chore: enhance pre-commit setup and correct installation instructions

cdragos · cdragos · commit 6e52f4b4ecde · 2024-07-04T14:36:05.000+08:00
- Add installation instructions for contributors to CONTRIBUTING.md
- Add pre-commit hooks setup guide to CONTRIBUTING.md
- Update package dependencies for pre-commit
- Integrate pyupgrade and apply to all files
- Update README to align installation instructions with setup.py
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -6,22 +6,22 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v4.6.0
     hooks:
-      - id: end-of-file-fixer
-      - id: trailing-whitespace
-      - id: check-yaml
+      - id: check-added-large-files
+      - id: check-case-conflict
       - id: check-docstring-first
       - id: check-executables-have-shebangs
       - id: check-toml
-      - id: check-case-conflict
-      - id: check-added-large-files
+      - id: check-yaml
       - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: end-of-file-fixer
       - id: forbid-new-submodules
+      - id: mixed-line-ending
       - id: pretty-format-json
         args: ['--autofix', '--no-sort-keys', '--indent=4']
-      - id: end-of-file-fixer
-      - id: mixed-line-ending
+      - id: trailing-whitespace
 
 
   - repo: https://github.com/PyCQA/isort
@@ -31,7 +31,7 @@ repos:
         name: Sort imports
 
   - repo: https://github.com/PyCQA/flake8
-    rev: 6.1.0
+    rev: 7.1.0
     hooks:
       - id: flake8
         name: Flake8 Checks
@@ -40,14 +40,20 @@ repos:
 
 
   -   repo: https://github.com/PyCQA/bandit
-      rev: '1.7.6'
+      rev: 1.7.9
       hooks:
       -   id: bandit
           args: ["-c", "pyproject.toml"]
           additional_dependencies: ["bandit[toml]"]
 
   -   repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.1.9
+      rev: v0.5.0
       hooks:
       -   id: ruff
           args: [--fix, --exit-non-zero-on-fix]
+
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.16.0
+    hooks:
+      - id: pyupgrade
+        args: [--py38-plus]
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -5,6 +5,27 @@ If you want to extend our Python library or if you find a bug, please open a PR!
 
 Also be sure to test your code with the `unittest` command at the `/root` level directory.
 
+## Installation for Contributors
+
+Before starting your work on the project, set up your development environment:
+
+1. Clone the repository:
+```bash
+git clone https://github.com/roboflow-ai/roboflow-python.git
+cd roboflow-python
+```
+
+2. Create and activate a virtual environment:
+```bash
+python3 -m venv env
+source env/bin/activate
+```
+
+3.Install the package in editable mode with development dependencies:
+```bash
+pip install -e ".[dev]"
+```
+
 ### Devcontainer
 
 This project comes with a [convenient devcontainer](https://www.loom.com/share/a183c4a351ed4700a79476fedf08ab9b) that makes it easier to run tests and has black configured to run on save.
@@ -54,3 +75,25 @@ Before that, install the dependencies:
 ```python
 python -m pip install mkdocs mkdocs-material mkdocstrings mkdocstrings[python]
 ```
+
+### Pre-commit Hooks
+
+To ensure code quality and consistency, we use pre-commit hooks. Follow these steps to set up pre-commit in your development environment:
+
+1. Install pre-commit:
+```bash
+pip install pre-commit
+```
+
+2. Install the git hook scripts:
+```bash
+pre-commit install
+```
+
+After installation, `pre-commit` will automatically run on git commit. The hooks perform checks and corrections related to code formatting, linting, and other rules as defined in the `.pre-commit-config.yaml` file.
+
+Note: If you need to bypass pre-commit hooks temporarily, you can use the `--no-verify` flag:
+
+```bash
+git commit --no-verify -m "Your commit message"
+```
diff --git a/README.md b/README.md
@@ -44,6 +44,13 @@ Run the following command to install the Roboflow Python package:
 pip install roboflow
 ```
 
+For desktop features, use:
+
+```bash
+pip install "roboflow[desktop]"
+```
+
+
 <details>
   <summary>Install from source</summary>
 
@@ -54,7 +61,7 @@ pip install roboflow
   cd roboflow-python
   python3 -m venv env
   source env/bin/activate
-  pip3 install -r requirements.txt
+  pip install .
   ```
 </details>
 
