public SearchResult(Document doc, float score)
{
Fields = new Dictionary<string, string>();
string id = doc.Get("id");
if (string.IsNullOrEmpty(id))
{
id = doc.Get("__NodeId");
}
Id = int.Parse(id);
Score = score;
//we can use lucene to find out the fields which have been stored for this particular document
//I'm not sure if it'll return fields that have null values though
var fields = doc.GetFields();
//ignore our internal fields though
foreach (Field field in fields.Cast<Field>())
{
string fieldName = field.Name();
Fields.Add(fieldName, doc.Get(fieldName));
//Examine returns some fields as e.g. __FieldName rather than fieldName
if (fieldName.StartsWith(LuceneIndexer.SpecialFieldPrefix))
{
int offset = LuceneIndexer.SpecialFieldPrefix.Length;
string tidiedFieldName = Char.ToLower(fieldName[offset]) + fieldName.Substring(offset + 1);
if (!Fields.ContainsKey(tidiedFieldName))
{
Fields.Add(tidiedFieldName, doc.Get(fieldName));
}
}
}
}
private static void SearchByFld2(string fld, string txt)
{
string strIndexDir = @"D:\Index";
Analyzer std = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
Lucene.Net.Store.Directory directory = Lucene.Net.Store.FSDirectory.Open(new System.IO.DirectoryInfo(strIndexDir));
Lucene.Net.Search.Searcher srchr =
new Lucene.Net.Search.IndexSearcher(Lucene.Net.Index.IndexReader.Open(directory, true));
var parser = new Lucene.Net.QueryParsers.QueryParser(Lucene.Net.Util.Version.LUCENE_30, fld, std);
Lucene.Net.Search.Query qry = parser.Parse(txt);
var cllctr = srchr.Search(qry, 1000);
Console.WriteLine(cllctr.TotalHits);
ScoreDoc[] hits = cllctr.ScoreDocs;
for (int i = 0; i < hits.Length; i++)
{
int docId = hits[i].Doc;
float score = hits[i].Score;
Lucene.Net.Documents.Document doc = srchr.Doc(docId);
Console.WriteLine("索引时间：" + doc.Get("addtime"));
Console.WriteLine("Searched from Text: " + doc.Get(fld));
}
Console.WriteLine("over");
}
// Activity 7
/// <summary>
/// Outputs results to the screen
/// </summary>
/// <param name="results">Search results</param>
public void DisplayResults(TopDocs results)
{
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
// retrieve the document from the 'ScoreDoc' object
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
if (doc.GetField("passage_text") != null)
{
string Result_passage_text = doc.Get("passage_text").ToString();
string Result_url = doc.Get("url").ToString();
Console.WriteLine("\n\nRank: " + rank + "\nPassage text: " + Result_passage_text);
Console.WriteLine("url: " + Result_url);
}
else
{
string Result_query = doc.Get("query").ToString();
string Result_answers = doc.Get("answers").ToString();
Console.WriteLine("\n\nRank: " + rank + "\nQuery: " + Result_query);
Console.WriteLine("answers: " + Result_answers);
}
//Console.WriteLine("Rank " + rank + " score " + scoreDoc.Score + " text " + myFieldValue);
}
}
public SearchResult(Document searchDoc,string sample,float score)
{
this.Id = searchDoc.Get("contentid");
this.Type = searchDoc.Get("type");
this.Sample = sample;
this.Score = score;
}
public TopDocs SearchIndex(string querytext)
{
querytext = querytext.ToLower();
// var multiFieldQuery = Parse
Query query = parser.Parse(querytext);
TopDocs results = searcher.Search(query, 500);
totalresultLabel.Text = "Total number of result is: " + (results.TotalHits).ToString();
int i = 0;
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
Array.Resize <string>(ref searchResultList, i + 1);
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
//string myFieldValue = doc.Get(TEXT_FN).ToString();
string titleValue = doc.Get(TITLE_FN).ToString();
string abstractValue = doc.Get(ABSTRACT_FN).ToString();
searchResultList[i] = "Q0 " + (scoreDoc.Doc + 1) + " " + rank + " " + scoreDoc.Score + " ";
i++;
}
return(results);
}
/// <summary>
/// Outputs results to the screen
/// </summary>
/// <param name="results">Search results</param>
public void DisplayResults(TopDocs results, int pagingIndex, int maxDisplay)
{
listView.Items.Clear();
int offset = pagingIndex * maxDisplay;
int realDisplay = Math.Min(maxDisplay, results.ScoreDocs.Length - offset);
string[] delimiter1 = new string[] { ".I", ".T", ".A", ".B", ".W", " ." };
int rank = offset;
string[] delimiter2 = new string[] { " ." };
//for (ScoreDoc scoreDoc in results.ScoreDocs)
for (int j = offset; j < offset + realDisplay; j++)
{
ScoreDoc scoreDoc = results.ScoreDocs[j];
rank++;
// retrieve the document from the 'ScoreDoc' object
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string titleValue = doc.Get(TITLE_FN).ToString();
string authorValue = doc.Get(AUTHOR_FN).ToString();
string biblioValue = doc.Get(BIBLIOGRAPHIC_FN).ToString();
string abstractValue = doc.Get(ABSTRACT_FN).ToString();
string[] array = abstractValue.Split(delimiter2, StringSplitOptions.None);
ListViewItem item = new ListViewItem(rank.ToString());
item.SubItems.Add(titleValue);
item.SubItems.Add(authorValue);
item.SubItems.Add(biblioValue);
item.SubItems.Add(array[0]);
item.SubItems.Add(abstractValue);
listView.Items.Add(item);
}
}
public LogEntry(Document document)
{
Id = Guid.Parse(document.Get("Id"));
Text = document.Get("Text");
Timestamp = new DateTime(long.Parse(document.Get("Timestamp")));
SourceHost = document.Get("SourceHost");
SourceFile = document.Get("SourceFile");
}
private Project MapSearchResult(Document doc)
{
return new Project
{
Id = int.Parse(doc.Get(SearchingFields.Id.ToString())),
Title = doc.Get(SearchingFields.Name.ToString())
};
}
/// <summary>
/// Maps the lucene document to data.
