-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathPythonParser.g4
165 lines (147 loc) · 6.75 KB
/
PythonParser.g4
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
/*
Python grammar
The MIT License (MIT)
Copyright (c) 2021 Robert Einhorn
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
*/
/*
* Project : an ANTLR4 parser grammar by the official Python 2.7.18 grammar
* https://github.com/RobEin/ANTLR4-parser-for-Python-2.7.18
* Developed by : Robert Einhorn
*/
// https://docs.python.org/2.7/reference/grammar.html
parser grammar PythonParser;
options { tokenVocab=PythonLexer; }
// ANTLR4 grammar for Python
// 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() and input() functions.
// NB: compound_stmt in single_input is followed by extra NEWLINE!
single_input: NEWLINE | simple_stmt | compound_stmt NEWLINE;
file_input: (NEWLINE | stmt)* EOF;
eval_input: testlist NEWLINE* EOF;
decorator: '@' dotted_name ( '(' arglist? ')' )? NEWLINE;
decorators: decorator+;
decorated: decorators (classdef | funcdef);
funcdef: 'def' NAME parameters ':' suite;
parameters: '(' varargslist? ')';
varargslist: ((fpdef ('=' test)? ',')*
('*' NAME (',' '**' NAME)? | '**' NAME) |
fpdef ('=' test)? (',' fpdef ('=' test)?)* ','?);
fpdef: NAME | '(' fplist ')';
fplist: fpdef (',' fpdef)* ','?;
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 (augassign (yield_expr|testlist) |
('=' (yield_expr|testlist))*);
augassign: ('+=' | '-=' | '*=' | '/=' | '%=' | '&=' | '|=' | '^=' |
'<<=' | '>>=' | '**=' | '//=');
// For normal 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?;
yield_stmt: yield_expr;
raise_stmt: 'raise' (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' 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;
if_stmt: 'if' test ':' suite ('elif' test ':' suite)* ('else' ':' suite)?;
while_stmt: 'while' 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' | ',') 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;
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';
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 trailer* ('**' factor)?;
atom: ('(' (yield_expr|testlist_comp)? ')' |
'[' listmaker? ']' |
'{' dictorsetmaker? '}' |
'`' testlist1 '`' |
NAME | NUMBER | STRING+);
listmaker: test ( list_for | (',' test)* ','? );
testlist_comp: test ( comp_for | (',' test)* ','? );
lambdef: 'lambda' varargslist? ':' test;
trailer: '(' arglist? ')' | '[' subscriptlist ']' | '.' NAME;
subscriptlist: subscript (',' subscript)* ','?;
subscript: '.' '.' '.' | test | test? ':' test? sliceop?;
sliceop: ':' test?;
exprlist: expr (',' expr)* ','?;
testlist: test (',' test)* ','?;
dictorsetmaker: ( (test ':' test (comp_for | (',' test ':' test)* ','?)) |
(test (comp_for | (',' test)* ','?)) );
classdef: 'class' NAME ('(' testlist? ')')? ':' suite;
arglist: (argument ',')* (argument ','?
|'*' test (',' argument)* (',' '**' test)?
|'**' test);
// 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.
argument: test comp_for? | test '=' test;
list_iter: list_for | list_if;
list_for: 'for' exprlist 'in' testlist_safe list_iter?;
list_if: 'if' old_test list_iter?;
comp_iter: comp_for | comp_if;
comp_for: 'for' exprlist 'in' or_test 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' testlist?;