bpo-40939: Use the new grammar for the grammar specification documentation (GH-19969)

(We censor the heck out of actions and some other stuff using a custom "highlighter".)

Co-authored-by: Guido van Rossum <guido@python.org>

Doc/conf.py

@@ -15,7 +15,7 @@ sys.path.append(os.path.abspath('includes'))
 
 extensions = ['sphinx.ext.coverage', 'sphinx.ext.doctest',
               'pyspecific', 'c_annotations', 'escape4chm',
-              'asdl_highlight']
+              'asdl_highlight', 'peg_highlight']
 
 
 doctest_global_setup = '''

Doc/reference/grammar.rst

@@ -1,7 +1,19 @@
 Full Grammar specification
 ==========================
 
-This is the full Python grammar, as it is read by the parser generator and used
+This is the full Python grammar, derived directly from the grammar
-to parse Python source files:
+used to generate the CPython parser (see :source:`Grammar/python.gram`).
+The version here omits details related to code generation and
+error recovery.
 
-.. literalinclude:: ../../Grammar/Grammar
+The notation is a mixture of `EBNF
+<https://en.wikipedia.org/wiki/Extended_Backus%E2%80%93Naur_form>`_
+and `PEG <https://en.wikipedia.org/wiki/Parsing_expression_grammar>`_.
+In particular, ``&`` followed by a symbol, token or parenthesized
+group indicates a positive lookahead (i.e., is required to match but
+not consumed), while ``!`` indicates a negative lookahead (i.e., is
+required _not_ to match).  We use the ``|`` separator to mean PEG's
+"ordered choice" (written as ``/`` in traditional PEG grammars).
+
+.. literalinclude:: ../../Grammar/python.gram
+  :language: peg

Doc/tools/extensions/peg_highlight.py

@@ -0,0 +1,75 @@
+from pygments.lexer import RegexLexer, bygroups, include
+from pygments.token import Comment, Generic, Keyword, Name, Operator, Punctuation, Text
+
+from sphinx.highlighting import lexers
+
+
+class PEGLexer(RegexLexer):
+    """Pygments Lexer for PEG grammar (.gram) files
+
+    This lexer strips the following elements from the grammar:
+
+        - Meta-tags
+        - Variable assignments
+        - Actions
+        - Lookaheads
+        - Rule types
+        - Rule options
+        - Rules named `invalid_*` or `incorrect_*`
+    """
+
+    name = "PEG"
+    aliases = ["peg"]
+    filenames = ["*.gram"]
+    _name = r"([^\W\d]\w*)"
+    _text_ws = r"(\s*)"
+
+    tokens = {
+        "ws": [(r"\n", Text), (r"\s+", Text), (r"#.*$", Comment.Singleline),],
+        "lookaheads": [
+            (r"(?<=\|\s)(&\w+\s?)", bygroups(None)),
+            (r"(?<=\|\s)(&'.+'\s?)", bygroups(None)),
+            (r'(?<=\|\s)(&".+"\s?)', bygroups(None)),
+            (r"(?<=\|\s)(&\(.+\)\s?)", bygroups(None)),
+        ],
+        "metas": [
+            (r"(@\w+ '''(.|\n)+?''')", bygroups(None)),
+            (r"^(@.*)$", bygroups(None)),
+        ],
+        "actions": [(r"{(.|\n)+?}", bygroups(None)),],
+        "strings": [
+            (r"'\w+?'", Keyword),
+            (r'"\w+?"', Keyword),
+            (r"'\W+?'", Text),
+            (r'"\W+?"', Text),
+        ],
+        "variables": [(_name + _text_ws + "(=)", bygroups(None, None, None),),],
+        "invalids": [
+            (r"^(\s+\|\s+invalid_\w+\s*\n)", bygroups(None)),
+            (r"^(\s+\|\s+incorrect_\w+\s*\n)", bygroups(None)),
+            (r"^(#.*invalid syntax.*(?:.|\n)*)", bygroups(None),),
+        ],
+        "root": [
+            include("invalids"),
+            include("ws"),
+            include("lookaheads"),
+            include("metas"),
+            include("actions"),
+            include("strings"),
+            include("variables"),
+            (r"\b(?!(NULL|EXTRA))([A-Z_]+)\b\s*(?!\()", Text,),
+            (
+                r"^\s*" + _name + "\s*" + "(\[.*\])?" + "\s*" + "(\(.+\))?" + "\s*(:)",
+                bygroups(Name.Function, None, None, Punctuation),
+            ),
+            (_name, Name.Function),
+            (r"[\||\.|\+|\*|\?]", Operator),
+            (r"{|}|\(|\)|\[|\]", Punctuation),
+            (r".", Text),
+        ],
+    }
+
+
+def setup(app):
+    lexers["peg"] = PEGLexer()
+    return {"version": "1.0", "parallel_read_safe": True}