/// </summary>
/// <returns>The lucene document to data.</returns>
/// <param name="doc">Document.</param>
private static SearchModel _mapLuceneDocumentToData (Document doc)
{
return new SearchModel {
Id = Convert.ToInt64 (doc.Get ("content_id")),
ContentTitle = doc.Get ("content_title"),
ContentSource = Convert.ToInt64(doc.Get ("source_id"))
};
}
private Group MapSearchResult(Document doc)
{
return new Group
{
Id = int.Parse(doc.Get(SearchingFields.Id.ToString())),
Name = doc.Get(SearchingFields.Name.ToString())
};
}
public LuceneArticle(Document document)
{
if (document != null)
{
this.Id = Convert.ToInt32(document.Get("Id"));
this.Title = document.Get("Title");
this.Content = document.Get("Content");
}
}
protected override ISearchResult BuildSearchResult(float score, Document document)
{
var searchResult = base.BuildSearchResult(score, document);
searchResult.Content.Add("author_id", document.Get("author_id"));
searchResult.Content.Add("author_name", document.Get("author_name"));
searchResult.Content.Add("author_firstName", document.Get("author_firstName"));
searchResult.Content.Add("author_lastName", document.Get("author_lastName"));
searchResult.Content.Add("biography", document.Get("biography"));
return searchResult;
}
protected virtual ISearchResult BuildSearchResult(float score, Document document)
{
Guid entityId = Guid.Empty;
Guid.TryParse(document.Get(IdFieldName), out entityId);
var timestamp = DateTime.FromFileTime(long.Parse(document.Get(TimeStampFieldName)));
var documentType = document.Get(TypeFieldName);
string content = document.Get(ContentFieldName);
return new SearchResult(entityId, content, score, timestamp, documentType);
}
protected override ISearchResult BuildSearchResult(float score, Document document)
{
var searchResult = base.BuildSearchResult(score, document);
// searchResult.Content.Add("photo_id", document.Get("photo_id"));
searchResult.Content.Add("owner", document.Get("owner"));
searchResult.Content.Add("title", document.Get("title"));
searchResult.Content.Add("owner_id", document.Get("owner_id"));
searchResult.Content.Add("description", document.Get("description"));
return searchResult;
}
private Lecturer MapSearchResult(Document doc)
{
return new Lecturer
{
Id = int.Parse(doc.Get(SearchingFields.Id.ToString())),
FirstName = doc.Get(SearchingFields.FirstName.ToString()),
MiddleName = doc.Get(SearchingFields.MiddleName.ToString()),
LastName = doc.Get(SearchingFields.LastName.ToString()),
Skill = doc.Get(SearchingFields.Name.ToString()) //логин
};
}
/// <summary>
/// Get the paths of Lemmas Images.
/// <para>Give the Lemma Name to get the images path for.</para>
/// <para>Returns a string array with the path of each image.</para>
/// </summary>
public string[] GetLemmaImagesPath(string lemmaName)
{
string directory = System.IO.Directory.GetCurrentDirectory();
string[] splitDir = directory.Split('\\');
if (splitDir[splitDir.Length - 1] == "Debug")
{
System.IO.Directory.SetCurrentDirectory("..\\..");
}
string[] splitLemmaName = lemmaName.Split('(');
string[] imageTypes = new string[] { "jpg", "svg", "png", "gif" };
string[] results = null;
string indexDir = "Index";
using (Lucene.Net.Store.Directory dir = FSDirectory.Open(indexDir))
using (IndexSearcher searcher = new IndexSearcher(dir))
{
Term term, term2;
WildcardQuery q, q2 = null;
BooleanQuery bq = new BooleanQuery();
term = new Term("title", "*" + splitLemmaName[0].ToLower() + "*");
q = new WildcardQuery(term);
bq.Add(q, Occur.MUST);
TopDocs hits = searcher.Search(bq, 10);
int j = 0;
if (hits.TotalHits > 10)
{
results = new string[10];
}
else
{
results = new string[hits.TotalHits];
}
foreach (ScoreDoc d in hits.ScoreDocs)
{
Lucene.Net.Documents.Document doc = searcher.Doc(d.Doc);
foreach (string type in imageTypes)
{
if (doc.Get("dataType").ToString() == type)
{
results[j++] = doc.Get("Content").ToString() + "." + doc.Get("dataType").ToString();
}
}
}
}
return(results);
}
/* Open pre-lockless index, add docs, do a delete &
* setNorm, and search */
public virtual void ChangeIndexNoAdds(System.String dirName)
{
dirName = FullDir(dirName);
Directory dir = FSDirectory.Open(new System.IO.DirectoryInfo(dirName));
// make sure searching sees right # hits
IndexSearcher searcher = new IndexSearcher(dir, true);
ScoreDoc[] hits = searcher.Search(new TermQuery(new Term("content", "aaa")), null, 1000).ScoreDocs;
Assert.AreEqual(34, hits.Length, "wrong number of hits");
Document d = searcher.Doc(hits[0].Doc);
Assert.AreEqual("21", d.Get("id"), "wrong first document");
searcher.Close();
// make sure we can do a delete & setNorm against this
// pre-lockless segment:
IndexReader reader = IndexReader.Open(dir, false);
Term searchTerm = new Term("id", "6");
int delCount = reader.DeleteDocuments(searchTerm);
Assert.AreEqual(1, delCount, "wrong delete count");
reader.SetNorm(22, "content", (float)2.0);
reader.Close();
// make sure they "took":
searcher = new IndexSearcher(dir, true);
hits = searcher.Search(new TermQuery(new Term("content", "aaa")), null, 1000).ScoreDocs;
Assert.AreEqual(33, hits.Length, "wrong number of hits");
d = searcher.Doc(hits[0].Doc);
Assert.AreEqual("22", d.Get("id"), "wrong first document");
TestHits(hits, 33, searcher.IndexReader);
searcher.Close();
// optimize
IndexWriter writer = new IndexWriter(dir, new WhitespaceAnalyzer(), false, IndexWriter.MaxFieldLength.UNLIMITED);
writer.Optimize();
writer.Close();
searcher = new IndexSearcher(dir, true);
hits = searcher.Search(new TermQuery(new Term("content", "aaa")), null, 1000).ScoreDocs;
Assert.AreEqual(33, hits.Length, "wrong number of hits");
d = searcher.Doc(hits[0].Doc);
Assert.AreEqual("22", d.Get("id"), "wrong first document");
TestHits(hits, 33, searcher.IndexReader);
searcher.Close();
dir.Close();
}
public NamespaceModel(Document document)
{
Name = document.Get(NamespaceNameField);
AssemblyName = document.Get(NamespaceAssemblyNameField);
PackageName = document.Get(NamespacePackageNameField);
