Enable pattern matching by default (#2758)

Co-authored-by: Richard Si <63936253+ichard26@users.noreply.github.com>

diff --git a/CHANGES.md b/CHANGES.md
index dc52ca34cbbb06675d101e27f2e1039b0b785c67..634db79bf730ffe1f51de26e859f64ff6f5e0a3b 100644 (file)
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -36,6 +36,8 @@
   Jupyter Notebooks (#2744)
 - Deprecate `--experimental-string-processing` and move the functionality under
   `--preview` (#2789)
   Jupyter Notebooks (#2744)
 - Deprecate `--experimental-string-processing` and move the functionality under
   `--preview` (#2789)

+- Enable Python 3.10+ by default, without any extra need to specify
+  `--target-version=py310`. (#2758)

 
 ### Packaging
 
 
 ### Packaging
 

diff --git a/src/black/parsing.py b/src/black/parsing.py
index 6b63368871c80c29a4e353d4c126d141235d0f61..db48ae4baf5cf181b7647609603c6f75d6b2d523 100644 (file)
--- a/src/black/parsing.py
+++ b/src/black/parsing.py
@@ -42,7 +42,6 @@ except ImportError:
         ast3 = ast
 
 
         ast3 = ast
 
 

-PY310_HINT: Final = "Consider using --target-version py310 to parse Python 3.10 code."

 PY2_HINT: Final = "Python 2 support was removed in version 22.0."
 
 
 PY2_HINT: Final = "Python 2 support was removed in version 22.0."
 
 


@@ -58,12 +57,11 @@ def get_grammars(target_versions: Set[TargetVersion]) -> List[Grammar]:
             pygram.python_grammar_no_print_statement_no_exec_statement_async_keywords,
             # Python 3.0-3.6
             pygram.python_grammar_no_print_statement_no_exec_statement,
             pygram.python_grammar_no_print_statement_no_exec_statement_async_keywords,
             # Python 3.0-3.6
             pygram.python_grammar_no_print_statement_no_exec_statement,

+            # Python 3.10+
+            pygram.python_grammar_soft_keywords,

         ]
 
     grammars = []
         ]
 
     grammars = []

-    if supports_feature(target_versions, Feature.PATTERN_MATCHING):
-        # Python 3.10+
-        grammars.append(pygram.python_grammar_soft_keywords)

     # If we have to parse both, try to parse async as a keyword first
     if not supports_feature(
         target_versions, Feature.ASYNC_IDENTIFIERS
     # If we have to parse both, try to parse async as a keyword first
     if not supports_feature(
         target_versions, Feature.ASYNC_IDENTIFIERS


@@ -75,6 +73,10 @@ def get_grammars(target_versions: Set[TargetVersion]) -> List[Grammar]:
     if not supports_feature(target_versions, Feature.ASYNC_KEYWORDS):
         # Python 3.0-3.6
         grammars.append(pygram.python_grammar_no_print_statement_no_exec_statement)
     if not supports_feature(target_versions, Feature.ASYNC_KEYWORDS):
         # Python 3.0-3.6
         grammars.append(pygram.python_grammar_no_print_statement_no_exec_statement)

+    if supports_feature(target_versions, Feature.PATTERN_MATCHING):
+        # Python 3.10+
+        grammars.append(pygram.python_grammar_soft_keywords)
+

     # At least one of the above branches must have been taken, because every Python
     # version has exactly one of the two 'ASYNC_*' flags
     return grammars
     # At least one of the above branches must have been taken, because every Python
     # version has exactly one of the two 'ASYNC_*' flags
     return grammars


@@ -86,6 +88,7 @@ def lib2to3_parse(src_txt: str, target_versions: Iterable[TargetVersion] = ()) -
         src_txt += "\n"
 
     grammars = get_grammars(set(target_versions))
         src_txt += "\n"
 
     grammars = get_grammars(set(target_versions))

+    errors = {}

     for grammar in grammars:
         drv = driver.Driver(grammar)
         try:
     for grammar in grammars:
         drv = driver.Driver(grammar)
         try:


@@ -99,20 +102,21 @@ def lib2to3_parse(src_txt: str, target_versions: Iterable[TargetVersion] = ()) -
                 faulty_line = lines[lineno - 1]
             except IndexError:
                 faulty_line = "<line number missing in source>"
                 faulty_line = lines[lineno - 1]
             except IndexError:
                 faulty_line = "<line number missing in source>"

-            exc = InvalidInput(f"Cannot parse: {lineno}:{column}: {faulty_line}")
+            errors[grammar.version] = InvalidInput(
+                f"Cannot parse: {lineno}:{column}: {faulty_line}"
+            )

 
         except TokenError as te:
             # In edge cases these are raised; and typically don't have a "faulty_line".
             lineno, column = te.args[1]
 
         except TokenError as te:
             # In edge cases these are raised; and typically don't have a "faulty_line".
             lineno, column = te.args[1]

-            exc = InvalidInput(f"Cannot parse: {lineno}:{column}: {te.args[0]}")
+            errors[grammar.version] = InvalidInput(
+                f"Cannot parse: {lineno}:{column}: {te.args[0]}"
+            )

 
     else:
 
     else:

-        if pygram.python_grammar_soft_keywords not in grammars and matches_grammar(
-            src_txt, pygram.python_grammar_soft_keywords
-        ):
-            original_msg = exc.args[0]
-            msg = f"{original_msg}\n{PY310_HINT}"
-            raise InvalidInput(msg) from None
+        # Choose the latest version when raising the actual parsing error.
+        assert len(errors) >= 1
+        exc = errors[max(errors)]

 
         if matches_grammar(src_txt, pygram.python_grammar) or matches_grammar(
             src_txt, pygram.python_grammar_no_print_statement
 
         if matches_grammar(src_txt, pygram.python_grammar) or matches_grammar(
             src_txt, pygram.python_grammar_no_print_statement

diff --git a/src/blib2to3/pgen2/grammar.py b/src/blib2to3/pgen2/grammar.py
index 56851070933a708d7a0fadce36bdb6c6ffd6e4c5..337a64f17269c80005c295e757949dc086dc7c19 100644 (file)
--- a/src/blib2to3/pgen2/grammar.py
+++ b/src/blib2to3/pgen2/grammar.py
@@ -92,6 +92,7 @@ class Grammar(object):
         self.soft_keywords: Dict[str, int] = {}
         self.tokens: Dict[int, int] = {}
         self.symbol2label: Dict[str, int] = {}
         self.soft_keywords: Dict[str, int] = {}
         self.tokens: Dict[int, int] = {}
         self.symbol2label: Dict[str, int] = {}

+        self.version: Tuple[int, int] = (0, 0)

         self.start = 256
         # Python 3.7+ parses async as a keyword, not an identifier
         self.async_keywords = False
         self.start = 256
         # Python 3.7+ parses async as a keyword, not an identifier
         self.async_keywords = False


@@ -145,6 +146,7 @@ class Grammar(object):
         new.labels = self.labels[:]
         new.states = self.states[:]
         new.start = self.start
         new.labels = self.labels[:]
         new.states = self.states[:]
         new.start = self.start

+        new.version = self.version

         new.async_keywords = self.async_keywords
         return new
 
         new.async_keywords = self.async_keywords
         return new
 

diff --git a/src/blib2to3/pygram.py b/src/blib2to3/pygram.py
index aa20b8104aea914d4751c6ed40a93a18cb57f76b..a3df9be1265655a413cdfae0163ab14512f85df1 100644 (file)
--- a/src/blib2to3/pygram.py
+++ b/src/blib2to3/pygram.py
@@ -178,6 +178,8 @@ def initialize(cache_dir: Union[str, "os.PathLike[str]", None] = None) -> None:
 
     # Python 2
     python_grammar = driver.load_packaged_grammar("blib2to3", _GRAMMAR_FILE, cache_dir)
 
     # Python 2
     python_grammar = driver.load_packaged_grammar("blib2to3", _GRAMMAR_FILE, cache_dir)

+    python_grammar.version = (2, 0)
+

     soft_keywords = python_grammar.soft_keywords.copy()
     python_grammar.soft_keywords.clear()
 
     soft_keywords = python_grammar.soft_keywords.copy()
     python_grammar.soft_keywords.clear()
 


