/
grammar_fstrings.jjt
463 lines (420 loc) · 12.2 KB
/
grammar_fstrings.jjt
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
// Notes on the grammar:
// The target of this grammar is to be able to make the pre-parsing step of f-strings.
// It tries to handle any error in the parsing to generate a valid AST (and still makes
// those errors available for processing later on).
//
// Unlike the python grammar, it can't make strings a lexical entity because
// that's dependent upon the context -- we just want to create strings inside
// the expression part, out of it, we should just handle it as regular text.
//
// Also, if we have unbalanced chars for some expression, we generate the AST
// going to the end of the f-string (so, this would be an open partition) -- while
// properly generating errors.
//
// This grammar is expected to be used along with the regular Python grammar:
// after finding an f-string in the regular python grammar, it should be verified
// with this grammar (and expressions should be extracted based on this AST) and later
// on, each expression can be fed to the python grammar again (to eval_input).
//
// it's even interesting to note that f-strings are actually a disguised eval -- so, things
// such as:
//
// a = 10
// print(f'''{f"{f'{a}'}"}''')
//
// are actually possible -- this means that to check for syntax errors we may need to
// recursively check it (although that's a corner case, so, we may skip it initially).
//
// Known differences from the 'official version':
//
// f' <text> { <expression> <optional !s, !r, or !a> <optional : format specifier> } <text>
//
// the optional versions can't have any space between them and the ending '}', whereas
// this grammar lets that happen (spaces are always skipped).
//
// i.e.: f'''{text !r }''' -- this is not valid in the regular version but is valid in this one.
options
{
// only non-defaults are given here.
NODE_SCOPE_HOOK = true; // call jjtree*NodeScope()
NODE_FACTORY = true;
NODE_USES_PARSER = true;
STATIC = false; // multiple parsers
COMMON_TOKEN_ACTION = true; // CommonTokenAction(Token)
DEBUG_PARSER = false; // must be used to enable tracing
DEBUG_LOOKAHEAD = false;
DEBUG_TOKEN_MANAGER = false; // used to debug the tokens we have generating
USER_CHAR_STREAM = true;
UNICODE_INPUT = true;
ERROR_REPORTING = true; // this is NOT used to shut down errors regarding javacc org.python.pydev.parser.jython.PythonGrammar$LookaheadSuccess
// because the generated information is not complete enough if we do it.
}
PARSER_BEGIN(FStringsGrammar)
package org.python.pydev.parser.grammar_fstrings;
import org.python.pydev.parser.jython.FastCharStream;
import org.python.pydev.shared_core.string.FastStringBuffer;
import org.python.pydev.parser.jython.ParseException;
import org.python.pydev.parser.jython.Token;
import org.python.pydev.parser.fastparser.grammar_fstrings_common.AbstractFStringsGrammar;
import org.python.pydev.parser.fastparser.grammar_fstrings_common.AbstractFStringsTokenManager;
import org.python.pydev.parser.fastparser.grammar_fstrings_common.JJTFStringsGrammarState;
import org.python.pydev.parser.fastparser.grammar_fstrings_common.Node;
import org.python.pydev.parser.fastparser.grammar_fstrings_common.SimpleNode;
import org.python.pydev.parser.fastparser.grammar_fstrings_common.FStringsAST;
public final class FStringsGrammar extends AbstractFStringsGrammar
{
}
PARSER_END(FStringsGrammar)
TOKEN_MGR_DECLS:
{
/**
* Called right after the creation of any token.
*/
protected final void CommonTokenAction(final Token initial) {
}
}
// ============= Lexical actions =============
SKIP: { " " | "\t" | "\n" | "\r" }
TOKEN : // What we care for.
{
< LPAREN: "(" >
| < RPAREN: ")" >
| < LBRACE: "{" >
| < RBRACE: "}" >
| < LBRACKET: "[" >
| < RBRACKET: "]" >
| < EXCLAMATION: "!" >
| < COLON: ":" >
| < QUOTE: "'" >
| < QUOTE2: "\"" >
| < BACKSLASH: "\\" >
}
TOKEN : // Anything which is not important but is a visible char should be marked as regular text.