PackageVersion = document.Get(NamespacePackageVersionField);
var targetFrameworksFieldValue = document.Get(NamespaceTargetFrameworksField);
TargetFrameworks = new List<string>();
if (!string.IsNullOrEmpty(targetFrameworksFieldValue))
{
TargetFrameworks.AddRange(targetFrameworksFieldValue.Split(new[] { ';' }, StringSplitOptions.RemoveEmptyEntries));
}
}
public static List <SearchResult> SeartchContact(string keyword, int startIndex, int pageSize, out int totalCount)
{
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(ContactIndexPath), new NoLockFactory());
IndexReader reader = IndexReader.Open(directory, true);
IndexSearcher searcher = new IndexSearcher(reader);
IEnumerable <string> keyList = SplitHelper.SplitWords(keyword);
PhraseQuery queryContact = new PhraseQuery();
foreach (var key in keyList)
{
queryContact.Add(new Term("contactInfo", key));
}
queryContact.SetSlop(100);
BooleanQuery query = new BooleanQuery();
query.Add(queryContact, BooleanClause.Occur.SHOULD); // SHOULD => 表示或者
// TopScoreDocCollector:盛放查询结果的容器
TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
// 使用query这个查询条件进行搜索，搜索结果放入collector
searcher.Search(query, null, collector);
// 首先获取总条数
totalCount = collector.GetTotalHits();
// 从查询结果中取出第m条到第n条的数据
ScoreDoc[] docs = collector.TopDocs(startIndex, pageSize).scoreDocs;
// 遍历查询结果
List <SearchResult> resultList = new List <SearchResult>();
for (int i = 0; i < docs.Length; i++)
{
// 拿到文档的id
int docId = docs[i].doc;
// 所以查询结果中只有id，具体内容需要二次查询
// 根据id查询内容：放进去的是Document，查出来的还是Document
Lucene.Net.Documents.Document doc = searcher.Doc(docId);
SearchResult result = new SearchResult();
result.UserId = doc.Get("id");
result.Name = doc.Get("name");
result.Email = doc.Get("email");
result.PhoneNumber = doc.Get("phone");
result.Position = doc.Get("position");
resultList.Add(result);
}
return(resultList);
}
public void SaveResult(string filePath)
{
string query = searchQuery;
CreateSearcher();
StreamWriter sw = new StreamWriter(filePath, true, Encoding.Default);//实例化StreamWriter
TopDocs results = searchResultDocs;
// TopDocs results = SearchText(query, searcher.MaxDoc);
saveQuery.Add(query);
int idx = saveQuery.IndexOf(query) + 1;
int length = Math.Abs(idx).ToString().Length;
string queryId = "";
if (length == 1)
{
queryId = "00" + idx.ToString();
}
if (length == 2)
{
queryId = "0" + idx.ToString();
}
if (length == 3)
{
queryId = idx.ToString();
}
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank += 1;
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string myFieldValue = doc.Get(TEXT_FN).ToString();
string passage_ID = doc.Get(ID_FN_PASSAGEID).ToString();
// string query_ID = doc.Get(ID_FN_QUERYID).ToString();
// resultsStr += "Rank " + rank + " text " + myFieldValue + "\n";
//string save = query + "\t" + "Q0" + "\t" + scoreDoc.Score + "\t" + "n9916113_our team";
sw.WriteLine(queryId + "\t" + "Q0" + "\t" + passage_ID + "\t" + rank + "\t" + scoreDoc.Score + "\t" + "n9916113_n10290320_n10381112_Climbers");
// sw.WriteLine(query_ID + "\t" + "Q0" + "\t" + passage_ID + "\t" + rank + "\t" + scoreDoc.Score + "\t" + "n9916113_n10290320_n10381112_Climbers"); //for simulation
//resultList.Add(save);
}
sw.Close();
CleanUpSearcher();
}
//override public List<long> GetRelevantDocs(string querytext)
override public Tuple <long, List <long> > GetRelevantDocs(string querytext)
{
long matched_query = 0;
querytext = querytext.ToLower();
Query query = parser.Parse(querytext);
TopDocs results = searcher.Search(query, 10000);
long rank = 0;
float toprank = 0f;
List <long> revevantList = new List <long>();
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
if (scoreDoc.Score < threshHold)
{
break;
}
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
long id = Convert.ToInt64(doc.Get(QID_FN).ToString());
string text = doc.Get(TEXT_FN).ToString();
CollectionQuery cq = collectionProvider.Querys[id];
Dictionary <long, CollectionPassage> cpd = collectionProvider.Passages;
if (rank == 0)
{
toprank = scoreDoc.Score;
matched_query = cq.query_id;
}
rank++;
foreach (var pid in cq.passages_id)
{
if (cpd[pid].is_selected == 1)
{
revevantList.Add(pid);
}
}
Console.WriteLine(rank.ToString() + ", " + text + "(" + scoreDoc.Score.ToString("0.000") + ":" +
(scoreDoc.Score / toprank).ToString("0.000") + ") ");
}
Console.WriteLine(string.Join(", ", revevantList));
//return revevantList;
return(new Tuple <long, List <long> >(matched_query, revevantList));
}
public AcadamicPublication GetAcadamicPublicationAt(int rank)
{
ScoreDoc[] results = topdocs.ScoreDocs;
AcadamicPublication newAP = new AcadamicPublication();
Lucene.Net.Documents.Document doc = indexSearcher.Doc(results[i].Doc);
newAP.DocID = doc.Get(DOCID_FN);
newAP.Title = doc.Get(TITLE_FN);
newAP.Author = doc.Get(AUTHOR_FN);
newAP.BibliographicInformation = doc.Get(BIBLIOGRAPHICINFORMATION_FN);
newAP.Abstract = doc.Get(ABSTRACT_FN);
return(newAP);
}
public List <String> SearchAndDisplayResults(string querytext)
{
topicID += 1;
List <String> resultList = new List <String>();
txtCont.Clear();
resultList.Add(querytext);
querytext = querytext.ToLower();
Dictionary <String, float> boosts = new Dictionary <string, float>();
boosts["passage_text"] = 2;
boosts["title"] = 10;
parser = new MultiFieldQueryParser(AppLuceneVersion, new String[] { "passage_text", "title" }, analyzer, boosts);
Query query = parser.Parse(querytext);
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
TopDocs results = searcher.Search(query, 100000);
stopwatch.Stop();
int hits = results.TotalHits;
resultList.Add(hits.ToString());
resultList.Add(stopwatch.ElapsedMilliseconds.ToString());
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string url = doc.Get("url");
string passage_text = doc.Get("passage_text");
string title = doc.Get("title");
string id = doc.Get("passage_id");
resultList.Add("\nRank " + rank + "\ntitle: " + title + "\nurl: " + url + "\npassage_text: " + passage_text + "\n");
string txt = topicID.ToString().PadLeft(3, '0') + " Q0 " + id + " " + rank + " " + scoreDoc.Score + " " + "n10057862_" + "n10296255_"
+ "n10056084_" + "n10153853_" + "HyperGloryTeam" + "\n";
txtCont.Add(txt);
}
return(resultList);
}
/// <summary>
/// Outputs results to the screen
/// </summary>
/// <param name="results">Search results</param>
public void DisplayResults(TopDocs results)
{
List <String> evalrecords = new List <String>();
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
// retrieve the document from the 'ScoreDoc' object
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string field_URL = doc.Get(TEXT).ToString();
//string field_Text = doc.Get(TEXT_PASSAGE).ToString();
//Console.WriteLine("Rank " + rank + " score " + scoreDoc.Score + " text " + myFieldValue);
Console.WriteLine();
Console.WriteLine("Rank #" + rank);
Console.WriteLine("Text: " + field_URL);
Console.WriteLine();
string topicId = "001";
string studgroup = "10124021";
String record = topicId + " Q0 " + TEXT + "" + rank + " " + scoreDoc.Score + " " + studgroup;
evalrecords.Add(record);
}
System.IO.File.WriteAllLines(@"C:\Users\Suprith Kangokar\Desktop\SEM 3\IFN647- Advance Info & Retreival\baseline.txt", evalrecords);
}
public IEnumerable <Guid> SearchDocuments(string criteria)
{
List <Guid> result = new List <Guid>();
using (var searcher = new IndexSearcher(LuceneDirectory, false))
{
var analyzer = new StandardAnalyzer(Version.LUCENE_30);
try
{
criteria = string.Format("*{0}*", criteria);
var queryParser = new QueryParser(Version.LUCENE_30, "Body", analyzer);
queryParser.AllowLeadingWildcard = true;
var query = queryParser.Parse(criteria);
var hits = searcher.Search(query, searcher.MaxDoc).ScoreDocs;
foreach (var hit in hits)
{
LuceneDocument luceneDocument = searcher.Doc(hit.Doc);
result.Add(Guid.Parse(luceneDocument.Get("FileID")));
}
}
catch { }
analyzer.Close();
}
return(result);
}
public List <string[]> DisplayResults(TopDocs results, string label)
{
List <string[]> retrievedDocs = new List <string[]>();
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
// retrieve the document from the 'ScoreDoc' object
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string[] temp = new string[2];
temp[0] = doc.Get("ID");
temp[1] = doc.Get(label);
retrievedDocs.Add(temp);
}
return(retrievedDocs);
}
public List <KeyValuePair <int, string> > FilterSearchResult(string filterText)
{
var result = new List <KeyValuePair <int, string> >();
//Setup searcher
IndexSearcher searcher = new IndexSearcher(idx);
//prepare search
var parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, LUCENE_FIELD_NAME, new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30));
var query = parser.Parse(filterText);
//Query query = new TermQuery(new Term(LUCENE_FIELD_NAME, filterText));
//Do the search
TopDocs hits = searcher.Search(query, int.MaxValue);
if (hits != null)
{
ScoreDoc[] scoreDocs = hits.ScoreDocs;
foreach (ScoreDoc scoreDoc in scoreDocs)
{
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
result.Add(new KeyValuePair <int, string>(Convert.ToInt32(doc.Get(LUCENE_ID_NAME)), doc.Get(LUCENE_FIELD_NAME)));
}
}
return(result);
}
/// <summary>
/// Get a ranked list of results
/// </summary>
/// <param name="query">A set of results</param>
public List <string> GetResults(string query)
{
searchQuery = query;
CreateSearcher();
TopDocs results = SearchText(query, 100);
searchResultDocs = results;
List <string> resultList = new List <string>();
int resultNum = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
// if (resultNum >= 10) { break; }
resultNum += 1;
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string myFieldValue = doc.Get(TEXT_FN).ToString();
// resultsStr += "Rank " + rank + " text " + myFieldValue + "\n";
resultList.Add(myFieldValue);
}
CleanUpSearcher();
return(resultList);
}
public Tuple <List <float>, List <string>, int> SearchText_baseline(string querytext)
{
List <float> valueListBase = new List <float>();
List <string> docsIdsListBase = new List <string>();
querytext = querytext.ToLower();
Query query = parser.Parse(querytext);
TopDocs results = searcher2.Search(query, max_hits);
if (results.TotalHits != 0) // Check if there are found results
{
for (int i = 0; i < results.TotalHits; i++) // Loop through the top 10 ranked documents
{
ScoreDoc scoreDoc = results.ScoreDocs[i]; // Get the ranked document
Lucene.Net.Documents.Document doc = searcher2.Doc(scoreDoc.Doc); // Get document contents
string text = doc.Get(TEXT_FN).ToString(); // Get document contents by fields
string score = scoreDoc.Score.ToString(); // Get document score
int idxI = text.IndexOf(".I ") + 3; // Get ID starting index
int idxT = text.IndexOf(".T\r\n"); // Get title starting index
string id = text.Substring(idxI, idxT - 1 - idxI); // Get ID string
docsIdsListBase.Add(id.Trim());
valueListBase.Add(scoreDoc.Score);
}
}
var result = Tuple.Create(valueListBase, docsIdsListBase, results.TotalHits);
return(result);
}
public static TestCustomSerializerClass CustomDeserializeFunction(Document doc)
{
var obj = new TestCustomSerializerClass();
obj.PropStringList = TestCustomSerializerClass.StringToCustomList(doc.Get("CustomList"));
return obj;
}
public static void Highlight(Document d, string query, Analyzer analyzer)
{
string contents = d.Get("contents");
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\"><b>", "</b></span>");
//SpanGradientFormatter formatter = new SpanGradientFormatter(10.0f, null, null, "#F1FD9F", "#EFF413");
//SimpleHTMLEncoder encoder = new SimpleHTMLEncoder();
SimpleFragmenter fragmenter = new SimpleFragmenter(250);
Highlighter hiliter = new Highlighter(formatter, new QueryScorer(QueryParser.Parse(query, "contents", analyzer)));
hiliter.SetTextFragmenter(fragmenter);
int numfragments = contents.Length / fragmenter.GetFragmentSize() + 1;// +1 ensures its never zero. More than the required number of fragments dont harm.
StringBuilder result = new StringBuilder("<html><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"><style>.highlight{background:yellow;}</style><head><title>Search Results - ");
result.Append(d.Get("filename"));
result.Append("</title></head><body><font face=Arial size=5>");
TokenStream tokenstream = analyzer.TokenStream("contents", new System.IO.StringReader(contents));
TextFragment[] frags = hiliter.GetBestTextFragments(tokenstream, contents, false, numfragments);
foreach (TextFragment frag in frags)
{
if (frag.GetScore() > 0)
{
result.Append(frag.ToString() + "<br/><hr/><br/>");
}
}
string contentspath = System.IO.Path.Combine(System.Windows.Forms.Application.StartupPath, "contents.html");
result.Append("</font><a target=_self href=\"file:///");
result.Append(contentspath);
result.Append("\">View Original Document...</a>");
result.Append("</body></html>");
result.Replace("\n", "<br/>");
string resultspath = System.IO.Path.Combine(System.Windows.Forms.Application.StartupPath, "results.html");
System.IO.File.WriteAllText(resultspath, result.ToString());
//webBrowser1.Url = new Uri("file:///" + resultspath);
Highlighter hiliter2 = new Highlighter(formatter, new QueryScorer(QueryParser.Parse(query, "contents", analyzer)));
hiliter2.SetTextFragmenter(fragmenter);
TokenStream tokstr = analyzer.TokenStream(new System.IO.StringReader(contents));
StringBuilder htmlcontents = new StringBuilder("<html><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"><style>.highlight{background:yellow;}</style><body><font face=Arial size=5>");
htmlcontents.Append(hiliter2.GetBestFragments(tokstr, contents, numfragments, "..."));
htmlcontents.Append("</font></body></html>");
htmlcontents.Replace("\n", "<br/>");
System.IO.File.WriteAllText(contentspath, htmlcontents.ToString());
}
public static void AddField(JObject obj, Document document, string to, string from)
{
string value = document.Get(from);
if (value != null)
{
obj[to] = value;
}
}
public static void AddFieldBool(JObject obj, Document document, string to, string from)
{
string value = document.Get(from);
if (value != null)
{
obj[to] = value.Equals("True", StringComparison.InvariantCultureIgnoreCase);
}
}
private void StartSearch()
{
string searchText = txtSearch.Text;
string whitelist = "^[a-zA-Z0-9-,. ]+$";
Regex pattern = new Regex(whitelist);
if (!pattern.IsMatch(searchText))
{
throw new Exception("Invalid Search Criteria");
}
//Supply conditions
Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
QueryParser parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, "Contents", analyzer);
Query query = parser.Parse(searchText);
string indexPath = HttpContext.Current.Request.PhysicalPath.Replace("Default.aspx", "Indexes\\");
Directory dir = FSDirectory.Open(new System.IO.DirectoryInfo(indexPath));
Lucene.Net.Search.Searcher searcher = new Lucene.Net.Search.IndexSearcher(Lucene.Net.Index.IndexReader.Open(dir, true));
TopDocs topDocs = searcher.Search(query, 100);
int countResults = topDocs.ScoreDocs.Length;
if (lblSearchResults.Text.Length > 0)
{
lblSearchResults.Text = "";
}
if (countResults > 0)
{
string results;
results = string.Format("<br />Search Results <br />");
for (int i = 0; i < countResults; i++)
{
ScoreDoc scoreDoc = topDocs.ScoreDocs[i];
int docId = scoreDoc.Doc;
float score = scoreDoc.Score;
Lucene.Net.Documents.Document doc = searcher.Doc(docId);
string docPath = doc.Get("FileName");
string urlLink = "~/" + docPath.Substring(docPath.LastIndexOf("Help"), docPath.Length - docPath.LastIndexOf("Help")).Replace("\\", "/");
results += "Text found in: <a href=" + urlLink.Replace("~/Help/", "") + "?txtSearch=" + searchText + ">" + urlLink + "</a><br />";
}
lblSearchResults.Text += results;
}
else
{
lblSearchResults.Text = "No records found for \"" + searchText + "\"";
}
searcher.Dispose();
}
public static TestCustomSerializerClass CustomMapperFunction2(Document doc)
{
var obj = new TestCustomSerializerClass();
obj.PropStringList = doc.Get("PropStringList").Split(new[] { "," }, StringSplitOptions.None).ToList();
obj.StringList = doc.Get("StringList").Split(new[] { "," }, StringSplitOptions.None).ToList();
obj.IntList = doc.Get("IntList").Split(new[] {","}, StringSplitOptions.None)
.Select(int.Parse)
.ToList();
obj.PropIntList = doc.Get("PropIntList").Split(new[] { "," }, StringSplitOptions.None)
.Select(int.Parse)
.ToList();
return obj;
}
public void DisplayResult(TopDocs topDocs)
{
for (int i = 0; i < topDocs.ScoreDocs.Length; i++)
{
Lucene.Net.Documents.Document document = searcher.Doc(topDocs.ScoreDocs[i].Doc);
string fieldValue = document.Get(TEXT_FN).ToString();
Console.WriteLine("Rank " + (i + 1) + " text : " + fieldValue);
}
}
/// <summary>
/// Searches the index for the querytext
/// </summary>
/// <param name="querytext">The text to search the index</param>
//public string SearchIndext(string querytext)
public List <Dictionary <string, string> > SearchIndext(string querytext)
{
List <Dictionary <string, string> > resultListDict = new List <Dictionary <string, string> >(); // Initiate a result list
Query query = DisplayQueries(querytext);
Console.WriteLine("query is " + query);
TopDocs results = searcher.Search(query, 100);
System.Console.WriteLine("Number of results is " + results.TotalHits);
int rank = 0;
// ScoreDocs : a array stores pointers of a query
// scoreDoc : a pointer of a query points to doc_ID and score (of the doc for the query)
