Enable linting via ruff

.github/workflows/lint.yml

@@ -0,0 +1,13 @@
+name: pre-commit
+on:
+  pull_request:
+    branches: [main]
+  push:
+    branches: [main]
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+      - uses: pre-commit/[email protected]

.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.0.291
+    hooks:
+      - id: ruff
+        args:
+          - --fix

aarch64_linux/build_aarch64_wheel.py

@@ -301,7 +301,7 @@ def build_torchvision(host: RemoteHost, *,
         # Remove .so files to force static linking
         host.run_cmd("rm miniforge3/lib/libpng.so miniforge3/lib/libpng16.so miniforge3/lib/libjpeg.so")
         # And patch setup.py to include libz dependency for libpng
-        host.run_cmd(['sed -i -e \'s/image_link_flags\.append("png")/image_link_flags += ["png", "z"]/\' vision/setup.py'])
+        host.run_cmd(['sed -i -e \'s/image_link_flags\\.append("png")/image_link_flags += ["png", "z"]/\' vision/setup.py'])
 
     build_vars = ""
     if branch == "nightly":

analytics/cubinsizes.py

@@ -12,7 +12,7 @@
 try:
     from elftools.elf.elffile import ELFFile
 except ModuleNotFoundError:
-    print(f'elftools module not found, trying to install it from pip')
+    print('elftools module not found, trying to install it from pip')
     from pip._internal import main as pip_main
     try:
         pip_main(["install", "pyelftools", "--user"])
@@ -106,7 +106,8 @@ def main():
     if os.path.splitext(fname)[1] == '.a':
         with ArFileCtx(fname):
             for fname in os.listdir("."):
-                if not fname.endswith(".o"): continue
+                if not fname.endswith(".o"):
+                    continue
                 for section_name in section_names:
                     elf_sizes = compute_cubin_sizes(fname, section_name)
                     dict_add(results[section_name], elf_sizes)

analytics/download_count_wheels.py

@@ -140,7 +140,7 @@ def output_results(bytes_cache: dict) -> None:
 def download_logs(log_directory: str, since: float):
     dt_now = datetime.now(timezone.utc)
     dt_end = datetime(dt_now.year, dt_now.month, dt_now.day, tzinfo=timezone.utc)
-    dt_start = dt_end - timedelta(days=1, hours=1) # Add 1 hour padding to account for potentially missed logs due to timing 
+    dt_start = dt_end - timedelta(days=1, hours=1) # Add 1 hour padding to account for potentially missed logs due to timing
     for key in tqdm(BUCKET.objects.filter(Prefix='cflogs')):
         remote_fname = key.key
         local_fname = os.path.join(log_directory, remote_fname)

analytics/duplicates_analyze.py

@@ -81,7 +81,7 @@ def print_symbols_overlap(libname1: str, libname2: str) -> None:
     sym1 = get_defined_symbols(libname1, verbose=True)
     sym2 = get_defined_symbols(libname2, verbose=True)
     sym1_size = sum(sym1.values())
-    sym2_size = sum(sym2.values())
+    sum(sym2.values())
     sym_overlap = set(sym1.keys()).intersection(set(sym2.keys()))
     overlap_size = sum(sym1[s] for s in sym_overlap)
     if overlap_size == 0:

analytics/s3_test_stats_analyze.py

@@ -33,7 +33,7 @@ def _get_latests_git_commit_sha_list(lookback: int):
 def _json_to_df(data: Dict[str, Any], granularity: str) -> pd.DataFrame:
     reformed_data = list()
     for fname, fdata in data['files'].items():
-        if granularity == 'file': 
+        if granularity == 'file':
             reformed_data.append({
                 "job": data['job'],
                 "sha": data['sha'],
@@ -42,7 +42,7 @@ def _json_to_df(data: Dict[str, Any], granularity: str) -> pd.DataFrame:
             })
         else:
             for sname, sdata in fdata['suites'].items():
-                if granularity == 'suite': 
+                if granularity == 'suite':
                     reformed_data.append({
                         "job": data['job'],
                         "sha": data['sha'],
@@ -140,8 +140,8 @@ def main():
         dataframe = parse_and_export_stats(f'{cache_folder}/test_time/', granularity)
         dataframe.to_pickle(output)
 
-                
+
 
 if __name__ == "__main__":
     main()
-    
+

manywheel/build_scripts/ssl-check.py

@@ -30,4 +30,4 @@
     print("...it DIDN'T!!!!!11!!1one!")
     sys.exit(1)
 except EXC:
-    print("...it did, yay.")
+    print("...it did, yay.")

ruff.toml

@@ -0,0 +1,15 @@
+ignore = [
+    "E501",  # line too long
+    "E402",
+    "F401",
+    "F403",
+    # "W503",
+    # "W504",
+]
+line-length = 120
+select = [
+    "E",
+    "F",
+    "W",
+]
+

test/smoke_test/smoke_test.py

@@ -69,8 +69,7 @@ def check_nightly_binaries_date(package: str) -> None:
     from datetime import datetime, timedelta
     format_dt = '%Y%m%d'
 
-    torch_str = torch.__version__
-    date_t_str = re.findall("dev\d+", torch.__version__)
+    date_t_str = re.findall(r"dev\d+", torch.__version__)
     date_t_delta = datetime.now() - datetime.strptime(date_t_str[0][3:], format_dt)
     if date_t_delta.days >= NIGHTLY_ALLOWED_DELTA:
         raise RuntimeError(
@@ -81,7 +80,7 @@ def check_nightly_binaries_date(package: str) -> None:
         for module in MODULES:
             imported_module = importlib.import_module(module["name"])
             module_version = imported_module.__version__
-            date_m_str = re.findall("dev\d+", module_version)
+            date_m_str = re.findall(r"dev\d+", module_version)
             date_m_delta = datetime.now() - datetime.strptime(date_m_str[0][3:], format_dt)
             print(f"Nightly date check for {module['name']} version {module_version}")
             if date_m_delta.days > NIGHTLY_ALLOWED_DELTA:
@@ -102,7 +101,7 @@ def test_cuda_runtime_errors_captured() -> None:
         else:
             raise e
     if(cuda_exception_missed):
-        raise RuntimeError( f"Expected CUDA RuntimeError but have not received!")
+        raise RuntimeError( "Expected CUDA RuntimeError but have not received!")
 
 def smoke_test_cuda(package: str, runtime_error_check: str) -> None:
     if not torch.cuda.is_available() and is_cuda_system:
@@ -145,27 +144,27 @@ def smoke_test_conv2d() -> None:
 
     print("Testing smoke_test_conv2d")
     # With square kernels and equal stride
-    m = nn.Conv2d(16, 33, 3, stride=2)
+    nn.Conv2d(16, 33, 3, stride=2)
     # non-square kernels and unequal stride and with padding
-    m = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2))
+    nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2))
     # non-square kernels and unequal stride and with padding and dilation
     basic_conv = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2), dilation=(3, 1))
     input = torch.randn(20, 16, 50, 100)
-    output = basic_conv(input)
+    basic_conv(input)
 
     if is_cuda_system:
         print("Testing smoke_test_conv2d with cuda")
         conv = nn.Conv2d(3, 3, 3).cuda()
         x = torch.randn(1, 3, 24, 24).cuda()
         with torch.cuda.amp.autocast():
-            out = conv(x)
+            conv(x)
 
         supported_dtypes = [torch.float16, torch.float32, torch.float64]
         for dtype in supported_dtypes:
             print(f"Testing smoke_test_conv2d with cuda for {dtype}")
             conv = basic_conv.to(dtype).cuda()
             input = torch.randn(20, 16, 50, 100, device="cuda").type(dtype)
-            output = conv(input)
+            conv(input)
 
 def smoke_test_linalg() -> None:
     print("Testing smoke_test_linalg")