@@ -191,6 +193,7 @@ def initialize(cache_dir: Union[str, "os.PathLike[str]", None] = None) -> None:
     python_grammar_no_print_statement_no_exec_statement = python_grammar.copy()
     del python_grammar_no_print_statement_no_exec_statement.keywords["print"]
     del python_grammar_no_print_statement_no_exec_statement.keywords["exec"]
     python_grammar_no_print_statement_no_exec_statement = python_grammar.copy()
     del python_grammar_no_print_statement_no_exec_statement.keywords["print"]
     del python_grammar_no_print_statement_no_exec_statement.keywords["exec"]

+    python_grammar_no_print_statement_no_exec_statement.version = (3, 0)

 
     # Python 3.7+
     python_grammar_no_print_statement_no_exec_statement_async_keywords = (
 
     # Python 3.7+
     python_grammar_no_print_statement_no_exec_statement_async_keywords = (


@@ -199,12 +202,14 @@ def initialize(cache_dir: Union[str, "os.PathLike[str]", None] = None) -> None:
     python_grammar_no_print_statement_no_exec_statement_async_keywords.async_keywords = (
         True
     )
     python_grammar_no_print_statement_no_exec_statement_async_keywords.async_keywords = (
         True
     )

+    python_grammar_no_print_statement_no_exec_statement_async_keywords.version = (3, 7)

 
     # Python 3.10+
     python_grammar_soft_keywords = (
         python_grammar_no_print_statement_no_exec_statement_async_keywords.copy()
     )
     python_grammar_soft_keywords.soft_keywords = soft_keywords
 
     # Python 3.10+
     python_grammar_soft_keywords = (
         python_grammar_no_print_statement_no_exec_statement_async_keywords.copy()
     )
     python_grammar_soft_keywords.soft_keywords = soft_keywords

+    python_grammar_soft_keywords.version = (3, 10)

 
     pattern_grammar = driver.load_packaged_grammar(
         "blib2to3", _PATTERN_GRAMMAR_FILE, cache_dir
 
     pattern_grammar = driver.load_packaged_grammar(
         "blib2to3", _PATTERN_GRAMMAR_FILE, cache_dir

diff --git a/tests/test_format.py b/tests/test_format.py
index 40f225c95547786d78bb85434164a17d1944f3b8..3895a095e863c2ec503fa43e272add8062da9f8e 100644 (file)
--- a/tests/test_format.py
+++ b/tests/test_format.py
@@ -191,6 +191,12 @@ def test_python_310(filename: str) -> None:
     assert_format(source, expected, mode, minimum_version=(3, 10))
 
 
     assert_format(source, expected, mode, minimum_version=(3, 10))
 
 

+def test_python_310_without_target_version() -> None:
+    source, expected = read_data("pattern_matching_simple")
+    mode = black.Mode()
+    assert_format(source, expected, mode, minimum_version=(3, 10))
+
+

 def test_patma_invalid() -> None:
     source, expected = read_data("pattern_matching_invalid")
     mode = black.Mode(target_versions={black.TargetVersion.PY310})
 def test_patma_invalid() -> None:
     source, expected = read_data("pattern_matching_invalid")
     mode = black.Mode(target_versions={black.TargetVersion.PY310})


@@ -200,15 +206,6 @@ def test_patma_invalid() -> None:
     exc_info.match("Cannot parse: 10:11")
 
 
     exc_info.match("Cannot parse: 10:11")
 
 

-def test_patma_hint() -> None:
-    source, expected = read_data("pattern_matching_simple")
-    mode = black.Mode(target_versions={black.TargetVersion.PY39})
-    with pytest.raises(black.parsing.InvalidInput) as exc_info:
-        assert_format(source, expected, mode, minimum_version=(3, 10))
-
-    exc_info.match(black.parsing.PY310_HINT)
-
-

 def test_python_2_hint() -> None:
     with pytest.raises(black.parsing.InvalidInput) as exc_info:
         assert_format("print 'daylily'", "print 'daylily'")
 def test_python_2_hint() -> None:
     with pytest.raises(black.parsing.InvalidInput) as exc_info:
         assert_format("print 'daylily'", "print 'daylily'")