Bump mypy to 0.780 in pre-commit config (#1887)

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

diff --git a/src/black/__init__.py b/src/black/__init__.py
index ffaafe23f9e74afbf624e7320460768a600c885b..5f0f89719f927d25327baff73d20dab7f81f13e1 100644 (file)
--- a/src/black/__init__.py
+++ b/src/black/__init__.py
@@ -68,6 +68,7 @@ DEFAULT_LINE_LENGTH = 88
 DEFAULT_EXCLUDES = r"/(\.direnv|\.eggs|\.git|\.hg|\.mypy_cache|\.nox|\.tox|\.venv|\.svn|_build|buck-out|build|dist)/"  # noqa: B950
 DEFAULT_INCLUDES = r"\.pyi?$"
 CACHE_DIR = Path(user_cache_dir("black", version=__version__))
 DEFAULT_EXCLUDES = r"/(\.direnv|\.eggs|\.git|\.hg|\.mypy_cache|\.nox|\.tox|\.venv|\.svn|_build|buck-out|build|dist)/"  # noqa: B950
 DEFAULT_INCLUDES = r"\.pyi?$"
 CACHE_DIR = Path(user_cache_dir("black", version=__version__))

+STDIN_PLACEHOLDER = "__BLACK_STDIN_FILENAME__"

 
 STRING_PREFIX_CHARS: Final = "furbFURB"  # All possible string prefix characters.
 
 
 STRING_PREFIX_CHARS: Final = "furbFURB"  # All possible string prefix characters.
 


@@ -178,14 +179,12 @@ class TargetVersion(Enum):
     PY36 = 6
     PY37 = 7
     PY38 = 8
     PY36 = 6
     PY37 = 7
     PY38 = 8

+    PY39 = 9

 
     def is_python2(self) -> bool:
         return self is TargetVersion.PY27
 
 
 
     def is_python2(self) -> bool:
         return self is TargetVersion.PY27
 
 

-PY36_VERSIONS = {TargetVersion.PY36, TargetVersion.PY37, TargetVersion.PY38}
-
-

 class Feature(Enum):
     # All string literals are unicode
     UNICODE_LITERALS = 1
 class Feature(Enum):
     # All string literals are unicode
     UNICODE_LITERALS = 1


@@ -199,6 +198,7 @@ class Feature(Enum):
     ASYNC_KEYWORDS = 7
     ASSIGNMENT_EXPRESSIONS = 8
     POS_ONLY_ARGUMENTS = 9
     ASYNC_KEYWORDS = 7
     ASSIGNMENT_EXPRESSIONS = 8
     POS_ONLY_ARGUMENTS = 9

+    RELAXED_DECORATORS = 10

     FORCE_OPTIONAL_PARENTHESES = 50
 
 
     FORCE_OPTIONAL_PARENTHESES = 50
 
 


@@ -237,6 +237,17 @@ VERSION_TO_FEATURES: Dict[TargetVersion, Set[Feature]] = {
         Feature.ASSIGNMENT_EXPRESSIONS,
         Feature.POS_ONLY_ARGUMENTS,
     },
         Feature.ASSIGNMENT_EXPRESSIONS,
         Feature.POS_ONLY_ARGUMENTS,
     },

+    TargetVersion.PY39: {
+        Feature.UNICODE_LITERALS,
+        Feature.F_STRINGS,
+        Feature.NUMERIC_UNDERSCORES,
+        Feature.TRAILING_COMMA_IN_CALL,
+        Feature.TRAILING_COMMA_IN_DEF,
+        Feature.ASYNC_KEYWORDS,
+        Feature.ASSIGNMENT_EXPRESSIONS,
+        Feature.RELAXED_DECORATORS,
+        Feature.POS_ONLY_ARGUMENTS,
+    },

 }
 
 
 }
 
 


@@ -444,7 +455,16 @@ def target_version_option_callback(
     type=str,
     help=(
         "Like --exclude, but files and directories matching this regex will be "
     type=str,
     help=(
         "Like --exclude, but files and directories matching this regex will be "

-        "excluded even when they are passed explicitly as arguments"
+        "excluded even when they are passed explicitly as arguments."
+    ),
+)
+@click.option(
+    "--stdin-filename",
+    type=str,
+    help=(
+        "The name of the file when passing it through stdin. Useful to make "
+        "sure Black will respect --force-exclude option on some "
+        "editors that rely on using stdin."

