def __init__(self, ix: index.FileIndex, ix_reader: IndexReader):
self._ix = ix
self._reader = ix_reader
self._pop_dn = []
for dx in ix_reader.iter_docs():
self._pop_dn += [(int(dx[1]['count']), dx[0])]
self._pop_dn.sort(reverse=True)
def terms_within(self, fieldname, text, maxdist, prefix=0):
if not self.has_word_graph(fieldname):
# This reader doesn't have a graph stored, use the slow method
return IndexReader.terms_within(self, fieldname, text, maxdist,
prefix=prefix)
return dawg.within(self._graph, text, k=maxdist, prefix=prefix,
address=self._graph.root(fieldname))
def lexicon(self, fieldname):
self._test_field(fieldname)
# If a fieldcache for the field is already loaded, we already have the
# values for the field in memory, so just yield them from there
if self.fieldcache_loaded(fieldname):
return self._texts_in_fieldcache(fieldname)
else:
return IndexReader.lexicon(self, fieldname)
def lexicon(self, fieldname):
self._test_field(fieldname)
# If a fieldcache for the field is already loaded, we already have the
# values for the field in memory, so just yield them from there
if self.fieldcache_loaded(fieldname):
return self._texts_in_fieldcache(fieldname)
else:
return IndexReader.lexicon(self, fieldname)
def expand_prefix(self, fieldname, prefix):
self._test_field(fieldname)
# If a fieldcache for the field is already loaded, we already have the
# values for the field in memory, so just yield them from there
if self.fieldcache_loaded(fieldname):
return self._texts_in_fieldcache(fieldname, prefix)
else:
# Call super
return IndexReader.expand_prefix(self, fieldname, prefix)
def expand_prefix(self, fieldname, prefix):
self._test_field(fieldname)
# If a fieldcache for the field is already loaded, we already have the
# values for the field in memory, so just yield them from there
if self.fieldcache_loaded(fieldname):
return self._texts_in_fieldcache(fieldname, prefix)
else:
# Call super
return IndexReader.expand_prefix(self, fieldname, prefix)
def terms_within(self, fieldname, text, maxdist, prefix=0):
if not self.has_word_graph(fieldname):
# This reader doesn't have a graph stored, use the slow method
return IndexReader.terms_within(self,
fieldname,
text,
maxdist,
prefix=prefix)
return dawg.within(self._graph,
text,
k=maxdist,
prefix=prefix,
address=self._graph.root(fieldname))
from whoosh.reading import IndexReader
from whoosh.index import open_dir
from whoosh.qparser import QueryParser
from whoosh.lang.porter import stem
import supportingFunctions
import math
import nltk
import os
import re
from nltk.corpus import stopwords
nltk.download('stopwords')
stop_words = set(stopwords.words('english'))
ix = open_dir("indexdir_robust04_full")
IndexReader()
#xx=IndexReader.all_terms('content')
p = ix.reader()
p2 = ix.schema
print((ix.schema))
# all the words in the corpus
bytestrings = list(p.lexicon("content"))
fieldobj = ix.schema["content"]
words = [fieldobj.from_bytes(bs) for bs in p.lexicon("content")]
#print ("the words are :" , words)
# queries is a dictionary with the keys being the query numbers and the elements are the query words
queries = {}
queries_path = '/home/niloo/rb04-queries2'
with open(queries_path, 'r') as q_file:
