001//////////////////////////////////////////////////////////////////////////////// 002// checkstyle: Checks Java source code for adherence to a set of rules. 003// Copyright (C) 2001-2019 the original author or authors. 004// 005// This library is free software; you can redistribute it and/or 006// modify it under the terms of the GNU Lesser General Public 007// License as published by the Free Software Foundation; either 008// version 2.1 of the License, or (at your option) any later version. 009// 010// This library is distributed in the hope that it will be useful, 011// but WITHOUT ANY WARRANTY; without even the implied warranty of 012// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 013// Lesser General Public License for more details. 014// 015// You should have received a copy of the GNU Lesser General Public 016// License along with this library; if not, write to the Free Software 017// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA 018//////////////////////////////////////////////////////////////////////////////// 019 020package com.puppycrawl.tools.checkstyle; 021 022import java.io.File; 023import java.io.IOException; 024import java.io.Reader; 025import java.io.StringReader; 026import java.nio.charset.StandardCharsets; 027import java.util.Locale; 028 029import antlr.CommonASTWithHiddenTokens; 030import antlr.CommonHiddenStreamToken; 031import antlr.RecognitionException; 032import antlr.Token; 033import antlr.TokenStreamException; 034import antlr.TokenStreamHiddenTokenFilter; 035import com.puppycrawl.tools.checkstyle.api.CheckstyleException; 036import com.puppycrawl.tools.checkstyle.api.DetailAST; 037import com.puppycrawl.tools.checkstyle.api.FileContents; 038import com.puppycrawl.tools.checkstyle.api.FileText; 039import com.puppycrawl.tools.checkstyle.api.TokenTypes; 040import com.puppycrawl.tools.checkstyle.grammar.GeneratedJavaLexer; 041import com.puppycrawl.tools.checkstyle.grammar.GeneratedJavaRecognizer; 042import com.puppycrawl.tools.checkstyle.utils.CommonUtil; 043 044/** 045 * Helper methods to parse java source files. 046 * 047 */ 048// -@cs[ClassDataAbstractionCoupling] No way to split up class usage. 049public final class JavaParser { 050 051 /** 052 * Enum to be used for test if comments should be used. 053 */ 054 public enum Options { 055 056 /** 057 * Comments nodes should be processed. 058 */ 059 WITH_COMMENTS, 060 061 /** 062 * Comments nodes should be ignored. 063 */ 064 WITHOUT_COMMENTS, 065 066 } 067 068 /** Stop instances being created. **/ 069 private JavaParser() { 070 } 071 072 /** 073 * Static helper method to parses a Java source file. 074 * @param contents contains the contents of the file 075 * @return the root of the AST 076 * @throws CheckstyleException if the contents is not a valid Java source 077 */ 078 public static DetailAST parse(FileContents contents) 079 throws CheckstyleException { 080 final String fullText = contents.getText().getFullText().toString(); 081 final Reader reader = new StringReader(fullText); 082 final GeneratedJavaLexer lexer = new GeneratedJavaLexer(reader); 083 lexer.setCommentListener(contents); 084 lexer.setTokenObjectClass("antlr.CommonHiddenStreamToken"); 085 086 final TokenStreamHiddenTokenFilter filter = new TokenStreamHiddenTokenFilter(lexer); 087 filter.hide(TokenTypes.SINGLE_LINE_COMMENT); 088 filter.hide(TokenTypes.BLOCK_COMMENT_BEGIN); 089 090 final GeneratedJavaRecognizer parser = new GeneratedJavaRecognizer(filter) { 091 @Override 092 public void reportError(RecognitionException ex) { 093 throw new IllegalStateException(ex); 094 } 095 }; 096 parser.setFilename(contents.getFileName()); 097 parser.setASTNodeClass(DetailAstImpl.class.getName()); 098 try { 099 parser.compilationUnit(); 100 } 101 catch (RecognitionException | TokenStreamException | IllegalStateException ex) { 102 final String exceptionMsg = String.format(Locale.ROOT, 103 "%s occurred while parsing file %s.", 104 ex.getClass().getSimpleName(), contents.getFileName()); 105 throw new CheckstyleException(exceptionMsg, ex); 106 } 107 108 return (DetailAST) parser.getAST(); 109 } 110 111 /** 112 * Parse a text and return the parse tree. 113 * @param text the text to parse 114 * @param options {@link Options} to