| 1 | /* |
|---|---|
| 2 | * Copyright (C) 2007-2010 Júlio Vilmar Gesser. |
| 3 | * Copyright (C) 2011, 2013-2020 The JavaParser Team. |
| 4 | * |
| 5 | * This file is part of JavaParser. |
| 6 | * |
| 7 | * JavaParser can be used either under the terms of |
| 8 | * a) the GNU Lesser General Public License as published by |
| 9 | * the Free Software Foundation, either version 3 of the License, or |
| 10 | * (at your option) any later version. |
| 11 | * b) the terms of the Apache License |
| 12 | * |
| 13 | * You should have received a copy of both licenses in LICENCE.LGPL and |
| 14 | * LICENCE.APACHE. Please refer to those files for details. |
| 15 | * |
| 16 | * JavaParser is distributed in the hope that it will be useful, |
| 17 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 18 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 19 | * GNU Lesser General Public License for more details. |
| 20 | */ |
| 21 | |
| 22 | package com.github.javaparser; |
| 23 | |
| 24 | import com.github.javaparser.ParseResult.PostProcessor; |
| 25 | import com.github.javaparser.Providers.PreProcessor; |
| 26 | import com.github.javaparser.UnicodeEscapeProcessingProvider.PositionMapping; |
| 27 | import com.github.javaparser.ast.CompilationUnit; |
| 28 | import com.github.javaparser.ast.Node; |
| 29 | import com.github.javaparser.ast.validator.*; |
| 30 | import com.github.javaparser.printer.lexicalpreservation.LexicalPreservingPrinter; |
| 31 | import com.github.javaparser.resolution.SymbolResolver; |
| 32 | import com.github.javaparser.utils.LineSeparator; |
| 33 | import com.github.javaparser.version.Java10PostProcessor; |
| 34 | import com.github.javaparser.version.Java11PostProcessor; |
| 35 | import com.github.javaparser.version.Java12PostProcessor; |
| 36 | import com.github.javaparser.version.Java13PostProcessor; |
| 37 | import com.github.javaparser.version.Java14PostProcessor; |
| 38 | |
| 39 | import java.nio.charset.Charset; |
| 40 | import java.util.ArrayList; |
| 41 | import java.util.List; |
| 42 | import java.util.Optional; |
| 43 | |
| 44 | import static com.github.javaparser.ParserConfiguration.LanguageLevel.JAVA_8; |
| 45 | |
| 46 | /** |
| 47 | * The configuration that is used by the parser. |
| 48 | * Note that this can be changed even when reusing the same JavaParser instance. |
| 49 | * It will pick up the changes. |
| 50 | */ |
| 51 | public class ParserConfiguration { |
| 52 | |
| 53 | public enum LanguageLevel { |
| 54 | /** |
| 55 | * Java 1.0 |
| 56 | */ |
| 57 | JAVA_1_0(new Java1_0Validator(), null), |
| 58 | /** |
| 59 | * Java 1.1 |
| 60 | */ |
| 61 | JAVA_1_1(new Java1_1Validator(), null), |
| 62 | /** |
| 63 | * Java 1.2 |
| 64 | */ |
| 65 | JAVA_1_2(new Java1_2Validator(), null), |
| 66 | /** |
| 67 | * Java 1.3 |
| 68 | */ |
| 69 | JAVA_1_3(new Java1_3Validator(), null), |
| 70 | /** |
| 71 | * Java 1.4 |
| 72 | */ |
| 73 | JAVA_1_4(new Java1_4Validator(), null), |
| 74 | /** |
| 75 | * Java 5 |
| 76 | */ |
| 77 | JAVA_5(new Java5Validator(), null), |
| 78 | /** |
| 79 | * Java 6 |
| 80 | */ |
| 81 | JAVA_6(new Java6Validator(), null), |
| 82 | /** |
| 83 | * Java 7 |
| 84 | */ |
| 85 | JAVA_7(new Java7Validator(), null), |
| 86 | /** |
| 87 | * Java 8 |
| 88 | */ |
| 89 | JAVA_8(new Java8Validator(), null), |
| 90 | /** |
| 91 | * Java 9 |
| 92 | */ |
| 93 | JAVA_9(new Java9Validator(), null), |
| 94 | /** |
| 95 | * Java 10 |
| 96 | */ |
| 97 | JAVA_10(new Java10Validator(), new Java10PostProcessor()), |
| 98 | /** |
| 99 | * Java 11 |
| 100 | */ |
| 101 | JAVA_11(new Java11Validator(), new Java11PostProcessor()), |
| 102 | /** |
| 103 | * Java 12 |
| 104 | */ |
| 105 | JAVA_12(new Java12Validator(), new Java12PostProcessor()), |
| 106 | /** |
| 107 | * Java 13 |
| 108 | */ |
| 109 | JAVA_13(new Java13Validator(), new Java13PostProcessor()), |
| 110 | /** |
