bpo-35975: Support parsing earlier minor versions of Python 3 (GH-12086)

This adds a `feature_version` flag to `ast.parse()` (documented) and `compile()` (hidden) that allow tweaking the parser to support older versions of the grammar. In particular if `feature_version` is 5 or 6, the hacks for the `async` and `await` keyword from PEP 492 are reinstated. (For 7 or higher, these are unconditionally treated as keywords, but they are still special tokens rather than `NAME` tokens that the parser driver recognizes.)



https://bugs.python.org/issue35975

Doc/library/ast.rst

@@ -126,7 +126,7 @@ The abstract grammar is currently defined as follows:
 Apart from the node classes, the :mod:`ast` module defines these utility functions
 and classes for traversing abstract syntax trees:
 
-.. function:: parse(source, filename='<unknown>', mode='exec', *, type_comments=False)
+.. function:: parse(source, filename='<unknown>', mode='exec', *, type_comments=False, feature_version=-1)
 
    Parse the source into an AST node.  Equivalent to ``compile(source,
    filename, mode, ast.PyCF_ONLY_AST)``.
@@ -145,13 +145,19 @@ and classes for traversing abstract syntax trees:
    modified to correspond to :pep:`484` "signature type comments",
    e.g. ``(str, int) -> List[str]``.
 
+   Also, setting ``feature_version`` to the minor version of an
+   earlier Python 3 version will attempt to parse using that version's
+   grammar.  For example, setting ``feature_version=4`` will allow
+   the use of ``async`` and ``await`` as variable names.  The lowest
+   supported value is 4; the highest is ``sys.version_info[1]``.
+
    .. warning::
       It is possible to crash the Python interpreter with a
       sufficiently large/complex string due to stack depth limitations
       in Python's AST compiler.
 
    .. versionchanged:: 3.8
-      Added ``type_comments=True`` and ``mode='func_type'``.
+      Added ``type_comments``, ``mode='func_type'`` and ``feature_version``.
 
 
 .. function:: literal_eval(node_or_string)

Doc/library/token-list.inc

@@ -203,6 +203,10 @@
 
 .. data:: OP
 
+.. data:: AWAIT
+
+.. data:: ASYNC
+
 .. data:: TYPE_IGNORE
 
 .. data:: TYPE_COMMENT

Doc/library/token.rst

@@ -88,3 +88,6 @@ the :mod:`tokenize` module.
 
 .. versionchanged:: 3.8
    Added :data:`TYPE_COMMENT`.
+   Added :data:`AWAIT` and :data:`ASYNC` tokens back (they're needed
+   to support parsing older Python versions for :func:`ast.parse` with
+   ``feature_version`` set to 6 or lower).

Grammar/Grammar

@@ -18,7 +18,7 @@ decorator: '@' dotted_name [ '(' [arglist] ')' ] NEWLINE
 decorators: decorator+
 decorated: decorators (classdef | funcdef | async_funcdef)
 
-async_funcdef: 'async' funcdef
+async_funcdef: ASYNC funcdef
 funcdef: 'def' NAME parameters ['->' test] ':' [TYPE_COMMENT] func_body_suite
 
 parameters: '(' [typedargslist] ')'
@@ -70,7 +70,7 @@ nonlocal_stmt: 'nonlocal' NAME (',' NAME)*
 assert_stmt: 'assert' test [',' test]
 
 compound_stmt: if_stmt | while_stmt | for_stmt | try_stmt | with_stmt | funcdef | classdef | decorated | async_stmt
-async_stmt: 'async' (funcdef | with_stmt | for_stmt)
+async_stmt: ASYNC (funcdef | with_stmt | for_stmt)
 if_stmt: 'if' namedexpr_test ':' suite ('elif' namedexpr_test ':' suite)* ['else' ':' suite]
 while_stmt: 'while' namedexpr_test ':' suite ['else' ':' suite]
 for_stmt: 'for' exprlist 'in' testlist ':' [TYPE_COMMENT] suite ['else' ':' suite]
@@ -106,7 +106,7 @@ arith_expr: term (('+'|'-') term)*
 term: factor (('*'|'@'|'/'|'%'|'//') factor)*
 factor: ('+'|'-'|'~') factor | power
 power: atom_expr ['**' factor]
-atom_expr: ['await'] atom trailer*
+atom_expr: [AWAIT] atom trailer*
 atom: ('(' [yield_expr|testlist_comp] ')' |
        '[' [testlist_comp] ']' |
        '{' [dictorsetmaker] '}' |
@@ -144,7 +144,7 @@ argument: ( test [comp_for] |
 
 comp_iter: comp_for | comp_if
 sync_comp_for: 'for' exprlist 'in' or_test [comp_iter]
-comp_for: ['async'] sync_comp_for
+comp_for: [ASYNC] sync_comp_for
 comp_if: 'if' test_nocond [comp_iter]
 
 # not used in grammar, but may appear in "node" passed from Parser to Compiler

Grammar/Tokens

@@ -55,6 +55,8 @@ ELLIPSIS                '...'
 COLONEQUAL              ':='
 
 OP
+AWAIT
+ASYNC
 TYPE_IGNORE
 TYPE_COMMENT
 ERRORTOKEN

Include/Python-ast.h

@@ -703,6 +703,7 @@ type_ignore_ty _Py_TypeIgnore(int lineno, PyArena *arena);
 
 PyObject* PyAST_mod2obj(mod_ty t);
 mod_ty PyAST_obj2mod(PyObject* ast, PyArena* arena, int mode);
+mod_ty PyAST_obj2mod_ex(PyObject* ast, PyArena* arena, int mode, int feature_version);
 int PyAST_Check(PyObject* obj);
 