diff --git a/roboflow/__init__.py b/roboflow/__init__.py
@@ -20,7 +20,7 @@
 def check_key(api_key, model, notebook, num_retries=0):
     if not isinstance(api_key, str):
         raise RuntimeError(
-            "API Key is of Incorrect Type \n Expected Type: " + str(type("")) + "\n Input Type: " + str(type(api_key))
+            "API Key is of Incorrect Type \n Expected Type: " + str(str) + "\n Input Type: " + str(type(api_key))
         )
 
     if any(c for c in api_key if c.islower()):  # check if any of the api key characters are lowercase
diff --git a/roboflow/core/project.py b/roboflow/core/project.py
@@ -335,7 +335,7 @@ def version(self, version_number: int, local: Optional[str] = None):
                 )
                 return vers
 
-        raise RuntimeError("Version number {} is not found.".format(version_number))
+        raise RuntimeError(f"Version number {version_number} is not found.")
 
     def check_valid_image(self, image_path: str):
         """
@@ -534,8 +534,8 @@ def _annotation_params(self, annotation_path):
             annotation_name = annotation_path["name"]
             annotation_string = annotation_path["rawText"]
         elif os.path.exists(annotation_path):
-            with open(annotation_path, "r"):
-                annotation_string = open(annotation_path, "r").read()
+            with open(annotation_path):
+                annotation_string = open(annotation_path).read()
             annotation_name = os.path.basename(annotation_path)
         elif self.type == "classification":
             print(f"-> using {annotation_path} as classname for classification project")
diff --git a/roboflow/core/version.py b/roboflow/core/version.py
@@ -541,7 +541,7 @@ def deploy(self, model_type: str, model_path: str, filename: str = "weights/best
         elif "yolov5" in model_type or "yolov7" in model_type or "yolov9" in model_type:
             # parse from yaml for yolov5
 
-            with open(os.path.join(model_path, "opt.yaml"), "r") as stream:
+            with open(os.path.join(model_path, "opt.yaml")) as stream:
                 opts = yaml.safe_load(stream)
 
             model_artifacts = {
@@ -651,7 +651,7 @@ def deploy_yolonas(self, model_type: str, model_path: str, filename: str = "weig
                 f"architecture: <one of [yolo_nas_s, yolo_nas_m, yolo_nas_l]."
                 f"s, m, l refer to small, medium, large architecture sizes, respectively>\n"
             )
-        with open(os.path.join(model_path, "opt.yaml"), "r") as stream:
+        with open(os.path.join(model_path, "opt.yaml")) as stream:
             opts = yaml.safe_load(stream)
         required_keys = ["imgsz", "batch_size", "architecture"]
         for key in required_keys:
diff --git a/roboflow/core/workspace.py b/roboflow/core/workspace.py
@@ -82,7 +82,7 @@ def project(self, project_id):
         # project_id = project_id.replace(self.url + "/", "")
 
         if "/" in project_id:
-            raise RuntimeError("The {} project is not available in this ({}) workspace".format(project_id, self.url))
+            raise RuntimeError(f"The {project_id} project is not available in this ({self.url}) workspace")
 
         dataset_info = rfapi.get_project(self.__api_key, self.url, project_id)
         dataset_info = dataset_info["project"]
diff --git a/roboflow/models/classification.py b/roboflow/models/classification.py
@@ -46,7 +46,7 @@ def __init__(
             ClassificationModel Object
         """
         # Instantiate different API URL parameters
-        super(ClassificationModel, self).__init__(api_key, id, version=version)
+        super().__init__(api_key, id, version=version)
         self.__api_key = api_key
         self.id = id
         self.name = name
diff --git a/roboflow/models/instance_segmentation.py b/roboflow/models/instance_segmentation.py
@@ -28,7 +28,7 @@ def __init__(
             preprocessing (dict): preprocessing to use for the image
             local (str): localhost address and port if pointing towards local inference engine
         """
-        super(InstanceSegmentationModel, self).__init__(api_key, version_id)
+        super().__init__(api_key, version_id)
 
         base_url = local or INSTANCE_SEGMENTATION_URL
         self.api_url = f"{base_url}/{self.dataset_id}/{self.version}"
@@ -57,7 +57,7 @@ def predict(self, image_path, confidence=40):
 
