarely(random) && !ShouldAvoidCodec("SimpleText")))
{
codec = new SimpleTextCodec();
}
else if ("CheapBastard".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) ||
("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) && randomVal == 8 && !ShouldAvoidCodec("CheapBastard") && !ShouldAvoidCodec("Lucene41")))
{
// we also avoid this codec if Lucene41 is avoided, since thats the postings format it uses.
codec = new CheapBastardCodec();
}
else if ("Asserting".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) ||
("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) && randomVal == 6 && !ShouldAvoidCodec("Asserting")))
{
codec = new AssertingCodec();
}
else if ("Compressing".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) ||
("random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal) && randomVal == 5 && !ShouldAvoidCodec("Compressing")))
{
codec = CompressingCodec.RandomInstance(random);
}
else if (!"random".Equals(LuceneTestCase.TEST_CODEC, StringComparison.Ordinal))
{
codec = Codec.ForName(LuceneTestCase.TEST_CODEC);
}
else if ("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT, StringComparison.Ordinal))
{
codec = new RandomCodec(random, avoidCodecs);
}
else
{
Debug.Assert(false);
}
Codec.Default = codec;
// Initialize locale/ timezone.
string testLocale = SystemProperties.GetProperty("tests.locale", "random");
string testTimeZone = SystemProperties.GetProperty("tests.timezone", "random");
// Always pick a random one for consistency (whether tests.locale was specified or not).
savedLocale = CultureInfo.CurrentCulture;
CultureInfo randomLocale = LuceneTestCase.RandomCulture(random);
locale = testLocale.Equals("random", StringComparison.Ordinal) ? randomLocale : LuceneTestCase.CultureForName(testLocale);
#if NETSTANDARD
CultureInfo.CurrentCulture = locale;
#else
Thread.CurrentThread.CurrentCulture = locale;
#endif
// TimeZone.getDefault will set user.timezone to the default timezone of the user's locale.
// So store the original property value and restore it at end.
restoreProperties["user.timezone"] = SystemProperties.GetProperty("user.timezone");
savedTimeZone = testInstance.TimeZone;
TimeZoneInfo randomTimeZone = LuceneTestCase.RandomTimeZone(random);
timeZone = testTimeZone.Equals("random", StringComparison.Ordinal) ? randomTimeZone : TimeZoneInfo.FindSystemTimeZoneById(testTimeZone);
//TimeZone.Default = TimeZone; // LUCENENET NOTE: There doesn't seem to be an equivalent to this, but I don't think we need it.
similarity = random.NextBoolean() ? (Similarity) new DefaultSimilarity() : new RandomSimilarityProvider(random);
// Check codec restrictions once at class level.
try
{
CheckCodecRestrictions(codec);
}
catch (Exception e)
{
Console.Error.WriteLine("NOTE: " + e.Message + " Suppressed codecs: " + Arrays.ToString(avoidCodecs.ToArray()));
throw; // LUCENENET: CA2200: Rethrow to preserve stack details (https://docs.microsoft.com/en-us/visualstudio/code-quality/ca2200-rethrow-to-preserve-stack-details)
}
}
static BooleanScorer2()
{
defaultSimilarity = Search.Similarity.Default;
}
/// <summary>
/// Creates a new config that that handles the live <seealso cref="IndexWriter"/>
/// settings.
/// </summary>
internal LiveIndexWriterConfig(IndexWriterConfig config)
{
maxBufferedDeleteTerms = config.MaxBufferedDeleteTerms;
maxBufferedDocs = config.MaxBufferedDocs;
mergedSegmentWarmer = config.MergedSegmentWarmer;
RamBufferSizeMB = config.RAMBufferSizeMB;
readerTermsIndexDivisor = config.ReaderTermsIndexDivisor;
termIndexInterval = config.TermIndexInterval;
MatchVersion = config.MatchVersion;
analyzer = config.Analyzer;
delPolicy = config.DelPolicy;
Commit = config.IndexCommit;
openMode = config.OpenMode;
similarity = config.Similarity;
mergeScheduler = config.MergeScheduler;
writeLockTimeout = config.WriteLockTimeout;
indexingChain = config.IndexingChain;
codec = config.Codec;
infoStream = config.InfoStream;
mergePolicy = config.MergePolicy;
indexerThreadPool = config.IndexerThreadPool;
readerPooling = config.ReaderPooling;
flushPolicy = config.FlushPolicy;
PerThreadHardLimitMB = config.RAMPerThreadHardLimitMB;
useCompoundFile = config.UseCompoundFile;
checkIntegrityAtMerge = config.CheckIntegrityAtMerge;
}
/// <summary>
/// Assigns the specified number with the specified probability to this mention.
/// </summary>
/// <param name="number">
/// The number to be given to this mention.
/// </param>
/// <param name="probability">
/// The probability assosicated with the number assignment.
/// </param>
public virtual void SetNumber(Similarity.NumberEnum number, double probability)
{
mNumber = number;
mNumberProbability = probability;
}
protected internal PayloadNearSpanScorer(PayloadNearQuery outerInstance, Spans spans, Weight weight, Similarity similarity, Similarity.SimScorer docScorer)
: base(spans, weight, docScorer)
{
this.OuterInstance = outerInstance;
this.Spans = spans;
}
protected internal PayloadNearSpanScorer(PayloadNearQuery enclosingInstance, Lucene.Net.Search.Spans.Spans spans, Weight weight, Similarity similarity, byte[] norms):base(spans, weight, similarity, norms)
{
InitBlock(enclosingInstance);
this.spans = spans;
}
public BoostingSpanScorer(BoostingTermWeight enclosingInstance, TermSpans spans, Weight weight, Similarity similarity, byte[] norms) : base(spans, weight, similarity, norms)
{
InitBlock(enclosingInstance);
positions = spans.GetPositions();
}
public CustomWeight(CustomScoreQuery enclosingInstance, Searcher searcher)
{
InitBlock(enclosingInstance);
this.similarity = Enclosing_Instance.GetSimilarity(searcher);
this.subQueryWeight = Enclosing_Instance.subQuery.Weight(searcher);
this.valSrcWeights = new Weight[Enclosing_Instance.valSrcQueries.Length];
for (int i = 0; i < Enclosing_Instance.valSrcQueries.Length; i++)
{
this.valSrcWeights[i] = Enclosing_Instance.valSrcQueries[i].CreateWeight(searcher);
}
this.qStrict = Enclosing_Instance.strict;
}
public PayloadTermSpanScorer(PayloadTermWeight enclosingInstance, TermSpans spans, Weight weight, Similarity similarity, byte[] norms):base(spans, weight, similarity, norms)
{
InitBlock(enclosingInstance);
positions = spans.Positions;
}
// used by IndexWriterConfig
internal LiveIndexWriterConfig(Analyzer analyzer, Version matchVersion)
{
this.analyzer = analyzer;
this.MatchVersion = matchVersion;
RamBufferSizeMB = IndexWriterConfig.DEFAULT_RAM_BUFFER_SIZE_MB;
maxBufferedDocs = IndexWriterConfig.DEFAULT_MAX_BUFFERED_DOCS;
maxBufferedDeleteTerms = IndexWriterConfig.DEFAULT_MAX_BUFFERED_DELETE_TERMS;
readerTermsIndexDivisor = IndexWriterConfig.DEFAULT_READER_TERMS_INDEX_DIVISOR;
mergedSegmentWarmer = null;
termIndexInterval = IndexWriterConfig.DEFAULT_TERM_INDEX_INTERVAL; // TODO: this should be private to the codec, not settable here
delPolicy = new KeepOnlyLastCommitDeletionPolicy();
Commit = null;
useCompoundFile = IndexWriterConfig.DEFAULT_USE_COMPOUND_FILE_SYSTEM;
openMode = OpenMode_e.CREATE_OR_APPEND;
similarity = IndexSearcher.DefaultSimilarity;
mergeScheduler = new ConcurrentMergeScheduler();
writeLockTimeout = IndexWriterConfig.WRITE_LOCK_TIMEOUT;
