[pull] main from RustPython:main

Lib/ast.py

@@ -1,28 +1,24 @@
 """
-    ast
-    ~~~
-
-    The `ast` module helps Python applications to process trees of the Python
-    abstract syntax grammar.  The abstract syntax itself might change with
-    each Python release; this module helps to find out programmatically what
-    the current grammar looks like and allows modifications of it.
-
-    An abstract syntax tree can be generated by passing `ast.PyCF_ONLY_AST` as
-    a flag to the `compile()` builtin function or by using the `parse()`
-    function from this module.  The result will be a tree of objects whose
-    classes all inherit from `ast.AST`.
-
-    A modified abstract syntax tree can be compiled into a Python code object
-    using the built-in `compile()` function.
-
-    Additionally various helper functions are provided that make working with
-    the trees simpler.  The main intention of the helper functions and this
-    module in general is to provide an easy to use interface for libraries
-    that work tightly with the python syntax (template engines for example).
-
-
-    :copyright: Copyright 2008 by Armin Ronacher.
-    :license: Python License.
+The `ast` module helps Python applications to process trees of the Python
+abstract syntax grammar.  The abstract syntax itself might change with
+each Python release; this module helps to find out programmatically what
+the current grammar looks like and allows modifications of it.
+
+An abstract syntax tree can be generated by passing `ast.PyCF_ONLY_AST` as
+a flag to the `compile()` builtin function or by using the `parse()`
+function from this module.  The result will be a tree of objects whose
+classes all inherit from `ast.AST`.
+
+A modified abstract syntax tree can be compiled into a Python code object
+using the built-in `compile()` function.
+
+Additionally various helper functions are provided that make working with
+the trees simpler.  The main intention of the helper functions and this
+module in general is to provide an easy to use interface for libraries
+that work tightly with the python syntax (template engines for example).
+
+:copyright: Copyright 2008 by Armin Ronacher.
+:license: Python License.
 """
 import sys
 import re
@@ -32,13 +28,15 @@
 
 
 def parse(source, filename='<unknown>', mode='exec', *,
-          type_comments=False, feature_version=None):
+          type_comments=False, feature_version=None, optimize=-1):
     """
     Parse the source into an AST node.
     Equivalent to compile(source, filename, mode, PyCF_ONLY_AST).
     Pass type_comments=True to get back type comments where the syntax allows.
     """
     flags = PyCF_ONLY_AST
+    if optimize > 0:
+        flags |= PyCF_OPTIMIZED_AST
     if type_comments:
         flags |= PyCF_TYPE_COMMENTS
     if feature_version is None:
@@ -50,7 +48,7 @@ def parse(source, filename='<unknown>', mode='exec', *,
         feature_version = minor
     # Else it should be an int giving the minor version for 3.x.
     return compile(source, filename, mode, flags,
-                   _feature_version=feature_version)
+                   _feature_version=feature_version, optimize=optimize)
 
 
 def literal_eval(node_or_string):
@@ -112,7 +110,11 @@ def _convert(node):
     return _convert(node_or_string)
 
 
-def dump(node, annotate_fields=True, include_attributes=False, *, indent=None):
+def dump(
+    node, annotate_fields=True, include_attributes=False,
+    *,
+    indent=None, show_empty=False,
+):
     """
     Return a formatted dump of the tree in node.  This is mainly useful for
     debugging purposes.  If annotate_fields is true (by default),
@@ -123,6 +125,8 @@ def dump(node, annotate_fields=True, include_attributes=False, *, indent=None):
     include_attributes can be set to true.  If indent is a non-negative
     integer or string, then the tree will be pretty-printed with that indent
     level. None (the default) selects the single line representation.
+    If show_empty is False, then empty lists and fields that are None
+    will be omitted from the output for better readability.
