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
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()
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()
