Port atoum tests to PHPUnit

.gitignore

@@ -2,7 +2,6 @@
 /coverage/*
 /samples/*
 /vendor/*
-/test*
 /xdebug/*
 /composer.phar
 /composer

.php_cs

@@ -18,5 +18,7 @@ return PhpCsFixer\Config::create()
         ->files()
         ->in(__DIR__ . '/samples')
         ->in(__DIR__ . '/src')
+        ->in(__DIR__ . '/test')
+        ->in(__DIR__ . '/tests')
         ->name('*.php')
-    );
+    );

.scrutinizer.yml

@@ -0,0 +1,11 @@
+# For more information about code coverage
+# See: https://scrutinizer-ci.com/docs/build/code_coverage
+build:
+  nodes:
+    coverage:
+      tests:
+        override:
+          - command: vendor/bin/phpunit --coverage-clover coverage/clover.xml
+            coverage:
+              file: coverage/clover.xml
+              format: clover

.travis.yml

@@ -18,9 +18,11 @@ jobs:
   include:
     - php: 7.2
       env: COMPOSER_FLAGS="--prefer-lowest"
+    - php: 7.4
+      env: COVERAGE_FLAGS="--coverage-clover coverage/clover.xml"
 
 install:
   - composer self-update
   - composer update --prefer-dist --no-progress --no-suggest --optimize-autoloader $COMPOSER_FLAGS
 
-script: ./vendor/bin/atoum -d src/Smalot/PdfParser/Tests/ -ncc
+script: vendor/bin/phpunit $COVERAGE_FLAGS

composer.json

@@ -21,14 +21,20 @@
         "tecnickcom/tcpdf": "^6.2.22"
     },
     "require-dev": {
-        "atoum/atoum": "^3.1",
+        "phpunit/phpunit": "^5.7.27|^6",
         "friendsofphp/php-cs-fixer": "^2.16.3"
     },
     "autoload": {
         "psr-0": {
             "Smalot\\PdfParser\\": "src/"
         }
     },
+    "autoload-dev": {
+        "psr-4": {
+            "Test\\Smalot\\PdfParser\\": "test/",
+            "Tests\\Smalot\\PdfParser\\": "tests/"
+        }
+    },
     "config": {
         "process-timeout": 1200
     }

phpunit.xml

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="UTF-8"?>
+
+<!-- https://phpunit.de/manual/current/en/appendixes.configuration.html -->
+<phpunit xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:noNamespaceSchemaLocation="http://schema.phpunit.de/6.1/phpunit.xsd"
+         backupGlobals="false"
+         backupStaticAttributes="false"
+         bootstrap="vendor/autoload.php"
+         colors="true"
+         convertErrorsToExceptions="true"
+         convertNoticesToExceptions="true"
+         convertWarningsToExceptions="true"
+         processIsolation="false"
+         stopOnFailure="false"
+         verbose="true"
+>
+    <php>
+        <ini name="error_reporting" value="-1" />
+        <ini name="zend.enable_gc" value="0"/>
+        <ini name="error_reporting" value="-1"/>
+        <ini name="intl.error_level" value="0"/>
+        <ini name="display_errors" value="On"/>
+    </php>
+
+    <testsuites>
+        <testsuite name="all">
+            <directory>tests</directory>
+        </testsuite>
+    </testsuites>
+    <filter>
+        <whitelist>
+            <directory>src</directory>
+        </whitelist>
+    </filter>
+</phpunit>

src/Smalot/PdfParser/Element.php

@@ -51,9 +51,6 @@ class Element
      */
     protected $document = null;
 
-    /**
-     * @var mixed
-     */
     protected $value = null;
 
     /**

src/Smalot/PdfParser/Page.php

@@ -35,9 +35,6 @@
 use Smalot\PdfParser\Element\ElementNull;
 use Smalot\PdfParser\Element\ElementXRef;
 
-/**
- * Class Page
- */
 class Page extends PDFObject
 {
     /**
@@ -272,16 +269,13 @@ public function getTextArray(self $page = null)
         return [];
     }
 
-    /*
+    /**
      * Gets all the text data with its internal representation of the page.
      *
      * @return array An array with the data and the internal representation
-     *
      */
-
     public function extractRawData()
     {
-        $text = $this->getText();
         /*
          * Now you can get the complete content of the object with the text on it
          */
@@ -313,14 +307,13 @@ public function extractRawData()
         return $extractedData;
     }
 
