10. 完整的语法规范¶
这是完整的 Python 语法规范,直接提取自用于生成 CPython 解析器的语法 (参见 Grammar/python.gram)。 这里显示的版本省略了有关代码生成和错误恢复的细节。
所用的标记法是 EBNF 和 PEG 的混合体。 特别地,&
后跟一个符号、形符或带括号的分组来表示正向前视(即要求执行匹配但不会被消耗掉),而 !
表示负向前视(即要求 _不_ 执行匹配)。 我们使用 |
分隔符来表示 PEG 的“有序选择” (在传统 PEG 语法中则写为 /
)。
# PEG grammar for Python
file: [statements] ENDMARKER
interactive: statement_newline
eval: expressions NEWLINE* ENDMARKER
func_type: '(' [type_expressions] ')' '->' expression NEWLINE* ENDMARKER
fstring: star_expressions
# type_expressions allow */** but ignore them
type_expressions:
| ','.expression+ ',' '*' expression ',' '**' expression
| ','.expression+ ',' '*' expression
| ','.expression+ ',' '**' expression
| '*' expression ',' '**' expression
| '*' expression
| '**' expression
| ','.expression+
statements: statement+
statement: compound_stmt | simple_stmt
statement_newline:
| compound_stmt NEWLINE
| simple_stmt
| NEWLINE
| ENDMARKER
simple_stmt:
| small_stmt !';' NEWLINE # Not needed, there for speedup
| ';'.small_stmt+ [';'] NEWLINE
# NOTE: assignment MUST precede expression, else parsing a simple assignment
# will throw a SyntaxError.
small_stmt:
| assignment
| star_expressions
| return_stmt
| import_stmt
| raise_stmt
| 'pass'
| del_stmt
| yield_stmt
| assert_stmt
| 'break'
| 'continue'
| global_stmt
| nonlocal_stmt
compound_stmt:
| function_def
| if_stmt
| class_def
| with_stmt
| for_stmt
| try_stmt
| while_stmt
# NOTE: annotated_rhs may start with 'yield'; yield_expr must start with 'yield'
assignment:
| NAME ':' expression ['=' annotated_rhs ]
| ('(' single_target ')'
| single_subscript_attribute_target) ':' expression ['=' annotated_rhs ]
| (star_targets '=' )+ (yield_expr | star_expressions) !'=' [TYPE_COMMENT]
| single_target augassign ~ (yield_expr | star_expressions)
augassign:
| '+='
| '-='
| '*='
| '@='
| '/='
| '%='
| '&='
| '|='
| '^='
| '<<='
| '>>='
| '**='
| '//='
global_stmt: 'global' ','.NAME+
nonlocal_stmt: 'nonlocal' ','.NAME+
yield_stmt: yield_expr
assert_stmt: 'assert' expression [',' expression ]
del_stmt:
| 'del' del_targets &(';' | NEWLINE)
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_from_targets
| 'from' ('.' | '...')+ 'import' import_from_targets
import_from_targets:
| '(' import_from_as_names [','] ')'
| import_from_as_names !','
| '*'
import_from_as_names:
| ','.import_from_as_name+
import_from_as_name:
| NAME ['as' NAME ]
dotted_as_names:
| ','.dotted_as_name+
dotted_as_name:
| dotted_name ['as' NAME ]
dotted_name:
| dotted_name '.' NAME
| NAME
if_stmt:
| 'if' named_expression ':' block elif_stmt
| 'if' named_expression ':' block [else_block]
elif_stmt:
| 'elif' named_expression ':' block elif_stmt
| 'elif' named_expression ':' block [else_block]
else_block: 'else' ':' block
while_stmt:
| 'while' named_expression ':' block [else_block]
for_stmt:
| 'for' star_targets 'in' ~ star_expressions ':' [TYPE_COMMENT] block [else_block]
| ASYNC 'for' star_targets 'in' ~ star_expressions ':' [TYPE_COMMENT] block [else_block]
with_stmt:
| 'with' '(' ','.with_item+ ','? ')' ':' block
| 'with' ','.with_item+ ':' [TYPE_COMMENT] block
| ASYNC 'with' '(' ','.with_item+ ','? ')' ':' block
| ASYNC 'with' ','.with_item+ ':' [TYPE_COMMENT] block
with_item:
| expression 'as' star_target &(',' | ')' | ':')
| expression
try_stmt:
| 'try' ':' block finally_block
| 'try' ':' block except_block+ [else_block] [finally_block]
except_block:
| 'except' expression ['as' NAME ] ':' block
| 'except' ':' block
finally_block: 'finally' ':' block
return_stmt:
| 'return' [star_expressions]
raise_stmt:
| 'raise' expression ['from' expression ]
| 'raise'
function_def:
| decorators function_def_raw
| function_def_raw
function_def_raw:
| 'def' NAME '(' [params] ')' ['->' expression ] ':' [func_type_comment] block
| ASYNC 'def' NAME '(' [params] ')' ['->' expression ] ':' [func_type_comment] block
func_type_comment:
| NEWLINE TYPE_COMMENT &(NEWLINE INDENT) # Must be followed by indented block
| TYPE_COMMENT
params:
| parameters
parameters:
| slash_no_default param_no_default* param_with_default* [star_etc]
| slash_with_default param_with_default* [star_etc]
| param_no_default+ param_with_default* [star_etc]
| param_with_default+ [star_etc]