//string output = "";
if (results.TotalHits != 0) // Check if there are results
{
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string myFieldValue = doc.Get(TEXT_FN_PASS_TEXT);
string myURL = doc.Get(TEXT_FN_URL);
string passId = doc.Get(TEXT_FN_PASS_ID);
string score = scoreDoc.Score.ToString();
string queryId = doc.Get(TEXT_FN_QUERY_ID);
Explanation e = searcher.Explain(query, scoreDoc.Doc);
char delimiters = '/';
string[] urlSeg = myURL.Split(delimiters);
resultListDict.Add(new Dictionary <string, string> {
{ "rank", rank.ToString() }, { "passId", passId },
{ "score", score }, { "title", urlSeg[2] }, { "url", myURL }, { "text", myFieldValue }, { "queryId", queryId }
});
//Console.WriteLine("Rank " + rank + " text " + myFieldValue + " URL " + myURL);
//Console.WriteLine(e);
}
}
return(resultListDict);
}
public List <Result> DisplayResults(TopDocs results, Lucene.Net.Search.Query query)
{
int rank = 0;
List <Result> retrievedResults = new List <Result>();
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
// retrieve the document from the 'ScoreDoc' object
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string url = doc.Get(URL_FN).ToString();
string title = GetTitle(url);
int passageID = Int32.Parse(doc.Get(PASSAGEID_FN));
retrievedResults.Add(new Result(rank, scoreDoc.Score, title, url, null, null, passageID));
}
return(retrievedResults);
}
public static IDictionary<string, string> DocToDict(Document doc, float score = 0)
{
var dict = new Dictionary<string, string>();
foreach (var field in doc.GetFields()) {
if (field.IsStored)
dict[field.Name] = doc.Get(field.Name);
}
dict["rank"] = score.ToString(CultureInfo.InvariantCulture);
return dict;
}
public BasicAuditEntry(Document doc, int luceneId)
{
User = doc.Get("user");
Role = doc.GetValues("role").ToList();
Id = new ID(doc.Get("id"));
Path = doc.Get("path");
DateTime tmp;
DateTime.TryParse(doc.Get("timestamp"), out tmp);
TimeStamp = tmp;
EventId = doc.Get("event");
Note = doc.Get("note");
Label = doc.Get("label");
Color = doc.Get("color");
Database = doc.Get("database");
Uid = luceneId.ToString();
}
private void btnFolder_Click(object sender, EventArgs e)
{
FolderBrowserDialog dia = new FolderBrowserDialog();
DialogResult res = dia.ShowDialog();
if (res != System.Windows.Forms.DialogResult.OK)
{
return;
}
FSDirectory dir = FSDirectory.GetDirectory(Environment.CurrentDirectory + "\\LuceneIndex");
//Lucene.Net.Store.RAMDirectory dir = new RAMDirectory();
Lucene.Net.Analysis.Standard.StandardAnalyzer an = new Lucene.Net.Analysis.Standard.StandardAnalyzer();
IndexWriter wr = new IndexWriter(dir, an,true);
IStemmer stemmer = new EnglishStemmer();
DirectoryInfo diMain = new DirectoryInfo(dia.SelectedPath);
foreach(FileInfo fi in diMain.GetFiles()){
Document doc = new Document();
doc.Add(new Field("title", fi.Name,Field.Store.YES, Field.Index.NO));
//doc.Add(new Field("text", File.ReadAllText(fi.FullName),Field.Store.YES, Field.Index.TOKENIZED,Field.TermVector.YES));
doc.Add(new Field("text", PerformStemming(stemmer,NLPToolkit.Tokenizer.TokenizeNow(File.ReadAllText(fi.FullName)).ToArray()), Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.YES));
wr.AddDocument(doc);
}
wr.Optimize();
wr.Flush();
wr.Close();
dir.Close();
IndexReader reader = IndexReader.Open(dir);
for (int i = 0; i < reader.MaxDoc(); i++)
{
if (reader.IsDeleted(i))
continue;
Document doc = reader.Document(i);
String docId = doc.Get("docId");
foreach (TermFreqVector vector in reader.GetTermFreqVectors(i))
{
foreach(string term in vector.GetTerms()){
Console.WriteLine(term);
}
}
// do something with docId here...
}
//IndexSearcher search = new IndexSearcher(wr.GetReader());
//MoreLikeThis mlt = new MoreLikeThis(wr.GetReader());
//FileInfo fitarget = new FileInfo(@"C:\Users\peacemaker\Desktop\TestNoBitcoin\test.txt");
//Query query = mlt.Like(fitarget);
//var hits = search.Search(query, int.MaxValue);
//foreach (ScoreDoc doc in hits.ScoreDocs)
//{
// textBox1.Text += doc.Score + Environment.NewLine;
//}
}
/// <summary>
/// Searches the index for the querytext
/// </summary>
/// <param name="querytext">The text to search the index</param>
public List <Dictionary <string, string> > SearchText(string querytext, int DocNum, bool check, out string processedQuery)
{
Query query;
if (check)
{
query = MultiAsIsparser.Parse("\"" + querytext + "\"");
}
else
{
string temp = Program.UrlPreprocessor2(querytext);
string querytext2 = temp.ToLower();
query = MultiParser.Parse(querytext2);
}
List <Dictionary <string, string> > resultList = new List <Dictionary <string, string> >();
processedQuery = query.ToString();
TopDocs results = searcher.Search(query, DocNum);
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
Dictionary <string, string> dict;
dict = new Dictionary <string, string>();
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string urlValue = doc.Get(pureURL).ToString();
string myPassID = doc.Get(passID).ToString();
string myPassText = doc.Get(passText).ToString();
string queryID = doc.Get(qID).ToString();
dict.Add("rank", rank.ToString());
dict.Add("score", scoreDoc.Score.ToString());
dict.Add("result", myPassText.ToString());
dict.Add("passID", myPassID.ToString());
dict.Add("url", urlValue.ToString());
dict.Add("qID", queryID.ToString());
resultList.Add(dict);
}
return(resultList);
}
public SearchResult(Document luceneDocument) {
Url = luceneDocument.Get("Url");
