-
Notifications
You must be signed in to change notification settings - Fork 39
Expand file tree
/
Copy pathLexer.java
More file actions
645 lines (595 loc) · 16.4 KB
/
Copy pathLexer.java
File metadata and controls
645 lines (595 loc) · 16.4 KB
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
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
// Copyright 2026 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// https://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package dev.cel.parser;
import com.google.common.collect.ImmutableMap;
import dev.cel.common.internal.CelCodePointArray;
import java.util.function.IntPredicate;
import org.jspecify.annotations.Nullable;
/**
* Fast lexer for CEL expressions.
*
* <p>Ported from {@code third_party/cel/cpp/parser/internal/lexer.h} and {@code lexer.cc}.
*/
final class Lexer {
enum TokenType {
ERROR("error"),
END("end"),
// Keywords
NULL("null"),
FALSE("false"),
TRUE("true"),
IN("in"),
RESERVED_WORD("reserved_word"),
// Literals
INT("int"),
UINT("uint"),
FLOAT("float"),
STRING("string"),
BYTES("bytes"),
// Identifiers
IDENT("ident"),
// Delimiters
LEFT_BRACKET("["),
RIGHT_BRACKET("]"),
LEFT_BRACE("{"),
RIGHT_BRACE("}"),
LEFT_PAREN("("),
RIGHT_PAREN(")"),
// Operators
DOT("."),
COMMA(","),
MINUS("-"),
PLUS("+"),
ASTERISK("*"),
SLASH("/"),
PERCENT("%"),
QUESTION("?"),
COLON(":"),
EXCLAMATION("!"),
EQUAL("="),
EQUAL_EQUAL("=="),
EXCLAMATION_EQUAL("!="),
LESS("<"),
LESS_EQUAL("<="),
GREATER(">"),
GREATER_EQUAL(">="),
LOGICAL_AND("&&"),
LOGICAL_OR("||");
private final String symbol;
TokenType(String symbol) {
this.symbol = symbol;
}
public String getSymbol() {
return symbol;
}
@Override
public String toString() {
return symbol;
}
}
static final class Token {
final TokenType type;
final int start;
final int end;
final @Nullable String text;
Token(TokenType type, int start, int end) {
this(type, start, end, null);
}
Token(TokenType type, int start, int end, @Nullable String text) {
this.type = type;
this.start = start;
this.end = end;
this.text = text;
}
@Override
public String toString() {
return "Token(" + type + ", " + start + ", " + end + ")";
}
}
static final class LexerError {
final int start;
final int end;
final String message;
LexerError(int start, int end, String message) {
this.start = start;
this.end = end;
this.message = message;
}
}
private static final ImmutableMap<String, TokenType> KEYWORDS =
ImmutableMap.<String, TokenType>builder()
.put("false", TokenType.FALSE)
.put("true", TokenType.TRUE)
.put("null", TokenType.NULL)
.put("in", TokenType.IN)
.put("as", TokenType.RESERVED_WORD)
.put("break", TokenType.RESERVED_WORD)
.put("const", TokenType.RESERVED_WORD)
.put("continue", TokenType.RESERVED_WORD)
.put("else", TokenType.RESERVED_WORD)
.put("for", TokenType.RESERVED_WORD)
.put("function", TokenType.RESERVED_WORD)
.put("if", TokenType.RESERVED_WORD)
.put("import", TokenType.RESERVED_WORD)
.put("let", TokenType.RESERVED_WORD)
.put("loop", TokenType.RESERVED_WORD)
.put("package", TokenType.RESERVED_WORD)
.put("namespace", TokenType.RESERVED_WORD)
.put("return", TokenType.RESERVED_WORD)
.put("var", TokenType.RESERVED_WORD)
.put("void", TokenType.RESERVED_WORD)
.put("while", TokenType.RESERVED_WORD)
.buildOrThrow();
private final CelCodePointArray content;
private final int size;
private int position;
private LexerError error;
Lexer(CelCodePointArray content) {
this.content = content;
this.size = content.size();
this.position = 0;
this.error = null;
}
Token lex() {
consumeWhitespaceAndComments();
int start = position;
if (position >= size) {
return makeToken(TokenType.END, start, start);
}
int c = content.get(position);
switch (c) {
case '.':
{
if (position + 1 < size && isDigit(content.get(position + 1))) {
return consumeNumericLiteral();
}
advance(1);
return makeToken(TokenType.DOT, start, position);
}
case ',':
{
advance(1);
return makeToken(TokenType.COMMA, start, position);
}
case '!':
{
advance(1);
if (consume('=')) {
return makeToken(TokenType.EXCLAMATION_EQUAL, start, position);
}
return makeToken(TokenType.EXCLAMATION, start, position);
}
case '?':
{
advance(1);
return makeToken(TokenType.QUESTION, start, position);
}
case '(':
{
advance(1);
return makeToken(TokenType.LEFT_PAREN, start, position);
}
case ')':
{
advance(1);
return makeToken(TokenType.RIGHT_PAREN, start, position);
}
case '{':
{
advance(1);
return makeToken(TokenType.LEFT_BRACE, start, position);
}
case '}':
{
advance(1);
return makeToken(TokenType.RIGHT_BRACE, start, position);
}
case '[':
{
advance(1);
return makeToken(TokenType.LEFT_BRACKET, start, position);
}
case ']':
{
advance(1);
return makeToken(TokenType.RIGHT_BRACKET, start, position);
}
case '=':
{
advance(1);
if (consume('=')) {
return makeToken(TokenType.EQUAL_EQUAL, start, position);
}
return makeToken(TokenType.EQUAL, start, position);
}
case '<':
{
advance(1);
if (consume('=')) {
return makeToken(TokenType.LESS_EQUAL, start, position);
}
return makeToken(TokenType.LESS, start, position);
}
case '>':
{
advance(1);
if (consume('=')) {
return makeToken(TokenType.GREATER_EQUAL, start, position);
}
return makeToken(TokenType.GREATER, start, position);
}
case ':':
{
advance(1);
return makeToken(TokenType.COLON, start, position);
}
case '%':
{
advance(1);
return makeToken(TokenType.PERCENT, start, position);
}
case '+':
{
advance(1);
return makeToken(TokenType.PLUS, start, position);
}
case '-':
{
advance(1);
return makeToken(TokenType.MINUS, start, position);
}
case '*':
{
advance(1);
return makeToken(TokenType.ASTERISK, start, position);
}
case '/':
{
advance(1);
return makeToken(TokenType.SLASH, start, position);
}
case '&':
{
advance(1);
if (consume('&')) {
return makeToken(TokenType.LOGICAL_AND, start, position);
}
return setError(start, position, "unexpected single '&', expected '&&'");
}
case '|':
{
advance(1);
if (consume('|')) {
return makeToken(TokenType.LOGICAL_OR, start, position);
}
return setError(start, position, "unexpected single '|', expected '||'");
}
case '_':
{
return consumeIdent();
}
case '`':
{
return consumeQuotedIdent();
}
case '\'':
{
return consumeStringLiteral(start, '\'', false, false);
}
case '"':
{
return consumeStringLiteral(start, '"', false, false);
}
case 'r':
case 'R':
case 'b':
case 'B':
{
Token token = consumePrefixedStringLiteral();
if (token != null) {
return token;
}
break;
}
default:
break;
}
if (isDigit(c)) {
return consumeNumericLiteral();
}
if (isAlpha(c)) {
return consumeIdent();
}
advance(1);
return setError(start, position, "unexpected character");
}
LexerError getError() {
return error;
}
int savePosition() {
return position;
}
void restorePosition(int pos) {
this.position = pos;
}
private static boolean isDigit(int c) {
return c >= '0' && c <= '9';
}
private static boolean isHexDigit(int c) {
return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F');
}
private static boolean isAlpha(int c) {
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
}
private static boolean isIdentTrailing(int c) {
return isDigit(c) || isAlpha(c) || c == '_';
}
private static boolean isPlusOrMinus(int c) {
return c == '+' || c == '-';
}
private Token makeToken(TokenType type, int start, int end) {
return new Token(type, start, end);
}
private Token makeToken(TokenType type, int start, int end, @Nullable String text) {
return new Token(type, start, end, text);
}
private Token setError(int start, int end, String message) {
this.error = new LexerError(start, end, message);
return new Token(TokenType.ERROR, start, end);
}
private void advance(int n) {
position += n;
}
private boolean match(int c) {
return position < size && content.get(position) == c;
}
private boolean consume(int c) {
if (match(c)) {
advance(1);
return true;
}
return false;
}
private boolean consumeIf(IntPredicate predicate) {
if (position < size) {
int cp = content.get(position);
if (predicate.test(cp)) {
advance(1);
return true;
}
}
return false;
}
private void consumeLine() {
while (position < size) {
if (content.get(position) == '\n') {
advance(1);
return;
}
advance(1);
}
}
private void consumeWhitespaceAndComments() {
while (position < size) {
int c = content.get(position);
switch (c) {
case '\f':
case '\n':
case ' ':
case '\r':
case 11: // \v
case '\t':
position++;
break;
case '/':
if (position + 1 < size && content.get(position + 1) == '/') {
consumeLine();
break;
} else {
return;
}
default:
return;
}
}
}
private boolean consumeDigits() {
int start = position;
while (position < size && isDigit(content.get(position))) {
position++;
}
return position > start;
}
private boolean consumeHexDigits() {
int start = position;
while (position < size && isHexDigit(content.get(position))) {
position++;
}
return position > start;
}
private TokenType consumeIntegralSuffix() {