             >>> prediction = model.predict("YOUR_IMAGE.jpg")
         """  # noqa: E501
-        return super(InstanceSegmentationModel, self).predict(
+        return super().predict(
             image_path,
             confidence=confidence,
             prediction_type=INSTANCE_SEGMENTATION_MODEL,
diff --git a/roboflow/models/keypoint_detection.py b/roboflow/models/keypoint_detection.py
@@ -44,7 +44,7 @@ def __init__(
             ClassificationModel Object
         """
         # Instantiate different API URL parameters
-        super(KeypointDetectionModel, self).__init__(api_key, id, version=version)
+        super().__init__(api_key, id, version=version)
         self.__api_key = api_key
         self.id = id
         self.name = name
diff --git a/roboflow/models/object_detection.py b/roboflow/models/object_detection.py
@@ -66,7 +66,7 @@ def __init__(
         """  # noqa: E501 // docs
         # Instantiate different API URL parameters
         # To be moved to predict
-        super(ObjectDetectionModel, self).__init__(api_key, id)
+        super().__init__(api_key, id)
         self.__api_key = api_key
         self.id = id
         self.name = name
diff --git a/roboflow/models/semantic_segmentation.py b/roboflow/models/semantic_segmentation.py
@@ -15,7 +15,7 @@ def __init__(self, api_key: str, version_id: str):
             api_key (str): private roboflow api key
             version_id (str): the workspace/project id
         """  # noqa: E501 // docs
-        super(SemanticSegmentationModel, self).__init__(api_key, version_id)
+        super().__init__(api_key, version_id)
         self.api_url = f"{SEMANTIC_SEGMENTATION_URL}/{self.dataset_id}/{self.version}"
 
     def predict(self, image_path: str, confidence: int = 50):  # type: ignore[override]
@@ -40,7 +40,7 @@ def predict(self, image_path: str, confidence: int = 50):  # type: ignore[overri
 
             >>> prediction = model.predict("YOUR_IMAGE.jpg")
         """  # noqa: E501 // docs
-        return super(SemanticSegmentationModel, self).predict(
+        return super().predict(
             image_path,
             confidence=confidence,
             prediction_type=SEMANTIC_SEGMENTATION_MODEL,
diff --git a/roboflow/util/folderparser.py b/roboflow/util/folderparser.py
@@ -191,7 +191,7 @@ def _loadAnnotations(folder, annotations):
     for ann in annotations:
         extension = ann["extension"]
         if extension == ".json":
-            with open(f"{folder}{ann['file']}", "r") as f:
+            with open(f"{folder}{ann['file']}") as f:
                 parsed = json.load(f)
                 parsedType = _guessAnnotationFileFormat(parsed, extension)
                 if parsedType:
@@ -205,7 +205,7 @@ def _loadAnnotations(folder, annotations):
 
 def _parseAnnotationCSV(filename):
     # TODO: use a proper CSV library?
-    with open(filename, "r") as f:
+    with open(filename) as f:
         lines = f.readlines()
     headers = lines[0]
     lines = [{"file_name": ld.split(",")[0].strip(), "line": ld} for ld in lines[1:]]
diff --git a/roboflow/util/image_utils.py b/roboflow/util/image_utils.py
@@ -81,11 +81,11 @@ def file2jpeg(image_path):
 
 def load_labelmap(f):
     if f.lower().endswith(".yaml") or f.lower().endswith(".yml"):
-        with open(f, "r") as file:
+        with open(f) as file:
             data = yaml.safe_load(file)
             if "names" in data:
                 return {i: name for i, name in enumerate(data["names"])}
     else:
-        with open(f, "r") as file:
+        with open(f) as file:
             lines = [line for line in file.readlines() if line.strip()]
         return {i: line.strip() for i, line in enumerate(lines)}
diff --git a/setup.py b/setup.py
@@ -3,17 +3,17 @@
 import setuptools
 from setuptools import find_packages
 
-with open("./roboflow/__init__.py", "r") as f:
+with open("./roboflow/__init__.py") as f:
     content = f.read()
 _search_version = re.search(r'__version__\s*=\s*[\'"]([^\'"]*)[\'"]', content)
 assert _search_version
 version = _search_version.group(1)
 
 
-with open("README.md", "r") as fh:
+with open("README.md") as fh:
     long_description = fh.read()
 
-with open("requirements.txt", "r") as fh:
+with open("requirements.txt") as fh:
     install_requires = fh.read().split("\n")
 
 setuptools.setup(
diff --git a/tests/__init__.py b/tests/__init__.py
@@ -34,7 +34,7 @@ def compare(a, b):
 
 class RoboflowTest(unittest.TestCase):
     def setUp(self):
-        super(RoboflowTest, self).setUp()
+        super().setUp()
         responses.start()
 
         # Check key
@@ -221,7 +221,7 @@ def setUp(self):
         self.connect_to_roboflow()
 
     def tearDown(self):
-        super(RoboflowTest, self).tearDown()
+        super().tearDown()
         responses.stop()
         responses.reset()
 
diff --git a/tests/models/test_instance_segmentation.py b/tests/models/test_instance_segmentation.py
@@ -54,7 +54,7 @@ class TestInstanceSegmentation(unittest.TestCase):
     }
 
     def setUp(self):
-        super(TestInstanceSegmentation, self).setUp()
+        super().setUp()
         self.version_id = f"{self.workspace}/{self.dataset_id}/{self.version}"
 
     def test_init_sets_attributes(self):
diff --git a/tests/models/test_object_detection.py b/tests/models/test_object_detection.py
@@ -43,7 +43,7 @@ class TestObjectDetection(unittest.TestCase):
     }
 
     def setUp(self):
-        super(TestObjectDetection, self).setUp()
+        super().setUp()
         self.version_id = f"{self.workspace}/{self.dataset_id}/{self.version}"
 
     def test_init_sets_attributes(self):
diff --git a/tests/test_version.py b/tests/test_version.py
@@ -11,7 +11,7 @@
 
 class TestDownload(unittest.TestCase):
     def setUp(self):
-        super(TestDownload, self).setUp()
+        super().setUp()
         self.api_url = "https://api.roboflow.com/test-workspace/test-project/4/coco"
         self.version = get_version(
             project_name="Test Dataset",
@@ -64,7 +64,7 @@ def test_download_returns_dataset(self, *_):
 
 class TestExport(unittest.TestCase):
     def setUp(self):
-        super(TestExport, self).setUp()
+        super().setUp()
         self.api_url = "https://api.roboflow.com/test-workspace/test-project/4/test-format"
         self.version = get_version(
             project_name="Test Dataset",
@@ -115,7 +115,7 @@ def test_export_raises_error_on_api_failure(self):
 @patch.object(os, "makedirs")
 class TestGetDownloadLocation(unittest.TestCase):
     def setUp(self, *_):
-        super(TestGetDownloadLocation, self).setUp()
+        super().setUp()
         self.version = get_version(
             project_name="Test Dataset",
             id="test-workspace/test-project/2",
@@ -148,7 +148,7 @@ def test_get_download_location_without_env_variable(self, *_):
 
 class TestGetDownloadURL(unittest.TestCase):
     def setUp(self):
-        super(TestGetDownloadURL, self).setUp()
+        super().setUp()
         self.version = get_version(
             project_name="Test Dataset",
             id="test-workspace/test-project/2",
@@ -172,7 +172,7 @@ def test_get_download_url(self):
 
 class TestGetFormatIdentifier(unittest.TestCase):
     def setUp(self):
-        super(TestGetFormatIdentifier, self).setUp()
+        super().setUp()
         self.version = get_version(
             project_name="Test Dataset",
             id="test-workspace/test-project/2",
diff --git a/tests/util/test_folderparser.py b/tests/util/test_folderparser.py

Original file line number	Diff line number	Diff line change
`@@ -20,7 +20,7 @@`
`20`	`20`	`def check_key(api_key, model, notebook, num_retries=0):`
`21`	`21`	`if not isinstance(api_key, str):`
`22`	`22`	`raise RuntimeError(`
`23`		`- "API Key is of Incorrect Type \n Expected Type: " + str(type("")) + "\n Input Type: " + str(type(api_key))`
	`23`	`+ "API Key is of Incorrect Type \n Expected Type: " + str(str) + "\n Input Type: " + str(type(api_key))`
`24`	`24`	`)`
`25`	`25`
`26`	`26`	`if any(c for c in api_key if c.islower()): # check if any of the api key characters are lowercase`