private Analyzer GetAnalyer(int type)
{
Analyzer analyzer;
string path =System.Configuration.ConfigurationSettings.AppSettings["Data"].ToString();
switch (type)
{
case 0:
analyzer=new StockFooAnalyzer(path);
break;
case 1:
analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_CURRENT);
break;
case 2:
analyzer = new SimpleAnalyzer();
break;
case 3:
analyzer = new StopAnalyzer(Lucene.Net.Util.Version.LUCENE_CURRENT);
break;
case 4:
analyzer = new KeywordAnalyzer();
break;
case 5:
analyzer = new WhitespaceAnalyzer();
break;
default:
analyzer = new StockFooAnalyzer(path);
break;
}
return analyzer;
}
public void SpecifyAnalyzer()
{
var analyzer = new SimpleAnalyzer();
map.Property(x => x.Date).AnalyzeWith(analyzer);
var mapper = GetMappingInfo("Date");
Assert.That(mapper.Analyzer, Is.SameAs(analyzer));
}
public virtual void TestSimple()
{
Analyzer a = new SimpleAnalyzer();
AssertAnalyzesTo(a, "foo bar FOO BAR", new System.String[]{"foo", "bar", "foo", "bar"});
AssertAnalyzesTo(a, "foo bar . FOO <> BAR", new System.String[]{"foo", "bar", "foo", "bar"});
AssertAnalyzesTo(a, "foo.bar.FOO.BAR", new System.String[]{"foo", "bar", "foo", "bar"});
AssertAnalyzesTo(a, "U.S.A.", new System.String[]{"u", "s", "a"});
AssertAnalyzesTo(a, "C++", new System.String[]{"c"});
AssertAnalyzesTo(a, "B2B", new System.String[]{"b", "b"});
AssertAnalyzesTo(a, "2B", new System.String[]{"b"});
AssertAnalyzesTo(a, "\"QUOTED\" word", new System.String[]{"quoted", "word"});
}
public void ReusabeleTokenStreamTest()
{
string testwords = "我是中国人，I can speak chinese!";
SimpleAnalyzer sanalyzer = new SimpleAnalyzer();
TokenStream ts = sanalyzer.ReusableTokenStream("", new StringReader(testwords));
Token token;
while ((token = ts.Next()) != null)
{
Console.WriteLine(token.TermText());
}
ts.Close();
}
public static void Main(System.String[] args)
{
try
{
Directory directory = new RAMDirectory();
Analyzer analyzer = new SimpleAnalyzer();
IndexWriter writer = new IndexWriter(directory, analyzer, true);
int MAX_DOCS = 225;
for (int j = 0; j < MAX_DOCS; j++)
{
Lucene.Net.Documents.Document d = new Lucene.Net.Documents.Document();
d.Add(new Field(PRIORITY_FIELD, HIGH_PRIORITY, Field.Store.YES, Field.Index.TOKENIZED));
d.Add(new Field(ID_FIELD, System.Convert.ToString(j), Field.Store.YES, Field.Index.TOKENIZED));
writer.AddDocument(d);
}
writer.Close();
// try a search without OR
Searcher searcher = new IndexSearcher(directory);
Hits hits = null;
Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.QueryParser(PRIORITY_FIELD, analyzer);
Query query = parser.Parse(HIGH_PRIORITY);
System.Console.Out.WriteLine("Query: " + query.ToString(PRIORITY_FIELD));
hits = searcher.Search(query);
PrintHits(hits);
searcher.Close();
// try a new search with OR
searcher = new IndexSearcher(directory);
hits = null;
parser = new Lucene.Net.QueryParsers.QueryParser(PRIORITY_FIELD, analyzer);
query = parser.Parse(HIGH_PRIORITY + " OR " + MED_PRIORITY);
System.Console.Out.WriteLine("Query: " + query.ToString(PRIORITY_FIELD));
hits = searcher.Search(query);
PrintHits(hits);
searcher.Close();
}
catch (System.Exception e)
{
System.Console.Out.WriteLine(" caught a " + e.GetType() + "\n with message: " + e.Message);
}
}
public virtual void TestSimple()
{
Analyzer a = new SimpleAnalyzer();
AssertAnalyzesTo(a, "foo bar FOO BAR", new System.String[] { "foo", "bar", "foo", "bar" });
AssertAnalyzesTo(a, "foo bar . FOO <> BAR", new System.String[] { "foo", "bar", "foo", "bar" });
AssertAnalyzesTo(a, "foo.bar.FOO.BAR", new System.String[] { "foo", "bar", "foo", "bar" });
AssertAnalyzesTo(a, "U.S.A.", new System.String[] { "u", "s", "a" });
AssertAnalyzesTo(a, "C++", new System.String[] { "c" });
AssertAnalyzesTo(a, "B2B", new System.String[] { "b", "b" });
AssertAnalyzesTo(a, "2B", new System.String[] { "b" });
AssertAnalyzesTo(a, "\"QUOTED\" word", new System.String[] { "quoted", "word" });
}
// This method takes a search term and a text as a parameter, and displays the text
// with the search term in bold.