| 111 | * Java 14 |
| 112 | */ |
| 113 | JAVA_14(new Java14Validator(), new Java14PostProcessor()); |
| 114 | |
| 115 | /** |
| 116 | * Does no post processing or validation. Only for people wanting the fastest parsing. |
| 117 | */ |
| 118 | public static LanguageLevel RAW = null; |
| 119 | /** |
| 120 | * The most used Java version. |
| 121 | */ |
| 122 | public static LanguageLevel POPULAR = JAVA_8; |
| 123 | /** |
| 124 | * The latest Java version that is available. |
| 125 | */ |
| 126 | public static LanguageLevel CURRENT = JAVA_13; |
| 127 | /** |
| 128 | * The newest Java features supported. |
| 129 | */ |
| 130 | public static LanguageLevel BLEEDING_EDGE = JAVA_14; |
| 131 | |
| 132 | final Validator validator; |
| 133 | final ParseResult.PostProcessor postProcessor; |
| 134 | |
| 135 | LanguageLevel(Validator validator, ParseResult.PostProcessor postProcessor) { |
| 136 | this.validator = validator; |
| 137 | this.postProcessor = postProcessor; |
| 138 | } |
| 139 | } |
| 140 | |
| 141 | |
| 142 | |
| 143 | // TODO: Add a configurable option e.g. setDesiredLineEnding(...) to replace/swap out existing line endings |
| 144 | private boolean detectOriginalLineSeparator = true; |
| 145 | private boolean storeTokens = true; |
| 146 | private boolean attributeComments = true; |
| 147 | private boolean doNotAssignCommentsPrecedingEmptyLines = true; |
| 148 | private boolean ignoreAnnotationsWhenAttributingComments = false; |
| 149 | private boolean lexicalPreservationEnabled = false; |
| 150 | private boolean preprocessUnicodeEscapes = false; |
| 151 | private SymbolResolver symbolResolver = null; |
| 152 | private int tabSize = 1; |
| 153 | private LanguageLevel languageLevel = JAVA_8; |
| 154 | private Charset characterEncoding = Providers.UTF8; |
| 155 | |
| 156 | private final List<Providers.PreProcessor> preProcessors = new ArrayList<>(); |
| 157 | private final List<ParseResult.PostProcessor> postProcessors = new ArrayList<>(); |
| 158 | |
| 159 | public ParserConfiguration() { |
| 160 | |
| 161 | class UnicodeEscapeProcessor implements PreProcessor, PostProcessor { |
| 162 | private UnicodeEscapeProcessingProvider _unicodeDecoder; |
| 163 | |
| 164 | @Override |
| 165 | public Provider process(Provider innerProvider) { |
| 166 | if (isPreprocessUnicodeEscapes()) { |
| 167 | _unicodeDecoder = new UnicodeEscapeProcessingProvider(innerProvider); |
| 168 | return _unicodeDecoder; |
| 169 | } |
| 170 | return innerProvider; |
| 171 | } |
| 172 | |
| 173 | @Override |
| 174 | public void process(ParseResult<? extends Node> result, |
| 175 | ParserConfiguration configuration) { |
| 176 | if (isPreprocessUnicodeEscapes()) { |
| 177 | result.getResult().ifPresent( |
| 178 | root -> { |
| 179 | PositionMapping mapping = _unicodeDecoder.getPositionMapping(); |
| 180 | if (!mapping.isEmpty()) { |
| 181 | root.walk( |
| 182 | node -> node.getRange().ifPresent( |
| 183 | range -> node.setRange(mapping.transform(range)))); |
| 184 | } |
| 185 | } |
| 186 | ); |
| 187 | } |
| 188 | } |
| 189 | } |
| 190 | |
| 191 | class LineEndingProcessor implements PreProcessor, PostProcessor { |
| 192 | private LineEndingProcessingProvider _lineEndingProcessingProvider; |
| 193 | |
| 194 | @Override |
| 195 | public Provider process(Provider innerProvider) { |
| 196 | if (isDetectOriginalLineSeparator()) { |
| 197 | _lineEndingProcessingProvider = new LineEndingProcessingProvider(innerProvider); |
| 198 | return _lineEndingProcessingProvider; |
| 199 | } |
| 200 | return innerProvider; |
| 201 | } |
| 202 | |
| 203 | @Override |
| 204 | public void process(ParseResult<? extends Node> result, ParserConfiguration configuration) { |
| 205 | if (isDetectOriginalLineSeparator()) { |
| 206 | result.getResult().ifPresent( |
| 207 | rootNode -> { |
| 208 | LineSeparator detectedLineSeparator = _lineEndingProcessingProvider.getDetectedLineEnding(); |
