Update clang-format linux hash and yaml import calls (#53932)

Summary:
Fixing Bandit security issues.
- yaml_load: Use of unsafe yaml load. Allows instantiation of arbitrary objects. Consider yaml.safe_load().
Test ID: B506
Severity: MEDIUM
Confidence: HIGH
File: ./caffe2/contrib/aten/gen_op.py
More info: https://bandit.readthedocs.io/en/latest/plugins/b506_yaml_load.html
235 if __name__ == '__main__':
236     decls = yaml.load(read(os.path.join(args.yaml_dir, 'Declarations.yaml')), Loader=Loader)
237     factory_methods = find_factory_methods(decls)

- Blacklist: Use of insecure MD2 (6149a26adb), MD4 (fc7f026980), MD5 (7ea9d9af4e), or SHA1 hash function.
Test ID: B303
Severity: MEDIUM
Confidence: HIGH
File: ./tools/clang_format_utils.py
More info: https://bandit.readthedocs.io/en/latest/blacklists/blacklist_calls.html#b303-md5
36
37     hash = hashlib.sha1()
38

Pull Request resolved: https://github.com/pytorch/pytorch/pull/53932

Reviewed By: jbschlosser

Differential Revision: D27072017

Pulled By: malfet

fbshipit-source-id: 2fef0119388797aee3cacdc880fc345bd2ba68ce

caffe2/contrib/aten/gen_op.py

@@ -47,9 +47,9 @@ OP_TEMPLATE = CT.from_file(
 
 try:
     # use faster C loader if available
-    from yaml import CLoader as Loader
+    from yaml import CSafeLoader as Loader
 except ImportError:
-    from yaml import Loader  # type: ignore[misc]
+    from yaml import SafeLoader as Loader  # type: ignore[misc]
 
 
 def write(filename, s):

test/test_namedtuple_return_api.py

@@ -26,7 +26,7 @@ class TestNamedTupleAPI(TestCase):
         operators_found = set()
         regex = re.compile(r"^(\w*)(\(|\.)")
         file = open(aten_native_yaml, 'r')
-        for f in yaml.load(file.read()):
+        for f in yaml.safe_load(file.read()):
             f = f['func']
             ret = f.split('->')[1].strip()
             name = regex.findall(f)[0][0]

tools/autograd/gen_python_functions.py

@@ -50,9 +50,9 @@ from typing import Dict, Optional, List, Tuple, Set, Sequence, Callable
 
 try:
     # use faster C loader if available
-    from yaml import CLoader as Loader
+    from yaml import CSafeLoader as Loader
 except ImportError:
-    from yaml import Loader  # type: ignore
+    from yaml import SafeLoader as Loader  # type: ignore
 
 #
 # declarations blocklist

tools/autograd/load_derivatives.py

@@ -17,9 +17,9 @@ from tools.codegen.utils import *
 
 try:
     # use faster C loader if available
-    from yaml import CLoader as Loader
+    from yaml import CSafeLoader as Loader
 except ImportError:
-    from yaml import Loader  # type: ignore
+    from yaml import SafeLoader as Loader  # type: ignore
 
 def load_derivatives(derivatives_yaml_path: str, native_yaml_path: str) -> Sequence[DifferentiabilityInfo]:
     with open(derivatives_yaml_path, 'r') as f:

tools/clang_format_hash/linux64/clang-format-linux64

@@ -1 +1 @@
-9073602de1c4e1748f2feea5a0782417b20e3043
+21ca53c291a88b53dac85751b7a0203ca610ac94b7adaff3c092cf30df4168f2

tools/clang_format_hash/mac/clang-format-mojave

@@ -1 +1 @@
-b24cc8972344c4e01afbbae78d6a414f7638ff6f
+5fde7bccf65032da297dfb1f18e4a95e96e278fa397e9dcaf364dfe23ec46353

tools/clang_format_utils.py

@@ -28,13 +28,13 @@ PLATFORM_TO_HASH = {
 CLANG_FORMAT_DIR = os.path.join(PYTORCH_ROOT, ".clang-format-bin")
 CLANG_FORMAT_PATH = os.path.join(CLANG_FORMAT_DIR, "clang-format")
 
-def compute_file_sha1(path: str) -> str:
-    """Compute the SHA1 hash of a file and return it as a hex string."""
+def compute_file_sha256(path: str) -> str:
+    """Compute the SHA256 hash of a file and return it as a hex string."""
     # If the file doesn't exist, return an empty string.
     if not os.path.exists(path):
         return ""
 
-    hash = hashlib.sha1()
+    hash = hashlib.sha256()
 
     # Open the file in binary mode and hash it.
     with open(path, "rb") as f:
@@ -84,7 +84,7 @@ def download_clang_format(path):
 def get_and_check_clang_format(verbose=False):
     """
     Download a platform-appropriate clang-format binary if one doesn't already exist at the expected location and verify
-    that it is the right binary by checking its SHA1 hash against the expected hash.
+    that it is the right binary by checking its SHA256 hash against the expected hash.
     """
     if not os.path.exists(CLANG_FORMAT_DIR):
         # If the directory doesn't exist, try to create it.
@@ -114,7 +114,7 @@ def get_and_check_clang_format(verbose=False):
                 print("Found pre-existing clang-format binary, skipping download")
 
     # Now that the binary is where it should be, hash it.
-    actual_bin_hash = compute_file_sha1(CLANG_FORMAT_PATH)
+    actual_bin_hash = compute_file_sha256(CLANG_FORMAT_PATH)
 
     # If the host platform is not in PLATFORM_TO_HASH, it is unsupported.
     if HOST_PLATFORM not in PLATFORM_TO_HASH:

tools/clang_tidy.py

@@ -173,7 +173,7 @@ def run_clang_tidy(options, line_filters, files):
 
         with open(options.config_file) as config:
             # Here we convert the YAML config file to a JSON blob.
-            command += ["-config", json.dumps(yaml.load(config, Loader=yaml.FullLoader))]
+            command += ["-config", json.dumps(yaml.load(config, Loader=yaml.SafeLoader))]
     command += options.extra_args
 
     if line_filters:

tools/codegen/gen.py

@@ -25,9 +25,9 @@ import tools.codegen.dest as dest
 
 try:
     # use faster C loader if available
-    from yaml import CLoader as Loader
+    from yaml import CSafeLoader as Loader
 except ImportError:
-    from yaml import Loader  # type: ignore
+    from yaml import SafeLoader as Loader  # type: ignore
 
 # Welcome to the ATen code generator v2!  The ATen code generator is
 # responsible for parsing native_functions.yaml and then generating

tools/codegen/selective_build/selector.py

@@ -95,13 +95,13 @@ class SelectiveBuilder:
 
     @staticmethod
     def from_yaml_str(config_contents: str) -> 'SelectiveBuilder':
-        contents = yaml.load(config_contents)
+        contents = yaml.safe_load(config_contents)
         return SelectiveBuilder.from_yaml_dict(contents)
 
     @staticmethod
     def from_yaml_path(config_path: str) -> 'SelectiveBuilder':
         with open(config_path, 'r') as f:
-            contents = yaml.load(f)
+            contents = yaml.safe_load(f)
             return SelectiveBuilder.from_yaml_dict(contents)
 
     @staticmethod

tools/setup_helpers/generate_code.py

@@ -5,9 +5,9 @@ import yaml
 
 try:
     # use faster C loader if available
-    from yaml import CLoader as YamlLoader
+    from yaml import CSafeLoader as YamlLoader
 except ImportError:
-    from yaml import Loader as YamlLoader
+    from yaml import SafeLoader as YamlLoader
 
 source_files = {'.py', '.cpp', '.h'}