From c27af42dfb0c09e3888acf05526b826d7340d9f6 Mon Sep 17 00:00:00 2001 From: Reid 'arrdem' McKenzie Date: Wed, 8 Mar 2023 15:28:56 -0700 Subject: [PATCH] Import the upstream Python unit tests covering tokenize and ast --- components/uast/test/python/test_ast.py | 2702 +++++++++++++++++ .../utokenize/test/python/test_tokenize.py | 2651 ++++++++++++++++ 2 files changed, 5353 insertions(+) create mode 100644 components/uast/test/python/test_ast.py create mode 100644 components/utokenize/test/python/test_tokenize.py diff --git a/components/uast/test/python/test_ast.py b/components/uast/test/python/test_ast.py new file mode 100644 index 0000000..7c9a57c --- /dev/null +++ b/components/uast/test/python/test_ast.py @@ -0,0 +1,2702 @@ +import ast +import builtins +import dis +import enum +import os +import sys +import types +import unittest +import warnings +import weakref +from textwrap import dedent + +from test import support +from test.support.ast_helper import ASTTestMixin + +def to_tuple(t): + if t is None or isinstance(t, (str, int, complex)) or t is Ellipsis: + return t + elif isinstance(t, list): + return [to_tuple(e) for e in t] + result = [t.__class__.__name__] + if hasattr(t, 'lineno') and hasattr(t, 'col_offset'): + result.append((t.lineno, t.col_offset)) + if hasattr(t, 'end_lineno') and hasattr(t, 'end_col_offset'): + result[-1] += (t.end_lineno, t.end_col_offset) + if t._fields is None: + return tuple(result) + for f in t._fields: + result.append(to_tuple(getattr(t, f))) + return tuple(result) + + +# These tests are compiled through "exec" +# There should be at least one test per statement +exec_tests = [ + # None + "None", + # Module docstring + "'module docstring'", + # FunctionDef + "def f(): pass", + # FunctionDef with docstring + "def f(): 'function docstring'", + # FunctionDef with arg + "def f(a): pass", + # FunctionDef with arg and default value + "def f(a=0): pass", + # FunctionDef with varargs + "def f(*args): pass", + # FunctionDef with varargs as TypeVarTuple + "def f(*args: *Ts): pass", + # FunctionDef with varargs as unpacked Tuple + "def f(*args: *tuple[int, ...]): pass", + # FunctionDef with varargs as unpacked Tuple *and* TypeVarTuple + "def f(*args: *tuple[int, *Ts]): pass", + # FunctionDef with kwargs + "def f(**kwargs): pass", + # FunctionDef with all kind of args and docstring + "def f(a, b=1, c=None, d=[], e={}, *args, f=42, **kwargs): 'doc for f()'", + # FunctionDef with type annotation on return involving unpacking + "def f() -> tuple[*Ts]: pass", + "def f() -> tuple[int, *Ts]: pass", + "def f() -> tuple[int, *tuple[int, ...]]: pass", + # ClassDef + "class C:pass", + # ClassDef with docstring + "class C: 'docstring for class C'", + # ClassDef, new style class + "class C(object): pass", + # Return + "def f():return 1", + # Delete + "del v", + # Assign + "v = 1", + "a,b = c", + "(a,b) = c", + "[a,b] = c", + # AnnAssign with unpacked types + "x: tuple[*Ts]", + "x: tuple[int, *Ts]", + "x: tuple[int, *tuple[str, ...]]", + # AugAssign + "v += 1", + # For + "for v in v:pass", + # While + "while v:pass", + # If + "if v:pass", + # If-Elif + "if a:\n pass\nelif b:\n pass", + # If-Elif-Else + "if a:\n pass\nelif b:\n pass\nelse:\n pass", + # With + "with x as y: pass", + "with x as y, z as q: pass", + # Raise + "raise Exception('string')", + # TryExcept + "try:\n pass\nexcept Exception:\n pass", + # TryFinally + "try:\n pass\nfinally:\n pass", + # TryStarExcept + "try:\n pass\nexcept* Exception:\n pass", + # Assert + "assert v", + # Import + "import sys", + # ImportFrom + "from sys import v", + # Global + "global v", + # Expr + "1", + # Pass, + "pass", + # Break + "for v in v:break", + # Continue + "for v in v:continue", + # for statements with naked tuples (see http://bugs.python.org/issue6704) + "for a,b in c: pass", + "for (a,b) in c: pass", + "for [a,b] in c: pass", + # Multiline generator expression (test for .lineno & .col_offset) + """( + ( + Aa + , + Bb + ) + for + Aa + , + Bb in Cc + )""", + # dictcomp + "{a : b for w in x for m in p if g}", + # dictcomp with naked tuple + "{a : b for v,w in x}", + # setcomp + "{r for l in x if g}", + # setcomp with naked tuple + "{r for l,m in x}", + # AsyncFunctionDef + "async def f():\n 'async function'\n await something()", + # AsyncFor + "async def f():\n async for e in i: 1\n else: 2", + # AsyncWith + "async def f():\n async with a as b: 1", + # PEP 448: Additional Unpacking Generalizations + "{**{1:2}, 2:3}", + "{*{1, 2}, 3}", + # Asynchronous comprehensions + "async def f():\n [i async for b in c]", + # Decorated FunctionDef + "@deco1\n@deco2()\n@deco3(1)\ndef f(): pass", + # Decorated AsyncFunctionDef + "@deco1\n@deco2()\n@deco3(1)\nasync def f(): pass", + # Decorated ClassDef + "@deco1\n@deco2()\n@deco3(1)\nclass C: pass", + # Decorator with generator argument + "@deco(a for a in b)\ndef f(): pass", + # Decorator with attribute + "@a.b.c\ndef f(): pass", + # Simple assignment expression + "(a := 1)", + # Positional-only arguments + "def f(a, /,): pass", + "def f(a, /, c, d, e): pass", + "def f(a, /, c, *, d, e): pass", + "def f(a, /, c, *, d, e, **kwargs): pass", + # Positional-only arguments with defaults + "def f(a=1, /,): pass", + "def f(a=1, /, b=2, c=4): pass", + "def f(a=1, /, b=2, *, c=4): pass", + "def f(a=1, /, b=2, *, c): pass", + "def f(a=1, /, b=2, *, c=4, **kwargs): pass", + "def f(a=1, /, b=2, *, c, **kwargs): pass", + +] + +# These are compiled through "single" +# because of overlap with "eval", it just tests what +# can't be tested with "eval" +single_tests = [ + "1+2" +] + +# These are compiled through "eval" +# It should test all expressions +eval_tests = [ + # None + "None", + # BoolOp + "a and b", + # BinOp + "a + b", + # UnaryOp + "not v", + # Lambda + "lambda:None", + # Dict + "{ 1:2 }", + # Empty dict + "{}", + # Set + "{None,}", + # Multiline dict (test for .lineno & .col_offset) + """{ + 1 + : + 2 + }""", + # ListComp + "[a for b in c if d]", + # GeneratorExp + "(a for b in c if d)", + # Comprehensions with multiple for targets + "[(a,b) for a,b in c]", + "[(a,b) for (a,b) in c]", + "[(a,b) for [a,b] in c]", + "{(a,b) for a,b in c}", + "{(a,b) for (a,b) in c}", + "{(a,b) for [a,b] in c}", + "((a,b) for a,b in c)", + "((a,b) for (a,b) in c)", + "((a,b) for [a,b] in c)", + # Yield - yield expressions can't work outside a function + # + # Compare + "1 < 2 < 3", + # Call + "f(1,2,c=3,*d,**e)", + # Call with multi-character starred + "f(*[0, 1])", + # Call with a generator argument + "f(a for a in b)", + # Num + "10", + # Str + "'string'", + # Attribute + "a.b", + # Subscript + "a[b:c]", + # Name + "v", + # List + "[1,2,3]", + # Empty list + "[]", + # Tuple + "1,2,3", + # Tuple + "(1,2,3)", + # Empty tuple + "()", + # Combination + "a.b.c.d(a.b[1:2])", + +] + +# TODO: expr_context, slice, boolop, operator, unaryop, cmpop, comprehension +# excepthandler, arguments, keywords, alias + +class AST_Tests(unittest.TestCase): + + def _is_ast_node(self, name, node): + if not isinstance(node, type): + return False + if "ast" not in node.__module__: + return False + return name != 'AST' and name[0].isupper() + + def _assertTrueorder(self, ast_node, parent_pos): + if not isinstance(ast_node, ast.AST) or ast_node._fields is None: + return + if isinstance(ast_node, (ast.expr, ast.stmt, ast.excepthandler)): + node_pos = (ast_node.lineno, ast_node.col_offset) + self.assertGreaterEqual(node_pos, parent_pos) + parent_pos = (ast_node.lineno, ast_node.col_offset) + for name in ast_node._fields: + value = getattr(ast_node, name) + if isinstance(value, list): + first_pos = parent_pos + if value and name == 'decorator_list': + first_pos = (value[0].lineno, value[0].col_offset) + for child in value: + self._assertTrueorder(child, first_pos) + elif value is not None: + self._assertTrueorder(value, parent_pos) + self.assertEqual(ast_node._fields, ast_node.__match_args__) + + def test_AST_objects(self): + x = ast.AST() + self.assertEqual(x._fields, ()) + x.foobar = 42 + self.assertEqual(x.foobar, 42) + self.assertEqual(x.__dict__["foobar"], 42) + + with self.assertRaises(AttributeError): + x.vararg + + with self.assertRaises(TypeError): + # "ast.AST constructor takes 0 positional arguments" + ast.AST(2) + + def test_AST_garbage_collection(self): + class X: + pass + a = ast.AST() + a.x = X() + a.x.a = a + ref = weakref.ref(a.x) + del a + support.gc_collect() + self.assertIsNone(ref()) + + def test_snippets(self): + for input, output, kind in ((exec_tests, exec_results, "exec"), + (single_tests, single_results, "single"), + (eval_tests, eval_results, "eval")): + for i, o in zip(input, output): + with self.subTest(action="parsing", input=i): + ast_tree = compile(i, "?", kind, ast.PyCF_ONLY_AST) + self.assertEqual(to_tuple(ast_tree), o) + self._assertTrueorder(ast_tree, (0, 0)) + with self.subTest(action="compiling", input=i, kind=kind): + compile(ast_tree, "?", kind) + + def test_ast_validation(self): + # compile() is the only function that calls PyAST_Validate + snippets_to_validate = exec_tests + single_tests + eval_tests + for snippet in snippets_to_validate: + tree = ast.parse(snippet) + compile(tree, '', 'exec') + + def test_invalid_position_information(self): + invalid_linenos = [ + (10, 1), (-10, -11), (10, -11), (-5, -2), (-5, 1) + ] + + for lineno, end_lineno in invalid_linenos: + with self.subTest(f"Check invalid linenos {lineno}:{end_lineno}"): + snippet = "a = 1" + tree = ast.parse(snippet) + tree.body[0].lineno = lineno + tree.body[0].end_lineno = end_lineno + with self.assertRaises(ValueError): + compile(tree, '', 'exec') + + invalid_col_offsets = [ + (10, 1), (-10, -11), (10, -11), (-5, -2), (-5, 1) + ] + for col_offset, end_col_offset in invalid_col_offsets: + with self.subTest(f"Check invalid col_offset {col_offset}:{end_col_offset}"): + snippet = "a = 1" + tree = ast.parse(snippet) + tree.body[0].col_offset = col_offset + tree.body[0].end_col_offset = end_col_offset + with self.assertRaises(ValueError): + compile(tree, '', 'exec') + + def test_compilation_of_ast_nodes_with_default_end_position_values(self): + tree = ast.Module(body=[ + ast.Import(names=[ast.alias(name='builtins', lineno=1, col_offset=0)], lineno=1, col_offset=0), + ast.Import(names=[ast.alias(name='traceback', lineno=0, col_offset=0)], lineno=0, col_offset=1) + ], type_ignores=[]) + + # Check that compilation doesn't crash. Note: this may crash explicitly only on debug mode. + compile(tree, "", "exec") + + def test_slice(self): + slc = ast.parse("x[::]").body[0].value.slice + self.assertIsNone(slc.upper) + self.assertIsNone(slc.lower) + self.assertIsNone(slc.step) + + def test_from_import(self): + im = ast.parse("from . import y").body[0] + self.assertIsNone(im.module) + + def test_non_interned_future_from_ast(self): + mod = ast.parse("from __future__ import division") + self.assertIsInstance(mod.body[0], ast.ImportFrom) + mod.body[0].module = " __future__ ".strip() + compile(mod, "", "exec") + + def test_alias(self): + im = ast.parse("from bar import y").body[0] + self.assertEqual(len(im.names), 1) + alias = im.names[0] + self.assertEqual(alias.name, 'y') + self.assertIsNone(alias.asname) + self.assertEqual(alias.lineno, 1) + self.assertEqual(alias.end_lineno, 1) + self.assertEqual(alias.col_offset, 16) + self.assertEqual(alias.end_col_offset, 17) + + im = ast.parse("from bar import *").body[0] + alias = im.names[0] + self.assertEqual(alias.name, '*') + self.assertIsNone(alias.asname) + self.assertEqual(alias.lineno, 1) + self.assertEqual(alias.end_lineno, 1) + self.assertEqual(alias.col_offset, 16) + self.assertEqual(alias.end_col_offset, 17) + + im = ast.parse("from bar import y as z").body[0] + alias = im.names[0] + self.assertEqual(alias.name, "y") + self.assertEqual(alias.asname, "z") + self.assertEqual(alias.lineno, 1) + self.assertEqual(alias.end_lineno, 1) + self.assertEqual(alias.col_offset, 16) + self.assertEqual(alias.end_col_offset, 22) + + im = ast.parse("import bar as foo").body[0] + alias = im.names[0] + self.assertEqual(alias.name, "bar") + self.assertEqual(alias.asname, "foo") + self.assertEqual(alias.lineno, 1) + self.assertEqual(alias.end_lineno, 1) + self.assertEqual(alias.col_offset, 7) + self.assertEqual(alias.end_col_offset, 17) + + def test_base_classes(self): + self.assertTrue(issubclass(ast.For, ast.stmt)) + self.assertTrue(issubclass(ast.Name, ast.expr)) + self.assertTrue(issubclass(ast.stmt, ast.AST)) + self.assertTrue(issubclass(ast.expr, ast.AST)) + self.assertTrue(issubclass(ast.comprehension, ast.AST)) + self.assertTrue(issubclass(ast.Gt, ast.AST)) + + def test_field_attr_existence(self): + for name, item in ast.__dict__.items(): + if self._is_ast_node(name, item): + if name == 'Index': + # Index(value) just returns value now. + # The argument is required. + continue + x = item() + if isinstance(x, ast.AST): + self.assertEqual(type(x._fields), tuple) + + def test_arguments(self): + x = ast.arguments() + self.assertEqual(x._fields, ('posonlyargs', 'args', 'vararg', 'kwonlyargs', + 'kw_defaults', 'kwarg', 'defaults')) + + with self.assertRaises(AttributeError): + x.args + self.assertIsNone(x.vararg) + + x = ast.arguments(*range(1, 8)) + self.assertEqual(x.args, 2) + self.assertEqual(x.vararg, 3) + + def test_field_attr_writable(self): + x = ast.Num() + # We can assign to _fields + x._fields = 666 + self.assertEqual(x._fields, 666) + + def test_classattrs(self): + x = ast.Num() + self.assertEqual(x._fields, ('value', 'kind')) + + with self.assertRaises(AttributeError): + x.value + + with self.assertRaises(AttributeError): + x.n + + x = ast.Num(42) + self.assertEqual(x.value, 42) + self.assertEqual(x.n, 42) + + with self.assertRaises(AttributeError): + x.lineno + + with self.assertRaises(AttributeError): + x.foobar + + x = ast.Num(lineno=2) + self.assertEqual(x.lineno, 2) + + x = ast.Num(42, lineno=0) + self.assertEqual(x.lineno, 0) + self.assertEqual(x._fields, ('value', 'kind')) + self.assertEqual(x.value, 42) + self.assertEqual(x.n, 42) + + self.assertRaises(TypeError, ast.Num, 1, None, 2) + self.assertRaises(TypeError, ast.Num, 1, None, 2, lineno=0) + + # Arbitrary keyword arguments are supported + self.assertEqual(ast.Constant(1, foo='bar').foo, 'bar') + self.assertEqual(ast.Num(1, foo='bar').foo, 'bar') + + with self.assertRaisesRegex(TypeError, "Num got multiple values for argument 'n'"): + ast.Num(1, n=2) + with self.assertRaisesRegex(TypeError, "Constant got multiple values for argument 'value'"): + ast.Constant(1, value=2) + + self.assertEqual(ast.Num(42).n, 42) + self.assertEqual(ast.Num(4.25).n, 4.25) + self.assertEqual(ast.Num(4.25j).n, 4.25j) + self.assertEqual(ast.Str('42').s, '42') + self.assertEqual(ast.Bytes(b'42').s, b'42') + self.assertIs(ast.NameConstant(True).value, True) + self.assertIs(ast.NameConstant(False).value, False) + self.assertIs(ast.NameConstant(None).value, None) + + self.assertEqual(ast.Constant(42).value, 42) + self.assertEqual(ast.Constant(4.25).value, 4.25) + self.assertEqual(ast.Constant(4.25j).value, 4.25j) + self.assertEqual(ast.Constant('42').value, '42') + self.assertEqual(ast.Constant(b'42').value, b'42') + self.assertIs(ast.Constant(True).value, True) + self.assertIs(ast.Constant(False).value, False) + self.assertIs(ast.Constant(None).value, None) + self.assertIs(ast.Constant(...).value, ...) + + def test_realtype(self): + self.assertEqual(type(ast.Num(42)), ast.Constant) + self.assertEqual(type(ast.Num(4.25)), ast.Constant) + self.assertEqual(type(ast.Num(4.25j)), ast.Constant) + self.assertEqual(type(ast.Str('42')), ast.Constant) + self.assertEqual(type(ast.Bytes(b'42')), ast.Constant) + self.assertEqual(type(ast.NameConstant(True)), ast.Constant) + self.assertEqual(type(ast.NameConstant(False)), ast.Constant) + self.assertEqual(type(ast.NameConstant(None)), ast.Constant) + self.assertEqual(type(ast.Ellipsis()), ast.Constant) + + def test_isinstance(self): + self.assertTrue(isinstance(ast.Num(42), ast.Num)) + self.assertTrue(isinstance(ast.Num(4.2), ast.Num)) + self.assertTrue(isinstance(ast.Num(4.2j), ast.Num)) + self.assertTrue(isinstance(ast.Str('42'), ast.Str)) + self.assertTrue(isinstance(ast.Bytes(b'42'), ast.Bytes)) + self.assertTrue(isinstance(ast.NameConstant(True), ast.NameConstant)) + self.assertTrue(isinstance(ast.NameConstant(False), ast.NameConstant)) + self.assertTrue(isinstance(ast.NameConstant(None), ast.NameConstant)) + self.assertTrue(isinstance(ast.Ellipsis(), ast.Ellipsis)) + + self.assertTrue(isinstance(ast.Constant(42), ast.Num)) + self.assertTrue(isinstance(ast.Constant(4.2), ast.Num)) + self.assertTrue(isinstance(ast.Constant(4.2j), ast.Num)) + self.assertTrue(isinstance(ast.Constant('42'), ast.Str)) + self.assertTrue(isinstance(ast.Constant(b'42'), ast.Bytes)) + self.assertTrue(isinstance(ast.Constant(True), ast.NameConstant)) + self.assertTrue(isinstance(ast.Constant(False), ast.NameConstant)) + self.assertTrue(isinstance(ast.Constant(None), ast.NameConstant)) + self.assertTrue(isinstance(ast.Constant(...), ast.Ellipsis)) + + self.assertFalse(isinstance(ast.Str('42'), ast.Num)) + self.assertFalse(isinstance(ast.Num(42), ast.Str)) + self.assertFalse(isinstance(ast.Str('42'), ast.Bytes)) + self.assertFalse(isinstance(ast.Num(42), ast.NameConstant)) + self.assertFalse(isinstance(ast.Num(42), ast.Ellipsis)) + self.assertFalse(isinstance(ast.NameConstant(True), ast.Num)) + self.assertFalse(isinstance(ast.NameConstant(False), ast.Num)) + + self.assertFalse(isinstance(ast.Constant('42'), ast.Num)) + self.assertFalse(isinstance(ast.Constant(42), ast.Str)) + self.assertFalse(isinstance(ast.Constant('42'), ast.Bytes)) + self.assertFalse(isinstance(ast.Constant(42), ast.NameConstant)) + self.assertFalse(isinstance(ast.Constant(42), ast.Ellipsis)) + self.assertFalse(isinstance(ast.Constant(True), ast.Num)) + self.assertFalse(isinstance(ast.Constant(False), ast.Num)) + + self.assertFalse(isinstance(ast.Constant(), ast.Num)) + self.assertFalse(isinstance(ast.Constant(), ast.Str)) + self.assertFalse(isinstance(ast.Constant(), ast.Bytes)) + self.assertFalse(isinstance(ast.Constant(), ast.NameConstant)) + self.assertFalse(isinstance(ast.Constant(), ast.Ellipsis)) + + class S(str): pass + self.assertTrue(isinstance(ast.Constant(S('42')), ast.Str)) + self.assertFalse(isinstance(ast.Constant(S('42')), ast.Num)) + + def test_subclasses(self): + class N(ast.Num): + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + self.z = 'spam' + class N2(ast.Num): + pass + + n = N(42) + self.assertEqual(n.n, 42) + self.assertEqual(n.z, 'spam') + self.assertEqual(type(n), N) + self.assertTrue(isinstance(n, N)) + self.assertTrue(isinstance(n, ast.Num)) + self.assertFalse(isinstance(n, N2)) + self.assertFalse(isinstance(ast.Num(42), N)) + n = N(n=42) + self.assertEqual(n.n, 42) + self.assertEqual(type(n), N) + + def test_module(self): + body = [ast.Num(42)] + x = ast.Module(body, []) + self.assertEqual(x.body, body) + + def test_nodeclasses(self): + # Zero arguments constructor explicitly allowed + x = ast.BinOp() + self.assertEqual(x._fields, ('left', 'op', 'right')) + + # Random attribute allowed too + x.foobarbaz = 5 + self.assertEqual(x.foobarbaz, 5) + + n1 = ast.Num(1) + n3 = ast.Num(3) + addop = ast.Add() + x = ast.BinOp(n1, addop, n3) + self.assertEqual(x.left, n1) + self.assertEqual(x.op, addop) + self.assertEqual(x.right, n3) + + x = ast.BinOp(1, 2, 3) + self.assertEqual(x.left, 1) + self.assertEqual(x.op, 2) + self.assertEqual(x.right, 3) + + x = ast.BinOp(1, 2, 3, lineno=0) + self.assertEqual(x.left, 1) + self.assertEqual(x.op, 2) + self.assertEqual(x.right, 3) + self.assertEqual(x.lineno, 0) + + # node raises exception when given too many arguments + self.assertRaises(TypeError, ast.BinOp, 1, 2, 3, 4) + # node raises exception when given too many arguments + self.assertRaises(TypeError, ast.BinOp, 1, 2, 3, 4, lineno=0) + + # can set attributes through kwargs too + x = ast.BinOp(left=1, op=2, right=3, lineno=0) + self.assertEqual(x.left, 1) + self.assertEqual(x.op, 2) + self.assertEqual(x.right, 3) + self.assertEqual(x.lineno, 0) + + # Random kwargs also allowed + x = ast.BinOp(1, 2, 3, foobarbaz=42) + self.assertEqual(x.foobarbaz, 42) + + def test_no_fields(self): + # this used to fail because Sub._fields was None + x = ast.Sub() + self.assertEqual(x._fields, ()) + + def test_pickling(self): + import pickle + + for protocol in range(pickle.HIGHEST_PROTOCOL + 1): + for ast in (compile(i, "?", "exec", 0x400) for i in exec_tests): + ast2 = pickle.loads(pickle.dumps(ast, protocol)) + self.assertEqual(to_tuple(ast2), to_tuple(ast)) + + def test_invalid_sum(self): + pos = dict(lineno=2, col_offset=3) + m = ast.Module([ast.Expr(ast.expr(**pos), **pos)], []) + with self.assertRaises(TypeError) as cm: + compile(m, "", "exec") + self.assertIn("but got ", "exec") + self.assertIn("identifier must be of type str", str(cm.exception)) + + def test_invalid_constant(self): + for invalid_constant in int, (1, 2, int), frozenset((1, 2, int)): + e = ast.Expression(body=ast.Constant(invalid_constant)) + ast.fix_missing_locations(e) + with self.assertRaisesRegex( + TypeError, "invalid type in Constant: type" + ): + compile(e, "", "eval") + + def test_empty_yield_from(self): + # Issue 16546: yield from value is not optional. + empty_yield_from = ast.parse("def f():\n yield from g()") + empty_yield_from.body[0].body[0].value.value = None + with self.assertRaises(ValueError) as cm: + compile(empty_yield_from, "", "exec") + self.assertIn("field 'value' is required", str(cm.exception)) + + @support.cpython_only + def test_issue31592(self): + # There shouldn't be an assertion failure in case of a bad + # unicodedata.normalize(). + import unicodedata + def bad_normalize(*args): + return None + with support.swap_attr(unicodedata, 'normalize', bad_normalize): + self.assertRaises(TypeError, ast.parse, '\u03D5') + + def test_issue18374_binop_col_offset(self): + tree = ast.parse('4+5+6+7') + parent_binop = tree.body[0].value + child_binop = parent_binop.left + grandchild_binop = child_binop.left + self.assertEqual(parent_binop.col_offset, 0) + self.assertEqual(parent_binop.end_col_offset, 7) + self.assertEqual(child_binop.col_offset, 0) + self.assertEqual(child_binop.end_col_offset, 5) + self.assertEqual(grandchild_binop.col_offset, 0) + self.assertEqual(grandchild_binop.end_col_offset, 3) + + tree = ast.parse('4+5-\\\n 6-7') + parent_binop = tree.body[0].value + child_binop = parent_binop.left + grandchild_binop = child_binop.left + self.assertEqual(parent_binop.col_offset, 0) + self.assertEqual(parent_binop.lineno, 1) + self.assertEqual(parent_binop.end_col_offset, 4) + self.assertEqual(parent_binop.end_lineno, 2) + + self.assertEqual(child_binop.col_offset, 0) + self.assertEqual(child_binop.lineno, 1) + self.assertEqual(child_binop.end_col_offset, 2) + self.assertEqual(child_binop.end_lineno, 2) + + self.assertEqual(grandchild_binop.col_offset, 0) + self.assertEqual(grandchild_binop.lineno, 1) + self.assertEqual(grandchild_binop.end_col_offset, 3) + self.assertEqual(grandchild_binop.end_lineno, 1) + + def test_issue39579_dotted_name_end_col_offset(self): + tree = ast.parse('@a.b.c\ndef f(): pass') + attr_b = tree.body[0].decorator_list[0].value + self.assertEqual(attr_b.end_col_offset, 4) + + def test_ast_asdl_signature(self): + self.assertEqual(ast.withitem.__doc__, "withitem(expr context_expr, expr? optional_vars)") + self.assertEqual(ast.GtE.__doc__, "GtE") + self.assertEqual(ast.Name.__doc__, "Name(identifier id, expr_context ctx)") + self.assertEqual(ast.cmpop.__doc__, "cmpop = Eq | NotEq | Lt | LtE | Gt | GtE | Is | IsNot | In | NotIn") + expressions = [f" | {node.__doc__}" for node in ast.expr.__subclasses__()] + expressions[0] = f"expr = {ast.expr.__subclasses__()[0].__doc__}" + self.assertCountEqual(ast.expr.__doc__.split("\n"), expressions) + + def test_positional_only_feature_version(self): + ast.parse('def foo(x, /): ...', feature_version=(3, 8)) + ast.parse('def bar(x=1, /): ...', feature_version=(3, 8)) + with self.assertRaises(SyntaxError): + ast.parse('def foo(x, /): ...', feature_version=(3, 7)) + with self.assertRaises(SyntaxError): + ast.parse('def bar(x=1, /): ...', feature_version=(3, 7)) + + ast.parse('lambda x, /: ...', feature_version=(3, 8)) + ast.parse('lambda x=1, /: ...', feature_version=(3, 8)) + with self.assertRaises(SyntaxError): + ast.parse('lambda x, /: ...', feature_version=(3, 7)) + with self.assertRaises(SyntaxError): + ast.parse('lambda x=1, /: ...', feature_version=(3, 7)) + + def test_parenthesized_with_feature_version(self): + ast.parse('with (CtxManager() as example): ...', feature_version=(3, 10)) + # While advertised as a feature in Python 3.10, this was allowed starting 3.9 + ast.parse('with (CtxManager() as example): ...', feature_version=(3, 9)) + with self.assertRaises(SyntaxError): + ast.parse('with (CtxManager() as example): ...', feature_version=(3, 8)) + ast.parse('with CtxManager() as example: ...', feature_version=(3, 8)) + + def test_debug_f_string_feature_version(self): + ast.parse('f"{x=}"', feature_version=(3, 8)) + with self.assertRaises(SyntaxError): + ast.parse('f"{x=}"', feature_version=(3, 7)) + + def test_assignment_expression_feature_version(self): + ast.parse('(x := 0)', feature_version=(3, 8)) + with self.assertRaises(SyntaxError): + ast.parse('(x := 0)', feature_version=(3, 7)) + + def test_exception_groups_feature_version(self): + code = dedent(''' + try: ... + except* Exception: ... + ''') + ast.parse(code) + with self.assertRaises(SyntaxError): + ast.parse(code, feature_version=(3, 10)) + + def test_invalid_major_feature_version(self): + with self.assertRaises(ValueError): + ast.parse('pass', feature_version=(2, 7)) + with self.assertRaises(ValueError): + ast.parse('pass', feature_version=(4, 0)) + + def test_constant_as_name(self): + for constant in "True", "False", "None": + expr = ast.Expression(ast.Name(constant, ast.Load())) + ast.fix_missing_locations(expr) + with self.assertRaisesRegex(ValueError, f"identifier field can't represent '{constant}' constant"): + compile(expr, "", "eval") + + def test_precedence_enum(self): + class _Precedence(enum.IntEnum): + """Precedence table that originated from python grammar.""" + NAMED_EXPR = enum.auto() # := + TUPLE = enum.auto() # , + YIELD = enum.auto() # 'yield', 'yield from' + TEST = enum.auto() # 'if'-'else', 'lambda' + OR = enum.auto() # 'or' + AND = enum.auto() # 'and' + NOT = enum.auto() # 'not' + CMP = enum.auto() # '<', '>', '==', '>=', '<=', '!=', + # 'in', 'not in', 'is', 'is not' + EXPR = enum.auto() + BOR = EXPR # '|' + BXOR = enum.auto() # '^' + BAND = enum.auto() # '&' + SHIFT = enum.auto() # '<<', '>>' + ARITH = enum.auto() # '+', '-' + TERM = enum.auto() # '*', '@', '/', '%', '//' + FACTOR = enum.auto() # unary '+', '-', '~' + POWER = enum.auto() # '**' + AWAIT = enum.auto() # 'await' + ATOM = enum.auto() + def next(self): + try: + return self.__class__(self + 1) + except ValueError: + return self + enum._test_simple_enum(_Precedence, ast._Precedence) + + @support.cpython_only + def test_ast_recursion_limit(self): + fail_depth = support.EXCEEDS_RECURSION_LIMIT + crash_depth = 100_000 + success_depth = 1200 + + def check_limit(prefix, repeated): + expect_ok = prefix + repeated * success_depth + ast.parse(expect_ok) + for depth in (fail_depth, crash_depth): + broken = prefix + repeated * depth + details = "Compiling ({!r} + {!r} * {})".format( + prefix, repeated, depth) + with self.assertRaises(RecursionError, msg=details): + with support.infinite_recursion(): + ast.parse(broken) + + check_limit("a", "()") + check_limit("a", ".b") + check_limit("a", "[0]") + check_limit("a", "*a") + + def test_null_bytes(self): + with self.assertRaises(SyntaxError, + msg="source code string cannot contain null bytes"): + ast.parse("a\0b") + +class ASTHelpers_Test(unittest.TestCase): + maxDiff = None + + def test_parse(self): + a = ast.parse('foo(1 + 1)') + b = compile('foo(1 + 1)', '', 'exec', ast.PyCF_ONLY_AST) + self.assertEqual(ast.dump(a), ast.dump(b)) + + def test_parse_in_error(self): + try: + 1/0 + except Exception: + with self.assertRaises(SyntaxError) as e: + ast.literal_eval(r"'\U'") + self.assertIsNotNone(e.exception.__context__) + + def test_dump(self): + node = ast.parse('spam(eggs, "and cheese")') + self.assertEqual(ast.dump(node), + "Module(body=[Expr(value=Call(func=Name(id='spam', ctx=Load()), " + "args=[Name(id='eggs', ctx=Load()), Constant(value='and cheese')], " + "keywords=[]))], type_ignores=[])" + ) + self.assertEqual(ast.dump(node, annotate_fields=False), + "Module([Expr(Call(Name('spam', Load()), [Name('eggs', Load()), " + "Constant('and cheese')], []))], [])" + ) + self.assertEqual(ast.dump(node, include_attributes=True), + "Module(body=[Expr(value=Call(func=Name(id='spam', ctx=Load(), " + "lineno=1, col_offset=0, end_lineno=1, end_col_offset=4), " + "args=[Name(id='eggs', ctx=Load(), lineno=1, col_offset=5, " + "end_lineno=1, end_col_offset=9), Constant(value='and cheese', " + "lineno=1, col_offset=11, end_lineno=1, end_col_offset=23)], keywords=[], " + "lineno=1, col_offset=0, end_lineno=1, end_col_offset=24), " + "lineno=1, col_offset=0, end_lineno=1, end_col_offset=24)], type_ignores=[])" + ) + + def test_dump_indent(self): + node = ast.parse('spam(eggs, "and cheese")') + self.assertEqual(ast.dump(node, indent=3), """\ +Module( + body=[ + Expr( + value=Call( + func=Name(id='spam', ctx=Load()), + args=[ + Name(id='eggs', ctx=Load()), + Constant(value='and cheese')], + keywords=[]))], + type_ignores=[])""") + self.assertEqual(ast.dump(node, annotate_fields=False, indent='\t'), """\ +Module( +\t[ +\t\tExpr( +\t\t\tCall( +\t\t\t\tName('spam', Load()), +\t\t\t\t[ +\t\t\t\t\tName('eggs', Load()), +\t\t\t\t\tConstant('and cheese')], +\t\t\t\t[]))], +\t[])""") + self.assertEqual(ast.dump(node, include_attributes=True, indent=3), """\ +Module( + body=[ + Expr( + value=Call( + func=Name( + id='spam', + ctx=Load(), + lineno=1, + col_offset=0, + end_lineno=1, + end_col_offset=4), + args=[ + Name( + id='eggs', + ctx=Load(), + lineno=1, + col_offset=5, + end_lineno=1, + end_col_offset=9), + Constant( + value='and cheese', + lineno=1, + col_offset=11, + end_lineno=1, + end_col_offset=23)], + keywords=[], + lineno=1, + col_offset=0, + end_lineno=1, + end_col_offset=24), + lineno=1, + col_offset=0, + end_lineno=1, + end_col_offset=24)], + type_ignores=[])""") + + def test_dump_incomplete(self): + node = ast.Raise(lineno=3, col_offset=4) + self.assertEqual(ast.dump(node), + "Raise()" + ) + self.assertEqual(ast.dump(node, include_attributes=True), + "Raise(lineno=3, col_offset=4)" + ) + node = ast.Raise(exc=ast.Name(id='e', ctx=ast.Load()), lineno=3, col_offset=4) + self.assertEqual(ast.dump(node), + "Raise(exc=Name(id='e', ctx=Load()))" + ) + self.assertEqual(ast.dump(node, annotate_fields=False), + "Raise(Name('e', Load()))" + ) + self.assertEqual(ast.dump(node, include_attributes=True), + "Raise(exc=Name(id='e', ctx=Load()), lineno=3, col_offset=4)" + ) + self.assertEqual(ast.dump(node, annotate_fields=False, include_attributes=True), + "Raise(Name('e', Load()), lineno=3, col_offset=4)" + ) + node = ast.Raise(cause=ast.Name(id='e', ctx=ast.Load())) + self.assertEqual(ast.dump(node), + "Raise(cause=Name(id='e', ctx=Load()))" + ) + self.assertEqual(ast.dump(node, annotate_fields=False), + "Raise(cause=Name('e', Load()))" + ) + + def test_copy_location(self): + src = ast.parse('1 + 1', mode='eval') + src.body.right = ast.copy_location(ast.Num(2), src.body.right) + self.assertEqual(ast.dump(src, include_attributes=True), + 'Expression(body=BinOp(left=Constant(value=1, lineno=1, col_offset=0, ' + 'end_lineno=1, end_col_offset=1), op=Add(), right=Constant(value=2, ' + 'lineno=1, col_offset=4, end_lineno=1, end_col_offset=5), lineno=1, ' + 'col_offset=0, end_lineno=1, end_col_offset=5))' + ) + src = ast.Call(col_offset=1, lineno=1, end_lineno=1, end_col_offset=1) + new = ast.copy_location(src, ast.Call(col_offset=None, lineno=None)) + self.assertIsNone(new.end_lineno) + self.assertIsNone(new.end_col_offset) + self.assertEqual(new.lineno, 1) + self.assertEqual(new.col_offset, 1) + + def test_fix_missing_locations(self): + src = ast.parse('write("spam")') + src.body.append(ast.Expr(ast.Call(ast.Name('spam', ast.Load()), + [ast.Str('eggs')], []))) + self.assertEqual(src, ast.fix_missing_locations(src)) + self.maxDiff = None + self.assertEqual(ast.dump(src, include_attributes=True), + "Module(body=[Expr(value=Call(func=Name(id='write', ctx=Load(), " + "lineno=1, col_offset=0, end_lineno=1, end_col_offset=5), " + "args=[Constant(value='spam', lineno=1, col_offset=6, end_lineno=1, " + "end_col_offset=12)], keywords=[], lineno=1, col_offset=0, end_lineno=1, " + "end_col_offset=13), lineno=1, col_offset=0, end_lineno=1, " + "end_col_offset=13), Expr(value=Call(func=Name(id='spam', ctx=Load(), " + "lineno=1, col_offset=0, end_lineno=1, end_col_offset=0), " + "args=[Constant(value='eggs', lineno=1, col_offset=0, end_lineno=1, " + "end_col_offset=0)], keywords=[], lineno=1, col_offset=0, end_lineno=1, " + "end_col_offset=0), lineno=1, col_offset=0, end_lineno=1, end_col_offset=0)], " + "type_ignores=[])" + ) + + def test_increment_lineno(self): + src = ast.parse('1 + 1', mode='eval') + self.assertEqual(ast.increment_lineno(src, n=3), src) + self.assertEqual(ast.dump(src, include_attributes=True), + 'Expression(body=BinOp(left=Constant(value=1, lineno=4, col_offset=0, ' + 'end_lineno=4, end_col_offset=1), op=Add(), right=Constant(value=1, ' + 'lineno=4, col_offset=4, end_lineno=4, end_col_offset=5), lineno=4, ' + 'col_offset=0, end_lineno=4, end_col_offset=5))' + ) + # issue10869: do not increment lineno of root twice + src = ast.parse('1 + 1', mode='eval') + self.assertEqual(ast.increment_lineno(src.body, n=3), src.body) + self.assertEqual(ast.dump(src, include_attributes=True), + 'Expression(body=BinOp(left=Constant(value=1, lineno=4, col_offset=0, ' + 'end_lineno=4, end_col_offset=1), op=Add(), right=Constant(value=1, ' + 'lineno=4, col_offset=4, end_lineno=4, end_col_offset=5), lineno=4, ' + 'col_offset=0, end_lineno=4, end_col_offset=5))' + ) + src = ast.Call( + func=ast.Name("test", ast.Load()), args=[], keywords=[], lineno=1 + ) + self.assertEqual(ast.increment_lineno(src).lineno, 2) + self.assertIsNone(ast.increment_lineno(src).end_lineno) + + def test_increment_lineno_on_module(self): + src = ast.parse(dedent("""\ + a = 1 + b = 2 # type: ignore + c = 3 + d = 4 # type: ignore@tag + """), type_comments=True) + ast.increment_lineno(src, n=5) + self.assertEqual(src.type_ignores[0].lineno, 7) + self.assertEqual(src.type_ignores[1].lineno, 9) + self.assertEqual(src.type_ignores[1].tag, '@tag') + + def test_iter_fields(self): + node = ast.parse('foo()', mode='eval') + d = dict(ast.iter_fields(node.body)) + self.assertEqual(d.pop('func').id, 'foo') + self.assertEqual(d, {'keywords': [], 'args': []}) + + def test_iter_child_nodes(self): + node = ast.parse("spam(23, 42, eggs='leek')", mode='eval') + self.assertEqual(len(list(ast.iter_child_nodes(node.body))), 4) + iterator = ast.iter_child_nodes(node.body) + self.assertEqual(next(iterator).id, 'spam') + self.assertEqual(next(iterator).value, 23) + self.assertEqual(next(iterator).value, 42) + self.assertEqual(ast.dump(next(iterator)), + "keyword(arg='eggs', value=Constant(value='leek'))" + ) + + def test_get_docstring(self): + node = ast.parse('"""line one\n line two"""') + self.assertEqual(ast.get_docstring(node), + 'line one\nline two') + + node = ast.parse('class foo:\n """line one\n line two"""') + self.assertEqual(ast.get_docstring(node.body[0]), + 'line one\nline two') + + node = ast.parse('def foo():\n """line one\n line two"""') + self.assertEqual(ast.get_docstring(node.body[0]), + 'line one\nline two') + + node = ast.parse('async def foo():\n """spam\n ham"""') + self.assertEqual(ast.get_docstring(node.body[0]), 'spam\nham') + + def test_get_docstring_none(self): + self.assertIsNone(ast.get_docstring(ast.parse(''))) + node = ast.parse('x = "not docstring"') + self.assertIsNone(ast.get_docstring(node)) + node = ast.parse('def foo():\n pass') + self.assertIsNone(ast.get_docstring(node)) + + node = ast.parse('class foo:\n pass') + self.assertIsNone(ast.get_docstring(node.body[0])) + node = ast.parse('class foo:\n x = "not docstring"') + self.assertIsNone(ast.get_docstring(node.body[0])) + node = ast.parse('class foo:\n def bar(self): pass') + self.assertIsNone(ast.get_docstring(node.body[0])) + + node = ast.parse('def foo():\n pass') + self.assertIsNone(ast.get_docstring(node.body[0])) + node = ast.parse('def foo():\n x = "not docstring"') + self.assertIsNone(ast.get_docstring(node.body[0])) + + node = ast.parse('async def foo():\n pass') + self.assertIsNone(ast.get_docstring(node.body[0])) + node = ast.parse('async def foo():\n x = "not docstring"') + self.assertIsNone(ast.get_docstring(node.body[0])) + + def test_multi_line_docstring_col_offset_and_lineno_issue16806(self): + node = ast.parse( + '"""line one\nline two"""\n\n' + 'def foo():\n """line one\n line two"""\n\n' + ' def bar():\n """line one\n line two"""\n' + ' """line one\n line two"""\n' + '"""line one\nline two"""\n\n' + ) + self.assertEqual(node.body[0].col_offset, 0) + self.assertEqual(node.body[0].lineno, 1) + self.assertEqual(node.body[1].body[0].col_offset, 2) + self.assertEqual(node.body[1].body[0].lineno, 5) + self.assertEqual(node.body[1].body[1].body[0].col_offset, 4) + self.assertEqual(node.body[1].body[1].body[0].lineno, 9) + self.assertEqual(node.body[1].body[2].col_offset, 2) + self.assertEqual(node.body[1].body[2].lineno, 11) + self.assertEqual(node.body[2].col_offset, 0) + self.assertEqual(node.body[2].lineno, 13) + + def test_elif_stmt_start_position(self): + node = ast.parse('if a:\n pass\nelif b:\n pass\n') + elif_stmt = node.body[0].orelse[0] + self.assertEqual(elif_stmt.lineno, 3) + self.assertEqual(elif_stmt.col_offset, 0) + + def test_elif_stmt_start_position_with_else(self): + node = ast.parse('if a:\n pass\nelif b:\n pass\nelse:\n pass\n') + elif_stmt = node.body[0].orelse[0] + self.assertEqual(elif_stmt.lineno, 3) + self.assertEqual(elif_stmt.col_offset, 0) + + def test_starred_expr_end_position_within_call(self): + node = ast.parse('f(*[0, 1])') + starred_expr = node.body[0].value.args[0] + self.assertEqual(starred_expr.end_lineno, 1) + self.assertEqual(starred_expr.end_col_offset, 9) + + def test_literal_eval(self): + self.assertEqual(ast.literal_eval('[1, 2, 3]'), [1, 2, 3]) + self.assertEqual(ast.literal_eval('{"foo": 42}'), {"foo": 42}) + self.assertEqual(ast.literal_eval('(True, False, None)'), (True, False, None)) + self.assertEqual(ast.literal_eval('{1, 2, 3}'), {1, 2, 3}) + self.assertEqual(ast.literal_eval('b"hi"'), b"hi") + self.assertEqual(ast.literal_eval('set()'), set()) + self.assertRaises(ValueError, ast.literal_eval, 'foo()') + self.assertEqual(ast.literal_eval('6'), 6) + self.assertEqual(ast.literal_eval('+6'), 6) + self.assertEqual(ast.literal_eval('-6'), -6) + self.assertEqual(ast.literal_eval('3.25'), 3.25) + self.assertEqual(ast.literal_eval('+3.25'), 3.25) + self.assertEqual(ast.literal_eval('-3.25'), -3.25) + self.assertEqual(repr(ast.literal_eval('-0.0')), '-0.0') + self.assertRaises(ValueError, ast.literal_eval, '++6') + self.assertRaises(ValueError, ast.literal_eval, '+True') + self.assertRaises(ValueError, ast.literal_eval, '2+3') + + def test_literal_eval_str_int_limit(self): + with support.adjust_int_max_str_digits(4000): + ast.literal_eval('3'*4000) # no error + with self.assertRaises(SyntaxError) as err_ctx: + ast.literal_eval('3'*4001) + self.assertIn('Exceeds the limit ', str(err_ctx.exception)) + self.assertIn(' Consider hexadecimal ', str(err_ctx.exception)) + + def test_literal_eval_complex(self): + # Issue #4907 + self.assertEqual(ast.literal_eval('6j'), 6j) + self.assertEqual(ast.literal_eval('-6j'), -6j) + self.assertEqual(ast.literal_eval('6.75j'), 6.75j) + self.assertEqual(ast.literal_eval('-6.75j'), -6.75j) + self.assertEqual(ast.literal_eval('3+6j'), 3+6j) + self.assertEqual(ast.literal_eval('-3+6j'), -3+6j) + self.assertEqual(ast.literal_eval('3-6j'), 3-6j) + self.assertEqual(ast.literal_eval('-3-6j'), -3-6j) + self.assertEqual(ast.literal_eval('3.25+6.75j'), 3.25+6.75j) + self.assertEqual(ast.literal_eval('-3.25+6.75j'), -3.25+6.75j) + self.assertEqual(ast.literal_eval('3.25-6.75j'), 3.25-6.75j) + self.assertEqual(ast.literal_eval('-3.25-6.75j'), -3.25-6.75j) + self.assertEqual(ast.literal_eval('(3+6j)'), 3+6j) + self.assertRaises(ValueError, ast.literal_eval, '-6j+3') + self.assertRaises(ValueError, ast.literal_eval, '-6j+3j') + self.assertRaises(ValueError, ast.literal_eval, '3+-6j') + self.assertRaises(ValueError, ast.literal_eval, '3+(0+6j)') + self.assertRaises(ValueError, ast.literal_eval, '-(3+6j)') + + def test_literal_eval_malformed_dict_nodes(self): + malformed = ast.Dict(keys=[ast.Constant(1), ast.Constant(2)], values=[ast.Constant(3)]) + self.assertRaises(ValueError, ast.literal_eval, malformed) + malformed = ast.Dict(keys=[ast.Constant(1)], values=[ast.Constant(2), ast.Constant(3)]) + self.assertRaises(ValueError, ast.literal_eval, malformed) + + def test_literal_eval_trailing_ws(self): + self.assertEqual(ast.literal_eval(" -1"), -1) + self.assertEqual(ast.literal_eval("\t\t-1"), -1) + self.assertEqual(ast.literal_eval(" \t -1"), -1) + self.assertRaises(IndentationError, ast.literal_eval, "\n -1") + + def test_literal_eval_malformed_lineno(self): + msg = r'malformed node or string on line 3:' + with self.assertRaisesRegex(ValueError, msg): + ast.literal_eval("{'a': 1,\n'b':2,\n'c':++3,\n'd':4}") + + node = ast.UnaryOp( + ast.UAdd(), ast.UnaryOp(ast.UAdd(), ast.Constant(6))) + self.assertIsNone(getattr(node, 'lineno', None)) + msg = r'malformed node or string:' + with self.assertRaisesRegex(ValueError, msg): + ast.literal_eval(node) + + def test_literal_eval_syntax_errors(self): + with self.assertRaisesRegex(SyntaxError, "unexpected indent"): + ast.literal_eval(r''' + \ + (\ + \ ''') + + def test_bad_integer(self): + # issue13436: Bad error message with invalid numeric values + body = [ast.ImportFrom(module='time', + names=[ast.alias(name='sleep')], + level=None, + lineno=None, col_offset=None)] + mod = ast.Module(body, []) + with self.assertRaises(ValueError) as cm: + compile(mod, 'test', 'exec') + self.assertIn("invalid integer value: None", str(cm.exception)) + + def test_level_as_none(self): + body = [ast.ImportFrom(module='time', + names=[ast.alias(name='sleep', + lineno=0, col_offset=0)], + level=None, + lineno=0, col_offset=0)] + mod = ast.Module(body, []) + code = compile(mod, 'test', 'exec') + ns = {} + exec(code, ns) + self.assertIn('sleep', ns) + + def test_recursion_direct(self): + e = ast.UnaryOp(op=ast.Not(), lineno=0, col_offset=0) + e.operand = e + with self.assertRaises(RecursionError): + with support.infinite_recursion(): + compile(ast.Expression(e), "", "eval") + + def test_recursion_indirect(self): + e = ast.UnaryOp(op=ast.Not(), lineno=0, col_offset=0) + f = ast.UnaryOp(op=ast.Not(), lineno=0, col_offset=0) + e.operand = f + f.operand = e + with self.assertRaises(RecursionError): + with support.infinite_recursion(): + compile(ast.Expression(e), "", "eval") + + +class ASTValidatorTests(unittest.TestCase): + + def mod(self, mod, msg=None, mode="exec", *, exc=ValueError): + mod.lineno = mod.col_offset = 0 + ast.fix_missing_locations(mod) + if msg is None: + compile(mod, "", mode) + else: + with self.assertRaises(exc) as cm: + compile(mod, "", mode) + self.assertIn(msg, str(cm.exception)) + + def expr(self, node, msg=None, *, exc=ValueError): + mod = ast.Module([ast.Expr(node)], []) + self.mod(mod, msg, exc=exc) + + def stmt(self, stmt, msg=None): + mod = ast.Module([stmt], []) + self.mod(mod, msg) + + def test_module(self): + m = ast.Interactive([ast.Expr(ast.Name("x", ast.Store()))]) + self.mod(m, "must have Load context", "single") + m = ast.Expression(ast.Name("x", ast.Store())) + self.mod(m, "must have Load context", "eval") + + def _check_arguments(self, fac, check): + def arguments(args=None, posonlyargs=None, vararg=None, + kwonlyargs=None, kwarg=None, + defaults=None, kw_defaults=None): + if args is None: + args = [] + if posonlyargs is None: + posonlyargs = [] + if kwonlyargs is None: + kwonlyargs = [] + if defaults is None: + defaults = [] + if kw_defaults is None: + kw_defaults = [] + args = ast.arguments(args, posonlyargs, vararg, kwonlyargs, + kw_defaults, kwarg, defaults) + return fac(args) + args = [ast.arg("x", ast.Name("x", ast.Store()))] + check(arguments(args=args), "must have Load context") + check(arguments(posonlyargs=args), "must have Load context") + check(arguments(kwonlyargs=args), "must have Load context") + check(arguments(defaults=[ast.Num(3)]), + "more positional defaults than args") + check(arguments(kw_defaults=[ast.Num(4)]), + "length of kwonlyargs is not the same as kw_defaults") + args = [ast.arg("x", ast.Name("x", ast.Load()))] + check(arguments(args=args, defaults=[ast.Name("x", ast.Store())]), + "must have Load context") + args = [ast.arg("a", ast.Name("x", ast.Load())), + ast.arg("b", ast.Name("y", ast.Load()))] + check(arguments(kwonlyargs=args, + kw_defaults=[None, ast.Name("x", ast.Store())]), + "must have Load context") + + def test_funcdef(self): + a = ast.arguments([], [], None, [], [], None, []) + f = ast.FunctionDef("x", a, [], [], None) + self.stmt(f, "empty body on FunctionDef") + f = ast.FunctionDef("x", a, [ast.Pass()], [ast.Name("x", ast.Store())], + None) + self.stmt(f, "must have Load context") + f = ast.FunctionDef("x", a, [ast.Pass()], [], + ast.Name("x", ast.Store())) + self.stmt(f, "must have Load context") + def fac(args): + return ast.FunctionDef("x", args, [ast.Pass()], [], None) + self._check_arguments(fac, self.stmt) + + def test_classdef(self): + def cls(bases=None, keywords=None, body=None, decorator_list=None): + if bases is None: + bases = [] + if keywords is None: + keywords = [] + if body is None: + body = [ast.Pass()] + if decorator_list is None: + decorator_list = [] + return ast.ClassDef("myclass", bases, keywords, + body, decorator_list) + self.stmt(cls(bases=[ast.Name("x", ast.Store())]), + "must have Load context") + self.stmt(cls(keywords=[ast.keyword("x", ast.Name("x", ast.Store()))]), + "must have Load context") + self.stmt(cls(body=[]), "empty body on ClassDef") + self.stmt(cls(body=[None]), "None disallowed") + self.stmt(cls(decorator_list=[ast.Name("x", ast.Store())]), + "must have Load context") + + def test_delete(self): + self.stmt(ast.Delete([]), "empty targets on Delete") + self.stmt(ast.Delete([None]), "None disallowed") + self.stmt(ast.Delete([ast.Name("x", ast.Load())]), + "must have Del context") + + def test_assign(self): + self.stmt(ast.Assign([], ast.Num(3)), "empty targets on Assign") + self.stmt(ast.Assign([None], ast.Num(3)), "None disallowed") + self.stmt(ast.Assign([ast.Name("x", ast.Load())], ast.Num(3)), + "must have Store context") + self.stmt(ast.Assign([ast.Name("x", ast.Store())], + ast.Name("y", ast.Store())), + "must have Load context") + + def test_augassign(self): + aug = ast.AugAssign(ast.Name("x", ast.Load()), ast.Add(), + ast.Name("y", ast.Load())) + self.stmt(aug, "must have Store context") + aug = ast.AugAssign(ast.Name("x", ast.Store()), ast.Add(), + ast.Name("y", ast.Store())) + self.stmt(aug, "must have Load context") + + def test_for(self): + x = ast.Name("x", ast.Store()) + y = ast.Name("y", ast.Load()) + p = ast.Pass() + self.stmt(ast.For(x, y, [], []), "empty body on For") + self.stmt(ast.For(ast.Name("x", ast.Load()), y, [p], []), + "must have Store context") + self.stmt(ast.For(x, ast.Name("y", ast.Store()), [p], []), + "must have Load context") + e = ast.Expr(ast.Name("x", ast.Store())) + self.stmt(ast.For(x, y, [e], []), "must have Load context") + self.stmt(ast.For(x, y, [p], [e]), "must have Load context") + + def test_while(self): + self.stmt(ast.While(ast.Num(3), [], []), "empty body on While") + self.stmt(ast.While(ast.Name("x", ast.Store()), [ast.Pass()], []), + "must have Load context") + self.stmt(ast.While(ast.Num(3), [ast.Pass()], + [ast.Expr(ast.Name("x", ast.Store()))]), + "must have Load context") + + def test_if(self): + self.stmt(ast.If(ast.Num(3), [], []), "empty body on If") + i = ast.If(ast.Name("x", ast.Store()), [ast.Pass()], []) + self.stmt(i, "must have Load context") + i = ast.If(ast.Num(3), [ast.Expr(ast.Name("x", ast.Store()))], []) + self.stmt(i, "must have Load context") + i = ast.If(ast.Num(3), [ast.Pass()], + [ast.Expr(ast.Name("x", ast.Store()))]) + self.stmt(i, "must have Load context") + + def test_with(self): + p = ast.Pass() + self.stmt(ast.With([], [p]), "empty items on With") + i = ast.withitem(ast.Num(3), None) + self.stmt(ast.With([i], []), "empty body on With") + i = ast.withitem(ast.Name("x", ast.Store()), None) + self.stmt(ast.With([i], [p]), "must have Load context") + i = ast.withitem(ast.Num(3), ast.Name("x", ast.Load())) + self.stmt(ast.With([i], [p]), "must have Store context") + + def test_raise(self): + r = ast.Raise(None, ast.Num(3)) + self.stmt(r, "Raise with cause but no exception") + r = ast.Raise(ast.Name("x", ast.Store()), None) + self.stmt(r, "must have Load context") + r = ast.Raise(ast.Num(4), ast.Name("x", ast.Store())) + self.stmt(r, "must have Load context") + + def test_try(self): + p = ast.Pass() + t = ast.Try([], [], [], [p]) + self.stmt(t, "empty body on Try") + t = ast.Try([ast.Expr(ast.Name("x", ast.Store()))], [], [], [p]) + self.stmt(t, "must have Load context") + t = ast.Try([p], [], [], []) + self.stmt(t, "Try has neither except handlers nor finalbody") + t = ast.Try([p], [], [p], [p]) + self.stmt(t, "Try has orelse but no except handlers") + t = ast.Try([p], [ast.ExceptHandler(None, "x", [])], [], []) + self.stmt(t, "empty body on ExceptHandler") + e = [ast.ExceptHandler(ast.Name("x", ast.Store()), "y", [p])] + self.stmt(ast.Try([p], e, [], []), "must have Load context") + e = [ast.ExceptHandler(None, "x", [p])] + t = ast.Try([p], e, [ast.Expr(ast.Name("x", ast.Store()))], [p]) + self.stmt(t, "must have Load context") + t = ast.Try([p], e, [p], [ast.Expr(ast.Name("x", ast.Store()))]) + self.stmt(t, "must have Load context") + + def test_try_star(self): + p = ast.Pass() + t = ast.TryStar([], [], [], [p]) + self.stmt(t, "empty body on TryStar") + t = ast.TryStar([ast.Expr(ast.Name("x", ast.Store()))], [], [], [p]) + self.stmt(t, "must have Load context") + t = ast.TryStar([p], [], [], []) + self.stmt(t, "TryStar has neither except handlers nor finalbody") + t = ast.TryStar([p], [], [p], [p]) + self.stmt(t, "TryStar has orelse but no except handlers") + t = ast.TryStar([p], [ast.ExceptHandler(None, "x", [])], [], []) + self.stmt(t, "empty body on ExceptHandler") + e = [ast.ExceptHandler(ast.Name("x", ast.Store()), "y", [p])] + self.stmt(ast.TryStar([p], e, [], []), "must have Load context") + e = [ast.ExceptHandler(None, "x", [p])] + t = ast.TryStar([p], e, [ast.Expr(ast.Name("x", ast.Store()))], [p]) + self.stmt(t, "must have Load context") + t = ast.TryStar([p], e, [p], [ast.Expr(ast.Name("x", ast.Store()))]) + self.stmt(t, "must have Load context") + + def test_assert(self): + self.stmt(ast.Assert(ast.Name("x", ast.Store()), None), + "must have Load context") + assrt = ast.Assert(ast.Name("x", ast.Load()), + ast.Name("y", ast.Store())) + self.stmt(assrt, "must have Load context") + + def test_import(self): + self.stmt(ast.Import([]), "empty names on Import") + + def test_importfrom(self): + imp = ast.ImportFrom(None, [ast.alias("x", None)], -42) + self.stmt(imp, "Negative ImportFrom level") + self.stmt(ast.ImportFrom(None, [], 0), "empty names on ImportFrom") + + def test_global(self): + self.stmt(ast.Global([]), "empty names on Global") + + def test_nonlocal(self): + self.stmt(ast.Nonlocal([]), "empty names on Nonlocal") + + def test_expr(self): + e = ast.Expr(ast.Name("x", ast.Store())) + self.stmt(e, "must have Load context") + + def test_boolop(self): + b = ast.BoolOp(ast.And(), []) + self.expr(b, "less than 2 values") + b = ast.BoolOp(ast.And(), [ast.Num(3)]) + self.expr(b, "less than 2 values") + b = ast.BoolOp(ast.And(), [ast.Num(4), None]) + self.expr(b, "None disallowed") + b = ast.BoolOp(ast.And(), [ast.Num(4), ast.Name("x", ast.Store())]) + self.expr(b, "must have Load context") + + def test_unaryop(self): + u = ast.UnaryOp(ast.Not(), ast.Name("x", ast.Store())) + self.expr(u, "must have Load context") + + def test_lambda(self): + a = ast.arguments([], [], None, [], [], None, []) + self.expr(ast.Lambda(a, ast.Name("x", ast.Store())), + "must have Load context") + def fac(args): + return ast.Lambda(args, ast.Name("x", ast.Load())) + self._check_arguments(fac, self.expr) + + def test_ifexp(self): + l = ast.Name("x", ast.Load()) + s = ast.Name("y", ast.Store()) + for args in (s, l, l), (l, s, l), (l, l, s): + self.expr(ast.IfExp(*args), "must have Load context") + + def test_dict(self): + d = ast.Dict([], [ast.Name("x", ast.Load())]) + self.expr(d, "same number of keys as values") + d = ast.Dict([ast.Name("x", ast.Load())], [None]) + self.expr(d, "None disallowed") + + def test_set(self): + self.expr(ast.Set([None]), "None disallowed") + s = ast.Set([ast.Name("x", ast.Store())]) + self.expr(s, "must have Load context") + + def _check_comprehension(self, fac): + self.expr(fac([]), "comprehension with no generators") + g = ast.comprehension(ast.Name("x", ast.Load()), + ast.Name("x", ast.Load()), [], 0) + self.expr(fac([g]), "must have Store context") + g = ast.comprehension(ast.Name("x", ast.Store()), + ast.Name("x", ast.Store()), [], 0) + self.expr(fac([g]), "must have Load context") + x = ast.Name("x", ast.Store()) + y = ast.Name("y", ast.Load()) + g = ast.comprehension(x, y, [None], 0) + self.expr(fac([g]), "None disallowed") + g = ast.comprehension(x, y, [ast.Name("x", ast.Store())], 0) + self.expr(fac([g]), "must have Load context") + + def _simple_comp(self, fac): + g = ast.comprehension(ast.Name("x", ast.Store()), + ast.Name("x", ast.Load()), [], 0) + self.expr(fac(ast.Name("x", ast.Store()), [g]), + "must have Load context") + def wrap(gens): + return fac(ast.Name("x", ast.Store()), gens) + self._check_comprehension(wrap) + + def test_listcomp(self): + self._simple_comp(ast.ListComp) + + def test_setcomp(self): + self._simple_comp(ast.SetComp) + + def test_generatorexp(self): + self._simple_comp(ast.GeneratorExp) + + def test_dictcomp(self): + g = ast.comprehension(ast.Name("y", ast.Store()), + ast.Name("p", ast.Load()), [], 0) + c = ast.DictComp(ast.Name("x", ast.Store()), + ast.Name("y", ast.Load()), [g]) + self.expr(c, "must have Load context") + c = ast.DictComp(ast.Name("x", ast.Load()), + ast.Name("y", ast.Store()), [g]) + self.expr(c, "must have Load context") + def factory(comps): + k = ast.Name("x", ast.Load()) + v = ast.Name("y", ast.Load()) + return ast.DictComp(k, v, comps) + self._check_comprehension(factory) + + def test_yield(self): + self.expr(ast.Yield(ast.Name("x", ast.Store())), "must have Load") + self.expr(ast.YieldFrom(ast.Name("x", ast.Store())), "must have Load") + + def test_compare(self): + left = ast.Name("x", ast.Load()) + comp = ast.Compare(left, [ast.In()], []) + self.expr(comp, "no comparators") + comp = ast.Compare(left, [ast.In()], [ast.Num(4), ast.Num(5)]) + self.expr(comp, "different number of comparators and operands") + comp = ast.Compare(ast.Num("blah"), [ast.In()], [left]) + self.expr(comp) + comp = ast.Compare(left, [ast.In()], [ast.Num("blah")]) + self.expr(comp) + + def test_call(self): + func = ast.Name("x", ast.Load()) + args = [ast.Name("y", ast.Load())] + keywords = [ast.keyword("w", ast.Name("z", ast.Load()))] + call = ast.Call(ast.Name("x", ast.Store()), args, keywords) + self.expr(call, "must have Load context") + call = ast.Call(func, [None], keywords) + self.expr(call, "None disallowed") + bad_keywords = [ast.keyword("w", ast.Name("z", ast.Store()))] + call = ast.Call(func, args, bad_keywords) + self.expr(call, "must have Load context") + + def test_num(self): + class subint(int): + pass + class subfloat(float): + pass + class subcomplex(complex): + pass + for obj in "0", "hello": + self.expr(ast.Num(obj)) + for obj in subint(), subfloat(), subcomplex(): + self.expr(ast.Num(obj), "invalid type", exc=TypeError) + + def test_attribute(self): + attr = ast.Attribute(ast.Name("x", ast.Store()), "y", ast.Load()) + self.expr(attr, "must have Load context") + + def test_subscript(self): + sub = ast.Subscript(ast.Name("x", ast.Store()), ast.Num(3), + ast.Load()) + self.expr(sub, "must have Load context") + x = ast.Name("x", ast.Load()) + sub = ast.Subscript(x, ast.Name("y", ast.Store()), + ast.Load()) + self.expr(sub, "must have Load context") + s = ast.Name("x", ast.Store()) + for args in (s, None, None), (None, s, None), (None, None, s): + sl = ast.Slice(*args) + self.expr(ast.Subscript(x, sl, ast.Load()), + "must have Load context") + sl = ast.Tuple([], ast.Load()) + self.expr(ast.Subscript(x, sl, ast.Load())) + sl = ast.Tuple([s], ast.Load()) + self.expr(ast.Subscript(x, sl, ast.Load()), "must have Load context") + + def test_starred(self): + left = ast.List([ast.Starred(ast.Name("x", ast.Load()), ast.Store())], + ast.Store()) + assign = ast.Assign([left], ast.Num(4)) + self.stmt(assign, "must have Store context") + + def _sequence(self, fac): + self.expr(fac([None], ast.Load()), "None disallowed") + self.expr(fac([ast.Name("x", ast.Store())], ast.Load()), + "must have Load context") + + def test_list(self): + self._sequence(ast.List) + + def test_tuple(self): + self._sequence(ast.Tuple) + + def test_nameconstant(self): + self.expr(ast.NameConstant(4)) + + def test_stdlib_validates(self): + stdlib = os.path.dirname(ast.__file__) + tests = [fn for fn in os.listdir(stdlib) if fn.endswith(".py")] + tests.extend(["test/test_grammar.py", "test/test_unpack_ex.py"]) + for module in tests: + with self.subTest(module): + fn = os.path.join(stdlib, module) + with open(fn, "r", encoding="utf-8") as fp: + source = fp.read() + mod = ast.parse(source, fn) + compile(mod, fn, "exec") + + constant_1 = ast.Constant(1) + pattern_1 = ast.MatchValue(constant_1) + + constant_x = ast.Constant('x') + pattern_x = ast.MatchValue(constant_x) + + constant_true = ast.Constant(True) + pattern_true = ast.MatchSingleton(True) + + name_carter = ast.Name('carter', ast.Load()) + + _MATCH_PATTERNS = [ + ast.MatchValue( + ast.Attribute( + ast.Attribute( + ast.Name('x', ast.Store()), + 'y', ast.Load() + ), + 'z', ast.Load() + ) + ), + ast.MatchValue( + ast.Attribute( + ast.Attribute( + ast.Name('x', ast.Load()), + 'y', ast.Store() + ), + 'z', ast.Load() + ) + ), + ast.MatchValue( + ast.Constant(...) + ), + ast.MatchValue( + ast.Constant(True) + ), + ast.MatchValue( + ast.Constant((1,2,3)) + ), + ast.MatchSingleton('string'), + ast.MatchSequence([ + ast.MatchSingleton('string') + ]), + ast.MatchSequence( + [ + ast.MatchSequence( + [ + ast.MatchSingleton('string') + ] + ) + ] + ), + ast.MatchMapping( + [constant_1, constant_true], + [pattern_x] + ), + ast.MatchMapping( + [constant_true, constant_1], + [pattern_x, pattern_1], + rest='True' + ), + ast.MatchMapping( + [constant_true, ast.Starred(ast.Name('lol', ast.Load()), ast.Load())], + [pattern_x, pattern_1], + rest='legit' + ), + ast.MatchClass( + ast.Attribute( + ast.Attribute( + constant_x, + 'y', ast.Load()), + 'z', ast.Load()), + patterns=[], kwd_attrs=[], kwd_patterns=[] + ), + ast.MatchClass( + name_carter, + patterns=[], + kwd_attrs=['True'], + kwd_patterns=[pattern_1] + ), + ast.MatchClass( + name_carter, + patterns=[], + kwd_attrs=[], + kwd_patterns=[pattern_1] + ), + ast.MatchClass( + name_carter, + patterns=[ast.MatchSingleton('string')], + kwd_attrs=[], + kwd_patterns=[] + ), + ast.MatchClass( + name_carter, + patterns=[ast.MatchStar()], + kwd_attrs=[], + kwd_patterns=[] + ), + ast.MatchClass( + name_carter, + patterns=[], + kwd_attrs=[], + kwd_patterns=[ast.MatchStar()] + ), + ast.MatchSequence( + [ + ast.MatchStar("True") + ] + ), + ast.MatchAs( + name='False' + ), + ast.MatchOr( + [] + ), + ast.MatchOr( + [pattern_1] + ), + ast.MatchOr( + [pattern_1, pattern_x, ast.MatchSingleton('xxx')] + ), + ast.MatchAs(name="_"), + ast.MatchStar(name="x"), + ast.MatchSequence([ast.MatchStar("_")]), + ast.MatchMapping([], [], rest="_"), + ] + + def test_match_validation_pattern(self): + name_x = ast.Name('x', ast.Load()) + for pattern in self._MATCH_PATTERNS: + with self.subTest(ast.dump(pattern, indent=4)): + node = ast.Match( + subject=name_x, + cases = [ + ast.match_case( + pattern=pattern, + body = [ast.Pass()] + ) + ] + ) + node = ast.fix_missing_locations(node) + module = ast.Module([node], []) + with self.assertRaises(ValueError): + compile(module, "", "exec") + + +class ConstantTests(unittest.TestCase): + """Tests on the ast.Constant node type.""" + + def compile_constant(self, value): + tree = ast.parse("x = 123") + + node = tree.body[0].value + new_node = ast.Constant(value=value) + ast.copy_location(new_node, node) + tree.body[0].value = new_node + + code = compile(tree, "", "exec") + + ns = {} + exec(code, ns) + return ns['x'] + + def test_validation(self): + with self.assertRaises(TypeError) as cm: + self.compile_constant([1, 2, 3]) + self.assertEqual(str(cm.exception), + "got an invalid type in Constant: list") + + def test_singletons(self): + for const in (None, False, True, Ellipsis, b'', frozenset()): + with self.subTest(const=const): + value = self.compile_constant(const) + self.assertIs(value, const) + + def test_values(self): + nested_tuple = (1,) + nested_frozenset = frozenset({1}) + for level in range(3): + nested_tuple = (nested_tuple, 2) + nested_frozenset = frozenset({nested_frozenset, 2}) + values = (123, 123.0, 123j, + "unicode", b'bytes', + tuple("tuple"), frozenset("frozenset"), + nested_tuple, nested_frozenset) + for value in values: + with self.subTest(value=value): + result = self.compile_constant(value) + self.assertEqual(result, value) + + def test_assign_to_constant(self): + tree = ast.parse("x = 1") + + target = tree.body[0].targets[0] + new_target = ast.Constant(value=1) + ast.copy_location(new_target, target) + tree.body[0].targets[0] = new_target + + with self.assertRaises(ValueError) as cm: + compile(tree, "string", "exec") + self.assertEqual(str(cm.exception), + "expression which can't be assigned " + "to in Store context") + + def test_get_docstring(self): + tree = ast.parse("'docstring'\nx = 1") + self.assertEqual(ast.get_docstring(tree), 'docstring') + + def get_load_const(self, tree): + # Compile to bytecode, disassemble and get parameter of LOAD_CONST + # instructions + co = compile(tree, '', 'exec') + consts = [] + for instr in dis.get_instructions(co): + if instr.opname == 'LOAD_CONST' or instr.opname == 'RETURN_CONST': + consts.append(instr.argval) + return consts + + @support.cpython_only + def test_load_const(self): + consts = [None, + True, False, + 124, + 2.0, + 3j, + "unicode", + b'bytes', + (1, 2, 3)] + + code = '\n'.join(['x={!r}'.format(const) for const in consts]) + code += '\nx = ...' + consts.extend((Ellipsis, None)) + + tree = ast.parse(code) + self.assertEqual(self.get_load_const(tree), + consts) + + # Replace expression nodes with constants + for assign, const in zip(tree.body, consts): + assert isinstance(assign, ast.Assign), ast.dump(assign) + new_node = ast.Constant(value=const) + ast.copy_location(new_node, assign.value) + assign.value = new_node + + self.assertEqual(self.get_load_const(tree), + consts) + + def test_literal_eval(self): + tree = ast.parse("1 + 2") + binop = tree.body[0].value + + new_left = ast.Constant(value=10) + ast.copy_location(new_left, binop.left) + binop.left = new_left + + new_right = ast.Constant(value=20j) + ast.copy_location(new_right, binop.right) + binop.right = new_right + + self.assertEqual(ast.literal_eval(binop), 10+20j) + + def test_string_kind(self): + c = ast.parse('"x"', mode='eval').body + self.assertEqual(c.value, "x") + self.assertEqual(c.kind, None) + + c = ast.parse('u"x"', mode='eval').body + self.assertEqual(c.value, "x") + self.assertEqual(c.kind, "u") + + c = ast.parse('r"x"', mode='eval').body + self.assertEqual(c.value, "x") + self.assertEqual(c.kind, None) + + c = ast.parse('b"x"', mode='eval').body + self.assertEqual(c.value, b"x") + self.assertEqual(c.kind, None) + + +class EndPositionTests(unittest.TestCase): + """Tests for end position of AST nodes. + + Testing end positions of nodes requires a bit of extra care + because of how LL parsers work. + """ + def _check_end_pos(self, ast_node, end_lineno, end_col_offset): + self.assertEqual(ast_node.end_lineno, end_lineno) + self.assertEqual(ast_node.end_col_offset, end_col_offset) + + def _check_content(self, source, ast_node, content): + self.assertEqual(ast.get_source_segment(source, ast_node), content) + + def _parse_value(self, s): + # Use duck-typing to support both single expression + # and a right hand side of an assignment statement. + return ast.parse(s).body[0].value + + def test_lambda(self): + s = 'lambda x, *y: None' + lam = self._parse_value(s) + self._check_content(s, lam.body, 'None') + self._check_content(s, lam.args.args[0], 'x') + self._check_content(s, lam.args.vararg, 'y') + + def test_func_def(self): + s = dedent(''' + def func(x: int, + *args: str, + z: float = 0, + **kwargs: Any) -> bool: + return True + ''').strip() + fdef = ast.parse(s).body[0] + self._check_end_pos(fdef, 5, 15) + self._check_content(s, fdef.body[0], 'return True') + self._check_content(s, fdef.args.args[0], 'x: int') + self._check_content(s, fdef.args.args[0].annotation, 'int') + self._check_content(s, fdef.args.kwarg, 'kwargs: Any') + self._check_content(s, fdef.args.kwarg.annotation, 'Any') + + def test_call(self): + s = 'func(x, y=2, **kw)' + call = self._parse_value(s) + self._check_content(s, call.func, 'func') + self._check_content(s, call.keywords[0].value, '2') + self._check_content(s, call.keywords[1].value, 'kw') + + def test_call_noargs(self): + s = 'x[0]()' + call = self._parse_value(s) + self._check_content(s, call.func, 'x[0]') + self._check_end_pos(call, 1, 6) + + def test_class_def(self): + s = dedent(''' + class C(A, B): + x: int = 0 + ''').strip() + cdef = ast.parse(s).body[0] + self._check_end_pos(cdef, 2, 14) + self._check_content(s, cdef.bases[1], 'B') + self._check_content(s, cdef.body[0], 'x: int = 0') + + def test_class_kw(self): + s = 'class S(metaclass=abc.ABCMeta): pass' + cdef = ast.parse(s).body[0] + self._check_content(s, cdef.keywords[0].value, 'abc.ABCMeta') + + def test_multi_line_str(self): + s = dedent(''' + x = """Some multi-line text. + + It goes on starting from same indent.""" + ''').strip() + assign = ast.parse(s).body[0] + self._check_end_pos(assign, 3, 40) + self._check_end_pos(assign.value, 3, 40) + + def test_continued_str(self): + s = dedent(''' + x = "first part" \\ + "second part" + ''').strip() + assign = ast.parse(s).body[0] + self._check_end_pos(assign, 2, 13) + self._check_end_pos(assign.value, 2, 13) + + def test_suites(self): + # We intentionally put these into the same string to check + # that empty lines are not part of the suite. + s = dedent(''' + while True: + pass + + if one(): + x = None + elif other(): + y = None + else: + z = None + + for x, y in stuff: + assert True + + try: + raise RuntimeError + except TypeError as e: + pass + + pass + ''').strip() + mod = ast.parse(s) + while_loop = mod.body[0] + if_stmt = mod.body[1] + for_loop = mod.body[2] + try_stmt = mod.body[3] + pass_stmt = mod.body[4] + + self._check_end_pos(while_loop, 2, 8) + self._check_end_pos(if_stmt, 9, 12) + self._check_end_pos(for_loop, 12, 15) + self._check_end_pos(try_stmt, 17, 8) + self._check_end_pos(pass_stmt, 19, 4) + + self._check_content(s, while_loop.test, 'True') + self._check_content(s, if_stmt.body[0], 'x = None') + self._check_content(s, if_stmt.orelse[0].test, 'other()') + self._check_content(s, for_loop.target, 'x, y') + self._check_content(s, try_stmt.body[0], 'raise RuntimeError') + self._check_content(s, try_stmt.handlers[0].type, 'TypeError') + + def test_fstring(self): + s = 'x = f"abc {x + y} abc"' + fstr = self._parse_value(s) + binop = fstr.values[1].value + self._check_content(s, binop, 'x + y') + + def test_fstring_multi_line(self): + s = dedent(''' + f"""Some multi-line text. + { + arg_one + + + arg_two + } + It goes on...""" + ''').strip() + fstr = self._parse_value(s) + binop = fstr.values[1].value + self._check_end_pos(binop, 5, 7) + self._check_content(s, binop.left, 'arg_one') + self._check_content(s, binop.right, 'arg_two') + + def test_import_from_multi_line(self): + s = dedent(''' + from x.y.z import ( + a, b, c as c + ) + ''').strip() + imp = ast.parse(s).body[0] + self._check_end_pos(imp, 3, 1) + self._check_end_pos(imp.names[2], 2, 16) + + def test_slices(self): + s1 = 'f()[1, 2] [0]' + s2 = 'x[ a.b: c.d]' + sm = dedent(''' + x[ a.b: f () , + g () : c.d + ] + ''').strip() + i1, i2, im = map(self._parse_value, (s1, s2, sm)) + self._check_content(s1, i1.value, 'f()[1, 2]') + self._check_content(s1, i1.value.slice, '1, 2') + self._check_content(s2, i2.slice.lower, 'a.b') + self._check_content(s2, i2.slice.upper, 'c.d') + self._check_content(sm, im.slice.elts[0].upper, 'f ()') + self._check_content(sm, im.slice.elts[1].lower, 'g ()') + self._check_end_pos(im, 3, 3) + + def test_binop(self): + s = dedent(''' + (1 * 2 + (3 ) + + 4 + ) + ''').strip() + binop = self._parse_value(s) + self._check_end_pos(binop, 2, 6) + self._check_content(s, binop.right, '4') + self._check_content(s, binop.left, '1 * 2 + (3 )') + self._check_content(s, binop.left.right, '3') + + def test_boolop(self): + s = dedent(''' + if (one_condition and + (other_condition or yet_another_one)): + pass + ''').strip() + bop = ast.parse(s).body[0].test + self._check_end_pos(bop, 2, 44) + self._check_content(s, bop.values[1], + 'other_condition or yet_another_one') + + def test_tuples(self): + s1 = 'x = () ;' + s2 = 'x = 1 , ;' + s3 = 'x = (1 , 2 ) ;' + sm = dedent(''' + x = ( + a, b, + ) + ''').strip() + t1, t2, t3, tm = map(self._parse_value, (s1, s2, s3, sm)) + self._check_content(s1, t1, '()') + self._check_content(s2, t2, '1 ,') + self._check_content(s3, t3, '(1 , 2 )') + self._check_end_pos(tm, 3, 1) + + def test_attribute_spaces(self): + s = 'func(x. y .z)' + call = self._parse_value(s) + self._check_content(s, call, s) + self._check_content(s, call.args[0], 'x. y .z') + + def test_redundant_parenthesis(self): + s = '( ( ( a + b ) ) )' + v = ast.parse(s).body[0].value + self.assertEqual(type(v).