public static void RealHighlighter(string searchTerm, string text)
{
TermQuery query = new TermQuery(new Term("mainText", searchTerm));
Lucene.Net.Search.Highlight.IScorer scorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(scorer);
System.IO.StringReader reader = new System.IO.StringReader(text);
TokenStream tokenStream = new SimpleAnalyzer().TokenStream("mainText", reader);
String[] toBePrinted = highlighter.GetBestFragments(tokenStream, text, 5); // 5 is the maximum number of fragments that gets tested
foreach (var word in toBePrinted)
{
Console.Write(word);
}
}
public static void Main(System.String[] args)
{
try
{
Directory directory = new RAMDirectory();
Analyzer analyzer = new SimpleAnalyzer();
IndexWriter writer = new IndexWriter(directory, analyzer, true);
System.String[] docs = new System.String[]{"a b c d e", "a b c d e a b c d e", "a b c d e f g h i j", "a c e", "e c a", "a c e a c e", "a c e a b c"};
for (int j = 0; j < docs.Length; j++)
{
Document d = new Document();
d.Add(Field.Text("contents", docs[j]));
writer.AddDocument(d);
}
writer.Close();
Searcher searcher = new IndexSearcher(directory);
System.String[] queries = new System.String[]{"\"a c e\""};
Hits hits = null;
QueryParsers.QueryParser parser = new QueryParsers.QueryParser("contents", analyzer);
parser.SetPhraseSlop(4);
for (int j = 0; j < queries.Length; j++)
{
Query query = parser.Parse(queries[j]);
System.Console.Out.WriteLine("Query: " + query.ToString("contents"));
//DateFilter filter =
// new DateFilter("modified", Time(1997,0,1), Time(1998,0,1));
//DateFilter filter = DateFilter.Before("modified", Time(1997,00,01));
//System.out.println(filter);
hits = searcher.Search(query);
System.Console.Out.WriteLine(hits.Length() + " total results");
for (int i = 0; i < hits.Length() && i < 10; i++)
{
Document d = hits.Doc(i);
System.Console.Out.WriteLine(i + " " + hits.Score(i) + " " + d.Get("contents"));
}
}
searcher.Close();
}
catch (System.Exception e)
{
System.Console.Out.WriteLine(" caught a " + e.GetType() + "\n with message: " + e.Message);
}
}
// TEST METHOD FOR HIGHLIGHTING.