indexingChain = DocumentsWriterPerThread.defaultIndexingChain;
codec = Codec.Default;
if (codec == null)
{
throw new System.NullReferenceException();
}
infoStream = Util.InfoStream.Default;
mergePolicy = new TieredMergePolicy();
flushPolicy = new FlushByRamOrCountsPolicy();
readerPooling = IndexWriterConfig.DEFAULT_READER_POOLING;
indexerThreadPool = new ThreadAffinityDocumentsWriterThreadPool(IndexWriterConfig.DEFAULT_MAX_THREAD_STATES);
PerThreadHardLimitMB = IndexWriterConfig.DEFAULT_RAM_PER_THREAD_HARD_LIMIT_MB;
}
public int CompareTo(Edge obj)
{
return(Similarity.CompareTo(obj.Similarity));
}
internal JustCompileSpanScorer(Spans spans, Weight weight, Similarity.SimScorer docScorer)
: base(spans, weight, docScorer)
{
}
public ValueSourceWeight(ValueSourceQuery enclosingInstance, Searcher searcher)
{
InitBlock(enclosingInstance);
this.similarity = Enclosing_Instance.GetSimilarity(searcher);
}
/// <summary>Constructs a Scorer.</summary>
/// <param name="similarity">The <c>Similarity</c> implementation used by this scorer.
/// </param>
protected internal Scorer(Similarity similarity)
{
this.similarity = similarity;
}
public PerFieldSimilarityWrapperHelper(Similarity ssBar, Similarity ssYak, Similarity ssA, Similarity ssB, Similarity ss)
{
this.ssBar = ssBar;
this.ssYak = ssYak;
this.ssA = ssA;
this.ssB = ssB;
this.ss = ss;
}
/// <summary>
/// Writes the document to the directory using the analyzer
/// and the similarity score; returns the SegmentInfo
/// describing the new segment
/// </summary>
public static SegmentCommitInfo WriteDoc(Random random, Directory dir, Analyzer analyzer, Similarity similarity, Document doc)
{
IndexWriter writer = new IndexWriter(dir, (new IndexWriterConfig(Util.LuceneTestCase.TEST_VERSION_CURRENT, analyzer)).SetSimilarity(similarity ?? IndexSearcher.DefaultSimilarity)); // LuceneTestCase.newIndexWriterConfig(random,
//writer.SetNoCFSRatio(0.0);
writer.AddDocument(doc);
writer.Commit();
SegmentCommitInfo info = writer.NewestSegment();
writer.Dispose();
return info;
}
public static float ComputeAndDecodeNorm(SweetSpotSimilarity decode, Similarity encode, FieldInvertState state)
{
return(decode.DecodeNormValue(ComputeAndGetNorm(encode, state)));
}
protected internal virtual void ProcessPayload(Similarity similarity)
{
if (positions.IsPayloadAvailable)
{
payload = positions.GetPayload(payload, 0);
payloadScore = Enclosing_Instance.Enclosing_Instance.function.CurrentScore(doc, Enclosing_Instance.Enclosing_Instance.internalTerm.Field, spans.Start(), spans.End(), payloadsSeen, payloadScore, similarity.ScorePayload(doc, Enclosing_Instance.Enclosing_Instance.internalTerm.Field, spans.Start(), spans.End(), payload, 0, positions.PayloadLength));
payloadsSeen++;
}
else
{
// zero out the payload?