__name__, 'BinOp') + self._check_content(s, v, 'a + b') + s2 = 'await ' + s + v = ast.parse(s2).body[0].value.value + self.assertEqual(type(v).__name__, 'BinOp') + self._check_content(s2, v, 'a + b') + + def test_trailers_with_redundant_parenthesis(self): + tests = ( + ('( ( ( a ) ) ) ( )', 'Call'), + ('( ( ( a ) ) ) ( b )', 'Call'), + ('( ( ( a ) ) ) [ b ]', 'Subscript'), + ('( ( ( a ) ) ) . b', 'Attribute'), + ) + for s, t in tests: + with self.subTest(s): + v = ast.parse(s).body[0].value + self.assertEqual(type(v).__name__, t) + self._check_content(s, v, s) + s2 = 'await ' + s + v = ast.parse(s2).body[0].value.value + self.assertEqual(type(v).__name__, t) + self._check_content(s2, v, s) + + def test_displays(self): + s1 = '[{}, {1, }, {1, 2,} ]' + s2 = '{a: b, f (): g () ,}' + c1 = self._parse_value(s1) + c2 = self._parse_value(s2) + self._check_content(s1, c1.elts[0], '{}') + self._check_content(s1, c1.elts[1], '{1, }') + self._check_content(s1, c1.elts[2], '{1, 2,}') + self._check_content(s2, c2.keys[1], 'f ()') + self._check_content(s2, c2.values[1], 'g ()') + + def test_comprehensions(self): + s = dedent(''' + x = [{x for x, y in stuff + if cond.x} for stuff in things] + ''').strip() + cmp = self._parse_value(s) + self._check_end_pos(cmp, 2, 37) + self._check_content(s, cmp.generators[0].iter, 'things') + self._check_content(s, cmp.elt.generators[0].iter, 'stuff') + self._check_content(s, cmp.elt.generators[0].ifs[0], 'cond.x') + self._check_content(s, cmp.elt.generators[0].target, 'x, y') + + def test_yield_await(self): + s = dedent(''' + async def f(): + yield x + await y + ''').strip() + fdef = ast.parse(s).body[0] + self._check_content(s, fdef.body[0].value, 'yield x') + self._check_content(s, fdef.body[1].value, 'await y') + + def test_source_segment_multi(self): + s_orig = dedent(''' + x = ( + a, b, + ) + () + ''').strip() + s_tuple = dedent(''' + ( + a, b, + ) + ''').strip() + binop = self._parse_value(s_orig) + self.assertEqual(ast.get_source_segment(s_orig, binop.left), s_tuple) + + def test_source_segment_padded(self): + s_orig = dedent(''' + class C: + def fun(self) -> None: + "ЖЖЖЖЖ" + ''').strip() + s_method = ' def fun(self) -> None:\n' \ + ' "ЖЖЖЖЖ"' + cdef = ast.parse(s_orig).body[0] + self.assertEqual(ast.get_source_segment(s_orig, cdef.body[0], padded=True), + s_method) + + def test_source_segment_endings(self): + s = 'v = 1\r\nw = 1\nx = 1\n\ry = 1\rz = 1\r\n' + v, w, x, y, z = ast.parse(s).body + self._check_content(s, v, 'v = 1') + self._check_content(s, w, 'w = 1') + self._check_content(s, x, 'x = 1') + self._check_content(s, y, 'y = 1') + self._check_content(s, z, 'z = 1') + + def test_source_segment_tabs(self): + s = dedent(''' + class C: + \t\f def fun(self) -> None: + \t\f pass + ''').strip() + s_method = ' \t\f def fun(self) -> None:\n' \ + ' \t\f pass' + + cdef = ast.parse(s).body[0] + self.assertEqual(ast.get_source_segment(s, cdef.body[0], padded=True), s_method) + + def test_source_segment_missing_info(self): + s = 'v = 1\r\nw = 1\nx = 1\n\ry = 1\r\n' + v, w, x, y = ast.parse(s).body + del v.lineno + del w.end_lineno + del x.col_offset + del y.end_col_offset + self.assertIsNone(ast.get_source_segment(s, v)) + self.assertIsNone(ast.get_source_segment(s, w)) + self.assertIsNone(ast.get_source_segment(s, x)) + self.assertIsNone(ast.get_source_segment(s, y)) + +class BaseNodeVisitorCases: + # Both `NodeVisitor` and `NodeTranformer` must raise these warnings: + def test_old_constant_nodes(self): + class Visitor(self.visitor_class): + def visit_Num(self, node): + log.append((node.lineno, 'Num', node.n)) + def visit_Str(self, node): + log.append((node.lineno, 'Str', node.s)) + def visit_Bytes(self, node): + log.append((node.lineno, 'Bytes', node.s)) + def visit_NameConstant(self, node): + log.append((node.lineno, 'NameConstant', node.value)) + def visit_Ellipsis(self, node): + log.append((node.lineno, 'Ellipsis', ...)) + mod = ast.parse(dedent('''\ + i = 42 + f = 4.25 + c = 4.25j + s = 'string' + b = b'bytes' + t = True + n = None + e = ... + ''')) + visitor = Visitor() + log = [] + with warnings.catch_warnings(record=True) as wlog: + warnings.filterwarnings('always', '', DeprecationWarning) + visitor.visit(mod) + self.assertEqual(log, [ + (1, 'Num', 42), + (2, 'Num', 4.25), + (3, 'Num', 4.25j), + (4, 'Str', 'string'), + (5, 'Bytes', b'bytes'), + (6, 'NameConstant', True), + (7, 'NameConstant', None), + (8, 'Ellipsis', ...), + ]) + self.assertEqual([str(w.message) for w in wlog], [ + 'visit_Num is deprecated; add visit_Constant', + 'visit_Num is deprecated; add visit_Constant', + 'visit_Num is deprecated; add visit_Constant', + 'visit_Str is deprecated; add visit_Constant', + 'visit_Bytes is deprecated; add visit_Constant', + 'visit_NameConstant is deprecated; add visit_Constant', + 'visit_NameConstant is deprecated; add visit_Constant', + 'visit_Ellipsis is deprecated; add visit_Constant', + ]) + + +class NodeVisitorTests(BaseNodeVisitorCases, unittest.TestCase): + visitor_class = ast.NodeVisitor + + +class NodeTransformerTests(ASTTestMixin, BaseNodeVisitorCases, unittest.TestCase): + visitor_class = ast.NodeTransformer + + def assertASTTransformation(self, tranformer_class, + initial_code, expected_code): + initial_ast = ast.parse(dedent(initial_code)) + expected_ast = ast.parse(dedent(expected_code)) + + tranformer = tranformer_class() + result_ast = ast.fix_missing_locations(tranformer.visit(initial_ast)) + + self.assertASTEqual(result_ast, expected_ast) + + def test_node_remove_single(self): + code = 'def func(arg) -> SomeType: ...' + expected = 'def func(arg): ...' + + # Since `FunctionDef.returns` is defined as a single value, we test + # the `if isinstance(old_value, AST):` branch here. + class SomeTypeRemover(ast.NodeTransformer): + def visit_Name(self, node: ast.Name): + self.generic_visit(node) + if node.id == 'SomeType': + return None + return node + + self.assertASTTransformation(SomeTypeRemover, code, expected) + + def test_node_remove_from_list(self): + code = """ + def func(arg): + print(arg) + yield arg + """ + expected = """ + def func(arg): + print(arg) + """ + + # Since `FunctionDef.body` is defined as a list, we test + # the `if isinstance(old_value, list):` branch here. + class YieldRemover(ast.NodeTransformer): + def visit_Expr(self, node: ast.Expr): + self.generic_visit(node) + if isinstance(node.value, ast.Yield): + return None # Remove `yield` from a function + return node + + self.assertASTTransformation(YieldRemover, code, expected) + + def test_node_return_list(self): + code = """ + class DSL(Base, kw1=True): ... + """ + expected = """ + class DSL(Base, kw1=True, kw2=True, kw3=False): ... + """ + + class ExtendKeywords(ast.NodeTransformer): + def visit_keyword(self, node: ast.keyword): + self.generic_visit(node) + if node.arg == 'kw1': + return [ + node, + ast.keyword('kw2', ast.Constant(True)), + ast.keyword('kw3', ast.Constant(False)), + ] + return node + + self.assertASTTransformation(ExtendKeywords, code, expected) + + def test_node_mutate(self): + code = """ + def func(arg): + print(arg) + """ + expected = """ + def func(arg): + log(arg) + """ + + class PrintToLog(ast.NodeTransformer): + def visit_Call(self, node: ast.Call): + self.generic_visit(node) + if isinstance(node.func, ast.Name) and node.func.id == 'print': + node.func.id = 'log' + return node + + self.assertASTTransformation(PrintToLog, code, expected) + + def test_node_replace(self): + code = """ + def func(arg): + print(arg) + """ + expected = """ + def func(arg): + logger.log(arg, debug=True) + """ + + class PrintToLog(ast.NodeTransformer): + def visit_Call(self, node: ast.Call): + self.generic_visit(node) + if isinstance(node.func, ast.Name) and node.func.id == 'print': + return ast.Call( + func=ast.Attribute( + ast.Name('logger', ctx=ast.Load()), + attr='log', + ctx=ast.Load(), + ), + args=node.args, + keywords=[ast.keyword('debug', ast.Constant(True))], + ) + return node + + self.assertASTTransformation(PrintToLog, code, expected) + + +@support.cpython_only +class ModuleStateTests(unittest.TestCase): + # bpo-41194, bpo-41261, bpo-41631: The _ast module uses a global state. + + def check_ast_module(self): + # Check that the _ast module still works as expected + code = 'x + 1' + filename = '' + mode = 'eval' + + # Create _ast.AST subclasses instances + ast_tree = compile(code, filename, mode, flags=ast.PyCF_ONLY_AST) + + # Call PyAST_Check() + code = compile(ast_tree, filename, mode) + self.assertIsInstance(code, types.CodeType) + + def test_reload_module(self): + # bpo-41194: Importing the _ast module twice must not crash. + with support.swap_item(sys.modules, '_ast', None): + del sys.modules['_ast'] + import _ast as ast1 + + del sys.modules['_ast'] + import _ast as ast2 + + self.check_ast_module() + + # Unloading the two _ast module instances must not crash. + del ast1 + del ast2 + support.gc_collect() + + self.check_ast_module() + + def test_sys_modules(self): + # bpo-41631: Test reproducing a Mercurial crash when PyAST_Check() + # imported the _ast module internally. + lazy_mod = object() + + def my_import(name, *args, **kw): + sys.modules[name] = lazy_mod + return lazy_mod + + with support.swap_item(sys.modules, '_ast', None): + del sys.modules['_ast'] + + with support.swap_attr(builtins, '__import__', my_import): + # Test that compile() does not import the _ast module + self.check_ast_module() + self.assertNotIn('_ast', sys.modules) + + # Sanity check of the test itself + import _ast + self.assertIs(_ast, lazy_mod) + + def test_subinterpreter(self): + # bpo-41631: Importing and using the _ast module in a subinterpreter + # must not crash. + code = dedent(''' + import _ast + import ast + import gc + import sys + import types + + # Create _ast.AST subclasses instances and call PyAST_Check() + ast_tree = compile('x+1', '', 'eval', + flags=ast.PyCF_ONLY_AST) + code = compile(ast_tree, 'string', 'eval') + if not isinstance(code, types.CodeType): + raise AssertionError + + # Unloading the _ast module must not crash. + del ast, _ast + del sys.modules['ast'], sys.modules['_ast'] + gc.collect() + ''') + res = support.run_in_subinterp(code) + self.assertEqual(res, 0) + + +def main(): + if __name__ != '__main__': + return + if sys.argv[1:] == ['-g']: + for statements, kind in ((exec_tests, "exec"), (single_tests, "single"), + (eval_tests, "eval")): + print(kind+"_results = [") + for statement in statements: + tree = ast.parse(statement, "?", kind) + print("%r," % (to_tuple(tree),)) + print("]") + print("main()") + raise SystemExit + unittest.main() + +#### EVERYTHING BELOW IS GENERATED BY python Lib/test/test_ast.py -g ##### +exec_results = [ +('Module', [('Expr', (1, 0, 1, 4), ('Constant', (1, 0, 1, 4), None, None))], []), +('Module', [('Expr', (1, 0, 1, 18), ('Constant', (1, 0, 1, 18), 'module docstring', None))], []), +('Module', [('FunctionDef', (1, 0, 1, 13), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (1, 9, 1, 13))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 29), 'f', ('arguments', [], [], None, [], [], None, []), [('Expr', (1, 9, 1, 29), ('Constant', (1, 9, 1, 29), 'function docstring', None))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 14), 'f', ('arguments', [], [('arg', (1, 6, 1, 7), 'a', None, None)], None, [], [], None, []), [('Pass', (1, 10, 1, 14))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 16), 'f', ('arguments', [], [('arg', (1, 6, 1, 7), 'a', None, None)], None, [], [], None, [('Constant', (1, 8, 1, 9), 0, None)]), [('Pass', (1, 12, 1, 16))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 18), 'f', ('arguments', [], [], ('arg', (1, 7, 1, 11), 'args', None, None), [], [], None, []), [('Pass', (1, 14, 1, 18))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 23), 'f', ('arguments', [], [], ('arg', (1, 7, 1, 16), 'args', ('Starred', (1, 13, 1, 16), ('Name', (1, 14, 1, 16), 'Ts', ('Load',)), ('Load',)), None), [], [], None, []), [('Pass', (1, 19, 1, 23))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 36), 'f', ('arguments', [], [], ('arg', (1, 7, 1, 29), 'args', ('Starred', (1, 13, 1, 29), ('Subscript', (1, 14, 1, 29), ('Name', (1, 14, 1, 19), 'tuple', ('Load',)), ('Tuple', (1, 20, 1, 28), [('Name', (1, 20, 1, 23), 'int', ('Load',)), ('Constant', (1, 25, 1, 28), Ellipsis, None)], ('Load',)), ('Load',)), ('Load',)), None), [], [], None, []), [('Pass', (1, 32, 1, 36))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 36), 'f', ('arguments', [], [], ('arg', (1, 7, 1, 29), 'args', ('Starred', (1, 13, 1, 29), ('Subscript', (1, 14, 1, 29), ('Name', (1, 14, 1, 19), 'tuple', ('Load',)), ('Tuple', (1, 20, 1, 28), [('Name', (1, 20, 1, 23), 'int', ('Load',)), ('Starred', (1, 25, 1, 28), ('Name', (1, 26, 1, 28), 'Ts', ('Load',)), ('Load',))], ('Load',)), ('Load',)), ('Load',)), None), [], [], None, []), [('Pass', (1, 32, 1, 36))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 21), 'f', ('arguments', [], [], None, [], [], ('arg', (1, 8, 1, 14), 'kwargs', None, None), []), [('Pass', (1, 17, 1, 21))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 71), 'f', ('arguments', [], [('arg', (1, 6, 1, 7), 'a', None, None), ('arg', (1, 9, 1, 10), 'b', None, None), ('arg', (1, 14, 1, 15), 'c', None, None), ('arg', (1, 22, 1, 23), 'd', None, None), ('arg', (1, 28, 1, 29), 'e', None, None)], ('arg', (1, 35, 1, 39), 'args', None, None), [('arg', (1, 41, 1, 42), 'f', None, None)], [('Constant', (1, 43, 1, 45), 42, None)], ('arg', (1, 49, 1, 55), 'kwargs', None, None), [('Constant', (1, 11, 1, 12), 1, None), ('Constant', (1, 16, 1, 20), None, None), ('List', (1, 24, 1, 26), [], ('Load',)), ('Dict', (1, 30, 1, 32), [], [])]), [('Expr', (1, 58, 1, 71), ('Constant', (1, 58, 1, 71), 'doc for f()', None))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 27), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (1, 23, 1, 27))], [], ('Subscript', (1, 11, 1, 21), ('Name', (1, 11, 1, 16), 'tuple', ('Load',)), ('Tuple', (1, 17, 1, 20), [('Starred', (1, 17, 1, 20), ('Name', (1, 18, 1, 20), 'Ts', ('Load',)), ('Load',))], ('Load',)), ('Load',)), None)], []), +('Module', [('FunctionDef', (1, 0, 1, 32), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (1, 28, 1, 32))], [], ('Subscript', (1, 11, 1, 26), ('Name', (1, 11, 1, 16), 'tuple', ('Load',)), ('Tuple', (1, 17, 1, 25), [('Name', (1, 17, 1, 20), 'int', ('Load',)), ('Starred', (1, 22, 1, 25), ('Name', (1, 23, 1, 25), 'Ts', ('Load',)), ('Load',))], ('Load',)), ('Load',)), None)], []), +('Module', [('FunctionDef', (1, 0, 1, 45), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (1, 41, 1, 45))], [], ('Subscript', (1, 11, 1, 39), ('Name', (1, 11, 1, 16), 'tuple', ('Load',)), ('Tuple', (1, 17, 1, 38), [('Name', (1, 17, 1, 20), 'int', ('Load',)), ('Starred', (1, 22, 1, 38), ('Subscript', (1, 23, 1, 38), ('Name', (1, 23, 1, 28), 'tuple', ('Load',)), ('Tuple', (1, 29, 1, 37), [('Name', (1, 29, 1, 32), 'int', ('Load',)), ('Constant', (1, 34, 1, 37), Ellipsis, None)], ('Load',)), ('Load',)), ('Load',))], ('Load',)), ('Load',)), None)], []), +('Module', [('ClassDef', (1, 0, 1, 12), 'C', [], [], [('Pass', (1, 8, 1, 12))], [])], []), +('Module', [('ClassDef', (1, 0, 1, 32), 'C', [], [], [('Expr', (1, 9, 1, 32), ('Constant', (1, 9, 1, 32), 'docstring for class C', None))], [])], []), +('Module', [('ClassDef', (1, 0, 1, 21), 'C', [('Name', (1, 8, 1, 14), 'object', ('Load',))], [], [('Pass', (1, 17, 1, 21))], [])], []), +('Module', [('FunctionDef', (1, 0, 1, 16), 'f', ('arguments', [], [], None, [], [], None, []), [('Return', (1, 8, 1, 16), ('Constant', (1, 15, 1, 16), 1, None))], [], None, None)], []), +('Module', [('Delete', (1, 0, 1, 5), [('Name', (1, 4, 1, 5), 'v', ('Del',))])], []), +('Module', [('Assign', (1, 0, 1, 5), [('Name', (1, 0, 1, 1), 'v', ('Store',))], ('Constant', (1, 4, 1, 5), 1, None), None)], []), +('Module', [('Assign', (1, 0, 1, 7), [('Tuple', (1, 0, 1, 3), [('Name', (1, 0, 1, 1), 'a', ('Store',)), ('Name', (1, 2, 1, 3), 'b', ('Store',))], ('Store',))], ('Name', (1, 6, 1, 7), 'c', ('Load',)), None)], []), +('Module', [('Assign', (1, 0, 1, 9), [('Tuple', (1, 0, 1, 5), [('Name', (1, 1, 1, 2), 'a', ('Store',)), ('Name', (1, 3, 1, 4), 'b', ('Store',))], ('Store',))], ('Name', (1, 8, 1, 9), 'c', ('Load',)), None)], []), +('Module', [('Assign', (1, 0, 1, 9), [('List', (1, 0, 1, 5), [('Name', (1, 1, 1, 2), 'a', ('Store',)), ('Name', (1, 3, 1, 4), 'b', ('Store',))], ('Store',))], ('Name', (1, 8, 1, 9), 'c', ('Load',)), None)], []), +('Module', [('AnnAssign', (1, 0, 1, 13), ('Name', (1, 0, 1, 1), 'x', ('Store',)), ('Subscript', (1, 3, 1, 13), ('Name', (1, 3, 1, 8), 'tuple', ('Load',)), ('Tuple', (1, 9, 1, 12), [('Starred', (1, 9, 1, 12), ('Name', (1, 10, 1, 12), 'Ts', ('Load',)), ('Load',))], ('Load',)), ('Load',)), None, 1)], []), +('Module', [('AnnAssign', (1, 0, 1, 18), ('Name', (1, 0, 1, 1), 'x', ('Store',)), ('Subscript', (1, 3, 1, 18), ('Name', (1, 3, 1, 8), 'tuple', ('Load',)), ('Tuple', (1, 9, 1, 17), [('Name', (1, 9, 1, 12), 'int', ('Load',)), ('Starred', (1, 14, 1, 17), ('Name', (1, 15, 1, 17), 'Ts', ('Load',)), ('Load',))], ('Load',)), ('Load',)), None, 1)], []), +('Module', [('AnnAssign', (1, 0, 1, 31), ('Name', (1, 0, 1, 1), 'x', ('Store',)), ('Subscript', (1, 3, 1, 31), ('Name', (1, 3, 1, 8), 'tuple', ('Load',)), ('Tuple', (1, 9, 1, 30), [('Name', (1, 9, 1, 12), 'int', ('Load',)), ('Starred', (1, 14, 1, 30), ('Subscript', (1, 15, 1, 30), ('Name', (1, 15, 1, 20), 'tuple', ('Load',)), ('Tuple', (1, 21, 1, 29), [('Name', (1, 21, 1, 24), 'str', ('Load',)), ('Constant', (1, 26, 1, 29), Ellipsis, None)], ('Load',)), ('Load',)), ('Load',))], ('Load',)), ('Load',)), None, 1)], []), +('Module', [('AugAssign', (1, 0, 1, 6), ('Name', (1, 0, 1, 1), 'v', ('Store',)), ('Add',), ('Constant', (1, 5, 1, 6), 1, None))], []), +('Module', [('For', (1, 0, 1, 15), ('Name', (1, 4, 1, 5), 'v', ('Store',)), ('Name', (1, 9, 1, 10), 'v', ('Load',)), [('Pass', (1, 11, 1, 15))], [], None)], []), +('Module', [('While', (1, 0, 1, 12), ('Name', (1, 6, 1, 7), 'v', ('Load',)), [('Pass', (1, 8, 1, 12))], [])], []), +('Module', [('If', (1, 0, 1, 9), ('Name', (1, 3, 1, 4), 'v', ('Load',)), [('Pass', (1, 5, 1, 9))], [])], []), +('Module', [('If', (1, 0, 4, 6), ('Name', (1, 3, 1, 4), 'a', ('Load',)), [('Pass', (2, 2, 2, 6))], [('If', (3, 0, 4, 6), ('Name', (3, 5, 3, 6), 'b', ('Load',)), [('Pass', (4, 2, 4, 6))], [])])], []), +('Module', [('If', (1, 0, 6, 6), ('Name', (1, 3, 1, 4), 'a', ('Load',)), [('Pass', (2, 2, 2, 6))], [('If', (3, 0, 6, 6), ('Name', (3, 5, 3, 6), 'b', ('Load',)), [('Pass', (4, 2, 4, 6))], [('Pass', (6, 2, 6, 6))])])], []), +('Module', [('With', (1, 0, 1, 17), [('withitem', ('Name', (1, 5, 1, 6), 'x', ('Load',)), ('Name', (1, 10, 1, 11), 'y', ('Store',)))], [('Pass', (1, 13, 1, 17))], None)], []), +('Module', [('With', (1, 0, 1, 25), [('withitem', ('Name', (1, 5, 1, 6), 'x', ('Load',)), ('Name', (1, 10, 1, 11), 'y', ('Store',))), ('withitem', ('Name', (1, 13, 1, 14), 'z', ('Load',)), ('Name', (1, 18, 1, 19), 'q', ('Store',)))], [('Pass', (1, 21, 1, 25))], None)], []), +('Module', [('Raise', (1, 0, 1, 25), ('Call', (1, 6, 1, 25), ('Name', (1, 6, 1, 15), 'Exception', ('Load',)), [('Constant', (1, 16, 1, 24), 'string', None)], []), None)], []), +('Module', [('Try', (1, 0, 4, 6), [('Pass', (2, 2, 2, 6))], [('ExceptHandler', (3, 0, 4, 6), ('Name', (3, 7, 3, 16), 'Exception', ('Load',)), None, [('Pass', (4, 2, 4, 6))])], [], [])], []), +('Module', [('Try', (1, 0, 4, 6), [('Pass', (2, 2, 2, 6))], [], [], [('Pass', (4, 2, 4, 6))])], []), +('Module', [('TryStar', (1, 0, 4, 6), [('Pass', (2, 2, 2, 6))], [('ExceptHandler', (3, 0, 4, 6), ('Name', (3, 8, 3, 17), 'Exception', ('Load',)), None, [('Pass', (4, 2, 4, 6))])], [], [])], []), +('Module', [('Assert', (1, 0, 1, 8), ('Name', (1, 7, 1, 8), 'v', ('Load',)), None)], []), +('Module', [('Import', (1, 0, 1, 10), [('alias', (1, 7, 1, 10), 'sys', None)])], []), +('Module', [('ImportFrom', (1, 0, 1, 17), 'sys', [('alias', (1, 16, 1, 17), 'v', None)], 0)], []), +('Module', [('Global', (1, 0, 1, 8), ['v'])], []), +('Module', [('Expr', (1, 