Skip to content

Instantly share code, notes, and snippets.

@kenoir
Created November 18, 2020 10:55
Show Gist options
  • Save kenoir/bd1eaddd4f3085de7300955df7cdf7c7 to your computer and use it in GitHub Desktop.
Save kenoir/bd1eaddd4f3085de7300955df7cdf7c7 to your computer and use it in GitHub Desktop.
@click.command()
@click.pass_context
def merge_chunks_index(ctx):
local_elastic_client = get_local_elastic_client()
import json
from pprint import pprint
import sys
import elasticsearch
found = set()
not_found = set()
has_migrated_transfer_packages = set()
matched_migrated_transfer_packages = set()
with open(f"/Users/robertkenny/Desktop/migration_state/index_chunks.json", 'r') as f:
for line in f:
doc = json.loads(line)
id = doc['_id']
if doc['_source']['transfer_package'] is not None:
has_migrated_transfer_packages.add(id)
try:
matched_doc = local_elastic_client.get(index="chunks", id=id)
if doc['_source']['transfer_package'] is not None:
matched_migrated_transfer_packages.add(id)
matched_doc['_source']['transfer_package'] = doc['_source']['transfer_package']
local_elastic_client.update(
index="chunks",
id=id,
body={"doc": matched_doc['_source']}
)
found.add(id)
except elasticsearch.exceptions.NotFoundError:
not_found.add(id)
print(f"Found:{len(found)}, Not found: {len(not_found)}")
print(f"has_migrated_transfer_packages:{len(has_migrated_transfer_packages)}")
print(f"matched_migrated_transfer_packages:{len(matched_migrated_transfer_packages)}")
#pprint(has_migrated_transfer_packages.difference(matched_migrated_transfer_packages))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment