Implement checker for copywrite header (aws-observability#6)

*Description of changes:*

In this commit, we are adding and enabling a checker that ensures a
copywrite header is added to every code file. Also we are fixing a
warning message by updating the .pylintrc to reference
"builtins.Exception" instead of "Exception". Also we apply header to
files missing it.

By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.

Author: thpierce

.pylintrc

@@ -15,8 +15,8 @@ ignore-patterns=
 ignore-paths=
 
 # Python code to execute, usually for sys.path manipulation such as
-# pygtk.require().
-#init-hook=
+# pygtk.require(). Required for custom checkers.
+init-hook='import sys; sys.path.append(".")'
 
 # Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
 # number of processors available to use.
@@ -29,7 +29,7 @@ limit-inference-results=100
 
 # List of plugins (as comma separated values of python modules names) to load,
 # usually to register additional checkers.
-load-plugins=pylint.extensions.no_self_use
+load-plugins=pylint.extensions.no_self_use,checkers.file_header_checker
 
 # Pickle collected data for later comparisons.
 persistent=yes
@@ -491,4 +491,4 @@ min-public-methods=2
 
 # Exceptions that will emit a warning when being caught. Defaults to
 # "Exception".
-overgeneral-exceptions=Exception
+overgeneral-exceptions=builtins.Exception

checkers/file_header_checker.py

@@ -0,0 +1,59 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+from pylint.checkers import BaseRawFileChecker
+
+COPYWRITE_STRING = (
+    "# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.\n"
+)
+COPYWRITE_BYTES = bytes(COPYWRITE_STRING, "utf-8")
+LICENSE_STRING = "# SPDX-License-Identifier: Apache-2.0"
+LICENSE_BYTES = bytes(LICENSE_STRING, "utf-8")
+
+
+class FileHeaderChecker(BaseRawFileChecker):
+    name = "file_header_checker"
+    msgs = {
+        "E1234": (
+            "File has missing or malformed header",
+            "missing-header",
+            "All files must have required header: \n"
+            + COPYWRITE_STRING
+            + LICENSE_STRING,
+        ),
+    }
+    options = ()
+
+    def process_module(self, node):
+        """
+        Check if the file has the required header in first and second lines of
+        the file. Some files may be scripts, which requires the first line to
+        be the shebang line, so handle that by ignoring the first line.
+        """
+        first_line = 0
+        second_line = 1
+        with node.stream() as stream:
+            for line_num, line in enumerate(stream):
+                if line_num == first_line and line.startswith(b"#!"):
+                    first_line += 1
+                    second_line += 1
+                elif line_num == first_line and is_bad_copywrite_line(line):
+                    self.add_message("missing-header", line=line_num)
+                    break
+                elif line_num == second_line and is_bad_license_line(line):
+                    self.add_message("missing-header", line=line_num)
+                    break
+                elif line_num > second_line:
+                    break
+
+
+def is_bad_copywrite_line(line: bytes) -> bool:
+    return not line.startswith(COPYWRITE_BYTES)
+
+
+def is_bad_license_line(line: bytes) -> bool:
+    return not line.startswith(LICENSE_BYTES)
+
+
+def register(linter) -> None:
+    linter.register_checker(FileHeaderChecker(linter))

scripts/check_for_valid_readme.py

@@ -1,3 +1,5 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
 """Test script to check given paths for valid README.rst files."""
 import argparse
 import sys

scripts/eachdist.py

@@ -1,4 +1,6 @@
 #!/usr/bin/env python3
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
 
 import argparse
 import os