if (consume('u') || consume('U')) {
return TokenType.UINT;
}
return TokenType.INT;
}
private Token consumeQuotedIdent() {
int start = position;
advance(1);
if (!consumeUntilAfter('`', /* isRaw= */ true)) {
return setError(start, position, "unterminated quoted identifier");
}
return makeToken(TokenType.IDENT, start, position);
}
private boolean consumeUntilAfter(int c, boolean isRaw) {
int pos = position;
boolean escaped = false;
while (pos < size) {
int cc = content.get(pos);
if (cc == '\n' || cc == '\r') {
position = pos;
return false;
}
if (!isRaw && cc == '\\') {
escaped = !escaped;
} else {
if (cc == c && (isRaw || !escaped)) {
position = pos + 1;
return true;
}
escaped = false;
}
pos++;
}
position = size;
return false;
}
private boolean consumeUntilAfterTripleQuote(int quote, boolean isRaw) {
int pos = position;
boolean escaped = false;
while (pos < size) {
int cc = content.get(pos);
if (!isRaw && cc == '\\') {
escaped = !escaped;
} else {
if ((isRaw || !escaped)
&& pos + 2 < size
&& cc == quote
&& content.get(pos + 1) == quote
&& content.get(pos + 2) == quote) {
position = pos + 3;
return true;
}
escaped = false;
}
pos++;
}
position = size;
return false;
}
private Token consumeStringLiteral(int start, int quote, boolean isBytes, boolean isRaw) {
advance(1);
boolean isTripleQuote =
position + 1 < size && content.get(position) == quote && content.get(position + 1) == quote;
if (isTripleQuote) {
advance(2);
if (!consumeUntilAfterTripleQuote(quote, isRaw)) {
return setError(
start,
position,
isBytes ? "unterminated bytes literal" : "unterminated string literal");
}
return makeToken(isBytes ? TokenType.BYTES : TokenType.STRING, start, position);
}
if (!consumeUntilAfter(quote, isRaw)) {
return setError(
start, position, isBytes ? "unterminated bytes literal" : "unterminated string literal");
}
return makeToken(isBytes ? TokenType.BYTES : TokenType.STRING, start, position);
}
private @Nullable Token consumePrefixedStringLiteral() {
int start = position;
if (position >= size) {
return null;
}
int c = content.get(position);
boolean isBytes = (c == 'b' || c == 'B');
boolean isRaw = (c == 'r' || c == 'R');
if (!isBytes && !isRaw) {
return null;
}
int lookahead = 1;
if (position + 1 < size) {
int c2 = content.get(position + 1);
if (isBytes ? (c2 == 'r' || c2 == 'R') : (c2 == 'b' || c2 == 'B')) {
isBytes = true;
isRaw = true;
lookahead = 2;
}
}
if (position + lookahead < size) {
int quote = content.get(position + lookahead);
if (quote == '"' || quote == '\'') {
advance(lookahead);
return consumeStringLiteral(start, quote, isBytes, isRaw);
}
}
return null;
}
private Token consumeNumericLiteral() {
int start = position;
int c = content.get(position);
boolean floatingPoint = false;
if (c == '.') {
floatingPoint = true;
advance(1);
if (!consumeDigits()) {
return setError(
start, position, "floating point literal missing digits after decimal separator");
}
} else {
advance(1);
if (c == '0' && consume('x')) {
if (!consumeHexDigits()) {
return setError(
start, position, "integral literal missing digits after hexadecimal separator");
}
TokenType tokenType = consumeIntegralSuffix();
if (consumeIf(Lexer::isIdentTrailing)) {
return setError(
start,
position,
tokenType.getSymbol() + " literal has unexpected trailing characters");
}
return makeToken(tokenType, start, position);
}
consumeDigits();
if (position < size
&& content.get(position) == '.'
&& position + 1 < size
&& isDigit(content.get(position + 1))) {
floatingPoint = true;
advance(1);
consumeDigits();
}
}
if (consume('e') || consume('E')) {
floatingPoint = true;
consumeIf(Lexer::isPlusOrMinus);
if (!consumeDigits()) {
return setError(
start, position, "floating point literal missing digits after exponent separator");
}
}
TokenType tokenType = floatingPoint ? TokenType.FLOAT : consumeIntegralSuffix();
if (consumeIf(Lexer::isIdentTrailing)) {
return setError(
start, position, tokenType.getSymbol() + " literal has unexpected trailing characters");
}
return makeToken(tokenType, start, position);
}
private Token consumeIdent() {
int start = position;
while (position < size && isIdentTrailing(content.get(position))) {
position++;
}
int end = position;
String word = content.substring(start, end);
TokenType keywordType = KEYWORDS.get(word);
if (keywordType != null) {
return makeToken(keywordType, start, end);
}
return makeToken(TokenType.IDENT, start, end, word);
}
}