Last active
February 19, 2020 08:26
-
-
Save 2ndBillingCycle/930f209e5932f0a7f87380fa3e00b2ff to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python3 | |
# Original code from @Teknikal_Domain: https://teknikaldomain.me/code/automating-algolia-search-indexing/#that-program | |
# Code changed without permission; all rights reserved Teknikal_Domain | |
import json | |
import sys | |
from pathlib import Path | |
from algoliasearch.search_client import SearchClient | |
assert sys.version_info >= (3, 6), "Python 3.6 or greater needed for f-strings" | |
print("Connecting") | |
client = SearchClient.create("XXXXXXXXXX", "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX") | |
index = client.init_index("blog_index") | |
print("Reading local data") | |
local_dat = json.load( | |
Path("teknikaldomain.me/tekpro-blog/public/index.json").read_text() | |
) | |
print(f"Saving {len(local_dat)} records to index") | |
index.save_objects(local_dat, {"autoGenerateObjectIDIfNotExist": False}) | |
print("Done") | |
print("Checking index for dead records") | |
print("Reading index data") | |
idx_dat = list(index.browse_objects({"query": ""})) | |
print(f"Got {len(idx_dat)} records") | |
if not idx_dat: | |
print("Done") | |
sys.exit(0) | |
# The below could help determine if you'll need multithreading | |
# python -m timeit -s "set1 = set(f'{x:0>256}' for x in range(1000000)); set2 = set(f'{x:0>256}' for x in range(1000001, 2000000))" "set1-set2" | |
# Or try | |
# from timeit import timeit | |
# set1 = set(f"{num:0>256}" for num in range(0 , 1000000)) | |
# set2 = set(f"{num:0>256}" for num in range(1000001, 2000000)) | |
# print(f"comparison took {timeit(lambda: set1 - set2, number=10)/10} seconds on average") | |
print("Now cross-checking datasets") | |
print(f"This may need a maximum of {len(idx_dat) * len(local_dat)} computations") | |
local_recs = set(local_rec["objectID"] for local_rec in local_dat) | |
index_recs = set(rec["objectID"] for rec in idx_dat) | |
dead_list = list(index_recs - local_recs) | |
if dead_list: | |
for object_id in dead_list: | |
print(f"Dead record: {object_id}") | |
print(f"Pruning {len(dead_list)} records") | |
index.delete_objects(dead_list) | |
else: | |
print("Index up to date") | |
print("Done") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment