Merge pull request #70 from bravadomizzou/master

Add ability to get form data fields as array

Author: mikehaertl

README.md

@@ -216,6 +216,9 @@ $data = $pdf->getData();
 // Get form data fields
 $pdf = new Pdf('/path/my.pdf');
 $data = $pdf->getDataFields();
+echo $data; // raw string; also can directly call $data->__toString();
+print_r($data); // metadata as array; also can directly call $data->__toArray();
+$field1Value = $data[0]['FieldValue']; // array access to a field's value
 ```
 
 #### How to perform more than one operation on a PDF

composer.json

@@ -11,7 +11,7 @@
         }
     ],
     "require": {
-        "php": ">=5.0.0",
+        "php": ">=5.3.0",
         "mikehaertl/php-shellcommand": "^1.0.2",
         "mikehaertl/php-tmpfile": "^1.0.0"
     },

src/DataFields.php

@@ -0,0 +1,109 @@
+<?php
+
+namespace mikehaertl\pdftk;
+
+use ArrayObject;
+
+/**
+ * Class DataFields
+ *
+ * @author Ray Holland <[email protected]>
+ */
+class DataFields extends ArrayObject
+{
+    private $_string;
+
+    private $_array;
+
+    /**
+     * DataFields constructor.
+     *
+     * @param string $input
+     * @param int $flags
+     * @param string $iterator_class
+     */
+    public function __construct($input = null, $flags = 0, $iterator_class = "ArrayIterator")
+    {
+        $this->_string = $input ?: '';
+        $this->_array  = $this->parseData($this->_string);
+
+        return parent::__construct($this->_array, $flags, $iterator_class);
+    }
+
+    /**
+     * @return string
+     */
+    public function __toString()
+    {
+        return $this->_string;
+    }
+
+    /**
+     * @return array
+     */
+    public function __toArray()
+    {
+        return $this->_array;
+    }
+
+    /**
+     * Parse the output of dump_data_fields into something usable.
+     * Derived from: http://stackoverflow.com/a/34864936/744228
+     * Example input (includes '---' line):
+     * ---
+     * FieldType: Text
+     * FieldName: Text1
+     * FieldFlags: 0
+     * FieldValue: University of Missouri : Ray-Holland
+     * FieldValueDefault: University of Missouri : Ray-Holland
+     * FieldJustification: Left
+     * FieldMaxLength: 99
+     *
+     * @param $dataString
+     * @return array
+     */
+    private function parseData($dataString)
+    {
+        $output = array();
+        $field  = array();
+        foreach (explode(PHP_EOL, $dataString) as $line) {
+            $trimmedLine = trim($line);
+            if ($trimmedLine === '---' || $trimmedLine === '') {
+                // Block completed; process it
+                if (sizeof($field) > 0) {
+                    $output[] = $field;
+                }
+                $field = array();
+                continue;
+            }
+            // Process contents of data block
+            $parts = explode(':', $line);
+            $key   = null;
+            $value = null;
+
+            // Handle colon in the value
+            if (sizeof($parts) !== 2) {
+                $key = $parts[0];
+                unset($parts[0]);
+                $value = implode(':', $parts);
+            }
+
+            $key   = $key   ?: trim($parts[0]);
+            $value = $value ?: trim($parts[1]);
+            if (isset($field[$key])) {
+                $field[$key]   = (array) $field[$key];
+                $field[$key][] = $value;
+            }
+            else {
+                $field[$key] = $value;
+            }
+        }
+
+        // process final block
+        if (sizeof($field) > 0) {
+            $output[] = $field;
+        }
+
+        return $output;
+    }
+}

src/Pdf.php

@@ -62,7 +62,7 @@ class Pdf
     protected $_data_utf8;
 
     /**
-     * @var string the PDF form field data as returned from getDataFields()
+     * @var DataFields the PDF form field data as returned from getDataFields()
      */
     protected $_dataFields;
     protected $_dataFields_utf8;
@@ -331,7 +331,7 @@ public function getData($utf8 = true)
 
     /**
      * @param bool $utf8 whether to dump the data UTF-8 encoded. Default is true.
-     * @return string|bool data about the PDF form fields or false on failure
+     * @return DataFields|bool data about the PDF form fields or false on failure
      */
     public function getDataFields($utf8 = true)
     {
@@ -342,7 +342,7 @@ public function getDataFields($utf8 = true)
             if (!$command->execute()) {
                 return false;
             } else {
-                $this->$property = trim($command->getOutput());
+                $this->$property = new DataFields(trim($command->getOutput()));
             }
         }
         return $this->$property;

tests/PdfTest.php

@@ -545,8 +545,10 @@ public function testCanGetDataFields()
 
         $pdf = new Pdf($form);
         $data = $pdf->getDataFields();
-        $this->assertInternalType('string', $data);
-        $this->assertEquals($this->formDataFields, $data);
+        $this->assertInternalType('string', $data->__toString());
+        $this->assertEquals($this->formDataFields, $data->__toString());
+        $this->assertInternalType('array', $data->__toArray());
+        $this->assertEquals($this->formDataFieldsArray, $data->__toArray());
     }
 
     protected function getDocument1()
@@ -621,4 +623,42 @@ protected function getOutFile()
 FieldJustification: Left
 EOD;
 
+    protected $formDataFieldsArray = array(
+        array(
+            'FieldType'          => 'Button',
+            'FieldName'          => 'checkbox 1',
+            'FieldFlags'         => '0',
+            'FieldValue'         => 'On',
+            'FieldJustification' => 'Left',
+            'FieldStateOption'   => array('Off', 'On'),
+        ),
+        array(
+            'FieldType'          => 'Button',
+            'FieldName'          => 'checkbox 2',
+            'FieldFlags'         => '0',
+            'FieldValue'         => 'On',
+            'FieldJustification' => 'Left',
+            'FieldStateOption'   => array('Off', 'On'),
+),
+        array(
+            'FieldType'          => 'Button',
+            'FieldName'          => 'radio 1',
+            'FieldFlags'         => '49152',
+            'FieldValue'         => '2',
+            'FieldJustification' => 'Left',
+            'FieldStateOption'   => array('1', '2', 'Off'),
+        ),
+        array(
+            'FieldType'          => 'Text',
+            'FieldName'          => 'email',
+            'FieldFlags'         => '0',
+            'FieldJustification' => 'Left',
+        ),
+        array(
+            'FieldType'          => 'Text',
+            'FieldName'          => 'name',
+            'FieldFlags'         => '0',
+            'FieldJustification' => 'Left',
+        ),
+    );
 }