}
}
public static byte ComputeAndGetNorm(Similarity s, FieldInvertState state)
{
return((byte)s.ComputeNorm(state));
}
public void TestSweetSpotComputeNorm()
{
SweetSpotSimilarity ss = new SweetSpotSimilarity();
ss.SetLengthNormFactors(1, 1, 0.5f, true);
Similarity d = new DefaultSimilarity();
Similarity s = ss;
// base case, should degrade
FieldInvertState invertState = new FieldInvertState("bogus");
invertState.Boost = 1.0f;
for (int i = 1; i < 1000; i++)
{
invertState.Length = i;
assertEquals("base case: i=" + i,
ComputeAndGetNorm(d, invertState),
ComputeAndGetNorm(s, invertState),
0.0f);
}
// make a sweet spot
ss.SetLengthNormFactors(3, 10, 0.5f, true);
for (int i = 3; i <= 10; i++)
{
invertState.Length = i;
assertEquals("3,10: spot i=" + i,
1.0f,
ComputeAndDecodeNorm(ss, ss, invertState),
0.0f);
}
for (int i = 10; i < 1000; i++)
{
invertState.Length = (i - 9);
byte normD = ComputeAndGetNorm(d, invertState);
invertState.Length = i;
byte normS = ComputeAndGetNorm(s, invertState);
assertEquals("3,10: 10<x : i=" + i,
normD,
normS,
0.0f);
}
// separate sweet spot for certain fields
SweetSpotSimilarity ssBar = new SweetSpotSimilarity();
ssBar.SetLengthNormFactors(8, 13, 0.5f, false);
SweetSpotSimilarity ssYak = new SweetSpotSimilarity();
ssYak.SetLengthNormFactors(6, 9, 0.5f, false);
SweetSpotSimilarity ssA = new SweetSpotSimilarity();
ssA.SetLengthNormFactors(5, 8, 0.5f, false);
SweetSpotSimilarity ssB = new SweetSpotSimilarity();
ssB.SetLengthNormFactors(5, 8, 0.1f, false);
Similarity sp = new PerFieldSimilarityWrapperHelper(ssBar, ssYak, ssA, ssB, ss);
invertState = new FieldInvertState("foo");
invertState.Boost = 1.0f;
for (int i = 3; i <= 10; i++)
{
invertState.Length = i;
assertEquals("f: 3,10: spot i=" + i,
1.0f,
ComputeAndDecodeNorm(ss, sp, invertState),
0.0f);
}
for (int i = 10; i < 1000; i++)
{
invertState.Length = (i - 9);
byte normD = ComputeAndGetNorm(d, invertState);
invertState.Length = (i);
byte normS = ComputeAndGetNorm(sp, invertState);
assertEquals("f: 3,10: 10<x : i=" + i,
normD,
normS,
0.0f);
}
invertState = new FieldInvertState("bar");
invertState.Boost = (1.0f);
for (int i = 8; i <= 13; i++)
{
invertState.Length = (i);
assertEquals("f: 8,13: spot i=" + i,
1.0f,
ComputeAndDecodeNorm(ss, sp, invertState),
0.0f);
}
invertState = new FieldInvertState("yak");
invertState.Boost = (1.0f);
for (int i = 6; i <= 9; i++)
{
invertState.Length = (i);
assertEquals("f: 6,9: spot i=" + i,
1.0f,
ComputeAndDecodeNorm(ss, sp, invertState),
0.0f);
}
invertState = new FieldInvertState("bar");
invertState.Boost = (1.0f);
for (int i = 13; i < 1000; i++)
{
invertState.Length = (i - 12);
byte normD = ComputeAndGetNorm(d, invertState);
invertState.Length = (i);
byte normS = ComputeAndGetNorm(sp, invertState);
assertEquals("f: 8,13: 13<x : i=" + i,
normD,
normS,
0.0f);
}
invertState = new FieldInvertState("yak");
invertState.Boost = (1.0f);
for (int i = 9; i < 1000; i++)
{
invertState.Length = (i - 8);
byte normD = ComputeAndGetNorm(d, invertState);
invertState.Length = (i);
byte normS = ComputeAndGetNorm(sp, invertState);
assertEquals("f: 6,9: 9<x : i=" + i,
normD,
normS,
0.0f);
}
// steepness
for (int i = 9; i < 1000; i++)
{
invertState = new FieldInvertState("a");
invertState.Boost = (1.0f);
invertState.Length = (i);
byte normSS = ComputeAndGetNorm(sp, invertState);
invertState = new FieldInvertState("b");
invertState.Boost = (1.0f);
invertState.Length = (i);
byte normS = ComputeAndGetNorm(sp, invertState);
assertTrue("s: i=" + i + " : a=" + normSS +
" < b=" + normS,
normSS < normS);
}
}
private void Proceed(string folderLocation, int nGramValue, string outputLocation, float threshold)
{
var pdfParser = new PdfParser();
var tfIdf = new DocumentTermFrequency();
var nGram = new Ngram();
var reports = new Dictionary <string, List <string> >();
foreach (var file in Directory.EnumerateFiles(folderLocation, "*.pdf"))
{
var fileName = Path.GetFileNameWithoutExtension(file);
var contents = pdfParser.GetText(file);
reports[fileName] = nGram.Create(contents, nGramValue);
}
var tfIdfMatrix = tfIdf.Create(reports);
var sw = new Stopwatch();
sw.Start();
Debug.WriteLine($"Create rowwise start.");
var sim = new Similarity().CreateRowWise(tfIdfMatrix);
Debug.WriteLine($"Create rowwise end ({sw.ElapsedMilliseconds} ms).");
// all report.
