Prepare release 0.8.5

Load newest grammar in face of a future grammar

.github/workflows/build.yml

@@ -29,7 +29,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', '3.13']
         experimental: [false]
     steps:
     - uses: actions/checkout@v2

CHANGELOG.rst

@@ -6,6 +6,11 @@ Changelog
 Unreleased
 ++++++++++
 
+0.8.5 (2025-08-23)
+++++++++++++++++++
+
+- Add a fallback grammar for Python 3.14+
+
 0.8.4 (2024-04-05)
 ++++++++++++++++++
 

README.rst

@@ -68,6 +68,8 @@ Resources
 Installation
 ============
 
+.. code-block:: bash
+
     pip install parso
 
 Future

conftest.py

@@ -13,7 +13,7 @@ from parso.utils import parse_version_string
 
 collect_ignore = ["setup.py"]
 
-_SUPPORTED_VERSIONS = '3.6', '3.7', '3.8', '3.9', '3.10'
+_SUPPORTED_VERSIONS = '3.6', '3.7', '3.8', '3.9', '3.10', '3.11', '3.12', '3.13', '3.14'
 
 
 @pytest.fixture(scope='session')

docs/docs/installation.rst

@@ -16,7 +16,7 @@ From git
 --------
 If you want to install the current development version (master branch)::
 
-    sudo pip install -e git://github.com/davidhalter/parso.git#egg=parso
+    sudo pip install -e git+https://github.com/davidhalter/parso.git#egg=parso
 
 
 Manual installation from a downloaded package (not recommended)

parso/__init__.py

@@ -43,7 +43,7 @@ from parso.grammar import Grammar, load_grammar
 from parso.utils import split_lines, python_bytes_to_unicode
 
 
-__version__ = '0.8.4'
+__version__ = '0.8.5'
 
 
 def parse(code=None, **kwargs):

parso/grammar.py

@@ -239,7 +239,16 @@ def load_grammar(*, version: str = None, path: str = None):
     :param str version: A python version string, e.g. ``version='3.8'``.
     :param str path: A path to a grammar file
     """
-    version_info = parse_version_string(version)
+    # NOTE: this (3, 14) should be updated to the latest version parso supports.
+    #       (if this doesn't happen, users will get older syntaxes and spurious warnings)
+    passed_version_info = parse_version_string(version)
+    version_info = min(passed_version_info, PythonVersionInfo(3, 14))
+
+    # # NOTE: this is commented out until parso properly supports newer Python grammars.
+    # if passed_version_info != version_info:
+    #     warnings.warn('parso does not support %s.%s yet.' % (
+    #         passed_version_info.major, passed_version_info.minor
+    #     ))
 
