Added code-smell check to verify filenames are allowed with Windows (#35436)

docs/docsite/rst/dev_guide/testing/sanity/no-illegal-filenames.rst

@@ -0,0 +1,61 @@
+Sanity Tests » no-illegal-filenames
+===================================
+
+Files and directories should not contain illegal characters or names so that
+Ansible can be checked out on any Operating System.
+
+Illegal Characters
+------------------
+
+The following characters are not allowed to be used in any part of the file or
+directory name;
+
+* ``<``
+* ``>``
+* ``:``
+* ``"``
+* ``/``
+* ``\``
+* ``|``
+* ``?``
+* ``*``
+* Any characters whose integer representations are in the range from 0 through to 31 like ``\n``
+
+The following characters are not allowed to be used as the last character of a
+file or directory;
+
+* ``.``
+* ``" "`` (just the space character)
+
+Illegal Names
+-------------
+
+The following names are not allowed to be used as the name of a file or
+directory excluding the extension;
+
+* ``CON``
+* ``PRN``
+* ``AUX``
+* ``NUL``
+* ``COM1``
+* ``COM2``
+* ``COM3``
+* ``COM4``
+* ``COM5``
+* ``COM6``
+* ``COM7``
+* ``COM8``
+* ``COM9``
+* ``LPT1``
+* ``LPT2``
+* ``LPT3``
+* ``LPT4``
+* ``LPT5``
+* ``LPT6``
+* ``LPT7``
+* ``LPT8``
+* ``LPT9``
+
+For example, the file ``folder/COM1``, ``folder/COM1.txt`` are illegal but
+``folder/COM1-file`` or ``folder/COM1-file.txt`` is allowed.
+

test/sanity/code-smell/no-illegal-filenames.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python
+
+# a script to check for illegal filenames on various Operating Systems. The
+# main rules are derived from restrictions on Windows
+# https://msdn.microsoft.com/en-us/library/aa365247#naming_conventions
+
+import os
+import struct
+
+ILLEGAL_CHARS = [
+    b'<',
+    b'>',
+    b':',
+    b'"',
+    b'/',
+    b'\\',
+    b'|',
+    b'?',
+    b'*'
+] + [struct.pack("b", i) for i in range(32)]
+
+ILLEGAL_NAMES = [
+    "CON",
+    "PRN",
+    "AUX",
+    "NUL",
+    "COM1",
+    "COM2",
+    "COM3",
+    "COM4",
+    "COM5",
+    "COM6",
+    "COM7",
+    "COM8",
+    "COM9",
+    "LPT1",
+    "LPT2",
+    "LPT3",
+    "LPT4",
+    "LPT5",
+    "LPT6",
+    "LPT7",
+    "LPT8",
+    "LPT9",
+]
+
+ILLEGAL_END_CHARS = [
+    '.',
+    ' ',
+]
+
+
+def check_path(path, dir=False):
+    errors = []
+    type_name = 'directory' if dir else 'file'
+    parent, file_name = os.path.split(path)
+    name, ext = os.path.splitext(file_name)
+
+    if name.upper() in ILLEGAL_NAMES:
+        errors.append("Illegal %s name %s: %s" % (type_name, name.upper(), path))
+
+    if file_name[-1] in ILLEGAL_END_CHARS:
+        errors.append("Illegal %s name end-char '%s': %s" % (type_name, file_name[-1], path))
+
+    bfile = file_name.encode('utf-8')
+    for char in ILLEGAL_CHARS:
+        if char in bfile:
+            errors.append("Illegal char %s in %s name: %s" % (char, type_name, path.encode('utf-8')))
+    return errors
+
+
+def main():
+    errors = []
+    for root, dirs, files in os.walk('.'):
+        for dir_name in dirs:
+            errors += check_path(os.path.abspath(os.path.join(root, dir_name)), dir=True)
+
+        for file_name in files:
+            errors += check_path(os.path.abspath(os.path.join(root, file_name)), dir=False)
+
+    if len(errors) > 0:
+        print('Ansible git repo should not contain any illegal filenames')
+        for error in errors:
+            print(error)
+        exit(1)
+
+
+if __name__ == '__main__':
+    main()