bpo-36541: Add lib2to3 grammar PEP-570 pos-only arg parsing (GH-23759)

Add positional only args support to lib2to3 pgen2.

This adds 3.8's PEP-570 support to lib2to3's pgen2.  lib2to3, while
being deprecated is still used by things to parse all versions of Python
code today.  We need it to support parsing modern 3.8 and 3.9 constructs.

Also add tests for complex *expr and **expr's.
(cherry picked from commit 42c9f0fd0a5e67d4ae0022bfd7370cb9725a5b01)

Co-authored-by: Gregory P. Smith <greg@krypto.org>

diff --git a/Lib/lib2to3/Grammar.txt b/Lib/lib2to3/Grammar.txt
index 8ce7fd8a89da67dade690e8c993c1d66d090bd0a..f6c2fc5b1f323153c4b2eaa7ab9ddaa93eb73dd3 100644 (file)
--- a/Lib/lib2to3/Grammar.txt
+++ b/Lib/lib2to3/Grammar.txt
@@ -18,15 +18,55 @@ decorated: decorators (classdef | funcdef | async_funcdef)
 async_funcdef: ASYNC funcdef
 funcdef: 'def' NAME parameters ['->' test] ':' suite
 parameters: '(' [typedargslist] ')'
-typedargslist: ((tfpdef ['=' test] ',')*
-                ('*' [tname] (',' tname ['=' test])* [',' ['**' tname [',']]] | '**' tname [','])
-                | tfpdef ['=' test] (',' tfpdef ['=' test])* [','])
+
+# The following definition for typedarglist is equivalent to this set of rules:
+#
+#     arguments = argument (',' argument)*
+#     argument = tfpdef ['=' test]
+#     kwargs = '**' tname [',']
+#     args = '*' [tname]
+#     kwonly_kwargs = (',' argument)* [',' [kwargs]]
+#     args_kwonly_kwargs = args kwonly_kwargs | kwargs
+#     poskeyword_args_kwonly_kwargs = arguments [',' [args_kwonly_kwargs]]
+#     typedargslist_no_posonly  = poskeyword_args_kwonly_kwargs | args_kwonly_kwargs
+#     typedarglist = arguments ',' '/' [',' [typedargslist_no_posonly]])|(typedargslist_no_posonly)"
+#
+# It needs to be fully expanded to allow our LL(1) parser to work on it.
+
+typedargslist: tfpdef ['=' test] (',' tfpdef ['=' test])* ',' '/' [
+                     ',' [((tfpdef ['=' test] ',')* ('*' [tname] (',' tname ['=' test])*
+                            [',' ['**' tname [',']]] | '**' tname [','])
+                     | tfpdef ['=' test] (',' tfpdef ['=' test])* [','])]
+                ] | ((tfpdef ['=' test] ',')* ('*' [tname] (',' tname ['=' test])*
+                     [',' ['**' tname [',']]] | '**' tname [','])
+                     | tfpdef ['=' test] (',' tfpdef ['=' test])* [','])
+
 tname: NAME [':' test]
 tfpdef: tname | '(' tfplist ')'
 tfplist: tfpdef (',' tfpdef)* [',']
-varargslist: ((vfpdef ['=' test] ',')*
-              ('*' [vname] (',' vname ['=' test])*  [',' ['**' vname [',']]] | '**' vname [','])
-              | vfpdef ['=' test] (',' vfpdef ['=' test])* [','])
+
+# The following definition for varargslist is equivalent to this set of rules:
+#
+#     arguments = argument (',' argument )*
+#     argument = vfpdef ['=' test]
+#     kwargs = '**' vname [',']
+#     args = '*' [vname]
+#     kwonly_kwargs = (',' argument )* [',' [kwargs]]
+#     args_kwonly_kwargs = args kwonly_kwargs | kwargs
+#     poskeyword_args_kwonly_kwargs = arguments [',' [args_kwonly_kwargs]]
+#     vararglist_no_posonly = poskeyword_args_kwonly_kwargs | args_kwonly_kwargs
+#     varargslist = arguments ',' '/' [','[(vararglist_no_posonly)]] | (vararglist_no_posonly)
+#
+# It needs to be fully expanded to allow our LL(1) parser to work on it.
+
+varargslist: vfpdef ['=' test ](',' vfpdef ['=' test])* ',' '/' [',' [
+                     ((vfpdef ['=' test] ',')* ('*' [vname] (',' vname ['=' test])*
+                            [',' ['**' vname [',']]] | '**' vname [','])
+                            | vfpdef ['=' test] (',' vfpdef ['=' test])* [','])
+                     ]] | ((vfpdef ['=' test] ',')*
+                     ('*' [vname] (',' vname ['=' test])*  [',' ['**' vname [',']]]| '**' vname [','])
+                     | vfpdef ['=' test] (',' vfpdef ['=' test])* [','])
+
 vname: NAME
 vfpdef: vname | '(' vfplist ')'
 vfplist: vfpdef (',' vfpdef)* [',']