     file = path or os.path.join(
         'python',

parso/python/grammar314.txt

@@ -0,0 +1,169 @@
+# Grammar for Python
+
+# NOTE WELL: You should also follow all the steps listed at
+# https://devguide.python.org/grammar/
+
+# Start symbols for the grammar:
+#       single_input is a single interactive statement;
+#       file_input is a module or sequence of commands read from an input file;
+#       eval_input is the input for the eval() functions.
+# NB: compound_stmt in single_input is followed by extra NEWLINE!
+single_input: NEWLINE | simple_stmt | compound_stmt NEWLINE
+file_input: stmt* ENDMARKER
+eval_input: testlist NEWLINE* ENDMARKER
+
+decorator: '@' namedexpr_test NEWLINE
+decorators: decorator+
+decorated: decorators (classdef | funcdef | async_funcdef)
+
+async_funcdef: 'async' funcdef
+funcdef: 'def' NAME parameters ['->' test] ':' suite
+
+parameters: '(' [typedargslist] ')'
+typedargslist: (
+  (tfpdef ['=' test] (',' tfpdef ['=' test])* ',' '/' [',' [ tfpdef ['=' test] (
+        ',' tfpdef ['=' test])* ([',' [
+        '*' [tfpdef] (',' tfpdef ['=' test])* [',' ['**' tfpdef [',']]]
+      | '**' tfpdef [',']]])
+  | '*' [tfpdef] (',' tfpdef ['=' test])* ([',' ['**' tfpdef [',']]])
+  | '**' tfpdef [',']]] )
+|  (tfpdef ['=' test] (',' tfpdef ['=' test])* [',' [
+        '*' [tfpdef] (',' tfpdef ['=' test])* [',' ['**' tfpdef [',']]]
+      | '**' tfpdef [',']]]
+  | '*' [tfpdef] (',' tfpdef ['=' test])* [',' ['**' tfpdef [',']]]
+  | '**' tfpdef [','])
+)
+tfpdef: NAME [':' test]
+varargslist: vfpdef ['=' test ](',' vfpdef ['=' test])* ',' '/' [',' [ (vfpdef ['=' test] (',' vfpdef ['=' test])* [',' [
+        '*' [vfpdef] (',' vfpdef ['=' test])* [',' ['**' vfpdef [',']]]
+      | '**' vfpdef [',']]]
+  | '*' [vfpdef] (',' vfpdef ['=' test])* [',' ['**' vfpdef [',']]]
+  | '**' vfpdef [',']) ]] | (vfpdef ['=' test] (',' vfpdef ['=' test])* [',' [
+        '*' [vfpdef] (',' vfpdef ['=' test])* [',' ['**' vfpdef [',']]]
+      | '**' vfpdef [',']]]
+  | '*' [vfpdef] (',' vfpdef ['=' test])* [',' ['**' vfpdef [',']]]
+  | '**' vfpdef [',']
+)
+vfpdef: NAME
+
+stmt: simple_stmt | compound_stmt | NEWLINE
+simple_stmt: small_stmt (';' small_stmt)* [';'] NEWLINE
+small_stmt: (expr_stmt | del_stmt | pass_stmt | flow_stmt |
+             import_stmt | global_stmt | nonlocal_stmt | assert_stmt)
+expr_stmt: testlist_star_expr (annassign | augassign (yield_expr|testlist) |
+                     ('=' (yield_expr|testlist_star_expr))*)
+annassign: ':' test ['=' (yield_expr|testlist_star_expr)]
+testlist_star_expr: (test|star_expr) (',' (test|star_expr))* [',']
+augassign: ('+=' | '-=' | '*=' | '@=' | '/=' | '%=' | '&=' | '|=' | '^=' |
+            '<<=' | '>>=' | '**=' | '//=')
+# For normal and annotated assignments, additional restrictions enforced by the interpreter
+del_stmt: 'del' exprlist
+pass_stmt: 'pass'
+flow_stmt: break_stmt | continue_stmt | return_stmt | raise_stmt | yield_stmt
+break_stmt: 'break'
+continue_stmt: 'continue'
+return_stmt: 'return' [testlist_star_expr]
+yield_stmt: yield_expr
+raise_stmt: 'raise' [test ['from' test]]
+import_stmt: import_name | import_from
+import_name: 'import' dotted_as_names
+# note below: the ('.' | '...') is necessary because '...' is tokenized as ELLIPSIS
+import_from: ('from' (('.' | '...')* dotted_name | ('.' | '...')+)
+              'import' ('*' | '(' import_as_names ')' | import_as_names))
+import_as_name: NAME ['as' NAME]
+dotted_as_name: dotted_name ['as' NAME]
+import_as_names: import_as_name (',' import_as_name)* [',']
+dotted_as_names: dotted_as_name (',' dotted_as_name)*
+dotted_name: NAME ('.' NAME)*
+global_stmt: 'global' NAME (',' NAME)*
+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)