     """
     def _format(node, level=0):
         if indent is not None:
@@ -135,6 +139,7 @@ def _format(node, level=0):
         if isinstance(node, AST):
             cls = type(node)
             args = []
+            args_buffer = []
             allsimple = True
             keywords = annotate_fields
             for name in node._fields:
@@ -146,6 +151,16 @@ def _format(node, level=0):
                 if value is None and getattr(cls, name, ...) is None:
                     keywords = True
                     continue
+                if not show_empty:
+                    if value == []:
+                        field_type = cls._field_types.get(name, object)
+                        if getattr(field_type, '__origin__', ...) is list:
+                            if not keywords:
+                                args_buffer.append(repr(value))
+                            continue
+                    if not keywords:
+                        args.extend(args_buffer)
+                        args_buffer = []
                 value, simple = _format(value, level)
                 allsimple = allsimple and simple
                 if keywords:
@@ -726,12 +741,11 @@ class _Unparser(NodeVisitor):
     output source code for the abstract syntax; original formatting
     is disregarded."""
 
-    def __init__(self, *, _avoid_backslashes=False):
+    def __init__(self):
         self._source = []
         self._precedences = {}
         self._type_ignores = {}
         self._indent = 0
-        self._avoid_backslashes = _avoid_backslashes
         self._in_try_star = False
 
     def interleave(self, inter, f, seq):
@@ -1104,12 +1118,21 @@ def visit_TypeVar(self, node):
         if node.bound:
             self.write(": ")
             self.traverse(node.bound)
+        if node.default_value:
+            self.write(" = ")
+            self.traverse(node.default_value)
 
     def visit_TypeVarTuple(self, node):
         self.write("*" + node.name)
+        if node.default_value:
+            self.write(" = ")
+            self.traverse(node.default_value)
 
     def visit_ParamSpec(self, node):
         self.write("**" + node.name)
+        if node.default_value:
+            self.write(" = ")
+            self.traverse(node.default_value)
 
     def visit_TypeAlias(self, node):
         self.fill("type ")
@@ -1246,9 +1269,14 @@ def visit_JoinedStr(self, node):
                     fallback_to_repr = True
                     break
                 quote_types = new_quote_types
-            elif "\n" in value:
-                quote_types = [q for q in quote_types if q in _MULTI_QUOTES]
-                assert quote_types
+            else:
+                if "\n" in value:
+                    quote_types = [q for q in quote_types if q in _MULTI_QUOTES]
+                    assert quote_types
+
+                new_quote_types = [q for q in quote_types if q not in value]
+                if new_quote_types:
+                    quote_types = new_quote_types
             new_fstring_parts.append(value)
 
         if fallback_to_repr:
@@ -1268,13 +1296,19 @@ def visit_JoinedStr(self, node):
         quote_type = quote_types[0]
         self.write(f"{quote_type}{value}{quote_type}")
 
-    def _write_fstring_inner(self, node):
+    def _write_fstring_inner(self, node, is_format_spec=False):
         if isinstance(node, JoinedStr):
             # for both the f-string itself, and format_spec
             for value in node.values:
-                self._write_fstring_inner(value)
+                self._write_fstring_inner(value, is_format_spec=is_format_spec)
         elif isinstance(node, Constant) and isinstance(node.value, str):
             value = node.value.replace("{", "{{").replace("}", "}}")
+
+            if is_format_spec:
+                value = value.replace("\\", "\\\\")
+                value = value.replace("'", "\\'")
+                value = value.replace('"', '\\"')
+                value = value.replace("\n", "\\n")
             self.write(value)
         elif isinstance(node, FormattedValue):
             self.visit_FormattedValue(node)
@@ -1297,7 +1331,7 @@ def unparse_inner(inner):
                 self.write(f"!{chr(node.conversion)}")
             if node.format_spec:
                 self.write(":")
-                self._write_fstring_inner(node.format_spec)
