Added pylint, enforce naming.

.ci/make.sh

@@ -131,7 +131,7 @@ if [[ "$CMD" == "assemble" ]]; then
   docker run \
     --rm -v $repo/.ci/output:/code/opensearch-py/dist \
     $product \
-    /bin/bash -c "python /code/opensearch-py/utils/build-dists.py $VERSION"
+    /bin/bash -c "python /code/opensearch-py/utils/build_dists.py $VERSION"
 
   # Verify that there are dists in .ci/output
 	if compgen -G ".ci/output/*" > /dev/null; then

CHANGELOG.md

@@ -3,6 +3,7 @@ Inspired from [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 
 ## [Unreleased]
 ### Added
+- Added pylint, enforcing `line-too-long` and `invalid-name` ([#590](https://github.com/opensearch-project/opensearch-py/pull/590))
 ### Changed
 ### Deprecated
 ### Removed

DEVELOPER_GUIDE.md

@@ -99,7 +99,15 @@ Note that integration tests require docker to be installed and running, and down
 
 ## Linter
 
-Run the linter and test suite to ensure your changes do not break existing code. The following will auto-format your changes.
+This library uses a combination of [pylint](https://github.com/pylint-dev/pylint), [black](https://github.com/psf/black), and [isort](https://github.com/PyCQA/isort) to enforce some consistency in code formatting or naming conventions. 
+
+Run the linters to ensure your changes do not break existing conventions. 
+
+```
+$ nox -rs lint
+```
+
+Use a formatter to auto-correct some common problems.
 
 ```
 $ nox -rs format

benchmarks/bench_async.py

@@ -16,14 +16,8 @@
 
 from opensearchpy import AsyncHttpConnection, AsyncOpenSearch
 
-host = "localhost"
-port = 9200
-auth = ("admin", "admin")
-index_name = "test-index-async"
-item_count = 100
 
-
-async def index_records(client: Any, item_count: int) -> None:
+async def index_records(client: Any, index_name: str, item_count: int) -> None:
     await asyncio.gather(
         *[
             client.index(
@@ -41,6 +35,11 @@ async def index_records(client: Any, item_count: int) -> None:
 
 
 async def test_async(client_count: int = 1, item_count: int = 1) -> None:
+    host = "localhost"
+    port = 9200
+    auth = ("admin", "admin")
+    index_name = "test-index-async"
+
     clients = []
     for i in range(client_count):
         clients.append(
@@ -61,7 +60,10 @@ async def test_async(client_count: int = 1, item_count: int = 1) -> None:
     await clients[0].indices.create(index_name)
 
     await asyncio.gather(
-        *[index_records(clients[i], item_count) for i in range(client_count)]
+        *[
+            index_records(clients[i], index_name, item_count)
+            for i in range(client_count)
+        ]
     )
 
     await clients[0].indices.refresh(index=index_name)
@@ -79,28 +81,31 @@ def test(item_count: int = 1, client_count: int = 1) -> None:
     loop.close()
 
 
+ITEM_COUNT = 100
+
+
 def test_1() -> None:
-    test(1, 32 * item_count)
+    test(1, 32 * ITEM_COUNT)
 
 
 def test_2() -> None:
-    test(2, 16 * item_count)
+    test(2, 16 * ITEM_COUNT)
 
 
 def test_4() -> None:
-    test(4, 8 * item_count)
+    test(4, 8 * ITEM_COUNT)
 
 
 def test_8() -> None:
-    test(8, 4 * item_count)
+    test(8, 4 * ITEM_COUNT)
 
 
 def test_16() -> None:
-    test(16, 2 * item_count)
+    test(16, 2 * ITEM_COUNT)
 
 
 def test_32() -> None:
-    test(32, item_count)
+    test(32, ITEM_COUNT)
 
 
 __benchmarks__ = [(test_1, test_8, "1 client vs. more clients (async)")]

benchmarks/bench_info_sync.py

@@ -20,22 +20,6 @@
 
 from opensearchpy import OpenSearch
 
-host = "localhost"
-port = 9200
-auth = ("admin", "admin")
-request_count = 250
-
-
-root = logging.getLogger()
-# root.setLevel(logging.DEBUG)
-# logging.getLogger("urllib3.connectionpool").setLevel(logging.DEBUG)
-
-handler = logging.StreamHandler(sys.stdout)
-handler.setLevel(logging.DEBUG)
-formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
-handler.setFormatter(formatter)
-root.addHandler(handler)
-
 
 def get_info(client: Any, request_count: int) -> float:
     tt: float = 0
@@ -48,6 +32,22 @@ def get_info(client: Any, request_count: int) -> float:
 
 