public static void Highlighter()
{
string textTest = "I am a man that follows hell.";
TermQuery queryTest = new TermQuery(new Term("", "hell"));
Lucene.Net.Search.Highlight.IScorer scorer = new QueryScorer(queryTest);
Highlighter highlighter = new Highlighter(scorer);
System.IO.StringReader reader = new System.IO.StringReader(textTest);
TokenStream tokenStream = new SimpleAnalyzer().TokenStream("field", reader);
String[] toBePrinted = highlighter.GetBestFragments(tokenStream, textTest, 1); // 1 is the maximum number of fragments that gets tested
foreach (var word in toBePrinted)
{
Console.WriteLine(word);
}
}
public void Code()
{
Analyzer _keywordanalyzer = new KeywordAnalyzer();
Analyzer _simpleanalyzer = new Lucene.Net.Analysis.SimpleAnalyzer();
Analyzer _stopanalyzer = new Lucene.Net.Analysis.StopAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
Analyzer _whitespaceanalyzer = new Lucene.Net.Analysis.WhitespaceAnalyzer();
Analyzer _standardanalyzer = new Lucene.Net.Analysis.Standard.StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
var _perfieldanalyzer = new Lucene.Net.Analysis.PerFieldAnalyzerWrapper(_standardanalyzer);
_perfieldanalyzer.AddAnalyzer("firstname", _keywordanalyzer);
_perfieldanalyzer.AddAnalyzer("lastname", _keywordanalyzer);
IndexWriter _writer = new IndexWriter(_directory, _perfieldanalyzer, IndexWriter.MaxFieldLength.UNLIMITED);
IndexReader _reader = _writer.GetReader();
IndexSearcher _searcher = new IndexSearcher(_reader);
//QueryParser parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, "title", _standardanalyzer);
string[] fields = new[] { "text", "title", "author" };
var boosts = new Dictionary <string, float>();
boosts.Add("text", 2.0f);
boosts.Add("title", 1.5f);
QueryParser parser = new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_30, fields, _standardanalyzer, boosts);
Query query = parser.Parse("lucene is great");
TopDocs hits = _searcher.Search(query, 1000);
IEnumerable <Document> docs = hits.ScoreDocs.Select(hit => _searcher.Doc(hit.Doc));
var books = docs.Select(doc => new Book()
{
Text = doc.Get("text"),
Title = doc.Get("title"),
Author = doc.Get("author"),
Length = Int32.Parse(doc.Get("length"))
});
_writer.Optimize();
_writer.Commit();
_writer.DeleteAll();
}
private void DoTest(System.IO.StringWriter out_Renamed, bool useCompoundFiles)
{
Directory directory = new RAMDirectory();
Analyzer analyzer = new SimpleAnalyzer();
IndexWriter writer = new IndexWriter(directory, analyzer, true);
writer.SetUseCompoundFile(useCompoundFiles);
int MAX_DOCS = 225;
for (int j = 0; j < MAX_DOCS; j++)
{
Document d = new Document();
d.Add(Field.Text(PRIORITY_FIELD, HIGH_PRIORITY));
d.Add(Field.Text(ID_FIELD, System.Convert.ToString(j)));
writer.AddDocument(d);
}
writer.Close();
// try a search without OR
Searcher searcher = new IndexSearcher(directory);
Hits hits = null;
QueryParsers.QueryParser parser = new QueryParsers.QueryParser(PRIORITY_FIELD, analyzer);
Query query = parser.Parse(HIGH_PRIORITY);
out_Renamed.WriteLine("Query: " + query.ToString(PRIORITY_FIELD));
hits = searcher.Search(query);
PrintHits(out_Renamed, hits);
CheckHits(hits, MAX_DOCS);
searcher.Close();
// try a new search with OR
searcher = new IndexSearcher(directory);
hits = null;
parser = new QueryParsers.QueryParser(PRIORITY_FIELD, analyzer);
query = parser.Parse(HIGH_PRIORITY + " OR " + MED_PRIORITY);
out_Renamed.WriteLine("Query: " + query.ToString(PRIORITY_FIELD));
hits = searcher.Search(query);
PrintHits(out_Renamed, hits);
CheckHits(hits, MAX_DOCS);
searcher.Close();
}
private void DoTestSearch(System.IO.StreamWriter out_Renamed, bool useCompoundFile)
{
Directory directory = new RAMDirectory();
Analyzer analyzer = new SimpleAnalyzer();
IndexWriter writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
writer.SetUseCompoundFile(useCompoundFile);
System.String[] docs = new System.String[]{"a b c d e", "a b c d e a b c d e", "a b c d e f g h i j", "a c e", "e c a", "a c e a c e", "a c e a b c"};