     ),
 )
 @click.option(
     ),
 )
 @click.option(


@@ -506,6 +526,7 @@ def main(
     include: str,
     exclude: str,
     force_exclude: Optional[str],
     include: str,
     exclude: str,
     force_exclude: Optional[str],

+    stdin_filename: Optional[str],

     src: Tuple[str, ...],
     config: Optional[str],
 ) -> None:
     src: Tuple[str, ...],
     config: Optional[str],
 ) -> None:


@@ -538,6 +559,7 @@ def main(
         exclude=exclude,
         force_exclude=force_exclude,
         report=report,
         exclude=exclude,
         force_exclude=force_exclude,
         report=report,

+        stdin_filename=stdin_filename,

     )
 
     path_empty(
     )
 
     path_empty(


@@ -577,6 +599,7 @@ def get_sources(
     exclude: str,
     force_exclude: Optional[str],
     report: "Report",
     exclude: str,
     force_exclude: Optional[str],
     report: "Report",

+    stdin_filename: Optional[str],

 ) -> Set[Path]:
     """Compute the set of files to be formatted."""
     try:
 ) -> Set[Path]:
     """Compute the set of files to be formatted."""
     try:


@@ -603,22 +626,14 @@ def get_sources(
     gitignore = get_gitignore(root)
 
     for s in src:
     gitignore = get_gitignore(root)
 
     for s in src:

-        p = Path(s)
-        if p.is_dir():
-            sources.update(
-                gen_python_files(
-                    p.iterdir(),
-                    root,
-                    include_regex,
-                    exclude_regex,
-                    force_exclude_regex,
-                    report,
-                    gitignore,
-                )
-            )
-        elif s == "-":
-            sources.add(p)
-        elif p.is_file():
+        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 = normalize_path_maybe_ignore(p, root, report)
             if normalized_path is None:
                 continue


@@ -633,6 +648,23 @@ def get_sources(
                 report.path_ignored(p, "matches the --force-exclude regular expression")
                 continue
 
                 report.path_ignored(p, "matches the --force-exclude regular expression")
                 continue
 

+            if is_stdin:
+                p = Path(f"{STDIN_PLACEHOLDER}{str(p)}")
+
+            sources.add(p)
+        elif p.is_dir():
+            sources.update(
+                gen_python_files(
+                    p.iterdir(),
+                    root,
+                    include_regex,
+                    exclude_regex,
+                    force_exclude_regex,
+                    report,
+                    gitignore,
+                )
+            )
+        elif s == "-":

             sources.add(p)
         else:
             err(f"invalid path: {s}")
             sources.add(p)
         else:
             err(f"invalid path: {s}")


@@ -660,7 +692,18 @@ def reformat_one(
     """
     try:
         changed = Changed.NO
     """
     try:
         changed = Changed.NO

-        if not src.is_file() and str(src) == "-":
+
+        if str(src) == "-":
+            is_stdin = True
+        elif str(src).startswith(STDIN_PLACEHOLDER):
+            is_stdin = True
+            # Use the original name again in case we want to print something
+            # to the user
+            src = Path(str(src)[len(STDIN_PLACEHOLDER) :])
+        else:
+            is_stdin = False
+
+        if is_stdin:

             if format_stdin_to_stdout(fast=fast, write_back=write_back, mode=mode):
                 changed = Changed.YES
         else:
             if format_stdin_to_stdout(fast=fast, write_back=write_back, mode=mode):
                 changed = Changed.YES
         else:


@@ -849,9 +892,9 @@ def color_diff(contents: str) -> str:
     for i, line in enumerate(lines):
         if line.startswith("+++") or line.startswith("---"):
             line = "\033[1;37m" + line + "\033[0m"  # bold white, reset
     for i, line in enumerate(lines):
         if line.startswith("+++") or line.startswith("---"):
             line = "\033[1;37m" + line + "\033[0m"  # bold white, reset

-        if line.startswith("@@"):
+        elif line.startswith("@@"):

             line = "\033[36m" + line + "\033[0m"  # cyan, reset
             line = "\033[36m" + line + "\033[0m"  # cyan, reset

-        if line.startswith("+"):
+        elif line.startswith("+"):

             line = "\033[32m" + line + "\033[0m"  # green, reset
         elif line.startswith("-"):
             line = "\033[31m" + line + "\033[0m"  # red, reset
             line = "\033[32m" + line + "\033[0m"  # green, reset
         elif line.startswith("-"):
             line = "\033[31m" + line + "\033[0m"  # red, reset


@@ -861,30 +904,22 @@ def color_diff(contents: str) -> str:
 
 def wrap_stream_for_windows(
     f: io.TextIOWrapper,
 
 def wrap_stream_for_windows(
     f: io.TextIOWrapper,

-) -> Union[io.TextIOWrapper, "colorama.AnsiToWin32.AnsiToWin32"]:
+) -> Union[io.TextIOWrapper, "colorama.AnsiToWin32"]:

     """
     """

-    Wrap the stream in colorama's wrap_stream so colors are shown on Windows.
+    Wrap stream with colorama's wrap_stream so colors are shown on Windows.

