def get_coll_termvector(self, field):
""" Returns collection term vector for the given field."""
self.open_reader()
fields = MultiFields.getFields(self.reader)
if fields is not None:
terms = fields.terms(field)
if terms:
termenum = terms.iterator(None)
for bytesref in BytesRefIterator.cast_(termenum):
yield bytesref.utf8ToString(), termenum
def index_scan():
print("Scanning the index")
#pdb.set_trace()
indexPath = File("indexOut/").toPath()
indexDir = FSDirectory.open(indexPath)
reader = DirectoryReader.open(indexDir)
fields = MultiFields.getFields(reader)
for field in fields:
term = MultiFields.getTerms(reader,field)
print(field, "->" , term)
def get_coll_termvector(self, field):
""" Returns collection term vector for the given field."""
self.open_reader()
fields = MultiFields.getFields(self.reader)
if fields is not None:
terms = fields.terms(field)
if terms:
termenum = terms.iterator(None)
for bytesref in BytesRefIterator.cast_(termenum):
yield bytesref.utf8ToString(), termenum
def fieldnames(self):
indexAndTaxonomy = self._indexAndTaxonomy
fieldnames = []
fields = MultiFields.getFields(indexAndTaxonomy.searcher.getIndexReader())
if fields is None:
return fieldnames
iterator = fields.iterator()
while iterator.hasNext():
fieldnames.append(iterator.next())
return fieldnames
def getTFForField(self, field):
tfs = {}
fields = MultiFields.getFields(self.reader)
terms = fields.terms(field)
enum = BytesRefIterator.cast_(terms.iterator(None))
try:
while enum.next():
termval = TermsEnum.cast_(enum)
termString = termval.term().utf8ToString()
freq = self.reader.totalTermFreq(Term(field, termString))
tfs[termString] = freq
except:
pass
return tfs
