Skip to content

Commit 3a245a8

Browse files
teverettteverett
authored
Merge pull request antlr#1386 from renatahodovan/wat
Add textual WebAssembly grammar.
2 parents 9bc8c46 + 408b06f commit 3a245a8

File tree

3 files changed

+683
-0
lines changed

3 files changed

+683
-0
lines changed

‎wat/README.md

+5
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,5 @@
1+
# Textual WebAssembly Grammar
2+
3+
An ANTLRv4 grammar for the [Wat](http://webassembly.github.io/spec/core/text/index.html) (textual [WebAssembly](https://en.wikipedia.org/wiki/WebAssembly)) format.
4+
5+
Inspired by the reference interpreter of the official WebAssembly GitHub [repository](https://github.com/WebAssembly/spec).

‎wat/WatLexer.g4

+280
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,280 @@
1+
/*
2+
Copyright (c) 2019 Renata Hodovan.
3+
All rights reserved.
4+
5+
Redistribution and use in source and binary forms, with or without
6+
modification, are permitted provided that the following conditions are met:
7+
8+
1. Redistributions of source code must retain the above copyright notice, this
9+
list of conditions and the following disclaimer.
10+
11+
2. Redistributions in binary form must reproduce the above copyright notice,
12+
this list of conditions and the following disclaimer in the documentation
13+
and/or other materials provided with the distribution.
14+
15+
3. Neither the name of the copyright holder nor the names of its contributors
16+
may be used to endorse or promote products derived from this software
17+
without specific prior written permission.
18+
19+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
20+
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
21+
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
22+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
23+
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24+
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
25+
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
26+
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
27+
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29+
*/
30+
31+
lexer grammar WatLexer;
32+
33+
LPAR : '(' ;
34+
RPAR : ')' ;
35+
36+
NAT : Nat ;
37+
INT : Int ;
38+
FLOAT : Float ;
39+
STRING : String ;
40+
VALUE_TYPE : NXX ;
41+
CONST : NXX '.const' ;
42+
43+
FUNCREF: 'funcref' ;
44+
MUT: 'mut' ;
45+
46+
NOP: 'nop' ;
47+
UNREACHABLE: 'unreachable' ;
48+
DROP: 'drop' ;
49+
BLOCK: 'block' ;
50+
LOOP: 'loop' ;
51+
END: 'end' ;
52+
BR: 'br' ;
53+
BR_IF: 'br_if' ;
54+
BR_TABLE: 'br_table' ;
55+
RETURN: 'return' ;
56+
IF: 'if' ;
57+
THEN: 'then' ;
58+
ELSE: 'else' ;
59+
SELECT: 'select' ;
60+
CALL: 'call' ;
61+
CALL_INDIRECT: 'call_indirect' ;
62+
63+
LOCAL_GET: 'local.get' ;
64+
LOCAL_SET: 'local.set' ;
65+
LOCAL_TEE: 'local.tee' ;
66+
GLOBAL_GET: 'global.get' ;
67+
GLOBAL_SET: 'global.set' ;
68+
69+
LOAD : NXX '.load' (MEM_SIZE '_' SIGN)? ;
70+
STORE : NXX '.store' (MEM_SIZE)? ;
71+
72+
OFFSET_EQ_NAT : 'offset=' Nat ;
73+
ALIGN_EQ_NAT : 'align=' Nat ;
74+
75+
UNARY
76+
: IXX '.clz'
77+
| IXX '.ctz'
78+
| IXX '.popcnt'
79+
| FXX '.neg'
80+
| FXX '.abs'
81+
| FXX '.sqrt'
82+
| FXX '.ceil'
83+
| FXX '.floor'
84+
| FXX '.trunc'
85+
| FXX '.nearest'
86+
;
87+
88+
BINARY
89+
: IXX '.add'
90+
| IXX '.sub'
91+
| IXX '.mul'
92+
| IXX '.div_s'
93+
| IXX '.div_u'
94+
| IXX '.rem_s'
95+
| IXX '.rem_u'
96+
| IXX '.and'
97+
| IXX '.or'
98+
| IXX '.xor'
99+
| IXX '.shl'
100+
| IXX '.shr_s'
101+
| IXX '.shr_u'
102+
| IXX '.rotl'
103+
| IXX '.rotr'
104+
| FXX '.add'
105+
| FXX '.sub'
106+
| FXX '.mul'
107+
| FXX '.div'
108+
| FXX '.min'
109+
| FXX '.max'
110+
| FXX '.copysign'
111+
;
112+
113+
TEST
114+
: IXX '.eqz'
115+
;
116+
117+
COMPARE
118+
: IXX '.eq'
119+
| IXX '.ne'
120+
| IXX '.lt_s'
121+
| IXX '.lt_u'
122+
| IXX '.le_s'
123+
| IXX '.le_u'
124+
| IXX '.gt_s'
125+
| IXX '.gt_u'
126+
| IXX '.ge_s'
127+