+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 ':' suite ['else' ':' suite]
+try_stmt: ('try' ':' suite
+           ((except_clause ':' suite)+
+            ['else' ':' suite]
+            ['finally' ':' suite] |
+           'finally' ':' suite))
+with_stmt: 'with' with_item (',' with_item)*  ':' suite
+with_item: test ['as' expr]
+# NB compile.c makes sure that the default except clause is last
+except_clause: 'except' [test ['as' NAME]]
+suite: simple_stmt | NEWLINE INDENT stmt+ DEDENT
+
+namedexpr_test: test [':=' test]
+test: or_test ['if' or_test 'else' test] | lambdef
+lambdef: 'lambda' [varargslist] ':' test
+or_test: and_test ('or' and_test)*
+and_test: not_test ('and' not_test)*
+not_test: 'not' not_test | comparison
+comparison: expr (comp_op expr)*
+# <> isn't actually a valid comparison operator in Python. It's here for the
+# sake of a __future__ import described in PEP 401 (which really works :-)
+comp_op: '<'|'>'|'=='|'>='|'<='|'<>'|'!='|'in'|'not' 'in'|'is'|'is' 'not'
+star_expr: '*' expr
+expr: xor_expr ('|' xor_expr)*
+xor_expr: and_expr ('^' and_expr)*
+and_expr: shift_expr ('&' shift_expr)*
+shift_expr: arith_expr (('<<'|'>>') arith_expr)*
+arith_expr: term (('+'|'-') term)*
+term: factor (('*'|'@'|'/'|'%'|'//') factor)*
+factor: ('+'|'-'|'~') factor | power
+power: atom_expr ['**' factor]
+atom_expr: ['await'] atom trailer*
+atom: ('(' [yield_expr|testlist_comp] ')' |
+       '[' [testlist_comp] ']' |
+       '{' [dictorsetmaker] '}' |
+       NAME | NUMBER | strings | '...' | 'None' | 'True' | 'False')
+testlist_comp: (namedexpr_test|star_expr) ( comp_for | (',' (namedexpr_test|star_expr))* [','] )
+trailer: '(' [arglist] ')' | '[' subscriptlist ']' | '.' NAME
+subscriptlist: subscript (',' subscript)* [',']
+subscript: test [':=' test] | [test] ':' [test] [sliceop]
+sliceop: ':' [test]
+exprlist: (expr|star_expr) (',' (expr|star_expr))* [',']
+testlist: test (',' test)* [',']
+dictorsetmaker: ( ((test ':' test | '**' expr)
+                   (comp_for | (',' (test ':' test | '**' expr))* [','])) |
+                  ((test [':=' test] | star_expr)
+                   (comp_for | (',' (test [':=' test] | star_expr))* [','])) )
+
+classdef: 'class' NAME ['(' [arglist] ')'] ':' suite
+
+arglist: argument (',' argument)*  [',']
+
+# The reason that keywords are test nodes instead of NAME is that using NAME
+# results in an ambiguity. ast.c makes sure it's a NAME.
+# "test '=' test" is really "keyword '=' test", but we have no such token.
+# These need to be in a single rule to avoid grammar that is ambiguous
+# to our LL(1) parser. Even though 'test' includes '*expr' in star_expr,
+# we explicitly match '*' here, too, to give it proper precedence.
+# Illegal combinations and orderings are blocked in ast.c:
+# multiple (test comp_for) arguments are blocked; keyword unpackings
+# that precede iterable unpackings are blocked; etc.
+argument: ( test [comp_for] |
+            test ':=' test |
+            test '=' test |
+            '**' test |
+            '*' test )
+
+comp_iter: comp_for | comp_if
+sync_comp_for: 'for' exprlist 'in' or_test [comp_iter]
+comp_for: ['async'] sync_comp_for
+comp_if: 'if' or_test [comp_iter]
+
+# not used in grammar, but may appear in "node" passed from Parser to Compiler
+encoding_decl: NAME
+
+yield_expr: 'yield' [yield_arg]
+yield_arg: 'from' test | testlist_star_expr
+
+strings: (STRING | fstring)+
+fstring: FSTRING_START fstring_content* FSTRING_END
+fstring_content: FSTRING_STRING | fstring_expr
+fstring_conversion: '!' NAME
+fstring_expr: '{' (testlist_comp | yield_expr) ['='] [ fstring_conversion ] [ fstring_format_spec ] '}'
+fstring_format_spec: ':' fstring_content*