diff --git a/Lib/lib2to3/tests/test_parser.py b/Lib/lib2to3/tests/test_parser.py
index 3a0e7f435e6d78754066087fa5ca23b85e553642..aafa09c3069ae53457fd8ab5307cf7f496479adf 100644 (file)
--- a/Lib/lib2to3/tests/test_parser.py
+++ b/Lib/lib2to3/tests/test_parser.py
@@ -272,6 +272,12 @@ class TestUnpackingGeneralizations(GrammarTest):
     def test_dict_display_2(self):
         self.validate("""{**{}, 3:4, **{5:6, 7:8}}""")
 
+    def test_complex_star_expression(self):
+        self.validate("func(* [] or [1])")
+
+    def test_complex_double_star_expression(self):
+        self.validate("func(**{1: 3} if False else {x: x for x in range(3)})")
+
     def test_argument_unpacking_1(self):
         self.validate("""f(a, *b, *c, d)""")
 
@@ -630,6 +636,7 @@ class TestLiterals(GrammarTest):
 
 
 class TestNamedAssignments(GrammarTest):
+    """Also known as the walrus operator."""
 
     def test_named_assignment_if(self):
         driver.parse_string("if f := x(): pass\n")
@@ -644,6 +651,30 @@ class TestNamedAssignments(GrammarTest):
         driver.parse_string("[(lastNum := num) == 1 for num in [1, 2, 3]]\n")
 
 
+class TestPositionalOnlyArgs(GrammarTest):
+
+    def test_one_pos_only_arg(self):
+        driver.parse_string("def one_pos_only_arg(a, /): pass\n")
+
+    def test_all_markers(self):
+        driver.parse_string(
+                "def all_markers(a, b=2, /, c, d=4, *, e=5, f): pass\n")
+
+    def test_all_with_args_and_kwargs(self):
+        driver.parse_string(
+                """def all_markers_with_args_and_kwargs(
+                           aa, b, /, _cc, d, *args, e, f_f, **kwargs,
+                   ):
+                       pass\n""")
+
+    def test_lambda_soup(self):
+        driver.parse_string(
+                "lambda a, b, /, c, d, *args, e, f, **kw: kw\n")
+
+    def test_only_positional_or_keyword(self):
+        driver.parse_string("def func(a,b,/,*,g,e=3): pass\n")
+
+
 class TestPickleableException(unittest.TestCase):
     def test_ParseError(self):
         err = ParseError('msg', 2, None, (1, 'context'))

diff --git a/Misc/NEWS.d/next/Library/2020-12-14-08-23-57.bpo-36541.qdEtZv.rst b/Misc/NEWS.d/next/Library/2020-12-14-08-23-57.bpo-36541.qdEtZv.rst
new file mode 100644 (file)
index 0000000..5678d8c
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2020-12-14-08-23-57.bpo-36541.qdEtZv.rst
@@ -0,0 +1,2 @@
+Fixed lib2to3.pgen2 to be able to parse PEP-570 positional only argument
+syntax.