0, 1, 1), ('Constant', (1, 0, 1, 1), 1, None))], []), +('Module', [('Pass', (1, 0, 1, 4))], []), +('Module', [('For', (1, 0, 1, 16), ('Name', (1, 4, 1, 5), 'v', ('Store',)), ('Name', (1, 9, 1, 10), 'v', ('Load',)), [('Break', (1, 11, 1, 16))], [], None)], []), +('Module', [('For', (1, 0, 1, 19), ('Name', (1, 4, 1, 5), 'v', ('Store',)), ('Name', (1, 9, 1, 10), 'v', ('Load',)), [('Continue', (1, 11, 1, 19))], [], None)], []), +('Module', [('For', (1, 0, 1, 18), ('Tuple', (1, 4, 1, 7), [('Name', (1, 4, 1, 5), 'a', ('Store',)), ('Name', (1, 6, 1, 7), 'b', ('Store',))], ('Store',)), ('Name', (1, 11, 1, 12), 'c', ('Load',)), [('Pass', (1, 14, 1, 18))], [], None)], []), +('Module', [('For', (1, 0, 1, 20), ('Tuple', (1, 4, 1, 9), [('Name', (1, 5, 1, 6), 'a', ('Store',)), ('Name', (1, 7, 1, 8), 'b', ('Store',))], ('Store',)), ('Name', (1, 13, 1, 14), 'c', ('Load',)), [('Pass', (1, 16, 1, 20))], [], None)], []), +('Module', [('For', (1, 0, 1, 20), ('List', (1, 4, 1, 9), [('Name', (1, 5, 1, 6), 'a', ('Store',)), ('Name', (1, 7, 1, 8), 'b', ('Store',))], ('Store',)), ('Name', (1, 13, 1, 14), 'c', ('Load',)), [('Pass', (1, 16, 1, 20))], [], None)], []), +('Module', [('Expr', (1, 0, 11, 5), ('GeneratorExp', (1, 0, 11, 5), ('Tuple', (2, 4, 6, 5), [('Name', (3, 4, 3, 6), 'Aa', ('Load',)), ('Name', (5, 7, 5, 9), 'Bb', ('Load',))], ('Load',)), [('comprehension', ('Tuple', (8, 4, 10, 6), [('Name', (8, 4, 8, 6), 'Aa', ('Store',)), ('Name', (10, 4, 10, 6), 'Bb', ('Store',))], ('Store',)), ('Name', (10, 10, 10, 12), 'Cc', ('Load',)), [], 0)]))], []), +('Module', [('Expr', (1, 0, 1, 34), ('DictComp', (1, 0, 1, 34), ('Name', (1, 1, 1, 2), 'a', ('Load',)), ('Name', (1, 5, 1, 6), 'b', ('Load',)), [('comprehension', ('Name', (1, 11, 1, 12), 'w', ('Store',)), ('Name', (1, 16, 1, 17), 'x', ('Load',)), [], 0), ('comprehension', ('Name', (1, 22, 1, 23), 'm', ('Store',)), ('Name', (1, 27, 1, 28), 'p', ('Load',)), [('Name', (1, 32, 1, 33), 'g', ('Load',))], 0)]))], []), +('Module', [('Expr', (1, 0, 1, 20), ('DictComp', (1, 0, 1, 20), ('Name', (1, 1, 1, 2), 'a', ('Load',)), ('Name', (1, 5, 1, 6), 'b', ('Load',)), [('comprehension', ('Tuple', (1, 11, 1, 14), [('Name', (1, 11, 1, 12), 'v', ('Store',)), ('Name', (1, 13, 1, 14), 'w', ('Store',))], ('Store',)), ('Name', (1, 18, 1, 19), 'x', ('Load',)), [], 0)]))], []), +('Module', [('Expr', (1, 0, 1, 19), ('SetComp', (1, 0, 1, 19), ('Name', (1, 1, 1, 2), 'r', ('Load',)), [('comprehension', ('Name', (1, 7, 1, 8), 'l', ('Store',)), ('Name', (1, 12, 1, 13), 'x', ('Load',)), [('Name', (1, 17, 1, 18), 'g', ('Load',))], 0)]))], []), +('Module', [('Expr', (1, 0, 1, 16), ('SetComp', (1, 0, 1, 16), ('Name', (1, 1, 1, 2), 'r', ('Load',)), [('comprehension', ('Tuple', (1, 7, 1, 10), [('Name', (1, 7, 1, 8), 'l', ('Store',)), ('Name', (1, 9, 1, 10), 'm', ('Store',))], ('Store',)), ('Name', (1, 14, 1, 15), 'x', ('Load',)), [], 0)]))], []), +('Module', [('AsyncFunctionDef', (1, 0, 3, 18), 'f', ('arguments', [], [], None, [], [], None, []), [('Expr', (2, 1, 2, 17), ('Constant', (2, 1, 2, 17), 'async function', None)), ('Expr', (3, 1, 3, 18), ('Await', (3, 1, 3, 18), ('Call', (3, 7, 3, 18), ('Name', (3, 7, 3, 16), 'something', ('Load',)), [], [])))], [], None, None)], []), +('Module', [('AsyncFunctionDef', (1, 0, 3, 8), 'f', ('arguments', [], [], None, [], [], None, []), [('AsyncFor', (2, 1, 3, 8), ('Name', (2, 11, 2, 12), 'e', ('Store',)), ('Name', (2, 16, 2, 17), 'i', ('Load',)), [('Expr', (2, 19, 2, 20), ('Constant', (2, 19, 2, 20), 1, None))], [('Expr', (3, 7, 3, 8), ('Constant', (3, 7, 3, 8), 2, None))], None)], [], None, None)], []), +('Module', [('AsyncFunctionDef', (1, 0, 2, 21), 'f', ('arguments', [], [], None, [], [], None, []), [('AsyncWith', (2, 1, 2, 21), [('withitem', ('Name', (2, 12, 2, 13), 'a', ('Load',)), ('Name', (2, 17, 2, 18), 'b', ('Store',)))], [('Expr', (2, 20, 2, 21), ('Constant', (2, 20, 2, 21), 1, None))], None)], [], None, None)], []), +('Module', [('Expr', (1, 0, 1, 14), ('Dict', (1, 0, 1, 14), [None, ('Constant', (1, 10, 1, 11), 2, None)], [('Dict', (1, 3, 1, 8), [('Constant', (1, 4, 1, 5), 1, None)], [('Constant', (1, 6, 1, 7), 2, None)]), ('Constant', (1, 12, 1, 13), 3, None)]))], []), +('Module', [('Expr', (1, 0, 1, 12), ('Set', (1, 0, 1, 12), [('Starred', (1, 1, 1, 8), ('Set', (1, 2, 1, 8), [('Constant', (1, 3, 1, 4), 1, None), ('Constant', (1, 6, 1, 7), 2, None)]), ('Load',)), ('Constant', (1, 10, 1, 11), 3, None)]))], []), +('Module', [('AsyncFunctionDef', (1, 0, 2, 21), 'f', ('arguments', [], [], None, [], [], None, []), [('Expr', (2, 1, 2, 21), ('ListComp', (2, 1, 2, 21), ('Name', (2, 2, 2, 3), 'i', ('Load',)), [('comprehension', ('Name', (2, 14, 2, 15), 'b', ('Store',)), ('Name', (2, 19, 2, 20), 'c', ('Load',)), [], 1)]))], [], None, None)], []), +('Module', [('FunctionDef', (4, 0, 4, 13), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (4, 9, 4, 13))], [('Name', (1, 1, 1, 6), 'deco1', ('Load',)), ('Call', (2, 1, 2, 8), ('Name', (2, 1, 2, 6), 'deco2', ('Load',)), [], []), ('Call', (3, 1, 3, 9), ('Name', (3, 1, 3, 6), 'deco3', ('Load',)), [('Constant', (3, 7, 3, 8), 1, None)], [])], None, None)], []), +('Module', [('AsyncFunctionDef', (4, 0, 4, 19), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (4, 15, 4, 19))], [('Name', (1, 1, 1, 6), 'deco1', ('Load',)), ('Call', (2, 1, 2, 8), ('Name', (2, 1, 2, 6), 'deco2', ('Load',)), [], []), ('Call', (3, 1, 3, 9), ('Name', (3, 1, 3, 6), 'deco3', ('Load',)), [('Constant', (3, 7, 3, 8), 1, None)], [])], None, None)], []), +('Module', [('ClassDef', (4, 0, 4, 13), 'C', [], [], [('Pass', (4, 9, 4, 13))], [('Name', (1, 1, 1, 6), 'deco1', ('Load',)), ('Call', (2, 1, 2, 8), ('Name', (2, 1, 2, 6), 'deco2', ('Load',)), [], []), ('Call', (3, 1, 3, 9), ('Name', (3, 1, 3, 6), 'deco3', ('Load',)), [('Constant', (3, 7, 3, 8), 1, None)], [])])], []), +('Module', [('FunctionDef', (2, 0, 2, 13), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (2, 9, 2, 13))], [('Call', (1, 1, 1, 19), ('Name', (1, 1, 1, 5), 'deco', ('Load',)), [('GeneratorExp', (1, 5, 1, 19), ('Name', (1, 6, 1, 7), 'a', ('Load',)), [('comprehension', ('Name', (1, 12, 1, 13), 'a', ('Store',)), ('Name', (1, 17, 1, 18), 'b', ('Load',)), [], 0)])], [])], None, None)], []), +('Module', [('FunctionDef', (2, 0, 2, 13), 'f', ('arguments', [], [], None, [], [], None, []), [('Pass', (2, 9, 2, 13))], [('Attribute', (1, 1, 1, 6), ('Attribute', (1, 1, 1, 4), ('Name', (1, 1, 1, 2), 'a', ('Load',)), 'b', ('Load',)), 'c', ('Load',))], None, None)], []), +('Module', [('Expr', (1, 0, 1, 8), ('NamedExpr', (1, 1, 1, 7), ('Name', (1, 1, 1, 2), 'a', ('Store',)), ('Constant', (1, 6, 1, 7), 1, None)))], []), +('Module', [('FunctionDef', (1, 0, 1, 18), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [], None, [], [], None, []), [('Pass', (1, 14, 1, 18))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 26), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 12, 1, 13), 'c', None, None), ('arg', (1, 15, 1, 16), 'd', None, None), ('arg', (1, 18, 1, 19), 'e', None, None)], None, [], [], None, []), [('Pass', (1, 22, 1, 26))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 29), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 12, 1, 13), 'c', None, None)], None, [('arg', (1, 18, 1, 19), 'd', None, None), ('arg', (1, 21, 1, 22), 'e', None, None)], [None, None], None, []), [('Pass', (1, 25, 1, 29))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 39), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 12, 1, 13), 'c', None, None)], None, [('arg', (1, 18, 1, 19), 'd', None, None), ('arg', (1, 21, 1, 22), 'e', None, None)], [None, None], ('arg', (1, 26, 1, 32), 'kwargs', None, None), []), [('Pass', (1, 35, 1, 39))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 20), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [], None, [], [], None, [('Constant', (1, 8, 1, 9), 1, None)]), [('Pass', (1, 16, 1, 20))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 29), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 14, 1, 15), 'b', None, None), ('arg', (1, 19, 1, 20), 'c', None, None)], None, [], [], None, [('Constant', (1, 8, 1, 9), 1, None), ('Constant', (1, 16, 1, 17), 2, None), ('Constant', (1, 21, 1, 22), 4, None)]), [('Pass', (1, 25, 1, 29))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 32), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 14, 1, 15), 'b', None, None)], None, [('arg', (1, 22, 1, 23), 'c', None, None)], [('Constant', (1, 24, 1, 25), 4, None)], None, [('Constant', (1, 8, 1, 9), 1, None), ('Constant', (1, 16, 1, 17), 2, None)]), [('Pass', (1, 28, 1, 32))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 30), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 14, 1, 15), 'b', None, None)], None, [('arg', (1, 22, 1, 23), 'c', None, None)], [None], None, [('Constant', (1, 8, 1, 9), 1, None), ('Constant', (1, 16, 1, 17), 2, None)]), [('Pass', (1, 26, 1, 30))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 42), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 14, 1, 15), 'b', None, None)], None, [('arg', (1, 22, 1, 23), 'c', None, None)], [('Constant', (1, 24, 1, 25), 4, None)], ('arg', (1, 29, 1, 35), 'kwargs', None, None), [('Constant', (1, 8, 1, 9), 1, None), ('Constant', (1, 16, 1, 17), 2, None)]), [('Pass', (1, 38, 1, 42))], [], None, None)], []), +('Module', [('FunctionDef', (1, 0, 1, 40), 'f', ('arguments', [('arg', (1, 6, 1, 7), 'a', None, None)], [('arg', (1, 14, 1, 15), 'b', None, None)], None, [('arg', (1, 22, 1, 23), 'c', None, None)], [None], ('arg', (1, 27, 1, 33), 'kwargs', None, None), [('Constant', (1, 8, 1, 9), 1, None), ('Constant', (1, 16, 1, 17), 2, None)]), [('Pass', (1, 36, 1, 40))], [], None, None)], []), +] +single_results = [ +('Interactive', [('Expr', (1, 0, 1, 3), ('BinOp', (1, 0, 1, 3), ('Constant', (1, 0, 1, 1), 1, None), ('Add',), ('Constant', (1, 2, 1, 3), 2, None)))]), +] +eval_results = [ +('Expression', ('Constant', (1, 0, 1, 4), None, None)), +('Expression', ('BoolOp', (1, 0, 1, 7), ('And',), [('Name', (1, 0, 1, 1), 'a', ('Load',)), ('Name', (1, 6, 1, 7), 'b', ('Load',))])), +('Expression', ('BinOp', (1, 0, 1, 5), ('Name', (1, 0, 1, 1), 'a', ('Load',)), ('Add',), ('Name', (1, 4, 1, 5), 'b', ('Load',)))), +('Expression', ('UnaryOp', (1, 0, 1, 5), ('Not',), ('Name', (1, 4, 1, 5), 'v', ('Load',)))), +('Expression', ('Lambda', (1, 0, 1, 11), ('arguments', [], [], None, [], [], None, []), ('Constant', (1, 7, 1, 11), None, None))), +('Expression', ('Dict', (1, 0, 1, 7), [('Constant', (1, 2, 1, 3), 1, None)], [('Constant', (1, 4, 1, 5), 2, None)])), +('Expression', ('Dict', (1, 0, 1, 2), [], [])), +('Expression', ('Set', (1, 0, 1, 7), [('Constant', (1, 1, 1, 5), None, None)])), +('Expression', ('Dict', (1, 0, 5, 6), [('Constant', (2, 6, 2, 7), 1, None)], [('Constant', (4, 10, 4, 11), 2, None)])), +('Expression', ('ListComp', (1, 0, 1, 19), ('Name', (1, 1, 1, 2), 'a', ('Load',)), [('comprehension', ('Name', (1, 7, 1, 8), 'b', ('Store',)), ('Name', (1, 12, 1, 13), 'c', ('Load',)), [('Name', (1, 17, 1, 18), 'd', ('Load',))], 0)])), +('Expression', ('GeneratorExp', (1, 0, 1, 19), ('Name', (1, 1, 1, 2), 'a', ('Load',)), [('comprehension', ('Name', (1, 7, 1, 8), 'b', ('Store',)), ('Name', (1, 12, 1, 13), 'c', ('Load',)), [('Name', (1, 17, 1, 18), 'd', ('Load',))], 0)])), +('Expression', ('ListComp', (1, 0, 1, 20), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('Tuple', (1, 11, 1, 14), [('Name', (1, 11, 1, 12), 'a', ('Store',)), ('Name', (1, 13, 1, 14), 'b', ('Store',))], ('Store',)), ('Name', (1, 18, 1, 19), 'c', ('Load',)), [], 0)])), +('Expression', ('ListComp', (1, 0, 1, 22), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('Tuple', (1, 11, 1, 16), [('Name', (1, 12, 1, 13), 'a', ('Store',)), ('Name', (1, 14, 1, 15), 'b', ('Store',))], ('Store',)), ('Name', (1, 20, 1, 21), 'c', ('Load',)), [], 0)])), +('Expression', ('ListComp', (1, 0, 1, 22), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('List', (1, 11, 1, 16), [('Name', (1, 12, 1, 13), 'a', ('Store',)), ('Name', (1, 14, 1, 15), 'b', ('Store',))], ('Store',)), ('Name', (1, 20, 1, 21), 'c', ('Load',)), [], 0)])), +('Expression', ('SetComp', (1, 0, 1, 20), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('Tuple', (1, 11, 1, 14), [('Name', (1, 11, 1, 12), 'a', ('Store',)), ('Name', (1, 13, 1, 14), 'b', ('Store',))], ('Store',)), ('Name', (1, 18, 1, 19), 'c', ('Load',)), [], 0)])), +('Expression', ('SetComp', (1, 0, 1, 22), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('Tuple', (1, 11, 1, 16), [('Name', (1, 12, 1, 13), 'a', ('Store',)), ('Name', (1, 14, 1, 15), 'b', ('Store',))], ('Store',)), ('Name', (1, 20, 1, 21), 'c', ('Load',)), [], 0)])), +('Expression', ('SetComp', (1, 0, 1, 22), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('List', (1, 11, 1, 16), [('Name', (1, 12, 1, 13), 'a', ('Store',)), ('Name', (1, 14, 1, 15), 'b', ('Store',))], ('Store',)), ('Name', (1, 20, 1, 21), 'c', ('Load',)), [], 0)])), +('Expression', ('GeneratorExp', (1, 0, 1, 20), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('Tuple', (1, 11, 1, 14), [('Name', (1, 11, 1, 12), 'a', ('Store',)), ('Name', (1, 13, 1, 14), 'b', ('Store',))], ('Store',)), ('Name', (1, 18, 1, 19), 'c', ('Load',)), [], 0)])), +('Expression', ('GeneratorExp', (1, 0, 1, 22), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('Tuple', (1, 11, 1, 16), [('Name', (1, 12, 1, 13), 'a', ('Store',)), ('Name', (1, 14, 1, 15), 'b', ('Store',))], ('Store',)), ('Name', (1, 20, 1, 21), 'c', ('Load',)), [], 0)])), +('Expression', ('GeneratorExp', (1, 0, 1, 22), ('Tuple', (1, 1, 1, 6), [('Name', (1, 2, 1, 3), 'a', ('Load',)), ('Name', (1, 4, 1, 5), 'b', ('Load',))], ('Load',)), [('comprehension', ('List', (1, 11, 1, 16), [('Name', (1, 12, 1, 13), 'a', ('Store',)), ('Name', (1, 14, 1, 15), 'b', ('Store',))], ('Store',)), ('Name', (1, 20, 1, 21), 'c', ('Load',)), [], 0)])), +('Expression', ('Compare', (1, 0, 1, 9), ('Constant', (1, 0, 1, 1), 1, None), [('Lt',), ('Lt',)], [('Constant', (1, 4, 1, 5), 2, None), ('Constant', (1, 8, 1, 9), 3, None)])), +('Expression', ('Call', (1, 0, 1, 17), ('Name', (1, 0, 1, 1), 'f', ('Load',)), [('Constant', (1, 2, 1, 3), 1, None), ('Constant', (1, 4, 1, 5), 2, None), ('Starred', (1, 10, 1, 12), ('Name', (1, 11, 1, 12), 'd', ('Load',)), ('Load',))], [('keyword', (1, 6, 1, 9), 'c', ('Constant', (1, 8, 1, 9), 3, None)), ('keyword', (1, 13, 1, 16), None, ('Name', (1, 15, 1, 16), 'e', ('Load',)))])), +('Expression', ('Call', (1, 0, 1, 10), ('Name', (1, 0, 1, 1), 'f', ('Load',)), [('Starred', (1, 2, 1, 9), ('List', (1, 3, 1, 9), [('Constant', (1, 4, 1, 5), 0, None), ('Constant', (1, 7, 1, 8), 1, None)], ('Load',)), ('Load',))], [])), +('Expression', ('Call', (1, 0, 1, 15), ('Name', (1, 0, 1, 1), 'f', ('Load',)), [('GeneratorExp', (1, 1, 1, 15), ('Name', (1, 2, 1, 3), 'a', ('Load',)), [('comprehension', ('Name', (1, 8, 1, 9), 'a', ('Store',)), ('Name', (1, 13, 1, 14), 'b', ('Load',)), [], 0)])], [])), +('Expression', ('Constant', (1, 0, 1, 2), 10, None)), +('Expression', ('Constant', (1, 0, 1, 8), 'string', None)), +('Expression', ('Attribute', (1, 0, 1, 3), ('Name', (1, 0, 1, 1), 'a', ('Load',)), 'b', ('Load',))), +('Expression', ('Subscript', (1, 0, 1, 6), ('Name', (1, 0, 1, 1), 'a', ('Load',)), ('Slice', (1, 2, 1, 5), ('Name', (1, 2, 1, 3), 'b', ('Load',)), ('Name', (1, 4, 1, 5), 'c', ('Load',)), None), ('Load',))), +('Expression', ('Name', (1, 0, 1, 1), 'v', ('Load',))), +('Expression', ('List', (1, 0, 1, 7), [('Constant', (1, 1, 1, 2), 1, None), ('Constant', (1, 3, 1, 4), 2, None), ('Constant', (1, 5, 1, 6), 3, None)], ('Load',))), +('Expression', ('List', (1, 0, 1, 2), [], ('Load',))), +('Expression', ('Tuple', (1, 0, 1, 5), [('Constant', (1, 0, 1, 1), 1, None), ('Constant', (1, 2, 1, 3), 2, None), ('Constant', (1, 4, 1, 5), 3, None)], ('Load',))), +('Expression', ('Tuple', (1, 0, 1, 7), [('Constant', (1, 1, 1, 2), 1, None), ('Constant', (1, 3, 1, 4), 2, None), ('Constant', (1, 5, 1, 6), 3, None)], ('Load',))), +('Expression', ('Tuple', (1, 0, 1, 2), [], ('Load',))), +('Expression', ('Call', (1, 0, 1, 17), ('Attribute', (1, 0, 1, 7), ('Attribute', (1, 0, 1, 5), ('Attribute', (1, 0, 1, 3), ('Name', (1, 0, 1, 1), 'a', ('Load',)), 'b', ('Load',)), 'c', ('Load',)), 'd', ('Load',)), [('Subscript', (1, 8, 1, 16), ('Attribute', (1, 8, 1, 11), ('Name', (1, 8, 1, 9), 'a', ('Load',)), 'b', ('Load',)), ('Slice', (1, 12, 1, 15), ('Constant', (1, 12, 1, 13), 1, None), ('Constant', (1, 14, 1, 15), 2, None), None), ('Load',))], [])), +] +main() diff --git a/components/utokenize/test/python/test_tokenize.py b/components/utokenize/test/python/test_tokenize.py new file mode 100644 index 0000000..63c2501 --- /dev/null +++ b/components/utokenize/test/python/test_tokenize.py @@ -0,0 +1,2651 @@ +from test import support +from test.support import os_helper +from tokenize import (tokenize, _tokenize, untokenize, NUMBER, NAME, OP, + STRING, ENDMARKER, ENCODING, tok_name, detect_encoding, + open as tokenize_open, Untokenizer, generate_tokens, + NEWLINE, _generate_tokens_from_c_tokenizer, DEDENT) +from io import BytesIO, StringIO +import unittest +from textwrap import dedent +from unittest import TestCase, mock +from test.test_grammar import (VALID_UNDERSCORE_LITERALS, + INVALID_UNDERSCORE_LITERALS) +from test.support import os_helper +from test.support.script_helper import run_test_script, make_script +import os +import token + +# Converts a source string into a list of textual representation +# of the tokens such as: +# ` NAME 'if' (1, 0) (1, 2)` +# to make writing tests easier. +def stringify_tokens_from_source(token_generator, source_string): + result = [] + num_lines = len(source_string.splitlines()) + missing_trailing_nl = source_string[-1] not in '\r\n' + + for type, token, start, end, line in token_generator: + if type == ENDMARKER: + break + # Ignore the new line on the last line if the input lacks one + if missing_trailing_nl and type == NEWLINE and end[0] == num_lines: + continue + type = tok_name[type] + result.append(f" {type:10} {token!r:13} {start} {end}") + + return result + +class TokenizeTest(TestCase): + # Tests for the tokenize module. + + # The tests can be really simple. Given a small fragment of source + # code, print out a table with tokens. The ENDMARKER, ENCODING and + # final NEWLINE are omitted for brevity. + + def check_tokenize(self, s, expected): + # Format the tokens in s in a table format. + # The ENDMARKER and final NEWLINE are omitted. + f = BytesIO(s.encode('utf-8')) + result = stringify_tokens_from_source(tokenize(f.readline), s) + self.assertEqual(result, + [" ENCODING 'utf-8' (0, 0) (0, 0)"] + + expected.rstrip().splitlines()) + + def test_implicit_newline(self): + # Make sure that the tokenizer puts in an implicit NEWLINE + # when the input lacks a trailing new line. + f = BytesIO("x".encode('utf-8')) + tokens = list(tokenize(f.readline)) + self.assertEqual(tokens[-2].type, NEWLINE) + self.assertEqual(tokens[-1].type, ENDMARKER) + + def test_basic(self): + self.check_tokenize("1 + 1", """\ + NUMBER '1' (1, 0) (1, 1) + OP '+' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + """) + self.check_tokenize("if False:\n" + " # NL\n" + " \n" + " True = False # NEWLINE\n", """\ + NAME 'if' (1, 0) (1, 2) + NAME 'False' (1, 3) (1, 8) + OP ':' (1, 8) (1, 9) + NEWLINE '\\n' (1, 9) (1, 10) + COMMENT '# NL' (2, 4) (2, 8) + NL '\\n' (2, 8) (2, 9) + NL '\\n' (3, 4) (3, 5) + INDENT ' ' (4, 0) (4, 4) + NAME 'True' (4, 4) (4, 8) + OP '=' (4, 9) (4, 10) + NAME 'False' (4, 11) (4, 16) + COMMENT '# NEWLINE' (4, 17) (4, 26) + NEWLINE '\\n' (4, 26) (4, 27) + DEDENT '' (5, 0) (5, 0) + """) + indent_error_file = b"""\ +def k(x): + x += 2 + x += 5 +""" + readline = BytesIO(indent_error_file).readline + with self.assertRaisesRegex(IndentationError, + "unindent does not match any " + "outer indentation level"): + for tok in tokenize(readline): + pass + + def test_int(self): + # Ordinary integers and binary operators + self.check_tokenize("0xff <= 255", """\ + NUMBER '0xff' (1, 0) (1, 4) + OP '<=' (1, 5) (1, 7) + NUMBER '255' (1, 8) (1, 11) + """) + self.check_tokenize("0b10 <= 255", """\ + NUMBER '0b10' (1, 0) (1, 4) + OP '<=' (1, 5) (1, 7) + NUMBER '255' (1, 8) (1, 11) + """) + self.check_tokenize("0o123 <= 0O123", """\ + NUMBER '0o123' (1, 0) (1, 5) + OP '<=' (1, 6) (1, 8) + NUMBER '0O123' (1, 9) (1, 14) + """) + self.check_tokenize("1234567 > ~0x15", """\ + NUMBER '1234567' (1, 0) (1, 7) + OP '>' (1, 8) (1, 9) + OP '~' (1, 10) (1, 11) + NUMBER '0x15' (1, 11) (1, 15) + """) + self.check_tokenize("2134568 != 1231515", """\ + NUMBER '2134568' (1, 0) (1, 7) + OP '!=' (1, 8) (1, 10) + NUMBER '1231515' (1, 11) (1, 18) + """) + self.check_tokenize("(-124561-1) & 200000000", """\ + OP '(' (1, 0) (1, 1) + OP '-' (1, 1) (1, 2) + NUMBER '124561' (1, 2) (1, 8) + OP '-' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + OP ')' (1, 10) (1, 11) + OP '&' (1, 12) (1, 13) + NUMBER '200000000' (1, 14) (1, 23) + """) + self.check_tokenize("0xdeadbeef != -1", """\ + NUMBER '0xdeadbeef' (1, 0) (1, 10) + OP '!