klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-09 13:25:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Extract hash func for incremental text indexing into separate method

Browse Source
This commit is contained in:
Debanjum Singh Solanky
2022-10-26 12:13:46 +05:30
parent 0de2ff9c97
commit a9cfd8b800
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/processor/text_to_jsonl.py
View File

@@ -3,6 +3,7 @@ from abc import ABC, abstractmethod
import hashlib import hashlib
import time import time
import logging import logging
from typing import Callable
# Internal Packages # Internal Packages
from src.utils.rawconfig import Entry, TextContentConfig from src.utils.rawconfig import Entry, TextContentConfig
@@ -18,11 +19,15 @@ class TextToJsonl(ABC):
@abstractmethod @abstractmethod
def process(self, previous_entries: list[Entry]=None) -> list[tuple[int, Entry]]: ... def process(self, previous_entries: list[Entry]=None) -> list[tuple[int, Entry]]: ...
@staticmethod
def hash_func(key: str) -> Callable:
return lambda entry: hashlib.md5(bytes(getattr(entry, key), encoding='utf-8')).hexdigest()
def mark_entries_for_update(self, current_entries: list[Entry], previous_entries: list[Entry], key='compiled', logger=None) -> list[tuple[int, Entry]]: def mark_entries_for_update(self, current_entries: list[Entry], previous_entries: list[Entry], key='compiled', logger=None) -> list[tuple[int, Entry]]:
# Hash all current and previous entries to identify new entries # Hash all current and previous entries to identify new entries
start = time.time() start = time.time()
current_entry_hashes = list(map(lambda e: hashlib.md5(bytes(getattr(e, key), encoding='utf-8')).hexdigest(), current_entries)) current_entry_hashes = list(map(TextToJsonl.hash_func(key), current_entries))
previous_entry_hashes = list(map(lambda e: hashlib.md5(bytes(getattr(e, key), encoding='utf-8')).hexdigest(), previous_entries)) previous_entry_hashes = list(map(TextToJsonl.hash_func(key), previous_entries))
end = time.time() end = time.time()
logger.debug(f"Hash previous, current entries: {end - start} seconds") logger.debug(f"Hash previous, current entries: {end - start} seconds")