 
 

-    If `colorama` is not found, then no change is made. If `colorama` does
-    exist, then it handles the logic to determine whether or not to change
-    things.
+    If `colorama` is unavailable, the original stream is returned unmodified.
+    Otherwise, the `wrap_stream()` function determines whether the stream needs
+    to be wrapped for a Windows environment and will accordingly either return
+    an `AnsiToWin32` wrapper or the original stream.

     """
     try:
     """
     try:

-        from colorama import initialise
-
-        # We set `strip=False` so that we can don't have to modify
-        # test_express_diff_with_color.
-        f = initialise.wrap_stream(
-            f, convert=None, strip=False, autoreset=False, wrap=True
-        )
-
-        # wrap_stream returns a `colorama.AnsiToWin32.AnsiToWin32` object
-        # which does not have a `detach()` method. So we fake one.
-        f.detach = lambda *args, **kwargs: None  # type: ignore
+        from colorama.initialise import wrap_stream

     except ImportError:
     except ImportError:

-        pass
-
-    return f
+        return f
+    else:
+        # Set `strip=False` to avoid needing to modify test_express_diff_with_color.
+        return wrap_stream(f, convert=None, strip=False, autoreset=False, wrap=True)

 
 
 def format_stdin_to_stdout(
 
 
 def format_stdin_to_stdout(


@@ -951,7 +986,7 @@ def format_str(src_contents: str, *, mode: Mode) -> FileContent:
     allowed.  Example:
 
     >>> import black
     allowed.  Example:
 
     >>> import black

-    >>> print(black.format_str("def f(arg:str='')->None:...", mode=Mode()))
+    >>> print(black.format_str("def f(arg:str='')->None:...", mode=black.Mode()))

     def f(arg: str = "") -> None:
         ...
 
     def f(arg: str = "") -> None:
         ...
 


@@ -2184,6 +2219,9 @@ def whitespace(leaf: Leaf, *, complex_subscript: bool) -> str:  # noqa: C901
         ):
             # Python 2 print chevron
             return NO
         ):
             # Python 2 print chevron
             return NO

+        elif prevp.type == token.AT and p.parent and p.parent.type == syms.decorator:
+            # no space in decorators
+            return NO

 
     elif prev.type in OPENING_BRACKETS:
         return NO
 
     elif prev.type in OPENING_BRACKETS:
         return NO


@@ -3585,7 +3623,8 @@ class StringSplitter(CustomSplitMapMixin, BaseStringSplitter):
         MIN_SUBSTR_SIZE characters.
 
         The string will ONLY be split on spaces (i.e. each new substring should
         MIN_SUBSTR_SIZE characters.
 
         The string will ONLY be split on spaces (i.e. each new substring should

-        start with a space).
+        start with a space). Note that the string will NOT be split on a space
+        which is escaped with a backslash.

 
         If the string is an f-string, it will NOT be split in the middle of an
         f-expression (e.g. in f"FooBar: {foo() if x else bar()}", {foo() if x
 
         If the string is an f-string, it will NOT be split in the middle of an
         f-expression (e.g. in f"FooBar: {foo() if x else bar()}", {foo() if x


@@ -3605,13 +3644,14 @@ class StringSplitter(CustomSplitMapMixin, BaseStringSplitter):
     MIN_SUBSTR_SIZE = 6
     # Matches an "f-expression" (e.g. {var}) that might be found in an f-string.
     RE_FEXPR = r"""
     MIN_SUBSTR_SIZE = 6
     # Matches an "f-expression" (e.g. {var}) that might be found in an f-string.
     RE_FEXPR = r"""

-    (?<!\{)\{
+    (?<!\{) (?:\{\{)* \{ (?!\{)

         (?:
             [^\{\}]
             | \{\{
             | \}\}
         (?:
             [^\{\}]
             | \{\{
             | \}\}

+            | (?R)

         )+?
         )+?