 #ifdef __cplusplus

Include/compile.h

@@ -27,6 +27,7 @@ PyAPI_FUNC(PyCodeObject *) PyNode_Compile(struct _node *, const char *);
 #ifndef Py_LIMITED_API
 typedef struct {
     int cf_flags;  /* bitmask of CO_xxx flags relevant to future */
+    int cf_feature_version;  /* minor Python version (PyCF_ONLY_AST) */
 } PyCompilerFlags;
 #endif
 

Include/parsetok.h

@@ -35,6 +35,7 @@ typedef struct {
 #define PyPARSE_IGNORE_COOKIE 0x0010
 #define PyPARSE_BARRY_AS_BDFL 0x0020
 #define PyPARSE_TYPE_COMMENTS 0x0040
+#define PyPARSE_ASYNC_HACKS   0x0080
 
 PyAPI_FUNC(node *) PyParser_ParseString(const char *, grammar *, int,
                                               perrdetail *);

Include/token.h

@@ -65,10 +65,12 @@ extern "C" {
 #define ELLIPSIS        52
 #define COLONEQUAL      53
 #define OP              54
-#define TYPE_IGNORE     55
-#define TYPE_COMMENT    56
-#define ERRORTOKEN      57
-#define N_TOKENS        61
+#define AWAIT           55
+#define ASYNC           56
+#define TYPE_IGNORE     57
+#define TYPE_COMMENT    58
+#define ERRORTOKEN      59
+#define N_TOKENS        63
 #define NT_OFFSET       256
 
 /* Special definitions for cooperation with parser */

Lib/ast.py

@@ -27,7 +27,8 @@
 from _ast import *
 
 
-def parse(source, filename='<unknown>', mode='exec', *, type_comments=False):
+def parse(source, filename='<unknown>', mode='exec', *,
+          type_comments=False, feature_version=-1):
     """
     Parse the source into an AST node.
     Equivalent to compile(source, filename, mode, PyCF_ONLY_AST).
@@ -36,7 +37,8 @@ def parse(source, filename='<unknown>', mode='exec', *, type_comments=False):
     flags = PyCF_ONLY_AST
     if type_comments:
         flags |= PyCF_TYPE_COMMENTS
-    return compile(source, filename, mode, flags)
+    return compile(source, filename, mode, flags,
+                   feature_version=feature_version)
 
 
 def literal_eval(node_or_string):

Lib/keyword.py

@@ -20,8 +20,6 @@ kwlist = [
         'and',
         'as',
         'assert',
-        'async',
-        'await',
         'break',
         'class',
         'continue',
@@ -52,6 +50,10 @@ kwlist = [
 #--end keywords--
         ]
 
+kwlist.append('async')
+kwlist.append('await')
+kwlist.sort()
+
 iskeyword = frozenset(kwlist).__contains__
 
 def main():

Lib/test/test_parser.py

@@ -916,7 +916,7 @@ class STObjectTestCase(unittest.TestCase):
                 return (n + 3) & ~3
             return 1 << (n - 1).bit_length()
 
-        basesize = support.calcobjsize('Pii')
+        basesize = support.calcobjsize('Piii')
         nodesize = struct.calcsize('hP3iP0h2i')
         def sizeofchildren(node):
             if node is None:

Lib/test/test_type_comments.py

 import ast
+import sys
 import unittest
 
 
@@ -20,6 +21,29 @@ async def bar():  # type: () -> int
     return await bar()
 """
 
+asyncvar = """\
+async = 12
+await = 13
+"""
+
+asynccomp = """\
+async def foo(xs):
+    [x async for x in xs]
+"""
+
+matmul = """\
+a = b @ c
+"""
+
+fstring = """\
+a = 42
+f"{a}"
+"""
+
+underscorednumber = """\
+a = 42_42_42
+"""
+
 redundantdef = """\
 def foo():  # type: () -> int
     # type: () -> str
@@ -155,80 +179,117 @@ def favk(
 
 class TypeCommentTests(unittest.TestCase):
 
-    def parse(self, source):
-        return ast.parse(source, type_comments=True)
+    lowest = 4  # Lowest minor version supported
+    highest = sys.version_info[1]  # Highest minor version
+
+    def parse(self, source, feature_version=highest):
+        return ast.parse(source, type_comments=True,
+                         feature_version=feature_version)
+
+    def parse_all(self, source, minver=lowest, maxver=highest, expected_regex=""):
+        for feature_version in range(self.lowest, self.highest + 1):
+            if minver <= feature_version <= maxver:
+                try:
+                    yield self.parse(source, feature_version)
+                except SyntaxError as err:
+                    raise SyntaxError(str(err) + f" feature_version={feature_version}")
+            else:
+                with self.assertRaisesRegex(SyntaxError, expected_regex,
+                                            msg=f"feature_version={feature_version}"):
+                    self.parse(source, feature_version)
 
     def classic_parse(self, source):
         return ast.parse(source)
 
     def test_funcdef(self):
-        tree = self.parse(funcdef)
-        self.assertEqual(tree.body[0].type_comment, "() -> int")
-        self.assertEqual(tree.body[1].type_comment, "() -> None")
+        for tree in self.parse_all(funcdef):
+            self.assertEqual(tree.body[0].type_comment, "() -> int")
+            self.assertEqual(tree.body[1].type_comment, "() -> None")
         tree = self.classic_parse(funcdef)
         self.assertEqual(tree.body[0].type_comment, None)
         self.assertEqual(tree.body[1].type_comment, None)
 
     def test_asyncdef(self):
-        tree = self.parse(asyncdef)
-        self.assertEqual(tree.body[0].type_comment, "() -> int")
-        self.assertEqual(tree.body[1].type_comment, "() -> int")
+        for tree in self.parse_all(asyncdef, minver=5):
+            self.assertEqual(tree.body[0].type_comment, "() -> int")
+            self.assertEqual(tree.body[1].type_comment, "() -> int")
         tree = self.classic_parse(asyncdef)
         self.assertEqual(tree.body[0].type_comment, None)
         self.assertEqual(tree.body[1].type_comment, None)
 
