Support formats csv and txt for CPD

pmd-compat6/src/it/cpd-for-java/invoker.properties

@@ -1,2 +1,4 @@
-invoker.goals = verify
+invoker.goals.1 = verify
+invoker.goals.2 = pmd:cpd-check -Dformat=csv
+invoker.goals.3 = pmd:cpd-check -Dformat=txt
 invoker.buildResult = failure

pmd-compat6/src/it/cpd-for-java/verify.bsh

@@ -14,6 +14,9 @@ String readFile(File file) throws IOException {
 
 File buildLogPath = new File(basedir, "build.log");
 String buildLog = readFile(buildLogPath);
+if (buildLog.contains("An API incompatibility was encountered while")) {
+    throw new RuntimeException("Executing failed due to API incompatibility");
+}
 if (!buildLog.contains("[INFO] CPD Failure: Found 8 lines of duplicated code at locations:")) {
     throw new RuntimeException("No CPD failures detected, did CPD run?");
 }
@@ -23,8 +26,7 @@ if (!buildLog.contains(classA + " line 3")) {
 }
 
 File cpdXmlReport = new File(basedir, "target/cpd.xml");
-if(!cpdXmlReport.exists())
-{
+if (!cpdXmlReport.exists()) {
     throw new FileNotFoundException("Could not find cpd xml report: " + cpdXmlReport);
 }
 String cpdXml = readFile(cpdXmlReport);
@@ -34,3 +36,27 @@ if (!cpdXml.contains("<duplication lines=\"8\" tokens=\"67\">")) {
 if (!cpdXml.contains(classA + "\"/>")) {
     throw new RuntimeException("Expected duplication has not been reported");
 }
+
+File csvReport = new File(basedir, "target/cpd.csv");
+if (!csvReport.exists()) {
+    throw new FileNotFoundException("Could not find cpd csv report: " + csvReport);
+}
+String csv = readFile(csvReport);
+if (!csv.contains("8,67,2,3,")) {
+    throw new RuntimeException("Expected duplication in CSV has not been reported");
+}
+if (!csv.contains(classA + ",")) {
+    throw new RuntimeException("Expected duplication in CSV has not been reported");
+}
+
+File textReport = new File(basedir, "target/cpd.txt");
+if (!textReport.exists()) {
+    throw new FileNotFoundException("Could not find cpd text report: " + textReport);
+}
+String text = readFile(textReport);
+if (!text.contains("Found a 8 line (67 tokens) duplication in the following files:")) {
+    throw new RuntimeException("Expected duplication in TXT has not been reported");
+}
+if (!text.contains("Starting at line 3 of ") && !text.contains(classA.toString())) {
+    throw new RuntimeException("Expected duplication in TXT has not been reported");
+}

