Merge pull request #4095 from pacvz:master

[core] CPD: Added begin and end token to XML reports #4095

.all-contributorsrc

@@ -6798,6 +6798,14 @@
       "contributions": [
         "doc"
       ]
+    },{
+      "login": "pacvz",
+      "name": "pacvz",
+      "avatar_url": "https://avatars.githubusercontent.com/u/35453365?v=4",
+      "profile": "https://github.com/pacvz",
+      "contributions": [
+        "code"
+      ]
     }
   ],
   "contributorsPerLine": 7,

docs/pages/pmd/userdocs/cpd/cpd_report_formats.md

@@ -104,9 +104,9 @@ Example:
    <file path="/home/pmd/source/pmd-core/src/test/java/net/sourceforge/pmd/RuleReferenceTest.java" totalNumberOfTokens="523"/>
    <file path="/home/pmd/source/pmd-core/src/test/java/net/sourceforge/pmd/lang/rule/xpath/JaxenXPathRuleQueryTest.java" totalNumberOfTokens="120"/>
    <duplication lines="33" tokens="239">
-      <file column="29" endcolumn="75" endline="64" line="32"
+      <file column="29" endcolumn="75" endline="64" line="32" begintoken="2356" endtoken="2594"
             path="/home/pmd/source/pmd-core/src/test/java/net/sourceforge/pmd/RuleReferenceTest.java"/>
-      <file column="37" endcolumn="75" endline="100" line="68"
+      <file column="37" endcolumn="75" endline="100" line="68" begintoken="5700" endtoken="5938"
             path="/home/pmd/source/pmd-core/src/test/java/net/sourceforge/pmd/RuleReferenceTest.java"/>
       <codefragment><![CDATA[    public void testOverride() {
         final StringProperty PROPERTY1_DESCRIPTOR = new StringProperty("property1", "Test property", null, 0f);
@@ -143,11 +143,11 @@ Example:
         validateOverriddenValues(PROPERTY1_DESCRIPTOR, PROPERTY2_DESCRIPTOR, ruleReference);]]></codefragment>
    </duplication>
    <duplication lines="16" tokens="110">
-      <file column="9" endcolumn="28" endline="81" line="66"
+      <file column="9" endcolumn="28" endline="81" line="66" begintoken="3000" endtoken="3109"
             path="/home/pmd/source/pmd-core/src/test/java/net/sourceforge/pmd/lang/rule/xpath/JaxenXPathRuleQueryTest.java"/>
-      <file column="9" endcolumn="28" endline="103" line="88"
+      <file column="9" endcolumn="28" endline="103" line="88" begintoken="3200" endtoken="3309"
             path="/home/pmd/source/pmd-core/src/test/java/net/sourceforge/pmd/lang/rule/xpath/JaxenXPathRuleQueryTest.java"/>
-      <file column="9" endcolumn="28" endline="125" line="110"
+      <file column="9" endcolumn="28" endline="125" line="110" begintoken="3400" endtoken="3509"
             path="/home/pmd/source/pmd-core/src/test/java/net/sourceforge/pmd/lang/rule/xpath/JaxenXPathRuleQueryTest.java"/>
       <codefragment><![CDATA[        JaxenXPathRuleQuery query = createQuery(xpath);
         List<String> ruleChainVisits = query.getRuleChainVisits();

docs/pages/release_notes.md

@@ -43,6 +43,7 @@ This is a {{ site.pmd.release_type }} release.
 * [#4081](https://github.com/pmd/pmd/pull/4081): \[apex] Remove Jorje leaks outside `ast` package - [@eklimo](https://github.com/eklimo)
 * [#4083](https://github.com/pmd/pmd/pull/4083): \[java] UnnecessaryImport false positive for on-demand imports of nested classes (fix for #4082) - [@abyss638](https://github.com/abyss638)
 * [#4092](https://github.com/pmd/pmd/pull/4092): \[apex] Implement ApexQualifiableNode for ASTUserEnum - [@aaronhurst-google](https://github.com/aaronhurst-google)
+* [#4095](https://github.com/pmd/pmd/pull/4095): \[core] CPD: Added begin and end token to XML reports - [@pacvz](https://github.com/pacvz)
 * [#4097](https://github.com/pmd/pmd/pull/4097): \[apex] ApexUnitTestClassShouldHaveAssertsRule: Support new Assert class (Apex v56.0) - [@tprouvot](https://github.com/tprouvot)
 * [#4104](https://github.com/pmd/pmd/pull/4104): \[doc] Add MegaLinter in the list of integrations - [@nvuillam](https://github.com/nvuillam)
 