+    def test_asyncvar(self):
+        for tree in self.parse_all(asyncvar, maxver=6):
+            pass
+
+    def test_asynccomp(self):
+        for tree in self.parse_all(asynccomp, minver=6):
+            pass
+
+    def test_matmul(self):
+        for tree in self.parse_all(matmul, minver=5):
+            pass
+
+    def test_fstring(self):
+        for tree in self.parse_all(fstring, minver=6):
+            pass
+
+    def test_underscorednumber(self):
+        for tree in self.parse_all(underscorednumber, minver=6):
+            pass
+
     def test_redundantdef(self):
-        with self.assertRaisesRegex(SyntaxError, "^Cannot have two type comments on def"):
-            tree = self.parse(redundantdef)
+        for tree in self.parse_all(redundantdef, maxver=0,
+                                expected_regex="^Cannot have two type comments on def"):
+            pass
 
     def test_nonasciidef(self):
-        tree = self.parse(nonasciidef)
-        self.assertEqual(tree.body[0].type_comment, "() -> àçčéñt")
+        for tree in self.parse_all(nonasciidef):
+            self.assertEqual(tree.body[0].type_comment, "() -> àçčéñt")
 
     def test_forstmt(self):
-        tree = self.parse(forstmt)
-        self.assertEqual(tree.body[0].type_comment, "int")
+        for tree in self.parse_all(forstmt):
+            self.assertEqual(tree.body[0].type_comment, "int")
         tree = self.classic_parse(forstmt)
         self.assertEqual(tree.body[0].type_comment, None)
 
     def test_withstmt(self):
-        tree = self.parse(withstmt)
-        self.assertEqual(tree.body[0].type_comment, "int")
+        for tree in self.parse_all(withstmt):
+            self.assertEqual(tree.body[0].type_comment, "int")
         tree = self.classic_parse(withstmt)
         self.assertEqual(tree.body[0].type_comment, None)
 
     def test_vardecl(self):
-        tree = self.parse(vardecl)
-        self.assertEqual(tree.body[0].type_comment, "int")
+        for tree in self.parse_all(vardecl):
+            self.assertEqual(tree.body[0].type_comment, "int")
         tree = self.classic_parse(vardecl)
         self.assertEqual(tree.body[0].type_comment, None)
 
     def test_ignores(self):
-        tree = self.parse(ignores)
-        self.assertEqual([ti.lineno for ti in tree.type_ignores], [2, 5])
+        for tree in self.parse_all(ignores):
+            self.assertEqual([ti.lineno for ti in tree.type_ignores], [2, 5])
         tree = self.classic_parse(ignores)
         self.assertEqual(tree.type_ignores, [])
 
     def test_longargs(self):
-        tree = self.parse(longargs)
-        for t in tree.body:
-            # The expected args are encoded in the function name
-            todo = set(t.name[1:])
-            self.assertEqual(len(t.args.args),
-                             len(todo) - bool(t.args.vararg) - bool(t.args.kwarg))
-            self.assertTrue(t.name.startswith('f'), t.name)
-            for c in t.name[1:]:
-                todo.remove(c)
-                if c == 'v':
-                    arg = t.args.vararg
-                elif c == 'k':
-                    arg = t.args.kwarg
-                else:
-                    assert 0 <= ord(c) - ord('a') < len(t.args.args)
-                    arg = t.args.args[ord(c) - ord('a')]
-                self.assertEqual(arg.arg, c)  # That's the argument name
-                self.assertEqual(arg.type_comment, arg.arg.upper())
-            assert not todo
+        for tree in self.parse_all(longargs):
+            for t in tree.body:
+                # The expected args are encoded in the function name
+                todo = set(t.name[1:])
+                self.assertEqual(len(t.args.args),
+                                 len(todo) - bool(t.args.vararg) - bool(t.args.kwarg))
+                self.assertTrue(t.name.startswith('f'), t.name)
+                for c in t.name[1:]:
+                    todo.remove(c)
+                    if c == 'v':
+                        arg = t.args.vararg
+                    elif c == 'k':
+                        arg = t.args.kwarg
+                    else:
+                        assert 0 <= ord(c) - ord('a') < len(t.args.args)
+                        arg = t.args.args[ord(c) - ord('a')]
+                    self.assertEqual(arg.arg, c)  # That's the argument name
+                    self.assertEqual(arg.type_comment, arg.arg.upper())
+                assert not todo
         tree = self.classic_parse(longargs)
         for t in tree.body:
             for arg in t.args.args + [t.args.vararg, t.args.kwarg]:
@@ -247,8 +308,8 @@ class TypeCommentTests(unittest.TestCase):
 
         def check_both_ways(source):
             ast.parse(source, type_comments=False)
-            with self.assertRaises(SyntaxError):
-                ast.parse(source, type_comments=True)
+            for tree in self.parse_all(source, maxver=0):
+                pass
 
         check_both_ways("pass  # type: int\n")
         check_both_ways("foo()  # type: int\n")