pytest.ini

@@ -10,3 +10,6 @@ norecursedirs = .* docs scripts normalizer_issue_files build
 # fine as long as we are using `clean_jedi_cache` as a session scoped
 # fixture.
 usefixtures = clean_parso_cache
+
+# Disallow warnings
+filterwarnings = error

setup.py

@@ -40,6 +40,11 @@ setup(
         'Programming Language :: Python :: 3.7',
         'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.9',
+        'Programming Language :: Python :: 3.10',
+        'Programming Language :: Python :: 3.11',
+        'Programming Language :: Python :: 3.12',
+        'Programming Language :: Python :: 3.13',
+        'Programming Language :: Python :: 3.14',
         'Topic :: Software Development :: Libraries :: Python Modules',
         'Topic :: Text Editors :: Integrated Development Environments (IDE)',
         'Topic :: Utilities',

test/failing_examples.py

@@ -29,7 +29,6 @@ FAILING_EXAMPLES = [
     'from foo import a,',
     'from __future__ import whatever',
     'from __future__ import braces',
-    'from .__future__ import whatever',
     'def f(x=3, y): pass',
     'lambda x=3, y: x',
     '__debug__ = 1',
@@ -216,7 +215,6 @@ FAILING_EXAMPLES = [
     'f"{\'\\\'}"',
     'f"{#}"',
     "f'{1!b}'",
-    "f'{1:{5:{3}}}'",
     "f'{'",
     "f'{'",
     "f'}'",
@@ -227,8 +225,6 @@ FAILING_EXAMPLES = [
     "f'{1;1}'",
     "f'{a;}'",
     "f'{b\"\" \"\"}'",
-    # f-string expression part cannot include a backslash
-    r'''f"{'\n'}"''',
 
     'async def foo():\n yield x\n return 1',
     'async def foo():\n yield x\n return 1',
@@ -413,3 +409,17 @@ if sys.version_info[:2] >= (3, 8):
     FAILING_EXAMPLES += [
         "f'{1=!b}'",
     ]
+
+if sys.version_info[:2] < (3, 12):
+    FAILING_EXAMPLES += [
+        # f-string expression part cannot include a backslash before 3.12
+        r'''f"{'\n'}"''',
+        # this compiles successfully but fails when evaluated in 3.12
+        "f'{1:{5:{3}}}'",
+    ]
+
+if sys.version_info[:2] < (3, 13):
+    # this compiles successfully but fails when evaluated in 3.13
+    FAILING_EXAMPLES += [
+        'from .__future__ import whatever',
+    ]

test/test_load_grammar.py

@@ -4,15 +4,20 @@ from parso import utils
 
 
 def test_load_inexisting_grammar():
-    # This version shouldn't be out for a while, but if we ever do, wow!
-    with pytest.raises(NotImplementedError):
-        load_grammar(version='15.8')
-    # The same is true for very old grammars (even though this is probably not
-    # going to be an issue.
+    # We support future grammars assuming future compatibility,
+    # but we don't know how to parse old grammars.
     with pytest.raises(NotImplementedError):
         load_grammar(version='1.5')
 
 
+def test_load_grammar_uses_older_syntax():
+    load_grammar(version='4.0')
+
+
+def test_load_grammar_doesnt_warn(each_version):
+    load_grammar(version=each_version)
+
+
 @pytest.mark.parametrize(('string', 'result'), [
     ('2', (2, 7)), ('3', (3, 6)), ('1.1', (1, 1)), ('1.1.1', (1, 1)), ('300.1.31', (300, 1))
 ])

test/test_python_errors.py

@@ -118,25 +118,57 @@ def _get_actual_exception(code):
             assert False, "The piece of code should raise an exception."
 
