Added samples, benchmarks and docs for nox format. (#556)

* Added samples for nox format.

Signed-off-by: dblock <[email protected]>

* Added space after #!/usr/bin/env python.

Signed-off-by: dblock <[email protected]>

* Added benchmarks and docs.

Signed-off-by: dblock <[email protected]>

---------

Signed-off-by: dblock <[email protected]>

CHANGELOG.md

@@ -13,6 +13,7 @@ Inspired from [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 - Added `remote store` client APIs ([#552](https://github.com/opensearch-project/opensearch-py/pull/552))
 - Added `nox -rs generate` ([#554](https://github.com/opensearch-project/opensearch-py/pull/554))
 - Added a utf-8 header to all .py files ([#557](https://github.com/opensearch-project/opensearch-py/pull/557))
+- Added `samples`, `benchmarks` and `docs` to `nox -rs format` ([#556](https://github.com/opensearch-project/opensearch-py/pull/556))
 ### Changed
 - Generate `tasks` client from API specs ([#508](https://github.com/opensearch-project/opensearch-py/pull/508))
 - Generate `ingest` client from API specs ([#513](https://github.com/opensearch-project/opensearch-py/pull/513))

benchmarks/bench_async.py

@@ -6,6 +6,9 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
 
 import asyncio
 import uuid
@@ -25,7 +28,7 @@ async def index_records(client, item_count):
             client.index(
                 index=index_name,
                 body={
-                    "title": f"Moneyball",
+                    "title": "Moneyball",
                     "director": "Bennett Miller",
                     "year": "2011",
                 },

benchmarks/bench_info_sync.py

@@ -6,6 +6,10 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import logging
 import sys
@@ -36,7 +40,7 @@ def get_info(client, request_count):
     tt = 0
     for n in range(request_count):
         start = time.time() * 1000
-        rc = client.info()
+        client.info()
         total_time = time.time() * 1000 - start
         tt += total_time
     return tt

benchmarks/bench_sync.py

@@ -6,8 +6,13 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
 
 import json
+import logging
+import sys
 import time
 import uuid
 
@@ -21,9 +26,6 @@ auth = ("admin", "admin")
 index_name = "test-index-sync"
 item_count = 1000
 
-import logging
-import sys
-
 root = logging.getLogger()
 # root.setLevel(logging.DEBUG)
 # logging.getLogger("urllib3.connectionpool").setLevel(logging.DEBUG)

benchmarks/bench_sync_async.py

@@ -6,6 +6,10 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import bench_async
 import bench_sync

benchmarks/thread_with_return_value.py

@@ -1,11 +1,13 @@
-#!/usr/bin/env python
-
 # -*- coding: utf-8 -*-
 # 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.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 from threading import Thread
 

docs/source/conf.py

@@ -1,3 +1,12 @@
+# 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.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 # Configuration file for the Sphinx documentation builder.
 #
 # This file only contains a selection of the most common options. For a full

noxfile.py

@@ -34,6 +34,9 @@ SOURCE_FILES = (
     "opensearchpy/",
     "test_opensearchpy/",
     "utils/",
+    "samples/",
+    "benchmarks/",
+    "docs/",
 )
 
 

samples/advanced_index_actions/advanced_index_actions_sample.py

@@ -1,6 +1,17 @@
-from opensearchpy import OpenSearch
+#!/usr/bin/env python
+
+# -*- coding: utf-8 -*-
+# 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.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
 import time
 
+from opensearchpy import OpenSearch
 
 # For cleaner output, comment in the two lines below to disable warnings and informational messages
 # import urllib3
@@ -10,73 +21,84 @@ import time
 def test_opensearch_examples():
     # Set up
     client = OpenSearch(
-        hosts=['https://localhost:9200'],
+        hosts=["https://localhost:9200"],
         use_ssl=True,
         verify_certs=False,
-        http_auth=('admin', 'admin')
+        http_auth=("admin", "admin"),
     )
-    client.indices.create(index='movies')
+    client.indices.create(index="movies")
     print("'movies' index created!")
 
     # Test Clear Index Cache
-    client.indices.clear_cache(index='movies')
+    client.indices.clear_cache(index="movies")
     print("Cache for 'movies' index cleared!")
-    client.indices.clear_cache(index='movies', query=True)
+    client.indices.clear_cache(index="movies", query=True)
     print("Query cache for 'movies' index cleared!")
-    client.indices.clear_cache(index='movies', fielddata=True, request=True)
+    client.indices.clear_cache(index="movies", fielddata=True, request=True)
     print("Field data and request cache for 'movies' index cleared!")
 
     # Test Flush Index
-    client.indices.flush(index='movies')
+    client.indices.flush(index="movies")
     print("'movies' index flushed!")
 
     # Test Refresh Index
-    client.indices.refresh(index='movies')
+    client.indices.refresh(index="movies")
     print("'movies' index refreshed!")
 
     # Test Close or Open Index
-    client.indices.close(index='movies')
+    client.indices.close(index="movies")
     print("'movies' index closed!")
     time.sleep(2)  # add sleep to ensure the index has time to close
-    client.indices.open(index='movies')
+    client.indices.open(index="movies")
     print("'movies' index opened!")
 
     # Test Force Merge Index
-    client.indices.forcemerge(index='movies')
+    client.indices.forcemerge(index="movies")
     print("'movies' index force merged!")
 
     # Test Clone
-    client.indices.put_settings(index='movies', body={'index': {'blocks': {'write': True}}})
+    client.indices.put_settings(
+        index="movies", body={"index": {"blocks": {"write": True}}}
+    )
     print("Write operations blocked for 'movies' index!")
     time.sleep(2)
-    client.indices.clone(index='movies', target='movies_clone')
+    client.indices.clone(index="movies", target="movies_clone")
     print("'movies' index cloned to 'movies_clone'!")
-    client.indices.put_settings(index='movies', body={'index': {'blocks': {'write': False}}})
+    client.indices.put_settings(
+        index="movies", body={"index": {"blocks": {"write": False}}}
+    )
     print("Write operations enabled for 'movies' index!")
 
     # Test Split
     client.indices.create(
-        index='books',
+        index="books",
-        body={'settings': {
+        body={
-            'index': {'number_of_shards': 5, 'number_of_routing_shards': 30, 'blocks': {'write': True}}}}
+            "settings": {
+                "index": {
+                    "number_of_shards": 5,
+                    "number_of_routing_shards": 30,
+                    "blocks": {"write": True},
+                }
+            }
+        },
     )
     print("'books' index created!")
     time.sleep(2)  # add sleep to ensure the index has time to become read-only
     client.indices.split(
-        index='books',
+        index="books",
-        target='bigger_books',
+        target="bigger_books",
-        body={'settings': {'index': {'number_of_shards': 10 }}}
+        body={"settings": {"index": {"number_of_shards": 10}}},
     )
     print("'books' index split into 'bigger_books'!")
-    client.indices.put_settings(index='books', body={'index': {'blocks': {'write': False}}})
+    client.indices.put_settings(
+        index="books", body={"index": {"blocks": {"write": False}}}
+    )
     print("Write operations enabled for 'books' index!")
 