Lib/token.py

@@ -58,14 +58,16 @@ RARROW = 51
 ELLIPSIS = 52
 COLONEQUAL = 53
 OP = 54
-TYPE_IGNORE = 55
-TYPE_COMMENT = 56
+AWAIT = 55
+ASYNC = 56
+TYPE_IGNORE = 57
+TYPE_COMMENT = 58
 # These aren't used by the C tokenizer but are needed for tokenize.py
-ERRORTOKEN = 57
-COMMENT = 58
-NL = 59
-ENCODING = 60
-N_TOKENS = 61
+ERRORTOKEN = 59
+COMMENT = 60
+NL = 61
+ENCODING = 62
+N_TOKENS = 63
 # Special definitions for cooperation with parser
 NT_OFFSET = 256
 

Misc/NEWS.d/next/Core and Builtins/2019-02-27-16-49-08.bpo-35975.IescLY.rst

+Add a ``feature_version`` flag to ``ast.parse()`` (documented) and
+``compile()`` (hidden) that allows tweaking the parser to support older
+versions of the grammar. In particular, if ``feature_version`` is 5 or 6,
+the hacks for the ``async`` and ``await`` keyword from PEP 492 are
+reinstated. (For 7 or higher, these are unconditionally treated as keywords,
+but they are still special tokens rather than ``NAME`` tokens that the
+parser driver recognizes.)

Modules/main.c

@@ -799,7 +799,7 @@ pymain_run_python(PyInterpreterState *interp, int *exitcode)
         Py_DECREF(path0);
     }
 
-    PyCompilerFlags cf = {.cf_flags = 0};
+    PyCompilerFlags cf = {.cf_flags = 0, .cf_feature_version = PY_MINOR_VERSION};
 
     pymain_header(config);
     pymain_import_readline(config);

Modules/parsermodule.c

@@ -341,6 +341,7 @@ parser_newstobject(node *st, int type)
         o->st_node = st;
         o->st_type = type;
         o->st_flags.cf_flags = 0;
+        o->st_flags.cf_feature_version = PY_MINOR_VERSION;
     }
     else {
         PyNode_Free(st);
@@ -584,8 +585,10 @@ parser_do_parse(PyObject *args, PyObject *kw, const char *argspec, int type)
 
         if (n) {
             res = parser_newstobject(n, type);
-            if (res)
+            if (res) {
                 ((PyST_Object *)res)->st_flags.cf_flags = flags & PyCF_MASK;
+                ((PyST_Object *)res)->st_flags.cf_feature_version = PY_MINOR_VERSION;
+            }
         }
         else {
             PyParser_SetError(&err);

Parser/asdl_c.py

@@ -1188,6 +1188,11 @@ PyObject* PyAST_mod2obj(mod_ty t)
 
 /* mode is 0 for "exec", 1 for "eval" and 2 for "single" input */
 mod_ty PyAST_obj2mod(PyObject* ast, PyArena* arena, int mode)
+{
+    return PyAST_obj2mod_ex(ast, arena, mode, PY_MINOR_VERSION);
+}
+
+mod_ty PyAST_obj2mod_ex(PyObject* ast, PyArena* arena, int mode, int feature_version)
 {
     mod_ty res;
     PyObject *req_type[3];
@@ -1269,6 +1274,7 @@ def main(srcfile, dump_module=False):
             f.write("\n")
             f.write("PyObject* PyAST_mod2obj(mod_ty t);\n")
             f.write("mod_ty PyAST_obj2mod(PyObject* ast, PyArena* arena, int mode);\n")
+            f.write("mod_ty PyAST_obj2mod_ex(PyObject* ast, PyArena* arena, int mode, int feature_version);\n")
             f.write("int PyAST_Check(PyObject* obj);\n")
             f.write('\n')
             f.write('#ifdef __cplusplus\n')

Parser/parsetok.c

@@ -101,6 +101,8 @@ PyParser_ParseStringObject(const char *s, PyObject *filename,
 
     Py_INCREF(err_ret->filename);
     tok->filename = err_ret->filename;
+    if (*flags & PyPARSE_ASYNC_HACKS)
+        tok->async_hacks = 1;
     return parsetok(tok, g, start, err_ret, flags);
 }
 

Parser/token.c

@@ -61,6 +61,8 @@ const char * const _PyParser_TokenNames[] = {
     "ELLIPSIS",
     "COLONEQUAL",
     "OP",
+    "AWAIT",
+    "ASYNC",
     "TYPE_IGNORE",
     "TYPE_COMMENT",
     "<ERRORTOKEN>",

Parser/tokenizer.c

@@ -84,6 +84,11 @@ tok_new(void)
     tok->decoding_buffer = NULL;
     tok->type_comments = 0;
 
+    tok->async_hacks = 0;
+    tok->async_def = 0;
+    tok->async_def_indent = 0;
+    tok->async_def_nl = 0;
+
     return tok;
 }
 
@@ -1196,6 +1201,31 @@ tok_get(struct tok_state *tok, char **p_start, char **p_end)
         }
     }
 