| 209 | |
| 210 | // Set the line ending on the root node |
| 211 | rootNode.setData(Node.LINE_SEPARATOR_KEY, detectedLineSeparator); |
| 212 | |
| 213 | // // Set the line ending on all children of the root node -- FIXME: Should ignore """textblocks""" |
| 214 | // rootNode.findAll(Node.class) |
| 215 | // .forEach(node -> node.setData(Node.LINE_SEPARATOR_KEY, detectedLineSeparator)); |
| 216 | } |
| 217 | ); |
| 218 | } |
| 219 | } |
| 220 | } |
| 221 | |
| 222 | UnicodeEscapeProcessor unicodeProcessor = new UnicodeEscapeProcessor(); |
| 223 | preProcessors.add(unicodeProcessor); |
| 224 | postProcessors.add(unicodeProcessor); |
| 225 | |
| 226 | LineEndingProcessor lineEndingProcessor = new LineEndingProcessor(); |
| 227 | preProcessors.add(lineEndingProcessor); |
| 228 | postProcessors.add(lineEndingProcessor); |
| 229 | |
| 230 | |
| 231 | postProcessors.add((result, configuration) -> { |
| 232 | if (configuration.isAttributeComments()) { |
| 233 | result.ifSuccessful(resultNode -> result |
| 234 | .getCommentsCollection().ifPresent(comments -> |
| 235 | new CommentsInserter(configuration).insertComments(resultNode, comments.copy().getComments()))); |
| 236 | } |
| 237 | }); |
| 238 | postProcessors.add((result, configuration) -> { |
| 239 | LanguageLevel languageLevel = getLanguageLevel(); |
| 240 | if (languageLevel != null) { |
| 241 | if (languageLevel.postProcessor != null) { |
| 242 | languageLevel.postProcessor.process(result, configuration); |
| 243 | } |
| 244 | if (languageLevel.validator != null) { |
| 245 | languageLevel.validator.accept(result.getResult().get(), new ProblemReporter(newProblem -> result.getProblems().add(newProblem))); |
| 246 | } |
| 247 | } |
| 248 | }); |
| 249 | postProcessors.add((result, configuration) -> configuration.getSymbolResolver().ifPresent(symbolResolver -> |
| 250 | result.ifSuccessful(resultNode -> { |
| 251 | if (resultNode instanceof CompilationUnit) { |
| 252 | resultNode.setData(Node.SYMBOL_RESOLVER_KEY, symbolResolver); |
| 253 | } |
| 254 | }) |
| 255 | )); |
| 256 | postProcessors.add((result, configuration) -> { |
| 257 | if (configuration.isLexicalPreservationEnabled()) { |
| 258 | result.ifSuccessful(LexicalPreservingPrinter::setup); |
| 259 | } |
| 260 | }); |
| 261 | } |
| 262 | |
| 263 | public boolean isAttributeComments() { |
| 264 | return attributeComments; |
| 265 | } |
| 266 | |
| 267 | /** |
| 268 | * Whether to run CommentsInserter, which will put the comments that were found in the source code into the comment |
| 269 | * and javadoc fields of the nodes it thinks they refer to. |
| 270 | */ |
| 271 | public ParserConfiguration setAttributeComments(boolean attributeComments) { |
| 272 | this.attributeComments = attributeComments; |
| 273 | return this; |
| 274 | } |
| 275 | |
| 276 | public boolean isDoNotAssignCommentsPrecedingEmptyLines() { |
| 277 | return doNotAssignCommentsPrecedingEmptyLines; |
| 278 | } |
| 279 | |
| 280 | public ParserConfiguration setDoNotAssignCommentsPrecedingEmptyLines(boolean doNotAssignCommentsPrecedingEmptyLines) { |
| 281 | this.doNotAssignCommentsPrecedingEmptyLines = doNotAssignCommentsPrecedingEmptyLines; |
| 282 | return this; |
| 283 | } |
| 284 | |
| 285 | public boolean isIgnoreAnnotationsWhenAttributingComments() { |
| 286 | return ignoreAnnotationsWhenAttributingComments; |
| 287 | } |
| 288 | |
| 289 | public ParserConfiguration setIgnoreAnnotationsWhenAttributingComments(boolean ignoreAnnotationsWhenAttributingComments) { |
| 290 | this.ignoreAnnotationsWhenAttributingComments = ignoreAnnotationsWhenAttributingComments; |
| 291 | return this; |
| 292 | } |
| 293 | |
| 294 | public ParserConfiguration setStoreTokens(boolean storeTokens) { |
| 295 | this.storeTokens = storeTokens; |
| 296 | if (!storeTokens) { |