     # Cleanup
-    client.indices.delete(index=['movies', 'books', 'movies_clone', 'bigger_books'])
+    client.indices.delete(index=["movies", "books", "movies_clone", "bigger_books"])
     print("All indices deleted!")
 
 
-
-
 if __name__ == "__main__":
     test_opensearch_examples()

samples/aws/search-requests.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 # -*- coding: utf-8 -*-
 # SPDX-License-Identifier: Apache-2.0
 #
@@ -9,62 +11,59 @@
 # GitHub history for details.
 
 import logging
-
 from os import environ
 from time import sleep
 from urllib.parse import urlparse
 
 from boto3 import Session
-from opensearchpy import RequestsAWSV4SignerAuth, OpenSearch, RequestsHttpConnection
+
+from opensearchpy import OpenSearch, RequestsAWSV4SignerAuth, RequestsHttpConnection
 
 # verbose logging
-logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.INFO)
+logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.INFO)
 
 # cluster endpoint, for example: my-test-domain.us-east-1.es.amazonaws.com
-url = urlparse(environ['ENDPOINT'])
+url = urlparse(environ["ENDPOINT"])
-region = environ.get('AWS_REGION', 'us-east-1')
+region = environ.get("AWS_REGION", "us-east-1")
-service = environ.get('SERVICE', 'es')
+service = environ.get("SERVICE", "es")
 
 credentials = Session().get_credentials()
 
 auth = RequestsAWSV4SignerAuth(credentials, region, service)
 
 client = OpenSearch(
-  hosts=[{
+    hosts=[{"host": url.netloc, "port": url.port or 443}],
-    'host': url.netloc,
+    http_auth=auth,
-    'port': url.port or 443
+    use_ssl=True,
-  }],
+    verify_certs=True,
-  http_auth=auth,
+    connection_class=RequestsHttpConnection,
-  use_ssl=True,
+    timeout=30,
-  verify_certs=True,
-  connection_class=RequestsHttpConnection,
-  timeout=30
 )
 
 # TODO: remove when OpenSearch Serverless adds support for /
-if service == 'es':
+if service == "es":
-  info = client.info()
+    info = client.info()
-  print(f"{info['version']['distribution']}: {info['version']['number']}")
+    print(f"{info['version']['distribution']}: {info['version']['number']}")
 
 # create an index
-index = 'movies'
+index = "movies"
 client.indices.create(index=index)
 
 try:
-  # index data
+    # index data
-  document = {'director': 'Bennett Miller', 'title': 'Moneyball', 'year': 2011}
+    document = {"director": "Bennett Miller", "title": "Moneyball", "year": 2011}
-  client.index(index=index, body=document, id='1')
+    client.index(index=index, body=document, id="1")
 
-  # wait for the document to index
+    # wait for the document to index
-  sleep(1)
+    sleep(1)
 
-  # search for the document
+    # search for the document
-  results = client.search(body={'query': {'match': {'director': 'miller'}}})
+    results = client.search(body={"query": {"match": {"director": "miller"}}})
-  for hit in results['hits']['hits']:
+    for hit in results["hits"]["hits"]:
-    print(hit['_source'])
+        print(hit["_source"])
 
-  # delete the document
+    # delete the document
-  client.delete(index=index, id='1')
+    client.delete(index=index, id="1")
 finally:
-  # delete the index
+    # delete the index
-  client.indices.delete(index=index)
+    client.indices.delete(index=index)

samples/aws/search-urllib3.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 # -*- coding: utf-8 -*-
 # SPDX-License-Identifier: Apache-2.0
 #
@@ -9,62 +11,59 @@
 # GitHub history for details.
 
 import logging
-
 from os import environ
 from time import sleep
 from urllib.parse import urlparse
 
 from boto3 import Session
-from opensearchpy import Urllib3AWSV4SignerAuth, OpenSearch, Urllib3HttpConnection
+
+from opensearchpy import OpenSearch, Urllib3AWSV4SignerAuth, Urllib3HttpConnection
 
 # verbose logging
-logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.INFO)
+logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.INFO)
 
 # cluster endpoint, for example: my-test-domain.us-east-1.es.amazonaws.com
-url = urlparse(environ['ENDPOINT'])
+url = urlparse(environ["ENDPOINT"])
-region = environ.get('AWS_REGION', 'us-east-1')
+region = environ.get("AWS_REGION", "us-east-1")
-service = environ.get('SERVICE', 'es')
+service = environ.get("SERVICE", "es")
 
 credentials = Session().get_credentials()
 
 auth = Urllib3AWSV4SignerAuth(credentials, region, service)
 
 client = OpenSearch(
-  hosts=[{
+    hosts=[{"host": url.netloc, "port": url.port or 443}],
-    'host': url.netloc,
+    http_auth=auth,
-    'port': url.port or 443
+    use_ssl=True,
-  }],
+    verify_certs=True,
-  http_auth=auth,
+    connection_class=Urllib3HttpConnection,
-  use_ssl=True,
+    timeout=30,
-  verify_certs=True,
-  connection_class=Urllib3HttpConnection,
-  timeout=30
 )
 
 # TODO: remove when OpenSearch Serverless adds support for /
-if service == 'es':
+if service == "es":
-  info = client.info()
+    info = client.info()
-  print(f"{info['version']['distribution']}: {info['version']['number']}")
+    print(f"{info['version']['distribution']}: {info['version']['number']}")
 
 # create an index
-index = 'movies'
+index = "movies"
 client.indices.create(index=index)
 
 try:
-  # index data
+    # index data
-  document = {'director': 'Bennett Miller', 'title': 'Moneyball', 'year': 2011}
+    document = {"director": "Bennett Miller", "title": "Moneyball", "year": 2011}
-  client.index(index=index, body=document, id='1')
+    client.index(index=index, body=document, id="1")
 
-  # wait for the document to index
+    # wait for the document to index
-  sleep(1)
+    sleep(1)
 
-  # search for the document
+    # search for the document
-  results = client.search(body={'query': {'match': {'director': 'miller'}}})
+    results = client.search(body={"query": {"match": {"director": "miller"}}})
-  for hit in results['hits']['hits']:
+    for hit in results["hits"]["hits"]:
-    print(hit['_source'])
+        print(hit["_source"])
 