=' (1, 11) (1, 13) + OP '-' (1, 14) (1, 15) + NUMBER '1' (1, 15) (1, 16) + """) + self.check_tokenize("0xdeadc0de & 12345", """\ + NUMBER '0xdeadc0de' (1, 0) (1, 10) + OP '&' (1, 11) (1, 12) + NUMBER '12345' (1, 13) (1, 18) + """) + self.check_tokenize("0xFF & 0x15 | 1234", """\ + NUMBER '0xFF' (1, 0) (1, 4) + OP '&' (1, 5) (1, 6) + NUMBER '0x15' (1, 7) (1, 11) + OP '|' (1, 12) (1, 13) + NUMBER '1234' (1, 14) (1, 18) + """) + + def test_long(self): + # Long integers + self.check_tokenize("x = 0", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '0' (1, 4) (1, 5) + """) + self.check_tokenize("x = 0xfffffffffff", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '0xfffffffffff' (1, 4) (1, 17) + """) + self.check_tokenize("x = 123141242151251616110", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '123141242151251616110' (1, 4) (1, 25) + """) + self.check_tokenize("x = -15921590215012591", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + OP '-' (1, 4) (1, 5) + NUMBER '15921590215012591' (1, 5) (1, 22) + """) + + def test_float(self): + # Floating point numbers + self.check_tokenize("x = 3.14159", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '3.14159' (1, 4) (1, 11) + """) + self.check_tokenize("x = 314159.", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '314159.' (1, 4) (1, 11) + """) + self.check_tokenize("x = .314159", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '.314159' (1, 4) (1, 11) + """) + self.check_tokenize("x = 3e14159", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '3e14159' (1, 4) (1, 11) + """) + self.check_tokenize("x = 3E123", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '3E123' (1, 4) (1, 9) + """) + self.check_tokenize("x+y = 3e-1230", """\ + NAME 'x' (1, 0) (1, 1) + OP '+' (1, 1) (1, 2) + NAME 'y' (1, 2) (1, 3) + OP '=' (1, 4) (1, 5) + NUMBER '3e-1230' (1, 6) (1, 13) + """) + self.check_tokenize("x = 3.14e159", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '3.14e159' (1, 4) (1, 12) + """) + + def test_underscore_literals(self): + def number_token(s): + f = BytesIO(s.encode('utf-8')) + for toktype, token, start, end, line in tokenize(f.readline): + if toktype == NUMBER: + return token + return 'invalid token' + for lit in VALID_UNDERSCORE_LITERALS: + if '(' in lit: + # this won't work with compound complex inputs + continue + self.assertEqual(number_token(lit), lit) + for lit in INVALID_UNDERSCORE_LITERALS: + self.assertNotEqual(number_token(lit), lit) + + def test_string(self): + # String literals + self.check_tokenize("x = ''; y = \"\"", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING "''" (1, 4) (1, 6) + OP ';' (1, 6) (1, 7) + NAME 'y' (1, 8) (1, 9) + OP '=' (1, 10) (1, 11) + STRING '""' (1, 12) (1, 14) + """) + self.check_tokenize("x = '\"'; y = \"'\"", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING '\\'"\\'' (1, 4) (1, 7) + OP ';' (1, 7) (1, 8) + NAME 'y' (1, 9) (1, 10) + OP '=' (1, 11) (1, 12) + STRING '"\\'"' (1, 13) (1, 16) + """) + self.check_tokenize("x = \"doesn't \"shrink\", does it\"", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING '"doesn\\'t "' (1, 4) (1, 14) + NAME 'shrink' (1, 14) (1, 20) + STRING '", does it"' (1, 20) (1, 31) + """) + self.check_tokenize("x = 'abc' + 'ABC'", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING "'abc'" (1, 4) (1, 9) + OP '+' (1, 10) (1, 11) + STRING "'ABC'" (1, 12) (1, 17) + """) + self.check_tokenize('y = "ABC" + "ABC"', """\ + NAME 'y' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING '"ABC"' (1, 4) (1, 9) + OP '+' (1, 10) (1, 11) + STRING '"ABC"' (1, 12) (1, 17) + """) + self.check_tokenize("x = r'abc' + r'ABC' + R'ABC' + R'ABC'", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING "r'abc'" (1, 4) (1, 10) + OP '+' (1, 11) (1, 12) + STRING "r'ABC'" (1, 13) (1, 19) + OP '+' (1, 20) (1, 21) + STRING "R'ABC'" (1, 22) (1, 28) + OP '+' (1, 29) (1, 30) + STRING "R'ABC'" (1, 31) (1, 37) + """) + self.check_tokenize('y = r"abc" + r"ABC" + R"ABC" + R"ABC"', """\ + NAME 'y' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING 'r"abc"' (1, 4) (1, 10) + OP '+' (1, 11) (1, 12) + STRING 'r"ABC"' (1, 13) (1, 19) + OP '+' (1, 20) (1, 21) + STRING 'R"ABC"' (1, 22) (1, 28) + OP '+' (1, 29) (1, 30) + STRING 'R"ABC"' (1, 31) (1, 37) + """) + + self.check_tokenize("u'abc' + U'abc'", """\ + STRING "u'abc'" (1, 0) (1, 6) + OP '+' (1, 7) (1, 8) + STRING "U'abc'" (1, 9) (1, 15) + """) + self.check_tokenize('u"abc" + U"abc"', """\ + STRING 'u"abc"' (1, 0) (1, 6) + OP '+' (1, 7) (1, 8) + STRING 'U"abc"' (1, 9) (1, 15) + """) + + self.check_tokenize("b'abc' + B'abc'", """\ + STRING "b'abc'" (1, 0) (1, 6) + OP '+' (1, 7) (1, 8) + STRING "B'abc'" (1, 9) (1, 15) + """) + self.check_tokenize('b"abc" + B"abc"', """\ + STRING 'b"abc"' (1, 0) (1, 6) + OP '+' (1, 7) (1, 8) + STRING 'B"abc"' (1, 9) (1, 15) + """) + self.check_tokenize("br'abc' + bR'abc' + Br'abc' + BR'abc'", """\ + STRING "br'abc'" (1, 0) (1, 7) + OP '+' (1, 8) (1, 9) + STRING "bR'abc'" (1, 10) (1, 17) + OP '+' (1, 18) (1, 19) + STRING "Br'abc'" (1, 20) (1, 27) + OP '+' (1, 28) (1, 29) + STRING "BR'abc'" (1, 30) (1, 37) + """) + self.check_tokenize('br"abc" + bR"abc" + Br"abc" + BR"abc"', """\ + STRING 'br"abc"' (1, 0) (1, 7) + OP '+' (1, 8) (1, 9) + STRING 'bR"abc"' (1, 10) (1, 17) + OP '+' (1, 18) (1, 19) + STRING 'Br"abc"' (1, 20) (1, 27) + OP '+' (1, 28) (1, 29) + STRING 'BR"abc"' (1, 30) (1, 37) + """) + self.check_tokenize("rb'abc' + rB'abc' + Rb'abc' + RB'abc'", """\ + STRING "rb'abc'" (1, 0) (1, 7) + OP '+' (1, 8) (1, 9) + STRING "rB'abc'" (1, 10) (1, 17) + OP '+' (1, 18) (1, 19) + STRING "Rb'abc'" (1, 20) (1, 27) + OP '+' (1, 28) (1, 29) + STRING "RB'abc'" (1, 30) (1, 37) + """) + self.check_tokenize('rb"abc" + rB"abc" + Rb"abc" + RB"abc"', """\ + STRING 'rb"abc"' (1, 0) (1, 7) + OP '+' (1, 8) (1, 9) + STRING 'rB"abc"' (1, 10) (1, 17) + OP '+' (1, 18) (1, 19) + STRING 'Rb"abc"' (1, 20) (1, 27) + OP '+' (1, 28) (1, 29) + STRING 'RB"abc"' (1, 30) (1, 37) + """) + # Check 0, 1, and 2 character string prefixes. + self.check_tokenize(r'"a\ +de\ +fg"', """\ + STRING '"a\\\\\\nde\\\\\\nfg"\' (1, 0) (3, 3) + """) + self.check_tokenize(r'u"a\ +de"', """\ + STRING 'u"a\\\\\\nde"\' (1, 0) (2, 3) + """) + self.check_tokenize(r'rb"a\ +d"', """\ + STRING 'rb"a\\\\\\nd"\' (1, 0) (2, 2) + """) + self.check_tokenize(r'"""a\ +b"""', """\ + STRING '\"\""a\\\\\\nb\"\""' (1, 0) (2, 4) + """) + self.check_tokenize(r'u"""a\ +b"""', """\ + STRING 'u\"\""a\\\\\\nb\"\""' (1, 0) (2, 4) + """) + self.check_tokenize(r'rb"""a\ +b\ +c"""', """\ + STRING 'rb"\""a\\\\\\nb\\\\\\nc"\""' (1, 0) (3, 4) + """) + self.check_tokenize('f"abc"', """\ + STRING 'f"abc"' (1, 0) (1, 6) + """) + self.check_tokenize('fR"a{b}c"', """\ + STRING 'fR"a{b}c"' (1, 0) (1, 9) + """) + self.check_tokenize('f"""abc"""', """\ + STRING 'f\"\"\"abc\"\"\"' (1, 0) (1, 10) + """) + self.check_tokenize(r'f"abc\ +def"', """\ + STRING 'f"abc\\\\\\ndef"' (1, 0) (2, 4) + """) + self.check_tokenize(r'Rf"abc\ +def"', """\ + STRING 'Rf"abc\\\\\\ndef"' (1, 0) (2, 4) + """) + + def test_function(self): + self.check_tokenize("def d22(a, b, c=2, d=2, *k): pass", """\ + NAME 'def' (1, 0) (1, 3) + NAME 'd22' (1, 4) (1, 7) + OP '(' (1, 7) (1, 8) + NAME 'a' (1, 8) (1, 9) + OP ',' (1, 9) (1, 10) + NAME 'b' (1, 11) (1, 12) + OP ',' (1, 12) (1, 13) + NAME 'c' (1, 14) (1, 15) + OP '=' (1, 15) (1, 16) + NUMBER '2' (1, 16) (1, 17) + OP ',' (1, 17) (1, 18) + NAME 'd' (1, 19) (1, 20) + OP '=' (1, 20) (1, 21) + NUMBER '2' (1, 21) (1, 22) + OP ',' (1, 22) (1, 23) + OP '*' (1, 24) (1, 25) + NAME 'k' (1, 25) (1, 26) + OP ')' (1, 26) (1, 27) + OP ':' (1, 27) (1, 28) + NAME 'pass' (1, 29) (1, 33) + """) + self.check_tokenize("def d01v_(a=1, *k, **w): pass", """\ + NAME 'def' (1, 0) (1, 3) + NAME 'd01v_' (1, 4) (1, 9) + OP '(' (1, 9) (1, 10) + NAME 'a' (1, 10) (1, 11) + OP '=' (1, 11) (1, 12) + NUMBER '1' (1, 12) (1, 13) + OP ',' (1, 13) (1, 14) + OP '*' (1, 15) (1, 16) + NAME 'k' (1, 16) (1, 17) + OP ',' (1, 17) (1, 18) + OP '**' (1, 19) (1, 21) + NAME 'w' (1, 21) (1, 22) + OP ')' (1, 22) (1, 23) + OP ':' (1, 23) (1, 24) + NAME 'pass' (1, 25) (1, 29) + """) + self.check_tokenize("def d23(a: str, b: int=3) -> int: pass", """\ + NAME 'def' (1, 0) (1, 3) + NAME 'd23' (1, 4) (1, 7) + OP '(' (1, 7) (1, 8) + NAME 'a' (1, 8) (1, 9) + OP ':' (1, 9) (1, 10) + NAME 'str' (1, 11) (1, 14) + OP ',' (1, 14) (1, 15) + NAME 'b' (1, 16) (1, 17) + OP ':' (1, 17) (1, 18) + NAME 'int' (1, 19) (1, 22) + OP '=' (1, 22) (1, 23) + NUMBER '3' (1, 23) (1, 24) + OP ')' (1, 24) (1, 25) + OP '->' (1, 26) (1, 28) + NAME 'int' (1, 29) (1, 32) + OP ':' (1, 32) (1, 33) + NAME 'pass' (1, 34) (1, 38) + """) + + def test_comparison(self): + # Comparison + self.check_tokenize("if 1 < 1 > 1 == 1 >= 5 <= 0x15 <= 0x12 != " + "1 and 5 in 1 not in 1 is 1 or 5 is not 1: pass", """\ + NAME 'if' (1, 0) (1, 2) + NUMBER '1' (1, 3) (1, 4) + OP '<' (1, 5) (1, 6) + NUMBER '1' (1, 7) (1, 8) + OP '>' (1, 9) (1, 10) + NUMBER '1' (1, 11) (1, 12) + OP '==' (1, 13) (1, 15) + NUMBER '1' (1, 16) (1, 17) + OP '>=' (1, 18) (1, 20) + NUMBER '5' (1, 21) (1, 22) + OP '<=' (1, 23) (1, 25) + NUMBER '0x15' (1, 26) (1, 30) + OP '<=' (1, 31) (1, 33) + NUMBER '0x12' (1, 34) (1, 38) + OP '!=' (1, 39) (1, 41) + NUMBER '1' (1, 42) (1, 43) + NAME 'and' (1, 44) (1, 47) + NUMBER '5' (1, 48) (1, 49) + NAME 'in' (1, 50) (1, 52) + NUMBER '1' (1, 53) (1, 54) + NAME 'not' (1, 55) (1, 58) + NAME 'in' (1, 59) (1, 61) + NUMBER '1' (1, 62) (1, 63) + NAME 'is' (1, 64) (1, 66) + NUMBER '1' (1, 67) (1, 68) + NAME 'or' (1, 69) (1, 71) + NUMBER '5' (1, 72) (1, 73) + NAME 'is' (1, 74) (1, 76) + NAME 'not' (1, 77) (1, 80) + NUMBER '1' (1, 81) (1, 82) + OP ':' (1, 82) (1, 83) + NAME 'pass' (1, 84) (1, 88) + """) + + def test_shift(self): + # Shift + self.check_tokenize("x = 1 << 1 >> 5", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + OP '<<' (1, 6) (1, 8) + NUMBER '1' (1, 9) (1, 10) + OP '>>' (1, 11) (1, 13) + NUMBER '5' (1, 14) (1, 15) + """) + + def test_additive(self): + # Additive + self.check_tokenize("x = 1 - y + 15 - 1 + 0x124 + z + a[5]", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + OP '-' (1, 6) (1, 7) + NAME 'y' (1, 8) (1, 9) + OP '+' (1, 10) (1, 11) + NUMBER '15' (1, 12) (1, 14) + OP '-' (1, 15) (1, 16) + NUMBER '1' (1, 17) (1, 18) + OP '+' (1, 19) (1, 20) + NUMBER '0x124' (1, 21) (1, 26) + OP '+' (1, 27) (1, 28) + NAME 'z' (1, 29) (1, 30) + OP '+' (1, 31) (1, 32) + NAME 'a' (1, 33) (1, 34) + OP '[' (1, 34) (1, 35) + NUMBER '5' (1, 35) (1, 36) + OP ']' (1, 36) (1, 37) + """) + + def test_multiplicative(self): + # Multiplicative + self.check_tokenize("x = 1//1*1/5*12%0x12@42", """\ + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + OP '//' (1, 5) (1, 7) + NUMBER '1' (1, 7) (1, 8) + OP '*' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + OP '/' (1, 10) (1, 11) + NUMBER '5' (1, 11) (1, 12) + OP '*' (1, 12) (1, 13) + NUMBER '12' (1, 13) (1, 15) + OP '%' (1, 15) (1, 16) + NUMBER '0x12' (1, 16) (1, 20) + OP '@' (1, 20) (1, 21) + NUMBER '42' (1, 21) (1, 23) + """) + + def test_unary(self): + # Unary + self.check_tokenize("~1 ^ 1 & 1 |1 ^ -1", """\ + OP '~' (1, 0) (1, 1) + NUMBER '1' (1, 1) (1, 2) + OP '^' (1, 3) (1, 4) + NUMBER '1' (1, 5) (1, 6) + OP '&' (1, 7) (1, 8) + NUMBER '1' (1, 9) (1, 10) + OP '|' (1, 11) (1, 12) + NUMBER '1' (1, 12) (1, 13) + OP '^' (1, 14) (1, 15) + OP '-' (1, 16) (1, 17) + NUMBER '1' (1, 17) (1, 18) + """) + self.check_tokenize("-1*1/1+1*1//1 - ---1**1", """\ + OP '-' (1, 0) (1, 1) + NUMBER '1' (1, 1) (1, 2) + OP '*' (1, 2) (1, 3) + NUMBER '1' (1, 3) (1, 4) + OP '/' (1, 4) (1, 5) + NUMBER '1' (1, 5) (1, 6) + OP '+' (1, 6) (1, 7) + NUMBER '1' (1, 7) (1, 8) + OP '*' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + OP '//' (1, 10) (1, 12) + NUMBER '1' (1, 12) (1, 13) + OP '-' (1, 14) (1, 15) + OP '-' (1, 16) (1, 17) + OP '-' (1, 17) (1, 18) + OP '-' (1, 18) (1, 19) + NUMBER '1' (1, 19) (1, 20) + OP '**' (1, 20) (1, 22) + NUMBER '1' (1, 22) (1, 23) + """) + + def test_selector(self): + # Selector + self.check_tokenize("import sys, time\nx = sys.modules['time'].time()", """\ + NAME 'import' (1, 0) (1, 6) + NAME 'sys' (1, 7) (1, 10) + OP ',' (1, 10) (1, 11) + NAME 'time' (1, 12) (1, 16) + NEWLINE '\\n' (1, 16) (1, 17) + NAME 'x' (2, 0) (2, 1) + OP '=' (2, 2) (2, 3) + NAME 'sys' (2, 4) (2, 7) + OP '.' (2, 7) (2, 8) + NAME 'modules' (2, 8) (2, 15) + OP '[' (2, 15) (2, 16) + STRING "'time'" (2, 16) (2, 22) + OP ']' (2, 22) (2, 23) + OP '.' (2, 23) (2, 24) + NAME 'time' (2, 24) (2, 28) + OP '(' (2, 28) (2, 29) + OP ')' (2, 29) (2, 30) + """) + + def test_method(self): + # Methods + self.check_tokenize("@staticmethod\ndef foo(x,y): pass", """\ + OP '@' (1, 0) (1, 1) + NAME 'staticmethod' (1, 1) (1, 13) + NEWLINE '\\n' (1, 13) (1, 14) + NAME 'def' (2, 0) (2, 3) + NAME 'foo' (2, 4) (2, 7) + OP '(' (2, 7) (2, 8) + NAME 'x' (2, 8) (2, 9) + OP ',' (2, 9) (2, 10) + NAME 'y' (2, 10) (2, 11) + OP ')' (2, 11) (2, 12) + OP ':' (2, 12) (2, 13) + NAME 'pass' (2, 14) (2, 18) + """) + + def test_tabs(self): + # Evil tabs + self.check_tokenize("def f():\n" + "\tif x\n" + " \tpass", """\ + NAME 'def' (1, 0) (1, 3) + NAME 'f' (1, 4) (1, 5) + OP '(' (1, 5) (1, 6) + OP ')' (1, 6) (1, 7) + OP ':' (1, 7) (1, 8) + NEWLINE '\\n' (1, 8) (1, 9) + INDENT '\\t' (2, 0) (2, 1) + NAME 'if' (2, 1) (2, 3) + NAME 'x' (2, 4) (2, 5) + NEWLINE '\\n' (2, 5) (2, 6) + INDENT ' \\t' (3, 0) (3, 9) + NAME 'pass' (3, 9) (3, 13) + DEDENT '' (4, 0) (4, 0) + DEDENT '' (4, 0) (4, 0) + """) + + def test_non_ascii_identifiers(self): + # Non-ascii identifiers + self.check_tokenize("Örter = 'places'\ngrün = 'green'", """\ + NAME 'Örter' (1, 0) (1, 5) + OP '=' (1, 6) (1, 7) + STRING "'places'" (1, 8) (1, 16) + NEWLINE '\\n' (1, 16) (1, 17) + NAME 'grün' (2, 0) (2, 4) + OP '=' (2, 5) (2, 6) + STRING "'green'" (2, 7) (2, 14) + """) + + def test_unicode(self): + # Legacy unicode literals: + self.check_tokenize("Örter = u'places'\ngrün = U'green'", """\ + NAME 'Örter' (1, 0) (1, 5) + OP '=' (1, 6) (1, 7) + STRING "u'places'" (1, 8) (1, 17) + NEWLINE '\\n' (1, 17) (1, 18) + NAME 'grün' (2, 0) (2, 4) + OP '=' (2, 5) (2, 6) + STRING "U'green'" (2, 7) (2, 15) + """) + + def test_async(self): + # Async/await extension: + self.check_tokenize("async = 1", """\ + NAME 'async' (1, 0) (1, 5) + OP '=' (1, 6) (1, 7) + NUMBER '1' (1, 8) (1, 9) + """) + + self.check_tokenize("a = (async = 1)", """\ + NAME 'a' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + OP '(' (1, 4) (1, 5) + NAME 'async' (1, 5) (1, 10) + OP '=' (1, 11) (1, 12) + NUMBER '1' (1, 13) (1, 14) + OP ')' (1, 14) (1, 15) + """) + + self.check_tokenize("async()", """\ + NAME 'async' (1, 0) (1, 5) + OP '(' (1, 5) (1, 6) + OP ')' (1, 6) (1, 7) + """) + + self.check_tokenize("class async(Bar):pass", """\ + NAME 'class' (1, 0) (1, 5) + NAME 'async' (1, 6) (1, 11) + OP '(' (1, 11) (1, 12) + NAME 'Bar' (1, 12) (1, 15) + OP ')' (1, 15) (1, 16) + OP ':' (1, 16) (1, 17) + NAME 'pass' (1, 17) (1, 21) + """) + + self.check_tokenize("class async:pass", """\ + NAME 'class' (1, 0) (1, 5) + NAME 'async' (1, 6) (1, 11) + OP ':' (1, 11) (1, 12) + NAME 'pass' (1, 12) (1, 16) + """) + + self.check_tokenize("await = 1", """\ + NAME 'await' (1, 0) (1, 5) + OP '=' (1, 6) (1, 7) + NUMBER '1' (1, 8) (1, 9) + """) + + self.check_tokenize("foo.async", """\ + NAME 'foo' (1, 0) (1, 3) + OP '.' (1, 3) (1, 4) + NAME 'async' (1, 4) (1, 9) + """) + + self.check_tokenize("async for a in b: pass", """\ + NAME 'async' (1, 0) (1, 5) + NAME 'for' (1, 6) (1, 9) + NAME 'a' (1, 10) (1, 11) + NAME 'in' (1, 12) (1, 14) + NAME 'b' (1, 15) (1, 16) + OP ':' (1, 16) (1, 17) + NAME 'pass' (1, 18) (1, 22) + """) + + self.check_tokenize("async with a as b: pass", """\ + NAME 'async' (1, 0) (1, 5) + NAME 'with' (1, 6) (1, 10) + NAME 'a' (1, 11) (1, 12) + NAME 'as' (1, 13) (1, 15) + NAME 'b' (1, 16) (1, 17) + OP ':' (1, 17) (1, 18) + NAME 'pass' (1, 19) (1, 23) + """) + + self.check_tokenize("async.foo", """\ + NAME 'async' (1, 0) (1, 5) + OP '.' (1, 5) (1, 6) + NAME 'foo' (1, 6) (1, 9) + """) + + self.check_tokenize("async", """\ + NAME 'async' (1, 0) (1, 5) + """) + + self.check_tokenize("async\n#comment\nawait", """\ + NAME 'async' (1, 0) (1, 5) + NEWLINE '\\n' (1, 5) (1, 6) + COMMENT '#comment' (2, 0) (2, 8) + NL '\\n' (2, 8) (2, 9) + NAME 'await' (3, 0) (3, 5) + """) + + self.check_tokenize("async\n...\nawait", """\ + NAME 'async' (1, 0) (1, 5) + NEWLINE '\\n' (1, 5) (1, 6) + OP '...' (2, 0) (2, 3) + NEWLINE '\\n' (2, 3) (2, 4) + NAME 'await' (3, 0) (3, 5) + """) + + self.check_tokenize("async\nawait", """\ + NAME 'async' (1, 0) (1, 5) + NEWLINE '\\n' (1, 5) (1, 6) + NAME 'await' (2, 0) (2, 5) + """) + + self.check_tokenize("foo.async + 1", """\ + NAME 'foo' (1, 0) (1, 3) + OP '.' (1, 3) (1, 4) + NAME 'async' (1, 4) (1, 9) + OP '+' (1, 10) (1, 11) + NUMBER '1' (1, 12) (1, 13) + """) + + self.check_tokenize("async def foo(): pass", """\ + NAME 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + OP '(' (1, 13) (1, 14) + OP ')' (1, 14) (1, 15) + OP ':' (1, 15) (1, 16) + NAME 'pass' (1, 17) (1, 21) + """) + + self.check_tokenize('''\ +async def foo(): + def foo(await): + await = 1 + if 1: + await +async += 1 +''', """\ + NAME 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + OP '(' (1, 13) (1, 14) + OP ')' (1, 14) (1, 15) + OP ':' (1, 15) (1, 16) + NEWLINE '\\n' (1, 16) (1, 17) + INDENT ' ' (2, 0) (2, 2) + NAME 'def' (2, 2) (2, 5) + NAME 'foo' (2, 6) (2, 9) + OP '(' (2, 9) (2, 10) + NAME 'await' (2, 10) (2, 15) + OP ')' (2, 15) (2, 16) + OP ':' (2, 16) (2, 17) + NEWLINE '\\n' (2, 17) (2, 18) + INDENT ' ' (3, 0) (3, 4) + NAME 'await' (3, 4) (3, 9) + OP '=' (3, 10) (3, 11) + NUMBER '1' (3, 12) (3, 13) + NEWLINE '\\n' (3, 13) (3, 14) + DEDENT '' (4, 2) (4, 2) + NAME 'if' (4, 2) (4, 4) + NUMBER '1' (4, 5) (4, 6) + OP ':' (4, 6) (4, 7) + NEWLINE '\\n' (4, 7) (4, 8) + INDENT ' ' (5, 0) (5, 4) + NAME 'await' (5, 4) (5, 9) + NEWLINE '\\n' (5, 9) (5, 10) + DEDENT '' (6, 0) (6, 0) + DEDENT '' (6, 0) (6, 0) + NAME 'async' (6, 0) (6, 5) + OP '+=' (6, 6) (6, 8) + NUMBER '1' (6, 9) (6, 10) + NEWLINE '\\n' (6, 10) (6, 11) + """) + + self.check_tokenize('''\ +async def foo(): + async for i in 1: pass''', """\ + NAME 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + OP '(' (1, 13) (1, 14) + OP ')' (1, 14) (1, 15) + OP ':' (1, 15) (1, 16) + NEWLINE '\\n' (1, 16) (1, 17) + INDENT ' ' (2, 0) (2, 2) + NAME 'async' (2, 2) (2, 7) + NAME 'for' (2, 8) (2, 11) + NAME 'i' (2, 12) (2, 13) + NAME 'in' (2, 14) (2, 16) + NUMBER '1' (2, 17) (2, 18) + OP ':' (2, 18) (2, 19) + NAME 'pass' (2, 20) (2, 24) + DEDENT '' (3, 0) (3, 0) + """) + + self.check_tokenize('''async def foo(async): await''', """\ + NAME 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + OP '(' (1, 13) (1, 14) + NAME 'async' (1, 14) (1, 19) + OP ')' (1, 19) (1, 20) + OP ':' (1, 20) (1, 21) + NAME 'await' (1, 22) (1, 27) + """) + + self.check_tokenize('''\ +def f(): + + def baz(): pass + async def bar(): pass + + await = 2''', """\ + NAME 'def' (1, 0) (1, 3) + NAME 'f' (1, 4) (1, 5) + OP '(' (1, 5) (1, 6) + OP ')' (1, 6) (1, 7) + OP ':' (1, 7) (1, 8) + NEWLINE '\\n' (1, 8) (1, 9) + NL '\\n' (2, 0) (2, 1) + INDENT ' ' (3, 0) (3, 2) + NAME 'def' (3, 2) (3, 5) + NAME 'baz' (3, 6) (3, 9) + OP '(' (3, 9) (3, 10) + OP ')' (3, 10) (3, 11) + OP ':' (3, 11) (3, 12) + NAME 'pass' (3, 13) (3, 17) + NEWLINE '\\n' (3, 17) (3, 18) + NAME 'async' (4, 2) (4, 7) + NAME 'def' (4, 8) (4, 11) + NAME 'bar' (4, 12) (4, 15) + OP '(' (4, 15) (4, 16) + OP ')' (4, 16) (4, 17) + OP ':' (4, 17) (4, 18) + NAME 'pass' (4, 19) (4, 23) + NEWLINE '\\n' (4, 23) (4, 24) + NL '\\n' (5, 0) (5, 1) + NAME 'await' (6, 2) (6, 7) + OP '=' (6, 8) (6, 9) + NUMBER '2' (6, 10) (6, 11) + DEDENT '' (7, 0) (7, 0) + """) + + self.check_tokenize('''\ +async def f(): + + def baz(): pass + async def bar(): pass + + await = 2''', """\ + NAME 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'f' (1, 10) (1, 11) + OP '(' (1, 11) (1, 12) + OP ')' (1, 12) (1, 13) + OP ':' (1, 13) (1, 14) + NEWLINE '\\n' (1, 14) (1, 15) + NL '\\n' (2, 0) (2, 1) + INDENT ' ' (3, 0) (3, 2) + NAME 'def' (3, 2) (3, 5) + NAME 'baz' (3, 6) (3, 9) + OP '(' (3, 9) (3, 10) + OP ')' (3, 10) (3, 11) + OP ':' (3, 11) (3, 12) + NAME 'pass' (3, 13) (3, 17) + NEWLINE '\\n' (3, 17) (3, 18) + NAME 'async' (4, 2) (4, 7) + NAME 'def' (4, 8) (4, 11) + NAME 'bar' (4, 12) (4, 15) + OP '(' (4, 15) (4, 16) + OP ')' (4, 16) (4, 17) + OP ':' (4, 17) (4, 18) + NAME 'pass' (4, 19) (4, 23) + NEWLINE '\\n' (4, 23) (4, 24) + NL '\\n' (5, 0) (5, 1) + NAME 'await' (6, 2) (6, 7) + OP '=' (6, 8) (6, 9) + NUMBER '2' (6, 10) (6, 11) + DEDENT '' (7, 0) (7, 0) + """) + +class GenerateTokensTest(TokenizeTest): + def check_tokenize(self, s, expected): + # Format the tokens in s in a table format. + # The ENDMARKER and final NEWLINE are omitted. + f = StringIO(s) + result = stringify_tokens_from_source(generate_tokens(f.readline), s) + self.assertEqual(result, expected.rstrip().splitlines()) + + +def decistmt(s): + result = [] + g = tokenize(BytesIO(s.encode('utf-8')).readline) # tokenize the string + for toknum, tokval, _, _, _ in g: + if toknum == NUMBER and '.' in tokval: # replace NUMBER tokens + result.extend([ + (NAME, 'Decimal'), + (OP, '('), + (STRING, repr(tokval)), + (OP, ')') + ]) + else: + result.append((toknum, tokval)) + return untokenize(result).decode('utf-8') + +class TestMisc(TestCase): + + def test_decistmt(self): + # Substitute Decimals for floats in a string of statements. + # This is an example from the docs. + + from decimal import Decimal + s = '+21.3e-5*-.1234/81.7' + self.assertEqual(decistmt(s), + "+Decimal ('21.3e-5')*-Decimal ('.1234')/Decimal ('81.7')") + + # The format of the exponent is inherited from the platform C library. + # Known cases are "e-007" (Windows) and "e-07" (not Windows). Since + # we're only showing 11 digits, and the 12th isn't close to 5, the + # rest of the output should be platform-independent. + self.assertRegex(repr(eval(s)), '-3.2171603427[0-9]*e-0+7') + + # Output from calculations with Decimal should be identical across all + # platforms. + self.assertEqual(eval(decistmt(s)), + Decimal('-3.217160342717258261933904529E-7')) + + +class TestTokenizerAdheresToPep0263(TestCase): + """ + Test that tokenizer adheres to the coding behaviour stipulated in PEP 0263. + """ + + def _testFile(self, filename): + path = os.path.join(os.path.dirname(__file__), filename) + TestRoundtrip.check_roundtrip(self, open(path, 'rb')) + + def test_utf8_coding_cookie_and_no_utf8_bom(self): + f = 'tokenize_tests-utf8-coding-cookie-and-no-utf8-bom-sig.txt' + self._testFile(f) + + def test_latin1_coding_cookie_and_utf8_bom(self): + """ + As per PEP 0263, if a file starts with a utf-8 BOM signature, the only + allowed encoding for the comment is 'utf-8'. The text file used in + this test starts with a BOM signature, but specifies latin1 as the + coding, so verify that a SyntaxError is raised, which matches the + behaviour of the interpreter when it encounters a similar condition. + """ + f = 'tokenize_tests-latin1-coding-cookie-and-utf8-bom-sig.txt' + self.assertRaises(SyntaxError, self._testFile, f) + + def test_no_coding_cookie_and_utf8_bom(self): + f = 'tokenize_tests-no-coding-cookie-and-utf8-bom-sig-only.txt' + self._testFile(f) + + def test_utf8_coding_cookie_and_utf8_bom(self): + f = 'tokenize_tests-utf8-coding-cookie-and-utf8-bom-sig.txt' + self._testFile(f) + + def test_bad_coding_cookie(self): + self.assertRaises(SyntaxError, self._testFile, 'bad_coding.py') + self.assertRaises(SyntaxError, self._testFile, 'bad_coding2.py') + + +class Test_Tokenize(TestCase): + + def test__tokenize_decodes_with_specified_encoding(self): + literal = '"ЉЊЈЁЂ"' + line = literal.encode('utf-8') + first = False + def readline(): + nonlocal first + if not first: + first = True + return line + else: + return b'' + + # skip the initial encoding token and the end tokens + tokens = list(_tokenize(readline, encoding='utf-8'))[1:-2] + expected_tokens = [(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"')] + self.assertEqual(tokens, expected_tokens, + "bytes not decoded with encoding") + + def test__tokenize_does_not_decode_with_encoding_none(self): + literal = '"ЉЊЈЁЂ"' + first = False + def readline(): + nonlocal