| star_etc
# Some duplication here because we can't write (',' | &')'),
# which is because we don't support empty alternatives (yet).
#
slash_no_default:
| param_no_default+ '/' ','
| param_no_default+ '/' &')'
slash_with_default:
| param_no_default* param_with_default+ '/' ','
| param_no_default* param_with_default+ '/' &')'
star_etc:
| '*' param_no_default param_maybe_default* [kwds]
| '*' ',' param_maybe_default+ [kwds]
| kwds
kwds: '**' param_no_default
# One parameter. This *includes* a following comma and type comment.
#
# There are three styles:
# - No default
# - With default
# - Maybe with default
#
# There are two alternative forms of each, to deal with type comments:
# - Ends in a comma followed by an optional type comment
# - No comma, optional type comment, must be followed by close paren
# The latter form is for a final parameter without trailing comma.
#
param_no_default:
| param ',' TYPE_COMMENT?
| param TYPE_COMMENT? &')'
param_with_default:
| param default ',' TYPE_COMMENT?
| param default TYPE_COMMENT? &')'
param_maybe_default:
| param default? ',' TYPE_COMMENT?
| param default? TYPE_COMMENT? &')'
param: NAME annotation?
annotation: ':' expression
default: '=' expression
decorators: ('@' named_expression NEWLINE )+
class_def:
| decorators class_def_raw
| class_def_raw
class_def_raw:
| 'class' NAME ['(' [arguments] ')' ] ':' block
block:
| NEWLINE INDENT statements DEDENT
| simple_stmt
expressions_list: ','.star_expression+ [',']
star_expressions:
| star_expression (',' star_expression )+ [',']
| star_expression ','
| star_expression
star_expression:
| '*' bitwise_or
| expression
star_named_expressions: ','.star_named_expression+ [',']
star_named_expression:
| '*' bitwise_or
| named_expression
named_expression:
| NAME ':=' ~ expression
| expression !':='
annotated_rhs: yield_expr | star_expressions
expressions:
| expression (',' expression )+ [',']
| expression ','
| expression
expression:
| disjunction 'if' disjunction 'else' expression
| disjunction
| lambdef
lambdef:
| 'lambda' [lambda_params] ':' expression
lambda_params:
| lambda_parameters
# lambda_parameters etc. duplicates parameters but without annotations
# or type comments, and if there's no comma after a parameter, we expect
# a colon, not a close parenthesis. (For more, see parameters above.)
#
lambda_parameters:
| lambda_slash_no_default lambda_param_no_default* lambda_param_with_default* [lambda_star_etc]
| lambda_slash_with_default lambda_param_with_default* [lambda_star_etc]
| lambda_param_no_default+ lambda_param_with_default* [lambda_star_etc]
| lambda_param_with_default+ [lambda_star_etc]
| lambda_star_etc
lambda_slash_no_default:
| lambda_param_no_default+ '/' ','
| lambda_param_no_default+ '/' &':'
lambda_slash_with_default:
| lambda_param_no_default* lambda_param_with_default+ '/' ','
| lambda_param_no_default* lambda_param_with_default+ '/' &':'
lambda_star_etc:
| '*' lambda_param_no_default lambda_param_maybe_default* [lambda_kwds]
| '*' ',' lambda_param_maybe_default+ [lambda_kwds]
| lambda_kwds
lambda_kwds: '**' lambda_param_no_default
lambda_param_no_default:
| lambda_param ','
| lambda_param &':'
lambda_param_with_default:
| lambda_param default ','
| lambda_param default &':'
lambda_param_maybe_default:
| lambda_param default? ','
| lambda_param default? &':'
lambda_param: NAME
disjunction:
| conjunction ('or' conjunction )+
| conjunction
conjunction:
| inversion ('and' inversion )+
| inversion
inversion:
| 'not' inversion
| comparison
comparison:
| bitwise_or compare_op_bitwise_or_pair+
| bitwise_or
compare_op_bitwise_or_pair:
| eq_bitwise_or
| noteq_bitwise_or
| lte_bitwise_or
| lt_bitwise_or
| gte_bitwise_or
| gt_bitwise_or
| notin_bitwise_or
| in_bitwise_or
| isnot_bitwise_or
| is_bitwise_or
eq_bitwise_or: '==' bitwise_or
noteq_bitwise_or:
| ('!=' ) bitwise_or
lte_bitwise_or: '<=' bitwise_or
lt_bitwise_or: '<' bitwise_or
gte_bitwise_or: '>=' bitwise_or
gt_bitwise_or: '>' bitwise_or
notin_bitwise_or: 'not' 'in' bitwise_or
in_bitwise_or: 'in' bitwise_or
isnot_bitwise_or: 'is' 'not' bitwise_or
is_bitwise_or: 'is' bitwise_or
bitwise_or:
| bitwise_or '|' bitwise_xor
| bitwise_xor
bitwise_xor:
| bitwise_xor '^' bitwise_and
| bitwise_and
bitwise_and:
| bitwise_and '&' shift_expr
| shift_expr
shift_expr:
| shift_expr '<<' sum
| shift_expr '>>' sum
| sum
sum:
| sum '+' term
| sum '-' term
| term
term:
| term '*' factor
| term '/' factor
| term '//' factor
| term '%' factor
| term '@' factor
| factor
factor:
| '+' factor
| '-' factor
| '~' factor
| power
power:
| await_primary '**' factor
| await_primary
await_primary:
| AWAIT primary
| primary
primary:
| invalid_primary # must be before 'primay genexp' because of invalid_genexp
| primary '.' NAME
| primary genexp
| primary '(' [arguments] ')'
| primary '[' slices ']'
| atom
slices:
| slice !','
| ','.slice+ [',']
slice:
| [expression] ':' [expression] [':' [expression] ]
| expression
atom:
| NAME
| 'True'
| 'False'
| 'None'
| '__peg_parser__'
| strings
| NUMBER
| (tuple | group | genexp)
| (list | listcomp)
| (dict | set | dictcomp | setcomp)
| '...'
strings: STRING+
list:
| '[' [star_named_expressions] ']'
listcomp:
| '[' named_expression ~ for_if_clauses ']'
tuple:
| '(' [star_named_expression ',' [star_named_expressions] ] ')'
group:
| '(' (yield_expr | named_expression) ')'
genexp:
| '(' expression ~ for_if_clauses ')'
set: '{' expressions_list '}'
setcomp:
| '{' expression ~ for_if_clauses '}'
dict:
| '{' [double_starred_kvpairs] '}'
dictcomp:
| '{' kvpair for_if_clauses '}'
double_starred_kvpairs: ','.double_starred_kvpair+ [',']
double_starred_kvpair:
| '**' bitwise_or
| kvpair
kvpair: expression ':' expression
for_if_clauses:
| for_if_clause+
for_if_clause:
| ASYNC 'for' star_targets 'in' ~ disjunction ('if' disjunction )*
| 'for' star_targets 'in' ~ disjunction ('if' disjunction )*
yield_expr:
| 'yield' 'from' expression
| 'yield' [star_expressions]
arguments:
| args [','] &')'
args:
| ','.(starred_expression | named_expression !'=')+ [',' kwargs ]
| kwargs
kwargs:
| ','.kwarg_or_starred+ ',' ','.kwarg_or_double_starred+
| ','.kwarg_or_starred+
| ','.kwarg_or_double_starred+
starred_expression:
| '*' expression
kwarg_or_starred:
| NAME '=' expression
| starred_expression
kwarg_or_double_starred:
| NAME '=' expression
| '**' expression
# NOTE: star_targets may contain *bitwise_or, targets may not.
star_targets:
| star_target !','
| star_target (',' star_target )* [',']
star_targets_seq: ','.star_target+ [',']
star_target:
| '*' (!'*' star_target)
| t_primary '.' NAME !t_lookahead
| t_primary '[' slices ']' !t_lookahead
| star_atom
star_atom:
| NAME
| '(' star_target ')'
| '(' [star_targets_seq] ')'
| '[' [star_targets_seq] ']'
single_target:
| single_subscript_attribute_target
| NAME
| '(' single_target ')'
single_subscript_attribute_target:
| t_primary '.' NAME !t_lookahead
| t_primary '[' slices ']' !t_lookahead
del_targets: ','.del_target+ [',']
del_target:
| t_primary '.' NAME !t_lookahead
| t_primary '[' slices ']' !t_lookahead
| del_t_atom
del_t_atom:
| NAME
| '(' del_target ')'
| '(' [del_targets] ')'
| '[' [del_targets] ']'
targets: ','.target+ [',']
target:
| t_primary '.' NAME !t_lookahead
| t_primary '[' slices ']' !t_lookahead
| t_atom
t_primary:
| t_primary '.' NAME &t_lookahead
| t_primary '[' slices ']' &t_lookahead
| t_primary genexp &t_lookahead
| t_primary '(' [arguments] ')' &t_lookahead
| atom &t_lookahead
t_lookahead: '(' | '[' | '.'
t_atom:
| NAME
| '(' target ')'
| '(' [targets] ')'
| '[' [targets] ']'