+    /* Peek ahead at the next character */
+    c = tok_nextc(tok);
+    tok_backup(tok, c);
+    /* Check if we are closing an async function */
+    if (tok->async_def
+        && !blankline
+        /* Due to some implementation artifacts of type comments,
+         * a TYPE_COMMENT at the start of a function won't set an
+         * indentation level and it will produce a NEWLINE after it.
+         * To avoid spuriously ending an async function due to this,
+         * wait until we have some non-newline char in front of us. */
+        && c != '\n'
+        && tok->level == 0
+        /* There was a NEWLINE after ASYNC DEF,
+           so we're past the signature. */
+        && tok->async_def_nl
+        /* Current indentation level is less than where
+           the async function was defined */
+        && tok->async_def_indent >= tok->indent)
+    {
+        tok->async_def = 0;
+        tok->async_def_indent = 0;
+        tok->async_def_nl = 0;
+    }
+
  again:
     tok->start = NULL;
     /* Skip spaces */
@@ -1310,6 +1340,50 @@ tok_get(struct tok_state *tok, char **p_start, char **p_end)
         *p_start = tok->start;
         *p_end = tok->cur;
 
+        /* async/await parsing block. */
+        if (tok->cur - tok->start == 5 && tok->start[0] == 'a') {
+            /* May be an 'async' or 'await' token.  For Python 3.7 or
+               later we recognize them unconditionally.  For Python
+               3.5 or 3.6 we recognize 'async' in front of 'def', and
+               either one inside of 'async def'.  (Technically we
+               shouldn't recognize these at all for 3.4 or earlier,
+               but there's no *valid* Python 3.4 code that would be
+               rejected, and async functions will be rejected in a
+               later phase.) */
+            if (!tok->async_hacks || tok->async_def) {
+                /* Always recognize the keywords. */
+                if (memcmp(tok->start, "async", 5) == 0) {
+                    return ASYNC;
+                }
+                if (memcmp(tok->start, "await", 5) == 0) {
+                    return AWAIT;
+                }
+            }
+            else if (memcmp(tok->start, "async", 5) == 0) {
+                /* The current token is 'async'.
+                   Look ahead one token to see if that is 'def'. */
+
+                struct tok_state ahead_tok;
+                char *ahead_tok_start = NULL, *ahead_tok_end = NULL;
+                int ahead_tok_kind;
+
+                memcpy(&ahead_tok, tok, sizeof(ahead_tok));
+                ahead_tok_kind = tok_get(&ahead_tok, &ahead_tok_start,
+                                         &ahead_tok_end);
+
+                if (ahead_tok_kind == NAME
+                    && ahead_tok.cur - ahead_tok.start == 3
+                    && memcmp(ahead_tok.start, "def", 3) == 0)
+                {
+                    /* The next token is going to be 'def', so instead of
+                       returning a plain NAME token, return ASYNC. */
+                    tok->async_def_indent = tok->indent;
+                    tok->async_def = 1;
+                    return ASYNC;
+                }
+            }
+        }
+
         return NAME;
     }
 
@@ -1322,6 +1396,11 @@ tok_get(struct tok_state *tok, char **p_start, char **p_end)
         *p_start = tok->start;
         *p_end = tok->cur - 1; /* Leave '\n' out of the string */
         tok->cont_line = 0;
+        if (tok->async_def) {
+            /* We're somewhere inside an 'async def' function, and
+               we've encountered a NEWLINE after its signature. */
+            tok->async_def_nl = 1;
+        }
         return NEWLINE;
     }
 

Parser/tokenizer.h

@@ -64,6 +64,13 @@ struct tok_state {
     const char* input; /* Tokenizer's newline translated copy of the string. */
 
     int type_comments;      /* Whether to look for type comments */
+
+    /* async/await related fields (still needed depending on feature_version) */
+    int async_hacks;     /* =1 if async/await aren't always keywords */
+    int async_def;        /* =1 if tokens are inside an 'async def' body. */
+    int async_def_indent; /* Indentation level of the outermost 'async def'. */
+    int async_def_nl;     /* =1 if the outermost 'async def' had at least one
+                             NEWLINE token after it. */
 };
 
 extern struct tok_state *PyTokenizer_FromString(const char *, int);

Python/Python-ast.c

@@ -8899,6 +8899,11 @@ PyObject* PyAST_mod2obj(mod_ty t)
 
 /* mode is 0 for "exec", 1 for "eval" and 2 for "single" input */
 mod_ty PyAST_obj2mod(PyObject* ast, PyArena* arena, int mode)
+{
+    return PyAST_obj2mod_ex(ast, arena, mode, PY_MINOR_VERSION);
+}
+
+mod_ty PyAST_obj2mod_ex(PyObject* ast, PyArena* arena, int mode, int feature_version)
 {
     mod_ty res;
     PyObject *req_type[3];

Python/ast.c

@@ -564,6 +564,7 @@ struct compiling {
     PyArena *c_arena; /* Arena for allocating memory. */
     PyObject *c_filename; /* filename */
     PyObject *c_normalize; /* Normalization function from unicodedata. */
+    int c_feature_version; /* Latest minor version of Python for allowed features */
 };
 
 static asdl_seq *seq_for_testlist(struct compiling *, const node *);
@@ -783,6 +784,7 @@ PyAST_FromNodeObject(const node *n, PyCompilerFlags *flags,
     /* borrowed reference */
     c.c_filename = filename;
     c.c_normalize = NULL;
+    c.c_feature_version = flags->cf_feature_version;
 
     if (TYPE(n) == encoding_decl)
         n = CHILD(n, 0);
@@ -955,7 +957,7 @@ PyAST_FromNode(const node *n, PyCompilerFlags *flags, const char *filename_str,
 */
 
