def doQuery(query, start, nb_results):
parser = QueryParser("text", StandardAnalyzer())
parser.setDefaultOperator(QueryParser.Operator.AND)
query = parser.parse(query)
hits = searcher.search(query)
return formatResultsPlain(query, hits, nb_results, start)
def getIndexWriter(self):
writer = IndexWriter(
DbDirectory(self.store.txn, self._db, self.store._blocks._db,
self._flags), StandardAnalyzer(), False)
writer.setUseCompoundFile(False)
return writer
def open(self, name, txn, **kwds):
super(IndexContainer, self).open(name, txn, **kwds)
if kwds.get('create', False):
directory = DbDirectory(txn, self._db, self.store._blocks._db,
self._flags)
indexWriter = IndexWriter(directory, StandardAnalyzer(), True)
indexWriter.close()
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 doQuery(searcher, flds, query, start, nb_results):
parser = QueryParser("text", StandardAnalyzer())
parser.setDefaultOperator(QueryParser.Operator.AND)
query = parser.parse(query)
hits = searcher.search(query)
formatResultsTable(query, flds, hits, start, nb_results)
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()
#!/usr/bin/env python2.4
from mailbox import UnixMailbox
from PyLucene import StandardAnalyzer, FSDirectory, IndexWriter
from email import EmailDoc
store = FSDirectory.getDirectory('chipy-index', True)
writer = IndexWriter(store, StandardAnalyzer(), True)
mailbox = UnixMailbox(open('chipy.mbox'))
while True:
msg = mailbox.next()
if msg == None: break
writer.addDocument(EmailDoc(msg))
writer.close()
def __init__(self, indexPath, batchMode=False, analyzer=None):
self.batchMode = batchMode
self.indexPath = indexPath
self.analyzer = analyzer or StandardAnalyzer()
#!/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
Field.Index.UN_TOKENIZED))
doc.add(
Field("pmid", pmid, Field.Store.YES, Field.Index.UN_TOKENIZED))
doc.add(
Field("text", span_text, Field.Store.YES,
Field.Index.TOKENIZED))
addAnnotations(doc, span_id)
writer.addDocument(doc)
except Exception, e:
sys.stderr.write("error: %s pmid: %s span_id: %s\n" %
(e, pmid, span_id))
i += 2
if __name__ == '__main__':
if len(sys.argv) == 1:
print "Usage: python index_spans.py data_norm index_dir annotation_files"
else:
(data_norm, index_dir, annotation_files) = \
(sys.argv[1], sys.argv[2], sys.argv[3:])
print "Loading annotations ..."
load(annotation_files)
print "Making the index ..."
writer = IndexWriter(index_dir, StandardAnalyzer(), True)
writer.setMaxFieldLength(7 * 1000 * 1000 * 10)
indexData(data_norm)
print "Optimizing index ..."
writer.optimize()
print "Indexing complete"
writer.close()