def term_info(self, fieldname, text):
term = (fieldname, text)
# Get the term infos for the sub-readers containing the term
tis = [(r.term_info(fieldname, text), offset)
for r, offset in zip_(self.readers, self.doc_offsets)
if term in r]
# If only one reader had the term, return its terminfo with the offset
# added
if not tis:
raise TermNotFound(term)
elif len(tis) == 1:
ti, offset = tis[0]
ti._minid += offset
ti._maxid += offset
return ti
# Combine the various statistics
w = sum(ti.weight() for ti, _ in tis)
df = sum(ti.doc_frequency() for ti, _ in tis)
ml = min(ti.min_length() for ti, _ in tis)
xl = max(ti.max_length() for ti, _ in tis)
xw = max(ti.max_weight() for ti, _ in tis)
# For min and max ID, we need to add the doc offsets
mid = min(ti.min_id() + offset for ti, offset in tis)
xid = max(ti.max_id() + offset for ti, offset in tis)
return TermInfo(w, df, ml, xl, xw, mid, xid)
def term_info(self, fieldname, text):
term = (fieldname, text)
# Get the term infos for the sub-readers containing the term
tis = [(r.term_info(fieldname, text), offset) for r, offset
in zip_(self.readers, self.doc_offsets) if term in r]
# If only one reader had the term, return its terminfo with the offset
# added
if not tis:
raise TermNotFound(term)
elif len(tis) == 1:
ti, offset = tis[0]
ti._minid += offset
ti._maxid += offset
return ti
# Combine the various statistics
w = sum(ti.weight() for ti, _ in tis)
df = sum(ti.doc_frequency() for ti, _ in tis)
ml = min(ti.min_length() for ti, _ in tis)
xl = max(ti.max_length() for ti, _ in tis)
xw = max(ti.max_weight() for ti, _ in tis)
# For min and max ID, we need to add the doc offsets
mid = min(ti.min_id() + offset for ti, offset in tis)
xid = max(ti.max_id() + offset for ti, offset in tis)
return TermInfo(w, df, ml, xl, xw, mid, xid)
def vector(self, docnum, fieldname):
if fieldname not in self.schema:
raise TermNotFound("No field %r" % fieldname)
vformat = self.schema[fieldname].vector
if not vformat:
raise Exception("No vectors are stored for field %r" % fieldname)
vformat = self.schema[fieldname].vector
ids, weights, values = zip_(*self.vectors[docnum, fieldname])
return ListMatcher(ids, weights, values, format=vformat)
def term_info(self, fieldname, text):
term = (fieldname, text)
# Get the term infos for the sub-readers containing the term
tis = [(r.term_info(fieldname, text), offset) for r, offset
in zip_(self.readers, self.doc_offsets) if term in r]
# If only one reader had the term, return its terminfo with the offset
# added
if not tis:
raise TermNotFound(term)
return combine_terminfos(tis)
def term_info(self, fieldname, text):
term = (fieldname, text)
# Get the term infos for the sub-readers containing the term
tis = [(r.term_info(fieldname, text), offset) for r, offset
in zip_(self.readers, self.doc_offsets) if term in r]
# If only one reader had the term, return its terminfo with the offset
# added
if not tis:
raise TermNotFound(term)
return combine_terminfos(tis)
def postings(self, fieldname, text, scorer=None):
self._test_field(fieldname)
try:
terminfo = self.term_info(fieldname, text)
except KeyError:
raise TermNotFound((fieldname, text))
format = self.schema[fieldname].format
postings = self.invindex[fieldname][text]
excludeset = self.deleted
if excludeset:
postings = [x for x in postings if x[0] not in excludeset]
if not postings:
return NullMatcher()
ids, weights, values = zip_(*postings)
lm = ListMatcher(ids, weights, values, format=format, scorer=scorer,
term=(fieldname, text), terminfo=terminfo)
return lm
def leaf_readers(self):
return zip_(self.readers, self.doc_offsets)
def leaf_readers(self):
return zip_(self.readers, self.doc_offsets)