-    /*
+    /**
      * Gets all the decoded text data with it internal representation from a page.
      *
      * @param array $extractedRawData the extracted data return by extractRawData or
      *                                null if extractRawData should be called
      *
      * @return array An array with the data and the internal representation
-     *
      */
     public function extractDecodedRawData($extractedRawData = null)
     {
@@ -331,14 +324,13 @@ public function extractDecodedRawData($extractedRawData = null)
         $currentFont = null;
         foreach ($extractedRawData as &$command) {
             if ('Tj' == $command['o'] or 'TJ' == $command['o']) {
-                $text = [];
                 $data = $command['c'];
                 if (!\is_array($data)) {
                     if (isset($currentFont)) {
                         $tmpText = $currentFont->decodeOctal($data);
                         //$tmpText = $currentFont->decodeHexadecimal($tmpText, false);
                     }
-                    $tmpText = $tjText = str_replace(
+                    $tmpText = str_replace(
                             ['\\\\', '\(', '\)', '\n', '\r', '\t', '\ '],
                             ['\\', '(', ')', "\n", "\r", "\t", ' '],
                             $tmpText
@@ -360,7 +352,7 @@ public function extractDecodedRawData($extractedRawData = null)
                         $decodedText = $currentFont->decodeOctal($tmpText);
                         //$tmpText = $currentFont->decodeHexadecimal($tmpText, false);
                     }
-                    $decodedText = $tjText = str_replace(
+                    $decodedText = str_replace(
                             ['\\\\', '\(', '\)', '\n', '\r', '\t', '\ '],
                             ['\\', '(', ')', "\n", "\r", "\t", ' '],
                             $decodedText
@@ -382,18 +374,17 @@ public function extractDecodedRawData($extractedRawData = null)
         return $extractedRawData;
     }
 
-    /*
+    /**
      * Gets just the Text commands that are involved in text positions and
      * Text Matrix (Tm)
      *
      * It extract just the PDF commands that are involved with text positions, and
      * the Text Matrix (Tm). These are: BT, ET, TL, Td, TD, Tm, T*, Tj, ', ", and TJ
      *
-     * @param array $extractedDecodedRawData The data extracted by extractDecodeRawData
-                           if it is null, the method extractDecodeRawData is called.
+     * @param array $extractedDecodedRawData The data extracted by extractDecodeRawData.
+     *                                       If it is null, the method extractDecodeRawData is called.
      *
      * @return array An array with the text command of the page
-     *
      */
     public function getDataCommands($extractedDecodedRawData = null)
     {
@@ -527,7 +518,7 @@ public function getDataCommands($extractedDecodedRawData = null)
         return $extractedData;
     }
 
-    /*
+    /**
      * Gets the Text Matrix of the text in the page
      *
      * Return an array where every item is an array where the first item is the
@@ -536,12 +527,11 @@ public function getDataCommands($extractedDecodedRawData = null)
      * text. The first 4 numbers has to be with Scalation, Rotation and Skew of the text.
      *
      * @param array $dataCommands the data extracted by getDataCommands
-     *                     if null getDataCommands is called.
+     *                            if null getDataCommands is called
      *
-     * @return array An array with the data of the page including the Tm information
-     *         of any text in the page.
+     * @return array an array with the data of the page including the Tm information
+     *               of any text in the page
      */
-
     public function getDataTm($dataCommands = null)
     {
         if (!isset($dataCommands) or !$dataCommands) {
@@ -731,17 +721,17 @@ public function getDataTm($dataCommands = null)
         return $extractedData;
     }
 
-    /*
+    /**
      * Gets text data that are around the given coordinates (X,Y)
      *
      * If the text is in near the given coordinates (X,Y) (or the TM info),
      * the text is returned.  The extractedData return by getDataTm, could be use to see
      * where is the coordinates of a given text, using the TM info for it.
      *
-     * @param float $x The X value of the coordinate to search for. if null
-     *                 just the Y value is considered (same Row)
-     * @param float $y The Y value of the coordinate to search for
-     *                 just the X value is considered (same column)
+     * @param float $x      The X value of the coordinate to search for. if null
+     *                      just the Y value is considered (same Row)
+     * @param float $y      The Y value of the coordinate to search for
+     *                      just the X value is considered (same column)
      * @param float $xError The value less or more to consider an X to be "near"
      * @param float $yError The value less or more to consider an Y to be "near"
      *