Grammar/Grammar

@@ -1,206 +0,0 @@
-# Grammar for Python
-
-# NOTE: Editing this file has no effect except on the docs.
-
-# 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.
-#       func_type_input is a PEP 484 Python 2 function type comment
-# NB: compound_stmt in single_input is followed by extra NEWLINE!
-# NB: due to the way TYPE_COMMENT is tokenized it will always be followed by a NEWLINE
-single_input: NEWLINE | simple_stmt | compound_stmt NEWLINE
-file_input: (NEWLINE | 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] ':' [TYPE_COMMENT] func_body_suite
-
-parameters: '(' [typedargslist] ')'
-
-# The following definition for typedarglist is equivalent to this set of rules:
-#
-#     arguments = argument (',' [TYPE_COMMENT] argument)*
-#     argument = tfpdef ['=' test]
-#     kwargs = '**' tfpdef [','] [TYPE_COMMENT]
-#     args = '*' [tfpdef]
-#     kwonly_kwargs = (',' [TYPE_COMMENT] argument)* (TYPE_COMMENT | [',' [TYPE_COMMENT] [kwargs]])
-#     args_kwonly_kwargs = args kwonly_kwargs | kwargs
-#     poskeyword_args_kwonly_kwargs = arguments ( TYPE_COMMENT | [',' [TYPE_COMMENT] [args_kwonly_kwargs]])
-#     typedargslist_no_posonly  = poskeyword_args_kwonly_kwargs | args_kwonly_kwargs
-#     typedarglist = (arguments ',' [TYPE_COMMENT] '/' [',' [[TYPE_COMMENT] 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] (',' [TYPE_COMMENT] tfpdef ['=' test])* ',' [TYPE_COMMENT] '/' [',' [ [TYPE_COMMENT] tfpdef ['=' test] (
-        ',' [TYPE_COMMENT] tfpdef ['=' test])* (TYPE_COMMENT | [',' [TYPE_COMMENT] [
-        '*' [tfpdef] (',' [TYPE_COMMENT] tfpdef ['=' test])* (TYPE_COMMENT | [',' [TYPE_COMMENT] ['**' tfpdef [','] [TYPE_COMMENT]]])
-      | '**' tfpdef [','] [TYPE_COMMENT]]])
-  | '*' [tfpdef] (',' [TYPE_COMMENT] tfpdef ['=' test])* (TYPE_COMMENT | [',' [TYPE_COMMENT] ['**' tfpdef [','] [TYPE_COMMENT]]])
-  | '**' tfpdef [','] [TYPE_COMMENT]]] )
-|  (tfpdef ['=' test] (',' [TYPE_COMMENT] tfpdef ['=' test])* (TYPE_COMMENT | [',' [TYPE_COMMENT] [
-   '*' [tfpdef] (',' [TYPE_COMMENT] tfpdef ['=' test])* (TYPE_COMMENT | [',' [TYPE_COMMENT] ['**' tfpdef [','] [TYPE_COMMENT]]])
-  | '**' tfpdef [','] [TYPE_COMMENT]]])
-  | '*' [tfpdef] (',' [TYPE_COMMENT] tfpdef ['=' test])* (TYPE_COMMENT | [',' [TYPE_COMMENT] ['**' tfpdef [','] [TYPE_COMMENT]]])
-  | '**' tfpdef [','] [TYPE_COMMENT])
-)
-tfpdef: NAME [':' test]
-
-# The following definition for varargslist is equivalent to this set of rules:
-#
-#     arguments = argument (',' argument )*
-#     argument = vfpdef ['=' test]
-#     kwargs = '**' vfpdef [',']
-#     args = '*' [vfpdef]
-#     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] (',' 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
-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))+ [TYPE_COMMENT]] )
-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 ':' [TYPE_COMMENT] suite ['else' ':' suite]
-try_stmt: ('try' ':' suite
-           ((except_clause ':' suite)+
-            ['else' ':' suite]
-            ['finally' ':' suite] |
-           'finally' ':' suite))
-with_stmt: 'with' with_item (',' with_item)*  ':' [TYPE_COMMENT] 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
-test_nocond: or_test | lambdef_nocond
-lambdef: 'lambda' [varargslist] ':' test
-lambdef_nocond: 'lambda' [varargslist] ':' test_nocond
-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 | STRING+ | '...' | '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] [sliceop]
-sliceop: ':' [test]
-exprlist: (expr|star_expr) (',' (expr|star_expr))* [',']
-testlist: test (',' test)* [',']
-dictorsetmaker: ( ((test ':' test | '**' expr)
-                   (comp_for | (',' (test ':' test | '**' expr))* [','])) |
-                  ((test | star_expr)
-                   (comp_for | (',' (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' test_nocond [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
-
-# the TYPE_COMMENT in suites is only parsed for funcdefs,
-# but can't go elsewhere due to ambiguity
-func_body_suite: simple_stmt | NEWLINE [TYPE_COMMENT NEWLINE] INDENT stmt+ DEDENT
-
-func_type_input: func_type NEWLINE* ENDMARKER
-func_type: '(' [typelist] ')' '->' test
-# typelist is a modified typedargslist (see above)
-typelist: (test (',' test)* [','
-       ['*' [test] (',' test)* [',' '**' test] | '**' test]]
-     |  '*' [test] (',' test)* [',' '**' test] | '**' test)