//public List<int> SearchIuses(string searchTerm)
//{
// List<int> results = new List<int>();
// IndexSearcher searcher = new IndexSearcher(FSDirectory.GetDirectory(indexPath));
// QueryParser parser = new QueryParser("Rubro", analyzer);
// parser.SetEnablePositionIncrements(false);
// PhraseQuery q = new PhraseQuery();
// String[] words = searchTerm.Split(' ');
// foreach (string word in words)
// {
// q.Add(new Term("Rubro", word));
// }
// Console.WriteLine(q.ToString());
// //Query query = parser.Parse(searchTerm);
// Hits hitsFound = searcher.Search(q);
// TesisIndx sampleDataFileRow = null;
// for (int i = 0; i < hitsFound.Length(); i++)
// {
// sampleDataFileRow = new TesisIndx();
// Document doc = hitsFound.Doc(i);
// sampleDataFileRow.Ius = int.Parse(doc.Get("Ius"));
// sampleDataFileRow.Rubro = doc.Get("Rubro");
// sampleDataFileRow.Texto = doc.Get("Texto");
// float score = hitsFound.Score(i);
// sampleDataFileRow.Score = score;
// results.Add(sampleDataFileRow.Ius);
// }
// parser = new QueryParser("Texto", analyzer);
// parser.SetEnablePositionIncrements(false);
// q = new PhraseQuery();
// words = searchTerm.Split(' ');
// foreach (string word in words)
// {
// q.Add(new Term("Texto", word));
// }
// // query = parser.Parse(searchTerm);
// hitsFound = searcher.Search(q);
// for (int i = 0; i < hitsFound.Length(); i++)
// {
// sampleDataFileRow = new TesisIndx();
// Document doc = hitsFound.Doc(i);
// sampleDataFileRow.Ius = int.Parse(doc.Get("Ius"));
// sampleDataFileRow.Rubro = doc.Get("Rubro");
// sampleDataFileRow.Texto = doc.Get("Texto");
// float score = hitsFound.Score(i);
// sampleDataFileRow.Score = score;
// results.Add(sampleDataFileRow.Ius);
// }
// results.Distinct();
// return results;
//}
/// <summary>
/// Busca en el índice previamente construido las tesis que tengan coincidencia ya sea en el Rubro o Texto
/// del término buscado
/// </summary>
/// <param name="searchTerm"></param>
/// <returns></returns>
public List <int> SearchIuses(string searchTerm)
{
List <int> results = new List <int>();
IndexSearcher searcher = new IndexSearcher(FSDirectory.GetDirectory(indexPath));
QueryParser parser = new QueryParser("RubroIndx", analyzer);
parser.SetEnablePositionIncrements(false);
Query query = parser.Parse(String.Format("\"{0}\"", searchTerm));
Console.WriteLine(query.ToString());
Hits hitsFound = searcher.Search(query);
TesisIndx sampleDataFileRow = null;
for (int i = 0; i < hitsFound.Length(); i++)
{
sampleDataFileRow = new TesisIndx();
Document doc = hitsFound.Doc(i);
sampleDataFileRow.Ius = int.Parse(doc.Get("Ius"));
sampleDataFileRow.RubroIndx = doc.Get("RubroIndx");
sampleDataFileRow.TextoIndx = doc.Get("TextoIndx");
float score = hitsFound.Score(i);
sampleDataFileRow.Score = score;
results.Add(sampleDataFileRow.Ius);
}
parser = new QueryParser("TextoIndx", analyzer);
parser.SetEnablePositionIncrements(false);
query = parser.Parse(String.Format("\"{0}\"", searchTerm));
Console.WriteLine(query.ToString());
hitsFound = searcher.Search(query);
for (int i = 0; i < hitsFound.Length(); i++)
{
sampleDataFileRow = new TesisIndx();
Document doc = hitsFound.Doc(i);
sampleDataFileRow.Ius = int.Parse(doc.Get("Ius"));
sampleDataFileRow.Rubro = doc.Get("RubroIndx");
sampleDataFileRow.Texto = doc.Get("TextoIndx");
float score = hitsFound.Score(i);
sampleDataFileRow.Score = score;
results.Add(sampleDataFileRow.Ius);
}
results.Distinct();
return(results);
}
public static IDictionary <string, string> Query(string searchTerm)
{
BuildIndexTask.Wait();
System.Text.RegularExpressions.Regex rgx = new System.Text.RegularExpressions.Regex("[^a-zA-Z0-9]");
searchTerm = rgx.Replace(searchTerm, " ");
IndexSearcher searcher = new IndexSearcher(luceneIndexDirectory);
QueryParser parser = new QueryParser("Guideline", analyzer);
Query query = parser.Parse(searchTerm.ToLower());
Hits hitsFound = searcher.Search(query);
IDictionary <string, string> results = new Dictionary <string, string>();
for (int i = 0; i < hitsFound.Length(); i++)
{
Document doc = hitsFound.Doc(i);
float score = hitsFound.Score(i);
string CodeSnippetName = doc.Get("CodeSnippetName");
string CodeSnippet = doc.Get("CodeSnippet");
if (score > 0.6)
{
results.Add(CodeSnippetName, CodeSnippet);
}
}
searcher.Close();
return(results);
}
public IEnumerable <DataFileRow> Search(string searchTerm)
{
IndexSearcher searcher = new IndexSearcher(luceneIndexDirectory);
QueryParser parser = new QueryParser("LineText", analyzer);
Query query = parser.Parse(searchTerm);
Hits hitsFound = searcher.Search(query);
List <DataFileRow> results = new List <DataFileRow>();
DataFileRow sampleDataFileRow = null;
for (int i = 0; i < hitsFound.Length(); i++)
{
sampleDataFileRow = new DataFileRow();
Document doc = hitsFound.Doc(i);
sampleDataFileRow.LineNumber = int.Parse(doc.Get("LineNumber"));
sampleDataFileRow.LineText = doc.Get("LineText");
float score = hitsFound.Score(i);
sampleDataFileRow.Score = score;
results.Add(sampleDataFileRow);
}
luceneIndexDirectory.Close();
searcher.Close();
return(results.OrderByDescending(x => x.Score).ToList());
}
public static void Main(string[] args)
{
string indexpath = args[0];
string query = args[1];
IndexSearcher searcher = new IndexSearcher(indexpath);
Query parsedquery = QueryParser.Parse(query,
"summary", new StandardAnalyzer());
Hits hits = searcher.Search(parsedquery);
Console.WriteLine("Found " + hits.Length() + " document(s) that matched query '" + query + "':\n");
for (int i = 0; i < hits.Length(); i++)
{
Document doc = hits.Doc(i);
Console.WriteLine(hits.Score(i) + ": " + doc.Get("excerpt") + "\n");
if (i == 50)
{
break;
}
}
searcher.Close();
}
void DoTitleMatches()
{
string term = searchterm;
try {
string[] terms = Regex.Split(term, " +");
term = "";
foreach (string t in terms)
{
term += t + "~ ";
}
searchterm = "title:(" + term + ")";
DateTime now = DateTime.UtcNow;
Query query = state.Parse(searchterm);
Hits hits = state.Searcher.Search(query);
int numhits = hits.Length();
LogRequest(searchterm, query, numhits, now);
SendHeaders(200, "OK");
for (int i = 0; i < numhits && i < 10; i++)
{
Document doc = hits.Doc(i);
float score = hits.Score(i);
string pageNamespace = doc.Get("namespace");
string title = doc.Get("title");
SendResultLine(score, pageNamespace, title);
}
} catch (Exception e) {
log.Error(e.Message + e.StackTrace);
}
}
public List <string> Search(string text)
{
List <string> lstFilteredValue = new List <string>();
try
{
IndexSearcher MyIndexSearcher = new IndexSearcher(LuceneDirectory);
Query mainQuery = this.GetParsedQuerywc(text);
//Do the search
Hits hits = MyIndexSearcher.Search(mainQuery);
int results = hits.Length();
for (int i = 0; i < results; i++)
{
Document doc = hits.Doc(i);
float score = hits.Score(i);
lstFilteredValue.Add(doc.Get("Name") + "," + doc.Get("Id"));
}
}
catch (Exception GeneralException)
{
}
return(lstFilteredValue);
}
public static IList <string> Search(string searchTerm)
{
System.Text.RegularExpressions.Regex rgx = new System.Text.RegularExpressions.Regex("[^a-zA-Z0-9]");
searchTerm = rgx.Replace(searchTerm, " ");
IndexSearcher searcher = new IndexSearcher(luceneIndexDirectory);
QueryParser parser = new QueryParser("Data", analyzer);
Query query = parser.Parse(searchTerm.ToLower());
Hits hitsFound = searcher.Search(query);
IList <string> results = new List <string>();
for (int i = 0; i < hitsFound.Length(); i++)
{
Document doc = hitsFound.Doc(i);
float score = hitsFound.Score(i);
string fileName = doc.Get("FileName");
if (score > 0.6)
{
results.Add(doc.Get("FileName"));
}
}
searcher.Close();
return(results);
}
public override List <SearchResult> Search(string searchStr)
{
List <SearchResult> results = new List <SearchResult>();
string cleanSearchStr = cleaner.Replace(searchStr, "").ToLower().Trim();
IndexSearcher searcher = new IndexSearcher(directory);
//QueryParser parser = new QueryParser("title", analyzer);
//Query query = parser.Parse(cleanSearchStr + "~0.7");
Query query = parser.Parse(cleanSearchStr + "~0.7");
Hits hits = searcher.Search(query);
int resultCount = hits.Length();
for (int i = 0; i < resultCount; i++)
{
SearchResult result = new SearchResult();
result.Item = DatabaseManager.Get <T>(int.Parse(hits.Doc(i).Get("id")));
result.Score = hits.Score(i);
results.Add(result);
}
return(results);
}
/// <summary>
/// Searches the index.
