klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-05 13:21:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Init word filter dictionary with default value as set to simplify code

Browse Source
This commit is contained in:
Debanjum Singh Solanky
2022-09-10 12:16:53 +03:00
parent 4d776d9c7a
commit e00bb53336
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/search_filter/word_filter.py
View File

@@ -3,6 +3,7 @@ import re
import time import time
import pickle import pickle
import logging import logging
from collections import defaultdict
# Internal Packages # Internal Packages
from src.search_filter.base_filter import BaseFilter from src.search_filter.base_filter import BaseFilter
@@ -37,19 +38,18 @@ class WordFilter(BaseFilter):
start = time.time() start = time.time()
self.cache = {} # Clear cache on (re-)generating entries_by_word_set self.cache = {} # Clear cache on (re-)generating entries_by_word_set
entry_splitter = r',|\.| |\]|\[\(|\)|\{|\}|\t|\n|\:' entry_splitter = r',|\.| |\]|\[\(|\)|\{|\}|\t|\n|\:'
self.word_to_entry_index = defaultdict(set)
# Create map of words to entries they exist in # Create map of words to entries they exist in
for entry_index, entry in enumerate(entries): for entry_index, entry in enumerate(entries):
for word in re.split(entry_splitter, entry[self.entry_key].lower()): for word in re.split(entry_splitter, entry[self.entry_key].lower()):
if word == '': if word == '':
continue continue
if word not in self.word_to_entry_index:
self.word_to_entry_index[word] = set()
self.word_to_entry_index[word].add(entry_index) self.word_to_entry_index[word].add(entry_index)
with self.filter_file.open('wb') as f: with self.filter_file.open('wb') as f:
pickle.dump(self.word_to_entry_index, f) pickle.dump(self.word_to_entry_index, f)
end = time.time() end = time.time()
logger.debug(f"Index {self.search_type} for word filter to {self.filter_file}: {end - start} seconds") logger.debug(f"Indexed {len(self.word_to_entry_index)} words of {self.search_type} type for word filter to {self.filter_file}: {end - start} seconds")
return self.word_to_entry_index return self.word_to_entry_index