{
<TEXT : ([
//0 - 32: space-related chars (we already skip the important ones, such as space and tab, others are invalid).
//33 = ! (exclamation)
//34 = " (quote)
"#"-"&", // 35 - 38
//39 = ' (single quote)
// 40, 41 = () (parenthesis)
"*"-"/", // 42 - 47
"0"-"9", // 48 - 57
//: = 58
";"-"@", // 59 - 64
"A"-"Z", // 65 - 90
// 91 == [
// 92 == \
// 93 = ]
"^"-"`", // 94 - 96
"a"-"z", // 97 - 122
// 123 = {
"|", // 124
// 125 = }
"~", // 126
// 127 = DEL (invisible)
"\u0080"-"\uffff" //Anything more than 128 is considered valid (unicode range)
])+ >
}
// ============= Syntatic/Semantic actions =============
FStringsAST f_string(): {Token t; Token doubleRbrace=null;}
{
(
f_string_expr()
|<TEXT>
|<QUOTE>
|<QUOTE2>
|<EXCLAMATION>
|<COLON>
|<BACKSLASH>
|<LPAREN>
|<RPAREN>
|<LBRACKET>
|<RBRACKET>
|t=<RBRACE> {doubleRbrace=null;} (doubleRbrace=<RBRACE>)? {
if(doubleRbrace == null) addParseError(t, "Single '}' not allowed.");
}
)* <EOF>
// jjtree does most things automatically for us, so, just
// popping its final node should do the trick for a reasonable AST.
// Note that we may need to mark the start/end of the nodes we're
// interested in (as jjtree.markNodeStartEnd).
{return new FStringsAST((SimpleNode)jjtree.popNode());}
}
void f_string_expr(): {Token start, end, bStart;boolean empty=true;SimpleNode bText;}
{
start = <LBRACE>
try{
(
(
{
bStart=getToken(1);
if(bStart.kind==LBRACE && bStart.beginColumn==start.beginColumn+1) {
// If we found 2 consecutive {{ it's an escaped {.
jj_consume_token(LBRACE);
throw DOUBLE_LBRACE_FOUND;
}
}
bText=balanced_expression_text()
{
empty=false;
}
)?
(type_conversion())?
(format_spec())?
try{
end = <RBRACE>
}catch(ParseException e){
addParseError(e, "Unbalanced '{'");
end = token;
}
{
jjtree.markNodeStartEnd(jjtThis, start, end);
if(empty){
errorPyExprEmpty(jjtThis);
}
}
)
}catch(DoubleLBraceFound e){
// Found double brace (not really an expression).
jjtree.markNodeStartEnd(jjtThis, start, start);
}
}
void type_conversion(): {Token t;boolean foundText=false;}
{
<EXCLAMATION>
(
t=<TEXT> {errorIfTextIsNotASR(t);}
{foundText=true;}
// It can't really be empty, but we make this node optional to generate a nice AST
// and then report the error later on.
)?
{if(!foundText){errorTypeConversionEmpty(jjtThis);}}
}
void format_spec(): {Token start, end, bStart;boolean empty=true;SimpleNode bText; Token t;}
{
<COLON>
(
(<TEXT> | <COLON>)+
|
start = <LBRACE>
try{
(
(
{
bStart=getToken(1);
if(bStart.kind==LBRACE && bStart.beginColumn==start.beginColumn+1) {
// If we found 2 consecutive {{ it's an escaped {.
jj_consume_token(LBRACE);
throw DOUBLE_LBRACE_FOUND;
}
}
bText=balanced_expression_text()
{
empty=false;
}
)?
try{
end = <RBRACE>
}catch(ParseException e){
addParseError(e, "Unbalanced '{'");
end = token;
}
{
jjtree.markNodeStartEnd(jjtThis, start, end);
if(empty){
errorPyExprEmpty(jjtThis);
}
}
)
}catch(DoubleLBraceFound e){
// Found double brace (not really an expression).
jjtree.markNodeStartEnd(jjtThis, start, start);
}
|
string()
|
string2()
|
t = <BACKSLASH> {errorBackSlashInvalidInFStrings(t);}
)*
}
SimpleNode balanced_expression_text(): {Token start; Token end; Token t;}
{
{
start = getToken(1);
}
(
initial_balanced_expression_text()
|
string()
|
string2()
|
// The main difference from this one to inner_balanced_expression_text_with_exclamation_and_colon
// is that at this level an exclamation or colon shoud not be matched, whereas in the next one it
// can be matched (so, the user can do f"{{'c':20}}").
(<TEXT>)+
|
t = <BACKSLASH> {errorBackSlashInvalidInFStrings(t);}
)+
{
end = token;
jjtree.markNodeStartEnd(jjtThis, start, end);
}
{return (SimpleNode)jjtree.peekNode();}
}
SimpleNode initial_balanced_expression_text(): {Token start; Token end;}
{
{
start = getToken(1);
}
(
(
<LPAREN>
(inner_balanced_expression_text_with_exclamation_and_colon())*
try{
<RPAREN>
}catch(ParseException e){
addParseError(e, "Unbalanced '('");
}
)
|
(
<LBRACE>
(inner_balanced_expression_text_with_exclamation_and_colon())*
try{
<RBRACE>
}catch(ParseException e){
addParseError(e, "Unbalanced '{'");
}
)
|
(
<LBRACKET>
(inner_balanced_expression_text_with_exclamation_and_colon())*
try{
<RBRACKET>
}catch(ParseException e){
addParseError(e, "Unbalanced '['");
}
)
)
{
end = token;
jjtree.markNodeStartEnd(jjtThis, start, end);
}
{return (SimpleNode)jjtree.peekNode();}
}
SimpleNode inner_balanced_expression_text_with_exclamation_and_colon(): {Token start; Token end; Token t;}
{
{
start = getToken(1);
}
(
(
<LPAREN>
(inner_balanced_expression_text_with_exclamation_and_colon())*
try{
<RPAREN>
}catch(ParseException e){
addParseError(e, "Unbalanced '('");
}
)
|
(
<LBRACE>
(inner_balanced_expression_text_with_exclamation_and_colon())*
try{
<RBRACE>
}catch(ParseException e){
addParseError(e, "Unbalanced '{'");
}
)
|
(
<LBRACKET>
(inner_balanced_expression_text_with_exclamation_and_colon())*
try{
<RBRACKET>
}catch(ParseException e){
addParseError(e, "Unbalanced '['");
}
)
|
string()
|
string2()
|
(
<TEXT>
|<EXCLAMATION>
|<COLON>
)+
|
t = <BACKSLASH> {errorBackSlashInvalidInFStrings(t);}
)
{
end = token;
jjtree.markNodeStartEnd(jjtThis, start, end);
}
{return (SimpleNode)jjtree.peekNode();}
}
void string(): {Token start; Token end; Token t;}
{
{
start = getToken(1);
}
<QUOTE>
(
<TEXT>
|<LPAREN>
|<RPAREN>
|<LBRACE>
|<RBRACE>
|<LBRACKET>
|<RBRACKET>
|<QUOTE2>
|<EXCLAMATION>
|<COLON>
|t = <BACKSLASH> {errorBackSlashInvalidInFStrings(t);}
)*
try{
<QUOTE>
}catch(ParseException e){
addParseError(e, "Unbalanced \"'\"");
}
{
end = token;
jjtree.markNodeStartEnd(jjtThis, start, end);
}
}
void string2(): {Token start; Token end; Token t;}
{
{
start = getToken(1);
}
<QUOTE2>
(
<TEXT>
|<LPAREN>
|<RPAREN>
|<LBRACE>
|<RBRACE>
|<LBRACKET>
|<RBRACKET>
|<QUOTE>
|<EXCLAMATION>
|<COLON>
|t = <BACKSLASH> {errorBackSlashInvalidInFStrings(t);}
)*
try{
<QUOTE2>
}catch(ParseException e){
addParseError(e, "Unbalanced '\"'");
}
{
end = token;
jjtree.markNodeStartEnd(jjtThis, start, end);
}
}