var strBuilder = new StringBuilder();
strBuilder.AppendLine("Roll,Similarity");
for (var r = 0; r < sim.GetLength(0); r++)
{
var line = "";
for (var c = 0; c < sim.GetLength(1); c++)
{
if (sim[r, c] > threshold)
{
line += $"{reports.Keys.ElementAt(c)}={Math.Round(sim[r, c] * 100, 2)}%,";
}
}
if (!string.IsNullOrEmpty(line))
{
var idx = line.LastIndexOf(',');
if (idx >= 0)
{
line = line.Substring(0, line.Length - 1);
}
}
strBuilder.AppendLine($"\"{reports.Keys.ElementAt(r)}\",\"{line}\"");
}
var output = $"{outputLocation}/Plagiarism_Output{DateTime.Now:yyyy-dd-M--HH-mm-ss}.csv";
File.WriteAllBytes(output, Encoding.UTF8.GetBytes(strBuilder.ToString()));
Process.Start(output);
}
public PayloadTermSpanScorer(PayloadTermQuery.PayloadTermWeight outerInstance, TermSpans spans, Weight weight, Similarity.SimScorer docScorer)
: base(spans, weight, docScorer)
{
this.OuterInstance = outerInstance;
TermSpans = spans;
}
public static string SetSimilarity(Similarity sim)
{
UseOBM25 = sim.Equals(Similarity.OkapiBM25);
return(Initialize());
}
/// <summary> Creates a <see cref="Scorer" /> with the given similarity and lists of required,
/// prohibited and optional scorers. In no required scorers are added, at least
/// one of the optional scorers will have to match during the search.
///
/// </summary>
/// <param name="similarity">The similarity to be used.
/// </param>
/// <param name="minNrShouldMatch">The minimum number of optional added scorers that should match
/// during the search. In case no required scorers are added, at least
/// one of the optional scorers will have to match during the search.
/// </param>
/// <param name="required">the list of required scorers.
/// </param>
/// <param name="prohibited">the list of prohibited scorers.
/// </param>
/// <param name="optional">the list of optional scorers.
/// </param>
public BooleanScorer2(Similarity similarity, int minNrShouldMatch,
System.Collections.Generic.List<Scorer> required,
System.Collections.Generic.List<Scorer> prohibited,
System.Collections.Generic.List<Scorer> optional)
: base(similarity)
{
if (minNrShouldMatch < 0)
{
throw new System.ArgumentException("Minimum number of optional scorers should not be negative");
}
coordinator = new Coordinator(this);
this.minNrShouldMatch = minNrShouldMatch;
optionalScorers = optional;
coordinator.maxCoord += optional.Count;
requiredScorers = required;
coordinator.maxCoord += required.Count;
prohibitedScorers = prohibited;
coordinator.Init();
countingSumScorer = MakeCountingSumScorer();
}
/// <summary>
/// Creates a RandomIndexWriter with a random config
///
/// LUCENENET specific
/// Similarity and TimeZone parameters allow a RandomIndexWriter to be
/// created without adding a dependency on
/// <see cref="LuceneTestCase.ClassEnv.Similarity"/> and
/// <see cref="LuceneTestCase.ClassEnv.TimeZone"/>
/// </summary>
public RandomIndexWriter(Random r, Directory dir, LuceneVersion v, Analyzer a, Similarity similarity, TimeZone timezone)
: this(r, dir, LuceneTestCase.NewIndexWriterConfig(r, v, a, similarity, timezone))
{
}
// constructor
internal ValueSourceScorer(ValueSourceQuery enclosingInstance, Similarity similarity, IndexReader reader, ValueSourceWeight w)
: base(similarity)
{
InitBlock(enclosingInstance);
this.weight = w;
this.qWeight = w.Value;
// this is when/where the values are first created.