 static operator_ty
-get_operator(const node *n)
+get_operator(struct compiling *c, const node *n)
 {
     switch (TYPE(n)) {
         case VBAR:
@@ -975,6 +977,11 @@ get_operator(const node *n)
         case STAR:
             return Mult;
         case AT:
+            if (c->c_feature_version < 5) {
+                ast_error(c, n,
+                          "The '@' operator is only supported in Python 3.5 and greater");
+                return (operator_ty)0;
+            }
             return MatMult;
         case SLASH:
             return Div;
@@ -1209,6 +1216,11 @@ ast_for_augassign(struct compiling *c, const node *n)
             else
                 return Mult;
         case '@':
+            if (c->c_feature_version < 5) {
+                ast_error(c, n,
+                          "The '@' operator is only supported in Python 3.5 and greater");
+                return (operator_ty)0;
+            }
             return MatMult;
         default:
             PyErr_Format(PyExc_SystemError, "invalid augassign: %s", STR(n));
@@ -1518,7 +1530,7 @@ ast_for_arguments(struct compiling *c, const node *n)
                 }
                 else if (found_default) {
                     ast_error(c, n,
-                             "non-default argument follows default argument");
+                              "non-default argument follows default argument");
                     return NULL;
                 }
                 arg = ast_for_arg(c, ch);
@@ -1719,6 +1731,12 @@ ast_for_funcdef_impl(struct compiling *c, const node *n0,
     node *tc;
     string type_comment = NULL;
 
+    if (is_async && c->c_feature_version < 5) {
+        ast_error(c, n,
+                  "Async functions are only supported in Python 3.5 and greater");
+        return NULL;
+    }
+
     REQ(n, funcdef);
 
     name = NEW_IDENTIFIER(CHILD(n, name_i));
@@ -1772,10 +1790,9 @@ ast_for_funcdef_impl(struct compiling *c, const node *n0,
 static stmt_ty
 ast_for_async_funcdef(struct compiling *c, const node *n, asdl_seq *decorator_seq)
 {
-    /* async_funcdef: 'async' funcdef */
+    /* async_funcdef: ASYNC funcdef */
     REQ(n, async_funcdef);
-    REQ(CHILD(n, 0), NAME);
-    assert(strcmp(STR(CHILD(n, 0)), "async") == 0);
+    REQ(CHILD(n, 0), ASYNC);
     REQ(CHILD(n, 1), funcdef);
 
     return ast_for_funcdef_impl(c, n, decorator_seq,
@@ -1794,10 +1811,9 @@ ast_for_funcdef(struct compiling *c, const node *n, asdl_seq *decorator_seq)
 static stmt_ty
 ast_for_async_stmt(struct compiling *c, const node *n)
 {
-    /* async_stmt: 'async' (funcdef | with_stmt | for_stmt) */
+    /* async_stmt: ASYNC (funcdef | with_stmt | for_stmt) */
     REQ(n, async_stmt);
-    REQ(CHILD(n, 0), NAME);
-    assert(strcmp(STR(CHILD(n, 0)), "async") == 0);
+    REQ(CHILD(n, 0), ASYNC);
 
     switch (TYPE(CHILD(n, 1))) {
         case funcdef:
@@ -1948,8 +1964,7 @@ count_comp_fors(struct compiling *c, const node *n)
     n_fors++;
     REQ(n, comp_for);
     if (NCH(n) == 2) {
-        REQ(CHILD(n, 0), NAME);
-        assert(strcmp(STR(CHILD(n, 0)), "async") == 0);
+        REQ(CHILD(n, 0), ASYNC);
         n = CHILD(n, 1);
     }
     else if (NCH(n) == 1) {
@@ -2034,8 +2049,7 @@ ast_for_comprehension(struct compiling *c, const node *n)
 
         if (NCH(n) == 2) {
             is_async = 1;
-            REQ(CHILD(n, 0), NAME);
-            assert(strcmp(STR(CHILD(n, 0)), "async") == 0);
+            REQ(CHILD(n, 0), ASYNC);
             sync_n = CHILD(n, 1);
         }
         else {
@@ -2043,6 +2057,13 @@ ast_for_comprehension(struct compiling *c, const node *n)
         }
         REQ(sync_n, sync_comp_for);
 
+        /* Async comprehensions only allowed in Python 3.6 and greater */
+        if (is_async && c->c_feature_version < 6) {
+            ast_error(c, n,
+                      "Async comprehensions are only supported in Python 3.6 and greater");
+            return NULL;
+        }
+
         for_ch = CHILD(sync_n, 1);
         t = ast_for_exprlist(c, for_ch, Store);
         if (!t)
@@ -2337,7 +2358,15 @@ ast_for_atom(struct compiling *c, const node *n)
         return str;
     }
     case NUMBER: {
-        PyObject *pynum = parsenumber(c, STR(ch));
+        PyObject *pynum;
+        /* Underscores in numeric literals are only allowed in Python 3.6 or greater */
+        /* Check for underscores here rather than in parse_number so we can report a line number on error */
+        if (c->c_feature_version < 6 && strchr(STR(ch), '_') != NULL) {
+            ast_error(c, ch,
+                      "Underscores in numeric literals are only supported in Python 3.6 and greater");
+            return NULL;
+        }
+        pynum = parsenumber(c, STR(ch));
         if (!pynum)
             return NULL;
 
@@ -2420,8 +2449,8 @@ ast_for_atom(struct compiling *c, const node *n)
                     TYPE(CHILD(ch, 3 - is_dict)) == comp_for) {
                 /* It's a dictionary comprehension. */
                 if (is_dict) {
-                    ast_error(c, n, "dict unpacking cannot be used in "
-                              "dict comprehension");
+                    ast_error(c, n,
+                              "dict unpacking cannot be used in dict comprehension");
                     return NULL;
                 }
                 res = ast_for_dictcomp(c, ch);
@@ -2524,7 +2553,7 @@ ast_for_binop(struct compiling *c, const node *n)
     if (!expr2)
         return NULL;
 
-    newoperator = get_operator(CHILD(n, 1));
+    newoperator = get_operator(c, CHILD(n, 1));
     if (!newoperator)
         return NULL;
 
@@ -2539,7 +2568,7 @@ ast_for_binop(struct compiling *c, const node *n)
         expr_ty tmp_result, tmp;
         const node* next_oper = CHILD(n, i * 2 + 1);
 
-        newoperator = get_operator(next_oper);
+        newoperator = get_operator(c, next_oper);
         if (!newoperator)
             return NULL;
 
@@ -2678,7 +2707,12 @@ ast_for_atom_expr(struct compiling *c, const node *n)
     REQ(n, atom_expr);
     nch = NCH(n);
 
-    if (TYPE(CHILD(n, 0)) == NAME && strcmp(STR(CHILD(n, 0)), "await") == 0) {
+    if (TYPE(CHILD(n, 0)) == AWAIT) {
+        if (c->c_feature_version < 5) {
+            ast_error(c, n,
+                      "Await expressions are only supported in Python 3.5 and greater");
+            return NULL;
+        }
         start = 1;
         assert(nch > 1);
     }
@@ -2775,7 +2809,7 @@ ast_for_expr(struct compiling *c, const node *n)
        term: factor (('*'|'@'|'/'|'%'|'//') factor)*
        factor: ('+'|'-'|'~') factor | power
        power: atom_expr ['**' factor]
-       atom_expr: ['await'] atom trailer*
+       atom_expr: [AWAIT] atom trailer*
        yield_expr: 'yield' [yield_arg]
     */
 
@@ -3233,6 +3267,13 @@ ast_for_expr_stmt(struct compiling *c, const node *n)
         node *deep, *ann = CHILD(n, 1);
         int simple = 1;
 
+        /* AnnAssigns are only allowed in Python 3.6 or greater */
+        if (c->c_feature_version < 6) {
+            ast_error(c, ch,
+                      "Variable annotation syntax is only supported in Python 3.6 and greater");
+            return NULL;
+        }
+
         /* we keep track of parens to qualify (x) as expression not name */
         deep = ch;
         while (NCH(deep) == 1) {
@@ -4050,6 +4091,13 @@ ast_for_for_stmt(struct compiling *c, const node *n0, bool is_async)
     int end_lineno, end_col_offset;
     int has_type_comment;
     string type_comment;
+
+    if (is_async && c->c_feature_version < 5) {
+        ast_error(c, n,
+                  "Async for loops are only supported in Python 3.5 and greater");
+        return NULL;
+    }
+
     /* for_stmt: 'for' exprlist 'in' testlist ':' [TYPE_COMMENT] suite ['else' ':' suite] */
     REQ(n, for_stmt);
 
@@ -4278,6 +4326,12 @@ ast_for_with_stmt(struct compiling *c, const node *n0, bool is_async)
     asdl_seq *items, *body;
     string type_comment;
 
+    if (is_async && c->c_feature_version < 5) {
+        ast_error(c, n,
+                  "Async with statements are only supported in Python 3.5 and greater");
+        return NULL;
+    }
+
     REQ(n, with_stmt);
 
     has_type_comment = TYPE(CHILD(n, NCH(n) - 2)) == TYPE_COMMENT;
@@ -4768,6 +4822,7 @@ fstring_compile_expr(const char *expr_start, const char *expr_end,
     str[len+2] = 0;
 
     cf.cf_flags = PyCF_ONLY_AST;
+    cf.cf_feature_version = PY_MINOR_VERSION;
     mod_n = PyParser_SimpleParseStringFlagsFilename(str, "<fstring>",
                                                     Py_eval_input, 0);
     if (!mod_n) {
@@ -5568,6 +5623,13 @@ parsestr(struct compiling *c, const node *n, int *bytesmode, int *rawmode,
             }
         }
     }
+
+    /* fstrings are only allowed in Python 3.6 and greater */
+    if (fmode && c->c_feature_version < 6) {
+        ast_error(c, n, "Format strings are only supported in Python 3.6 and greater");
+        return -1;
+    }
+
     if (fmode && *bytesmode) {
         PyErr_BadInternalCall();
         return -1;

Python/bltinmodule.c

@@ -745,6 +745,7 @@ compile as builtin_compile
     flags: int = 0
     dont_inherit: bool(accept={int}) = False
     optimize: int = -1
+    feature_version: int = -1
 
 Compile source into a code object that can be executed by exec() or eval().
 
@@ -763,8 +764,8 @@ in addition to any features explicitly specified.
 static PyObject *
 builtin_compile_impl(PyObject *module, PyObject *source, PyObject *filename,
                      const char *mode, int flags, int dont_inherit,
-                     int optimize)
-/*[clinic end generated code: output=1fa176e33452bb63 input=0ff726f595eb9fcd]*/
+                     int optimize, int feature_version)
+/*[clinic end generated code: output=b0c09c84f116d3d7 input=5fcc30651a6acaa9]*/
 {
     PyObject *source_copy;
     const char *str;
@@ -775,6 +776,10 @@ builtin_compile_impl(PyObject *module, PyObject *source, PyObject *filename,
     PyObject *result;
 
     cf.cf_flags = flags | PyCF_SOURCE_IS_UTF8;
+    cf.cf_feature_version = PY_MINOR_VERSION;
+    if (feature_version >= 0 && (flags & PyCF_ONLY_AST)) {
+        cf.cf_feature_version = feature_version;
+    }
 
