#1090 cpp parser exception with inline asm

pmd-core/src/main/java/net/sourceforge/pmd/cpd/CPDConfiguration.java

@@ -62,6 +62,13 @@ public class CPDConfiguration extends AbstractConfiguration {
 	@Parameter(names = "--skip-lexical-errors", description = "Skip files which can't be tokenized due to invalid characters instead of aborting CPD", required = false)
 	private boolean skipLexicalErrors = false;
 
+	@Parameter(names = "--no-skip-blocks", description = "Do not skip code blocks marked with --skip-blocks-pattern (e.g. #if 0 until #endif)", required = false)
+	private boolean noSkipBlocks = false;
+
+	@Parameter(names = "--skip-blocks-pattern", description = "Pattern to find the blocks to skip. Start and End pattern separated by |. "
+	        + "Default is \"" + Tokenizer.DEFAULT_SKIP_BLOCKS_PATTERN + "\".", required = false)
+	private String skipBlocksPattern = Tokenizer.DEFAULT_SKIP_BLOCKS_PATTERN;
+
 	@Parameter(names = "--files", variableArity = true, description = "List of files and directories to process", required = false)
 	private List<String> files;
 
@@ -180,6 +187,8 @@ public class CPDConfiguration extends AbstractConfiguration {
         } else {
             properties.remove(Tokenizer.IGNORE_ANNOTATIONS);
 		}
+	    properties.setProperty(Tokenizer.OPTION_SKIP_BLOCKS, Boolean.toString(!configuration.isNoSkipBlocks()));
+	    properties.setProperty(Tokenizer.OPTION_SKIP_BLOCKS_PATTERN, configuration.getSkipBlocksPattern());
 		configuration.getLanguage().setProperties(properties);
 	}
 
@@ -341,4 +350,20 @@ public class CPDConfiguration extends AbstractConfiguration {
 	public String getEncoding() {
 		return encoding;
 	}
+
+    public boolean isNoSkipBlocks() {
+        return noSkipBlocks;
+    }
+
+    public void setNoSkipBlocks(boolean noSkipBlocks) {
+        this.noSkipBlocks = noSkipBlocks;
+    }
+
+    public String getSkipBlocksPattern() {
+        return skipBlocksPattern;
+    }
+
+    public void setSkipBlocksPattern(String skipBlocksPattern) {
+        this.skipBlocksPattern = skipBlocksPattern;
+    }
 }

pmd-core/src/main/java/net/sourceforge/pmd/cpd/CPDTask.java

@@ -49,6 +49,8 @@ public class CPDTask extends Task {
     private boolean ignoreAnnotations;
     private boolean skipLexicalErrors;
     private boolean skipDuplicateFiles;
+    private boolean skipBlocks = true;
+    private String skipBlocksPattern = Tokenizer.DEFAULT_SKIP_BLOCKS_PATTERN;
     private File outputFile;
     private String encoding = System.getProperty("file.encoding");
     private List<FileSet> filesets = new ArrayList<FileSet>();
@@ -102,6 +104,8 @@ public class CPDTask extends Task {
         if (ignoreAnnotations) {
             p.setProperty(Tokenizer.IGNORE_ANNOTATIONS, "true");
         }
+        p.setProperty(Tokenizer.OPTION_SKIP_BLOCKS, Boolean.toString(skipBlocks));
+        p.setProperty(Tokenizer.OPTION_SKIP_BLOCKS_PATTERN, skipBlocksPattern);
         return LanguageFactory.createLanguage(language, p);
     }
 
@@ -208,6 +212,14 @@ public class CPDTask extends Task {
         this.encoding = encoding;
     }
 
+    public void setSkipBlocks(boolean skipBlocks) {
+        this.skipBlocks = skipBlocks;
+    }
+
+    public void setSkipBlocksPattern(String skipBlocksPattern) {
+        this.skipBlocksPattern = skipBlocksPattern;
+    }
+
     public static class FormatAttribute extends EnumeratedAttribute {
         private static final String[] FORMATS = new String[]{XML_FORMAT, TEXT_FORMAT, CSV_FORMAT};
         public String[] getValues() {

pmd-core/src/main/java/net/sourceforge/pmd/cpd/Tokenizer.java

@@ -9,6 +9,23 @@ public interface Tokenizer {
     String IGNORE_LITERALS = "ignore_literals";
     String IGNORE_IDENTIFIERS = "ignore_identifiers";
     String IGNORE_ANNOTATIONS = "ignore_annotations";
+    /**
+     * Enables or disabled skipping of blocks like a pre-processor.
+     * It is a boolean property.
+     * The default value is <code>true</code>.
+     * @see #OPTION_SKIP_BLOCKS_PATTERN
+     */
+    String OPTION_SKIP_BLOCKS = "net.sourceforge.pmd.cpd.Tokenizer.skipBlocks";
+    /**
+     * Configures the pattern, to find the blocks to skip.
+     * It is a string property and contains of two parts, separated by {@code |}.
+     * The first part is the start pattern, the second part is the ending pattern.
+     * Default value is "{@code #if 0|#endif}".
+     * @see #DEFAULT_SKIP_BLOCKS_PATTERN
+     */
+    String OPTION_SKIP_BLOCKS_PATTERN = "net.sourceforge.pmd.cpd.Tokenizer.skipBlocksPattern";
+
+    String DEFAULT_SKIP_BLOCKS_PATTERN = "#if 0|#endif";
 
     void tokenize(SourceCode sourceCode, Tokens tokenEntries) throws IOException;
 }