-    (?<!\})(?:\}\})*\}(?!\})
+    (?<!\}) \} (?:\}\})* (?!\})

     """
 
     def do_splitter_match(self, line: Line) -> TMatchResult:
     """
 
     def do_splitter_match(self, line: Line) -> TMatchResult:


@@ -3925,11 +3965,23 @@ class StringSplitter(CustomSplitMapMixin, BaseStringSplitter):
                 section of this classes' docstring would be be met by returning @i.
             """
             is_space = string[i] == " "
                 section of this classes' docstring would be be met by returning @i.
             """
             is_space = string[i] == " "

+
+            is_not_escaped = True
+            j = i - 1
+            while is_valid_index(j) and string[j] == "\\":
+                is_not_escaped = not is_not_escaped
+                j -= 1
+

             is_big_enough = (
                 len(string[i:]) >= self.MIN_SUBSTR_SIZE
                 and len(string[:i]) >= self.MIN_SUBSTR_SIZE
             )
             is_big_enough = (
                 len(string[i:]) >= self.MIN_SUBSTR_SIZE
                 and len(string[:i]) >= self.MIN_SUBSTR_SIZE
             )

-            return is_space and is_big_enough and not breaks_fstring_expression(i)
+            return (
+                is_space
+                and is_not_escaped
+                and is_big_enough
+                and not breaks_fstring_expression(i)
+            )

 
         # First, we check all indices BELOW @max_break_idx.
         break_idx = max_break_idx
 
         # First, we check all indices BELOW @max_break_idx.
         break_idx = max_break_idx


@@ -5173,31 +5225,52 @@ def normalize_numeric_literal(leaf: Leaf) -> None:
         # Leave octal and binary literals alone.
         pass
     elif text.startswith("0x"):
         # 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()}"
+        text = format_hex(text)

     elif "e" in text:
     elif "e" in text:

-        before, after = text.split("e")
-        sign = ""
-        if after.startswith("-"):
-            after = after[1:]
-            sign = "-"
-        elif after.startswith("+"):
-            after = after[1:]
-        before = format_float_or_int_string(before)
-        text = f"{before}e{sign}{after}"
+        text = format_scientific_notation(text)

     elif text.endswith(("j", "l")):
     elif text.endswith(("j", "l")):

-        number = text[:-1]
-        suffix = text[-1]
-        # Capitalize in "2L" because "l" looks too similar to "1".
-        if suffix == "l":
-            suffix = "L"
-        text = f"{format_float_or_int_string(number)}{suffix}"
+        text = format_long_or_complex_number(text)

     else:
         text = format_float_or_int_string(text)
     leaf.value = text
 
 
     else:
         text = format_float_or_int_string(text)
     leaf.value = text
 
 

+def format_hex(text: str) -> str:
+    """
+    Formats a hexadecimal string like "0x12b3"
+
+    Uses lowercase because of similarity between "B" and "8", which
+    can cause security issues.
+    see: https://github.com/psf/black/issues/1692
+    """
+
+    before, after = text[:2], text[2:]
+    return f"{before}{after.lower()}"
+
+
+def format_scientific_notation(text: str) -> str:
+    """Formats a numeric string utilizing scentific notation"""
+    before, after = text.split("e")
+    sign = ""
+    if after.startswith("-"):
+        after = after[1:]
+        sign = "-"
+    elif after.startswith("+"):
+        after = after[1:]
+    before = format_float_or_int_string(before)
+    return f"{before}e{sign}{after}"
+
+
+def format_long_or_complex_number(text: str) -> str:
+    """Formats a long or complex string like `10L` or `10j`"""
+    number = text[:-1]
+    suffix = text[-1]
+    # Capitalize in "2L" because "l" looks too similar to "1".
+    if suffix == "l":
+        suffix = "L"
+    return f"{format_float_or_int_string(number)}{suffix}"
+
+

 def format_float_or_int_string(text: str) -> str:
     """Formats a float string like "1.0"."""
     if "." not in text:
 def format_float_or_int_string(text: str) -> str:
     """Formats a float string like "1.0"."""
     if "." not in text:


@@ -5499,6 +5572,49 @@ def is_walrus_assignment(node: LN) -> bool:
     return inner is not None and inner.type == syms.namedexpr_test
 
 
     return inner is not None and inner.type == syms.namedexpr_test
 
 

