Lines Matching +full:bom +full:- +full:path

4 # SPDX-License-Identifier: Apache-2.0 OR GPL-2.0-or-later
8 including incorrect file permissions, presence of tabs, non-Unix line endings,
9 trailing whitespace, and presence of UTF-8 BOM.
21     from typing import FrozenSet, Optional, Pattern # pylint: disable=unused-import
25 import scripts_path # pylint: disable=unused-import
30     """Base class for file-wide issue tracking.
38     ``path_exemptions``: files whose path (relative to the root of the source
40     ``None`` to match no path. Paths are normalized and converted to ``/``
43     ``heading``: human-readable description of the issue
49     # pylint: disable=no-member
57         filepath = os.path.normpath(filepath)
60         seps = os.path.sep
61         if os.path.altsep is not None:
62             seps += os.path.altsep
69         or whose path matches ``self.path_exemptions`` will not be checked.
118     """Base class for line-by-line issue tracking.
149     _root, ext = os.path.splitext(filepath)
183     _shebang_re = re.compile(rb'^#! ?(?:/bin/(bash|sh)(?: -[^\n ]*)?'
209                 # Shebang on a non-executable file
229                 f.seek(-1, 2)
240     """Track files that start with a UTF-8 BOM.
241     Files should be ASCII or UTF-8. Valid UTF-8 does not start with a BOM."""
243     heading = "UTF-8 BOM present:"
257     heading = "Invalid UTF-8 or forbidden character:"
259     # Only allow valid UTF-8, and only other explicitly allowed characters.
260     # We deliberately exclude all characters that aren't a simple non-blank,
261     # non-zero-width glyph, apart from a very small set (tab, ordinary space,
262     # line breaks, "basic" no-break space and soft hyphen). In particular,
263     # non-ASCII control characters, combinig characters, and Unicode state
264     # changes (e.g. right-to-left text) are forbidden.
266     # for example '-' (U+002D HYPHEN-MINUS) vs '­' (U+00AD SOFT HYPHEN) vs
270         '\t\n\r -~', # ASCII (tabs and line endings are checked separately)
271         '\u00A0-\u00FF', # Latin-1 Supplement (for NO-BREAK SPACE and punctuation)
272         '\u2010-\u2027\u2030-\u205E', # General Punctuation (printable)
273         '\u2070\u2071\u2074-\u208E\u2090-\u209C', # Superscripts and Subscripts
274         '\u2190-\u21FF', # Arrows
275         '\u2200-\u22FF', # Mathematical Symbols
276         '\u2500-\u257F' # Box Drawings characters used in markdown trees
284             text = line.decode('utf-8')
288             # Strip BOM (U+FEFF ZERO WIDTH NO-BREAK SPACE) at the beginning.
289             # Which files are allowed to have a BOM is handled in
295     """Track files with non-Unix line endings (i.e. files with CR)."""
297     heading = "Non-Unix line endings:"
309     """Track files with non-Windows line endings (i.e. CR or LF not in CRLF)."""
311     heading = "Non-Windows line endings:"
319         return not line.endswith(b"\r\n") or b"\r" in line[:-2]
367     """Sanity-check files under the current directory."""
401         bytes_output = subprocess.check_output(['git', 'ls-files', '-z'])
402         bytes_filepaths = bytes_output.split(b'\0')[:-1]
404         # Prepend './' to files in the top-level directory so that
405         # something like `'/Makefile' in fp` matches in the top-level
407         return [fp if os.path.dirname(fp) else os.path.join(os.curdir, fp)
428         "-l", "--log_file", type=str, help="path to optional output log",