-  # delete the document
+    # delete the document
-  client.delete(index=index, id='1')
+    client.delete(index=index, id="1")
 finally:
-  # delete the index
+    # delete the index
-  client.indices.delete(index=index)
+    client.indices.delete(index=index)

samples/bulk/bulk-array.py

@@ -6,55 +6,53 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import os
-import json
 
 from opensearchpy import OpenSearch
 
 # connect to an instance of OpenSearch
 
-host = os.getenv('HOST', default='localhost')
+host = os.getenv("HOST", default="localhost")
-port = int(os.getenv('PORT', 9200))
+port = int(os.getenv("PORT", 9200))
-auth = (
+auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
-    os.getenv('USERNAME', 'admin'), 
-    os.getenv('PASSWORD', 'admin')
-)
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # check whether an index exists
 index_name = "my-index"
 
 if not client.indices.exists(index_name):
-
+    client.indices.create(
-    client.indices.create(index_name, 
+        index_name,
         body={
-            "mappings":{
+            "mappings": {
                 "properties": {
-                    "value": {
+                    "value": {"type": "float"},
-                        "type": "float"
-                    },
                 }
             }
-        }
+        },
     )
 
 # index data
 data = []
 for i in range(100):
-    data.append({ "index": {"_index": index_name, "_id": i }})
+    data.append({"index": {"_index": index_name, "_id": i}})
-    data.append({ "value": i })
+    data.append({"value": i})
 
 rc = client.bulk(data)
 if rc["errors"]:
-    print(f"There were errors:")
+    print("There were errors:")
     for item in rc["items"]:
         print(f"{item['index']['status']}: {item['index']['error']['type']}")
 else:
@@ -62,4 +60,3 @@ else:
 
 # delete index
 client.indices.delete(index=index_name)
-

samples/bulk/bulk-helpers.py

@@ -6,54 +6,51 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import os
-import json
 
 from opensearchpy import OpenSearch, helpers
 
 # connect to an instance of OpenSearch
 
-host = os.getenv('HOST', default='localhost')
+host = os.getenv("HOST", default="localhost")
-port = int(os.getenv('PORT', 9200))
+port = int(os.getenv("PORT", 9200))
-auth = (
+auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
-    os.getenv('USERNAME', 'admin'), 
-    os.getenv('PASSWORD', 'admin')
-)
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # check whether an index exists
 index_name = "my-index"
 
 if not client.indices.exists(index_name):
-
+    client.indices.create(
-    client.indices.create(index_name, 
+        index_name,
         body={
-            "mappings":{
+            "mappings": {
                 "properties": {
-                    "value": {
+                    "value": {"type": "float"},
-                        "type": "float"
-                    },
                 }
             }
-        }
+        },
     )
 
 # index data
 data = []
 for i in range(100):
-    data.append({ "_index": index_name, "_id": i, "value": i })
+    data.append({"_index": index_name, "_id": i, "value": i})
 
 rc = helpers.bulk(client, data)
 print(f"Bulk-inserted {rc[0]} items.")
 
 # delete index
 client.indices.delete(index=index_name)
-

samples/bulk/bulk-ld.py

@@ -6,55 +6,54 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
-import os
 import json
+import os
 
 from opensearchpy import OpenSearch
 
 # connect to an instance of OpenSearch
 
-host = os.getenv('HOST', default='localhost')
+host = os.getenv("HOST", default="localhost")
-port = int(os.getenv('PORT', 9200))
+port = int(os.getenv("PORT", 9200))
-auth = (
+auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
-    os.getenv('USERNAME', 'admin'), 
-    os.getenv('PASSWORD', 'admin')
-)
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # check whether an index exists
 index_name = "my-index"
 
 if not client.indices.exists(index_name):
-
+    client.indices.create(
-    client.indices.create(index_name, 
+        index_name,
         body={
-            "mappings":{
+            "mappings": {
                 "properties": {
-                    "value": {
+                    "value": {"type": "float"},
-                        "type": "float"
-                    },
                 }
             }
-        }
+        },
     )
 
 # index data
-data = ''
+data = ""
 for i in range(100):
-    data += json.dumps({ "index": {"_index": index_name, "_id": i }}) + "\n"
+    data += json.dumps({"index": {"_index": index_name, "_id": i}}) + "\n"
-    data += json.dumps({ "value": i }) + "\n"
+    data += json.dumps({"value": i}) + "\n"
 
 rc = client.bulk(data)
 if rc["errors"]:
-    print(f"There were errors:")
+    print("There were errors:")
     for item in rc["items"]:
         print(f"{item['index']['status']}: {item['index']['error']['type']}")
 else:
@@ -62,4 +61,3 @@ else:
 
 # delete index
 client.indices.delete(index=index_name)
-

samples/hello/hello-async.py

@@ -6,103 +6,91 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import asyncio
 
 from opensearchpy import AsyncOpenSearch
 
+
 async def main():
     # connect to OpenSearch
-    host = 'localhost'
+    host = "localhost"
     port = 9200
-    auth = ('admin', 'admin') # For testing only. Don't store credentials in code.
+    auth = ("admin", "admin")  # For testing only. Don't store credentials in code.
 
     client = AsyncOpenSearch(
-        hosts = [{'host': host, 'port': port}],
+        hosts=[{"host": host, "port": port}],
-        http_auth = auth,
+        http_auth=auth,
-        use_ssl = True,
+        use_ssl=True,
-        verify_certs = False,
+        verify_certs=False,
-        ssl_show_warn = False
+        ssl_show_warn=False,
     )
 
     try:
-      info = await client.info()
+        info = await client.info()
-      print(f"Welcome to {info['version']['distribution']} {info['version']['number']}!")
+        print(
-
+            f"Welcome to {info['version']['distribution']} {info['version']['number']}!"
-      # create an index
-
-      index_name = 'test-index'
-
-      index_body = {
-        'settings': {
-          'index': {
-            'number_of_shards': 4
-          }
-        }
-      }
-
-      if not await client.indices.exists(index=index_name):
-        await client.indices.create(
-          index_name, 
-          body=index_body
         )
 
-      # add some documents to the index, asynchronously
+        # create an index
-      await asyncio.gather(*[
-          client.index(
-              index = index_name,
-              body = {
-                'title': f"Moneyball {i}",
-                'director': 'Bennett Miller',
-                'year': '2011'
-              },
-              id = i
-          ) for i in range(10)
-      ])
 
-      # refresh the index
+        index_name = "test-index"
-      await client.indices.refresh(index=index_name)
 
-      # search for a document
+        index_body = {"settings": {"index": {"number_of_shards": 4}}}
-      q = 'miller'
 