pmd-compat6/src/main/java/net/sourceforge/pmd/cpd/CSVRenderer.java

@@ -0,0 +1,132 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+// This class has been taken from 7.0.0-SNAPSHOT
+// Changes: implements old interface CPDRenderer, old render(Iterator<Match> matches, Writer writer) method
+
+package net.sourceforge.pmd.cpd;
+
+import java.io.IOException;
+import java.io.Writer;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Paths;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Set;
+
+import org.apache.commons.lang3.StringEscapeUtils;
+
+import net.sourceforge.pmd.cpd.renderer.CPDRenderer;
+import net.sourceforge.pmd.lang.document.FileLocation;
+import net.sourceforge.pmd.lang.document.TextFile;
+import net.sourceforge.pmd.lang.java.JavaLanguageModule;
+
+/**
+ * Renders a report to CSV. The CSV format renders each match (duplication)
+ * as a single line with the following columns:
+ * <ul>
+ * <li>lines (optional): The number of lines the first mark of a match spans.
+ * Only output if the {@code lineCountPerFile} is disabled (see ctor params).</li>
+ * <li>tokens: The number of duplicated tokens in a match (size of the match).</li>
+ * <li>occurrences: The number of duplicates in a match (number of times the tokens were found in distinct places).</li>
+ * </ul>
+ *
+ * <p>Trailing each line are pairs (or triples, if {@code lineCountPerFile} is enabled)
+ * of fields describing each file where the duplication was found in the format
+ * {@code (start line, line count (optional), file path)}. These repeat at least twice.
+ *
+ * <h3>Examples</h3>
+ * <p>
+ * Example without {@code lineCountPerFile}:
+ * <pre>{@code
+ * lines,tokens,occurrences
+ * 10,75,2,48,/var/file1,73,/var/file2
+ * }</pre>
+ * This describes one match with the following characteristics:
+ * <ul>
+ * <li>The first duplicate instance is 10 lines long;
+ * <li>75 duplicated tokens;
+ * <li>2 duplicate instances;
+ * <li>The first duplicate instance is in file {@code /var/file1} and starts at line 48;</li>
+ * <li>The second duplicate instance is in file {@code /var/file2} and starts at line 73.</li>
+ * </ul>
+ * <p>
+ * Example with {@code lineCountPerFile}:
+ * <pre>{@code
+ * tokens,occurrences
+ * 75,2,48,10,/var/file1,73,12,/var/file2
+ * }</pre>
+ * This describes one match with the following characteristics:
+ * <ul>
+ * <li>75 duplicated tokens
+ * <li>2 duplicate instances
+ * <li>The first duplicate instance is in file {@code /var/file1}, starts at line 48, and is 10 lines long;</li>
+ * <li>The second duplicate instance is in file {@code /var/file2}, starts at line 73, and is 12 lines long.</li>
+ * </ul>
+ */
+public class CSVRenderer implements CPDReportRenderer, CPDRenderer {
+
+    private final char separator;
+    private final boolean lineCountPerFile;
+
+    public static final char DEFAULT_SEPARATOR = ',';
+    public static final boolean DEFAULT_LINECOUNTPERFILE = false;
+
+    public CSVRenderer() {
+        this(DEFAULT_SEPARATOR, DEFAULT_LINECOUNTPERFILE);
+    }
+
+    public CSVRenderer(boolean lineCountPerFile) {
+        this(DEFAULT_SEPARATOR, lineCountPerFile);
+    }
+
+    public CSVRenderer(char separatorChar) {
+        this(separatorChar, DEFAULT_LINECOUNTPERFILE);
+    }
+
+    public CSVRenderer(char separatorChar, boolean lineCountPerFile) {
+        this.separator = separatorChar;
+        this.lineCountPerFile = lineCountPerFile;
+    }
+
+    @Override
+    public void render(CPDReport report, Writer writer) throws IOException {
+        if (!lineCountPerFile) {
+            writer.append("lines").append(separator);
+        }
+        writer.append("tokens").append(separator).append("occurrences").append(System.lineSeparator());
+
+        for (Match match : report.getMatches()) {
+            if (!lineCountPerFile) {
+                writer.append(String.valueOf(match.getLineCount())).append(separator);
+            }
+            writer.append(String.valueOf(match.getTokenCount())).append(separator)
+                    .append(String.valueOf(match.getMarkCount())).append(separator);
+            for (Iterator<Mark> marks = match.iterator(); marks.hasNext();) {
+                Mark mark = marks.next();
+                FileLocation loc = mark.getLocation();
+
+                writer.append(String.valueOf(loc.getStartLine())).append(separator);
+                if (lineCountPerFile) {
+                    writer.append(String.valueOf(loc.getLineCount())).append(separator);
+                }
+                writer.append(StringEscapeUtils.escapeCsv(report.getDisplayName(loc.getFileId())));
+                if (marks.hasNext()) {
+                    writer.append(separator);
+                }
+            }
+            writer.append(System.lineSeparator());
+        }
+        writer.flush();
+    }
+
+    // ------------------- compat extensions --------------------
+    @Override
+    public void render(Iterator<Match> matches, Writer writer) throws IOException {
+        RendererHelper.render(matches, writer, this);
+    }
+}

pmd-compat6/src/main/java/net/sourceforge/pmd/cpd/RendererHelper.java

@@ -0,0 +1,49 @@
+/*
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+import java.io.IOException;
+import java.io.Writer;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Paths;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Set;
+
+import net.sourceforge.pmd.cpd.renderer.CPDRenderer;
+import net.sourceforge.pmd.lang.document.TextFile;
+import net.sourceforge.pmd.lang.java.JavaLanguageModule;
+
+final class RendererHelper {
+    private RendererHelper() {
+        // utility class
+    }
+
+    static void render(Iterator<Match> matches, Writer writer, CPDReportRenderer renderer) throws IOException {
+        List<Match> matchesList = new ArrayList<>();
+        matches.forEachRemaining(matchesList::add);
+
+        List<TextFile> textFiles = new ArrayList<>();
+        Set<String> paths = new HashSet<>();
+        for (Match match : matchesList) {
+            for (Mark mark : match.getMarkSet()) {
+                paths.add(mark.getFilename());
+            }
+        }
+        for (String path : paths) {
+            textFiles.add(TextFile.forPath(Paths.get(path), StandardCharsets.UTF_8, JavaLanguageModule.getInstance().getDefaultVersion()));
+        }
+
+        try (SourceManager sourceManager = new SourceManager(textFiles)) {
+            CPDReport report = new CPDReport(sourceManager, matchesList, Collections.emptyMap());
+            renderer.render(report, writer);
+        } catch (Exception e) {
+            throw new RuntimeException(e);
+        }
+    }
+}

pmd-compat6/src/main/java/net/sourceforge/pmd/cpd/SimpleRenderer.java

@@ -0,0 +1,90 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+// This class has been taken from 7.0.0-SNAPSHOT
+// Changes: implements old interface CPDRenderer, old render(Iterator<Match> matches, Writer writer) method
+
+package net.sourceforge.pmd.cpd;
+
+import java.io.IOException;
+import java.io.PrintWriter;
+import java.io.Writer;
+import java.util.Iterator;
+
+import net.sourceforge.pmd.cpd.renderer.CPDRenderer;
+import net.sourceforge.pmd.lang.document.Chars;
+import net.sourceforge.pmd.lang.document.FileLocation;
+import net.sourceforge.pmd.util.StringUtil;
+
+public class SimpleRenderer implements CPDReportRenderer, CPDRenderer {
+
+    private String separator;
+    private boolean trimLeadingWhitespace;
+
+    public static final String DEFAULT_SEPARATOR = "=====================================================================";
+
+    public SimpleRenderer() {
+        this(false);
+    }
+
+    public SimpleRenderer(boolean trimLeadingWhitespace) {
+        this(DEFAULT_SEPARATOR);
+        this.trimLeadingWhitespace = trimLeadingWhitespace;
+    }
+
+    public SimpleRenderer(String theSeparator) {
+        separator = theSeparator;
+    }
+
+    @Override
+    public void render(CPDReport report, Writer writer0) throws IOException {
+        PrintWriter writer = new PrintWriter(writer0);
+        Iterator<Match> matches = report.getMatches().iterator();
+        if (matches.hasNext()) {
+            renderOn(report, writer, matches.next());
+        }
+
+        while (matches.hasNext()) {
+            Match match = matches.next();
+            writer.println(separator);
+            renderOn(report, writer, match);
+        }
+        writer.flush();
+    }
+
+    private void renderOn(CPDReport report, PrintWriter writer, Match match) throws IOException {
+
+        writer.append("Found a ").append(String.valueOf(match.getLineCount())).append(" line (").append(String.valueOf(match.getTokenCount()))
+              .append(" tokens) duplication in the following files: ").println();
+
+        for (Mark mark : match) {
+            FileLocation loc = mark.getLocation();
+            writer.append("Starting at line ")
+                  .append(String.valueOf(loc.getStartLine()))
+                  .append(" of ").append(report.getDisplayName(loc.getFileId()))
+                  .println();
+        }
+
+        writer.println(); // add a line to separate the source from the desc above
+
+        Chars source = report.getSourceCodeSlice(match.getFirstMark());
+
+        if (trimLeadingWhitespace) {
+            for (Chars line : StringUtil.linesWithTrimIndent(source)) {
+                line.writeFully(writer);
+                writer.println();
+            }
+            return;
+        }
+
+        source.writeFully(writer);
+        writer.println();
+    }
+
+    // ------------------- compat extensions --------------------
+    @Override
+    public void render(Iterator<Match> matches, Writer writer) throws IOException {
+        RendererHelper.render(matches, writer, this);
+    }
+}

pmd-compat6/src/main/java/net/sourceforge/pmd/cpd/XMLRenderer.java

@@ -169,25 +169,6 @@ public final class XMLRenderer implements CPDReportRenderer, CPDRenderer {
     // ------------------- compat extensions --------------------
     @Override
     public void render(Iterator<Match> matches, Writer writer) throws IOException {
-        List<Match> matchesList = new ArrayList<>();
-        matches.forEachRemaining(matchesList::add);
-
-        List<TextFile> textFiles = new ArrayList<>();
-        Set<String> paths = new HashSet<>();
-        for (Match match : matchesList) {
-            for (Mark mark : match.getMarkSet()) {
-                paths.add(mark.getFilename());
-            }
-        }
-        for (String path : paths) {
-            textFiles.add(TextFile.forPath(Paths.get(path), StandardCharsets.UTF_8, JavaLanguageModule.getInstance().getDefaultVersion()));
-        }
-
-        try (SourceManager sourcManager = new SourceManager(textFiles)) {
-            CPDReport report = new CPDReport(sourcManager, matchesList, Collections.emptyMap());
-            render(report, writer);
-        } catch (Exception e) {
-            throw new RuntimeException(e);
-        }
+        RendererHelper.render(matches, writer, this);
     }
 }