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

@@ -35,6 +35,10 @@ public int getBeginColumn() {
         return this.token.getBeginColumn(); // TODO Java 1.8 make optional
     }
 
+    public int getBeginTokenIndex() {
+        return this.token.getIndex();
+    }
+
     public int getEndLine() {
         return getBeginLine() + getLineCount() - 1;
     }
@@ -48,6 +52,10 @@ public int getEndColumn() {
         return this.endToken == null ? -1 : this.endToken.getEndColumn(); // TODO Java 1.8 make optional
     }
 
+    public int getEndTokenIndex() {
+        return this.endToken == null ? -1 : this.endToken.getIndex();
+    }
+
     public int getLineCount() {
         return this.lineCount;
     }

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

@@ -152,6 +152,12 @@ private Element addFilesToDuplicationElement(Document doc, Element duplication,
             if (endCol != -1) {
                 file.setAttribute("endcolumn", String.valueOf(endCol));
             }
+            final int beginIndex = mark.getBeginTokenIndex();
+            final int endIndex = mark.getEndTokenIndex();
+            file.setAttribute("begintoken", String.valueOf(beginIndex));
+            if (endIndex != -1) {
+                file.setAttribute("endtoken", String.valueOf(endIndex));
+            }
             duplication.appendChild(file);
         }
         return duplication;

pmd-core/src/test/java/net/sourceforge/pmd/cpd/XMLRendererTest.java

@@ -216,6 +216,38 @@ public void testFilesWithNumberOfTokens() throws IOException, ParserConfiguratio
         assertEquals("888", attributes.getNamedItem("totalNumberOfTokens").getNodeValue());
     }
 
+    @Test
+    public void testGetDuplicationStartEnd() throws IOException, ParserConfigurationException, SAXException {
+        TokenEntry.clearImages();
+        final CPDReportRenderer renderer = new XMLRenderer();
+        final List<Match> matches = new ArrayList<>();
+        final String filename = "/var/Foo.java";
+        final int lineCount = 6;
+        final String codeFragment = "code\nfragment";
+        final Mark mark1 = createMark("public", filename, 1, lineCount, codeFragment, 2, 3);
+        final Mark mark2 = createMark("stuff", filename, 73, lineCount, codeFragment, 4, 5);
+        final Match match = new Match(75, mark1, mark2);
+        matches.add(match);
+        final Map<String, Integer> numberOfTokensPerFile = new HashMap<>();
+        numberOfTokensPerFile.put(filename, 888);
+        final CPDReport report = new CPDReport(matches, numberOfTokensPerFile);
+        final StringWriter writer = new StringWriter();
+        renderer.render(report, writer);
+        final String xmlOutput = writer.toString();
+        final Document doc = DocumentBuilderFactory.newInstance().newDocumentBuilder()
+                .parse(new ByteArrayInputStream(xmlOutput.getBytes(ENCODING)));
+        final NodeList files = doc.getElementsByTagName("file");
+        final Node dup_1 = files.item(1);
+        final NamedNodeMap attrs_1 = dup_1.getAttributes();
+        assertEquals("0", attrs_1.getNamedItem("begintoken").getNodeValue());
+        assertEquals("1", attrs_1.getNamedItem("endtoken").getNodeValue());
+
+        final Node dup_2 = files.item(2);
+        final NamedNodeMap attrs_2 = dup_2.getAttributes();
+        assertEquals("2", attrs_2.getNamedItem("begintoken").getNodeValue());
+        assertEquals("3", attrs_2.getNamedItem("endtoken").getNodeValue());
+    }
+
     @Test
     public void testRendererEncodedPath() throws IOException {
         CPDRenderer renderer = new XMLRenderer();