for (int j = 0; j < docs.Length; j++)
{
Document d = new Document();
d.Add(new Field("contents", docs[j], Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(d);
}
writer.Close();
Searcher searcher = new IndexSearcher(directory);
System.String[] queries = new System.String[]{"a b", "\"a b\"", "\"a b c\"", "a c", "\"a c\"", "\"a c e\""};
ScoreDoc[] hits = null;
QueryParser parser = new QueryParser("contents", analyzer);
parser.SetPhraseSlop(4);
for (int j = 0; j < queries.Length; j++)
{
Query query = parser.Parse(queries[j]);
out_Renamed.WriteLine("Query: " + query.ToString("contents"));
//DateFilter filter =
// new DateFilter("modified", Time(1997,0,1), Time(1998,0,1));
//DateFilter filter = DateFilter.Before("modified", Time(1997,00,01));
//System.out.println(filter);
hits = searcher.Search(query, null, 1000).scoreDocs;
out_Renamed.WriteLine(hits.Length + " total results");
for (int i = 0; i < hits.Length && i < 10; i++)
{
Document d = searcher.Doc(hits[i].doc);
out_Renamed.WriteLine(i + " " + hits[i].score + " " + d.Get("contents"));
}
}
searcher.Close();
}
public void WithoutGettingErrors()
{
using(var luceneCodecDirectory = new LuceneCodecDirectory(Path, Enumerable.Empty<AbstractIndexCodec>()))
using(var simpleAnalyzer = new SimpleAnalyzer())
{
using (var w = new IndexWriter(luceneCodecDirectory, simpleAnalyzer, true, IndexWriter.MaxFieldLength.UNLIMITED))
{
var doc = new Lucene.Net.Documents.Document();
doc.Add(new Field("test", "value", Field.Store.YES, Field.Index.ANALYZED));
w.AddDocument(doc);
}
using(var s = new IndexSearcher(luceneCodecDirectory))
{
var termQuery = new TermQuery(new Term("test", "value"));
var topDocs = s.Search(termQuery, 10);
Assert.Equal(1, topDocs.TotalHits);
}
}
}
// This method is printing out the message details given the index document.
// NOTE: The field "mainText" must be stored in indexing level. Same goes for any
// other field you want to search.
private static void DisplayMessage(Document d, string searchTerm)
{
// THIS IS USED IN THE DATABASE INDEXic
//Console.WriteLine("id: " + d.Get("id") + "\n" + "messageBox: " + d.Get("messageBox") + "\n" + "incoming: " + d.Get("incoming") + "\n" + "date: " + d.Get("date") + "\n" + "mainText: " + d.Get("mainText"));
// THIS IS USED IN MY TEST FILES
//Console.WriteLine("id: " + d.Get("id") + "\n" + "mainText: " + d.Get("mainText"));
string text = d.Get("mainText");
TermQuery query = new TermQuery(new Term("mainText", searchTerm));
Lucene.Net.Search.Highlight.IScorer scorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(scorer);
System.IO.StringReader reader = new System.IO.StringReader(text);
TokenStream tokenStream = new SimpleAnalyzer().TokenStream("mainText", reader);
String[] toBePrinted = highlighter.GetBestFragments(tokenStream, text, 5); // 5 is the maximum number of fragments that gets tested
foreach (var word in toBePrinted)
{
Console.Write(word);
}
Console.WriteLine("=====================");
Console.ReadKey();
}
private void InitLucene()
{
analyzer = new Lucene.Net.Analysis.SimpleAnalyzer();
parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, TEXT_FN, analyzer);
}
/// <summary>
/// Returns an Analyzer for the given AnalyzerType
/// </summary>
/// <param name="oAnalyzerType">Enumeration value</param>
/// <returns>Analyzer</returns>
public static Analyzer GetAnalyzer(AnalyzerType oAnalyzerType)
{
Analyzer oAnalyzer = null;
switch (oAnalyzerType)
{
case AnalyzerType.SimpleAnalyzer:
oAnalyzer = new SimpleAnalyzer();
break;
case AnalyzerType.StopAnalyzer:
oAnalyzer = new StopAnalyzer();
break;
case AnalyzerType.WhitespaceAnalyzer:
oAnalyzer = new WhitespaceAnalyzer();
break;
default:
case AnalyzerType.StandardAnalyzer:
oAnalyzer = new StandardAnalyzer();
break;
}
return oAnalyzer;
}
private void DoTest(System.IO.StreamWriter out_Renamed, bool useCompoundFiles)
{
Directory directory = new RAMDirectory();
Analyzer analyzer = new SimpleAnalyzer();