/// </summary>
/// <param name="queryText"></param>
/// <param name="categoryNames"></param>
/// <param name="pageIndex"></param>
/// <param name="pageSize"></param>
/// <param name="roleIds"></param>
/// <returns></returns>
public SearchResultCollection Find(string queryText, IList <string> categoryNames, int pageIndex, int pageSize, IEnumerable <int> roleIds)
{
long startTicks = DateTime.Now.Ticks;
// the overall-query
BooleanQuery query = new BooleanQuery();
// add our parsed query
if (!String.IsNullOrEmpty(queryText))
{
Query multiQuery = MultiFieldQueryParser.Parse(new[] { queryText, queryText, queryText }, new[] { "title", "summary", "contents" }, new StandardAnalyzer());
query.Add(multiQuery, BooleanClause.Occur.MUST);
}
// add the security constraint - must be satisfied
query.Add(this.BuildSecurityQuery(roleIds), BooleanClause.Occur.MUST);
// Add the category query (if available)
if (categoryNames != null)
{
query.Add(this.BuildCategoryQuery(categoryNames), BooleanClause.Occur.MUST);
}
IndexSearcher searcher = new IndexSearcher(this._indexDirectory);
Hits hits = searcher.Search(query);
int start = pageIndex * pageSize;
int end = (pageIndex + 1) * pageSize;
if (hits.Length() <= end)
{
end = hits.Length();
}
SearchResultCollection results = new SearchResultCollection(end);
results.TotalCount = hits.Length();
results.PageIndex = pageIndex;
for (int i = start; i < end; i++)
{
SearchResult result = new SearchResult();
result.Title = hits.Doc(i).Get("title");
result.Summary = hits.Doc(i).Get("summary");
result.Author = hits.Doc(i).Get("author");
result.ModuleType = hits.Doc(i).Get("moduletype");
result.Path = hits.Doc(i).Get("path");
string[] categories = hits.Doc(i).GetValues("category");
result.Category = categories != null?String.Join(", ", categories) : String.Empty;
result.DateCreated = DateTime.Parse((hits.Doc(i).Get("datecreated")));
result.Score = hits.Score(i);
result.Boost = hits.Doc(i).GetBoost();
result.SectionId = Int32.Parse(hits.Doc(i).Get("sectionid"));
results.Add(result);
}
searcher.Close();
results.ExecutionTime = DateTime.Now.Ticks - startTicks;
return(results);
}
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);
}
}
public EntityInfo Extract(Hits hits, int index)
{
Document doc = hits.Doc(index);
//TODO if we are lonly looking for score (unlikely), avoid accessing doc (lazy load)
EntityInfo entityInfo = Extract(doc);
object[] eip = entityInfo.Projection;
if (eip != null && eip.Length > 0)
{
for (int x = 0; x < projection.Length; x++)
{
switch (projection[x])
{
case ProjectionConstants.SCORE:
eip[x] = hits.Score(index);
break;
case ProjectionConstants.ID:
eip[x] = entityInfo.Id;
break;
case ProjectionConstants.DOCUMENT:
eip[x] = doc;
break;
case ProjectionConstants.DOCUMENT_ID:
eip[x] = hits.Id(index);
break;
case ProjectionConstants.BOOST:
eip[x] = doc.GetBoost();
break;
case ProjectionConstants.THIS:
//THIS could be projected more than once
//THIS loading delayed to the Loader phase
if (entityInfo.IndexesOfThis == null)
{
entityInfo.IndexesOfThis = new List <int>(1);
}
entityInfo.IndexesOfThis.Add(x);
break;
}
}
}
return(entityInfo);
}
private void DoTestSearch(System.IO.StringWriter out_Renamed, bool useCompoundFile)
{
Directory directory = new RAMDirectory();
Analyzer analyzer = new SimpleAnalyzer();
IndexWriter writer = new IndexWriter(directory, analyzer, true);
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(Field.Text("contents", docs[j]));
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\"" };
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]);
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);
out_Renamed.WriteLine(hits.Length() + " total results");
for (int i = 0; i < hits.Length() && i < 10; i++)
{
Document d = hits.Doc(i);
out_Renamed.WriteLine(i + " " + hits.Score(i) + " " + d.Get("contents"));
}
}
searcher.Close();
}
public string[] Fncsearch(string strSearchContent)
{
DateTime start = DateTime.Now;
try
{
searcher = new IndexSearcher(this.pathIndex);
}
catch (IOException ex)
{
System.Windows.Forms.MessageBox.Show("The index doesn't exist or is damaged. Please rebuild the index.\r\n\r\nDetails:\r\n" + ex.Message);
return(null);
}
if (strSearchContent.Trim(new char[] { ' ' }) == String.Empty)
{
return(null);
}
if (strSearchContent == "*")
{
MessageBox.Show("Sorry cannot search files with *");
}
Query query = QueryParser.Parse(strSearchContent, "text", new StandardAnalyzer());
Hits hits = searcher.Search(query);
string[] strTempArr = new string[hits.Length()];
for (int i = 0; i < hits.Length(); i++)
{
Document doc = hits.Doc(i);
string filename = doc.Get("title");
string path = doc.Get("path");
string folder = System.IO.Path.GetDirectoryName(path);
DirectoryInfo di = new DirectoryInfo(folder);
string s = filename + " " + path + " " + hits.Score(i).ToString();
System.Windows.Forms.ListViewItem item = new System.Windows.Forms.ListViewItem(new string[] { null, filename, di.Name, hits.Score(i).ToString() });
item.Tag = path;
strTempArr[i] = s;
}
searcher.Close();
//string searchReport = String.Format("Search took {0}. Found {1} items.", (DateTime.Now - start), hits.Length());
//status(searchReport);
return(strTempArr);
}
internal IList <ISbItem> OpenSearchRequest(string phrase, out int total)
{
IList <ISbItem> versiculos = new List <ISbItem>();
IndexSearcher searcher = this.DefaultIndex.GetIndex();
QueryParser queryParser = new QueryParser("versiculo", new StandardAnalyzer());
Hits hits = searcher.Search(queryParser.Parse(phrase));
total = hits.Length();
for (int i = 0; i < (hits.Length() > maxOpenSearchResults ? maxOpenSearchResults : hits.Length()); i++)
{
ISbItem item = this.DefaultContainer.Ext().GetByID(Convert.ToInt64(hits.Doc(i).Get("id"))) as ISbItem;
item.Tag = hits.Score(i).ToString();
this.DefaultContainer.Activate(item, 1);
versiculos.Add(item);
}
return(versiculos);
}
public DataTable search(string searchText)
{
DateTime start = DateTime.Now;
try
{
searcher = new IndexSearcher(this.pathIndex);
}
catch (IOException ex)
{
throw new IndexDamagedException("The index doesn't exist or is damaged. Please rebuild the index.\r\n\r\nDetails:\r\n" + ex.Message);
}
if ((searchText.Trim() != null && searchText.Trim().Length == 0))
{
return(new DataTable());
}
Query query = QueryParser.Parse(searchText, "text", new StandardAnalyzer());
Hits hits = searcher.Search(query);
DataTable dt = new DataTable();
dt.Columns.Add("title", typeof(string));
dt.Columns.Add("path", typeof(string));
dt.Columns.Add("hits", typeof(string));
for (int i = 0; i < hits.Length(); i++)
{
DataRow dr = dt.NewRow();
Document doc = hits.Doc(i);
dr["title"] = doc.Get("title");
dr["path"] = doc.Get("path");
dr["hits"] = hits.Score(i).ToString();
dt.Rows.Add(dr);
}
searcher.Close();
return(dt);
}
void DoRawSearch()
{
DateTime now = DateTime.UtcNow;
Query query = state.Parse(searchterm);
Hits hits = state.Searcher.Search(query);
int numhits = hits.Length();
LogRequest("(raw)", query, numhits, now);
SendHeaders(200, "OK");
for (int i = 0; i < numhits && i < 10; i++)
{
Document doc = hits.Doc(i);
float score = hits.Score(i);
string pageNamespace = doc.Get("namespace");
string title = doc.Get("title");
SendResultLine(score, pageNamespace, title);
}
}
/// <summary>
/// This method searches for the search term passed by the caller.