Title = luceneDocument.Get("Title");
Body = luceneDocument.Get("Body");
Description = luceneDocument.Get("Description");
PublishDate = luceneDocument.Get("PublishDate");
LastUpdatedDate = luceneDocument.Get("LastUpdatedDate");
Author = luceneDocument.Get("Author");
}
private void CheckHits(ScoreDoc[] hits, int expectedCount, IndexSearcher searcher)
{
Assert.AreEqual(expectedCount, hits.Length, "total results");
for (int i = 0; i < hits.Length; i++)
{
if (i < 10 || (i > 94 && i < 105))
{
Documents.Document d = searcher.Doc(hits[i].Doc);
Assert.AreEqual(Convert.ToString(i), d.Get(ID_FIELD), "check " + i);
}
}
}
private void PrintHits(TextWriter @out, ScoreDoc[] hits, IndexSearcher searcher)
{
@out.WriteLine(hits.Length + " total results\n");
for (int i = 0; i < hits.Length; i++)
{
if (i < 10 || (i > 94 && i < 105))
{
Documents.Document d = searcher.Doc(hits[i].Doc);
@out.WriteLine(i + " " + d.Get(ID_FIELD));
}
}
}
public void SaveResultForSimulation(string query, string filePath, string query_ID)
{
CreateSearcher();
StreamWriter sw = new StreamWriter(filePath, true, Encoding.Default); //instantiate StreamWriter
TopDocs results = SearchText(query, 10);
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank += 1;
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string myFieldValue = doc.Get(TEXT_FN).ToString();
string passage_ID = doc.Get(ID_FN_PASSAGEID).ToString();
sw.WriteLine(query_ID + "\t" + "Q0" + "\t" + passage_ID + "\t" + rank + "\t" + scoreDoc.Score + "\t" + "n9916113_n10290320_n10381112_Climbers"); //for simulation
}
sw.Close();
CleanUpSearcher();
}
protected virtual SearchEngineResult CreateSearchResult(Document doc, float score)
{
var result = new SearchEngineResult
{
ID = doc.Get("Key"),
Title = doc.Get("Title"),
Url = doc.Get("Url"),
TypeID = byte.Parse(doc.Get("Type")),
Excerpt = doc.Get("Excerpt"),
Score = score
};
//-- This is out here incase later we accommodate areas that belong to more than one country
byte countryID = 0;
if (byte.TryParse(doc.Get("Country"), out countryID))
{
result.CountryID = countryID;
result.Flag = cf.Caching.AppLookups.CountryFlag(result.CountryID);
}
return result;
}
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);
}
}
private static string HighlightText(int id, string field, Highlighter highlighter, IndexSearcher searcher, Analyzer analyzer)
{
Lucene.Net.Documents.Document doc = searcher.Doc(id);
var highlightedText = "";
var text = doc.Get(field);
if (text == null)
{
return(String.Empty);
}
TokenStream tokenStream = TokenSources.GetAnyTokenStream(searcher.IndexReader, id, field, analyzer);
highlightedText = highlighter.GetBestFragments(tokenStream, text, 2, "...");
return(highlightedText);
}
// Generates top documents by ranking results
public List <string> SaveResults(TopDocs topDocs)
{
List <string> searchResultList = new List <string>();
int rank = 0;
foreach (ScoreDoc scoreDoc in topDocs.ScoreDocs)
{
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
rank++;
Lucene.Net.Documents.Document doc1 = searcher.Doc(scoreDoc.Doc);
string myFieldValue = doc.Get(TEXT_FN).ToString();
string result = "Q0" + "\t" + scoreDoc.Doc + "\t" + rank + "\t" + scoreDoc.Score + "\t";
searchResultList.Add(result);
}
return(searchResultList);
}
// Activity 7
/// <summary>
/// Outputs results to the screen
/// </summary>
/// <param name="results">Search results</param>
public void DisplayResults(TopDocs results)
{
var form1 = new Form1();
int rank = 0;
foreach (ScoreDoc scoreDoc in results.ScoreDocs)
{
rank++;
// retrieve the document from the 'ScoreDoc' object
Lucene.Net.Documents.Document doc = searcher.Doc(scoreDoc.Doc);
string myFieldValue = doc.Get(TEXT_FN).ToString();
ListViewItem item = new ListViewItem(rank.ToString());
item.SubItems.Add(myFieldValue);
form1.listView.Items.Add(item);
}
}
public static List <int> SeartchUser(string keyword)
{
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(UserInfoIndexPath), new NoLockFactory());
IndexReader reader = IndexReader.Open(directory, true);
IndexSearcher searcher = new IndexSearcher(reader);
IEnumerable <string> keyList = SplitHelper.SplitWords(keyword);
PhraseQuery queryUserInfo = new PhraseQuery();
foreach (var key in keyList)
{
queryUserInfo.Add(new Term("userInfo", key));
}
queryUserInfo.SetSlop(100);
BooleanQuery query = new BooleanQuery();
query.Add(queryUserInfo, BooleanClause.Occur.SHOULD);
// TopScoreDocCollector:盛放查询结果的容器
TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
// 使用query这个查询条件进行搜索，搜索结果放入collector
searcher.Search(query, null, collector);
// 首先获取总条数
int totalCount = collector.GetTotalHits();
//这里取所有的数据 以方便后续的查找。
ScoreDoc[] docs = collector.TopDocs(0, totalCount).scoreDocs;
// 遍历查询结果
List <int> resultList = new List <int>();
for (int i = 0; i < docs.Length; i++)
{
// 拿到文档的id，因为Document可能非常占内存（DataSet和DataReader的区别）
int docId = docs[i].doc;
// 所以查询结果中只有id，具体内容需要二次查询
// 根据id查询内容：放进去的是Document，查出来的还是Document
Lucene.Net.Documents.Document doc = searcher.Doc(docId);
int uid = Convert.ToInt32(doc.Get("id"));
resultList.Add(uid);
}
return(resultList);
}
private void DoTestSearch(Random random, StringWriter @out, bool useCompoundFile)
{
Store.Directory directory = NewDirectory();
Analyzer analyzer = new MockAnalyzer(random);
IndexWriterConfig conf = NewIndexWriterConfig(TEST_VERSION_CURRENT, analyzer);
MergePolicy mp = conf.MergePolicy;
mp.NoCFSRatio = useCompoundFile ? 1.0 : 0.0;
IndexWriter writer = new IndexWriter(directory, conf);