first + if not first: + first = True + return literal + else: + return b'' + + # skip the end tokens + tokens = list(_tokenize(readline, encoding=None))[:-2] + expected_tokens = [(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"')] + self.assertEqual(tokens, expected_tokens, + "string not tokenized when encoding is None") + + +class TestDetectEncoding(TestCase): + + def get_readline(self, lines): + index = 0 + def readline(): + nonlocal index + if index == len(lines): + raise StopIteration + line = lines[index] + index += 1 + return line + return readline + + def test_no_bom_no_encoding_cookie(self): + lines = ( + b'# something\n', + b'print(something)\n', + b'do_something(else)\n' + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'utf-8') + self.assertEqual(consumed_lines, list(lines[:2])) + + def test_bom_no_cookie(self): + lines = ( + b'\xef\xbb\xbf# something\n', + b'print(something)\n', + b'do_something(else)\n' + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'utf-8-sig') + self.assertEqual(consumed_lines, + [b'# something\n', b'print(something)\n']) + + def test_cookie_first_line_no_bom(self): + lines = ( + b'# -*- coding: latin-1 -*-\n', + b'print(something)\n', + b'do_something(else)\n' + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'iso-8859-1') + self.assertEqual(consumed_lines, [b'# -*- coding: latin-1 -*-\n']) + + def test_matched_bom_and_cookie_first_line(self): + lines = ( + b'\xef\xbb\xbf# coding=utf-8\n', + b'print(something)\n', + b'do_something(else)\n' + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'utf-8-sig') + self.assertEqual(consumed_lines, [b'# coding=utf-8\n']) + + def test_mismatched_bom_and_cookie_first_line_raises_syntaxerror(self): + lines = ( + b'\xef\xbb\xbf# vim: set fileencoding=ascii :\n', + b'print(something)\n', + b'do_something(else)\n' + ) + readline = self.get_readline(lines) + self.assertRaises(SyntaxError, detect_encoding, readline) + + def test_cookie_second_line_no_bom(self): + lines = ( + b'#! something\n', + b'# vim: set fileencoding=ascii :\n', + b'print(something)\n', + b'do_something(else)\n' + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'ascii') + expected = [b'#! something\n', b'# vim: set fileencoding=ascii :\n'] + self.assertEqual(consumed_lines, expected) + + def test_matched_bom_and_cookie_second_line(self): + lines = ( + b'\xef\xbb\xbf#! something\n', + b'f# coding=utf-8\n', + b'print(something)\n', + b'do_something(else)\n' + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'utf-8-sig') + self.assertEqual(consumed_lines, + [b'#! something\n', b'f# coding=utf-8\n']) + + def test_mismatched_bom_and_cookie_second_line_raises_syntaxerror(self): + lines = ( + b'\xef\xbb\xbf#! something\n', + b'# vim: set fileencoding=ascii :\n', + b'print(something)\n', + b'do_something(else)\n' + ) + readline = self.get_readline(lines) + self.assertRaises(SyntaxError, detect_encoding, readline) + + def test_cookie_second_line_noncommented_first_line(self): + lines = ( + b"print('\xc2\xa3')\n", + b'# vim: set fileencoding=iso8859-15 :\n', + b"print('\xe2\x82\xac')\n" + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'utf-8') + expected = [b"print('\xc2\xa3')\n"] + self.assertEqual(consumed_lines, expected) + + def test_cookie_second_line_commented_first_line(self): + lines = ( + b"#print('\xc2\xa3')\n", + b'# vim: set fileencoding=iso8859-15 :\n', + b"print('\xe2\x82\xac')\n" + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'iso8859-15') + expected = [b"#print('\xc2\xa3')\n", b'# vim: set fileencoding=iso8859-15 :\n'] + self.assertEqual(consumed_lines, expected) + + def test_cookie_second_line_empty_first_line(self): + lines = ( + b'\n', + b'# vim: set fileencoding=iso8859-15 :\n', + b"print('\xe2\x82\xac')\n" + ) + encoding, consumed_lines = detect_encoding(self.get_readline(lines)) + self.assertEqual(encoding, 'iso8859-15') + expected = [b'\n', b'# vim: set fileencoding=iso8859-15 :\n'] + self.assertEqual(consumed_lines, expected) + + def test_latin1_normalization(self): + # See get_normal_name() in tokenizer.c. + encodings = ("latin-1", "iso-8859-1", "iso-latin-1", "latin-1-unix", + "iso-8859-1-unix", "iso-latin-1-mac") + for encoding in encodings: + for rep in ("-", "_"): + enc = encoding.replace("-", rep) + lines = (b"#!/usr/bin/python\n", + b"# coding: " + enc.encode("ascii") + b"\n", + b"print(things)\n", + b"do_something += 4\n") + rl = self.get_readline(lines) + found, consumed_lines = detect_encoding(rl) + self.assertEqual(found, "iso-8859-1") + + def test_syntaxerror_latin1(self): + # Issue 14629: need to raise SyntaxError if the first + # line(s) have non-UTF-8 characters + lines = ( + b'print("\xdf")', # Latin-1: LATIN SMALL LETTER SHARP S + ) + readline = self.get_readline(lines) + self.assertRaises(SyntaxError, detect_encoding, readline) + + + def test_utf8_normalization(self): + # See get_normal_name() in tokenizer.c. + encodings = ("utf-8", "utf-8-mac", "utf-8-unix") + for encoding in encodings: + for rep in ("-", "_"): + enc = encoding.replace("-", rep) + lines = (b"#!/usr/bin/python\n", + b"# coding: " + enc.encode("ascii") + b"\n", + b"1 + 3\n") + rl = self.get_readline(lines) + found, consumed_lines = detect_encoding(rl) + self.assertEqual(found, "utf-8") + + def test_short_files(self): + readline = self.get_readline((b'print(something)\n',)) + encoding, consumed_lines = detect_encoding(readline) + self.assertEqual(encoding, 'utf-8') + self.assertEqual(consumed_lines, [b'print(something)\n']) + + encoding, consumed_lines = detect_encoding(self.get_readline(())) + self.assertEqual(encoding, 'utf-8') + self.assertEqual(consumed_lines, []) + + readline = self.get_readline((b'\xef\xbb\xbfprint(something)\n',)) + encoding, consumed_lines = detect_encoding(readline) + self.assertEqual(encoding, 'utf-8-sig') + self.assertEqual(consumed_lines, [b'print(something)\n']) + + readline = self.get_readline((b'\xef\xbb\xbf',)) + encoding, consumed_lines = detect_encoding(readline) + self.assertEqual(encoding, 'utf-8-sig') + self.assertEqual(consumed_lines, []) + + readline = self.get_readline((b'# coding: bad\n',)) + self.assertRaises(SyntaxError, detect_encoding, readline) + + def test_false_encoding(self): + # Issue 18873: "Encoding" detected in non-comment lines + readline = self.get_readline((b'print("#coding=fake")',)) + encoding, consumed_lines = detect_encoding(readline) + self.assertEqual(encoding, 'utf-8') + self.assertEqual(consumed_lines, [b'print("#coding=fake")']) + + def test_open(self): + filename = os_helper.TESTFN + '.py' + self.addCleanup(os_helper.unlink, filename) + + # test coding cookie + for encoding in ('iso-8859-15', 'utf-8'): + with open(filename, 'w', encoding=encoding) as fp: + print("# coding: %s" % encoding, file=fp) + print("print('euro:\u20ac')", file=fp) + with tokenize_open(filename) as fp: + self.assertEqual(fp.encoding, encoding) + self.assertEqual(fp.mode, 'r') + + # test BOM (no coding cookie) + with open(filename, 'w', encoding='utf-8-sig') as fp: + print("print('euro:\u20ac')", file=fp) + with tokenize_open(filename) as fp: + self.assertEqual(fp.encoding, 'utf-8-sig') + self.assertEqual(fp.mode, 'r') + + def test_filename_in_exception(self): + # When possible, include the file name in the exception. + path = 'some_file_path' + lines = ( + b'print("\xdf")', # Latin-1: LATIN SMALL LETTER SHARP S + ) + class Bunk: + def __init__(self, lines, path): + self.name = path + self._lines = lines + self._index = 0 + + def readline(self): + if self._index == len(lines): + raise StopIteration + line = lines[self._index] + self._index += 1 + return line + + with self.assertRaises(SyntaxError): + ins = Bunk(lines, path) + # Make sure lacking a name isn't an issue. + del ins.name + detect_encoding(ins.readline) + with self.assertRaisesRegex(SyntaxError, '.*{}'.format(path)): + ins = Bunk(lines, path) + detect_encoding(ins.readline) + + def test_open_error(self): + # Issue #23840: open() must close the binary file on error + m = BytesIO(b'#coding:xxx') + with mock.patch('tokenize._builtin_open', return_value=m): + self.assertRaises(SyntaxError, tokenize_open, 'foobar') + self.assertTrue(m.closed) + + +class TestTokenize(TestCase): + + def test_tokenize(self): + import tokenize as tokenize_module + encoding = object() + encoding_used = None + def mock_detect_encoding(readline): + return encoding, [b'first', b'second'] + + def mock__tokenize(readline, encoding): + nonlocal encoding_used + encoding_used = encoding + out = [] + while True: + next_line = readline() + if next_line: + out.append(next_line) + continue + return out + + counter = 0 + def mock_readline(): + nonlocal counter + counter += 1 + if counter == 5: + return b'' + return str(counter).encode() + + orig_detect_encoding = tokenize_module.detect_encoding + orig__tokenize = tokenize_module._tokenize + tokenize_module.detect_encoding = mock_detect_encoding + tokenize_module._tokenize = mock__tokenize + try: + results = tokenize(mock_readline) + self.assertEqual(list(results), + [b'first', b'second', b'1', b'2', b'3', b'4']) + finally: + tokenize_module.detect_encoding = orig_detect_encoding + tokenize_module._tokenize = orig__tokenize + + self.assertEqual(encoding_used, encoding) + + def test_oneline_defs(self): + buf = [] + for i in range(500): + buf.append('def i{i}(): return {i}'.format(i=i)) + buf.append('OK') + buf = '\n'.join(buf) + + # Test that 500 consequent, one-line defs is OK + toks = list(tokenize(BytesIO(buf.encode('utf-8')).readline)) + self.assertEqual(toks[-3].string, 'OK') # [-1] is always ENDMARKER + # [-2] is always NEWLINE + + def assertExactTypeEqual(self, opstr, *optypes): + tokens = list(tokenize(BytesIO(opstr.encode('utf-8')).readline)) + num_optypes = len(optypes) + self.assertEqual(len(tokens), 3 + num_optypes) + self.assertEqual(tok_name[tokens[0].exact_type], + tok_name[ENCODING]) + for i in range(num_optypes): + self.assertEqual(tok_name[tokens[i + 1].exact_type], + tok_name[optypes[i]]) + self.assertEqual(tok_name[tokens[1 + num_optypes].exact_type], + tok_name[token.NEWLINE]) + self.assertEqual(tok_name[tokens[2 + num_optypes].exact_type], + tok_name[token.ENDMARKER]) + + def test_exact_type(self): + self.assertExactTypeEqual('()', token.LPAR, token.RPAR) + self.assertExactTypeEqual('[]', token.LSQB, token.RSQB) + self.assertExactTypeEqual(':', token.COLON) + self.assertExactTypeEqual(',', token.COMMA) + self.assertExactTypeEqual(';', token.SEMI) + self.assertExactTypeEqual('+', token.PLUS) + self.assertExactTypeEqual('-', token.MINUS) + self.assertExactTypeEqual('*', token.STAR) + self.assertExactTypeEqual('/', token.SLASH) + self.assertExactTypeEqual('|', token.VBAR) + self.assertExactTypeEqual('&', token.AMPER) + self.assertExactTypeEqual('<', token.LESS) + self.assertExactTypeEqual('>', token.GREATER) + self.assertExactTypeEqual('=', token.EQUAL) + self.assertExactTypeEqual('.', token.DOT) + self.assertExactTypeEqual('%', token.PERCENT) + self.assertExactTypeEqual('{}', token.LBRACE, token.RBRACE) + self.assertExactTypeEqual('==', token.EQEQUAL) + self.assertExactTypeEqual('!=', token.NOTEQUAL) + self.assertExactTypeEqual('<=', token.LESSEQUAL) + self.assertExactTypeEqual('>=', token.GREATEREQUAL) + self.assertExactTypeEqual('~', token.TILDE) + self.assertExactTypeEqual('^', token.CIRCUMFLEX) + self.assertExactTypeEqual('<<', token.LEFTSHIFT) + self.assertExactTypeEqual('>>', token.RIGHTSHIFT) + self.assertExactTypeEqual('**', token.DOUBLESTAR) + self.assertExactTypeEqual('+=', token.PLUSEQUAL) + self.assertExactTypeEqual('-=', token.MINEQUAL) + self.assertExactTypeEqual('*=', token.STAREQUAL) + self.assertExactTypeEqual('/=', token.SLASHEQUAL) + self.assertExactTypeEqual('%=', token.PERCENTEQUAL) + self.assertExactTypeEqual('&=', token.AMPEREQUAL) + self.assertExactTypeEqual('|=', token.VBAREQUAL) + self.assertExactTypeEqual('^=', token.CIRCUMFLEXEQUAL) + self.assertExactTypeEqual('^=', token.CIRCUMFLEXEQUAL) + self.assertExactTypeEqual('<<=', token.LEFTSHIFTEQUAL) + self.assertExactTypeEqual('>>=', token.RIGHTSHIFTEQUAL) + self.assertExactTypeEqual('**=', token.DOUBLESTAREQUAL) + self.assertExactTypeEqual('//', token.DOUBLESLASH) + self.assertExactTypeEqual('//=', token.DOUBLESLASHEQUAL) + self.assertExactTypeEqual(':=', token.COLONEQUAL) + self.assertExactTypeEqual('...', token.ELLIPSIS) + self.assertExactTypeEqual('->', token.RARROW) + self.assertExactTypeEqual('@', token.AT) + self.assertExactTypeEqual('@=', token.ATEQUAL) + + self.assertExactTypeEqual('a**2+b**2==c**2', + NAME, token.DOUBLESTAR, NUMBER, + token.PLUS, + NAME, token.DOUBLESTAR, NUMBER, + token.EQEQUAL, + NAME, token.DOUBLESTAR, NUMBER) + self.assertExactTypeEqual('{1, 2, 3}', + token.LBRACE, + token.NUMBER, token.COMMA, + token.NUMBER, token.COMMA, + token.NUMBER, + token.RBRACE) + self.assertExactTypeEqual('^(x & 0x1)', + token.CIRCUMFLEX, + token.LPAR, + token.NAME, token.AMPER, token.NUMBER, + token.RPAR) + + def test_pathological_trailing_whitespace(self): + # See http://bugs.python.org/issue16152 + self.assertExactTypeEqual('@ ', token.AT) + + def test_comment_at_the_end_of_the_source_without_newline(self): + # See http://bugs.python.org/issue44667 + source = 'b = 1\n\n#test' + expected_tokens = [token.NAME, token.EQUAL, token.NUMBER, token.NEWLINE, token.NL, token.COMMENT] + + tokens = list(tokenize(BytesIO(source.encode('utf-8')).readline)) + self.assertEqual(tok_name[tokens[0].exact_type], tok_name[ENCODING]) + for i in range(6): + self.assertEqual(tok_name[tokens[i + 1].exact_type], tok_name[expected_tokens[i]]) + self.assertEqual(tok_name[tokens[-1].exact_type], tok_name[token.ENDMARKER]) + +class UntokenizeTest(TestCase): + + def test_bad_input_order(self): + # raise if previous row + u = Untokenizer() + u.prev_row = 2 + u.prev_col = 2 + with self.assertRaises(ValueError) as cm: + u.add_whitespace((1,3)) + self.assertEqual(cm.exception.args[0], + 'start (1,3) precedes previous end (2,2)') + # raise if previous column in row + self.assertRaises(ValueError, u.add_whitespace, (2,1)) + + def test_backslash_continuation(self): + # The problem is that \ leaves no token + u = Untokenizer() + u.prev_row = 1 + u.prev_col = 1 + u.tokens = [] + u.add_whitespace((2, 0)) + self.assertEqual(u.tokens, ['\\\n']) + u.prev_row = 2 + u.add_whitespace((4, 4)) + self.assertEqual(u.tokens, ['\\\n', '\\\n\\\n', ' ']) + TestRoundtrip.check_roundtrip(self, 'a\n b\n c\n \\\n c\n') + + def test_iter_compat(self): + u = Untokenizer() + token = (NAME, 'Hello') + tokens = [(ENCODING, 'utf-8'), token] + u.compat(token, iter([])) + self.assertEqual(u.tokens, ["Hello "]) + u = Untokenizer() + self.assertEqual(u.untokenize(iter([token])), 'Hello ') + u = Untokenizer() + self.assertEqual(u.untokenize(iter(tokens)), 'Hello ') + self.assertEqual(u.encoding, 'utf-8') + self.assertEqual(untokenize(iter(tokens)), b'Hello ') + + +class TestRoundtrip(TestCase): + + def check_roundtrip(self, f): + """ + Test roundtrip for `untokenize`. `f` is an open file or a string. + The source code in f is tokenized to both 5- and 2-tuples. + Both sequences are converted back to source code via + tokenize.untokenize(), and the latter tokenized again to 2-tuples. + The test fails if the 3 pair tokenizations do not match. + + When untokenize bugs are fixed, untokenize with 5-tuples should + reproduce code that does not contain a backslash continuation + following spaces. A proper test should test this. + """ + # Get source code and original tokenizations + if isinstance(f, str): + code = f.encode('utf-8') + else: + code = f.read() + f.close() + readline = iter(code.splitlines(keepends=True)).__next__ + tokens5 = list(tokenize(readline)) + tokens2 = [tok[:2] for tok in tokens5] + # Reproduce tokens2 from pairs + bytes_from2 = untokenize(tokens2) + readline2 = iter(bytes_from2.splitlines(keepends=True)).__next__ + tokens2_from2 = [tok[:2] for tok in tokenize(readline2)] + self.assertEqual(tokens2_from2, tokens2) + # Reproduce tokens2 from 5-tuples + bytes_from5 = untokenize(tokens5) + readline5 = iter(bytes_from5.splitlines(keepends=True)).__next__ + tokens2_from5 = [tok[:2] for tok in tokenize(readline5)] + self.assertEqual(tokens2_from5, tokens2) + + def test_roundtrip(self): + # There are some standard formatting practices that are easy to get right. + + self.check_roundtrip("if x == 1:\n" + " print(x)\n") + self.check_roundtrip("# This is a comment\n" + "# This also\n") + + # Some people use different formatting conventions, which makes + # untokenize a little trickier. Note that this test involves trailing + # whitespace after the colon. Note that we use hex escapes to make the + # two trailing blanks apparent in the expected output. + + self.check_roundtrip("if x == 1 : \n" + " print(x)\n") + fn = support.findfile("tokenize_tests.txt") + with open(fn, 'rb') as f: + self.check_roundtrip(f) + self.check_roundtrip("if x == 1:\n" + " # A comment by itself.\n" + " print(x) # Comment here, too.\n" + " # Another comment.\n" + "after_if = True\n") + self.check_roundtrip("if (x # The comments need to go in the right place\n" + " == 1):\n" + " print('x==1')\n") + self.check_roundtrip("class Test: # A comment here\n" + " # A comment with weird indent\n" + " after_com = 5\n" + " def x(m): return m*5 # a one liner\n" + " def y(m): # A whitespace after the colon\n" + " return y*4 # 3-space indent\n") + + # Some error-handling code + self.check_roundtrip("try: import somemodule\n" + "except ImportError: # comment\n" + " print('Can not import' # comment2\n)" + "else: print('Loaded')\n") + + def test_continuation(self): + # Balancing continuation + self.check_roundtrip("a = (3,4, \n" + "5,6)\n" + "y = [3, 4,\n" + "5]\n" + "z = {'a': 5,\n" + "'b':15, 'c':True}\n" + "x = len(y) + 5 - a[\n" + "3] - a[2]\n" + "+ len(z) - z[\n" + "'b']\n") + + def test_backslash_continuation(self): + # Backslash means line continuation, except for comments + self.check_roundtrip("x=1+\\\n" + "1\n" + "# This is a comment\\\n" + "# This also\n") + self.check_roundtrip("# Comment \\\n" + "x = 0") + + def test_string_concatenation(self): + # Two string literals on the same line + self.check_roundtrip("'' ''") + + def test_random_files(self): + # Test roundtrip on random python modules. + # pass the '-ucpu' option to process the full directory. + + import glob, random + fn = support.findfile("tokenize_tests.txt") + tempdir = os.path.dirname(fn) or os.curdir + testfiles = glob.glob(os.path.join(glob.escape(tempdir), "test*.py")) + + # Tokenize is broken on test_pep3131.py because regular expressions are + # broken on the obscure unicode identifiers in it. *sigh* + # With roundtrip extended to test the 5-tuple mode of untokenize, + # 7 more testfiles fail. Remove them also until the failure is diagnosed. + + testfiles.remove(os.path.join(tempdir, "test_unicode_identifiers.py")) + for f in ('buffer', 'builtin', 'fileio', 'inspect', 'os', 'platform', 'sys'): + testfiles.remove(os.path.join(tempdir, "test_%s.py") % f) + + if not support.is_resource_enabled("cpu"): + testfiles = random.sample(testfiles, 10) + + for testfile in testfiles: + if support.verbose >= 2: + print('tokenize', testfile) + with open(testfile, 'rb') as f: + with self.subTest(file=testfile): + self.check_roundtrip(f) + + + def roundtrip(self, code): + if isinstance(code, str): + code = code.encode('utf-8') + return untokenize(tokenize(BytesIO(code).readline)).decode('utf-8') + + def test_indentation_semantics_retained(self): + """ + Ensure that although whitespace might be mutated in a roundtrip, + the semantic meaning of the indentation remains consistent. + """ + code = "if False:\n\tx=3\n\tx=3\n" + codelines = self.roundtrip(code).split('\n') + self.assertEqual(codelines[1], codelines[2]) + self.check_roundtrip(code) + + +class CTokenizeTest(TestCase): + def check_tokenize(self, s, expected): + # Format the tokens in s in a table format. + # The ENDMARKER and final NEWLINE are omitted. + with self.subTest(source=s): + result = stringify_tokens_from_source( + _generate_tokens_from_c_tokenizer(s), s + ) + self.assertEqual(result, expected.rstrip().splitlines()) + + def test_int(self): + + self.check_tokenize('0xff <= 255', """\ + NUMBER '0xff' (1, 0) (1, 4) + LESSEQUAL '<=' (1, 5) (1, 7) + NUMBER '255' (1, 8) (1, 11) + """) + + self.check_tokenize('0b10 <= 255', """\ + NUMBER '0b10' (1, 0) (1, 4) + LESSEQUAL '<=' (1, 5) (1, 7) + NUMBER '255' (1, 8) (1, 11) + """) + + self.check_tokenize('0o123 <= 0O123', """\ + NUMBER '0o123' (1, 0) (1, 5) + LESSEQUAL '<=' (1, 6) (1, 8) + NUMBER '0O123' (1, 9) (1, 14) + """) + + self.check_tokenize('1234567 > ~0x15', """\ + NUMBER '1234567' (1, 0) (1, 7) + GREATER '>' (1, 8) (1, 9) + TILDE '~' (1, 10) (1, 11) + NUMBER '0x15' (1, 11) (1, 15) + """) + + self.check_tokenize('2134568 != 1231515', """\ + NUMBER '2134568' (1, 0) (1, 7) + NOTEQUAL '!=' (1, 8) (1, 10) + NUMBER '1231515' (1, 11) (1, 18) + """) + + self.check_tokenize('(-124561-1) & 200000000', """\ + LPAR '(' (1, 0) (1, 1) + MINUS '-' (1, 1) (1, 2) + NUMBER '124561' (1, 2) (1, 8) + MINUS '-' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + RPAR ')' (1, 10) (1, 11) + AMPER '&' (1, 12) (1, 13) + NUMBER '200000000' (1, 14) (1, 23) + """) + + self.check_tokenize('0xdeadbeef != -1', """\ + NUMBER '0xdeadbeef' (1, 0) (1, 10) + NOTEQUAL '!