-      query = {
+        if not await client.indices.exists(index=index_name):
-        'size': 5,
+            await client.indices.create(index_name, body=index_body)
-        'query': {
+
-          'multi_match': {
+        # add some documents to the index, asynchronously
-            'query': q,
+        await asyncio.gather(
-            'fields': ['title^2', 'director']
+            *[
-          }
+                client.index(
+                    index=index_name,
+                    body={
+                        "title": f"Moneyball {i}",
+                        "director": "Bennett Miller",
+                        "year": "2011",
+                    },
+                    id=i,
+                )
+                for i in range(10)
+            ]
+        )
+
+        # refresh the index
+        await client.indices.refresh(index=index_name)
+
+        # search for a document
+        q = "miller"
+
+        query = {
+            "size": 5,
+            "query": {"multi_match": {"query": q, "fields": ["title^2", "director"]}},
         }
-      }
 
-      results = await client.search(
+        results = await client.search(body=query, index=index_name)
-          body = query,
-          index = index_name
-      )
 
-      for hit in results["hits"]["hits"]:
+        for hit in results["hits"]["hits"]:
-        print(hit)
+            print(hit)
 
-      # delete the documents
+        # delete the documents
-      await asyncio.gather(*[
+        await asyncio.gather(
-        client.delete(
+            *[client.delete(index=index_name, id=i) for i in range(10)]
-          index = index_name,
+        )
-          id = i
-        ) for i in range(10)
-      ])
 
-      # delete the index
+        # delete the index
-      await client.indices.delete(
+        await client.indices.delete(index=index_name)
-          index = index_name
-      )
 
     finally:
-      await client.close()
+        await client.close()
+
 
 if __name__ == "__main__":
     loop = asyncio.new_event_loop()
     asyncio.set_event_loop(loop)
     loop.run_until_complete(main())
     loop.close()
-

samples/hello/hello.py

@@ -6,21 +6,25 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 from opensearchpy import OpenSearch
 
 # connect to OpenSearch
 
-host = 'localhost'
+host = "localhost"
 port = 9200
-auth = ('admin', 'admin') # For testing only. Don't store credentials in code.
+auth = ("admin", "admin")  # For testing only. Don't store credentials in code.
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 info = client.info()
@@ -28,76 +32,45 @@ print(f"Welcome to {info['version']['distribution']} {info['version']['number']}
 
 # create an index
 
-index_name = 'test-index'
+index_name = "test-index"
 
-index_body = {
+index_body = {"settings": {"index": {"number_of_shards": 4}}}
-  'settings': {
-    'index': {
-      'number_of_shards': 4
-    }
-  }
-}
 
-response = client.indices.create(
+response = client.indices.create(index_name, body=index_body)
-  index_name, 
-  body=index_body
-)
 
 print(response)
 
 # add a document to the index
 
-document = {
+document = {"title": "Moneyball", "director": "Bennett Miller", "year": "2011"}
-  'title': 'Moneyball',
-  'director': 'Bennett Miller',
-  'year': '2011'
-}
 
-id = '1'
+id = "1"
 
-response = client.index(
+response = client.index(index=index_name, body=document, id=id, refresh=True)
-    index = index_name,
-    body = document,
-    id = id,
-    refresh = True
-)
 
 print(response)
 
 # search for a document
 
-q = 'miller'
+q = "miller"
 
 query = {
-  'size': 5,
+    "size": 5,
-  'query': {
+    "query": {"multi_match": {"query": q, "fields": ["title^2", "director"]}},
-    'multi_match': {
-      'query': q,
-      'fields': ['title^2', 'director']
-    }
-  }
 }
 
-response = client.search(
+response = client.search(body=query, index=index_name)
-    body = query,
-    index = index_name
-)
 
 print(response)
 
 # delete the document
 
-response = client.delete(
+response = client.delete(index=index_name, id=id)
-    index = index_name,
-    id = id
-)
 
 print(response)
 
 # delete the index
 
-response = client.indices.delete(
+response = client.indices.delete(index=index_name)
-    index = index_name
-)
 
 print(response)

samples/index_template/index_template_sample.py

@@ -1,143 +1,129 @@
+#!/usr/bin/env python
+
+# -*- coding: utf-8 -*-
+# 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.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
 from opensearchpy import OpenSearch
 
 # Create a client instance
 client = OpenSearch(
-  hosts=['https://localhost:9200'],
+    hosts=["https://localhost:9200"],
-  use_ssl=True,
+    use_ssl=True,
-  verify_certs=False,
+    verify_certs=False,
-  http_auth=('admin', 'admin')
+    http_auth=("admin", "admin"),
 )
 
 # You can create an index template to define default settings and mappings for indices of certain patterns. The following example creates an index template named `books` with default settings and mappings for indices of the `books-*` pattern:
 client.indices.put_index_template(
-name='books',
+    name="books",
-body={
+    body={
-  'index_patterns': ['books-*'],
+        "index_patterns": ["books-*"],
-  'priority': 1,
+        "priority": 1,
-  'template': {
+        "template": {
-    'settings': {
+            "settings": {"index": {"number_of_shards": 3, "number_of_replicas": 0}},
-      'index': {
+            "mappings": {
-        'number_of_shards': 3,
+                "properties": {
-        'number_of_replicas': 0
+                    "title": {"type": "text"},
-      }
+                    "author": {"type": "text"},
+                    "published_on": {"type": "date"},
+                    "pages": {"type": "integer"},
+                }
+            },
+        },
     },
-    'mappings': {
-      'properties': {
-        'title': { 'type': 'text' },
-        'author': { 'type': 'text' },
-        'published_on': { 'type': 'date' },
-        'pages': { 'type': 'integer' }
-      }
-    }
-  }
-}
 )
 
 # Now, when you create an index that matches the `books-*` pattern, OpenSearch will automatically apply the template's settings and mappings to the index. Let's create an index named books-nonfiction and verify that its settings and mappings match those of the template:
-client.indices.create(index='books-nonfiction')
+client.indices.create(index="books-nonfiction")
-print(client.indices.get(index='books-nonfiction'))
+print(client.indices.get(index="books-nonfiction"))
 
 # If multiple index templates match the index's name, OpenSearch will apply the template with the highest `priority`. The following example creates two index templates named `books-*` and `books-fiction-*` with different settings:
 client.indices.put_index_template(
-name='books',
+    name="books",
-body={
+    body={
-  'index_patterns': ['books-*'],
+        "index_patterns": ["books-*"],
-  'priority': 1,
+        "priority": 1,
-  'template': {
+        "template": {
-    'settings': {
+            "settings": {"index": {"number_of_shards": 3, "number_of_replicas": 0}}
-      'index': {
+        },
-        'number_of_shards': 3,
+    },
-        'number_of_replicas': 0
-      }
-    }
-  }
-}
 )
 
 client.indices.put_index_template(
-name='books-fiction',
+    name="books-fiction",
-body={
+    body={
-  'index_patterns': ['books-fiction-*'],
+        "index_patterns": ["books-fiction-*"],
-  'priority': 2,
+        "priority": 2,
-  'template': {
+        "template": {
-    'settings': {
+            "settings": {"index": {"number_of_shards": 1, "number_of_replicas": 1}}
-      'index': {
+        },
-        'number_of_shards': 1,
+    },
-        'number_of_replicas': 1
-      }
-    }
-  }
-}
 )
 