/// </summary>
/// <param name="searchTerm">The search term as a string that the caller wants to search for within the
/// index as referenced by this object.</param>
/// <param name="ids">An out parameter that is populated by this method for the caller with docments ids.</param>
/// <param name="results">An out parameter that is populated by this method for the caller with docments text.</param>
/// <param name="scores">An out parameter that is populated by this method for the caller with docments scores.</param>
internal int Search(string searchTerm, out Object[] ids, out string[] results, out float[] scores, WordExpander expandWithWordNet, bool expandOnNoHits)
{
checkDbLock();
if (!IsDbPresent)
{
ids = new Document[0];
results = new string[0];
scores = new float[0];
return(0);
}
IndexSearcher indexSearcher = new IndexSearcher(_directory);
try
{
QueryParser queryParser = new QueryParser(_fieldName, _analyzer);
Query query = queryParser.Parse(searchTerm);
Hits hits = indexSearcher.Search(query);
int numHits = hits.Length();
ids = new Document[numHits];
results = new string[numHits];
scores = new float[numHits];
for (int i = 0; i < numHits; ++i)
{
float score = hits.Score(i);
var hdoc = hits.Doc(i);
string text = hdoc.Get(_fieldName);
//string idAsText = hdoc.Get(MyLuceneIndexer.DOC_ID_FIELD_NAME);
ids[i] = hdoc;
results[i] = text;
scores[i] = score;
}
if (numHits == 0 && expandOnNoHits)
{
// Try expansion
//QueryParser queryParser = new QueryParser(_fieldName, _analyzer);
MultiFieldQueryParser queryParserWN = new MultiFieldQueryParser(
new string[] { _fieldName, MyLuceneIndexer.HYPO_FIELD_NAME },
_analyzer);
string hypo_expand = expandWithWordNet(searchTerm, false);
Query queryWN = queryParserWN.Parse(hypo_expand);
Hits hitsWN = indexSearcher.Search(queryWN);
int numHitsWN = hitsWN.Length();
ids = new Document[numHitsWN];
results = new string[numHitsWN];
scores = new float[numHitsWN];
for (int i = 0; i < numHitsWN; ++i)
{
float score = hitsWN.Score(i);
string text = hitsWN.Doc(i).Get(_fieldName);
//string idAsText = hitsWN.Doc(i).Get(MyLuceneIndexer.DOC_ID_FIELD_NAME);
ids[i] = hitsWN.Doc(i);// UInt64.Parse(idAsText);
results[i] = text;
scores[i] = score;
}
}
}
finally
{
indexSearcher.Close();
}
return(ids.Length);
}/*
internal int DeleteTopScoring0(string searchQuery, bool mustContainExact)
{
checkDbLock();
if (!IsDbPresent)
{
return(0);
}
// Searching:
ulong[] ids;
string[] results;
float[] scores;
int numHits;
// find it
writeToLog("Replacing best \"{0}\"...", searchQuery);
//Search(query, out ids, out results, out scores);
IndexSearcher indexSearcher = new IndexSearcher(_directory);
int deleted = 0;
try
{
QueryParser queryParser = new QueryParser(_fieldName, _analyzer);
Query query = queryParser.Parse(searchQuery);
Hits hits = indexSearcher.Search(query);
string searchQueryToLower = searchQuery.ToLower();
numHits = hits.Length();
// if we want to do something smarter later
ids = new ulong[numHits];
results = new string[numHits];
scores = new float[numHits];
for (int i = 0; i < numHits; ++i)
{
float score = hits.Score(i);
string text = hits.Doc(i).Get(_fieldName);
string idAsText = hits.Doc(i).Get(MyLuceneIndexer.DOC_ID_FIELD_NAME);
ids[i] = UInt64.Parse(idAsText);
results[i] = text;
scores[i] = score;
}
if (numHits > 0)
{
//IndexReader indexReader = indexSearcher.GetIndexReader();
IndexWriter indexWriter = new IndexWriter(_directory, _analyzer);
float topscore = scores[0];
for (int i = 0; i < numHits; i++)
{
if (scores[i] == topscore)
{
if (mustContainExact)
{
// checks word order basically?
if (!results[i].ToLower().Contains(searchQueryToLower))
{
writeToLog("Cannot or wont delete " + searchQueryToLower);
continue;
}
}
writeToLog("DEBUG9 deleting " + searchQueryToLower);
//indexSearcher.GetIndexReader().DeleteDocument(i);
//indexReader.DeleteDocuments(new Term( MyLuceneIndexer.DOC_ID_FIELD_NAME, ids[i].ToString () ) );
indexWriter.DeleteDocuments(new Term(MyLuceneIndexer.DOC_ID_FIELD_NAME, ids[i].ToString()));
deleted++;
}
}
//indexReader.Commit();
//indexReader.Close();
indexWriter.Commit();
indexWriter.Close();
}
}
finally
{
indexSearcher.Close();
}
return(deleted);
}
/// <summary>
/// 构造返回结果
/// </summary>
/// <returns></returns>
private List <ProductSimpleInfo> ProductBinding(Hits hits, string key, int order, int pageNo, int pageLen, out int recCount)
{
recCount = hits.Length();
// 合并
int n = 0;
ProductSimpleInfo info = null;
IList <ProductSimpleInfo> list = new List <ProductSimpleInfo>();
while (n < recCount)
{
// 去除匹配度太低结果
if (hits.Score(n) < 0.01)
{
n++;
continue;
}
try
{
info = new ProductSimpleInfo()
{
productID = int.Parse(hits.Doc(n).Get("ProductID")),
productCode = hits.Doc(n).Get("ProductCode"),
chineseName = hits.Doc(n).Get("ChineseName"),
cadn = hits.Doc(n).Get("CADN"),
longName = hits.Doc(n).Get("LongName"),
pinyinName = hits.Doc(n).Get("PinyinName"),
marketPrice = decimal.Parse(hits.Doc(n).Get("MarketPrice")),
tradePrice = decimal.Parse(hits.Doc(n).Get("TradePrice")),
sellCount = int.Parse(hits.Doc(n).Get("SellCount")),
favorCount = int.Parse(hits.Doc(n).Get("Favorite")),
productType = short.Parse(hits.Doc(n).Get("ProductType")),
specifications = hits.Doc(n).Get("Specifications"),
images = hits.Doc(n).Get("Images"),
actions = short.Parse(hits.Doc(n).Get("Actions")),
comments = int.Parse(hits.Doc(n).Get("Comments")),
selling = int.Parse(hits.Doc(n).Get("Selling")),
manufacturer = hits.Doc(n).Get("Manufacturer"),
sellingTime = DateTime.Parse(hits.Doc(n).Get("SellingTime")),
recommend = float.Parse(hits.Doc(n).Get("Recommend")),
preferential = float.Parse(hits.Doc(n).Get("Preferential")),
brandName = hits.Doc(n).Get("BrandName")
};
if (order <= 0)
{
info.level = GetProductLevel(hits.Score(n), 1);
info.score = GetProductLevel(info.sellCount, 0) + n;
}
}
catch { }
finally
{
if (info != null)
{
list.Add(info);
}
n++;
}
}
recCount = list.Count();
// 返回数据
switch (order)
{
case 1:
// 人气 降序
return(list.OrderByDescending(i => i.favorCount).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 2:
// 人气 升序
return(list.OrderByDescending(i => i.favorCount).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 3:
// 新品 降序
return(list.OrderByDescending(i => i.sellingTime).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 4:
// 新品 升序
return(list.OrderBy(i => i.sellingTime).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 5:
// 销量 降序
return(list.OrderByDescending(i => i.sellCount).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 6:
// 销量 升序
return(list.OrderBy(i => i.sellCount).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 7:
// 价格 降序
return(list.OrderByDescending(i => i.tradePrice).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 8:
// 价格 升序
return(list.OrderBy(i => i.tradePrice).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
case 9:
// 综合 升序
return(list.OrderBy(i => i.level).ThenBy(i => i.score).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
default:
return(list.OrderByDescending(i => i.level).ThenBy(i => i.score).Skip(pageLen * (pageNo - 1)).Take(pageLen).ToList());
}
}
/// <summary>
/// 商品结果参数 品牌/分类
/// </summary>
/// <param name="hits"></param>
private IList <JXSearchEntity> ProductParaList(Hits hits)
{
int id = 0;
IList <JXSearchEntity> list = new List <JXSearchEntity>();
try
{
int recCount = hits.Length(); // 总记录数
for (int j = 0; j < recCount; j++)
{
if (hits.Score(j) < 0.01)
{
continue;
}
#region 分类1
if (hits.Doc(j).Get("CFID1").Length > 0)
{
id = int.Parse(hits.Doc(j).Get("CFID1"));
if (list.Where(g => g.id == id && g.typeID == 2).Count() <= 0)
{
list.Add(new JXSearchEntity()
{
id = id,
chineseName = hits.Doc(j).Get("CFName1"),
typeID = 2,
parentID = int.Parse(hits.Doc(j).Get("ParentID1"))
});
}
}
#endregion
#region 分类2
if (hits.Doc(j).Get("CFID2").Length > 0)
{
id = int.Parse(hits.Doc(j).Get("CFID2"));
if (list.Where(g => g.id == id && g.typeID == 2).Count() <= 0)
{
list.Add(new JXSearchEntity()
{
id = id,
chineseName = hits.Doc(j).Get("CFName2"),
typeID = 2,
parentID = int.Parse(hits.Doc(j).Get("ParentID2"))
});
}
}
#endregion
#region 分类3
if (hits.Doc(j).Get("CFID3").Length > 0)
{
id = int.Parse(hits.Doc(j).Get("CFID3"));
if (list.Where(g => g.id == id && g.typeID == 2).Count() <= 0)
{
list.Add(new JXSearchEntity()
{
id = id,
chineseName = hits.Doc(j).Get("CFName3"),
typeID = 2,
parentID = int.Parse(hits.Doc(j).Get("ParentID3"))
});
}
}
#endregion
#region 品牌
if (hits.Doc(j).Get("BrandID").Length > 0)
{
id = int.Parse(hits.Doc(j).Get("BrandID"));
if (list.Where(g => g.brandID == id && g.typeID == 5).Count() <= 0)
{
list.Add(new JXSearchEntity()
{
brandID = id,
brandName = hits.Doc(j).Get("BrandName"),
letter = hits.Doc(j).Get("BrandLetter"),
typeID = 5
});
}
}
#endregion
}
}
catch { }
return(list);
}
} // constructor
/// <summary>
/// Searches the keyword index using the keywordQuery.
