Repository navigation
Expand file tree
/
Copy pathParserOptions.java
More file actions
451 lines (399 loc) · 18.4 KB
/
Copy pathParserOptions.java
File metadata and controls
451 lines (399 loc) · 18.4 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
package graphql.parser;
import graphql.PublicApi;
import java.util.function.Consumer;
import static graphql.Assert.assertNotNull;
/**
* Options that control how the {@link Parser} behaves.
*/
@PublicApi
public class ParserOptions {
/**
* A graphql hacking vector is to send nonsensical queries with large tokens that contain a repeated characters
* that burn lots of parsing CPU time and burn memory representing a document that won't ever execute.
* To prevent this for most users, graphql-java sets this value to 1MB.
* ANTLR parsing time is linear to the number of characters presented. The more you
* allow the longer it takes.
* <p>
* If you want to allow more, then {@link #setDefaultParserOptions(ParserOptions)} allows you to change this
* JVM wide.
*/
public static final int MAX_QUERY_CHARACTERS = 1024 * 1024; // 1 MB
/**
* A graphql hacking vector is to send nonsensical queries with lots of tokens that burn lots of parsing CPU time and burn
* memory representing a document that won't ever execute. To prevent this for most users, graphql-java
* sets this value to 15000. ANTLR parsing time is linear to the number of tokens presented. The more you
* allow the longer it takes.
* <p>
* If you want to allow more, then {@link #setDefaultParserOptions(ParserOptions)} allows you to change this
* JVM wide.
*/
public static final int MAX_QUERY_TOKENS = 15_000;
/**
* Another graphql hacking vector is to send large amounts of whitespace in operations that burn lots of parsing CPU time and burn
* memory representing a document. Whitespace token processing in ANTLR is 2 orders of magnitude faster than grammar token processing
* however it still takes some time to happen.
* <p>
* If you want to allow more, then {@link #setDefaultParserOptions(ParserOptions)} allows you to change this
* JVM wide.
*/
public static final int MAX_WHITESPACE_TOKENS = 200_000;
/**
* A numeric literal is represented by a single token, regardless of how many characters it contains. Converting
* very large numeric literals into arbitrary precision numbers can consume excessive CPU and memory. To prevent
* this for most users, graphql-java limits numeric literals to 100 characters.
* <p>
* If you want to allow more, then {@link #setDefaultParserOptions(ParserOptions)} allows you to change this
* JVM wide.
*/
public static final int MAX_NUMERIC_LITERAL_CHARACTERS = 100;
/**
* A graphql hacking vector is to send nonsensical queries that have lots of grammar rule depth to them which
* can cause stack overflow exceptions during the query parsing. To prevent this for most users, graphql-java
* sets this value to 500 grammar rules deep.
* <p>
* If you want to allow more, then {@link #setDefaultParserOptions(ParserOptions)} allows you to change this
* JVM wide.
*/
public static final int MAX_RULE_DEPTH = 500;
private static ParserOptions defaultJvmParserOptions = newParserOptions()
.captureIgnoredChars(false)
.captureSourceLocation(true)
.captureLineComments(true)
.readerTrackData(true)
.maxCharacters(MAX_QUERY_CHARACTERS)
.maxTokens(MAX_QUERY_TOKENS) // to prevent a billion laughs style attacks, we set a default for graphql-java
.maxWhitespaceTokens(MAX_WHITESPACE_TOKENS)
.maxNumericLiteralCharacters(MAX_NUMERIC_LITERAL_CHARACTERS)
.maxRuleDepth(MAX_RULE_DEPTH)
.redactTokenParserErrorMessages(false)
.build();
private static ParserOptions defaultJvmOperationParserOptions = newParserOptions()
.captureIgnoredChars(false)
.captureSourceLocation(true)
.captureLineComments(false) // #comments are not useful in query parsing
.readerTrackData(true)
.maxCharacters(MAX_QUERY_CHARACTERS)
.maxTokens(MAX_QUERY_TOKENS) // to prevent a billion laughs style attacks, we set a default for graphql-java
.maxWhitespaceTokens(MAX_WHITESPACE_TOKENS)
.maxNumericLiteralCharacters(MAX_NUMERIC_LITERAL_CHARACTERS)
.maxRuleDepth(MAX_RULE_DEPTH)
.redactTokenParserErrorMessages(false)
.build();
private static ParserOptions defaultJvmSdlParserOptions = newParserOptions()
.captureIgnoredChars(false)
.captureSourceLocation(true)
.captureLineComments(true) // #comments are useful in SDL parsing
.readerTrackData(true)
.maxCharacters(Integer.MAX_VALUE)
.maxTokens(Integer.MAX_VALUE) // we are less worried about a billion laughs with SDL parsing since the call path is not facing attackers
.maxWhitespaceTokens(Integer.MAX_VALUE)
.maxNumericLiteralCharacters(MAX_NUMERIC_LITERAL_CHARACTERS)
.maxRuleDepth(Integer.MAX_VALUE)
.redactTokenParserErrorMessages(false)
.build();
/**
* By default, the Parser will not capture ignored characters. A static holds this default
* value in a JVM wide basis options object.
