gh-294: Vendoring lib2to3

python · corona10 · Jun 12, 2023 · Jun 11, 2023 · Jun 11, 2023 · Jun 11, 2023
commit 8439c96ecebb1c27473463117654fd4ac8118020
diff --git a/pyperformance/data-files/benchmarks/bm_2to3/run_benchmark.py b/pyperformance/data-files/benchmarks/bm_2to3/run_benchmark.py
@@ -1,6 +1,7 @@
 import glob
 import os.path
 import sys
+import subprocess
 
 import pyperf
 
@@ -14,5 +15,10 @@
     datadir = os.path.join(os.path.dirname(__file__), 'data', '2to3')
     pyfiles = glob.glob(os.path.join(datadir, '*.py.txt'))
 
+    try:
+        import lib2to3
+    except ModuleNotFoundError:
+        vendor = os.path.join(os.path.dirname(__file__), 'vendor')
+        subprocess.run([sys.executable, "-m", "pip", "install", vendor])
     command = [sys.executable, "-m", "lib2to3", "-f", "all"] + pyfiles
     runner.bench_command('2to3', command)
diff --git a/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/Grammar.txt b/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/Grammar.txt
@@ -0,0 +1,196 @@
+# Grammar for 2to3. This grammar supports Python 2.x and 3.x.
+
+# NOTE WELL: You should also follow all the steps listed at
+# https://devguide.python.org/grammar/
+
+# Start symbols for the grammar:
+#	file_input is a module or sequence of commands read from an input file;
+#	single_input is a single interactive statement;
+#	eval_input is the input for the eval() and input() functions.
+# NB: compound_stmt in single_input is followed by extra NEWLINE!
+file_input: (NEWLINE | stmt)* ENDMARKER
+single_input: NEWLINE | simple_stmt | compound_stmt NEWLINE
+eval_input: testlist NEWLINE* ENDMARKER
+
+decorator: '@' dotted_name [ '(' [arglist] ')' ] NEWLINE
+decorators: decorator+
+decorated: decorators (classdef | funcdef | async_funcdef)
+async_funcdef: ASYNC funcdef
+funcdef: 'def' NAME parameters ['->' test] ':' suite
+parameters: '(' [typedargslist] ')'
+
+# 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)* [',']
+
+# 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)* [',']
+
+stmt: simple_stmt | compound_stmt
+simple_stmt: small_stmt (';' small_stmt)* [';'] NEWLINE
+small_stmt: (expr_stmt | print_stmt  | del_stmt | pass_stmt | flow_stmt |
+             import_stmt | global_stmt | exec_stmt | assert_stmt)
+expr_stmt: testlist_star_expr (annassign | augassign (yield_expr|testlist) |
+                     ('=' (yield_expr|testlist_star_expr))*)
+annassign: ':' test ['=' test]
+testlist_star_expr: (test|star_expr) (',' (test|star_expr))* [',']
+augassign: ('+=' | '-=' | '*=' | '@=' | '/=' | '%=' | '&=' | '|=' | '^=' |
+            '<<=' | '>>=' | '**=' | '//=')
+# For normal and annotated assignments, additional restrictions enforced by the interpreter
+print_stmt: 'print' ( [ test (',' test)* [','] ] |
+                      '>>' test [ (',' test)+ [','] ] )
+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 | ',' test [',' test]]]
+import_stmt: import_name | import_from
+import_name: 'import' dotted_as_names
+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' | 'nonlocal') NAME (',' NAME)*
+exec_stmt: 'exec' expr ['in' test [',' test]]
+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]
+with_var: 'as' expr
+# NB compile.c makes sure that the default except clause is last
+except_clause: 'except' [test [(',' | 'as') test]]
+suite: simple_stmt | NEWLINE INDENT stmt+ DEDENT
+
+# Backward compatibility cruft to support:
+# [ x for x in lambda: True, lambda: False if x() ]
+# even while also allowing:
+# lambda x: 5 if x else 2
+# (But not a mix of the two)
+testlist_safe: old_test [(',' old_test)+ [',']]
+old_test: or_test | old_lambdef
+old_lambdef: 'lambda' [varargslist] ':' old_test
+
+namedexpr_test: test [':=' test]
+test: or_test ['if' or_test 'else' test] | lambdef
+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)*
+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: [AWAIT] atom trailer* ['**' factor]
+atom: ('(' [yield_expr|testlist_gexp] ')' |
+       '[' [listmaker] ']' |
+       '{' [dictsetmaker] '}' |
+       '`' testlist1 '`' |
+       NAME | NUMBER | STRING+ | '.' '.' '.')
+listmaker: (namedexpr_test|star_expr) ( comp_for | (',' (namedexpr_test|star_expr))* [','] )
+testlist_gexp: (namedexpr_test|star_expr) ( comp_for | (',' (namedexpr_test|star_expr))* [','] )
+lambdef: 'lambda' [varargslist] ':' test
+trailer: '(' [arglist] ')' | '[' subscriptlist ']' | '.' NAME
+subscriptlist: subscript (',' subscript)* [',']
+subscript: test | [test] ':' [test] [sliceop]
+sliceop: ':' [test]
+exprlist: (expr|star_expr) (',' (expr|star_expr))* [',']
+testlist: test (',' test)* [',']
+dictsetmaker: ( ((test ':' test | '**' expr)
+                 (comp_for | (',' (test ':' test | '**' expr))* [','])) |
+                ((test | star_expr)
+		 (comp_for | (',' (test | star_expr))* [','])) )
+
+classdef: 'class' NAME ['(' [arglist] ')'] ':' suite
+
+arglist: argument (',' argument)* [',']
+
+# "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
+comp_for: [ASYNC] 'for' exprlist 'in' testlist_safe [comp_iter]
+comp_if: 'if' old_test [comp_iter]
+
+testlist1: test (',' test)*
+
+# 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
diff --git a/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/PatternGrammar.txt b/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/PatternGrammar.txt
@@ -0,0 +1,28 @@
+# Copyright 2006 Google, Inc. All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement.
+
+# A grammar to describe tree matching patterns.
+# Not shown here:
+# - 'TOKEN' stands for any token (leaf node)
+# - 'any' stands for any node (leaf or interior)
+# With 'any' we can still specify the sub-structure.
+
+# The start symbol is 'Matcher'.
+
+Matcher: Alternatives ENDMARKER
+
+Alternatives: Alternative ('|' Alternative)*
+
+Alternative: (Unit | NegatedUnit)+
+
+Unit: [NAME '='] ( STRING [Repeater]
+                 | NAME [Details] [Repeater]
+                 | '(' Alternatives ')' [Repeater]
+                 | '[' Alternatives ']'
+		 )
+
+NegatedUnit: 'not' (STRING | NAME [Details] | '(' Alternatives ')')
+
+Repeater: '*' | '+' | '{' NUMBER [',' NUMBER] '}'
+
+Details: '<' Alternatives '>'
diff --git a/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/__init__.py b/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/__init__.py
@@ -0,0 +1,8 @@
+import warnings
+
+
+warnings.warn(
+    "lib2to3 package is deprecated and may not be able to parse Python 3.10+",
+    DeprecationWarning,
+    stacklevel=2,
+)
diff --git a/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/__main__.py b/pyperformance/data-files/benchmarks/bm_2to3/vendor/lib2to3/__main__.py
@@ -0,0 +1,4 @@
+import sys
+from .main import main
+
+sys.exit(main("lib2to3.fixes"))