///
/// See http://www.dotlucene.net/documentation/QuerySyntax.html for the format of the keywordQuery.
///
/// This function will return a fully-filled array of IndexableFileInfo objects.
/// </summary>
/// <param name="keywordQuery"></param>
/// <param name="queryForHighlighter"></param>
/// <returns></returns>
public IndexableFileInfo[] doSearch(string keywordQuery, string queryForHighlighter)
{
IndexSearcher searcher;
IndexReader indexReader;
try
{
FSDirectory indexDir = FSDirectory.GetDirectory(this.luceneIndexDir, false);
indexReader = IndexReader.Open(indexDir);
searcher = new IndexSearcher(indexReader);
}
catch
{
// if the luceneIndexDir does not contain index files (yet), IndexSearcher
// throws a nice Exception.
return(new IndexableFileInfo[0]);
}
List <IndexableFileInfo> arrayList = new List <IndexableFileInfo>();
try
{
string Query = keywordQuery;
if (Query == String.Empty)
{
return(new IndexableFileInfo[0]);
}
string HighlighterQuery = queryForHighlighter;
// -- weirdly enough, when the query is empty, an exception is thrown during the QueryParser.Parse
// this hack gets around that.
if (HighlighterQuery == String.Empty)
{
HighlighterQuery = Guid.NewGuid().ToString();
}
// parse the query, "text" is the default field to search
// note: use the StandardAnalyzer! (the SimpleAnalyzer doesn't work correctly when searching by fields that are integers!)
// MultiFieldQueryParser queryParser = new MultiFieldQueryParser(new string[] { "title", "contents" }, new hatWebPortalAnalyzer());
MultiFieldQueryParser queryParser = new MultiFieldQueryParser(new string[] { "title", "contents" }, new SimpleAnalyzer());
queryParser.SetDefaultOperator(QueryParser.AND_OPERATOR);
Query query = queryParser.Parse(Query);
QueryParser highlightQueryParser = new QueryParser("contents", new hatWebPortalAnalyzer());
Query highlighterQuery = highlightQueryParser.Parse(HighlighterQuery);
query = searcher.Rewrite(query); // is this needed?? " Expert: called to re-write queries into primitive queries."
// search
Hits hits = searcher.Search(query, Sort.RELEVANCE);
// create highlighter
Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter("<strong>", "</strong>"), new QueryScorer(highlighterQuery));
// -- go through hits and return results
for (int i = 0; i < hits.Length(); i++)
{
Document d = hits.Doc(i);
string filename = d.Get("filename");
string plainText = d.Get("contents");
string title = d.Get("title");
string sectionName = d.Get("SectionName");
string filenameParams = d.Get("filenameParams");
bool contentIsPageSummary = Convert.ToBoolean(d.Get("contentIsPageSummary"));
double score = Convert.ToDouble(hits.Score(i));
DateTime lastModified = DateTools.StringToDate(d.Get("LastModified"));
TokenStream tokenStream = new hatWebPortalAnalyzer().TokenStream("contents", new StringReader(plainText));
string fragment = plainText;
if (!contentIsPageSummary)
{
fragment = highlighter.GetBestFragments(tokenStream, plainText, 2, "...");
}
IndexableFileInfo newHit = new IndexableFileInfo(filename, filenameParams, title, fragment, sectionName, lastModified, contentIsPageSummary, score);
arrayList.Add(newHit);
} // for
}
finally
{
searcher.Close();
indexReader.Close();
}
return(arrayList.ToArray());
} // SearchActiveDocument
/// <summary>
/// search support multiple modules
/// </summary>
/// <param name="siteId"></param>
/// <param name="isAdmin"></param>
/// <param name="userRoles"></param>
/// <param name="queryText"></param>
/// <param name="highlightResults"></param>
/// <param name="highlightedFragmentSize"></param>
/// <param name="pageNumber"></param>
/// <param name="pageSize"></param>
/// <param name="totalHits"></param>
/// <param name="invalidQuery"></param>
/// <param name="moduleIDs"></param>
/// <returns></returns>
public static IndexItemCollection Search(
int siteId,
bool isAdmin,
List <string> userRoles,
string queryText,
bool highlightResults,
int highlightedFragmentSize,
int pageNumber,
int pageSize,
out int totalHits,
out bool invalidQuery,
params Guid[] moduleIDs
)
{
invalidQuery = false;
totalHits = 0;
string indexPath = GetIndexPath(siteId);
IndexItemCollection results = new IndexItemCollection();
if (string.IsNullOrEmpty(queryText))
{
return(results);
}
bool useBackwardCompatibilityMode = true;
if (
(ConfigurationManager.AppSettings["SearchUseBackwardCompatibilityMode"] != null) &&
(ConfigurationManager.AppSettings["SearchUseBackwardCompatibilityMode"] == "false")
)
{
useBackwardCompatibilityMode = false;
}
bool IncludeModuleRoleFilters = false;
if (
(ConfigurationManager.AppSettings["SearchIncludeModuleRoleFilters"] != null) &&
(ConfigurationManager.AppSettings["SearchIncludeModuleRoleFilters"] == "true")
)
{
IncludeModuleRoleFilters = true;
}
if (IndexReader.IndexExists(indexPath))
{
if (log.IsDebugEnabled)
{
log.Debug("Entered Search, indexPath = " + indexPath);
}
long startTicks = DateTime.Now.Ticks;
try
{
BooleanQuery mainQuery = new BooleanQuery();
if ((!isAdmin) && (!useBackwardCompatibilityMode))
{
AddRoleQueries(userRoles, mainQuery);
}
if ((!isAdmin) && (IncludeModuleRoleFilters))
{
AddModuleRoleQueries(userRoles, mainQuery);
}
Query multiQuery = MultiFieldQueryParser.Parse(
new string[] { queryText, queryText, queryText, queryText, queryText, queryText.Replace("*", string.Empty) },
new string[] { "Title", "ModuleTitle", "contents", "PageName", "PageMetaDesc", "Keyword" },
new StandardAnalyzer());
mainQuery.Add(multiQuery, BooleanClause.Occur.MUST);
if (!useBackwardCompatibilityMode)
{
Term beginDateStart = new Term("PublishBeginDate", DateTime.MinValue.ToString("s"));
Term beginDateEnd = new Term("PublishBeginDate", DateTime.UtcNow.ToString("s"));
RangeQuery beginDateQuery = new RangeQuery(beginDateStart, beginDateEnd, true);
mainQuery.Add(beginDateQuery, BooleanClause.Occur.MUST);
Term endDateStart = new Term("PublishEndDate", DateTime.UtcNow.ToString("s"));
Term endDateEnd = new Term("PublishEndDate", DateTime.MaxValue.ToString("s"));
RangeQuery endDateQuery = new RangeQuery(endDateStart, endDateEnd, true);
mainQuery.Add(endDateQuery, BooleanClause.Occur.MUST);
}
if (moduleIDs != null && moduleIDs.Length > 0)
{
BooleanQuery featureFilter = new BooleanQuery();
moduleIDs.ToList().ForEach(x => {
if (x != Guid.Empty)
{
featureFilter.Add(new TermQuery(new Term("FeatureId", x.ToString())), BooleanClause.Occur.SHOULD);
}
});
if (featureFilter.Clauses().Count > 0)
{
mainQuery.Add(featureFilter, BooleanClause.Occur.MUST);
}
}
IndexSearcher searcher = new IndexSearcher(indexPath);
// a 0 based colection
Hits hits = searcher.Search(mainQuery);
int startHit = 0;
if (pageNumber > 1)
{
startHit = ((pageNumber - 1) * pageSize);
}
totalHits = hits.Length();
int end = startHit + pageSize;
if (totalHits <= end)
{
end = totalHits;
}
int itemsAdded = 0;
int itemsToAdd = end;
// in backward compatibility mode if multiple pages of results are found we amy not be showing every user the correct
// number of hits they can see as we only filter out the current page
//we may decrement total hits if filtering results so keep the original count
int actualHits = totalHits;
if (!useBackwardCompatibilityMode)
{
// this new way is much cleaner
//all filtering is done by query so the hitcount is true
//whereas with the old way it could be wrong since there
// were possibly results filtered out after the query returned.