 def test(thread_count: int = 1, request_count: int = 1, client_count: int = 1) -> None:
+    host = "localhost"
+    port = 9200
+    auth = ("admin", "admin")
+
+    root = logging.getLogger()
+    # root.setLevel(logging.DEBUG)
+    # logging.getLogger("urllib3.connectionpool").setLevel(logging.DEBUG)
+
+    handler = logging.StreamHandler(sys.stdout)
+    handler.setLevel(logging.DEBUG)
+    formatter = logging.Formatter(
+        "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+    )
+    handler.setFormatter(formatter)
+    root.addHandler(handler)
+
     clients = []
     for i in range(client_count):
         clients.append(
@@ -76,24 +76,27 @@ def test(thread_count: int = 1, request_count: int = 1, client_count: int = 1) -
     print(f"latency={latency}")
 
 
+REQUEST_COUNT = 250
+
+
 def test_1() -> None:
-    test(1, 32 * request_count, 1)
+    test(1, 32 * REQUEST_COUNT, 1)
 
 
 def test_2() -> None:
-    test(2, 16 * request_count, 2)
+    test(2, 16 * REQUEST_COUNT, 2)
 
 
 def test_4() -> None:
-    test(4, 8 * request_count, 3)
+    test(4, 8 * REQUEST_COUNT, 3)
 
 
 def test_8() -> None:
-    test(8, 4 * request_count, 8)
+    test(8, 4 * REQUEST_COUNT, 8)
 
 
 def test_32() -> None:
-    test(32, request_count, 32)
+    test(32, REQUEST_COUNT, 32)
 
 
 __benchmarks__ = [(test_1, test_32, "1 thread vs. 32 threads (sync)")]

benchmarks/bench_sync.py

@@ -21,24 +21,8 @@
 
 from opensearchpy import OpenSearch, Urllib3HttpConnection
 
-host = "localhost"
-port = 9200
-auth = ("admin", "admin")
-index_name = "test-index-sync"
-item_count = 1000
 
-root = logging.getLogger()
-# root.setLevel(logging.DEBUG)
-# logging.getLogger("urllib3.connectionpool").setLevel(logging.DEBUG)
-
-handler = logging.StreamHandler(sys.stdout)
-handler.setLevel(logging.DEBUG)
-formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
-handler.setFormatter(formatter)
-root.addHandler(handler)
-
-
-def index_records(client: Any, item_count: int) -> Any:
+def index_records(client: Any, index_name: str, item_count: int) -> Any:
     tt = 0
     for n in range(10):
         data: Any = []
@@ -65,6 +49,23 @@ def index_records(client: Any, item_count: int) -> Any:
 
 
 def test(thread_count: int = 1, item_count: int = 1, client_count: int = 1) -> None:
+    host = "localhost"
+    port = 9200
+    auth = ("admin", "admin")
+    index_name = "test-index-sync"
+
+    root = logging.getLogger()
+    # root.setLevel(logging.DEBUG)
+    # logging.getLogger("urllib3.connectionpool").setLevel(logging.DEBUG)
+
+    handler = logging.StreamHandler(sys.stdout)
+    handler.setLevel(logging.DEBUG)
+    formatter = logging.Formatter(
+        "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+    )
+    handler.setFormatter(formatter)
+    root.addHandler(handler)
+
     clients = []
     for i in range(client_count):
         clients.append(
@@ -96,7 +97,8 @@ def test(thread_count: int = 1, item_count: int = 1, client_count: int = 1) -> N
     threads = []
     for thread_id in range(thread_count):
         thread = ThreadWithReturnValue(
-            target=index_records, args=[clients[thread_id % len(clients)], item_count]
+            target=index_records,
+            args=[clients[thread_id % len(clients)], index_name, item_count],
         )
         threads.append(thread)
         thread.start()
@@ -113,24 +115,27 @@ def test(thread_count: int = 1, item_count: int = 1, client_count: int = 1) -> N
     print(f"{count}, latency={latency}")
 
 
+ITEM_COUNT = 1000
+
+
 def test_1() -> None:
-    test(1, 32 * item_count, 1)
+    test(1, 32 * ITEM_COUNT, 1)
 
 
 def test_2() -> None:
-    test(2, 16 * item_count, 2)
+    test(2, 16 * ITEM_COUNT, 2)
 
 
 def test_4() -> None:
-    test(4, 8 * item_count, 3)
+    test(4, 8 * ITEM_COUNT, 3)
 
 
 def test_8() -> None:
-    test(8, 4 * item_count, 8)
+    test(8, 4 * ITEM_COUNT, 8)
 
 
 def test_32() -> None:
-    test(32, item_count, 32)
+    test(32, ITEM_COUNT, 32)
 
 
 __benchmarks__ = [(test_1, test_32, "1 thread vs. 32 threads (sync)")]