def __init__(self, lexicon):
BaseIndex.__init__(self, lexicon)
# ._wordinfo for Okapi is
# wid -> {docid -> frequency}; t -> D -> f(D, t)
# ._docweight for Okapi is
# docid -> # of words in the doc
# This is just len(self._docwords[docid]), but _docwords is stored
# in compressed form, so uncompressing it just to count the list
# length would be ridiculously expensive.
# sum(self._docweight.values()), the total # of words in all docs
# This is a long for "better safe than sorry" reasons. It isn't
# used often enough that speed should matter.
self._totaldoclen = 0L
def __init__(self, lexicon):
BaseIndex.__init__(self, lexicon)
# ._wordinfo for Okapi is
# wid -> {docid -> frequency}; t -> D -> f(D, t)
# ._docweight for Okapi is
# docid -> # of words in the doc
# This is just len(self._docwords[docid]), but _docwords is stored
# in compressed form, so uncompressing it just to count the list
# length would be ridiculously expensive.
# sum(self._docweight.values()), the total # of words in all docs
# This is a long for "better safe than sorry" reasons. It isn't
# used often enough that speed should matter.
# Use a BTree.Length.Length object to avoid concurrent write conflicts
self._totaldoclen = Length(0L)
def __init__(self, lexicon):
BaseIndex.__init__(self, lexicon)
def __init__(self, lexicon):
BaseIndex.__init__(self, lexicon)
def unindex_doc(self, docid):
self._change_doc_len(-self._docweight[docid])
BaseIndex.unindex_doc(self, docid)
def _reindex_doc(self, docid, text):
self._change_doc_len(-self._docweight[docid])
return BaseIndex._reindex_doc(self, docid, text)
def index_doc(self, docid, text):
count = BaseIndex.index_doc(self, docid, text)
self._change_doc_len(count)
return count
def unindex_doc(self, docid):
self._change_doc_len(-self._docweight[docid])
BaseIndex.unindex_doc(self, docid)
def _reindex_doc(self, docid, text):
self._change_doc_len(-self._docweight[docid])
return BaseIndex._reindex_doc(self, docid, text)
def index_doc(self, docid, text):
count = BaseIndex.index_doc(self, docid, text)
self._change_doc_len(count)
return count
def unindex_doc(self, docid):
self._totaldoclen -= self._docweight[docid]
BaseIndex.unindex_doc(self, docid)
def _reindex_doc(self, docid, text):
self._totaldoclen -= self._docweight[docid]
return BaseIndex._reindex_doc(self, docid, text)
def index_doc(self, docid, text):
count = BaseIndex.index_doc(self, docid, text)
self._totaldoclen += count
return count
