Python index.DirectoryReader类代码示例

 def open_reader(self):
     """Open IndexReader."""
     if self.reader is None:
         if self.use_ram:
             print "reading from ram directory ..."
             self.reader = DirectoryReader.open(self.ram_dir)
         else:
             self.reader = DirectoryReader.open(self.dir)

	def search(self, input_query=None, max_answers=10):
		''' Searches the given query in the index '''
		if input_query is None:
			return None

		base_dir = '.'
		directory = SimpleFSDirectory(File(os.path.join(base_dir, self.index_dir)))
		searcher = IndexSearcher(DirectoryReader.open(directory))
		analyzer = StandardAnalyzer(Version.LUCENE_CURRENT)
		
		
		# query = QueryParser(Version.LUCENE_CURRENT, "title", analyzer).parse(input_query)
		parser = MultiFieldQueryParser(Version.LUCENE_CURRENT, (self._posts_fields + self._answer_fields), analyzer)
		query = MultiFieldQueryParser.parse(parser, input_query)

		scoreDocs = searcher.search(query, max_answers).scoreDocs
		print "%s total matching documents." % len(scoreDocs)

		docs = []
		for scoreDoc in scoreDocs:
			doc = searcher.doc(scoreDoc.doc)
			doc_dict = dict((field.name(), field.stringValue()) for field in doc.getFields())
			docs.append(doc_dict)
			# print doc
		return docs

 def __init__(self, db_path):
     directory = SimpleFSDirectory(File(db_path))
     reader = DirectoryReader.open(directory)
     self.searcher = IndexSearcher(reader)
     self.analyzer = StandardAnalyzer(Version.LUCENE_CURRENT)
     logger.info("Loaded DB from %s with %d documents: ",
                 db_path, reader.numDocs())

	def __init__ (self):
		
		self.mDocumentDirectory = "/home/hnguyen/Projects/CLIFinder/operations.sub"
		self.mIndexDirectory = "/home/hnguyen/Projects/CLIFinder/cli.index"

		self.mIndexReader = None
		if os.path.isdir(self.mIndexDirectory) and self.mIndexReader == None:
			directory = SimpleFSDirectory(File(self.mIndexDirectory))
			self.mIndexReader = DirectoryReader.open(directory)

		
		############################### IndexingEngine Settings ######################################
		self.mSimilarity = DecreaseLengthNormSimilarity()
		self.mOpenMode = IndexWriterConfig.OpenMode.CREATE
		##############################################################################################
				
		self.mIsDebug = False

		if self.mIsDebug:
		############################### Setting up loggers ###########################################
			self.mIndexingLogPath = "/home/hnguyen/Projects/CLIFinder/logs/indexing.log"
			self.mSearchingLogPath = "/home/hnguyen/Projects/CLIFinder/logs/searching.log"
	
			self.mIndexingLogger = LoggingEngine(self.mIndexingLogPath, "IndexingLogger", Queue.Queue())
			self.mSearchingLogger = LoggingEngine(self.mSearchingLogPath, "SearchingLogger", Queue.Queue())

			self.mIndexingLogger.start()
			self.mSearchingLogger.start()
			atexit.register(self.clear)

    def search(self, field, text):
        """
        search text within indexed data

        input:
            field   fieldname of the value that will be indexed
            text    text to search

        output:
            hits    return a list of hits

        """
        results = []
        idx_reader = DirectoryReader.open(self.directory)
        idx_searcher = IndexSearcher(idx_reader)

        # parse query
        parser = AnalyzingQueryParser(Version.LUCENE_CURRENT, field, self.analyser)
        query = parser.parse(text)

        # search
        hits = idx_searcher.search(query, 1000).scoreDocs.tolist()
        for hit in hits:
            doc = idx_searcher.doc(hit.doc)
            score = hit.score
            title = doc.get(field)
            url = doc.get("url")
            results.append((score, url, title))

        return results

def buscar(indexDir, args,options = None):
    #lucene.initVM(vmargs=['-Djava.awt.headless=true'])
    
    fsDir = SimpleFSDirectory(File(indexDir))
    #print fsDir
    
    #Criando buscador baseado no diretorio dos indices passados pelo usuario
    searcher = IndexSearcher(DirectoryReader.open(fsDir))
    
    #Analizador para filtro dos tokens 
    analyzer = StandardAnalyzer(Version.LUCENE_CURRENT)
    #print analyzer

    #Criando um QueryParser usando por padrao contents
    #Variavel com as restricoes da busca
    parser = QueryParser(Version.LUCENE_CURRENT, "keywords", analyzer)
    #print parser

    parser.setDefaultOperator(QueryParser.Operator.AND)

    #print args
    #Juntando parametros passados com o valor do mesmo
    command = ' +'.join(args)
    #print command

    query = parser.parse(command)
    print query

    #Criando um JArray com resultado da consulta
    return searcher.search(query, 200).scoreDocs

    def query(self, data):
        if self.fil.exists():
            searcher = IndexSearcher(DirectoryReader.open(self.d))
            query = QueryParser(
                Version.LUCENE_30,
                "id",
                self.analyzer).parse(
                data['query'])
            hits = searcher.search(query, 100000)

            results = {}

            results['totalHits'] = hits.totalHits
            results['hits'] = {}

            for hit in hits.scoreDocs:
                record = {}
                doc = searcher.doc(hit.doc)
                fields = doc.getFields()
                record['score'] = hit.score
                for field in fields:
                    if field.name() != "id":
                        record[field.name()] = field.stringValue()
                results['hits'][doc.get('id')] = record

            searcher.getIndexReader().close()
            return results

    def __init__(self, index_path, method, logger=None, use_default_similarity=False):
        self.index_path=index_path
        directory = SimpleFSDirectory(File(self.index_path))
        self.analyzer = StandardAnalyzer(LuceneVersion.LUCENE_CURRENT)
        self.reader=DirectoryReader.open(directory)
        self.searcher = IndexSearcher(self.reader)