QueryScorer scorer = new QueryScorer(multiQuery);
Formatter formatter = new SimpleHTMLFormatter("<span class='searchterm'>", "</span>");
Highlighter highlighter = new Highlighter(formatter, scorer);
highlighter.SetTextFragmenter(new SimpleFragmenter(highlightedFragmentSize));
for (int i = startHit; i < itemsToAdd; i++)
{
IndexItem indexItem = new IndexItem(hits.Doc(i), hits.Score(i));
if (highlightResults)
{
try
{
TokenStream stream = new StandardAnalyzer().TokenStream("contents", new StringReader(hits.Doc(i).Get("contents")));
string highlightedResult = highlighter.GetBestFragment(stream, hits.Doc(i).Get("contents"));
if (highlightedResult != null)
{
indexItem.Intro = highlightedResult;
}
}
catch (NullReferenceException) { }
}
results.Add(indexItem);
itemsAdded += 1;
}
}
else
{
//backward compatible with old indexes
int filteredItems = 0;
for (int i = startHit; i < itemsToAdd; i++)
{
bool needToDecrementTotalHits = false;
if (
(isAdmin) ||
(WebUser.IsContentAdmin) ||
(WebUser.IsInRoles(hits.Doc(i).Get("ViewRoles")))
)
{
IndexItem indexItem = new IndexItem(hits.Doc(i), hits.Score(i));
if (
(DateTime.UtcNow > indexItem.PublishBeginDate) &&
(DateTime.UtcNow < indexItem.PublishEndDate)
)
{
results.Add(indexItem);
}
else
{
needToDecrementTotalHits = true;
}
}
else
{
needToDecrementTotalHits = true;
}
//filtered out a result so need to decrement
if (needToDecrementTotalHits)
{
filteredItems += 1;
totalHits -= 1;
//we also are not getting as many results as the page size so if there are more items
//we should increment itemsToAdd
if ((itemsAdded + filteredItems) < actualHits)
{
itemsToAdd += 1;
}
}
}
}
searcher.Close();
results.ItemCount = itemsAdded;
results.PageIndex = pageNumber;
results.ExecutionTime = DateTime.Now.Ticks - startTicks;
}
catch (ParseException ex)
{
invalidQuery = true;
log.Error("handled error for search terms " + queryText, ex);
// these parser exceptions are generally caused by
// spambots posting too much junk into the search form
// heres an option to automatically ban the ip address
HandleSpam(queryText, ex);
return(results);
}
catch (BooleanQuery.TooManyClauses ex)
{
invalidQuery = true;
log.Error("handled error for search terms " + queryText, ex);
return(results);
}
}
return(results);
}
static void Main(string[] args)
{
String indexPath = @"C:\Users\Brandon\Desktop\Multimedia Retrieval\W3 Files\Index";
//Analyzers build token streams which analyze text
Analyzer analyzer = new StandardAnalyzer();
IndexWriter writer = new IndexWriter(indexPath, analyzer, true);
//Set the seedUrl and initialize the crawler
String seedUrl = "http://sydney.edu.au/engineering/it/";
WebCrawler crawler = new WebCrawler();
Queue <String> linkQueue = new Queue <String>();
linkQueue.Enqueue(seedUrl);
HashSet <String> linkSet = new HashSet <String>();
Console.Write("Sites Explored: 0");
//Iteratively extract links from the first URL in the frontier
//and adds its content to index
while (linkQueue.Count != 0 && linkSet.Count < 50)
{
String currentLink = linkQueue.Dequeue();
try
{
if (linkSet.Contains(currentLink))
{
continue;
}
String content = crawler.getUrlContent(currentLink);
crawler.getLinks(linkQueue, content, currentLink);
linkSet.Add(currentLink);
Document doc = new Document();
doc.Add(new Field("link", currentLink, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("content", content, Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
Console.Write("\rSites Explored: {0}", linkSet.Count);
}
catch (Exception) { continue; }
}
writer.Optimize();
writer.Close();
Console.WriteLine();
//Execute the search
String search = "suits";
QueryParser parser = new QueryParser("content", analyzer);
Query query = parser.Parse(search);
var searcher = new IndexSearcher(indexPath);
Hits hits = searcher.Search(query);
int results = hits.Length();
Console.WriteLine("Found {0} results for \"{1}\"", results, search);
for (int i = 0; i < results; i++)
{
Document doc = hits.Doc(i);
float score = hits.Score(i);
Console.WriteLine("Result num {0}, score {1}", i + 1, score);
Console.WriteLine("URL: {0}", doc.Get("link"));
}
}
public override void Search(string SearchString)
{
base.Search(SearchString);
SearchString = SearchString.ToLower();
var dir = FSDirectory.GetDirectory(IndexPath, false);
var searcher = new IndexSearcher(dir);
var parser = new QueryParser(ContentField, new StandardAnalyzer());
foreach (var s in SearchString.Split(new [] { ' ' }))
{
var query = parser.GetFuzzyQuery(ContentField, s, MinSimilarity);
Hits hits = searcher.Search(query);
for (int i = 0; i < hits.Length(); i++)
{
Document doc = hits.Doc(i);
var result = new SearchResult {
Score = hits.Score(i), Plugin = doc.Get(PluginField)
};
//Text des aktuellen Dokuments auslesen
string text = doc.Get(ContentField);
//Alle indizierten Wörter dieses Dokumentes auslesen
var tpv = (TermPositionVector)IndexReader.Open(dir).GetTermFreqVector(hits.Id(i), ContentField);
String[] DocTerms = tpv.GetTerms();
//Die Anzahl der Erscheinungen aller Wörter auslesen
int[] freq = tpv.GetTermFrequencies();
var words = new List <string>(DocTerms);
//Hier wollen wir nun die Positionen der Erscheinungen des Suchwortes herausfinden
for (int t = 0; t < freq.Length; t++)
{
//Falls das Suchwort mit dem aktuellen Wort übereinstimmt...