+                self._write_fstring_inner(node.format_spec, is_format_spec=True)
 
     def visit_Name(self, node):
         self.write(node.id)
@@ -1317,8 +1351,6 @@ def _write_constant(self, value):
                 .replace("inf", _INFSTR)
                 .replace("nan", f"({_INFSTR}-{_INFSTR})")
             )
-        elif self._avoid_backslashes and isinstance(value, str):
-            self._write_str_avoiding_backslashes(value)
         else:
             self.write(repr(value))
 
@@ -1805,8 +1837,7 @@ def main():
     import argparse
 
     parser = argparse.ArgumentParser(prog='python -m ast')
-    parser.add_argument('infile', type=argparse.FileType(mode='rb'), nargs='?',
-                        default='-',
+    parser.add_argument('infile', nargs='?', default='-',
                         help='the file to parse; defaults to stdin')
     parser.add_argument('-m', '--mode', default='exec',
                         choices=('exec', 'single', 'eval', 'func_type'),
@@ -1820,9 +1851,14 @@ def main():
                         help='indentation of nodes (number of spaces)')
     args = parser.parse_args()
 
-    with args.infile as infile:
-        source = infile.read()
-    tree = parse(source, args.infile.name, args.mode, type_comments=args.no_type_comments)
+    if args.infile == '-':
+        name = '<stdin>'
+        source = sys.stdin.buffer.read()
+    else:
+        name = args.infile
+        with open(args.infile, 'rb') as infile:
+            source = infile.read()
+    tree = parse(source, name, args.mode, type_comments=args.no_type_comments)
     print(dump(tree, include_attributes=args.include_attributes, indent=args.indent))
 
 if __name__ == '__main__':

Lib/json/__init__.py

@@ -1,4 +1,4 @@
-r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
+r"""JSON (JavaScript Object Notation) <https://json.org> is a subset of
 JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
 interchange format.
 

Lib/json/decoder.py

@@ -41,7 +41,6 @@ def _from_serde(cls, msg, doc, line, col):
         pos += col
         return cls(msg, doc, pos)
 
-
     # Note that this exception is used from _json
     def __init__(self, msg, doc, pos):
         lineno = doc.count('\n', 0, pos) + 1
@@ -65,17 +64,18 @@ def __reduce__(self):
 }
 
 
+HEXDIGITS = re.compile(r'[0-9A-Fa-f]{4}', FLAGS)
 STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
 BACKSLASH = {
     '"': '"', '\\': '\\', '/': '/',
     'b': '\b', 'f': '\f', 'n': '\n', 'r': '\r', 't': '\t',
 }
 
-def _decode_uXXXX(s, pos):
-    esc = s[pos + 1:pos + 5]
-    if len(esc) == 4 and esc[1] not in 'xX':
+def _decode_uXXXX(s, pos, _m=HEXDIGITS.match):
+    esc = _m(s, pos + 1)
+    if esc is not None:
         try:
-            return int(esc, 16)
+            return int(esc.group(), 16)
         except ValueError:
             pass
     msg = "Invalid \\uXXXX escape"
@@ -215,10 +215,13 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
             break
         elif nextchar != ',':
             raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
+        comma_idx = end - 1
         end = _w(s, end).end()
         nextchar = s[end:end + 1]
         end += 1
         if nextchar != '"':
+            if nextchar == '}':
+                raise JSONDecodeError("Illegal trailing comma before end of object", s, comma_idx)
             raise JSONDecodeError(
                 "Expecting property name enclosed in double quotes", s, end - 1)
     if object_pairs_hook is not None:
@@ -255,19 +258,23 @@ def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
             break
         elif nextchar != ',':
             raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
+        comma_idx = end - 1
         try:
             if s[end] in _ws:
                 end += 1
                 if s[end] in _ws:
                     end = _w(s, end + 1).end()
+            nextchar = s[end:end + 1]
         except IndexError:
             pass
+        if nextchar == ']':
+            raise JSONDecodeError("Illegal trailing comma before end of array", s, comma_idx)
 
     return values, end
 
 
 class JSONDecoder(object):
-    """Simple JSON <http://json.org> decoder
+    """Simple JSON <https://json.org> decoder
 
     Performs the following translations in decoding by default: