Sort default excludes, include the leading slash

[etc/vim.git] / black.py

diff --git a/black.py b/black.py
index 4599bdd98a9ae536bb25c27d4b3d1511e0523f17..61b884ad262ccf3e08a0fc380f5cd9607839515c 100644 (file)
--- a/black.py
+++ b/black.py
@@ -46,6 +46,10 @@ from blib2to3.pgen2.parse import ParseError
 
 __version__ = "18.5b1"
 DEFAULT_LINE_LENGTH = 88
+DEFAULT_EXCLUDES = (
+    r"/(\.git|\.hg|\.mypy_cache|\.tox|\.venv|_build|buck-out|build|dist)/"
+)
+DEFAULT_INCLUDES = r"\.pyi?$"
 CACHE_DIR = Path(user_cache_dir("black", version=__version__))
 
 
@@ -189,6 +193,28 @@ class FileMode(Flag):
     is_flag=True,
     help="Don't normalize string quotes or prefixes.",
 )
+@click.option(
+    "--include",
+    type=str,
+    default=DEFAULT_INCLUDES,
+    help=(
+        "A regular expression that matches files and directories that should be "
+        "included on recursive searches. On Windows, use forward slashes for "
+        "directories."
+    ),
+    show_default=True,
+)
+@click.option(
+    "--exclude",
+    type=str,
+    default=DEFAULT_EXCLUDES,
+    help=(
+        "A regular expression that matches files and directories that should be "
+        "excluded on recursive searches. On Windows, use forward slashes for "
+        "directories."
+    ),
+    show_default=True,
+)
 @click.version_option(version=__version__)
 @click.argument(
     "src",
@@ -208,14 +234,26 @@ def main(
     py36: bool,
     skip_string_normalization: bool,
     quiet: bool,
+    include: str,
+    exclude: str,
     src: List[str],
 ) -> None:
     """The uncompromising code formatter."""
     sources: List[Path] = []
+    try:
+        include_regex = re.compile(include)
+    except re.error:
+        err(f"Invalid regular expression for include given: {include!r}")
+        ctx.exit(2)
+    try:
+        exclude_regex = re.compile(exclude)
+    except re.error:
+        err(f"Invalid regular expression for exclude given: {exclude!r}")
+        ctx.exit(2)
     for s in src:
         p = Path(s)
         if p.is_dir():
-            sources.extend(gen_python_files_in_dir(p))
+            sources.extend(gen_python_files_in_dir(p, include_regex, exclude_regex))
         elif p.is_file():
             # if a file was explicitly given, we don't care about its extension
             sources.append(p)
@@ -2750,33 +2788,35 @@ def get_future_imports(node: Node) -> Set[str]:
     return imports
 
 
-PYTHON_EXTENSIONS = {".py", ".pyi"}
-BLACKLISTED_DIRECTORIES = {
-    "build",
-    "buck-out",
-    "dist",
-    "_build",
-    ".git",
-    ".hg",
-    ".mypy_cache",
-    ".tox",
-    ".venv",
-}
-
-
-def gen_python_files_in_dir(path: Path) -> Iterator[Path]:
-    """Generate all files under `path` which aren't under BLACKLISTED_DIRECTORIES
-    and have one of the PYTHON_EXTENSIONS.
+def gen_python_files_in_dir(
+    path: Path, include: Pattern[str], exclude: Pattern[str]
+) -> Iterator[Path]:
+    """Generate all files under `path` whose paths are not excluded by the
+    `exclude` regex, but are included by the `include` regex.
     """
+
     for child in path.iterdir():
+        searchable_path = str(child.as_posix())
+        if Path(child.parts[0]).is_dir():
+            searchable_path = "/" + searchable_path
         if child.is_dir():
-            if child.name in BLACKLISTED_DIRECTORIES:
+            searchable_path = searchable_path + "/"
+            exclude_match = exclude.search(searchable_path)
+            if exclude_match and len(exclude_match.group()) > 0:
                 continue
 
-            yield from gen_python_files_in_dir(child)
+            yield from gen_python_files_in_dir(child, include, exclude)
 
-        elif child.is_file() and child.suffix in PYTHON_EXTENSIONS:
-            yield child
+        else:
+            include_match = include.search(searchable_path)
+            exclude_match = exclude.search(searchable_path)
+            if (
+                child.is_file()
+                and include_match
+                and len(include_match.group()) > 0
+                and (not exclude_match or len(exclude_match.group()) == 0)
+            ):
+                yield child
 
 
 @dataclass