control inclusion of comment nodes 115 * @return the root node of the parse tree 116 * @throws CheckstyleException if the text is not a valid Java source 117 */ 118 public static DetailAST parseFileText(FileText text, Options options) 119 throws CheckstyleException { 120 final FileContents contents = new FileContents(text); 121 DetailAST ast = parse(contents); 122 if (options == Options.WITH_COMMENTS) { 123 ast = appendHiddenCommentNodes(ast); 124 } 125 return ast; 126 } 127 128 /** 129 * Parses Java source file. 130 * @param file the file to parse 131 * @param options {@link Options} to control inclusion of comment nodes 132 * @return DetailAST tree 133 * @throws IOException if the file could not be read 134 * @throws CheckstyleException if the file is not a valid Java source file 135 */ 136 public static DetailAST parseFile(File file, Options options) 137 throws IOException, CheckstyleException { 138 final FileText text = new FileText(file.getAbsoluteFile(), 139 System.getProperty("file.encoding", StandardCharsets.UTF_8.name())); 140 return parseFileText(text, options); 141 } 142 143 /** 144 * Appends comment nodes to existing AST. 145 * It traverses each node in AST, looks for hidden comment tokens 146 * and appends found comment tokens as nodes in AST. 147 * @param root of AST 148 * @return root of AST with comment nodes 149 */ 150 public static DetailAST appendHiddenCommentNodes(DetailAST root) { 151 DetailAST result = root; 152 DetailAST curNode = root; 153 DetailAST lastNode = root; 154 155 while (curNode != null) { 156 lastNode = curNode; 157 158 CommonHiddenStreamToken tokenBefore = ((CommonASTWithHiddenTokens) curNode) 159 .getHiddenBefore(); 160 DetailAST currentSibling = curNode; 161 while (tokenBefore != null) { 162 final DetailAST newCommentNode = 163 createCommentAstFromToken(tokenBefore); 164 165 ((DetailAstImpl) currentSibling).addPreviousSibling(newCommentNode); 166 167 if (currentSibling == result) { 168 result = newCommentNode; 169 } 170 171 currentSibling = newCommentNode; 172 tokenBefore = tokenBefore.getHiddenBefore(); 173 } 174 175 DetailAST toVisit = curNode.getFirstChild(); 176 while (curNode != null && toVisit == null) { 177 toVisit = curNode.getNextSibling(); 178 curNode = curNode.getParent(); 179 } 180 curNode = toVisit; 181 } 182 if (lastNode != null) { 183 CommonHiddenStreamToken tokenAfter = ((CommonASTWithHiddenTokens) lastNode) 184 .getHiddenAfter(); 185 DetailAST currentSibling = lastNode; 186 while (tokenAfter != null) { 187 final DetailAST newCommentNode = 188 createCommentAstFromToken(tokenAfter); 189 190 ((DetailAstImpl) currentSibling).addNextSibling(newCommentNode); 191 192 currentSibling = newCommentNode; 193 tokenAfter = tokenAfter.getHiddenAfter(); 194 } 195 } 196 return result; 197 } 198 199 /** 200 * Create comment AST from token. Depending on token type 201 * SINGLE_LINE_COMMENT or BLOCK_COMMENT_BEGIN is created. 202 * @param token to create the AST 203 * @return DetailAST of comment node 204 */ 205 private static DetailAST createCommentAstFromToken(Token token) { 206 final DetailAST commentAst; 207 if (token.getType() == TokenTypes.SINGLE_LINE_COMMENT) { 208 commentAst = createSlCommentNode(token); 209 } 210 else { 211 commentAst = CommonUtil.createBlockCommentNode(token); 212 } 213 return commentAst; 214 } 215 216 /** 217 * Create single-line comment from token. 218 * @param token to create the AST 219 * @return DetailAST with SINGLE_LINE_COMMENT type 220 */ 221 private static DetailAST createSlCommentNode(Token token) { 222 final DetailAstImpl slComment = new DetailAstImpl(); 223 slComment.setType(TokenTypes.SINGLE_LINE_COMMENT); 224 slComment.setText("//"); 225 226 // column counting begins from 0 227 slComment.setColumnNo(token.getColumn() - 1); 228 slComment.setLineNo(token.getLine()); 229 230 final DetailAstImpl slCommentContent = new DetailAstImpl(); 231 slCommentContent.setType(TokenTypes.COMMENT_CONTENT); 232 233 // column counting begins from 0 234 // plus length of '//' 235 slCommentContent.setColumnNo(token.getColumn() - 1 + 2); 236 slCommentContent.setLineNo(token.getLine()); 237 slCommentContent.setText(token.getText()); 238 239 slComment.addChild(slCommentContent); 240 return slComment; 241 } 242 243}