 # # Test multiple index templates
-client.indices.create(index='books-fiction-romance')
+client.indices.create(index="books-fiction-romance")
-print(client.indices.get(index='books-fiction-romance'))
+print(client.indices.get(index="books-fiction-romance"))
 
 
 # Composable index templates are a new type of index template that allow you to define multiple component templates and compose them into a final template. The following example creates a component template named `books_mappings` with default mappings for indices of the `books-*` and `books-fiction-*` patterns:
 client.cluster.put_component_template(
-name='books_mappings',
+    name="books_mappings",
-body={
+    body={
-  'template': {
+        "template": {
-    'mappings': {
+            "mappings": {
-      'properties': {
+                "properties": {
-        'title': { 'type': 'text' },
+                    "title": {"type": "text"},
-        'author': { 'type': 'text' },
+                    "author": {"type": "text"},
-        'published_on': { 'type': 'date' },
+                    "published_on": {"type": "date"},
-        'pages': { 'type': 'integer' }
+                    "pages": {"type": "integer"},
-      }
+                }
-    }
+            }
-  }
+        }
-}
+    },
 )
 
 client.indices.put_index_template(
-name='books',
+    name="books",
-body={
+    body={
-  'index_patterns': ['books-*'],
+        "index_patterns": ["books-*"],
-  'composed_of': ['books_mappings'],
+        "composed_of": ["books_mappings"],
-  'priority': 4,
+        "priority": 4,
-  'template': {
+        "template": {
-    'settings': {
+            "settings": {"index": {"number_of_shards": 3, "number_of_replicas": 0}}
-      'index': {
+        },
-        'number_of_shards': 3,
+    },
-        'number_of_replicas': 0
-      }
-    }
-  }
-}
 )
 
 client.indices.put_index_template(
-name='books-fiction',
+    name="books-fiction",
-body={
+    body={
-  'index_patterns': ['books-fiction-*'],
+        "index_patterns": ["books-fiction-*"],
-  'composed_of': ['books_mappings'],
+        "composed_of": ["books_mappings"],
-  'priority': 5,
+        "priority": 5,
-  'template': {
+        "template": {
-    'settings': {
+            "settings": {"index": {"number_of_shards": 1, "number_of_replicas": 1}}
-      'index': {
+        },
-        'number_of_shards': 1,
+    },
-        'number_of_replicas': 1
-      }
-    }
-  }
-}
 )
 
 
 # Test composable index templates
-client.indices.create(index='books-fiction-horror')
+client.indices.create(index="books-fiction-horror")
-print(client.indices.get(index='books-fiction-horror'))
+print(client.indices.get(index="books-fiction-horror"))
 
 # Get an index template
-print(client.indices.get_index_template(name='books'))
+print(client.indices.get_index_template(name="books"))
 
 # Delete an index template
-client.indices.delete_index_template(name='books')
+client.indices.delete_index_template(name="books")
 
 # Cleanup
-client.indices.delete(index='books-*')
+client.indices.delete(index="books-*")
-client.indices.delete_index_template(name='books-fiction')
+client.indices.delete_index_template(name="books-fiction")
-client.cluster.delete_component_template(name='books_mappings')
+client.cluster.delete_component_template(name="books_mappings")

samples/json/hello-async.py

@@ -6,86 +6,91 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import asyncio
 
 from opensearchpy import AsyncOpenSearch
 
+
 async def main():
     # connect to OpenSearch
-    host = 'localhost'
+    host = "localhost"
     port = 9200
-    auth = ('admin', 'admin') # For testing only. Don't store credentials in code.
+    auth = ("admin", "admin")  # For testing only. Don't store credentials in code.
 
     client = AsyncOpenSearch(
-        hosts = [{'host': host, 'port': port}],
+        hosts=[{"host": host, "port": port}],
-        http_auth = auth,
+        http_auth=auth,
-        use_ssl = True,
+        use_ssl=True,
-        verify_certs = False,
+        verify_certs=False,
-        ssl_show_warn = False
+        ssl_show_warn=False,
     )
 
     try:
-      info = await client.transport.perform_request('GET', '/')
+        info = await client.transport.perform_request("GET", "/")
-      print(f"Welcome to {info['version']['distribution']} {info['version']['number']}!")
+        print(
+            f"Welcome to {info['version']['distribution']} {info['version']['number']}!"
+        )
 
-      # create an index
+        # create an index
 
-      index_name = 'movies'
+        index_name = "movies"
 
-      index_body = {
+        index_body = {"settings": {"index": {"number_of_shards": 4}}}
-        'settings': {
+
-          'index': {
+        print(
-            'number_of_shards': 4
+            await client.transport.perform_request(
-          }
+                "PUT", f"/{index_name}", body=index_body
+            )
+        )
+
+        # add a document to the index
+
+        document = {"title": "Moneyball", "director": "Bennett Miller", "year": "2011"}
+
+        id = "1"
+
+        print(
+            await client.transport.perform_request(
+                "PUT", f"/{index_name}/_doc/{id}?refresh=true", body=document
+            )
+        )
+
+        # search for a document
+
+        q = "miller"
+
+        query = {
+            "size": 5,
+            "query": {"multi_match": {"query": q, "fields": ["title^2", "director"]}},
         }
-      }
 
-      print(await client.transport.perform_request("PUT", f"/{index_name}", body=index_body))
+        print(
+            await client.transport.perform_request(
+                "POST", f"/{index_name}/_search", body=query
+            )
+        )
 
-      # add a document to the index
+        # delete the document
 
-      document = {
+        print(
-        'title': 'Moneyball',
+            await client.transport.perform_request("DELETE", f"/{index_name}/_doc/{id}")
-        'director': 'Bennett Miller',
+        )
-        'year': '2011'
-      }
 
-      id = '1'
+        # delete the index
-
-      print(await client.transport.perform_request("PUT", f"/{index_name}/_doc/{id}?refresh=true", body = document))
-
-      # search for a document
-
-      q = 'miller'
-
-      query = {
-        'size': 5,
-        'query': {
-          'multi_match': {
-            'query': q,
-            'fields': ['title^2', 'director']
-          }
-        }
-      }
-
-      print(await client.transport.perform_request("POST", f"/{index_name}/_search", body = query))
-
-      # delete the document
-
-      print(await client.transport.perform_request("DELETE", f"/{index_name}/_doc/{id}"))
-
-      # delete the index
-
-      print(await client.transport.perform_request("DELETE", f"/{index_name}"))
 
+        print(await client.transport.perform_request("DELETE", f"/{index_name}"))
 
     finally:
-      await client.close()
+        await client.close()
+
 
 if __name__ == "__main__":
     loop = asyncio.new_event_loop()
     asyncio.set_event_loop(loop)
     loop.run_until_complete(main())
     loop.close()
-

samples/json/hello.py

@@ -6,67 +6,60 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 from opensearchpy import OpenSearch
 
 # connect to OpenSearch
 
-host = 'localhost'
+host = "localhost"
 port = 9200
-auth = ('admin', 'admin') # For testing only. Don't store credentials in code.
+auth = ("admin", "admin")  # For testing only. Don't store credentials in code.
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
-info = client.transport.perform_request('GET', '/')
+info = client.transport.perform_request("GET", "/")
 print(f"Welcome to {info['version']['distribution']} {info['version']['number']}!")
 