if (ContainsSearchString(SearchString, DocTerms[t], words))
{
//...können wir die Positionen auslesen
TermVectorOffsetInfo[] offsets = tpv.GetOffsets(t);
//Das Array beinhaltet nun für das Suchwort alle Auftreten mit jeweils Anfang und Ende
for (int j = 0; j < offsets.Length; j++)
{
//Jetz muss nur noch ein kleiner Kontextausschnitt ausgelesen werden, damit der User etwas damit anfangen kann
int start = offsets[j].GetStartOffset();
int end = offsets[j].GetEndOffset();
int contextStart = start - ContextLeftOffset;
contextStart = contextStart < 0 ? 0 : contextStart;
int contextEnd = end + ContextRightOffset;
contextEnd = contextEnd > text.Length ? text.Length : contextEnd;
//Nun wollen wir noch bis zum Ende des nächsten Wortes lesen, um das Ergebnis besser lesbar zu machen
int nextEndSpace = text.IndexOf(" ", contextEnd);
contextEnd = nextEndSpace > 0 ? nextEndSpace : contextEnd;
//Maximal so viele Zeichen darf der Text nach einem Leerzeichen links von dem Suchergebnis durchsucht werden
int leftSpaceOffset = contextStart;
//Finden des nächstenLeerzeichens links vom Suchergebnis
int nextStartSpace = text.LastIndexOf(" ", contextStart, leftSpaceOffset);
//Falls es kein Space in der Nöhe gibt brauchen wir natürlich auch nichts verändern
contextStart = nextStartSpace > 0 ? nextStartSpace : contextStart;
int contextLength = contextEnd - contextStart;
contextLength = contextLength > text.Length ? text.Length : contextLength;
//Kontext auslesen
string context = text.Substring(contextStart, contextLength);
//und den Searchresults zusammen mit dem zugehörigen PlugInNamen und dem HitScore hinzufügen
result.Contexts.Add(context);
}
}
}
SearchResults.Add(result);
}
}
}
/// <summary>
/// 查询索引
/// </summary>
/// <param name="fieldName">FieldName</param>
/// <param name="keywords">关键字</param>
/// <param name="pageIndex">当前页</param>
/// <param name="pageSize">分页大小</param>
/// <param name="totalRecord">总的记录</param>
/// <returns>索引列表</returns>
/// <remarks>2013-08-15 朱成果 创建</remarks>
public List <CBPdProductIndex> QueryDoc(string fieldName, string keywords, int pageIndex, int pageSize, out int totalRecord)
{
var search = new IndexSearcher(IndexStorePath);
Query searchQuery;
if (!string.IsNullOrEmpty(fieldName) && !string.IsNullOrEmpty(keywords))
{
#region [关键字查询]
var query = new BooleanQuery();
BooleanQuery childQuery;
BooleanQuery esenQuery;
if (fieldName == "ProductName")
{
#region 2016-4-6 杨浩 新增模糊搜索
childQuery = new BooleanQuery();
esenQuery = new BooleanQuery();
//模糊搜索
//esenQuery.Add(new FuzzyQuery(new Term("ProductName", Regex.Replace(keywords, @"\s", ""))), BooleanClause.Occur.SHOULD);
//esenQuery.SetBoost(4.0F);
//分词 盘古分词
var keyWordsSplitBySpace = GetKeyWordsSplitBySpace(keywords);
//string keyWordsSplitBySpace = string.Format("{0}^{1}.0", keywords, (int)Math.Pow(3, 5));
//不启用分词，直接用模糊搜索
QueryParser productNameQueryParser = new QueryParser(global::Lucene.Net.Util.Version.LUCENE_29, "ProductName", new PanGuAnalyzer(true));
Query productNameQuery = productNameQueryParser.Parse(keyWordsSplitBySpace);
childQuery.Add(productNameQuery, BooleanClause.Occur.SHOULD);
//以什么开头，输入“ja”就可以搜到包含java和javascript两项结果了
Query prefixQuery_productName = new PrefixQuery(new Term("ProductName", keywords.Trim()));
//直接模糊匹配,假设你想搜索跟‘wuzza’相似的词语,你可能得到‘fuzzy’和‘wuzzy’。
Query fuzzyQuery_productName = new FuzzyQuery(new Term("ProductName", keywords.Trim()));
//通配符搜索
Query wildcardQuery_productName = new WildcardQuery(new Term("ProductName", string.Format("{0}", keywords.Trim())));
childQuery.Add(prefixQuery_productName, BooleanClause.Occur.SHOULD);
childQuery.Add(fuzzyQuery_productName, BooleanClause.Occur.SHOULD);
childQuery.Add(wildcardQuery_productName, BooleanClause.Occur.SHOULD);
childQuery.SetBoost(4.0F);
//childQuery.Add(esenQuery, BooleanClause.Occur.SHOULD);
query.Add(childQuery, BooleanClause.Occur.MUST);
#endregion
//childQuery = new BooleanQuery();
//esenQuery = new BooleanQuery();
////全词去空格
//esenQuery.Add(new TermQuery(new Term("ProductName", Regex.Replace(keywords, @"\s", ""))),
// BooleanClause.Occur.SHOULD);
//esenQuery.SetBoost(3.0F);
//childQuery.Add(esenQuery, BooleanClause.Occur.SHOULD);
//esenQuery = new BooleanQuery();
////分词 盘古分词
//esenQuery.Add(new QueryParser("ProductName", new PanGuAnalyzer(true)).Parse(keywords),
// BooleanClause.Occur.SHOULD);
////分词 按空格
//var keyColl = keywords.Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries);
//foreach (var item in keyColl)
//{
// esenQuery.Add(new TermQuery(new Term("ProductName", item)),
// BooleanClause.Occur.SHOULD);
//}
//esenQuery.SetBoost(2.9F);
//childQuery.Add(esenQuery, BooleanClause.Occur.SHOULD);
//query.Add(childQuery, BooleanClause.Occur.MUST);
}
else if (fieldName == "Category")
{
childQuery = new BooleanQuery();
esenQuery = new BooleanQuery();
esenQuery.Add(new TermQuery(new Term("Category", keywords)),
BooleanClause.Occur.SHOULD);
esenQuery.SetBoost(3.0F);
childQuery.Add(esenQuery, BooleanClause.Occur.SHOULD);
esenQuery = new BooleanQuery();
esenQuery.Add(new WildcardQuery(new Term("AssociationCategory", string.Format("*,{0},*", keywords))),
BooleanClause.Occur.SHOULD);
esenQuery.SetBoost(2.8F);
childQuery.Add(esenQuery, BooleanClause.Occur.SHOULD);
query.Add(childQuery, BooleanClause.Occur.MUST);
}
else if (fieldName == "BrandSysNo")
{
childQuery = new BooleanQuery();
childQuery.Add(new TermQuery(new Term("BrandSysNo", keywords)),
BooleanClause.Occur.SHOULD);
childQuery.SetBoost(3.0F);
query.Add(childQuery, BooleanClause.Occur.MUST);
}
else if (fieldName == "DealerSysNos")
{
childQuery = new BooleanQuery();
childQuery.Add(new WildcardQuery(new Term("DealerSysNos", string.Format("*,{0},*", keywords))),
BooleanClause.Occur.SHOULD);
childQuery.SetBoost(2.8F);
query.Add(childQuery, BooleanClause.Occur.MUST);
}
else if (fieldName == "ProductGroupCode")
{
childQuery = new BooleanQuery();
childQuery.Add(new WildcardQuery(new Term("ProductGroupCode", string.Format("*,{0},*", keywords))),
BooleanClause.Occur.SHOULD);
childQuery.SetBoost(2.8F);
query.Add(childQuery, BooleanClause.Occur.MUST);
}
else
{
query.Add(new TermQuery(new Term(fieldName, keywords)),
BooleanClause.Occur.SHOULD);
}
#endregion
searchQuery = query;
}
else
{
searchQuery = new WildcardQuery(new Term("ProductName", "*雪花秀*"));
}
//排序方式
var sort = new Sort();
//搜索
Hits hits = search.Search(searchQuery, sort);
totalRecord = hits.Length();//总的记录
int startIndex = (pageIndex - 1) * pageSize;
if (startIndex < 0)
{
startIndex = 0;
}
int endIndex = startIndex + pageSize;
if (endIndex > totalRecord - 1)
{
endIndex = totalRecord - 1;
}
List <CBPdProductIndex> lst = new List <CBPdProductIndex>();
for (int i = startIndex; i <= endIndex; i++)
{
var doc = hits.Doc(i);
lst.Add(
new CBPdProductIndex
{
DocID = hits.Id(i),
Score = hits.Score(i),
AssociationCategory = doc.Get("AssociationCategory"),
Attributes = doc.Get("Attributes"),
Barcode = doc.Get("Barcode"),
BrandSysNo = Convert.ToInt32(doc.Get("BrandSysNo")),
Category = Convert.ToInt32(doc.Get("Category")),
DisplayOrder = Convert.ToInt32(doc.Get("DisplayOrder")),
NameAcronymy = doc.Get("NameAcronymy"),
Prices = doc.Get("Prices"),
ProductImage = doc.Get("ProductImage"),
ProductName = doc.Get("ProductName"),
QRCode = doc.Get("QRCode"),
Status = Convert.ToInt32(doc.Get("Status")),
SysNo = Convert.ToInt32(doc.Get("SysNo")),
BasicPrice = Convert.ToDecimal(doc.Get("BasicPrice")),
Price = Convert.ToDecimal(doc.Get("Price")),
DispalySymbol = 0,
RankPrice = 0.00M,
ProductGroupCode = Convert.ToString(doc.Get("ProductGroupCode")),
DealerSysNos = doc.Get("DealerSysNos"),
WarehouseSysNos = doc.Get("WarehouseSysNos")
});
}
search.Close();
return(lst);
}
public float Score(int i)
{
return(hits.Score(i));
}
public static Hashtable Search(bool api)
{
BillType type;
int number;
int session = -1;
if (HttpContext.Current.Request["session"] != null && HttpContext.Current.Request["session"] != "")
{
session = int.Parse(HttpContext.Current.Request["session"]);
}
string q = HttpContext.Current.Request["q"];
int start = 0, count = (!api ? 30 : 1000);
if (HttpContext.Current.Request["start"] != null)
{
start = int.Parse(HttpContext.Current.Request["start"]);
}
if (HttpContext.Current.Request["count"] != null)
{
count = int.Parse(HttpContext.Current.Request["count"]);
}
BooleanQuery query = new BooleanQuery();
Hashtable no_results = new Hashtable();
no_results["count"] = 0;
if (q != null && q.IndexOf("*") > -1)
{
return(no_results);
}
if (!api && session == -1 && q != null)
{
int slash = q.IndexOf('/');
if (slash >= q.Length - 4 && slash > 2)
{
try {
session = int.Parse(q.Substring(slash + 1)); // and if that worked...
q = q.Substring(0, slash);
HttpContext.Current.Response.Redirect("billsearch.xpd?session=" + session + "&q=" + HttpUtility.UrlEncode(q));
return(null);
} catch { }
}
}
if (session == -1)
{
session = Util.CurrentSession;
}
//Console.Error.WriteLine("Find: " + q);
string search_method = "search";
ArrayList specs = new ArrayList();
Hashtable scores = new Hashtable();
// Match a bill number exactly
if (q != null && Bills.ParseID(q, out type, out number))
{
if (!api)
{
// Redirect the user right to the bill page.