IndexWriter writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
writer.UseCompoundFile = useCompoundFiles;
int MAX_DOCS = 225;
for (int j = 0; j < MAX_DOCS; j++)
{
Document d = new Document();
d.Add(new Field(PRIORITY_FIELD, HIGH_PRIORITY, Field.Store.YES, Field.Index.ANALYZED));
d.Add(new Field(ID_FIELD, System.Convert.ToString(j), Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(d);
}
writer.Close();
// try a search without OR
Searcher searcher = new IndexSearcher(directory, true);
QueryParser parser = new QueryParser(Util.Version.LUCENE_CURRENT, PRIORITY_FIELD, analyzer);
Query query = parser.Parse(HIGH_PRIORITY);
out_Renamed.WriteLine("Query: " + query.ToString(PRIORITY_FIELD));
ScoreDoc[] hits = searcher.Search(query, null, MAX_DOCS).ScoreDocs;
PrintHits(out_Renamed, hits, searcher);
CheckHits(hits, MAX_DOCS, searcher);
searcher.Close();
// try a new search with OR
searcher = new IndexSearcher(directory, true);
hits = null;
parser = new QueryParser(Util.Version.LUCENE_CURRENT, PRIORITY_FIELD, analyzer);
query = parser.Parse(HIGH_PRIORITY + " OR " + MED_PRIORITY);
out_Renamed.WriteLine("Query: " + query.ToString(PRIORITY_FIELD));
hits = searcher.Search(query, null, MAX_DOCS).ScoreDocs;
PrintHits(out_Renamed, hits, searcher);
CheckHits(hits, MAX_DOCS, searcher);
searcher.Close();
}
public static string[] SplitWords2(string content)
{
List<string> strList = new List<string>();
Analyzer analyzer = new Lucene.Net.Analysis.SimpleAnalyzer();//指定使用盘古 PanGuAnalyzer 分词算法
TokenStream tokenStream = analyzer.TokenStream("", new StringReader(content));
Lucene.Net.Analysis.Tokenattributes.ITermAttribute ita;
bool hasNext = tokenStream.IncrementToken();
while (hasNext)
{
ita = tokenStream.GetAttribute<Lucene.Net.Analysis.Tokenattributes.ITermAttribute>();
strList.Add(ita.Term);
hasNext = tokenStream.IncrementToken();
}
return strList.ToArray();
}
private void queryRhino_Lucene()
{
try
{
String indexRhinoFile = System.IO.Directory.GetCurrentDirectory() + @"\rhino-documents.json";
String queryRhinoFile = System.IO.Directory.GetCurrentDirectory() + @"\rhino-queries.json";
String indexLuceneFile = System.IO.Directory.GetCurrentDirectory() + @"\lucene-documents.json";
String queryLuceneFile = System.IO.Directory.GetCurrentDirectory() + @"\lucene-queries.json";
List<indexDocument> results = new List<indexDocument>();
List<indexQuery> queries = new List<indexQuery>();
String line;
System.IO.StreamReader indexFile = new System.IO.StreamReader(indexLuceneFile);
//System.IO.StreamReader indexFile = new System.IO.StreamReader(indexRhinoFile);
while ((line = indexFile.ReadLine()) != null)
{
indexDocument result = JsonConvert.DeserializeObject<indexDocument>(line);
results.Add(result);
}
indexFile.Close();
line = "";
System.IO.StreamReader queryFile = new System.IO.StreamReader(queryLuceneFile);
//System.IO.StreamReader queryFile = new System.IO.StreamReader(queryRhinoFile);
while ((line = queryFile.ReadLine()) != null)
{
indexQuery query = JsonConvert.DeserializeObject<indexQuery>(line);
queries.Add(query);
}
queryFile.Close();
Lucene.Net.Store.Directory indexDirectory = FSDirectory.Open(@"c:\TEMP_LUCENE2");//System.IO.Directory.GetCurrentDirectory());
//Lucene.Net.Store.Directory indexDirectory = FSDirectory.Open(@"c:\TEMP_RHINO2");
Analyzer analyzer = new SimpleAnalyzer();
//Analyzer analyzer = new StopAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
//Analyzer analyzer = new WhitespaceAnalyzer();
// Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
//CREATE INDEX
IndexWriterConfig config = new IndexWriterConfig();
IndexWriter writer = new IndexWriter(indexDirectory, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
//For each line in LUCENE-DOCUMENTS
foreach (indexDocument d in results)
{
Document doc;// = new Document();
doc = d.ToDocument();