+def is_simple_decorator_trailer(node: LN, last: bool = False) -> bool:
+    """Return True iff `node` is a trailer valid in a simple decorator"""
+    return node.type == syms.trailer and (
+        (
+            len(node.children) == 2
+            and node.children[0].type == token.DOT
+            and node.children[1].type == token.NAME
+        )
+        # last trailer can be arguments
+        or (
+            last
+            and len(node.children) == 3
+            and node.children[0].type == token.LPAR
+            # and node.children[1].type == syms.argument
+            and node.children[2].type == token.RPAR
+        )
+    )
+
+
+def is_simple_decorator_expression(node: LN) -> bool:
+    """Return True iff `node` could be a 'dotted name' decorator
+
+    This function takes the node of the 'namedexpr_test' of the new decorator
+    grammar and test if it would be valid under the old decorator grammar.
+
+    The old grammar was: decorator: @ dotted_name [arguments] NEWLINE
+    The new grammar is : decorator: @ namedexpr_test NEWLINE
+    """
+    if node.type == token.NAME:
+        return True
+    if node.type == syms.power:
+        if node.children:
+            return (
+                node.children[0].type == token.NAME
+                and all(map(is_simple_decorator_trailer, node.children[1:-1]))
+                and (
+                    len(node.children) < 2
+                    or is_simple_decorator_trailer(node.children[-1], last=True)
+                )
+            )
+    return False
+
+

 def is_yield(node: LN) -> bool:
     """Return True if `node` holds a `yield` or `yield from` expression."""
     if node.type == syms.yield_expr:
 def is_yield(node: LN) -> bool:
     """Return True if `node` holds a `yield` or `yield from` expression."""
     if node.type == syms.yield_expr:


@@ -5684,6 +5800,8 @@ def get_features_used(node: Node) -> Set[Feature]:
     - underscores in numeric literals;
     - trailing commas after * or ** in function signatures and calls;
     - positional only arguments in function signatures and lambdas;
     - underscores in numeric literals;
     - trailing commas after * or ** in function signatures and calls;
     - positional only arguments in function signatures and lambdas;

+    - assignment expression;
+    - relaxed decorator syntax;

     """
     features: Set[Feature] = set()
     for n in node.pre_order():
     """
     features: Set[Feature] = set()
     for n in node.pre_order():


@@ -5703,6 +5821,12 @@ def get_features_used(node: Node) -> Set[Feature]:
         elif n.type == token.COLONEQUAL:
             features.add(Feature.ASSIGNMENT_EXPRESSIONS)
 
         elif n.type == token.COLONEQUAL:
             features.add(Feature.ASSIGNMENT_EXPRESSIONS)
 

+        elif n.type == syms.decorator:
+            if len(n.children) > 1 and not is_simple_decorator_expression(
+                n.children[1]
+            ):
+                features.add(Feature.RELAXED_DECORATORS)
+

         elif (
             n.type in {syms.typedargslist, syms.arglist}
             and n.children
         elif (
             n.type in {syms.typedargslist, syms.arglist}
             and n.children


@@ -6674,13 +6798,33 @@ def is_docstring(leaf: Leaf) -> bool:
     return False
 
 
     return False
 
 

+def lines_with_leading_tabs_expanded(s: str) -> List[str]:
+    """
+    Splits string into lines and expands only leading tabs (following the normal
+    Python rules)
+    """
+    lines = []
+    for line in s.splitlines():
+        # Find the index of the first non-whitespace character after a string of
+        # whitespace that includes at least one tab
+        match = re.match(r"\s*\t+\s*(\S)", line)
+        if match:
+            first_non_whitespace_idx = match.start(1)
+
+            lines.append(
+                line[:first_non_whitespace_idx].expandtabs()
+                + line[first_non_whitespace_idx:]
+            )
+        else:
+            lines.append(line)
+    return lines
+
+

 def fix_docstring(docstring: str, prefix: str) -> str:
     # https://www.python.org/dev/peps/pep-0257/#handling-docstring-indentation
     if not docstring:
         return ""
 def fix_docstring(docstring: str, prefix: str) -> str:
     # https://www.python.org/dev/peps/pep-0257/#handling-docstring-indentation
     if not docstring:
         return ""

-    # Convert tabs to spaces (following the normal Python rules)
-    # and split into a list of lines:
-    lines = docstring.expandtabs().splitlines()
+    lines = lines_with_leading_tabs_expanded(docstring)

     # Determine minimum indentation (first line doesn't count):
     indent = sys.maxsize
     for line in lines[1:]:
     # Determine minimum indentation (first line doesn't count):
     indent = sys.maxsize
     for line in lines[1:]: