1 /***
2 * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
3 */
4 package net.sourceforge.pmd.cpd;
5
6 import org.apache.tools.ant.BuildException;
7 import org.apache.tools.ant.DirectoryScanner;
8 import org.apache.tools.ant.Project;
9 import org.apache.tools.ant.Task;
10 import org.apache.tools.ant.types.EnumeratedAttribute;
11 import org.apache.tools.ant.types.FileSet;
12
13 import java.io.File;
14 import java.io.IOException;
15 import java.util.ArrayList;
16 import java.util.Iterator;
17 import java.util.List;
18 import java.util.Properties;
19
20 /***
21 * CPDTask
22 * <p/>
23 * Runs the CPD utility via ant. The ant task looks like this:
24 * <p/>
25 * <project name="CPDProj" default="main" basedir=".">
26 * <taskdef name="cpd" classname="net.sourceforge.pmd.cpd.CPDTask" />
27 * <target name="main">
28 * <cpd ignoreIdentifiers="true" ignoreLiterals="true" minimumTokenCount="100" outputFile="c:\cpdrun.txt">
29 * <fileset dir="/path/to/my/src">
30 * <include name="*.java"/>
31 * </fileset>
32 * </cpd>
33 * </target>
34 * </project>
35 * <p/>
36 * Required: minimumTokenCount, outputFile, and at least one file
37 */
38 public class CPDTask extends Task {
39
40 private static final String TEXT_FORMAT = "text";
41 private static final String XML_FORMAT = "xml";
42 private static final String CSV_FORMAT = "csv";
43
44 private String format = TEXT_FORMAT;
45 private int minimumTokenCount;
46 private boolean ignoreLiterals;
47 private boolean ignoreIdentifiers;
48 private File outputFile;
49 private List filesets = new ArrayList();
50
51 public void execute() throws BuildException {
52 try {
53 validateFields();
54
55 log("Tokenizing files", Project.MSG_INFO);
56 Properties p = new Properties();
57 if (ignoreLiterals) {
58 p.setProperty(JavaTokenizer.IGNORE_LITERALS, "true");
59 }
60 if (ignoreIdentifiers) {
61 p.setProperty(JavaTokenizer.IGNORE_IDENTIFIERS, "true");
62 }
63 CPD cpd = new CPD(minimumTokenCount, new JavaLanguage(p));
64 tokenizeFiles(cpd);
65
66 log("Starting to analyze code", Project.MSG_INFO);
67 long timeTaken = analyzeCode(cpd);
68 log("Done analyzing code; that took " + timeTaken + " milliseconds");
69
70 log("Generating report", Project.MSG_INFO);
71 report(cpd);
72 } catch (IOException ioe) {
73 log(ioe.toString(), Project.MSG_ERR);
74 throw new BuildException("IOException during task execution", ioe);
75 } catch (ReportException re) {
76 re.printStackTrace();
77 log(re.toString(), Project.MSG_ERR);
78 throw new BuildException("ReportException during task execution", re);
79 }
80 }
81
82 private void report(CPD cpd) throws ReportException {
83 if (!cpd.getMatches().hasNext()) {
84 log("No duplicates over " + minimumTokenCount + " tokens found", Project.MSG_INFO);
85 }
86 Renderer renderer = createRenderer();
87 if (outputFile.isAbsolute()) {
88 new FileReporter(outputFile).report(renderer.render(cpd.getMatches()));
89 } else {
90 new FileReporter(new File(getProject().getBaseDir(), outputFile.toString()));
91 }
92 }
93
94
95 private void tokenizeFiles(CPD cpd) throws IOException {
96 for (Iterator iterator = filesets.iterator(); iterator.hasNext();) {
97 FileSet fileSet = (FileSet) iterator.next();
98 DirectoryScanner directoryScanner = fileSet.getDirectoryScanner(getProject());
99 String[] includedFiles = directoryScanner.getIncludedFiles();
100 for (int i = 0; i < includedFiles.length; i++) {
101 File file = new File(directoryScanner.getBasedir() + System.getProperty("file.separator") + includedFiles[i]);
102 log("Tokenizing " + file.getAbsolutePath(), Project.MSG_VERBOSE);
103 cpd.add(file);
104 }
105 }
106 }
107
108 private long analyzeCode(CPD cpd) {
109 long start = System.currentTimeMillis();
110 cpd.go();
111 long stop = System.currentTimeMillis();
112 return stop - start;
113 }
114
115 private Renderer createRenderer() {
116 if (format.equals(TEXT_FORMAT)) {
117 return new SimpleRenderer();
118 } else if (format.equals(CSV_FORMAT)) {
119 return new CSVRenderer();
120 }
121 return new XMLRenderer();
122 }
123
124 private void validateFields() throws BuildException {
125 if (minimumTokenCount == 0) {
126 throw new BuildException("minimumTokenCount is required and must be greater than zero");
127 } else if (outputFile == null) {
128 throw new BuildException("outputFile is a required attribute");
129 } else if (filesets.isEmpty()) {
130 throw new BuildException("Must include at least one FileSet");
131 }
132 }
133
134 public void addFileset(FileSet set) {
135 filesets.add(set);
136 }
137
138 public void setMinimumTokenCount(int minimumTokenCount) {
139 this.minimumTokenCount = minimumTokenCount;
140 }
141
142 public void setIgnoreLiterals(boolean value) {
143 this.ignoreLiterals = value;
144 }
145
146 public void setIgnoreIdentifiers(boolean value) {
147 this.ignoreIdentifiers = value;
148 }
149
150 public void setOutputFile(File outputFile) {
151 this.outputFile = outputFile;
152 }
153
154 public void setFormat(FormatAttribute formatAttribute) {
155 format = formatAttribute.getValue();
156 }
157
158 public static class FormatAttribute extends EnumeratedAttribute {
159 private String[] formats = new String[]{XML_FORMAT, TEXT_FORMAT, CSV_FORMAT};
160
161 public String[] getValues() {
162 return formats;
163 }
164 }
165 }