// Don't even check if bill exists.
HttpContext.Current.Response.Redirect(
Bills.BillLink2(session, type, number));
return(null);
}
else
{
search_method = "search by bill number";
scores[session + EnumsConv.BillTypeToString(type) + number] = 1.0F;
specs.Add(new Database.AndSpec(
new Database.SpecEQ("session", session),
new Database.SpecEQ("type", EnumsConv.BillTypeToString(type)),
new Database.SpecEQ("number", number)));
}
}
// Match public law number exactly
if (!api && q != null && (q.StartsWith("P.L.") || q.StartsWith("PL")))
{
try {
string num = null;
if (q.StartsWith("P.L."))
{
num = q.Substring(4);
}
if (q.StartsWith("PL"))
{
num = q.Substring(2);
}
num = num.Replace(" ", "");
int dash = num.IndexOf('-');
int s = int.Parse(num.Substring(0, dash));
TableRow bill = Util.Database.DBSelectFirst("billindex", "session, type, number",
new Database.SpecEQ("idx", "publiclawnumber"),
new Database.SpecEQ("session", s),
new Database.SpecEQ("value", num));
if (bill != null)
{
if (!api)
{
HttpContext.Current.Response.Redirect(Bills.BillLink3((int)bill["session"], (string)bill["type"], (int)bill["number"]));
return(null);
}
else
{
search_method = "search by public law number";
scores[(int)bill["session"] + (string)bill["type"] + (int)bill["number"]] = 1.0F;
specs.Add(new Database.AndSpec(
new Database.SpecEQ("session", (int)bill["session"]),
new Database.SpecEQ("type", (string)bill["type"]),
new Database.SpecEQ("number", (int)bill["number"])));
}
}
} catch {
}
}
if (session == -1)
{
session = Util.CurrentSession;
}
// Match USC reference
Regex uscexp = new Regex(@"(\d[0-9A-Za-z\-]*)\s+U\.?S\.?C\.?\s+(\d[0-9A-Za-z\-]*)((\s*\([^\) ]+\))*)",
RegexOptions.IgnoreCase);
Match uscmc = (q == null ? null : uscexp.Match(q));
if (uscmc != null && uscmc.Success)
{
string title = uscmc.Groups[1].Value;
string section = uscmc.Groups[2].Value;
string paragraph = uscmc.Groups[3].Value;
string[] ps = paragraph.Split('[', '(', ')', ' ');
int psi = 0; while (psi < ps.Length - 1 && ps[psi] == "")
{
psi++;
}
int pse = ps.Length - 1; while (pse > 0 && ps[pse] == "")
{
pse--;
}
if (ps.Length != 0)
{
paragraph = "_" + String.Join("_", ps, psi, pse - psi + 1);
}
Table table = Util.Database.DBSelect("billusc", "session, type, number",
new Database.SpecEQ("session", session),
new Database.OrSpec(
new Database.SpecEQ("ref", title + "_" + section + paragraph),
new Database.SpecStartsWith("ref", title + "_" + section + paragraph + "_")));
foreach (TableRow bill in table)
{
search_method = "search by U.S.C. section";
scores[(int)bill["session"] + (string)bill["type"] + (int)bill["number"]] = 1.0F;
specs.Add(new Database.AndSpec(
new Database.SpecEQ("session", (int)bill["session"]),
new Database.SpecEQ("type", (string)bill["type"]),
new Database.SpecEQ("number", (int)bill["number"])));
}
}
int total_count = -1;
if (specs.Count == 0)
{
if (q != null && q.Trim() != "")
{
BooleanQuery query1 = new BooleanQuery();
query.Add(query1, BooleanClause.Occur.MUST);
try {
/*if (!q.StartsWith("-")) {
* PhraseQuery pq = new PhraseQuery();
* pq.Add( new Term("shorttitles", q) );
* pq.SetBoost((float)4);
* query1.Add(pq, false, false);
* }*/
Query query_titles2 = new QueryParser("shorttitles", new StandardAnalyzer()).Parse(q);
query_titles2.SetBoost((float)3);
query1.Add(query_titles2, BooleanClause.Occur.SHOULD);
Query query_titles1 = new QueryParser("officialtitles", new StandardAnalyzer()).Parse(q);
query_titles1.SetBoost((float)2);
query1.Add(query_titles1, BooleanClause.Occur.SHOULD);
Query query_summary = new QueryParser("summary", new StandardAnalyzer()).Parse(q);
query1.Add(query_summary, BooleanClause.Occur.SHOULD);
Query query_text = new QueryParser("fulltext", new StandardAnalyzer()).Parse(q);
query1.Add(query_text, BooleanClause.Occur.SHOULD);
} catch (Exception e) {
return(no_results);
}
}
string chamber = HttpContext.Current.Request["chamber"];
string[] status = HttpContext.Current.Request["status"] == null ? null : HttpContext.Current.Request["status"].Split(',');
string sponsor = HttpContext.Current.Request["sponsor"];
string cosponsor = HttpContext.Current.Request["cosponsor"];
if (chamber != null && (chamber == "s" || chamber == "h"))
{
query.Add(new WildcardQuery(new Term("type", chamber + "*")), BooleanClause.Occur.MUST);
}
if (status != null && status[0] != "")
{
List <Term> terms = new List <Term>();
foreach (string s in status)
{
terms.Add(new Term("state", s));
}
MultiPhraseQuery mpq = new MultiPhraseQuery();
mpq.Add(terms.ToArray());
query.Add(mpq, BooleanClause.Occur.MUST);
}
if (sponsor != null && sponsor != "")
{
query.Add(new TermQuery(new Term("sponsor", sponsor)), BooleanClause.Occur.MUST);
}
if (cosponsor != null && cosponsor != "")
{
query.Add(new TermQuery(new Term("cosponsor", cosponsor)), BooleanClause.Occur.MUST);
}
IndexSearcher searcher = new IndexSearcher(Util.DataPath + Path.DirectorySeparatorChar + session + Path.DirectorySeparatorChar + "index.bills.lucene");
Sort sort = null;
if (HttpContext.Current.Request["sort"] != null && HttpContext.Current.Request["sort"] == "introduced")
{
sort = new Sort(new SortField("introduced", SortField.STRING, true));
}
if (HttpContext.Current.Request["sort"] != null && HttpContext.Current.Request["sort"] == "lastaction")
{
sort = new Sort(new SortField("lastaction", SortField.STRING, true));
}
Hits hits = searcher.Search(query, sort == null ? new Sort() : sort);
int end = hits.Length();
if (start + count < end)
{
end = start + count;
}
total_count = hits.Length();
for (int i = start; i < end; i++)
{
Document doc = hits.Doc(i);
string billsession = doc.Get("session");
string billtype = doc.Get("type");
string billnumber = doc.Get("number");
int istatus = (int)EnumsConv.BillStatusFromString(doc.Get("status"));
float score;
if (sort == null) // readjust the score based on status
{
score = hits.Score(i) + istatus / (float)8 * (float).2;
}
else // keep order from Lucene
{
score = -i;
}
scores[billsession + billtype + billnumber] = score;
specs.Add(new Database.AndSpec(
new Database.SpecEQ("session", billsession),
new Database.SpecEQ("type", billtype),
new Database.SpecEQ("number", billnumber)));
}
if (HttpContext.Current.Request["sort"] != null && HttpContext.Current.Request["sort"] == "hits" && specs.Count > 0)
{
Table hitsinfo = Util.Database.DBSelect("billhits", "*",
Database.OrSpec.New((Database.Spec[])specs.ToArray(typeof(Database.Spec))));
foreach (TableRow billhits in hitsinfo)
{
scores["" + billhits["session"] + billhits["type"] + billhits["number"]] = (float)(int)billhits["hits1"];
}
}
}
if (specs.Count == 0)
{
return(no_results);
}
Table billinfo = Util.Database.DBSelect("billstatus", "*",
Database.OrSpec.New((Database.Spec[])specs.ToArray(typeof(Database.Spec))));
if (total_count == -1)
{
total_count = billinfo.Rows;
}
ArrayList ret = new ArrayList();
foreach (TableRow r in billinfo)
{
ret.Add(r);
}
BillHitComparer bhc = new BillHitComparer();
bhc.scores = scores;
ret.Sort(bhc);
Hashtable ret2 = new Hashtable();
ret2["count"] = total_count;
ret2["method"] = search_method;
ret2["results"] = ret;
return(ret2);
}
//TODO: The last param, Cache isn't used. Remove it and update dependant projects. (Version 1.3)
public static SearchResults <Document> GetDocuments(QueryParser defaultQueryParser, QueryParser customQueryParser, IndexSearcher indexSearcher, string query, int pageNumber, int pageSize, bool shouldDocumentsBeClustered, string sort, int maximumNumberOfDocumentsToScore, Cache cache)
{
Query query2 = customQueryParser.Parse(query);
Hits hits = null;
if (!string.IsNullOrEmpty(sort))
{
string[] sorts = sort.ToLower().Split(",".ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
List <SortField> sortFields = new List <SortField>(sorts.Length / 2);
for (int i = 0; i < sorts.Length; i++)
{
if (sorts[i].Split(' ')[1] == "asc")
{
sortFields.Add(new SortField(sorts[i].Split(' ')[0], false));
}
else
{
sortFields.Add(new SortField(sorts[i].Split(' ')[0], true));
}
}
hits = indexSearcher.Search(query2, new Sort(sortFields.ToArray()));
}
else
{
hits = indexSearcher.Search(query2);
}
SearchResults <Document> searchResults = new SearchResults <Document>();
searchResults.Documents = new List <Document>();
searchResults.Query = query2;
if (hits.Length() != 0)
{
Dictionary <string, string> domains = new Dictionary <string, string>();
PriorityQueue <Document> priorityQueue = new PriorityQueue <Document>();
//Get the Hits!!!