 # create an index
 
-index_name = 'movies'
+index_name = "movies"
 
-index_body = {
+index_body = {"settings": {"index": {"number_of_shards": 4}}}
-  'settings': {
-    'index': {
-      'number_of_shards': 4
-    }
-  }
-}
 
 print(client.transport.perform_request("PUT", f"/{index_name}", body=index_body))
 
 # add a document to the index
 
-document = {
+document = {"title": "Moneyball", "director": "Bennett Miller", "year": "2011"}
-  'title': 'Moneyball',
-  'director': 'Bennett Miller',
-  'year': '2011'
-}
 
-id = '1'
+id = "1"
 
-print(client.transport.perform_request("PUT", f"/{index_name}/_doc/{id}?refresh=true", body = document))
+print(
+    client.transport.perform_request(
+        "PUT", f"/{index_name}/_doc/{id}?refresh=true", body=document
+    )
+)
 
 # search for a document
 
-q = 'miller'
+q = "miller"
 
 query = {
-  'size': 5,
+    "size": 5,
-  'query': {
+    "query": {"multi_match": {"query": q, "fields": ["title^2", "director"]}},
-    'multi_match': {
-      'query': q,
-      'fields': ['title^2', 'director']
-    }
-  }
 }
 
-print(client.transport.perform_request("POST", f"/{index_name}/_search", body = query))
+print(client.transport.perform_request("POST", f"/{index_name}/_search", body=query))
 
 # delete the document
 

samples/knn/knn-async-basics.py

@@ -6,29 +6,31 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import asyncio
 import os
 import random
 
-from opensearchpy import AsyncOpenSearch, AsyncHttpConnection, helpers
+from opensearchpy import AsyncHttpConnection, AsyncOpenSearch, helpers
+
 
 async def main():
     # connect to an instance of OpenSearch
-    host = os.getenv('HOST', default='localhost')
+    host = os.getenv("HOST", default="localhost")
-    port = int(os.getenv('PORT', 9200))
+    port = int(os.getenv("PORT", 9200))
-    auth = (
+    auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
-        os.getenv('USERNAME', 'admin'), 
-        os.getenv('PASSWORD', 'admin')
-    )
 
     client = AsyncOpenSearch(
-        hosts = [{'host': host, 'port': port}],
+        hosts=[{"host": host, "port": port}],
-        http_auth = auth,
+        http_auth=auth,
-        use_ssl = True,
+        use_ssl=True,
-        verify_certs = False,
+        verify_certs=False,
         connection_class=AsyncHttpConnection,
-        ssl_show_warn = False
+        ssl_show_warn=False,
     )
 
     # check whether an index exists
@@ -36,20 +38,16 @@ async def main():
     dimensions = 5
 
     if not await client.indices.exists(index_name):
-        await client.indices.create(index_name, 
+        await client.indices.create(
+            index_name,
             body={
-                "settings":{
+                "settings": {"index.knn": True},
-                    "index.knn": True
+                "mappings": {
-                },
-                "mappings":{
                     "properties": {
-                        "values": {
+                        "values": {"type": "knn_vector", "dimension": dimensions},
-                            "type": "knn_vector", 
-                            "dimension": dimensions
-                        },
                     }
-                }
+                },
-            }
+            },
         )
 
     # index data
@@ -59,11 +57,13 @@ async def main():
         for j in range(dimensions):
             vec.append(round(random.uniform(0, 1), 2))
 
-        vectors.append({
+        vectors.append(
-            "_index": index_name,
+            {
-            "_id": i,
+                "_index": index_name,
-            "values": vec,
+                "_id": i,
-        })
+                "values": vec,
+            }
+        )
 
     # bulk index
     await helpers.async_bulk(client, vectors)
@@ -86,9 +86,9 @@ async def main():
 
     await client.close()
 
+
 if __name__ == "__main__":
     loop = asyncio.new_event_loop()
     asyncio.set_event_loop(loop)
     loop.run_until_complete(main())
     loop.close()
-

samples/knn/knn-basics.py

@@ -6,6 +6,10 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import os
 import random
@@ -14,19 +18,16 @@ from opensearchpy import OpenSearch, helpers
 
 # connect to an instance of OpenSearch
 
-host = os.getenv('HOST', default='localhost')
+host = os.getenv("HOST", default="localhost")
-port = int(os.getenv('PORT', 9200))
+port = int(os.getenv("PORT", 9200))
-auth = (
+auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
-    os.getenv('USERNAME', 'admin'), 
-    os.getenv('PASSWORD', 'admin')
-)
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # check whether an index exists
@@ -34,20 +35,16 @@ index_name = "my-index"
 dimensions = 5
 
 if not client.indices.exists(index_name):
-    client.indices.create(index_name, 
+    client.indices.create(
+        index_name,
         body={
-            "settings":{
+            "settings": {"index.knn": True},
-                "index.knn": True
+            "mappings": {
-            },
-            "mappings":{
                 "properties": {
-                    "values": {
+                    "values": {"type": "knn_vector", "dimension": dimensions},
-                        "type": "knn_vector", 
-                        "dimension": dimensions
-                    },
                 }
-            }
+            },
-        }
+        },
     )
 
 # index data
@@ -57,11 +54,13 @@ for i in range(10):
     for j in range(dimensions):
         vec.append(round(random.uniform(0, 1), 2))
 
-    vectors.append({
+    vectors.append(
-        "_index": index_name,
+        {
-        "_id": i,
+            "_index": index_name,
-        "values": vec,
+            "_id": i,
-    })
+            "values": vec,
+        }
+    )
 
 # bulk index
 helpers.bulk(client, vectors)
@@ -81,4 +80,3 @@ for hit in results["hits"]["hits"]:
 
 # delete index
 client.indices.delete(index=index_name)
-

samples/knn/knn-boolean-filter.py

@@ -6,6 +6,10 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import os
 import random
@@ -14,19 +18,16 @@ from opensearchpy import OpenSearch, helpers
 
