def main(argv):
# defaults
query = ''
start = 0
nb_results = 10
try:
opts, args = getopt.getopt(argv, "i:q:s:r:", \
["lucene_index=", "query=", "start=", "nb_results="])
except getopt.GetoptError:
usage()
sys.exit(2)
if not opts:
usage()
sys.exit()
for opt, arg in opts:
if opt in ("-i", "--lucene_index"):
fsDir = FSDirectory.getDirectory(arg, False)
searcher = IndexSearcher(fsDir)
elif opt in ("-q", "--query"):
query = arg
elif opt in ("-s", "--start"):
start = int(arg)
elif opt in ("-r", "--nb_results"):
nb_results = int(arg)
doQuery(searcher, query, start, nb_results)
def searchDocuments(self, version, query, attribute=None):
directory = DbDirectory(self.store.txn, self._db,
self.store._blocks._db, self._flags)
searcher = IndexSearcher(directory)
query = QueryParser.parse(query, "contents", StandardAnalyzer())
docs = {}
for i, doc in searcher.search(query):
ver = long(doc['version'])
if ver <= version:
uuid = UUID(doc['owner'])
dv = docs.get(uuid, None)
if dv is None or dv[0] < ver:
docAttr = doc['attribute']
if attribute is None or attribute == docAttr:
docs[uuid] = (ver, docAttr)
searcher.close()
return docs
def _getdoc(self, filename, args):
doc = "0 |"
m = self.__class__.p.search(args)
if m and filename == '/search':
# doc = doQuery(m.group(1).split('+'), int(m.group(2)), int(m.group(3)))
doc = doQuery(urllib.unquote(m.group(1)), int(m.group(2)), int(m.group(3)))
return doc
def do_GET(self):
url = urlparse.urlsplit(self.path)
doc = self._getdoc(url[2], url[3])
self._writeheaders(doc)
self.wfile.write(doc)
class SearchServer(HTTPServer):
allow_reuse_address = 1
if __name__ == '__main__':
if len(sys.argv) != 2:
print "Usage: python lucene_server.py index_dir"
else:
indexDir = sys.argv[1]
fsDir = FSDirectory.getDirectory(indexDir, False)
searcher = IndexSearcher(fsDir)
serveraddr = ('', SERVER_PORT)
srvr = SearchServer(serveraddr, SearchRequestHandler)
print "Ready to serve search queries"
srvr.serve_forever()
#!/usr/bin/python
from sys import argv
from PyLucene import FSDirectory, IndexSearcher, TermQuery, Term
id = argv[1].strip()
directory = FSDirectory.getDirectory( 'chipy-index', False )
searcher = IndexSearcher( directory )
query = TermQuery( Term( 'id', id ) )
hits = searcher.search( query )
doc = hits.doc(0)
print "ID: %s" % doc.getField('id').stringValue()
print "From: %s" % doc.getField('from').stringValue()
print "Subject: %s" % doc.getField('subject').stringValue()
print "Date: %s" % doc.getField('date').stringValue()
print doc.getField('body').stringValue()
print
results = []
for i, doc in hits:
results.append([doc.get("name"), doc.get("owner").encode('gbk'), doc.get("title").encode('gbk')])
# sort result
results.sort(lambda x,y: cmp(x[0],y[0]))
for name,owner,title in results:
print name, owner, title
def test_fixture():
global BOARDSPATH
BOARDSPATH = './'
if __name__ == '__main__':
#test_fixture()
board = sys.argv[1]
querystr = sys.argv[2].decode('gbk').strip()
path = BOARDSPATH+board+'/'+RECENT_INDEX
if not os.path.exists(path) or len(querystr) == 0:
sys.exit(-1)
directory = FSDirectory.getDirectory(path, False)
searcher = IndexSearcher(directory)
analyzer = StandardAnalyzer()
run(searcher, analyzer, querystr)
searcher.close()
'path' and 'name' fields for each of the hits it finds in the index. Note that
search.close() is currently commented out because it causes a stack overflow in
some cases.
