phpcpd 8.2.0 release. Added possibility to generate html report, extended report xml file, fixed some bugs, updated documentation.

Author: DKravtsov

.gitignore

@@ -1,5 +1,6 @@
 reports/*
 !reports/.gitkeep
+!reports/phpcpd/.gitkeep
 
 /.env.local
 /build/phar

.idea/htdocs.iml

@@ -2,6 +2,16 @@
 
 All notable changes in PHPCPD are documented in this file using the [Keep a CHANGELOG](http://keepachangelog.com/) principles.
 
+## [8.2.0] - 2025-05-01
+
+### Added
+
+* Added possibility to use [xalan](https://xalan.apache.org) cli tool for generating html report with datatable and possibility to export into csv, excel, pdf formats or print it.
+
+### Updated
+
+* Changed and extended xml report format.
+
 ## [8.1.1] - 2025-04-13
 
 ### Added

ChangeLog.md

@@ -39,6 +39,7 @@ RUN apt-get update && apt-get upgrade -y && apt-get install -y \
       wget \
       gpg \
       debsecan \
+      xalan \
     && docker-php-ext-configure intl \
     && docker-php-ext-install \
       sockets \

Dockerfile

@@ -93,6 +93,7 @@ info: ## Shows php, composer, phing, phive versions
 	@make exec cmd="composer --version"
 	@make exec cmd="php phing.phar -v"
 	@make exec cmd="phive --version"
+	@make exec cmd="xalan -v"
 
 logs: ## Shows logs from the php container. Use ctrl+c in order to exit
 ifeq ($(INSIDE_DOCKER_CONTAINER), 0)
@@ -120,6 +121,12 @@ signed-phar: ## Create signed PHAR archive of PHPCPD and all its dependencies (r
 phpunit: ## Runs PhpUnit tests and create coverage report inside reports/coverage folder
 	@make exec-bash cmd="./vendor/bin/phpunit -c phpunit.xml.dist --coverage-html reports/coverage --coverage-clover reports/clover.xml --log-junit reports/junit.xml"
 
+phpcpd-run: ## Runs phpcpd
+	@make exec-bash cmd="php phpcpd --fuzzy --log-pmd=reports/phpcpd/phpcpd-report-v1.xml tests/Fixture"
+
+phpcpd-html-report: ## Generate html report (should be run after phpcpd-run)
+	@make exec-bash cmd="xalan -in reports/phpcpd/phpcpd-report-v1.xml -xsl https://systemsdk.github.io/phpcpd/report/phpcpd-html-v1_0_0.xslt -out reports/phpcpd/phpcpd-report-v1.html"
+
 report-code-coverage: ## Updates code coverage on coveralls.io. Note: COVERALLS_REPO_TOKEN should be set on CI side.
 	@make exec-bash cmd="export COVERALLS_REPO_TOKEN=${COVERALLS_REPO_TOKEN} && php ./vendor/bin/php-coveralls -v --coverage_clover reports/clover.xml --json_path reports/coverals.json"
 

Makefile

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project name="phpcpd" default="setup">
     <property name="basedir" value="." override="false"/>
-    <property name="version" value="8.1.1" override="false"/>
+    <property name="version" value="8.2.0" override="false"/>
     <target name="setup" depends="clean,install-dependencies"/>
 