     if (flags &
         ~(PyCF_MASK | PyCF_MASK_OBSOLETE | PyCF_DONT_IMPLY_DEDENT | PyCF_ONLY_AST | PyCF_TYPE_COMMENTS))
@@ -981,6 +986,7 @@ builtin_eval_impl(PyObject *module, PyObject *source, PyObject *globals,
     }
 
     cf.cf_flags = PyCF_SOURCE_IS_UTF8;
+    cf.cf_feature_version = PY_MINOR_VERSION;
     str = source_as_string(source, "eval", "string, bytes or code", &cf, &source_copy);
     if (str == NULL)
         return NULL;
@@ -1068,6 +1074,7 @@ builtin_exec_impl(PyObject *module, PyObject *source, PyObject *globals,
         const char *str;
         PyCompilerFlags cf;
         cf.cf_flags = PyCF_SOURCE_IS_UTF8;
+        cf.cf_feature_version = PY_MINOR_VERSION;
         str = source_as_string(source, "exec",
                                        "string, bytes or code", &cf,
                                        &source_copy);

Python/clinic/bltinmodule.c.h

@@ -151,7 +151,7 @@ exit:
 
 PyDoc_STRVAR(builtin_compile__doc__,
 "compile($module, /, source, filename, mode, flags=0,\n"
-"        dont_inherit=False, optimize=-1)\n"
+"        dont_inherit=False, optimize=-1, feature_version=-1)\n"
 "--\n"
 "\n"
 "Compile source into a code object that can be executed by exec() or eval().\n"
@@ -173,26 +173,27 @@ PyDoc_STRVAR(builtin_compile__doc__,
 static PyObject *
 builtin_compile_impl(PyObject *module, PyObject *source, PyObject *filename,
                      const char *mode, int flags, int dont_inherit,
-                     int optimize);
+                     int optimize, int feature_version);
 
 static PyObject *
 builtin_compile(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
 {
     PyObject *return_value = NULL;
-    static const char * const _keywords[] = {"source", "filename", "mode", "flags", "dont_inherit", "optimize", NULL};
-    static _PyArg_Parser _parser = {"OO&s|iii:compile", _keywords, 0};
+    static const char * const _keywords[] = {"source", "filename", "mode", "flags", "dont_inherit", "optimize", "feature_version", NULL};
+    static _PyArg_Parser _parser = {"OO&s|iiii:compile", _keywords, 0};
     PyObject *source;
     PyObject *filename;
     const char *mode;
     int flags = 0;
     int dont_inherit = 0;
     int optimize = -1;
+    int feature_version = -1;
 
     if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser,
-        &source, PyUnicode_FSDecoder, &filename, &mode, &flags, &dont_inherit, &optimize)) {
+        &source, PyUnicode_FSDecoder, &filename, &mode, &flags, &dont_inherit, &optimize, &feature_version)) {
         goto exit;
     }
-    return_value = builtin_compile_impl(module, source, filename, mode, flags, dont_inherit, optimize);
+    return_value = builtin_compile_impl(module, source, filename, mode, flags, dont_inherit, optimize, feature_version);
 
 exit:
     return return_value;
@@ -754,4 +755,4 @@ builtin_issubclass(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
 exit:
     return return_value;
 }
-/*[clinic end generated code: output=54e5e33dcc2659e0 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=00b97a48ea49eaf2 input=a9049054013a1b77]*/

Python/compile.c

@@ -330,6 +330,7 @@ PyAST_CompileObject(mod_ty mod, PyObject *filename, PyCompilerFlags *flags,
         goto finally;
     if (!flags) {
         local_flags.cf_flags = 0;
+        local_flags.cf_feature_version = PY_MINOR_VERSION;
         flags = &local_flags;
     }
     merged = c.c_future->ff_features | flags->cf_flags;

Python/pythonrun.c

@@ -105,6 +105,7 @@ PyRun_InteractiveLoopFlags(FILE *fp, const char *filename_str, PyCompilerFlags *
     if (flags == NULL) {
         flags = &local_flags;
         local_flags.cf_flags = 0;
+        local_flags.cf_feature_version = PY_MINOR_VERSION;
     }
     v = _PySys_GetObjectId(&PyId_ps1);
     if (v == NULL) {
@@ -1165,6 +1166,7 @@ Py_SymtableStringObject(const char *str, PyObject *filename, int start)
         return NULL;
 
     flags.cf_flags = 0;
+    flags.cf_feature_version = PY_MINOR_VERSION;
     mod = PyParser_ASTFromStringObject(str, filename, start, &flags, arena);
     if (mod == NULL) {
         PyArena_Free(arena);
@@ -1198,12 +1200,15 @@ PyParser_ASTFromStringObject(const char *s, PyObject *filename, int start,
     PyCompilerFlags localflags;
     perrdetail err;
     int iflags = PARSER_FLAGS(flags);
+    if (flags && flags->cf_feature_version < 7)
+        iflags |= PyPARSE_ASYNC_HACKS;
 
     node *n = PyParser_ParseStringObject(s, filename,
                                          &_PyParser_Grammar, start, &err,
                                          &iflags);
     if (flags == NULL) {
         localflags.cf_flags = 0;
+        localflags.cf_feature_version = PY_MINOR_VERSION;
         flags = &localflags;
     }
     if (n) {
@@ -1249,6 +1254,7 @@ PyParser_ASTFromFileObject(FILE *fp, PyObject *filename, const char* enc,
                                        start, ps1, ps2, &err, &iflags);
     if (flags == NULL) {
         localflags.cf_flags = 0;
+        localflags.cf_feature_version = PY_MINOR_VERSION;
         flags = &localflags;
     }
     if (n) {