//TODO: Optimize this!!! (Version 1.3)
for (int j = 0; j < hits.Length() && searchResults.Documents.Count < maximumNumberOfDocumentsToScore && priorityQueue.Count < maximumNumberOfDocumentsToScore; j++)
{
Document document = hits.Doc(j);
float score = hits.Score(j);
document.Add(new Field("documentid", j.ToString(), Field.Store.YES, Field.Index.NO));
document.Add(new Field("relevancyscore", score.ToString(), Field.Store.YES, Field.Index.NO));
if (!string.IsNullOrEmpty(sort))
{
if (shouldDocumentsBeClustered)
{
if (document.GetField("domain") != null)
{
string domain = document.GetField("domain").StringValue();
if (!domains.ContainsKey(domain))
{
domains.Add(domain, null);
if (searchResults.Documents.Count < pageSize && j >= (pageNumber * pageSize) - pageSize)
{
searchResults.Documents.Add(document);
}
}
}
}
else
{
if (searchResults.Documents.Count < pageSize && j >= (pageNumber * pageSize) - pageSize)
{
searchResults.Documents.Add(document);
}
}
}
else
{
priorityQueue.Enqueue(document, score * double.Parse(document.GetField("strength").StringValue()));
}
}
if (string.IsNullOrEmpty(sort))
{
for (int i = 0; i < hits.Length() && priorityQueue.Count != 0; i++)
{
Document document = priorityQueue.Dequeue();
if (shouldDocumentsBeClustered)
{
if (document.GetField("domain") != null)
{
string domain = document.GetField("domain").StringValue();
if (!domains.ContainsKey(domain))
{
domains.Add(domain, null);
if (searchResults.Documents.Count < pageSize && i >= (pageNumber * pageSize) - pageSize)
{
searchResults.Documents.Add(document);
}
}
else
{
i--;
}
}
}
else
{
if (searchResults.Documents.Count < pageSize && i >= (pageNumber * pageSize) - pageSize)
{
searchResults.Documents.Add(document);
}
}
}
}
if (shouldDocumentsBeClustered)
{
searchResults.TotalNumberOfHits = domains.Count;
}
else
{
searchResults.TotalNumberOfHits = hits.Length();
}
}
return(searchResults);
}
private void DoNormalSearch(int offset, int limit, NamespaceFilter namespaces)
{
string encsearchterm = String.Format("title:({0})^4 OR ({1})", searchterm, searchterm);
DateTime now = DateTime.UtcNow;
Query query;
/* If we fail to parse the query, it's probably due to illegal
* use of metacharacters, so we escape them all and try again.
*/
try {
query = state.Parse(encsearchterm);
} catch (Exception e) {
string escaped = "";
for (int i = 0; i < searchterm.Length; ++i)
{
escaped += "\\" + searchterm[i];
}
encsearchterm = "title:(" + escaped + ")^4 OR (" + escaped + ")";
try {
query = state.Parse(encsearchterm);
} catch (Exception e2) {
log.Error("Problem parsing search term: " + e2.Message + "\n" + e2.StackTrace);
return;
}
}
Hits hits = null;
try {
hits = state.Searcher.Search(query);
} catch (Exception e) {
log.Error("Error searching: " + e.Message + "\n" + e.StackTrace);
return;
}
SendHeaders(200, "OK");
int numhits = hits.Length();
LogRequest(searchterm, query, numhits, now);
SendOutputLine(numhits.ToString());
if (numhits == 0)
{
string spelfix = MakeSpelFix(searchterm);
SendOutputLine(HttpUtility.UrlEncode(spelfix, Encoding.UTF8));
}
else
{
// Lucene's filters seem to want to run over the entire
// document set, which is really slow. We'll do namespace
// checks as we go along, and stop once we've seen enough.
//
// The good side is that we can return the first N documents
// pretty quickly. The bad side is that the total hits
// number we return is bogus: it's for all namespaces combined.
int matches = 0;
//string lastMatch = "";
for (int i = 0; i < numhits && i < maxoffset; i++)
{
Document doc = hits.Doc(i);
string pageNamespace = doc.Get("namespace");
if (namespaces.filter(pageNamespace))
{
if (matches++ < offset)
{
continue;
}
string title = doc.Get("title");
/*
* string squish = pageNamespace+":"+title;
* if (lastMatch.Equals(squish)) {
* // skip duplicate results due to indexing bugs
* maxoffset++;
* matches--;
* continue;
* }
* lastMatch = squish;
*/
float score = hits.Score(i);
SendResultLine(score, pageNamespace, title);
if (matches >= (limit + offset))
{
break;
}
}
}
}
}
public static void Main(String[] a)
{
String indexName = "localhost_index";
String fn = "c:/Program Files/Apache Group/Apache/htdocs/manual/vhosts/index.html.en";
Uri url = null;
for (int i = 0; i < a.Length; i++)
{
if (a[i].Equals("-i"))
{
indexName = a[++i];
}
else if (a[i].Equals("-f"))
{
fn = a[++i];
}
else if (a[i].Equals("-url"))
{
url = new Uri(a[++i]);
}
}
StreamWriter temp_writer;
temp_writer = new StreamWriter(Console.OpenStandardOutput(), Console.Out.Encoding);
temp_writer.AutoFlush = true;
StreamWriter o = temp_writer;
IndexReader r = IndexReader.Open(indexName);
o.WriteLine("Open index " + indexName + " which has " + r.NumDocs() + " docs");
LuceneMoreLikeThis mlt = new LuceneMoreLikeThis(r);
o.WriteLine("Query generation parameters:");
o.WriteLine(mlt.DescribeParams());
o.WriteLine();
Query query = null;
if (url != null)
{
o.WriteLine("Parsing URL: " + url);
query = mlt.Like(url);
}
else if (fn != null)
{
o.WriteLine("Parsing file: " + fn);
query = mlt.Like(new FileInfo(fn));
}
o.WriteLine("q: " + query);
o.WriteLine();
IndexSearcher searcher = new IndexSearcher(indexName);
Hits hits = searcher.Search(query);
int len = hits.Length();
o.WriteLine("found: " + len + " documents matching");
o.WriteLine();
for (int i = 0; i < Math.Min(25, len); i++)
{
Document d = hits.Doc(i);
String summary = d.Get("summary");
o.WriteLine("score : " + hits.Score(i));
o.WriteLine("url : " + d.Get("url"));
o.WriteLine("\ttitle : " + d.Get("title"));
if (summary != null)
{
o.WriteLine("\tsummary: " + d.Get("summary"));
}
o.WriteLine();
}
}