| IXX '.ge_u'
128+
| FXX '.eq'
129+
| FXX '.ne'
130+
| FXX '.lt'
131+
| FXX '.le'
132+
| FXX '.gt'
133+
| FXX '.ge'
134+
;
135+
136+
CONVERT
137+
: 'i32.wrap_i64'
138+
| 'i64.extend_i32_s'
139+
| 'i64.extend_i32_u'
140+
| 'f32.demote_f64'
141+
| 'f64.promote_f32'
142+
| IXX '.trunc_f32_s'
143+
| IXX '.trunc_f32_u'
144+
| IXX '.trunc_f64_s'
145+
| IXX '.trunc_f64_u'
146+
| FXX '.convert_i32_s'
147+
| FXX '.convert_i32_u'
148+
| FXX '.convert_i64_s'
149+
| FXX '.convert_i64_u'
150+
| 'f32.reinterpret_i32'
151+
| 'f64.reinterpret_i64'
152+
| 'i32.reinterpret_f32'
153+
| 'i64.reinterpret_f64'
154+
;
155+
156+
MEMORY_SIZE : 'memory.size' ;
157+
MEMORY_GROW : 'memory.grow' ;
158+
159+
TYPE: 'type' ;
160+
FUNC: 'func' ;
161+
START: 'start' ;
162+
PARAM: 'param' ;
163+
RESULT: 'result' ;
164+
LOCAL: 'local' ;
165+
GLOBAL: 'global' ;
166+
TABLE: 'table' ;
167+
MEMORY: 'memory' ;
168+
ELEM: 'elem' ;
169+
DATA: 'data' ;
170+
OFFSET: 'offset' ;
171+
IMPORT: 'import' ;
172+
EXPORT: 'export' ;
173+
174+
MODULE : 'module' ;
175+
BIN : 'binary' ;
176+
QUOTE : 'quote' ;
177+
178+
SCRIPT: 'script' ;
179+
REGISTER: 'register' ;
180+
INVOKE: 'invoke' ;
181+
GET: 'get' ;
182+
ASSERT_MALFORMED: 'assert_malformed' ;
183+
ASSERT_INVALID: 'assert_invalid' ;
184+
ASSERT_UNLINKABLE: 'assert_unlinkable' ;
185+
ASSERT_RETURN: 'assert_return' ;
186+
ASSERT_RETURN_CANONICAL_NAN: 'assert_return_canonical_nan' ;
187+
ASSERT_RETURN_ARITHMETIC_NAN: 'assert_return_arithmetic_nan' ;
188+
ASSERT_TRAP: 'assert_trap' ;
189+
ASSERT_EXHAUSTION: 'assert_exhaustion' ;
190+
INPUT: 'input' ;
191+
OUTPUT: 'output' ;
192+
193+
VAR : Name ;
194+
195+
SPACE
196+
: [ \t\r\n] -> skip
197+
;
198+
199+
COMMENT
200+
: ( '(;' .*? ';)'
201+
| ';;' .*? '\n')-> skip
202+
;
203+
204+
fragment Symbol
205+
: '.' | '+' | '-' | '*' | '/' | '\\' | '^' | '~' | '=' | '<' | '>' | '!' | '?' | '@' | '#' | '$' | '%' | '&' | '|' | ':' | '\'' | '`'
206+
;
207+
208+
fragment Num
209+
: Digit ('_'? Digit)*
210+
;
211+
212+
fragment HexNum
213+
: HexDigit ('_'? HexDigit)*
214+
;
215+
216+
fragment Sign
217+
: '+' | '-'
218+
;
219+
220+
fragment Digit
221+
: [0-9]
222+
;
223+
224+
fragment HexDigit
225+
: [0-9a-fA-F]
226+
;
227+
228+
fragment Letter
229+
: [a-zA-Z]
230+
;
231+
232+
fragment Nat : Num | ('0x' HexNum) ;
233+
fragment Int : Sign Nat ;
234+
fragment Frac : Num ;
235+
fragment HexFrac : HexNum ;
236+
237+
fragment Float
238+
: Sign? Num '.' Frac?
239+
| Sign? Num ('.' Frac?)? ('e' | 'E') Sign? Num
240+
| Sign? '0x' HexNum '.' HexFrac?
241+
| Sign? '0x' HexNum ('.' HexFrac?)? ('p' | 'P') Sign? Num
242+
| Sign? 'inf'
243+
| Sign? 'nan'
244+
| Sign? 'nan:' '0x' HexNum
245+
;
246+
247+
fragment String
248+
: '"' ( Char | '\n' | '\t' | '\\' | '\'' | '\\' HexDigit HexDigit | '\\u{' HexDigit+ '}' )* '"'
249+
;
250+
251+
fragment Name
252+
: '$' (Letter | Digit | '_' | Symbol)+
253+
;
254+
255+
fragment Escape : [nrt'"\\] ;
256+
257+
fragment IXX : 'i' ('32' | '64') ;
258+
fragment FXX : 'f' ('32' | '64') ;
259+
fragment NXX : IXX | FXX ;
260+
fragment MIXX : 'i' ('8' | '16' | '32' | '64') ;
261+
fragment MFXX : 'f' ('32' | '64') ;
262+
fragment SIGN : 's' | 'u' ;
263+
fragment MEM_SIZE : '8' | '16' | '32' ;
264+
265+
fragment Char : ~["'\\\u0000-\u001f\u007f-\u00ff] ;
266+
fragment Ascii : [\u0000-\u007f] ;
267+
fragment Ascii_no_nl : [\u0000-\u0009\u000b-\u007f] ;
268+
fragment Utf8Cont : [\u0080-\u00bf] ;
269+
fragment Utf8 : Ascii | Utf8Enc ;
270+
fragment Utf8_no_nl : Ascii_no_nl | Utf8Enc ;
271+
272+
fragment Utf8Enc
273+
: [\u00c2-\u00df] Utf8Cont
274+
| [\u00e0] [\u00a0-\u00bf] Utf8Cont
275+
| [\u00ed] [\u0080-\u009f] Utf8Cont
276+
| [\u00e1-\u00ec\u00ee-\u00ef] Utf8Cont Utf8Cont
277+
| [\u00f0] [\u0090-\u00bf] Utf8Cont Utf8Cont
278+
| [\u00f4] [\u0080-\u008f] Utf8Cont Utf8Cont
279+
| [\u00f1-\u00f3] Utf8Cont Utf8Cont Utf8Cont
280+
;

0 commit comments

Comments
 (0)