"""
src_node = lib2to3_parse(src_contents)
dst_contents = ""
- lines = LineGenerator()
- elt = EmptyLineTracker()
+ future_imports = get_future_imports(src_node)
py36 = is_python36(src_node)
+ lines = LineGenerator(remove_u_prefix=py36 or "unicode_literals" in future_imports)
+ elt = EmptyLineTracker()
empty_line = Line()
after = 0
for current_line in lines.visit(src_node):
in ways that will no longer stringify to valid Python code on the tree.
"""
current_line: Line = Factory(Line)
+ remove_u_prefix: bool = False
def line(self, indent: int = 0, type: Type[Line] = Line) -> Iterator[Line]:
"""Generate a line.
else:
normalize_prefix(node, inside_brackets=any_open_brackets)
if node.type == token.STRING:
+ normalize_string_prefix(node, remove_u_prefix=self.remove_u_prefix)
normalize_string_quotes(node)
if node.type not in WHITESPACE:
self.current_line.append(node)
leaf.prefix = ""
+def normalize_string_prefix(leaf: Leaf, remove_u_prefix: bool = False) -> None:
+ """Make all string prefixes lowercase.
+
+ If remove_u_prefix is given, also removes any u prefix from the string.
+
+ Note: Mutates its argument.
+ """
+ match = re.match(r"^([furbFURB]*)(.*)$", leaf.value, re.DOTALL)
+ assert match is not None, f"failed to match string {leaf.value!r}"
+ orig_prefix = match.group(1)
+ new_prefix = orig_prefix.lower()
+ if remove_u_prefix:
+ new_prefix = new_prefix.replace("u", "")
+ leaf.value = f"{new_prefix}{match.group(2)}"
+
+
def normalize_string_quotes(leaf: Leaf) -> None:
"""Prefer double quotes but only if it doesn't cause more escaping.
node.type != syms.atom
or is_empty_tuple(node)
or is_one_tuple(node)
+ or is_yield(node)
or max_delimiter_priority_in_atom(node) >= COMMA_PRIORITY
):
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:
+ return True
+
+ if node.type == token.NAME and node.value == "yield": # type: ignore
+ return True
+
+ if node.type != syms.atom:
+ return False
+
+ if len(node.children) != 3:
+ return False
+
+ lpar, expr, rpar = node.children
+ if lpar.type == token.LPAR and rpar.type == token.RPAR:
+ return is_yield(expr)
+
+ return False
+
+
def is_vararg(leaf: Leaf, within: Set[NodeType]) -> bool:
"""Return True if `leaf` is a star or double star in a vararg or kwarg.
If `within` includes VARARGS_PARENTS, this applies to function signatures.
- If `within` includes COLLECTION_LIBERALS_PARENTS, it applies to right
- hand-side extended iterable unpacking (PEP 3132) and additional unpacking
+ If `within` includes UNPACKING_PARENTS, it applies to right hand-side
+ extended iterable unpacking (PEP 3132) and additional unpacking
generalizations (PEP 448).
"""
if leaf.type not in STARS or not leaf.parent:
return False
+def get_future_imports(node: Node) -> Set[str]:
+ """Return a set of __future__ imports in the file."""
+ imports = set()
+ for child in node.children:
+ if child.type != syms.simple_stmt:
+ break
+ first_child = child.children[0]
+ if isinstance(first_child, Leaf):
+ # Continue looking if we see a docstring; otherwise stop.
+ if (
+ len(child.children) == 2
+ and first_child.type == token.STRING
+ and child.children[1].type == token.NEWLINE
+ ):
+ continue
+ else:
+ break
+ elif first_child.type == syms.import_from:
+ module_name = first_child.children[1]
+ if not isinstance(module_name, Leaf) or module_name.value != "__future__":
+ break
+ for import_from_child in first_child.children[3:]:
+ if isinstance(import_from_child, Leaf):
+ if import_from_child.type == token.NAME:
+ imports.add(import_from_child.value)
+ else:
+ assert import_from_child.type == syms.import_as_names
+ for leaf in import_from_child.children:
+ if isinstance(leaf, Leaf) and leaf.type == token.NAME:
+ imports.add(leaf.value)
+ else:
+ break
+ return imports
+
+
PYTHON_EXTENSIONS = {".py"}
BLACKLISTED_DIRECTORIES = {
"build", "buck-out", "dist", "_build", ".git", ".hg", ".mypy_cache", ".tox", ".venv"