*
* Significant memory savings can be made if we do NOT capture ignored characters,
* especially in SDL parsing.
*
* @return the static default JVM value
*
* @see graphql.language.IgnoredChar
* @see graphql.language.SourceLocation
*/
public static ParserOptions getDefaultParserOptions() {
return defaultJvmParserOptions;
}
/**
* By default, the Parser will not capture ignored characters. A static holds this default
* value in a JVM wide basis options object.
*
* Significant memory savings can be made if we do NOT capture ignored characters,
* especially in SDL parsing. So we have set this to false by default.
*
* This static can be set to true to allow the behavior of version 16.x or before.
*
* @param options - the new default JVM parser options
*
* @see graphql.language.IgnoredChar
* @see graphql.language.SourceLocation
*/
public static void setDefaultParserOptions(ParserOptions options) {
defaultJvmParserOptions = assertNotNull(options);
}
/**
* By default, for operation parsing, the Parser will not capture ignored characters, and it will not capture line comments into AST
* elements . A static holds this default value for operation parsing in a JVM wide basis options object.
*
* @return the static default JVM value for operation parsing
*
* @see graphql.language.IgnoredChar
* @see graphql.language.SourceLocation
*/
public static ParserOptions getDefaultOperationParserOptions() {
return defaultJvmOperationParserOptions;
}
/**
* By default, the Parser will not capture ignored characters or line comments. A static holds this default
* value in a JVM wide basis options object for operation parsing.
*
* This static can be set to true to allow the behavior of version 16.x or before.
*
* @param options - the new default JVM parser options for operation parsing
*
* @see graphql.language.IgnoredChar
* @see graphql.language.SourceLocation
*/
public static void setDefaultOperationParserOptions(ParserOptions options) {
defaultJvmOperationParserOptions = assertNotNull(options);
}
/**
* By default, for SDL parsing, the Parser will not capture ignored characters, but it will capture line comments into AST
* elements. The SDL default options allow unlimited tokens and whitespace, since a DOS attack vector is
* not commonly available via schema SDL parsing.
*
* A static holds this default value for SDL parsing in a JVM wide basis options object.
*
* @return the static default JVM value for SDL parsing
*
* @see graphql.language.IgnoredChar
* @see graphql.language.SourceLocation
* @see graphql.schema.idl.SchemaParser
*/
public static ParserOptions getDefaultSdlParserOptions() {
return defaultJvmSdlParserOptions;
}
/**
* By default, for SDL parsing, the Parser will not capture ignored characters, but it will capture line comments into AST
* elements . A static holds this default value for operation parsing in a JVM wide basis options object.
*
* This static can be set to true to allow the behavior of version 16.x or before.
*
* @param options - the new default JVM parser options for SDL parsing
*
* @see graphql.language.IgnoredChar
* @see graphql.language.SourceLocation
*/
public static void setDefaultSdlParserOptions(ParserOptions options) {
defaultJvmSdlParserOptions = assertNotNull(options);
}
private final boolean captureIgnoredChars;
private final boolean captureSourceLocation;
private final boolean captureLineComments;
private final boolean readerTrackData;
private final int maxCharacters;
private final int maxTokens;
private final int maxWhitespaceTokens;
private final int maxNumericLiteralCharacters;
private final int maxRuleDepth;
private final boolean redactTokenParserErrorMessages;
private final ParsingListener parsingListener;
private ParserOptions(Builder builder) {
this.captureIgnoredChars = builder.captureIgnoredChars;
this.captureSourceLocation = builder.captureSourceLocation;
this.captureLineComments = builder.captureLineComments;
this.readerTrackData = builder.readerTrackData;
this.maxCharacters = builder.maxCharacters;
this.maxTokens = builder.maxTokens;
this.maxWhitespaceTokens = builder.maxWhitespaceTokens;
this.maxNumericLiteralCharacters = builder.maxNumericLiteralCharacters;
this.maxRuleDepth = builder.maxRuleDepth;
this.redactTokenParserErrorMessages = builder.redactTokenParserErrorMessages;
this.parsingListener = builder.parsingListener;
}
/**
* Significant memory savings can be made if we do NOT capture ignored characters,
* especially in SDL parsing. So we have set this to false by default.
*
* @return true if ignored chars should be captured as AST nodes
*/
public boolean isCaptureIgnoredChars() {
return captureIgnoredChars;
}
/**
* Memory savings can be made if we do NOT set {@link graphql.language.SourceLocation}s
* on AST nodes, especially in SDL parsing.
*
* @return true if {@link graphql.language.SourceLocation}s should be captured as AST nodes
*
* @see graphql.language.SourceLocation
*/
public boolean isCaptureSourceLocation() {
return captureSourceLocation;
}
/**
* Single-line {@link graphql.language.Comment}s do not have any semantic meaning in
* GraphQL source documents, as such you may wish to ignore them.
* <p>
* This option does not ignore documentation {@link graphql.language.Description}s.
*
* @return true if {@link graphql.language.Comment}s should be captured as AST nodes
*
* @see graphql.language.SourceLocation
*/
public boolean isCaptureLineComments() {
return captureLineComments;
}
/**
* Controls whether the underlying {@link MultiSourceReader} should track previously read data or not.
*
* @return true if {@link MultiSourceReader} should track data in memory.
*/
public boolean isReaderTrackData() {
return readerTrackData;
}
/**
* A graphql hacking vector is to send nonsensical queries that contain a repeated characters that burn lots of parsing CPU time and burn
* memory representing a document that won't ever execute. To prevent this for most users, graphql-java
* sets this value to 1MB.
*
* @return the maximum number of characters the parser will accept, after which an exception will be thrown.
*/
public int getMaxCharacters() {
return maxCharacters;
}
/**
* A graphql hacking vector is to send nonsensical queries that burn lots of parsing CPU time and burns
* memory representing a document that won't ever execute. To prevent this you can set a maximum number of parse
* tokens that will be accepted before an exception is thrown and the parsing is stopped.
*
* @return the maximum number of raw tokens the parser will accept, after which an exception will be thrown.
*/
public int getMaxTokens() {
return maxTokens;
}
/**
* A graphql hacking vector is to send larges amounts of whitespace that burn lots of parsing CPU time and burn
* memory representing a document. To prevent this you can set a maximum number of whitespace parse
* tokens that will be accepted before an exception is thrown and the parsing is stopped.
*
* @return the maximum number of raw whitespace tokens the parser will accept, after which an exception will be thrown.
*/
public int getMaxWhitespaceTokens() {
return maxWhitespaceTokens;
}
/**
* A numeric literal is represented by a single token, regardless of how many characters it contains. Converting
* very large numeric literals into arbitrary precision numbers can consume excessive CPU and memory. This limit
* stops parsing before that conversion takes place.
*
* @return the maximum number of characters permitted in an integer or floating-point literal
*/
public int getMaxNumericLiteralCharacters() {
return maxNumericLiteralCharacters;
}
/**
* A graphql hacking vector is to send nonsensical queries that have lots of rule depth to them which
* can cause stack overflow exceptions during the query parsing. To prevent this you can set a value
* that is the maximum depth allowed before an exception is thrown and the parsing is stopped.
*
* @return the maximum token depth the parser will accept, after which an exception will be thrown.
*/
public int getMaxRuleDepth() {
return maxRuleDepth;
}
/**
* Option to redact offending tokens in parser error messages.
* By default, the parser will include the offending token in the error message, if possible.
*
* @return true if the token parser messages should be redacted
*/
public boolean isRedactTokenParserErrorMessages() {
return redactTokenParserErrorMessages;
}
public ParsingListener getParsingListener() {
return parsingListener;
}
public ParserOptions transform(Consumer<Builder> builderConsumer) {
Builder builder = new Builder(this);
builderConsumer.accept(builder);
return builder.build();
}
public static Builder newParserOptions() {
return new Builder();
}
public static class Builder {
private boolean captureIgnoredChars = false;
private boolean captureSourceLocation = true;
private boolean captureLineComments = true;
private boolean readerTrackData = true;
private ParsingListener parsingListener = ParsingListener.NOOP;
private int maxCharacters = MAX_QUERY_CHARACTERS;
private int maxTokens = MAX_QUERY_TOKENS;
private int maxWhitespaceTokens = MAX_WHITESPACE_TOKENS;
private int maxNumericLiteralCharacters = MAX_NUMERIC_LITERAL_CHARACTERS;
private int maxRuleDepth = MAX_RULE_DEPTH;
private boolean redactTokenParserErrorMessages = false;
Builder() {
}
Builder(ParserOptions parserOptions) {
this.captureIgnoredChars = parserOptions.captureIgnoredChars;
this.captureSourceLocation = parserOptions.captureSourceLocation;
this.captureLineComments = parserOptions.captureLineComments;
this.maxCharacters = parserOptions.maxCharacters;
this.maxTokens = parserOptions.maxTokens;
this.maxWhitespaceTokens = parserOptions.maxWhitespaceTokens;
this.maxNumericLiteralCharacters = parserOptions.maxNumericLiteralCharacters;
this.maxRuleDepth = parserOptions.maxRuleDepth;
this.redactTokenParserErrorMessages = parserOptions.redactTokenParserErrorMessages;
this.parsingListener = parserOptions.parsingListener;
}
public Builder captureIgnoredChars(boolean captureIgnoredChars) {
this.captureIgnoredChars = captureIgnoredChars;
return this;
}
public Builder captureSourceLocation(boolean captureSourceLocation) {
this.captureSourceLocation = captureSourceLocation;
return this;
}
public Builder captureLineComments(boolean captureLineComments) {
this.captureLineComments = captureLineComments;
return this;
}
public Builder readerTrackData(boolean readerTrackData) {
this.readerTrackData = readerTrackData;
return this;
}
public Builder maxCharacters(int maxCharacters) {
this.maxCharacters = maxCharacters;
return this;
}
public Builder maxTokens(int maxTokens) {
this.maxTokens = maxTokens;
return this;
}
public Builder maxWhitespaceTokens(int maxWhitespaceTokens) {
this.maxWhitespaceTokens = maxWhitespaceTokens;
return this;
}
/**
* Sets the maximum number of characters permitted in an integer or floating-point literal. Parsing is
* cancelled before converting a larger literal into an arbitrary precision number.
*
* @param maxNumericLiteralCharacters the maximum number of characters permitted in a numeric literal
*
* @return this builder
*/
public Builder maxNumericLiteralCharacters(int maxNumericLiteralCharacters) {
this.maxNumericLiteralCharacters = maxNumericLiteralCharacters;
return this;
}
public Builder maxRuleDepth(int maxRuleDepth) {
this.maxRuleDepth = maxRuleDepth;
return this;
}
public Builder redactTokenParserErrorMessages(boolean redactTokenParserErrorMessages) {
this.redactTokenParserErrorMessages = redactTokenParserErrorMessages;
return this;
}
public Builder parsingListener(ParsingListener parsingListener) {
this.parsingListener = assertNotNull(parsingListener);
return this;
}
public ParserOptions build() {
return new ParserOptions(this);
}
}
}