Skip to content

Commit

Permalink
The client can serialize an array for you.
Browse files Browse the repository at this point in the history
Signed-off-by: dblock <dblock@amazon.com>
  • Loading branch information
dblock committed Jul 25, 2023
1 parent e12dd7e commit 7460b50
Show file tree
Hide file tree
Showing 2 changed files with 83 additions and 0 deletions.
19 changes: 19 additions & 0 deletions guides/bulk.md
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,25 @@ docs = '''
{"name": "baz"}
'''

response = client.bulk(docs)
if response["errors"]:
print(f"There were errors!")
else:
print(f"Bulk-inserted {len(rc['items'])} items.")
```

The client can also serialize an array of data into bulk-delimited JSON for you. See [samples/bulk/bulk-array.py](../samples/bulk/bulk-array.py) for a working sample.

```python
data = [
{ "index": { "_index": "index-2022-06-08", "_id": 1 }}
{ "name": "foo"}
{ "index": { "_index": "index-2022-06-09", "_id": 2 }}
{ "name": "bar"}
{ "index": { "_index": "index-2022-06-10", "_id": 3 }}
{ "name": "baz"}
]

response = client.bulk(data)
if response["errors"]:
print(f"There were errors!")
Expand Down
64 changes: 64 additions & 0 deletions samples/bulk/bulk-array.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
#!/usr/bin/env python

# SPDX-License-Identifier: Apache-2.0
#
# The OpenSearch Contributors require contributions made to
# this file be licensed under the Apache-2.0 license or a
# compatible open source license.

import os
import json

from opensearchpy import OpenSearch

# connect to an instance of OpenSearch

host = os.getenv('HOST', default='localhost')
port = int(os.getenv('PORT', 9200))
auth = (
os.getenv('USERNAME', 'admin'),
os.getenv('PASSWORD', 'admin')
)

client = OpenSearch(
hosts = [{'host': host, 'port': port}],
http_auth = auth,
use_ssl = True,
verify_certs = False,
ssl_show_warn = False
)

# check whether an index exists
index_name = "my-index"

if not client.indices.exists(index_name):

client.indices.create(index_name,
body={
"mappings":{
"properties": {
"value": {
"type": "float"
},
}
}
}
)

# index data
data = []
for i in range(100):
data.append({ "index": {"_index": index_name, "_id": i }})
data.append({ "value": i })

rc = client.bulk(data)
if rc["errors"]:
print(f"There were errors:")
for item in rc["items"]:
print(f"{item['index']['status']}: {item['index']['error']['type']}")
else:
print(f"Bulk-inserted {len(rc['items'])} items.")

# delete index
client.indices.delete(index=index_name)

0 comments on commit 7460b50

Please sign in to comment.