//doc.Add(new Field("name", d.name, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("id", d.id, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("file_name", d.file_name, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("tokens", d.tokens.ToString(), Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
writer.AddDocument(doc);
}
writer.Optimize();
writer.Commit();
writer.Dispose();
//System.IO.StreamWriter resultsFile = new System.IO.StreamWriter(@"C:\JSON_RESULTS\lucene_results.json");
//File.Create(@"C:\rhino_results.json");
//System.IO.StreamWriter resultsFile = new System.IO.StreamWriter(@"C:\JSON_RESULTS\rhino_results.json", true);
//SEARCH
//For each query
foreach (indexQuery q in queries)
{
Document query;// = new Document();
query = q.ToDocument();
//console.writeline("Query " + query.Get("id"));
String jsonResult = "{\"query_id\": " + query.Get("id") + ", ";
Field[] title_tokens = query.GetFields("title_tokens");
Field[] description_tokens = query.GetFields("description_tokens");
String title_query = "";
String description_query = "";
foreach (Field f in title_tokens)
{
title_query += " " + f.StringValue;
}
foreach (Field f in description_tokens)
{
description_query += " " + f.StringValue;
}
String query1 = title_query + " " + description_query;
String query2 = title_query;
String query3 = description_query;
QueryParser queryParser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, "tokens", analyzer);
Query query1Parsed = queryParser.Parse(query1);
Query query2Parsed = queryParser.Parse(query2);
Query query3Parsed = queryParser.Parse(query3);
int hitsPerPage = 20;
//Lucene.Net.Store.Directory directory = FSDirectory.Open(System.IO.Directory.GetCurrentDirectory());
IndexReader reader = DirectoryReader.Open(indexDirectory, true);
IndexSearcher searcher = new IndexSearcher(reader);
//console.writeline("---------------");
jsonResult += "\"title_and_description\": [";
//console.writeline("Results for query #1 - Tile and Description:");
TopDocs docs = searcher.Search(query1Parsed, hitsPerPage);
ScoreDoc[] hits = docs.ScoreDocs;
for (int i = 0; i < hits.Length; i++)
{
int docId = hits[i].Doc;
Document d = searcher.Doc(docId);
//string file_name = d.Get("file_name");
//console.writeline("DocId: " + docId.ToString());
if (i == hits.Length - 1) jsonResult += (docId + 1).ToString();
else jsonResult += (docId + 1).ToString() + ", ";
}
jsonResult += "], ";
//console.writeline("---------------");
jsonResult += "\"title_only\": [";
//console.writeline("Results for query #2 - Title only:");
docs = searcher.Search(query2Parsed, hitsPerPage);
hits = docs.ScoreDocs;
for (int i = 0; i < hits.Length; i++)
{
int docId = hits[i].Doc;
Document d = searcher.Doc(docId);
//string file_name = d.Get("file_name");
//console.writeline("DocId: " + docId.ToString());
if (i == hits.Length - 1) jsonResult += (docId + 1).ToString();
else jsonResult += (docId + 1).ToString() + ", ";
}
jsonResult += "], ";
//console.writeline("---------------");
jsonResult += "\"description_only\": [";
//console.writeline("Results for query #3 - Description only:");
docs = searcher.Search(query3Parsed, hitsPerPage);
hits = docs.ScoreDocs;
for (int i = 0; i < hits.Length; i++)
{
int docId = hits[i].Doc;
Document d = searcher.Doc(docId);
//string file_name = d.Get("file_name");
//console.writeline("DocId: " + docId.ToString());
if (i == hits.Length - 1) jsonResult += (docId + 1).ToString();
else jsonResult += (docId + 1).ToString() + ", ";
}
jsonResult += "]}";
//console.writeline("---------------");
//resultsFile.WriteLine(jsonResult);
Console.WriteLine(jsonResult);
}
//resultsFile.Close();
}
catch (Exception ex) { MessageBox.Show(ex.ToString()); }
}
public virtual Lucene.Net.QueryParsers.QueryParser GetParser(Analyzer a)
{
if (a == null)
a = new SimpleAnalyzer();
Lucene.Net.QueryParsers.QueryParser qp = new Lucene.Net.QueryParsers.QueryParser("field", a);
qp.SetDefaultOperator(Lucene.Net.QueryParsers.QueryParser.OR_OPERATOR);
return qp;
}
public virtual Query GetQueryDOA(System.String query, Analyzer a)
{
if (a == null)
a = new SimpleAnalyzer();
Lucene.Net.QueryParsers.QueryParser qp = new Lucene.Net.QueryParsers.QueryParser("field", a);
qp.SetDefaultOperator(Lucene.Net.QueryParsers.QueryParser.AND_OPERATOR);
return qp.Parse(query);
}
public void TestQueryScorerHits()
{
Analyzer analyzer = new SimpleAnalyzer();
QueryParser qp = new QueryParser(TEST_VERSION, FIELD_NAME, analyzer);
query = qp.Parse("\"very long\"");
searcher = new IndexSearcher(ramDir, true);
TopDocs hits = searcher.Search(query, 10);
QueryScorer scorer = new QueryScorer(query, FIELD_NAME);
Highlighter highlighter = new Highlighter(scorer);
for (int i = 0; i < hits.ScoreDocs.Length; i++)
{
Document doc = searcher.Doc(hits.ScoreDocs[i].Doc);
String storedField = doc.Get(FIELD_NAME);
TokenStream stream = TokenSources.GetAnyTokenStream(searcher.IndexReader, hits.ScoreDocs[i].Doc,
FIELD_NAME, doc, analyzer);
IFragmenter fragmenter = new SimpleSpanFragmenter(scorer);
highlighter.TextFragmenter = fragmenter;
String fragment = highlighter.GetBestFragment(stream, storedField);
Console.WriteLine(fragment);
}
}
private void OpenIndexWriter()
{
var dir = FSDirectory.Open(new DirectoryInfo(Config.IndexPath));
//create an analyzer to process the text
var analyzer = new SimpleAnalyzer();
//create the index writer with the directory and analyzer defined.
_indexWriter = new IndexWriter(dir, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
_indexWriter.SetMaxBufferedDocs(IndexWriter.DISABLE_AUTO_FLUSH);
}
public void addToDictionary()
{
String derbyJson = AppDomain.CurrentDomain.BaseDirectory + @"jira\derby_issues_filtered.json";
String ofbizJson = AppDomain.CurrentDomain.BaseDirectory + @"jira\ofbiz_issues_filtered.json";
List<Issue> issuesDerby = new List<Issue>();
List<Issue> issuesOfbiz = new List<Issue>();
String line;
System.IO.StreamReader indexFileDerby = new System.IO.StreamReader(derbyJson);
System.IO.StreamReader indexFileOfbiz = new System.IO.StreamReader(ofbizJson);
//System.IO.StreamReader indexFile = new System.IO.StreamReader(indexRhinoFile);
while ((line = indexFileDerby.ReadLine()) != null)
{
Issue issue = JsonConvert.DeserializeObject<Issue>(line);
issuesDerby.Add(issue);
}
indexFileDerby.Close();
while ((line = indexFileOfbiz.ReadLine()) != null)
{
Issue issue = JsonConvert.DeserializeObject<Issue>(line);
issuesOfbiz.Add(issue);
}
indexFileOfbiz.Close();
Lucene.Net.Store.Directory indexDirectory = FSDirectory.Open(@"c:\temp_corpus"); //System.IO.Directory.GetCurrentDirectory());
//Lucene.Net.Store.Directory indexDirectory = FSDirectory.Open(@"c:\TEMP_RHINO2");
Analyzer analyzer = new SimpleAnalyzer();
//Analyzer analyzer = new StopAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
//Analyzer analyzer = new WhitespaceAnalyzer();
// Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
//CREATE INDEX
IndexWriterConfig config = new IndexWriterConfig();
IndexWriter writer = new IndexWriter(indexDirectory, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
//For each line in LUCENE-DOCUMENTS
foreach (Issue d in issuesDerby)
{
Document doc;// = new Document();
doc = d.ToDocument();
//doc.Add(new Field("name", d.name, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("id", d.id, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("file_name", d.file_name, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("tokens", d.tokens.ToString(), Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
writer.AddDocument(doc);
}
writer.Optimize();
writer.Commit();
writer.Dispose();
foreach (Issue d in issuesOfbiz)
{
Document doc;// = new Document();
doc = d.ToDocument();
//doc.Add(new Field("name", d.name, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("id", d.id, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("file_name", d.file_name, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
//doc.Add(new Field("tokens", d.tokens.ToString(), Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
writer.AddDocument(doc);
}
writer.Optimize();
writer.Commit();
writer.Dispose();
}