Speed up new backtracking parser (#2728)

[etc/vim.git] / src / black / files.py

diff --git a/src/black/files.py b/src/black/files.py
index de5161566052738a866ff10647396e702e2dbec1..18c84237bf0ecee74221ca48c25bc62fb995c41b 100644 (file)
--- a/src/black/files.py
+++ b/src/black/files.py
@@ -17,18 +17,21 @@ from typing import (
     TYPE_CHECKING,
 )
 
+from mypy_extensions import mypyc_attr
 from pathspec import PathSpec
-import toml
+from pathspec.patterns.gitwildmatch import GitWildMatchPatternError
+import tomli
 
 from black.output import err
 from black.report import Report
+from black.handle_ipynb_magics import jupyter_dependencies_are_installed
 
 if TYPE_CHECKING:
     import colorama  # noqa: F401
 
 
 @lru_cache()
-def find_project_root(srcs: Sequence[str]) -> Path:
+def find_project_root(srcs: Sequence[str]) -> Tuple[Path, str]:
     """Return a directory containing .git, .hg, or pyproject.toml.
 
     That directory will be a common parent of all files and directories
@@ -36,9 +39,13 @@ def find_project_root(srcs: Sequence[str]) -> Path:
 
     If no directory in the tree contains a marker that would specify it's the
     project root, the root of the file system is returned.
+
+    Returns a two-tuple with the first element as the project root path and
+    the second element as a string describing the method by which the
+    project root was discovered.
     """
     if not srcs:
-        return Path("/").resolve()
+        srcs = [str(Path.cwd().resolve())]
 
     path_srcs = [Path(Path.cwd(), src).resolve() for src in srcs]
 
@@ -55,20 +62,20 @@ def find_project_root(srcs: Sequence[str]) -> Path:
 
     for directory in (common_base, *common_base.parents):
         if (directory / ".git").exists():
-            return directory
+            return directory, ".git directory"
 
         if (directory / ".hg").is_dir():
-            return directory
+            return directory, ".hg directory"
 
         if (directory / "pyproject.toml").is_file():
-            return directory
+            return directory, "pyproject.toml"
 
-    return directory
+    return directory, "file system root"
 
 
 def find_pyproject_toml(path_search_start: Tuple[str, ...]) -> Optional[str]:
     """Find the absolute filepath to a pyproject.toml if it exists"""
-    path_project_root = find_project_root(path_search_start)
+    path_project_root, _ = find_project_root(path_search_start)
     path_pyproject_toml = path_project_root / "pyproject.toml"
     if path_pyproject_toml.is_file():
         return str(path_pyproject_toml)
@@ -86,12 +93,14 @@ def find_pyproject_toml(path_search_start: Tuple[str, ...]) -> Optional[str]:
         return None
 
 
+@mypyc_attr(patchable=True)
 def parse_pyproject_toml(path_config: str) -> Dict[str, Any]:
     """Parse a pyproject toml file, pulling out relevant parts for Black
 
-    If parsing fails, will raise a toml.TomlDecodeError
+    If parsing fails, will raise a tomli.TOMLDecodeError
     """
-    pyproject_toml = toml.load(path_config)
+    with open(path_config, "rb") as f:
+        pyproject_toml = tomli.load(f)
     config = pyproject_toml.get("tool", {}).get("black", {})
     return {k.replace("--", "").replace("-", "_"): v for k, v in config.items()}
 
@@ -120,11 +129,17 @@ def get_gitignore(root: Path) -> PathSpec:
     if gitignore.is_file():
         with gitignore.open(encoding="utf-8") as gf:
             lines = gf.readlines()
-    return PathSpec.from_lines("gitwildmatch", lines)
+    try:
+        return PathSpec.from_lines("gitwildmatch", lines)
+    except GitWildMatchPatternError as e:
+        err(f"Could not parse {gitignore}: {e}")
+        raise
 
 
 def normalize_path_maybe_ignore(
-    path: Path, root: Path, report: Report
+    path: Path,
+    root: Path,
+    report: Optional[Report] = None,
 ) -> Optional[str]:
     """Normalize `path`. May return `None` if `path` was ignored.
 
@@ -134,12 +149,16 @@ def normalize_path_maybe_ignore(
         abspath = path if path.is_absolute() else Path.cwd() / path
         normalized_path = abspath.resolve().relative_to(root).as_posix()
     except OSError as e:
-        report.path_ignored(path, f"cannot be read because {e}")
+        if report:
+            report.path_ignored(path, f"cannot be read because {e}")
         return None
 
     except ValueError:
         if path.is_symlink():
-            report.path_ignored(path, f"is a symbolic link that points outside {root}")
+            if report:
+                report.path_ignored(
+                    path, f"is a symbolic link that points outside {root}"
+                )
             return None
 
         raise
@@ -164,6 +183,9 @@ def gen_python_files(
     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,
@@ -215,9 +237,15 @@ def gen_python_files(
                 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