     <target name="clean" description="Cleanup build artifacts">

build.xml

@@ -0,0 +1,119 @@
+# PHP Copy/Paste Detector report
+This document describing how you can generate report.
+
+## Requirements for html report generation
+* [Xalan](https://xalan.apache.org) tool
+* created folder (f.e. `reports/phpcpd`) with write access where you want to save your report
+
+Note: You can find some already-made examples inside our solutions on our [GitHub page](https://github.com/systemsdk) 
+
+## Steps for html report generation
+You need to run the next commands for html report generation:
+
+1. Run PHP Copy/Paste Detector
+```bash
+php ./vendor/bin/phpcpd --fuzzy --verbose --log-pmd=reports/phpcpd/phpcpd-report-v1.xml src
+```
+
+Note: `src` is a folder where your php source code for analyzing
+
+2. Run xalan tool for report generation
+```bash
+xalan -in reports/phpcpd/phpcpd-report-v1.xml -xsl https://systemsdk.github.io/phpcpd/report/phpcpd-html-v1_0_0.xslt -out reports/phpcpd/phpcpd-report-v1.html
+```
+
+3. Now you can open the report using your web-browser
+
+![Path mappings](images/report_example_01.png)
+
+[Example](https://systemsdk.github.io/phpcpd/report/report-example.html)
+
+Note: Please use menu items `Enable datatable`, `Disable datatabl` for enable/disable [DataTables](https://datatables.net/).
+
+## Xml report format
+This format uses `xml` to output the duplications in a more structured format. The `xml` format can then further be processed using `xslt` transformations. See section xslt below for examples.
+
+Report file example:
+```
+<?xml version="1.0" encoding="UTF-8"?>
+<pmd-cpd xmlns="https://systemsdk.github.io/phpcpd/report" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" phpcpdVersion="8.2.0" timestamp="2025-04-29T17:39:52+00:00" version="1.0.0" xsi:schemaLocation="https://systemsdk.github.io/phpcpd/report https://systemsdk.github.io/phpcpd/report/phpcpd-report-v1_0_0.xsd">
+  <duplication lines="59" tokens="136">
+    <file line="116" endline="175" path="/var/www/html/tests/Fixture/Math.php"/>
+    <file line="217" endline="276" path="/var/www/html/tests/Fixture/Math.php"/>
+    <codefragment><![CDATA[    public function div($v1, $v2)
+    {
+        $v3 = $v1 / ($v2 + $v1);
+        if ($v3 &gt; 14)
+        {
+            $v4 = 0;
+            for ($i = 0; $i &lt; $v3; $i++)
+            {
+                $v4 += ($v2 * $i);
+            }
+        }
+        $v5 = ($v4 &lt; $v3 ? ($v3 - $v4) : ($v4 - $v3));
+
+        $v6 = ($v1 * $v2 * $v3 * $v4 * $v5);
+
+        $d = array($v1, $v2, $v3, $v4, $v5, $v6);
+
+        $v7 = 1;
+        for ($i = 0; $i &lt; $v6; $i++)
+        {
+            shuffle( $d );
+            $v7 = $v7 + $i * end($d);
+        }
+
+        $v8 = $v7;
+        foreach ( $d as $x )
+        {
+            $v8 *= $x;
+        }
+
+        $v3 = $v1 / ($v2 + $v1);
+        if ($v3 &gt; 14)
+        {
+            $v4 = 0;
+            for ($i = 0; $i &lt; $v3; $i++)
+            {
+                $v4 += ($v2 * $i);
+            }
+        }
+        $v5 = ($v4 &lt; $v3 ? ($v3 - $v4) : ($v4 - $v3));
+
+        $v6 = ($v1 * $v2 * $v3 * $v4 * $v5);
+
+        $d = array($v1, $v2, $v3, $v4, $v5, $v6);
+
+        $v7 = 1;
+        for ($i = 0; $i &lt; $v6; $i++)
+        {
+            shuffle( $d );
+            $v7 = $v7 + $i * end($d);
+        }
+
+        $v8 = $v7;
+        foreach ( $d as $x )
+        {
+            $v8 *= $x;
+        }
+
+        return $v8;
+]]></codefragment>
+  </duplication>
+</pmd-cpd>
+```
+
+## Xslt
+This is not a direct report format. But you can use one of the following `xslt` stylesheets to convert the report into `html`. Or you can write your own stylesheet.
+
+`https://systemsdk.github.io/phpcpd/report/phpcpd-html-v1_0_0.xslt`
+
+This stylesheet is available and using for html report generation mentioned above.
+
+It requires javascript enabled and uses [Bootstrap](https://getbootstrap.com/), [jQuery](https://jquery.com/), and [DataTables](https://datatables.net/).
+
+## Schema versions
+PHP Copy/Past detector tool is building xml report that has schema `https://systemsdk.github.io/phpcpd/report/phpcpd-report-v1_0_0.xsd`.
+
+You can find xsd versions history [here](schema.md).

composer.lock

@@ -0,0 +1,11 @@
+# PHPCPD Report Schema
+This document describing PHPCPD report schema.
+
+## PHPCPD Report Schema 1.0.0
+Namespace: `https://systemsdk.github.io/phpcpd/report`
+
+Schema Location: `https://systemsdk.github.io/phpcpd/report/phpcpd-report-v1_0_0.xsd`
+
+Current Version: 1.0.0 (since phpcpd 8.2.0)
+
+Last Change: 2025-05-01