        # uncomment one of these lines to change the type of parser, query and weight used
        if use_default_similarity:
            self.query_parser=QueryParser
        else:
            self.query_parser=FieldAgnosticQueryParser

        if use_default_similarity:
            similarity=DefaultSimilarity()
            self.useExplainQuery=False
        else:
            similarity=FieldAgnosticSimilarity()
            self.useExplainQuery=True
        # by default, FieldAgnosticSimilarity uses coord factor, can be disabled
##        similarity.useCoord=False

        self.searcher.setSimilarity(similarity)
        self.method=method # never used?
        self.logger=logger

	def search(self):
		''' Searches the given query in the index '''

		lucene.initVM(vmargs=['-Djava.awt.headless=true'])
		# print 'lucene', lucene.VERSION
		# base_dir = os.path.dirname(os.path.abspath('.'))
		base_dir = '.'
		directory = SimpleFSDirectory(File(os.path.join(base_dir, self.index_dir)))
		searcher = IndexSearcher(DirectoryReader.open(directory))
		analyzer = StandardAnalyzer(Version.LUCENE_CURRENT)
		

		while True:
			print
			print "Hit enter with no input to quit."
			command = raw_input("Query:")
			if command == '':
				return

			print
			print "Searching for:", command

			query = QueryParser(Version.LUCENE_CURRENT, "title",
								analyzer).parse(command)
			scoreDocs = searcher.search(query, 50).scoreDocs
			print "%s total matching documents." % len(scoreDocs)

			for scoreDoc in scoreDocs:
				doc = searcher.doc(scoreDoc.doc)
				# print 'path:', doc.get("path"), 'name:', doc.get("name")
				print doc

def search():

	lucene.initVM(vmargs=['-Djava.awt.headless=true'])
    
	args = []
	if request.method == 'POST':
		if request.form['ies']:
			args.append('+ies:'+request.form['ies'])
		if request.form['area']:
			args.append('+area:'+request.form['area'])
		if request.form['professor']:
			args.append('+professor:'+request.form['professor'])
		if request.form['conceito']:
			#args.append('m:'+request.form['conceito']+'d:'+request.form['conceito']+'f:'+request.form['conceito'])
			args.append('m:'+request.form['conceito'])
			args.append('d:'+request.form['conceito'])
			args.append('f:'+request.form['conceito'])

	table = []
	if(len(args) > 0): 
		scoreDocs = mansearch.buscar('indexer/',args)
		fsDir = SimpleFSDirectory(File(indexDir))
		searcher = IndexSearcher(DirectoryReader.open(fsDir))
		for scoreDoc in scoreDocs:
			doc = searcher.doc(scoreDoc.doc)
			table.append(dict((field.name(), field.stringValue()) for field in doc.getFields()))
	return render_template('busca.html',table = table)
	
	pass

def config():
    base_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
    directory = SimpleFSDirectory(File(os.path.join(base_dir, INDEX_DIR)))
    searcher = IndexSearcher(DirectoryReader.open(directory))
    bm25Sim = BM25Similarity(2.0,0.75) #BM25 with these default values: k1 = 1.2, b = 0.75.
    searcher.setSimilarity(bm25Sim)
    analyzer = SmartChineseAnalyzer(Version.LUCENE_CURRENT)
    return searcher,analyzer

 def search_docs(self, value, field="general_info"):
     MAX_RESULTS = 1000
     searcher = IndexSearcher(DirectoryReader.open(self.store))
     query = QueryParser(Version.LUCENE_CURRENT, field,
                         self.analyzer).parse(value)
     topDocs = searcher.search(query, MAX_RESULTS)
     
     return [searcher.doc(hit.doc) for hit in topDocs.scoreDocs]

 def _maybeReopen(self):
     if len(self._latestModifications) > 10000:
         newReader = DirectoryReader.openIfChanged(self._reader, self._writer, True)
         if not newReader is None:
             self._reader.close()
             self._reader = newReader
             self._searcher = IndexSearcher(self._reader)
             self._latestModifications.clear()

 def __init__(self,base_dir, index_dir,index_file,queryDict):
     self.baseDir = base_dir
     self.indexFile = os.path.join(index_dir,index_file)
     lucene.initVM(vmargs=['-Djava.awt.headless=true']) # uncomment when run Retrieve separately
     directory = SimpleFSDirectory(File(self.indexFile))
     searcher = IndexSearcher(DirectoryReader.open(directory))
     self.BM25(searcher,queryDict)
     del searcher

def build_corpus(n=0):
    sbcs = texeval_corpus.test_subcorpora
    sbc = sbcs[n]
    # Hack for parallelizing queries, uses one index per domain.
    directory = FSDirectory.open(File(wiki_index+'-'+sbc))
    searcher = IndexSearcher(DirectoryReader.open(directory))
    analyzer = StandardAnalyzer(Version.LUCENE_CURRENT)
    build_corpus_from_terms_with_wiki(sbc, searcher, analyzer)