Add ruff precommit linting and formatting (#731)

* add ruff and pre-commit as dev-dependencies

* .py-files after ruff formatting

* output of notebook formatting - autofixed

* manual fixes to satisfy linter

* small fix to address equality test in tests/integration/test_integration_docker.py::TestMsmarcoDockerDeployment::test_instantiate_vespa_docker_from_container_name_or_id

* Add explanation about linting and formatting to README.md

.pre-commit-config.yaml

@@ -0,0 +1,13 @@
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.3.5
+  hooks:
+    # Run the linter.
+    - id: ruff
+      types_or: [ python, pyi, jupyter ]
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format
+      types_or: [ python, pyi, jupyter ]
+

README.md

@@ -25,9 +25,15 @@ Code licensed under the Apache 2.0 license. See [LICENSE](LICENSE) for terms.
 
 
 ## Development environment
-Check [screwdriver.yaml](screwdriver.yaml) to see which packages and environment variables
-need to be set to run unit and integration tests.
+To install editable version of the library with dev dependencies, run the following command from the root directory of the repository:
 
+```python
+pip install -e .[]
+```
+
+Note that this will enforce linting and formatting with [Ruff](https://github.com/astral-sh/ruff), which also will be triggered by a [pre-commit](https://pre-commit.com/)-hook.
+
+This means that you may get an error message when trying to commit changes if the code does not pass the linting and formatting checks. The errors are detailed in the output, and you can optionally run manually with `ruff` CLI-tool.
 
 ## Releases
 Find releases and release notes on [GitHub](https://github.com/vespa-engine/pyvespa/releases).

docs/sphinx/source/application-packages.ipynb

@@ -70,7 +70,8 @@
     }
    ],
    "source": [
-    "import os, tempfile\n",
+    "import os\n",
+    "import tempfile\n",
     "from pathlib import Path\n",
     "from vespa.package import ApplicationPackage\n",
     "\n",
@@ -80,7 +81,7 @@
     "temp_dir = tempfile.TemporaryDirectory()\n",
     "app_package.to_files(temp_dir.name)\n",
     "\n",
-    "for p in Path(temp_dir.name).rglob('*'):\n",
+    "for p in Path(temp_dir.name).rglob(\"*\"):\n",
     "    if p.is_file():\n",
     "        print(p)"
    ]
@@ -139,17 +140,19 @@
     "from vespa.package import Field, FieldSet, RankProfile\n",
     "\n",
     "app_package.schema.add_fields(\n",
-    "    Field(name = \"id\",    type = \"string\", indexing = [\"attribute\", \"summary\"]),\n",
-    "    Field(name = \"title\", type = \"string\", indexing = [\"index\", \"summary\"], index = \"enable-bm25\"),\n",
-    "    Field(name = \"body\",  type = \"string\", indexing = [\"index\", \"summary\"], index = \"enable-bm25\")\n",
+    "    Field(name=\"id\", type=\"string\", indexing=[\"attribute\", \"summary\"]),\n",
+    "    Field(\n",
+    "        name=\"title\", type=\"string\", indexing=[\"index\", \"summary\"], index=\"enable-bm25\"\n",
+    "    ),\n",
+    "    Field(\n",
+    "        name=\"body\", type=\"string\", indexing=[\"index\", \"summary\"], index=\"enable-bm25\"\n",
+    "    ),\n",
     ")\n",
     "\n",
-    "app_package.schema.add_field_set(\n",
-    "    FieldSet(name = \"default\", fields = [\"title\", \"body\"])\n",
-    ")\n",
+    "app_package.schema.add_field_set(FieldSet(name=\"default\", fields=[\"title\", \"body\"]))\n",
     "\n",
     "app_package.schema.add_rank_profile(\n",
-    "    RankProfile(name = \"default\", first_phase = \"bm25(title) + bm25(body)\")\n",
+    "    RankProfile(name=\"default\", first_phase=\"bm25(title) + bm25(body)\")\n",
     ")"
    ]
   },
@@ -377,7 +380,9 @@
     }
    ],
    "source": [
-    "vespa_connection = vespa_container.deploy_from_disk(application_name=app_name, application_root=temp_dir.name)"
+    "vespa_connection = vespa_container.deploy_from_disk(\n",
+    "    application_name=app_name, application_root=temp_dir.name\n",
+    ")"
    ]
   },
   {

docs/sphinx/source/conf.py

@@ -63,4 +63,4 @@
 }
 
 # anchoring with github sites will always fail
-linkcheck_ignore = [r'https://github.com/.*#.*', r'http://localhost:\d+/']
+linkcheck_ignore = [r"https://github.com/.*#.*", r"http://localhost:\d+/"]