Merge d3eac68 into 9bf816b

docs/changes/2.x/2.0.0.md

@@ -4,6 +4,8 @@
 
 ## Enhancements
 
+- IOFactory : Added extractVariables method to extract variables from a document [@sibalonat](https://github.com/sibalonat) in [#2515](https://github.com/PHPOffice/PHPWord/pull/2515)
+
 ### Bug fixes
 
 - MsDoc Reader : Correct Font Size Calculation by [@oleibman](https://github.com/oleibman) fixing [#2526](https://github.com/PHPOffice/PHPWord/issues/2526) in [#2531](https://github.com/PHPOffice/PHPWord/pull/2531)

samples/Sample_44_ExtractVariablesFromReaderWord2007.php

@@ -0,0 +1,14 @@
+<?php
+
+include_once 'Sample_Header.php';
+
+// Read contents
+$name = basename(__FILE__, '.php');
+
+$source = __DIR__ . "/resources/{$name}.docx";
+
+echo date('H:i:s'), " Reading contents from `{$source}`", EOL;
+
+$variables = \PhpOffice\PhpWord\IOFactory::extractVariables($source);
+
+var_dump($variables);

src/PhpWord/IOFactory.php

@@ -17,6 +17,8 @@
 
 namespace PhpOffice\PhpWord;
 
+use PhpOffice\PhpWord\Element\Text;
+use PhpOffice\PhpWord\Element\TextRun;
 use PhpOffice\PhpWord\Exception\Exception;
 use PhpOffice\PhpWord\Reader\ReaderInterface;
 use PhpOffice\PhpWord\Writer\WriterInterface;
@@ -89,6 +91,43 @@ public static function load($filename, $readerName = 'Word2007')
         return $reader->load($filename);
     }
 
+    /**
+     * Loads PhpWord ${variable} from file.
+     *
+     * @param string $filename The name of the file
+     *
+     * @return array The extracted variables
+     */
+    public static function extractVariables(string $filename, string $readerName = 'Word2007'): array
+    {
+        /** @var \PhpOffice\PhpWord\Reader\ReaderInterface $reader */
+        $reader = self::createReader($readerName);
+        $document = $reader->load($filename);
+        $extractedVariables = [];
+        foreach ($document->getSections() as $section) {
+            $concatenatedText = '';
+            foreach ($section->getElements() as $element) {
+                if ($element instanceof TextRun) {
+                    foreach ($element->getElements() as $textElement) {
+                        if ($textElement instanceof Text) {
+                            $text = $textElement->getText();
+                            $concatenatedText .= $text;
+                        }
+                    }
+                }
+            }
+            preg_match_all('/\$\{([^}]+)\}/', $concatenatedText, $matches);
+            if (!empty($matches[1])) {
+                foreach ($matches[1] as $match) {
+                    $trimmedMatch = trim($match);
+                    $extractedVariables[] = $trimmedMatch;
+                }
+            }
+        }
+
+        return $extractedVariables;
+    }
+
     /**
      * Check if it's a concrete class (not abstract nor interface).
      *

tests/PhpWordTests/IOFactoryTest.php

@@ -116,4 +116,17 @@ public function testLoad(): void
             IOFactory::load($file)
         );
     }
+
+    /**
+     * Test for extractVariables method.
+     */
+    public function testExtractVariables(): void
+    {
+        $file = __DIR__ . '/_files/templates/extract-variable.docx';
+        $extractedVariables = IOFactory::extractVariables($file, 'Word2007');
+
+        $expectedVariables = ['date', 'A1', 'B1'];
+
+        self::assertEquals($expectedVariables, $extractedVariables, 'Extracted variables do not match expected variables.');
+    }
 }