hiifong/pmd
1
0
Fork 0
forked from phoedos/pmd
Code Pull Requests Activity

abstraction for cpd with antlr

Browse Source
This commit is contained in:
lsoncini 2018-07-21 20:10:24 -03:00
parent 0f9bc63bfc
commit 32b7cba79a
5 changed files with 103 additions and 76 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pmd-core/pom.xml
View File

@ -96,7 +96,10 @@
<artifactId>ant</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.antlr</groupId>
<artifactId>antlr4-runtime</artifactId>
</dependency>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>

9
pmd-core/src/main/java/net/sourceforge/pmd/RuleSet.java
View File

@ -58,12 +58,9 @@ public class RuleSet implements ChecksumAware {
/**
* Creates a new RuleSet with the given checksum.
*
* @param checksum
* A checksum of the ruleset, should change only if the ruleset
* was configured differently
* @param rules
* The rules to be applied as part of this ruleset
*
* @param builder
* A rule set builder.
*/
private RuleSet(final RuleSetBuilder builder) {
checksum = builder.checksum;

91
pmd-core/src/main/java/net/sourceforge/pmd/cpd/AntlrTokenizer.java Normal file
View File

@ -0,0 +1,91 @@
/**
* BSD-style license; for more info see http://pmd.sourceforge.net/license.html
*/
package net.sourceforge.pmd.cpd;
import org.antlr.v4.runtime.BaseErrorListener;
import org.antlr.v4.runtime.CharStream;
import org.antlr.v4.runtime.CharStreams;
import org.antlr.v4.runtime.Lexer;
import org.antlr.v4.runtime.RecognitionException;
import org.antlr.v4.runtime.Recognizer;
import org.antlr.v4.runtime.Token;
import net.sourceforge.pmd.lang.ast.TokenMgrError;
public abstract class AntlrTokenizer implements Tokenizer {
private final Lexer lexer;
/**
* Constructor.
*
* @param lexer lexer.
*/
public AntlrTokenizer(Lexer lexer) {
this.lexer = lexer;
}
@Override
public void tokenize(final SourceCode sourceCode, final Tokens tokenEntries) {
StringBuilder buffer = sourceCode.getCodeBuffer();
try {
CharStream charStream = CharStreams.fromString(buffer.toString());
lexer.reset();
lexer.setInputStream(charStream);
lexer.removeErrorListeners();
lexer.addErrorListener(new ErrorHandler());
Token token = lexer.nextToken();
while (token.getType() != Token.EOF) {
if (token.getChannel() != Lexer.HIDDEN) {
TokenEntry tokenEntry = new TokenEntry(token.getText(), sourceCode.getFileName(), token.getLine());
tokenEntries.add(tokenEntry);
}
token = lexer.nextToken();
}
} catch (ANTLRSyntaxError err) {
// Wrap exceptions of the ANTLR tokenizer in a TokenMgrError, so
// they are correctly handled
// when CPD is executed with the '--skipLexicalErrors' command line
// option
throw new TokenMgrError("Lexical error in file " + sourceCode.getFileName() + " at line " + err.getLine()
+ ", column " + err.getColumn() + ". Encountered: " + err.getMessage(),
TokenMgrError.LEXICAL_ERROR);
} finally {
tokenEntries.add(TokenEntry.getEOF());
}
}
private static class ErrorHandler extends BaseErrorListener {
@Override
public void syntaxError(Recognizer<?, ?> recognizer, Object offendingSymbol, int line, int charPositionInLine,
String msg, RecognitionException ex) {
throw new ANTLRSyntaxError(msg, line, charPositionInLine, ex);
}
}
private static class ANTLRSyntaxError extends RuntimeException {
private static final long serialVersionUID = 1L;
private final int line;
private final int column;
ANTLRSyntaxError(String msg, int line, int column, RecognitionException cause) {
super(msg, cause);
this.line = line;
this.column = column;
}
public int getLine() {
return line;
}
public int getColumn() {
return column;
}
}
}

73
pmd-swift/src/main/java/net/sourceforge/pmd/cpd/SwiftTokenizer.java
View File

@ -4,79 +4,14 @@
package net.sourceforge.pmd.cpd;
import org.antlr.v4.runtime.ANTLRInputStream;
import org.antlr.v4.runtime.BaseErrorListener;
import org.antlr.v4.runtime.Lexer;
import org.antlr.v4.runtime.RecognitionException;
import org.antlr.v4.runtime.Recognizer;
import org.antlr.v4.runtime.Token;
import net.sourceforge.pmd.lang.ast.TokenMgrError;
import net.sourceforge.pmd.lang.swift.antlr4.SwiftLexer;
/**
* The Swift Tokenizer
* SwiftTokenizer
*/
public class SwiftTokenizer implements Tokenizer {
@Override
public void tokenize(SourceCode sourceCode, Tokens tokenEntries) {
StringBuilder buffer = sourceCode.getCodeBuffer();
try {
ANTLRInputStream ais = new ANTLRInputStream(buffer.toString());
SwiftLexer lexer = new SwiftLexer(ais);
lexer.removeErrorListeners();
lexer.addErrorListener(new ErrorHandler());
Token token = lexer.nextToken();
while (token.getType() != Token.EOF) {
if (token.getChannel() != Lexer.HIDDEN) {
TokenEntry tokenEntry = new TokenEntry(token.getText(), sourceCode.getFileName(), token.getLine());
tokenEntries.add(tokenEntry);
}
token = lexer.nextToken();
}
} catch (ANTLRSyntaxError err) {
// Wrap exceptions of the Swift tokenizer in a TokenMgrError, so
// they are correctly handled
// when CPD is executed with the '--skipLexicalErrors' command line
// option
throw new TokenMgrError("Lexical error in file " + sourceCode.getFileName() + " at line " + err.getLine()
+ ", column " + err.getColumn() + ". Encountered: " + err.getMessage(),
TokenMgrError.LEXICAL_ERROR);
} finally {
tokenEntries.add(TokenEntry.getEOF());
}
}
private static class ErrorHandler extends BaseErrorListener {
@Override
public void syntaxError(Recognizer<?, ?> recognizer, Object offendingSymbol, int line, int charPositionInLine,
String msg, RecognitionException ex) {
throw new ANTLRSyntaxError(msg, line, charPositionInLine, ex);
}
}
private static class ANTLRSyntaxError extends RuntimeException {
private static final long serialVersionUID = 1L;
private final int line;
private final int column;
ANTLRSyntaxError(String msg, int line, int column, RecognitionException cause) {
super(msg, cause);
this.line = line;
this.column = column;
}
public int getLine() {
return line;
}
public int getColumn() {
return column;
}
public class SwiftTokenizer extends AntlrTokenizer {
public SwiftTokenizer() {
super(new SwiftLexer(null));
}
}

1
pom.xml
View File

@ -286,6 +286,7 @@ Additionally it includes CPD, the copy-paste-detector. CPD finds duplicated code
<version>${antlr.version}</version>
<configuration>
<inputEncoding>${project.build.sourceEncoding}</inputEncoding>
<visitor>true</visitor>
</configuration>
<executions>
<execution>