     # SyntaxError
-    if wanted == 'SyntaxError: assignment to keyword':
+    # Some errors have changed error message in later versions of Python,
+    # and we give a translation table here.  We deal with special cases
+    # below.
+    translations = {
+        'SyntaxError: f-string: unterminated string':
+        'SyntaxError: EOL while scanning string literal',
+        "SyntaxError: f-string: expecting '}'":
+        'SyntaxError: EOL while scanning string literal',
+        'SyntaxError: f-string: empty expression not allowed':
+        'SyntaxError: invalid syntax',
+        "SyntaxError: f-string expression part cannot include '#'":
+        'SyntaxError: invalid syntax',
+        "SyntaxError: f-string: single '}' is not allowed":
+        'SyntaxError: invalid syntax',
+        'SyntaxError: cannot use starred expression here':
+        "SyntaxError: can't use starred expression here",
+        'SyntaxError: f-string: cannot use starred expression here':
+        "SyntaxError: f-string: can't use starred expression here",
+        'SyntaxError: unterminated string literal':
+        'SyntaxError: EOL while scanning string literal',
+        'SyntaxError: parameter without a default follows parameter with a default':
+        'SyntaxError: non-default argument follows default argument',
+        "SyntaxError: 'yield from' outside function":
+        "SyntaxError: 'yield' outside function",
+        "SyntaxError: f-string: valid expression required before '}'":
+        'SyntaxError: invalid syntax',
+        "SyntaxError: '{' was never closed":
+        'SyntaxError: invalid syntax',
+        "SyntaxError: f-string: invalid conversion character 'b': expected 's', 'r', or 'a'":
+        "SyntaxError: f-string: invalid conversion character: expected 's', 'r', or 'a'",
+        "SyntaxError: (value error) Invalid format specifier '  5' for object of type 'int'":
+        'SyntaxError: f-string: expressions nested too deeply',
+        "SyntaxError: f-string: expecting a valid expression after '{'":
+        'SyntaxError: f-string: invalid syntax',
+        "SyntaxError: f-string: expecting '=', or '!', or ':', or '}'":
+        'SyntaxError: f-string: invalid syntax',
+        "SyntaxError: f-string: expecting '=', or '!', or ':', or '}'":
+        'SyntaxError: f-string: invalid syntax',
+    }
+
+    if wanted in translations:
+        wanted = translations[wanted]
+    elif wanted == 'SyntaxError: assignment to keyword':
         return [wanted, "SyntaxError: can't assign to keyword",
                 'SyntaxError: cannot assign to __debug__'], line_nr
-    elif wanted == 'SyntaxError: f-string: unterminated string':
-        wanted = 'SyntaxError: EOL while scanning string literal'
     elif wanted == 'SyntaxError: f-string expression part cannot include a backslash':
         return [
             wanted,
             "SyntaxError: EOL while scanning string literal",
             "SyntaxError: unexpected character after line continuation character",
         ], line_nr
-    elif wanted == "SyntaxError: f-string: expecting '}'":
-        wanted = 'SyntaxError: EOL while scanning string literal'
-    elif wanted == 'SyntaxError: f-string: empty expression not allowed':
-        wanted = 'SyntaxError: invalid syntax'
-    elif wanted == "SyntaxError: f-string expression part cannot include '#'":
-        wanted = 'SyntaxError: invalid syntax'
-    elif wanted == "SyntaxError: f-string: single '}' is not allowed":
-        wanted = 'SyntaxError: invalid syntax'
     elif "Maybe you meant '==' instead of '='?" in wanted:
         wanted = wanted.removesuffix(" here. Maybe you meant '==' instead of '='?")
     elif re.match(
@@ -148,17 +180,27 @@ def _get_actual_exception(code):
         wanted,
     ):
         wanted = 'SyntaxError: EOF while scanning triple-quoted string literal'
-    elif wanted == 'SyntaxError: cannot use starred expression here':
-        wanted = "SyntaxError: can't use starred expression here"
-    elif wanted == 'SyntaxError: f-string: cannot use starred expression here':
-        wanted = "SyntaxError: f-string: can't use starred expression here"
     elif re.match(
         r"IndentationError: expected an indented block after '[^']*' statement on line \d",
         wanted,
     ):
         wanted = 'IndentationError: expected an indented block'
-    elif wanted == 'SyntaxError: unterminated string literal':
-        wanted = 'SyntaxError: EOL while scanning string literal'
+    # The following two errors are produced for both some f-strings and
+    # some non-f-strings in Python 3.13:
+    elif wanted == "SyntaxError: can't use starred expression here":
+        wanted = [
+            "SyntaxError: can't use starred expression here",
+            "SyntaxError: f-string: can't use starred expression here"
+        ]
+    elif wanted == 'SyntaxError: cannot mix bytes and nonbytes literals':
+        wanted = [
+            'SyntaxError: cannot mix bytes and nonbytes literals',
+            'SyntaxError: f-string: cannot mix bytes and nonbytes literals'
+        ]
+
+    if isinstance(wanted, list):
+        return wanted, line_nr
+    else:
         return [wanted], line_nr