"""
def run(searcher, analyzer):
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("contents", analyzer).parse(command)
hits = searcher.search(query)
print "%s total matching documents" % hits.length()
for i, doc in hits:
print 'path:', doc.get("path"), 'name:', doc.get("name"), 100*hits.score(i)
if __name__ == '__main__':
STORE_DIR = "index"
print 'PyLucene', VERSION, 'Lucene', LUCENE_VERSION
directory = FSDirectory.getDirectory(STORE_DIR, False)
searcher = IndexSearcher(directory)
analyzer = StandardAnalyzer()
run(searcher, analyzer)
searcher.close()
def getIndexSearcher(self):
# if not IndexSupport.searchers.has_key(self.indexPath) or not IndexSupport.searchers[self.indexPath].getIndexReader().isCurrent():
# IndexSupport.searchers[self.indexPath] = IndexSearcher(self.getIndexReader())
# return IndexSupport.searchers[self.indexPath]
return IndexSearcher(self.getIndexReader())
#!/usr/bin/env python2.4
from sys import argv
from PyLucene import FSDirectory, IndexSearcher, QueryParser, StandardAnalyzer
string = argv[1].strip()
directory = FSDirectory.getDirectory( 'chipy-index', False )
searcher = IndexSearcher( directory )
query = QueryParser.parse( string, 'all', StandardAnalyzer() )
hits = searcher.search( query )
for i in range(0,hits.length()):
doc = hits.doc(i)
print "ID: %s" % doc.getField('id').stringValue()
print "From: %s" % doc.getField('from').stringValue()
print "Subject: %s" % doc.getField('subject').stringValue()
print "Date: %s" % doc.getField('date').stringValue()
print
def _prepareSearcher(self):
# TODO: test index.currentVersion to update searcher,
# allowing concurrence in search and write
if self._searcher:
self._searcher.close()
self._searcher = IndexSearcher(self._directory)
def __init__(self, directory, shaManager):
self._directory = directory
self._searcher = IndexSearcher(self._directory)
self._shaManager = shaManager
class SearchAppService:
def __init__(self, directory, shaManager):
self._directory = directory
self._searcher = IndexSearcher(self._directory)
self._shaManager = shaManager
def _prepareSearcher(self):
# TODO: test index.currentVersion to update searcher,
# allowing concurrence in search and write
if self._searcher:
self._searcher.close()
self._searcher = IndexSearcher(self._directory)
def search(self, query):
print "Searching ", query
import re
if re.match("^[a-f0-9]{40}$", query):
return self.searchBySHA(query)
elif query.startswith("http://"):
return self.searchByURI(query)
elif '@' in query:
if not query.startswith('mailto'):
query = "mailto:" + query
return self.searchBySHA(sha.new(query).hexdigest())
else:
return self.searchByName(query)
def searchByURI(self, query):
#print "Searching by URI"
query = "\"" + query + "\""
parser = QueryParser("uri", KeywordAnalyzer())
return self._performSearch(parser, query)
def searchByName(self, query):
#print "Preguntando por nombre"
parser = QueryParser("name", StandardAnalyzer())
return self._performSearch(parser, query)
def searchBySHA(self, query):
print "Preguntando por SHA"
uris = self._shaManager.searchSha(query)
if uris == None or len(uris) == 0 :
return []
def rebuildFoafs(uri):
foaf = self.searchByURI(uri)
if foaf == []:
return [{'sha':query, 'uri':uri}]
else:
return foaf
return reduce(operator.concat, map(rebuildFoafs, uris))
def _performSearch(self, queryParser,query):
q = queryParser.parse(query)
self._prepareSearcher()
hits = self._searcher.search(q)
result = []
for i in range(0, hits.length()):
d = hits.doc(i)
result.append(FoafDocumentFactory.getFOAFFromDocument(d))
return result
def close(self):
self._shaManager.close()
