def gen_python_files(
paths: Iterable[Path],
root: Path,
include: Pattern[str],
exclude: Pattern[str],
extend_exclude: Optional[Pattern[str]],
force_exclude: Optional[Pattern[str]],
report: Report,
gitignore: Optional[PathSpec],
*,
verbose: bool,
quiet: bool,
) -> Iterator[Path]:
"""Generate all files under `path` whose paths are not excluded by the
`exclude_regex`, `extend_exclude`, or `force_exclude` regexes,
but are included by the `include` regex.
Symbolic links pointing outside of the `root` directory are ignored.
`report` is where output about exclusions goes.
"""
assert root.is_absolute(
), f"INTERNAL ERROR: `root` must be absolute but is {root}"
for child in paths:
normalized_path = normalize_path_maybe_ignore(child, root, report)
if normalized_path is None:
continue
# First ignore files matching .gitignore, if passed
if gitignore is not None and gitignore.match_file(normalized_path):
report.path_ignored(child, "matches the .gitignore file content")
continue
# Then ignore with `--exclude` `--extend-exclude` and `--force-exclude` options.
normalized_path = "/" + normalized_path
if child.is_dir():
normalized_path += "/"
if path_is_excluded(normalized_path, exclude):
report.path_ignored(child,
"matches the --exclude regular expression")
continue
if path_is_excluded(normalized_path, extend_exclude):
report.path_ignored(
child, "matches the --extend-exclude regular expression")
continue
if path_is_excluded(normalized_path, force_exclude):
report.path_ignored(
child, "matches the --force-exclude regular expression")
continue
if child.is_dir():
# If gitignore is None, gitignore usage is disabled, while a Falsey
# gitignore is when the directory doesn't have a .gitignore file.
yield from gen_python_files(
child.iterdir(),
root,
include,
exclude,
extend_exclude,
force_exclude,
report,
gitignore +
get_gitignore(child) if gitignore is not None else None,
verbose=verbose,
quiet=quiet,
)
elif child.is_file():
if child.suffix == ".ipynb" and not jupyter_dependencies_are_installed(
verbose=verbose, quiet=quiet):
continue
include_match = include.search(
normalized_path) if include else True
if include_match:
yield child
def get_sources(
*,
ctx: click.Context,
src: Tuple[str, ...],
quiet: bool,
verbose: bool,
include: Pattern[str],
exclude: Optional[Pattern[str]],
extend_exclude: Optional[Pattern[str]],
force_exclude: Optional[Pattern[str]],
report: "Report",
stdin_filename: Optional[str],
) -> Set[Path]:
"""Compute the set of files to be formatted."""
root = find_project_root(src)
sources: Set[Path] = set()
path_empty(src, "No Path provided. Nothing to do 😴", quiet, verbose, ctx)
if exclude is None:
exclude = re_compile_maybe_verbose(DEFAULT_EXCLUDES)
gitignore = get_gitignore(root)
else:
gitignore = None
for s in src:
if s == "-" and stdin_filename:
p = Path(stdin_filename)
is_stdin = True
else:
p = Path(s)
is_stdin = False
if is_stdin or p.is_file():
normalized_path = normalize_path_maybe_ignore(p, root, report)
if normalized_path is None:
continue
normalized_path = "/" + normalized_path
# Hard-exclude any files that matches the `--force-exclude` regex.
if force_exclude:
force_exclude_match = force_exclude.search(normalized_path)
else:
force_exclude_match = None
if force_exclude_match and force_exclude_match.group(0):
report.path_ignored(
p, "matches the --force-exclude regular expression")
continue
if is_stdin:
p = Path(f"{STDIN_PLACEHOLDER}{str(p)}")
if p.suffix == ".ipynb" and not jupyter_dependencies_are_installed(
verbose=verbose, quiet=quiet):
continue
sources.add(p)
elif p.is_dir():
sources.update(
gen_python_files(
p.iterdir(),
root,
include,
exclude,
extend_exclude,
force_exclude,
report,
gitignore,
verbose=verbose,
quiet=quiet,
))
elif s == "-":
sources.add(p)
else:
err(f"invalid path: {s}")
return sources