string[] docs = new 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++)
{
Documents.Document d = new Documents.Document();
d.Add(NewTextField("contents", docs[j], Field.Store.YES));
d.Add(NewStringField("id", "" + j, Field.Store.NO));
writer.AddDocument(d);
}
writer.Dispose();
IndexReader reader = DirectoryReader.Open(directory);
IndexSearcher searcher = NewSearcher(reader);
ScoreDoc[] hits = null;
Sort sort = new Sort(SortField.FIELD_SCORE, new SortField("id", SortFieldType.INT32));
foreach (Query query in BuildQueries())
{
@out.WriteLine("Query: " + query.ToString("contents"));
if (Verbose)
{
Console.WriteLine("TEST: query=" + query);
}
hits = searcher.Search(query, null, 1000, sort).ScoreDocs;
@out.WriteLine(hits.Length + " total results");
for (int i = 0; i < hits.Length && i < 10; i++)
{
Documents.Document d = searcher.Doc(hits[i].Doc);
@out.WriteLine(i + " " + hits[i].Score + " " + d.Get("contents"));
}
}
reader.Dispose();
directory.Dispose();
}
public Entry(Document doc, float score, int positionByScore)
{
this.Hash = doc.Get("Hash");
this.Path = doc.Get("Path");
this.Name = doc.Get("Name");
this.Text = doc.Get("Text");
this.All = doc.Get("All");
this.ModifiedOn = DateTime.ParseExact(doc.Get("ModifiedOn"), DateFormat, null);
this.Score = score;
this.PositionByScore = positionByScore;
}
public virtual void TestBinaryField()
{
Document doc = new Document();
Fieldable stringFld = new Field("string", binaryVal, Field.Store.YES, Field.Index.NO);
Fieldable binaryFld = new Field("binary", System.Text.UTF8Encoding.UTF8.GetBytes(binaryVal), Field.Store.YES);
Fieldable binaryFld2 = new Field("binary", System.Text.UTF8Encoding.UTF8.GetBytes(binaryVal2), Field.Store.YES);
doc.Add(stringFld);
doc.Add(binaryFld);
Assert.AreEqual(2, doc.fields_ForNUnit.Count);
Assert.IsTrue(binaryFld.IsBinary());
Assert.IsTrue(binaryFld.IsStored());
Assert.IsFalse(binaryFld.IsIndexed());
Assert.IsFalse(binaryFld.IsTokenized());
System.String binaryTest = new System.String(System.Text.UTF8Encoding.UTF8.GetChars(doc.GetBinaryValue("binary")));
Assert.IsTrue(binaryTest.Equals(binaryVal));
System.String stringTest = doc.Get("string");
Assert.IsTrue(binaryTest.Equals(stringTest));
doc.Add(binaryFld2);
Assert.AreEqual(3, doc.fields_ForNUnit.Count);
byte[][] binaryTests = doc.GetBinaryValues("binary");
Assert.AreEqual(2, binaryTests.Length);
binaryTest = new System.String(System.Text.UTF8Encoding.UTF8.GetChars(binaryTests[0]));
System.String binaryTest2 = new System.String(System.Text.UTF8Encoding.UTF8.GetChars(binaryTests[1]));
Assert.IsFalse(binaryTest.Equals(binaryTest2));
Assert.IsTrue(binaryTest.Equals(binaryVal));
Assert.IsTrue(binaryTest2.Equals(binaryVal2));
doc.RemoveField("string");
Assert.AreEqual(2, doc.fields_ForNUnit.Count);
doc.RemoveFields("binary");
Assert.AreEqual(0, doc.fields_ForNUnit.Count);
}
private NameInfo DocumentToNameInfo (Document doc)
{
NameInfo info;
info = new NameInfo ();
string str;
str = doc.Get ("Uri");
info.Id = GuidFu.FromUriString (str);
bool have_name = false;
bool have_parent_id = false;
bool have_is_dir = false;
foreach (Field f in doc.Fields ()) {
Property prop;
prop = GetPropertyFromDocument (f, doc, false);
if (prop == null)
continue;
switch (prop.Key) {
case Property.ExactFilenamePropKey:
info.Name = prop.Value;
have_name = true;
break;
case Property.ParentDirUriPropKey:
info.ParentId = GuidFu.FromUriString (prop.Value);
have_parent_id = true;
break;
case Property.IsDirectoryPropKey:
info.IsDirectory = (prop.Value == "true");
have_is_dir = true;
break;
}
if (have_name && have_parent_id && have_is_dir)
break;
}
return info;
}
private Student MapSearchResult(Document doc)
{
int groupId;
int.TryParse(doc.Get(SearchingFields.Group.ToString()), out groupId);
return new Student
{
Id = int.Parse(doc.Get(SearchingFields.Id.ToString())),
FirstName = doc.Get(SearchingFields.FirstName.ToString()),
MiddleName = doc.Get(SearchingFields.MiddleName.ToString()),
LastName = doc.Get(SearchingFields.LastName.ToString()),
Email = doc.Get(SearchingFields.Name.ToString()), //логин
GroupId = groupId
};
}
public ExtensionModel(Document document)
{
Name = document.Get(ExtensionNameField);
FullName = document.Get(ExtensionFullNameField);
Namespace = document.Get(ExtensionNamespaceField);
AssemblyName = document.Get(ExtensionAssemblyNameField);
PackageName = document.Get(ExtensionPackageNameField);
PackageVersion = document.Get(ExtensionPackageVersionField);
var targetFrameworksFieldValue = document.Get(ExtensionTargetFrameworksField);
var targetFrameworks = new List<string>();
if (!string.IsNullOrEmpty(targetFrameworksFieldValue))
{
targetFrameworks.AddRange(targetFrameworksFieldValue.Split(new[] { ';' }, StringSplitOptions.RemoveEmptyEntries));
}
TargetFrameworks = targetFrameworks;
}
// 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 static LuceneSearchModel _mapLuceneDocumentToData(Document doc, float score = 0)
{
return new LuceneSearchModel
{
Id = Guid.Parse(doc.Get(AppConstants.LucId)),
TopicName = doc.Get(AppConstants.LucTopicName),
PostContent = doc.Get(AppConstants.LucPostContent),
DateCreated = DateTools.StringToDate(doc.Get(AppConstants.LucDateCreated)),
TopicId = Guid.Parse(doc.Get(AppConstants.LucTopicId)),
UserId = Guid.Parse(doc.Get(AppConstants.LucUserId)),
Username = doc.Get(AppConstants.LucUsername),
TopicUrl = doc.Get(AppConstants.LucTopicUrl),
Score = score
};
}