=' (1, 11) (1, 13) + MINUS '-' (1, 14) (1, 15) + NUMBER '1' (1, 15) (1, 16) + """) + + self.check_tokenize('0xdeadc0de & 12345', """\ + NUMBER '0xdeadc0de' (1, 0) (1, 10) + AMPER '&' (1, 11) (1, 12) + NUMBER '12345' (1, 13) (1, 18) + """) + + self.check_tokenize('0xFF & 0x15 | 1234', """\ + NUMBER '0xFF' (1, 0) (1, 4) + AMPER '&' (1, 5) (1, 6) + NUMBER '0x15' (1, 7) (1, 11) + VBAR '|' (1, 12) (1, 13) + NUMBER '1234' (1, 14) (1, 18) + """) + + def test_float(self): + + self.check_tokenize('x = 3.14159', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '3.14159' (1, 4) (1, 11) + """) + + self.check_tokenize('x = 314159.', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '314159.' (1, 4) (1, 11) + """) + + self.check_tokenize('x = .314159', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '.314159' (1, 4) (1, 11) + """) + + self.check_tokenize('x = 3e14159', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '3e14159' (1, 4) (1, 11) + """) + + self.check_tokenize('x = 3E123', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '3E123' (1, 4) (1, 9) + """) + + self.check_tokenize('x+y = 3e-1230', """\ + NAME 'x' (1, 0) (1, 1) + PLUS '+' (1, 1) (1, 2) + NAME 'y' (1, 2) (1, 3) + EQUAL '=' (1, 4) (1, 5) + NUMBER '3e-1230' (1, 6) (1, 13) + """) + + self.check_tokenize('x = 3.14e159', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '3.14e159' (1, 4) (1, 12) + """) + + def test_string(self): + + self.check_tokenize('x = \'\'; y = ""', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + STRING "''" (1, 4) (1, 6) + SEMI ';' (1, 6) (1, 7) + NAME 'y' (1, 8) (1, 9) + EQUAL '=' (1, 10) (1, 11) + STRING '""' (1, 12) (1, 14) + """) + + self.check_tokenize('x = \'"\'; y = "\'"', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + STRING '\\'"\\'' (1, 4) (1, 7) + SEMI ';' (1, 7) (1, 8) + NAME 'y' (1, 9) (1, 10) + EQUAL '=' (1, 11) (1, 12) + STRING '"\\'"' (1, 13) (1, 16) + """) + + self.check_tokenize('x = "doesn\'t "shrink", does it"', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + STRING '"doesn\\'t "' (1, 4) (1, 14) + NAME 'shrink' (1, 14) (1, 20) + STRING '", does it"' (1, 20) (1, 31) + """) + + self.check_tokenize("x = 'abc' + 'ABC'", """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + STRING "'abc'" (1, 4) (1, 9) + PLUS '+' (1, 10) (1, 11) + STRING "'ABC'" (1, 12) (1, 17) + """) + + self.check_tokenize('y = "ABC" + "ABC"', """\ + NAME 'y' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + STRING '"ABC"' (1, 4) (1, 9) + PLUS '+' (1, 10) (1, 11) + STRING '"ABC"' (1, 12) (1, 17) + """) + + self.check_tokenize("x = r'abc' + r'ABC' + R'ABC' + R'ABC'", """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + STRING "r'abc'" (1, 4) (1, 10) + PLUS '+' (1, 11) (1, 12) + STRING "r'ABC'" (1, 13) (1, 19) + PLUS '+' (1, 20) (1, 21) + STRING "R'ABC'" (1, 22) (1, 28) + PLUS '+' (1, 29) (1, 30) + STRING "R'ABC'" (1, 31) (1, 37) + """) + + self.check_tokenize('y = r"abc" + r"ABC" + R"ABC" + R"ABC"', """\ + NAME 'y' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + STRING 'r"abc"' (1, 4) (1, 10) + PLUS '+' (1, 11) (1, 12) + STRING 'r"ABC"' (1, 13) (1, 19) + PLUS '+' (1, 20) (1, 21) + STRING 'R"ABC"' (1, 22) (1, 28) + PLUS '+' (1, 29) (1, 30) + STRING 'R"ABC"' (1, 31) (1, 37) + """) + + self.check_tokenize("u'abc' + U'abc'", """\ + STRING "u'abc'" (1, 0) (1, 6) + PLUS '+' (1, 7) (1, 8) + STRING "U'abc'" (1, 9) (1, 15) + """) + + self.check_tokenize('u"abc" + U"abc"', """\ + STRING 'u"abc"' (1, 0) (1, 6) + PLUS '+' (1, 7) (1, 8) + STRING 'U"abc"' (1, 9) (1, 15) + """) + + self.check_tokenize("b'abc' + B'abc'", """\ + STRING "b'abc'" (1, 0) (1, 6) + PLUS '+' (1, 7) (1, 8) + STRING "B'abc'" (1, 9) (1, 15) + """) + + self.check_tokenize('b"abc" + B"abc"', """\ + STRING 'b"abc"' (1, 0) (1, 6) + PLUS '+' (1, 7) (1, 8) + STRING 'B"abc"' (1, 9) (1, 15) + """) + + self.check_tokenize("br'abc' + bR'abc' + Br'abc' + BR'abc'", """\ + STRING "br'abc'" (1, 0) (1, 7) + PLUS '+' (1, 8) (1, 9) + STRING "bR'abc'" (1, 10) (1, 17) + PLUS '+' (1, 18) (1, 19) + STRING "Br'abc'" (1, 20) (1, 27) + PLUS '+' (1, 28) (1, 29) + STRING "BR'abc'" (1, 30) (1, 37) + """) + + self.check_tokenize('br"abc" + bR"abc" + Br"abc" + BR"abc"', """\ + STRING 'br"abc"' (1, 0) (1, 7) + PLUS '+' (1, 8) (1, 9) + STRING 'bR"abc"' (1, 10) (1, 17) + PLUS '+' (1, 18) (1, 19) + STRING 'Br"abc"' (1, 20) (1, 27) + PLUS '+' (1, 28) (1, 29) + STRING 'BR"abc"' (1, 30) (1, 37) + """) + + self.check_tokenize("rb'abc' + rB'abc' + Rb'abc' + RB'abc'", """\ + STRING "rb'abc'" (1, 0) (1, 7) + PLUS '+' (1, 8) (1, 9) + STRING "rB'abc'" (1, 10) (1, 17) + PLUS '+' (1, 18) (1, 19) + STRING "Rb'abc'" (1, 20) (1, 27) + PLUS '+' (1, 28) (1, 29) + STRING "RB'abc'" (1, 30) (1, 37) + """) + + self.check_tokenize('rb"abc" + rB"abc" + Rb"abc" + RB"abc"', """\ + STRING 'rb"abc"' (1, 0) (1, 7) + PLUS '+' (1, 8) (1, 9) + STRING 'rB"abc"' (1, 10) (1, 17) + PLUS '+' (1, 18) (1, 19) + STRING 'Rb"abc"' (1, 20) (1, 27) + PLUS '+' (1, 28) (1, 29) + STRING 'RB"abc"' (1, 30) (1, 37) + """) + + self.check_tokenize('"a\\\nde\\\nfg"', """\ + STRING '"a\\\\\\nde\\\\\\nfg"\' (1, 0) (3, 3) + """) + + self.check_tokenize('u"a\\\nde"', """\ + STRING 'u"a\\\\\\nde"\' (1, 0) (2, 3) + """) + + self.check_tokenize('rb"a\\\nd"', """\ + STRING 'rb"a\\\\\\nd"\' (1, 0) (2, 2) + """) + + self.check_tokenize(r'"""a\ +b"""', """\ + STRING '\"\""a\\\\\\nb\"\""' (1, 0) (2, 4) + """) + self.check_tokenize(r'u"""a\ +b"""', """\ + STRING 'u\"\""a\\\\\\nb\"\""' (1, 0) (2, 4) + """) + self.check_tokenize(r'rb"""a\ +b\ +c"""', """\ + STRING 'rb"\""a\\\\\\nb\\\\\\nc"\""' (1, 0) (3, 4) + """) + + self.check_tokenize('f"abc"', """\ + STRING 'f"abc"' (1, 0) (1, 6) + """) + + self.check_tokenize('fR"a{b}c"', """\ + STRING 'fR"a{b}c"' (1, 0) (1, 9) + """) + + self.check_tokenize('f"""abc"""', """\ + STRING 'f\"\"\"abc\"\"\"' (1, 0) (1, 10) + """) + + self.check_tokenize(r'f"abc\ +def"', """\ + STRING 'f"abc\\\\\\ndef"' (1, 0) (2, 4) + """) + + self.check_tokenize(r'Rf"abc\ +def"', """\ + STRING 'Rf"abc\\\\\\ndef"' (1, 0) (2, 4) + """) + + def test_function(self): + + self.check_tokenize('def d22(a, b, c=2, d=2, *k): pass', """\ + NAME 'def' (1, 0) (1, 3) + NAME 'd22' (1, 4) (1, 7) + LPAR '(' (1, 7) (1, 8) + NAME 'a' (1, 8) (1, 9) + COMMA ',' (1, 9) (1, 10) + NAME 'b' (1, 11) (1, 12) + COMMA ',' (1, 12) (1, 13) + NAME 'c' (1, 14) (1, 15) + EQUAL '=' (1, 15) (1, 16) + NUMBER '2' (1, 16) (1, 17) + COMMA ',' (1, 17) (1, 18) + NAME 'd' (1, 19) (1, 20) + EQUAL '=' (1, 20) (1, 21) + NUMBER '2' (1, 21) (1, 22) + COMMA ',' (1, 22) (1, 23) + STAR '*' (1, 24) (1, 25) + NAME 'k' (1, 25) (1, 26) + RPAR ')' (1, 26) (1, 27) + COLON ':' (1, 27) (1, 28) + NAME 'pass' (1, 29) (1, 33) + """) + + self.check_tokenize('def d01v_(a=1, *k, **w): pass', """\ + NAME 'def' (1, 0) (1, 3) + NAME 'd01v_' (1, 4) (1, 9) + LPAR '(' (1, 9) (1, 10) + NAME 'a' (1, 10) (1, 11) + EQUAL '=' (1, 11) (1, 12) + NUMBER '1' (1, 12) (1, 13) + COMMA ',' (1, 13) (1, 14) + STAR '*' (1, 15) (1, 16) + NAME 'k' (1, 16) (1, 17) + COMMA ',' (1, 17) (1, 18) + DOUBLESTAR '**' (1, 19) (1, 21) + NAME 'w' (1, 21) (1, 22) + RPAR ')' (1, 22) (1, 23) + COLON ':' (1, 23) (1, 24) + NAME 'pass' (1, 25) (1, 29) + """) + + self.check_tokenize('def d23(a: str, b: int=3) -> int: pass', """\ + NAME 'def' (1, 0) (1, 3) + NAME 'd23' (1, 4) (1, 7) + LPAR '(' (1, 7) (1, 8) + NAME 'a' (1, 8) (1, 9) + COLON ':' (1, 9) (1, 10) + NAME 'str' (1, 11) (1, 14) + COMMA ',' (1, 14) (1, 15) + NAME 'b' (1, 16) (1, 17) + COLON ':' (1, 17) (1, 18) + NAME 'int' (1, 19) (1, 22) + EQUAL '=' (1, 22) (1, 23) + NUMBER '3' (1, 23) (1, 24) + RPAR ')' (1, 24) (1, 25) + RARROW '->' (1, 26) (1, 28) + NAME 'int' (1, 29) (1, 32) + COLON ':' (1, 32) (1, 33) + NAME 'pass' (1, 34) (1, 38) + """) + + def test_comparison(self): + + self.check_tokenize("if 1 < 1 > 1 == 1 >= 5 <= 0x15 <= 0x12 != " + "1 and 5 in 1 not in 1 is 1 or 5 is not 1: pass", """\ + NAME 'if' (1, 0) (1, 2) + NUMBER '1' (1, 3) (1, 4) + LESS '<' (1, 5) (1, 6) + NUMBER '1' (1, 7) (1, 8) + GREATER '>' (1, 9) (1, 10) + NUMBER '1' (1, 11) (1, 12) + EQEQUAL '==' (1, 13) (1, 15) + NUMBER '1' (1, 16) (1, 17) + GREATEREQUAL '>=' (1, 18) (1, 20) + NUMBER '5' (1, 21) (1, 22) + LESSEQUAL '<=' (1, 23) (1, 25) + NUMBER '0x15' (1, 26) (1, 30) + LESSEQUAL '<=' (1, 31) (1, 33) + NUMBER '0x12' (1, 34) (1, 38) + NOTEQUAL '!=' (1, 39) (1, 41) + NUMBER '1' (1, 42) (1, 43) + NAME 'and' (1, 44) (1, 47) + NUMBER '5' (1, 48) (1, 49) + NAME 'in' (1, 50) (1, 52) + NUMBER '1' (1, 53) (1, 54) + NAME 'not' (1, 55) (1, 58) + NAME 'in' (1, 59) (1, 61) + NUMBER '1' (1, 62) (1, 63) + NAME 'is' (1, 64) (1, 66) + NUMBER '1' (1, 67) (1, 68) + NAME 'or' (1, 69) (1, 71) + NUMBER '5' (1, 72) (1, 73) + NAME 'is' (1, 74) (1, 76) + NAME 'not' (1, 77) (1, 80) + NUMBER '1' (1, 81) (1, 82) + COLON ':' (1, 82) (1, 83) + NAME 'pass' (1, 84) (1, 88) + """) + + def test_additive(self): + + self.check_tokenize('x = 1 - y + 15 - 1 + 0x124 + z + a[5]', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + MINUS '-' (1, 6) (1, 7) + NAME 'y' (1, 8) (1, 9) + PLUS '+' (1, 10) (1, 11) + NUMBER '15' (1, 12) (1, 14) + MINUS '-' (1, 15) (1, 16) + NUMBER '1' (1, 17) (1, 18) + PLUS '+' (1, 19) (1, 20) + NUMBER '0x124' (1, 21) (1, 26) + PLUS '+' (1, 27) (1, 28) + NAME 'z' (1, 29) (1, 30) + PLUS '+' (1, 31) (1, 32) + NAME 'a' (1, 33) (1, 34) + LSQB '[' (1, 34) (1, 35) + NUMBER '5' (1, 35) (1, 36) + RSQB ']' (1, 36) (1, 37) + """) + + def test_multiplicative(self): + + self.check_tokenize('x = 1//1*1/5*12%0x12@42', """\ + NAME 'x' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + DOUBLESLASH '//' (1, 5) (1, 7) + NUMBER '1' (1, 7) (1, 8) + STAR '*' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + SLASH '/' (1, 10) (1, 11) + NUMBER '5' (1, 11) (1, 12) + STAR '*' (1, 12) (1, 13) + NUMBER '12' (1, 13) (1, 15) + PERCENT '%' (1, 15) (1, 16) + NUMBER '0x12' (1, 16) (1, 20) + AT '@' (1, 20) (1, 21) + NUMBER '42' (1, 21) (1, 23) + """) + + def test_unary(self): + + self.check_tokenize('~1 ^ 1 & 1 |1 ^ -1', """\ + TILDE '~' (1, 0) (1, 1) + NUMBER '1' (1, 1) (1, 2) + CIRCUMFLEX '^' (1, 3) (1, 4) + NUMBER '1' (1, 5) (1, 6) + AMPER '&' (1, 7) (1, 8) + NUMBER '1' (1, 9) (1, 10) + VBAR '|' (1, 11) (1, 12) + NUMBER '1' (1, 12) (1, 13) + CIRCUMFLEX '^' (1, 14) (1, 15) + MINUS '-' (1, 16) (1, 17) + NUMBER '1' (1, 17) (1, 18) + """) + + self.check_tokenize('-1*1/1+1*1//1 - ---1**1', """\ + MINUS '-' (1, 0) (1, 1) + NUMBER '1' (1, 1) (1, 2) + STAR '*' (1, 2) (1, 3) + NUMBER '1' (1, 3) (1, 4) + SLASH '/' (1, 4) (1, 5) + NUMBER '1' (1, 5) (1, 6) + PLUS '+' (1, 6) (1, 7) + NUMBER '1' (1, 7) (1, 8) + STAR '*' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + DOUBLESLASH '//' (1, 10) (1, 12) + NUMBER '1' (1, 12) (1, 13) + MINUS '-' (1, 14) (1, 15) + MINUS '-' (1, 16) (1, 17) + MINUS '-' (1, 17) (1, 18) + MINUS '-' (1, 18) (1, 19) + NUMBER '1' (1, 19) (1, 20) + DOUBLESTAR '**' (1, 20) (1, 22) + NUMBER '1' (1, 22) (1, 23) + """) + + def test_selector(self): + + self.check_tokenize("import sys, time\nx = sys.modules['time'].time()", """\ + NAME 'import' (1, 0) (1, 6) + NAME 'sys' (1, 7) (1, 10) + COMMA ',' (1, 10) (1, 11) + NAME 'time' (1, 12) (1, 16) + NEWLINE '' (1, 16) (1, 16) + NAME 'x' (2, 0) (2, 1) + EQUAL '=' (2, 2) (2, 3) + NAME 'sys' (2, 4) (2, 7) + DOT '.' (2, 7) (2, 8) + NAME 'modules' (2, 8) (2, 15) + LSQB '[' (2, 15) (2, 16) + STRING "'time'" (2, 16) (2, 22) + RSQB ']' (2, 22) (2, 23) + DOT '.' (2, 23) (2, 24) + NAME 'time' (2, 24) (2, 28) + LPAR '(' (2, 28) (2, 29) + RPAR ')' (2, 29) (2, 30) + """) + + def test_method(self): + + self.check_tokenize('@staticmethod\ndef foo(x,y): pass', """\ + AT '@' (1, 0) (1, 1) + NAME 'staticmethod' (1, 1) (1, 13) + NEWLINE '' (1, 13) (1, 13) + NAME 'def' (2, 0) (2, 3) + NAME 'foo' (2, 4) (2, 7) + LPAR '(' (2, 7) (2, 8) + NAME 'x' (2, 8) (2, 9) + COMMA ',' (2, 9) (2, 10) + NAME 'y' (2, 10) (2, 11) + RPAR ')' (2, 11) (2, 12) + COLON ':' (2, 12) (2, 13) + NAME 'pass' (2, 14) (2, 18) + """) + + def test_tabs(self): + + self.check_tokenize('@staticmethod\ndef foo(x,y): pass', """\ + AT '@' (1, 0) (1, 1) + NAME 'staticmethod' (1, 1) (1, 13) + NEWLINE '' (1, 13) (1, 13) + NAME 'def' (2, 0) (2, 3) + NAME 'foo' (2, 4) (2, 7) + LPAR '(' (2, 7) (2, 8) + NAME 'x' (2, 8) (2, 9) + COMMA ',' (2, 9) (2, 10) + NAME 'y' (2, 10) (2, 11) + RPAR ')' (2, 11) (2, 12) + COLON ':' (2, 12) (2, 13) + NAME 'pass' (2, 14) (2, 18) + """) + + def test_async(self): + + self.check_tokenize('async = 1', """\ + ASYNC 'async' (1, 0) (1, 5) + EQUAL '=' (1, 6) (1, 7) + NUMBER '1' (1, 8) (1, 9) + """) + + self.check_tokenize('a = (async = 1)', """\ + NAME 'a' (1, 0) (1, 1) + EQUAL '=' (1, 2) (1, 3) + LPAR '(' (1, 4) (1, 5) + ASYNC 'async' (1, 5) (1, 10) + EQUAL '=' (1, 11) (1, 12) + NUMBER '1' (1, 13) (1, 14) + RPAR ')' (1, 14) (1, 15) + """) + + self.check_tokenize('async()', """\ + ASYNC 'async' (1, 0) (1, 5) + LPAR '(' (1, 5) (1, 6) + RPAR ')' (1, 6) (1, 7) + """) + + self.check_tokenize('class async(Bar):pass', """\ + NAME 'class' (1, 0) (1, 5) + ASYNC 'async' (1, 6) (1, 11) + LPAR '(' (1, 11) (1, 12) + NAME 'Bar' (1, 12) (1, 15) + RPAR ')' (1, 15) (1, 16) + COLON ':' (1, 16) (1, 17) + NAME 'pass' (1, 17) (1, 21) + """) + + self.check_tokenize('class async:pass', """\ + NAME 'class' (1, 0) (1, 5) + ASYNC 'async' (1, 6) (1, 11) + COLON ':' (1, 11) (1, 12) + NAME 'pass' (1, 12) (1, 16) + """) + + self.check_tokenize('await = 1', """\ + AWAIT 'await' (1, 0) (1, 5) + EQUAL '=' (1, 6) (1, 7) + NUMBER '1' (1, 8) (1, 9) + """) + + self.check_tokenize('foo.async', """\ + NAME 'foo' (1, 0) (1, 3) + DOT '.' (1, 3) (1, 4) + ASYNC 'async' (1, 4) (1, 9) + """) + + self.check_tokenize('async for a in b: pass', """\ + ASYNC 'async' (1, 0) (1, 5) + NAME 'for' (1, 6) (1, 9) + NAME 'a' (1, 10) (1, 11) + NAME 'in' (1, 12) (1, 14) + NAME 'b' (1, 15) (1, 16) + COLON ':' (1, 16) (1, 17) + NAME 'pass' (1, 18) (1, 22) + """) + + self.check_tokenize('async with a as b: pass', """\ + ASYNC 'async' (1, 0) (1, 5) + NAME 'with' (1, 6) (1, 10) + NAME 'a' (1, 11) (1, 12) + NAME 'as' (1, 13) (1, 15) + NAME 'b' (1, 16) (1, 17) + COLON ':' (1, 17) (1, 18) + NAME 'pass' (1, 19) (1, 23) + """) + + self.check_tokenize('async.foo', """\ + ASYNC 'async' (1, 0) (1, 5) + DOT '.' (1, 5) (1, 6) + NAME 'foo' (1, 6) (1, 9) + """) + + self.check_tokenize('async', """\ + ASYNC 'async' (1, 0) (1, 5) + """) + + self.check_tokenize('async\n#comment\nawait', """\ + ASYNC 'async' (1, 0) (1, 5) + NEWLINE '' (1, 5) (1, 5) + AWAIT 'await' (3, 0) (3, 5) + """) + + self.check_tokenize('async\n...\nawait', """\ + ASYNC 'async' (1, 0) (1, 5) + NEWLINE '' (1, 5) (1, 5) + ELLIPSIS '...' (2, 0) (2, 3) + NEWLINE '' (2, 3) (2, 3) + AWAIT 'await' (3, 0) (3, 5) + """) + + self.check_tokenize('async\nawait', """\ + ASYNC 'async' (1, 0) (1, 5) + NEWLINE '' (1, 5) (1, 5) + AWAIT 'await' (2, 0) (2, 5) + """) + + self.check_tokenize('foo.async + 1', """\ + NAME 'foo' (1, 0) (1, 3) + DOT '.' (1, 3) (1, 4) + ASYNC 'async' (1, 4) (1, 9) + PLUS '+' (1, 10) (1, 11) + NUMBER '1' (1, 12) (1, 13) + """) + + self.check_tokenize('async def foo(): pass', """\ + ASYNC 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + LPAR '(' (1, 13) (1, 14) + RPAR ')' (1, 14) (1, 15) + COLON ':' (1, 15) (1, 16) + NAME 'pass' (1, 17) (1, 21) + """) + + self.check_tokenize('''\ +async def foo(): + def foo(await): + await = 1 + if 1: + await +async += 1 +''', """\ + ASYNC 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + LPAR '(' (1, 13) (1, 14) + RPAR ')' (1, 14) (1, 15) + COLON ':' (1, 15) (1, 16) + NEWLINE '' (1, 16) (1, 16) + INDENT '' (2, -1) (2, -1) + NAME 'def' (2, 2) (2, 5) + NAME 'foo' (2, 6) (2, 9) + LPAR '(' (2, 9) (2, 10) + AWAIT 'await' (2, 10) (2, 15) + RPAR ')' (2, 15) (2, 16) + COLON ':' (2, 16) (2, 17) + NEWLINE '' (2, 17) (2, 17) + INDENT '' (3, -1) (3, -1) + AWAIT 'await' (3, 4) (3, 9) + EQUAL '=' (3, 10) (3, 11) + NUMBER '1' (3, 12) (3, 13) + NEWLINE '' (3, 13) (3, 13) + DEDENT '' (4, -1) (4, -1) + NAME 'if' (4, 2) (4, 4) + NUMBER '1' (4, 5) (4, 6) + COLON ':' (4, 6) (4, 7) + NEWLINE '' (4, 7) (4, 7) + INDENT '' (5, -1) (5, -1) + AWAIT 'await' (5, 4) (5, 9) + NEWLINE '' (5, 9) (5, 9) + DEDENT '' (6, -1) (6, -1) + DEDENT '' (6, -1) (6, -1) + ASYNC 'async' (6, 0) (6, 5) + PLUSEQUAL '+=' (6, 6) (6, 8) + NUMBER '1' (6, 9) (6, 10) + NEWLINE '' (6, 10) (6, 10) + """) + + self.check_tokenize('async def foo():\n async for i in 1: pass', """\ + ASYNC 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + LPAR '(' (1, 13) (1, 14) + RPAR ')' (1, 14) (1, 15) + COLON ':' (1, 15) (1, 16) + NEWLINE '' (1, 16) (1, 16) + INDENT '' (2, -1) (2, -1) + ASYNC 'async' (2, 2) (2, 7) + NAME 'for' (2, 8) (2, 11) + NAME 'i' (2, 12) (2, 13) + NAME 'in' (2, 14) (2, 16) + NUMBER '1' (2, 17) (2, 18) + COLON ':' (2, 18) (2, 19) + NAME 'pass' (2, 20) (2, 24) + DEDENT '' (2, -1) (2, -1) + """) + + self.check_tokenize('async def foo(async): await', """\ + ASYNC 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'foo' (1, 10) (1, 13) + LPAR '(' (1, 13) (1, 14) + ASYNC 'async' (1, 14) (1, 19) + RPAR ')' (1, 19) (1, 20) + COLON ':' (1, 20) (1, 21) + AWAIT 'await' (1, 22) (1, 27) + """) + + self.check_tokenize('''\ +def f(): + + def baz(): pass + async def bar(): pass + + await = 2''', """\ + NAME 'def' (1, 0) (1, 3) + NAME 'f' (1, 4) (1, 5) + LPAR '(' (1, 5) (1, 6) + RPAR ')' (1, 6) (1, 7) + COLON ':' (1, 7) (1, 8) + NEWLINE '' (1, 8) (1, 8) + INDENT '' (3, -1) (3, -1) + NAME 'def' (3, 2) (3, 5) + NAME 'baz' (3, 6) (3, 9) + LPAR '(' (3, 9) (3, 10) + RPAR ')' (3, 10) (3, 11) + COLON ':' (3, 11) (3, 12) + NAME 'pass' (3, 13) (3, 17) + NEWLINE '' (3, 17) (3, 17) + ASYNC 'async' (4, 2) (4, 7) + NAME 'def' (4, 8) (4, 11) + NAME 'bar' (4, 12) (4, 15) + LPAR '(' (4, 15) (4, 16) + RPAR ')' (4, 16) (4, 17) + COLON ':' (4, 17) (4, 18) + NAME 'pass' (4, 19) (4, 23) + NEWLINE '' (4, 23) (4, 23) + AWAIT 'await' (6, 2) (6, 7) + EQUAL '=' (6, 8) (6, 9) + NUMBER '2' (6, 10) (6, 11) + DEDENT '' (6, -1) (6, -1) + """) + + self.check_tokenize('''\ +async def f(): + + def baz(): pass + async def bar(): pass + + await = 2''', """\ + ASYNC 'async' (1, 0) (1, 5) + NAME 'def' (1, 6) (1, 9) + NAME 'f' (1, 10) (1, 11) + LPAR '(' (1, 11) (1, 12) + RPAR ')' (1, 12) (1, 13) + COLON ':' (1, 13) (1, 14) + NEWLINE '' (1, 14) (1, 14) + INDENT '' (3, -1) (3, -1) + NAME 'def' (3, 2) (3, 5) + NAME 'baz' (3, 6) (3, 9) + LPAR '(' (3, 9) (3, 10) + RPAR ')' (3, 10) (3, 11) + COLON ':' (3, 11) (3, 12) + NAME 'pass' (3, 13) (3, 17) + NEWLINE '' (3, 17) (3, 17) + ASYNC 'async' (4, 2) (4, 7) + NAME 'def' (4, 8) (4, 11) + NAME 'bar' (4, 12) (4, 15) + LPAR '(' (4, 15) (4, 16) + RPAR ')' (4, 16) (4, 17) + COLON ':' (4, 17) (4, 18) + NAME 'pass' (4, 19) (4, 23) + NEWLINE '' (4, 23) (4, 23) + AWAIT 'await' (6, 2) (6, 7) + EQUAL '=' (6, 8) (6, 9) + NUMBER '2' (6, 10) (6, 11) + DEDENT '' (6, -1) (6, -1) + """) + + def test_unicode(self): + + self.check_tokenize("Örter = u'places'\ngrün = U'green'", """\ + NAME 'Örter' (1, 0) (1, 6) + EQUAL '=' (1, 7) (1, 8) + STRING "u'places'" (1, 9) (1, 18) + NEWLINE '' (1, 18) (1, 18) + NAME 'grün' (2, 0) (2, 5) + EQUAL '=' (2, 6) (2, 7) + STRING "U'green'" (2, 8) (2, 16) + """) + + def test_invalid_syntax(self): + def get_tokens(string): + return list(_generate_tokens_from_c_tokenizer(string)) + + self.assertRaises(SyntaxError, get_tokens, "(1+2]") + self.assertRaises(SyntaxError, get_tokens, "(1+2}") + self.assertRaises(SyntaxError, get_tokens, "{1+2]") + + self.assertRaises(SyntaxError, get_tokens, "1_") + self.assertRaises(SyntaxError, get_tokens, "1.2_") + self.assertRaises(SyntaxError, get_tokens, "1e2_") + self.assertRaises(SyntaxError, get_tokens, "1e+") + + self.assertRaises(SyntaxError, get_tokens, "\xa0") + self.assertRaises(SyntaxError, get_tokens, "€") + + self.assertRaises(SyntaxError, get_tokens, "0b12") + self.assertRaises(SyntaxError, get_tokens, "0b1_2") + self.assertRaises(SyntaxError, get_tokens, "0b2") + self.assertRaises(SyntaxError, get_tokens, "0b1_") + self.assertRaises(SyntaxError, get_tokens, "0b") + self.assertRaises(SyntaxError, get_tokens, "0o18") + self.assertRaises(SyntaxError, get_tokens, "0o1_8") + self.assertRaises(SyntaxError, get_tokens, "0o8") + self.assertRaises(SyntaxError, get_tokens, "0o1_") + self.assertRaises(SyntaxError, get_tokens, "0o") + self.assertRaises(SyntaxError, get_tokens, "0x1_") + self.assertRaises(SyntaxError, get_tokens, "0x") + self.assertRaises(SyntaxError, get_tokens, "1_") + self.assertRaises(SyntaxError, get_tokens, "012") + self.assertRaises(SyntaxError, get_tokens, "1.2_") + self.assertRaises(SyntaxError, get_tokens, "1e2_") + self.assertRaises(SyntaxError, get_tokens, "1e+") + + self.assertRaises(SyntaxError, get_tokens, "'sdfsdf") + self.assertRaises(SyntaxError, get_tokens, "'''sdfsdf''") + + self.assertRaises(SyntaxError, get_tokens, "("*1000+"a"+")"*1000) + self.assertRaises(SyntaxError, get_tokens, "]") + + def test_max_indent(self): + MAXINDENT = 100 + + def generate_source(indents): + source = ''.join((' ' * x) + 'if True:\n' for x in range(indents)) + source += ' ' * indents + 'pass\n' + return source + + valid = generate_source(MAXINDENT - 1) + tokens = list(_generate_tokens_from_c_tokenizer(valid)) + self.assertEqual(tokens[-1].type, DEDENT) + compile(valid, "", "exec") + + invalid = generate_source(MAXINDENT) + tokens = list(_generate_tokens_from_c_tokenizer(invalid)) + self.assertEqual(tokens[-1].type, NEWLINE) + self.assertRaises( + IndentationError, compile, invalid, "", "exec" + ) + + def test_continuation_lines_indentation(self): + def get_tokens(string): + return [(kind, string) for (kind, string, *_) in _generate_tokens_from_c_tokenizer(string)] + + code = dedent(""" + def fib(n): + \\ + '''Print a Fibonacci series up to n.''' + \\ + a, b = 0, 1 + """) + + self.check_tokenize(code, """\ + NAME 'def' (2, 0) (2, 3) + NAME 'fib' (2, 4) (2, 7) + LPAR '(' (2, 7) (2, 8) + NAME 'n' (2, 8) (2, 9) + RPAR ')' (2, 9) (2, 10) + COLON ':' (2, 10) (2, 11) + NEWLINE '' (2, 11) (2, 11) + INDENT '' (4, -1) (4, -1) + STRING "'''Print a Fibonacci series up to n.'''" (4, 0) (4, 39) + NEWLINE '' (4, 39) (4, 39) + NAME 'a' (6, 0) (6, 1) + COMMA ',' (6, 1) (6, 2) + NAME 'b' (6, 3) (6, 4) + EQUAL '=' (6, 5) (6, 6) + NUMBER '0' (6, 7) (6, 8) + COMMA ',' (6, 8) (6, 9) + NUMBER '1' (6, 10) (6, 11) + NEWLINE '' (6, 11) (6, 11) + DEDENT '' (6, -1) (6, -1) + """) + + code_no_cont = dedent(""" + def fib(n): + '''Print a Fibonacci series up to n.''' + a, b = 0, 1 + """) + + self.assertEqual(get_tokens(code), get_tokens(code_no_cont)) + + code = dedent(""" + pass + \\ + + pass + """) + + self.check_tokenize(code, """\ + NAME 'pass' (2, 0) (2, 4) + NEWLINE '' (2, 4) (2, 4) + NAME 'pass' (5, 0) (5, 4) + NEWLINE '' (5, 4) (5, 4) + """) + + code_no_cont = dedent(""" + pass + pass + """) + + self.assertEqual(get_tokens(code), get_tokens(code_no_cont)) + + code = dedent(""" + if x: + y = 1 + \\ + \\ + \\ + \\ + foo = 1 + """) + + self.check_tokenize(code, """\ + NAME 'if' (2, 0) (2, 2) + NAME 'x' (2, 3) (2, 4) + COLON ':' (2, 4) (2, 5) + NEWLINE '' (2, 5) (2, 5) + INDENT '' (3, -1) (3, -1) + NAME 'y' (3, 4) (3, 5) + EQUAL '=' (3, 6) (3, 7) + NUMBER '1' (3, 8) (3, 9) + NEWLINE '' (3, 9) (3, 9) + NAME 'foo' (8, 4) (8, 7) + EQUAL '=' (8, 8) (8, 9) + NUMBER '1' (8, 10) (8, 11) + NEWLINE '' (8, 11) (8, 11) + DEDENT '' (8, -1) (8, -1) + """) + + code_no_cont = dedent(""" + if x: + y = 1 + foo = 1 + """) + + self.assertEqual(get_tokens(code), get_tokens(code_no_cont)) + + +class CTokenizerBufferTests(unittest.TestCase): + def test_newline_at_the_end_of_buffer(self): + # See issue 99581: Make sure that if we need to add a new line at the + # end of the buffer, we have enough space in the buffer, specially when + # the current line is as long as the buffer space available. + test_script = f"""\ + #coding: latin-1 + #{"a"*10000} + #{"a"*10002}""" + with os_helper.temp_dir() as temp_dir: + file_name = make_script(temp_dir, 'foo', test_script) + run_test_script(file_name) + + +if __name__ == "__main__": + unittest.main()