vals = Enclosing_Instance.valSrc.GetValues(reader);
termDocs = reader.TermDocs(null);
}
public NormsSimilarity(Similarity @in)
{
this.@in = @in;
}
/*
private static String[] getLemmas(MentionContext xec) {
//TODO: Try multi-word lemmas first.
String word = xec.getHeadTokenText();
return DictionaryFactory.getDictionary().getLemmas(word,"NN");
}
private static Set getSynsetSet(MentionContext xec) {
//System.err.println("getting synsets for mention:"+xec.toText());
Set synsetSet = new HashSet();
String[] lemmas = getLemmas(xec);
for (int li = 0; li < lemmas.length; li++) {
String[] synsets = DictionaryFactory.getDictionary().getParentSenseKeys(lemmas[li],"NN",0);
for (int si=0,sn=synsets.length;si<sn;si++) {
synsetSet.add(synsets[si]);
}
}
return (synsetSet);
}
*/
/// <summary>
/// Assigns the specified gender with the specified probability to this mention.
/// </summary>
/// <param name="gender">
/// The gender to be given to this mention.
/// </param>
/// <param name="probability">
/// The probability assosicated with the gender assignment.
/// </param>
public virtual void SetGender(Similarity.GenderEnum gender, double probability)
{
mGender = gender;
mGenderProbability = probability;
}
/// <summary>
/// create a RandomIndexWriter with a random config: Uses TEST_VERSION_CURRENT
///
/// LUCENENET specific
/// Similarity and TimeZone parameters allow a RandomIndexWriter to be
/// created without adding a dependency on
/// <see cref="LuceneTestCase.ClassEnv.Similarity"/> and
/// <see cref="LuceneTestCase.ClassEnv.TimeZone"/>
/// </summary>
public RandomIndexWriter(Random r, Directory dir, Analyzer a, Similarity similarity, TimeZoneInfo timezone)
: this(r, dir, LuceneTestCase.NewIndexWriterConfig(r, LuceneTestCase.TEST_VERSION_CURRENT, a, similarity, timezone))
{
}
/// <summary>
/// Expert: set the <seealso cref="Similarity"/> implementation used by this IndexWriter.
/// <p>
/// <b>NOTE:</b> the similarity cannot be null.
///
/// <p>Only takes effect when IndexWriter is first created.
/// </summary>
public IndexWriterConfig SetSimilarity(Similarity similarity)
{
if (similarity == null)
{
throw new System.ArgumentException("similarity must not be null");
}
this.similarity = similarity;
return this;
}
public TestRuleSetupAndRestoreClassEnv()
{
/*// if verbose: print some debugging stuff about which codecs are loaded.