 # connect to an instance of OpenSearch
 
-host = os.getenv('HOST', default='localhost')
+host = os.getenv("HOST", default="localhost")
-port = int(os.getenv('PORT', 9200))
+port = int(os.getenv("PORT", 9200))
-auth = (
+auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
-    os.getenv('USERNAME', 'admin'), 
-    os.getenv('PASSWORD', 'admin')
-)
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # check whether an index exists
@@ -34,38 +35,34 @@ index_name = "my-index"
 dimensions = 5
 
 if not client.indices.exists(index_name):
-    client.indices.create(index_name, 
+    client.indices.create(
+        index_name,
         body={
-            "settings":{
+            "settings": {"index.knn": True},
-                "index.knn": True
+            "mappings": {
-            },
-            "mappings":{
                 "properties": {
-                    "values": {
+                    "values": {"type": "knn_vector", "dimension": dimensions},
-                        "type": "knn_vector", 
-                        "dimension": dimensions
-                    },
                 }
-            }
+            },
-        }
+        },
     )
 
 # index data
 vectors = []
-genres = ['fiction', 'drama', 'romance']
+genres = ["fiction", "drama", "romance"]
 for i in range(3000):
     vec = []
     for j in range(dimensions):
         vec.append(round(random.uniform(0, 1), 2))
 
-    vectors.append({
+    vectors.append(
-        "_index": index_name,
+        {
-        "_id": i,
+            "_index": index_name,
-        "values": vec,
+            "_id": i,
-        "metadata": {
+            "values": vec,
-            "genre": random.choice(genres)
+            "metadata": {"genre": random.choice(genres)},
         }
-    })
+    )
 
 # bulk index
 helpers.bulk(client, vectors)
@@ -82,23 +79,8 @@ print(f"Searching for {vec} with the '{genre}' genre ...")
 search_query = {
     "query": {
         "bool": {
-            "filter": {
+            "filter": {"bool": {"must": [{"term": {"metadata.genre": genre}}]}},
-                "bool": {
+            "must": {"knn": {"values": {"vector": vec, "k": 5}}},
-                    "must": [{
-                        "term": {
-                            "metadata.genre": genre
-                        }
-                    }]
-                }
-            },
-            "must": {
-                "knn": {
-                    "values": {
-                        "vector": vec, 
-                        "k": 5
-                    }
-                }
-            }
         }
     }
 }

samples/knn/knn-efficient-filter.py

@@ -6,42 +6,43 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import os
-import random
 
 from opensearchpy import OpenSearch, helpers
 
 # connect to an instance of OpenSearch
 
-host = os.getenv('HOST', default='localhost')
+host = os.getenv("HOST", default="localhost")
-port = int(os.getenv('PORT', 9200))
+port = int(os.getenv("PORT", 9200))
-auth = (
+auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
-    os.getenv('USERNAME', 'admin'), 
-    os.getenv('PASSWORD', 'admin')
-)
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # check whether an index exists
 index_name = "hotels-index"
 
 if not client.indices.exists(index_name):
-    client.indices.create(index_name, 
+    client.indices.create(
+        index_name,
         body={
-            "settings":{
+            "settings": {
                 "index.knn": True,
                 "knn.algo_param.ef_search": 100,
                 "number_of_shards": 1,
-                "number_of_replicas": 0
+                "number_of_replicas": 0,
             },
-            "mappings":{
+            "mappings": {
                 "properties": {
                     "location": {
                         "type": "knn_vector",
@@ -50,31 +51,100 @@ if not client.indices.exists(index_name):
                             "name": "hnsw",
                             "space_type": "l2",
                             "engine": "lucene",
-                            "parameters": {
+                            "parameters": {"ef_construction": 100, "m": 16},
-                                "ef_construction": 100,
+                        },
-                                "m": 16
-                            }
-                        }
                     },
                 }
-            }
+            },
-        }
+        },
     )
 
 # index data
 vectors = [
-    { "_index": "hotels-index", "_id": "1", "location": [5.2, 4.4], "parking" : "true", "rating" : 5 },
+    {
-    { "_index": "hotels-index", "_id": "2", "location": [5.2, 3.9], "parking" : "false", "rating" : 4 },
+        "_index": "hotels-index",
-    { "_index": "hotels-index", "_id": "3", "location": [4.9, 3.4], "parking" : "true", "rating" : 9 },
+        "_id": "1",
-    { "_index": "hotels-index", "_id": "4", "location": [4.2, 4.6], "parking" : "false", "rating" : 6},
+        "location": [5.2, 4.4],
-    { "_index": "hotels-index", "_id": "5", "location": [3.3, 4.5], "parking" : "true", "rating" : 8 },
+        "parking": "true",
-    { "_index": "hotels-index", "_id": "6", "location": [6.4, 3.4], "parking" : "true", "rating" : 9 },
+        "rating": 5,
-    { "_index": "hotels-index", "_id": "7", "location": [4.2, 6.2], "parking" : "true", "rating" : 5 },
+    },
-    { "_index": "hotels-index", "_id": "8", "location": [2.4, 4.0], "parking" : "true", "rating" : 8 },
+    {
-    { "_index": "hotels-index", "_id": "9", "location": [1.4, 3.2], "parking" : "false", "rating" : 5 },
+        "_index": "hotels-index",
-    { "_index": "hotels-index", "_id": "10", "location": [7.0, 9.9], "parking" : "true", "rating" : 9 },
+        "_id": "2",
-    { "_index": "hotels-index", "_id": "11", "location": [3.0, 2.3], "parking" : "false", "rating" : 6 },
+        "location": [5.2, 3.9],
-    { "_index": "hotels-index", "_id": "12", "location": [5.0, 1.0], "parking" : "true", "rating" : 3 },
+        "parking": "false",
+        "rating": 4,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "3",
+        "location": [4.9, 3.4],
+        "parking": "true",
+        "rating": 9,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "4",
+        "location": [4.2, 4.6],
+        "parking": "false",
+        "rating": 6,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "5",
+        "location": [3.3, 4.5],
+        "parking": "true",
+        "rating": 8,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "6",
+        "location": [6.4, 3.4],
+        "parking": "true",
+        "rating": 9,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "7",
+        "location": [4.2, 6.2],
+        "parking": "true",
+        "rating": 5,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "8",
+        "location": [2.4, 4.0],
+        "parking": "true",
+        "rating": 8,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "9",
+        "location": [1.4, 3.2],
+        "parking": "false",
+        "rating": 5,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "10",
+        "location": [7.0, 9.9],
+        "parking": "true",
+        "rating": 9,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "11",
+        "location": [3.0, 2.3],
+        "parking": "false",
+        "rating": 6,
+    },
+    {
+        "_index": "hotels-index",
+        "_id": "12",
+        "location": [5.0, 1.0],
+        "parking": "true",
+        "rating": 3,
+    },
 ]
 
