def SearchExactAll(self, keyword):
"블로그 내용과 ID에 대해여 Exact Matching 수행"
searcher = lucene.IndexSearcher(self.store)
print("Searching for ", keyword)
k = keyword.decode('cp949').encode('utf-8')
tqBloger = lucene.TermQuery(lucene.Term("bloger", k))
tqContents = lucene.TermQuery(lucene.Term("contents", k))
qBoolean = lucene.BooleanQuery()
qBoolean.add(tqBloger, lucene.BooleanClause.Occur.SHOULD)
qBoolean.add(tqContents, lucene.BooleanClause.Occur.SHOULD)
hits = searcher.search(qBoolean)
print ("%s matching documents" % hits.length())
return self.__MakeResultFormat(hits, searcher)
def SearchPrefixContents(self, keyword):
"블로그 내용에 대하여 Prefix Matching 수행"
searcher = lucene.IndexSearcher(self.store)
print("Searching for ", keyword)
k = keyword.decode('cp949').encode('utf-8')
query = lucene.PrefixQuery( lucene.Term("contents", k) )
hits = searcher.search(query)
print ("%s matching documents" % hits.length())
return self.__MakeResultFormat(hits, searcher)
def getHitCount(self, fieldName, searchString):
reader = lucene.IndexReader.open(self.dir, True) #readOnly = True
print '%s total docs in index' % reader.numDocs()
reader.close()
searcher = lucene.IndexSearcher(self.dir, True) #readOnly = True
t = lucene.Term(fieldName, searchString)
query = lucene.TermQuery(t)
hitCount = len(searcher.search(query, 50).scoreDocs)
searcher.close()
print "%s total matching documents for %s\n---------------" \
% (hitCount, searchString)
return hitCount
def get_word_list(text, is_list=False, field_name = 'fieldname'):
if is_list:
new_text = ""
for i in text:
new_text += i + "\n"
text = new_text
lucene.initVM(lucene.CLASSPATH)
analyzer = lucene.KoreanAnalyzer();
#directory = lucene.FSDirectory.open("/tmp/testindex");
directory = lucene.RAMDirectory()
# writer
writer = lucene.IndexWriter(directory, analyzer)
doc = lucene.Document()
doc.add(lucene.Field(field_name, text, lucene.Field.Store.YES, lucene.Field.Index.ANALYZED));
writer.addDocument(doc);
writer.close();
# get all terms from all index
ireader = lucene.IndexReader.open(directory, False)
term = lucene.Term(field_name, '')
termenum = ireader.terms(term)
term = termenum.term()
i = 0
word_list = []
while term and term.field() == field_name:
i += 1
termDocs = ireader.termDocs(term)
termDocs.next()
#print "[%04d]===> <%s> " % (i, term.text())
#print term.text() + " : " + str(termDocs.freq())
word_list.append({'text': term.text(), 'freq': termDocs.freq()})
term = termenum.next() and termenum.term()
ireader.close();
directory.close();
return word_list
def handle_noargs(self, **options):
siteconfig = SiteConfiguration.objects.get_current()
# Refuse to do anything if they haven't turned on search.
if not siteconfig.get("search_enable"):
sys.stderr.write('Search is currently disabled. It must be '
'enabled in the Review Board administration '
'settings to run this command.\n')
sys.exit(1)
if not have_lucene:
sys.stderr.write('PyLucene is required to build the search index.\n')
sys.exit(1)
incremental = options.get('incremental', True)
store_dir = siteconfig.get("search_index_file")
if not os.path.exists(store_dir):
os.mkdir(store_dir)
timestamp_file = os.path.join(store_dir, 'timestamp')
timestamp = 0
if incremental:
try:
f = open(timestamp_file, 'r')
timestamp = datetime.utcfromtimestamp(int(f.read()))
f.close()
except IOError:
incremental = False
f = open(timestamp_file, 'w')
f.write('%d' % time.time())
f.close()
if lucene_is_2x:
store = lucene.FSDirectory.getDirectory(store_dir, False)
writer = lucene.IndexWriter(store, False,
lucene.StandardAnalyzer(),
not incremental)
elif lucene_is_3x:
store = lucene.FSDirectory.open(lucene.File(store_dir))
writer = lucene.IndexWriter(store,
lucene.StandardAnalyzer(lucene.Version.LUCENE_CURRENT),
not incremental,
lucene.IndexWriter.MaxFieldLength.LIMITED)
else:
assert False
status = Q(status='P') | Q(status='S')
objects = ReviewRequest.objects.filter(status)
if incremental:
query = Q(last_updated__gt=timestamp)
# FIXME: re-index based on reviews once reviews are indexed. I
# tried ORing this in, but it doesn't seem to work.
# Q(review__timestamp__gt=timestamp)
objects = objects.filter(query)
if sys.stdout.isatty():
print 'Creating Review Request Index'
totalobjs = objects.count()
i = 0
prev_pct = -1
for request in objects:
try:
# Remove the old documents from the index
if incremental:
writer.deleteDocuments(lucene.Term('id', str(request.id)))
self.index_review_request(writer, request)
if sys.stdout.isatty():
i += 1
pct = (i * 100 / totalobjs)
if pct != prev_pct:
sys.stdout.write(" [%s%%]\r" % pct)
sys.stdout.flush()
prev_pct = pct
except Exception, e:
sys.stderr.write('Error indexing ReviewRequest #%d: %s\n' % \
(request.id, e))
def testDelete(self, fieldName, searchString):
reader = lucene.IndexReader.open(self.dir, False) #readOnly = False
reader.deleteDocuments(lucene.Term(fieldName, searchString))
reader.close()