| 297 | setAttributeComments(false); |
| 298 | } |
| 299 | return this; |
| 300 | } |
| 301 | |
| 302 | public boolean isStoreTokens() { |
| 303 | return storeTokens; |
| 304 | } |
| 305 | |
| 306 | public int getTabSize() { |
| 307 | return tabSize; |
| 308 | } |
| 309 | |
| 310 | /** |
| 311 | * When a TAB character is encountered during parsing, the column position will be increased by this value. |
| 312 | * By default it is 1. |
| 313 | */ |
| 314 | public ParserConfiguration setTabSize(int tabSize) { |
| 315 | this.tabSize = tabSize; |
| 316 | return this; |
| 317 | } |
| 318 | |
| 319 | /** |
| 320 | * Disabled by default. |
| 321 | * When this is enabled, LexicalPreservingPrinter.print can be used to reproduce |
| 322 | * the original formatting of the file. |
| 323 | */ |
| 324 | public ParserConfiguration setLexicalPreservationEnabled(boolean lexicalPreservationEnabled) { |
| 325 | this.lexicalPreservationEnabled = lexicalPreservationEnabled; |
| 326 | return this; |
| 327 | } |
| 328 | |
| 329 | public boolean isLexicalPreservationEnabled() { |
| 330 | return lexicalPreservationEnabled; |
| 331 | } |
| 332 | |
| 333 | /** |
| 334 | * Retrieve the SymbolResolver to be used while parsing, if any. |
| 335 | */ |
| 336 | public Optional<SymbolResolver> getSymbolResolver() { |
| 337 | return Optional.ofNullable(symbolResolver); |
| 338 | } |
| 339 | |
| 340 | /** |
| 341 | * Set the SymbolResolver to be injected while parsing. |
| 342 | */ |
| 343 | public ParserConfiguration setSymbolResolver(SymbolResolver symbolResolver) { |
| 344 | this.symbolResolver = symbolResolver; |
| 345 | return this; |
| 346 | } |
| 347 | |
| 348 | public List<Providers.PreProcessor> getPreProcessors() { |
| 349 | return preProcessors; |
| 350 | } |
| 351 | |
| 352 | public List<ParseResult.PostProcessor> getPostProcessors() { |
| 353 | return postProcessors; |
| 354 | } |
| 355 | |
| 356 | public ParserConfiguration setLanguageLevel(LanguageLevel languageLevel) { |
| 357 | this.languageLevel = languageLevel; |
| 358 | return this; |
| 359 | } |
| 360 | |
| 361 | public LanguageLevel getLanguageLevel() { |
| 362 | return languageLevel; |
| 363 | } |
| 364 | |
| 365 | /** |
| 366 | * When set to true, unicode escape handling is done by preprocessing the whole input, |
| 367 | * meaning that all unicode escapes are turned into unicode characters before parsing. |
| 368 | * That means the AST will never contain literal unicode escapes. However, |
| 369 | * positions in the AST will point to the original input, which is exactly the same as without this option. |
| 370 | * Without this option enabled, the unicode escapes will not be processed and are transfered intact to the AST. |
| 371 | */ |
| 372 | public ParserConfiguration setPreprocessUnicodeEscapes(boolean preprocessUnicodeEscapes) { |
| 373 | this.preprocessUnicodeEscapes = preprocessUnicodeEscapes; |
| 374 | return this; |
| 375 | } |
| 376 | |
| 377 | public boolean isPreprocessUnicodeEscapes() { |
| 378 | return preprocessUnicodeEscapes; |
| 379 | } |
| 380 | |
| 381 | public ParserConfiguration setDetectOriginalLineSeparator(boolean detectOriginalLineSeparator) { |
| 382 | this.detectOriginalLineSeparator = detectOriginalLineSeparator; |
| 383 | return this; |
| 384 | } |
| 385 | |
| 386 | public boolean isDetectOriginalLineSeparator() { |
| 387 | return detectOriginalLineSeparator; |
| 388 | } |
| 389 | |
| 390 | public Charset getCharacterEncoding() { |
| 391 | return characterEncoding; |
| 392 | } |
| 393 | |
| 394 | /** |
| 395 | * The character encoding used for reading input from files and streams. By default UTF8 is used. |
| 396 | */ |
| 397 | public ParserConfiguration setCharacterEncoding(Charset characterEncoding) { |
| 398 | this.characterEncoding = characterEncoding; |
| 399 | return this; |
| 400 | } |
| 401 | |
| 402 | } |
| 403 |
Members