 helpers.bulk(client, vectors)
@@ -87,30 +157,19 @@ search_query = {
     "query": {
         "knn": {
             "location": {
-            "vector": [5, 4],
+                "vector": [5, 4],
-            "k": 3,
+                "k": 3,
-            "filter": {
+                "filter": {
-                "bool": {
+                    "bool": {
-                    "must": [
+                        "must": [
-                        {
+                            {"range": {"rating": {"gte": 8, "lte": 10}}},
-                            "range": {
+                            {"term": {"parking": "true"}},
-                                "rating": {
-                                    "gte": 8,
-                                    "lte": 10
-                                }
-                            }
-                        },
-                        {
-                            "term": {
-                                "parking": "true"
-                                }
-                            }
                         ]
                     }
-                }
+                },
             }
         }
-    }
+    },
 }
 
 results = client.search(index=index_name, body=search_query)

samples/security/roles.py

@@ -6,6 +6,9 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
 
 
 # A basic OpenSearch sample that create and manage roles.
@@ -14,16 +17,16 @@ from opensearchpy import OpenSearch
 
 # connect to OpenSearch
 
-host = 'localhost'
+host = "localhost"
 port = 9200
-auth = ('admin', 'admin') # For testing only. Don't store credentials in code.
+auth = ("admin", "admin")  # For testing only. Don't store credentials in code.
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # Create a Role
@@ -31,16 +34,16 @@ client = OpenSearch(
 role_name = "test-role"
 
 role_content = {
-  "cluster_permissions": ["cluster_monitor"],
+    "cluster_permissions": ["cluster_monitor"],
-  "index_permissions": [
+    "index_permissions": [
-      {
+        {
-          "index_patterns": ["index", "test-*"],
+            "index_patterns": ["index", "test-*"],
-          "allowed_actions": [
+            "allowed_actions": [
-              "data_access",
+                "data_access",
-              "indices_monitor",
+                "indices_monitor",
-          ],
+            ],
-      }
+        }
-  ],
+    ],
 }
 
 response = client.security.create_role(role_name, body=role_content)

samples/security/users.py

@@ -6,6 +6,9 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
 
 
 # A basic OpenSearch sample that create and manage users.
@@ -14,16 +17,16 @@ from opensearchpy import OpenSearch
 
 # connect to OpenSearch
 
-host = 'localhost'
+host = "localhost"
 port = 9200
-auth = ('admin', 'admin') # For testing only. Don't store credentials in code.
+auth = ("admin", "admin")  # For testing only. Don't store credentials in code.
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
+    hosts=[{"host": host, "port": port}],
-    http_auth = auth,
+    http_auth=auth,
-    use_ssl = True,
+    use_ssl=True,
-    verify_certs = False,
+    verify_certs=False,
-    ssl_show_warn = False
+    ssl_show_warn=False,
 )
 
 # Create a User

test_opensearchpy/run_tests.py

@@ -1,10 +1,14 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 # 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.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
+
 #
 # Modifications Copyright OpenSearch Contributors. See
 # GitHub history for details.

utils/generate-api.py

@@ -1,10 +1,14 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 # 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.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
+
 #
 # Modifications Copyright OpenSearch Contributors. See
 # GitHub history for details.

utils/license-headers.py

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # SPDX-License-Identifier: Apache-2.0
 #
 # The OpenSearch Contributors require contributions made to
@@ -6,24 +7,6 @@
 #
 # Modifications Copyright OpenSearch Contributors. See
 # GitHub history for details.
-#
-#  Licensed to Elasticsearch B.V. under one or more contributor
-#  license agreements. See the NOTICE file distributed with
-#  this work for additional information regarding copyright
-#  ownership. Elasticsearch B.V. licenses this file to you under
-#  the Apache License, Version 2.0 (the "License"); you may
-#  not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
-#
-# 	http://www.apache.org/licenses/LICENSE-2.0
-#
-#  Unless required by applicable law or agreed to in writing,
-#  software distributed under the License is distributed on an
-#  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-#  KIND, either express or implied.  See the License for the
-#  specific language governing permissions and limitations
-#  under the License.
-
 
 """Script which verifies that all source files have a license header.
 Has two modes: 'fix' and 'check'. 'fix' fixes problems, 'check' will
@@ -33,20 +16,20 @@ error out if 'fix' would have changed the file.
 import os
 import re
 import sys
-from itertools import chain
 from typing import Iterator, List
 
-lines_to_keep = ["# -*- coding: utf-8 -*-\n", "#!/usr/bin/env python\n"]
+lines_to_keep = ["# -*- coding: utf-8 -*-", "#!/usr/bin/env python"]
-license_header_lines = [
+
-    "# SPDX-License-Identifier: Apache-2.0\n",
+license_header = """
-    "#\n",
+# SPDX-License-Identifier: Apache-2.0
-    "# The OpenSearch Contributors require contributions made to\n",
+#
-    "# this file be licensed under the Apache-2.0 license or a\n",
+# The OpenSearch Contributors require contributions made to
-    "# compatible open source license.\n",
+# this file be licensed under the Apache-2.0 license or a
-    "#\n",
+# compatible open source license.
-    "# Modifications Copyright OpenSearch Contributors. See\n",
+#
-    "# GitHub history for details.\n",
+# Modifications Copyright OpenSearch Contributors. See
-]
+# GitHub history for details.
+""".strip()
 
 
 def find_files_to_fix(sources: List[str]) -> Iterator[str]:
@@ -67,20 +50,18 @@ def find_files_to_fix(sources: List[str]) -> Iterator[str]:
 def does_file_need_fix(filepath: str) -> bool:
     if not re.search(r"\.pyi?$", filepath):
         return False
+    existing_header = ""
     with open(filepath, mode="r") as f:
-        first_license_line = None
         for line in f:
-            if line == license_header_lines[0]:
+            line = line.strip()
-                first_license_line = line
+            if len(line) == 0 or line in lines_to_keep:
+                pass
+            elif line[0] == "#":
+                existing_header += line
+                existing_header += "\n"
+            else:
                 break
-            elif line not in lines_to_keep:
+    return not existing_header.startswith(license_header)
-                return True
-        for header_line, line in zip(
-            license_header_lines, chain((first_license_line,), f)
-        ):
-            if line != header_line:
-                return True
-    return False
 
 
 def add_header_to_file(filepath: str) -> None:
@@ -88,9 +69,9 @@ def add_header_to_file(filepath: str) -> None:
         lines = list(f)
     i = 0
     for i, line in enumerate(lines):
-        if line not in lines_to_keep:
+        if len(line) > 0 and line not in lines_to_keep:
             break
-    lines = lines[:i] + license_header_lines + lines[i:]
+    lines = lines[:i] + [license_header] + lines[i:]
     with open(filepath, mode="w") as f:
         f.truncate()
         f.write("".join(lines))