def removeWordIdsForDocId(self, docid, wids):
for wid in wids:
try:
if isinstance(self._forward_idx[wid], int):
del self._forward_idx[wid]
else:
self._forward_idx[wid].remove(docid)
if len(self._forward_idx[wid])==0:
del self._forward_idx[wid]
except KeyError: pass
old_wids = decode(self._reverse_idx[docid])
new_wids = [w for w in old_wids if w not in wids]
self._reverse_idx[docid] = encode(new_wids)
self._frequencies[docid] = self._get_frequencies(new_wids)
def removeDocument(self, docid):
""" remove a document and all its words from the storage """
try:
wids = decode(self._reverse_idx[docid])
except KeyError: return
del self._reverse_idx[docid]
del self._frequencies[docid]
for wid in wids:
try:
if isinstance(self._forward_idx[wid], int):
del self._forward_idx[wid]
else:
self._forward_idx[wid].remove(docid)
except KeyError: pass
try:
if len(self._forward_idx[wid]) == 0:
del self._forward_idx[wid]
except KeyError: pass
self._length.change(-1)
def getWordIdsForDocId(self, docid):
""" return a sequence of words contained in the document with
ID 'docId'
"""
return decode(self._reverse_idx[docid])