* if (LuceneTestCase.VERBOSE)
* {
* ISet<string> codecs = Codec.AvailableCodecs();
* foreach (string codec in codecs)
* {
* Console.WriteLine("Loaded codec: '" + codec + "': " + Codec.ForName(codec).GetType().Name);
* }
*
* ISet<string> postingsFormats = PostingsFormat.AvailablePostingsFormats();
* foreach (string postingsFormat in postingsFormats)
* {
* Console.WriteLine("Loaded postingsFormat: '" + postingsFormat + "': " + PostingsFormat.ForName(postingsFormat).GetType().Name);
* }
* }
*
* SavedInfoStream = InfoStream.Default;
* Random random = RandomizedContext.Current.Random;
* bool v = random.NextBoolean();
* if (LuceneTestCase.INFOSTREAM)
* {
* InfoStream.Default = new ThreadNameFixingPrintStreamInfoStream(Console.Out);
* }
* else if (v)
* {
* InfoStream.Default = new NullInfoStream();
* }
*
* Type targetClass = RandomizedContext.Current.GetTargetType;
* AvoidCodecs = new HashSet<string>();
*
* // set back to default
* LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = false;
*
* SavedCodec = Codec.Default;
* int randomVal = random.Next(10);
* if ("Lucene3x".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 3 && !ShouldAvoidCodec("Lucene3x"))) // preflex-only setup
* {
* Codec = Codec.ForName("Lucene3x");
* Debug.Assert((Codec is PreFlexRWCodec), "fix your classpath to have tests-framework.jar before lucene-core.jar");
* LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
* }
* else if ("Lucene40".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && randomVal == 0 && !ShouldAvoidCodec("Lucene40"))) // 4.0 setup
* {
* Codec = Codec.ForName("Lucene40");
* LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
* Debug.Assert(Codec is Lucene40RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
* Debug.Assert((PostingsFormat.ForName("Lucene40") is Lucene40RWPostingsFormat), "fix your classpath to have tests-framework.jar before lucene-core.jar");
* }
* else if ("Lucene41".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 1 && !ShouldAvoidCodec("Lucene41")))
* {
* Codec = Codec.ForName("Lucene41");
* LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
* Debug.Assert(Codec is Lucene41RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
* }
* else if ("Lucene42".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 2 && !ShouldAvoidCodec("Lucene42")))
* {
* Codec = Codec.ForName("Lucene42");
* LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
* Debug.Assert(Codec is Lucene42RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
* }
* else if ("Lucene45".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && "random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) && "random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) && randomVal == 5 && !ShouldAvoidCodec("Lucene45")))
* {
* Codec = Codec.ForName("Lucene45");
* LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE = true;
* Debug.Assert(Codec is Lucene45RWCodec, "fix your classpath to have tests-framework.jar before lucene-core.jar");
* }
* else if (("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT) == false) || ("random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT) == false))
* {
* // the user wired postings or DV: this is messy
* // refactor into RandomCodec....
*
* PostingsFormat format;
* if ("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT))
* {
* format = PostingsFormat.ForName("Lucene41");
* }
* else
* {
* format = PostingsFormat.ForName(LuceneTestCase.TEST_POSTINGSFORMAT);
* }
*
* DocValuesFormat dvFormat;
* if ("random".Equals(LuceneTestCase.TEST_DOCVALUESFORMAT))
* {
* dvFormat = DocValuesFormat.ForName("Lucene45");
* }
* else
* {
* dvFormat = DocValuesFormat.ForName(LuceneTestCase.TEST_DOCVALUESFORMAT);
* }
*
* Codec = new Lucene46CodecAnonymousInnerClassHelper(this, format, dvFormat);
* }
* else if ("Asserting".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && randomVal == 6 && !ShouldAvoidCodec("Asserting")))
* {
* Codec = new AssertingCodec();
* }
* else if ("Compressing".Equals(LuceneTestCase.TEST_CODEC) || ("random".Equals(LuceneTestCase.TEST_CODEC) && randomVal == 5 && !ShouldAvoidCodec("Compressing")))
* {
* Codec = CompressingCodec.RandomInstance(random);
* }
* else if (!"random".Equals(LuceneTestCase.TEST_CODEC))
* {
* Codec = Codec.ForName(LuceneTestCase.TEST_CODEC);
* }
* else if ("random".Equals(LuceneTestCase.TEST_POSTINGSFORMAT))
* {
* Codec = new RandomCodec(random, AvoidCodecs);
* }
* else
* {
* Debug.Assert(false);
* }
* Codec.Default = Codec;
*/
Random random = new Random(1);
Similarity = random.NextBoolean() ? (Similarity) new DefaultSimilarity() : new RandomSimilarityProvider(new Random(1));
/*
* // Check codec restrictions once at class level.
* try
* {
* CheckCodecRestrictions(Codec);
* }
* catch (Exception e)
* {
* Console.Error.WriteLine("NOTE: " + e.Message + " Suppressed codecs: " + Arrays.ToString(AvoidCodecs.ToArray()));
* throw e;
* }*/
}
