Add underscores to numeric literals with more than six digits (#529)

[etc/vim.git] / black.py

diff --git a/black.py b/black.py
index 8d53194680309ce664af0e0a77105c31c2343824..56765313aa85b0571c7831f209573bd2b3fbb955 100644 (file)
--- a/black.py
+++ b/black.py
@@ -50,7 +50,7 @@ from blib2to3.pgen2.parse import ParseError
 __version__ = "18.6b4"
 DEFAULT_LINE_LENGTH = 88
 DEFAULT_EXCLUDES = (
-    r"/(\.git|\.hg|\.mypy_cache|\.tox|\.venv|_build|buck-out|build|dist)/"
+    r"/(\.git|\.hg|\.mypy_cache|\.nox|\.tox|\.venv|_build|buck-out|build|dist)/"
 )
 DEFAULT_INCLUDES = r"\.pyi?$"
 CACHE_DIR = Path(user_cache_dir("black", version=__version__))
@@ -79,15 +79,15 @@ syms = pygram.python_symbols
 
 
 class NothingChanged(UserWarning):
-    """Raised by :func:`format_file` when reformatted code is the same as source."""
+    """Raised when reformatted code is the same as source."""
 
 
 class CannotSplit(Exception):
-    """A readable split that fits the allotted line length is impossible.
+    """A readable split that fits the allotted line length is impossible."""
 
-    Raised by :func:`left_hand_split`, :func:`right_hand_split`, and
-    :func:`delimiter_split`.
-    """
+
+class InvalidInput(ValueError):
+    """Raised when input source code fails all parse attempts."""
 
 
 class WriteBack(Enum):
@@ -115,10 +115,16 @@ class FileMode(Flag):
     PYTHON36 = 1
     PYI = 2
     NO_STRING_NORMALIZATION = 4
+    NO_NUMERIC_UNDERSCORE_NORMALIZATION = 8
 
     @classmethod
     def from_configuration(
-        cls, *, py36: bool, pyi: bool, skip_string_normalization: bool
+        cls,
+        *,
+        py36: bool,
+        pyi: bool,
+        skip_string_normalization: bool,
+        skip_numeric_underscore_normalization: bool,
     ) -> "FileMode":
         mode = cls.AUTO_DETECT
         if py36:
@@ -127,6 +133,8 @@ class FileMode(Flag):
             mode |= cls.PYI
         if skip_string_normalization:
             mode |= cls.NO_STRING_NORMALIZATION
+        if skip_numeric_underscore_normalization:
+            mode |= cls.NO_NUMERIC_UNDERSCORE_NORMALIZATION
         return mode
 
 
@@ -196,6 +204,12 @@ def read_pyproject_toml(
     is_flag=True,
     help="Don't normalize string quotes or prefixes.",
 )
+@click.option(
+    "-N",
+    "--skip-numeric-underscore-normalization",
+    is_flag=True,
+    help="Don't normalize underscores in numeric literals.",
+)
 @click.option(
     "--check",
     is_flag=True,
@@ -286,6 +300,7 @@ def main(
     pyi: bool,
     py36: bool,
     skip_string_normalization: bool,
+    skip_numeric_underscore_normalization: bool,
     quiet: bool,
     verbose: bool,
     include: str,
@@ -296,7 +311,10 @@ def main(
     """The uncompromising code formatter."""
     write_back = WriteBack.from_configuration(check=check, diff=diff)
     mode = FileMode.from_configuration(
-        py36=py36, pyi=pyi, skip_string_normalization=skip_string_normalization
+        py36=py36,
+        pyi=pyi,
+        skip_string_normalization=skip_string_normalization,
+        skip_numeric_underscore_normalization=skip_numeric_underscore_normalization,
     )
     if config and verbose:
         out(f"Using configuration from {config}.", bold=False, fg="blue")
@@ -618,7 +636,8 @@ def format_str(
         remove_u_prefix=py36 or "unicode_literals" in future_imports,
         is_pyi=is_pyi,
         normalize_strings=normalize_strings,
-        allow_underscores=py36,
+        allow_underscores=py36
+        and not bool(mode & FileMode.NO_NUMERIC_UNDERSCORE_NORMALIZATION),
     )
     elt = EmptyLineTracker(is_pyi=is_pyi)
     empty_line = Line()
@@ -676,7 +695,7 @@ def lib2to3_parse(src_txt: str) -> Node:
                 faulty_line = lines[lineno - 1]
             except IndexError:
                 faulty_line = "<line number missing in source>"
-            exc = ValueError(f"Cannot parse: {lineno}:{column}: {faulty_line}")
+            exc = InvalidInput(f"Cannot parse: {lineno}:{column}: {faulty_line}")
     else:
         raise exc from None
 
@@ -2013,6 +2032,16 @@ def generate_comments(leaf: LN) -> Iterator[Leaf]:
 
 @dataclass
 class ProtoComment:
+    """Describes a piece of syntax that is a comment.
+
+    It's not a :class:`blib2to3.pytree.Leaf` so that:
+
+    * it can be cached (`Leaf` objects should not be reused more than once as
+      they store their lineno, column, prefix, and parent information);
+    * `newlines` and `consumed` fields are kept separate from the `value`. This
+      simplifies handling of special marker comments like ``# fmt: off/on``.
+    """
+
     type: int  # token.COMMENT or STANDALONE_COMMENT
     value: str  # content of the comment
     newlines: int  # how many newlines before the comment
@@ -2021,6 +2050,7 @@ class ProtoComment:
 
 @lru_cache(maxsize=4096)
 def list_comments(prefix: str, *, is_endmarker: bool) -> List[ProtoComment]:
+    """Return a list of :class:`ProtoComment` objects parsed from the given `prefix`."""
     result: List[ProtoComment] = []
     if not prefix or "#" not in prefix:
         return result
@@ -2531,9 +2561,13 @@ def normalize_numeric_literal(leaf: Leaf, allow_underscores: bool) -> None:
     in Python 2 long literals), and long number literals are split using underscores.
     """
     text = leaf.value.lower()
-    if text.startswith(("0o", "0x", "0b")):
-        # Leave octal, hex, and binary literals alone.
+    if text.startswith(("0o", "0b")):
+        # Leave octal and binary literals alone.
         pass
+    elif text.startswith("0x"):
+        # Change hex literals to upper case.
+        before, after = text[:2], text[2:]
+        text = f"{before}{after.upper()}"
     elif "e" in text:
         before, after = text.split("e")
         sign = ""
@@ -2585,8 +2619,8 @@ def format_int_string(
         return text
 
     text = text.replace("_", "")
-    if len(text) <= 6:
-        # No underscores for numbers <= 6 digits long.
+    if len(text) <= 5:
+        # No underscores for numbers <= 5 digits long.
         return text
 
     if count_from_end: