CRM/Utils/PDF/Document.php

   1 <?php
   2 /*
   3  +--------------------------------------------------------------------+
   4  | Copyright CiviCRM LLC. All rights reserved.                        |
   5  |                                                                    |
   6  | This work is published under the GNU AGPLv3 license with some      |
   7  | permitted exceptions and without any warranty. For full license    |
   8  | and copyright information, see https://civicrm.org/licensing       |
   9  +--------------------------------------------------------------------+
  10  */
  11
  12 /**
  13  *
  14  * @package CRM
  15  * @copyright CiviCRM LLC https://civicrm.org/licensing
  16  */
  17
  18 require_once 'TbsZip/tbszip.php';
  19
  20 /**
  21  * Class CRM_Utils_PDF_Document.
  22  */
  23 class CRM_Utils_PDF_Document {
  24
  25   public static $ooxmlMap = [
  26     'docx' => [
  27       'dataFile' => 'word/document.xml',
  28       'startTag' => '<w:body>',
  29       'pageBreak' => '<w:p><w:pPr><w:pStyle w:val="Normal"/><w:rPr></w:rPr></w:pPr><w:r><w:rPr></w:rPr></w:r><w:r><w:br w:type="page"/></w:r></w:p>',
  30       'endTag' => '</w:body></w:document>',
  31     ],
  32     'odt' => [
  33       'dataFile' => 'content.xml',
  34       'startTag' => '<office:body>',
  35       'pageBreak' => '<text:p text:style-name="Standard"></text:p>',
  36       'endTag' => '</office:body></office:document-content>',
  37     ],
  38   ];
  39
  40   /**
  41    * Convert html to a Doc file.
  42    *
  43    * @param array $pages
  44    *   List of HTML snippets.
  45    * @param string $fileName
  46    *   The logical filename to return to client.
  47    *   Ex: "HelloWorld.odt".
  48    * @param array|int $format
  49    */
  50   public static function html2doc($pages, $fileName, $format = []) {
  51     if (is_array($format)) {
  52       // PDF Page Format parameters passed in - merge with defaults
  53       $format += CRM_Core_BAO_PdfFormat::getDefaultValues();
  54     }
  55     else {
  56       // PDF Page Format ID passed in
  57       $format = CRM_Core_BAO_PdfFormat::getById($format);
  58     }
  59     $paperSize = CRM_Core_BAO_PaperSize::getByName($format['paper_size']);
  60
  61     $metric = CRM_Core_BAO_PdfFormat::getValue('metric', $format);
  62     $pageStyle = [
  63       'orientation' => CRM_Core_BAO_PdfFormat::getValue('orientation', $format),
  64       'pageSizeW' => self::toTwip($paperSize['width'], $paperSize['metric']),
  65       'pageSizeH' => self::toTwip($paperSize['height'], $paperSize['metric']),
  66       'marginTop' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_top', $format), $metric),
  67       'marginRight' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_right', $format), $metric),
  68       'marginBottom' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_bottom', $format), $metric),
  69       'marginLeft' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_left', $format), $metric),
  70     ];
  71     if (CIVICRM_UF === 'UnitTests' && headers_sent()) {
  72       // Streaming content will 'die' in unit tests unless ob_start()
  73       // has been called.
  74       throw new CRM_Core_Exception_PrematureExitException('_html2doc called', [
  75         'html' => $pages,
  76         'fileName' => $fileName,
  77         'pageStyle' => $pageStyle,
  78       ]);
  79     }
  80
  81     $ext = pathinfo($fileName, PATHINFO_EXTENSION);
  82
  83     $phpWord = new \PhpOffice\PhpWord\PhpWord();
  84
  85     $phpWord->getDocInfo()
  86       ->setCreator(CRM_Core_DAO::getFieldValue('CRM_Contact_BAO_Contact', CRM_Core_Session::getLoggedInContactID(), 'display_name'));
  87
  88     foreach ((array) $pages as $page => $html) {
  89       $section = $phpWord->addSection($pageStyle + ['breakType' => 'nextPage']);
  90       \PhpOffice\PhpWord\Shared\Html::addHtml($section, $html);
  91     }
  92
  93     self::printDoc($phpWord, $ext, $fileName);
  94   }
  95
  96   /**
  97    * @param object|string $phpWord
  98    * @param string $ext
  99    *   File extension/type.
 100    *   Ex: docx, odt, html.
 101    * @param string $fileName
 102    *   The logical filename to return to client.
 103    *   Ex: "HelloWorld.odt".
 104    *   Alternatively, a full path of a file to display. This seems sketchy.
 105    *   Ex: "/var/lib/data/HelloWorld.odt".
 106    */
 107   public static function printDoc($phpWord, $ext, $fileName) {
 108     $formats = [
 109       'docx' => 'Word2007',
 110       'odt' => 'ODText',
 111       'html' => 'HTML',
 112       // todo
 113       'pdf' => 'PDF',
 114     ];
 115
 116     if (realpath($fileName)) {
 117       $phpWord = \PhpOffice\PhpWord\IOFactory::load($fileName, $formats[$ext]);
 118     }
 119
 120     //CRM-20015
 121     \PhpOffice\PhpWord\Settings::setOutputEscapingEnabled(TRUE);
 122     $objWriter = \PhpOffice\PhpWord\IOFactory::createWriter($phpWord, $formats[$ext]);
 123
 124     CRM_Utils_System::setHttpHeader('Content-Type', "application/$ext");
 125     CRM_Utils_System::setHttpHeader('Content-Disposition', 'attachment; filename="' . $fileName . '"');
 126     $objWriter->save("php://output");
 127   }
 128
 129   /**
 130    * @param $value
 131    * @param $metric
 132    * @return int
 133    */
 134   public static function toTwip($value, $metric) {
 135     $point = CRM_Utils_PDF_Utils::convertMetric($value, $metric, 'pt');
 136     return \PhpOffice\PhpWord\Shared\Converter::pointToTwip($point);
 137   }
 138
 139   /**
 140    * @param array $path  docx/odt file path
 141    * @param string $type  File type
 142    *
 143    * @return array
 144    *   Return extracted content of document in HTML and document type
 145    */
 146   public static function docReader($path, $type) {
 147     $type = array_search($type, CRM_Core_SelectValues::documentApplicationType());
 148     $fileType = ($type == 'docx') ? 'Word2007' : 'ODText';
 149
 150     $phpWord = \PhpOffice\PhpWord\IOFactory::load($path, $fileType);
 151     $phpWordHTML = new \PhpOffice\PhpWord\Writer\HTML($phpWord);
 152
 153     // return the html content for tokenreplacment and eventually used for document download
 154     return [$phpWordHTML->getWriterPart('Body')->write(), $type];
 155   }
 156
 157   /**
 158    * Extract content of docx/odt file
 159    *
 160    * @param string $filePath  Document file path
 161    * @param string $docType  File type of document
 162    *
 163    * @return array
 164    *   [string, clsTbsZip]
 165    */
 166   public static function unzipDoc($filePath, $docType) {
 167     $dataFile = self::$ooxmlMap[$docType]['dataFile'];
 168
 169     $zip = new clsTbsZip();
 170     $zip->Open($filePath);
 171     $content = $zip->FileRead($dataFile);
 172
 173     return [$content, $zip];
 174   }
 175
 176   /**
 177    * Modify contents of docx/odt file(s) and later merged into one final document
 178    *
 179    * @param array $contents
 180    *   Content of formatted/token-replaced document.
 181    *   List of HTML snippets.
 182    * @param string $fileName
 183    *   The logical filename to return to client.
 184    *   Ex: "HelloWorld.odt".
 185    * @param string $docType
 186    *   Document type e.g. odt/docx
 187    * @param clsTbsZip $zip
 188    *   Zip archive
 189    * @param bool $returnFinalContent
 190    *   Return the content of file document as a string used in unit test
 191    *
 192    * @return string
 193    */
 194   public static function printDocuments($contents, $fileName, $docType, $zip, $returnFinalContent = FALSE) {
 195     $dataMap = self::$ooxmlMap[$docType];
 196
 197     $finalContent = $zip->FileRead($dataMap['dataFile']);
 198
 199     // token-replaced document contents of each contact will be merged into final document
 200     foreach ($contents as $key => $content) {
 201       if ($key == 0) {
 202         $finalContent = $content;
 203         continue;
 204       }
 205
 206       // 1. fetch the start position of document body
 207       // 2. later fetch only the body part starting from position $start
 208       // 3. replace closing body tag with pageBreak
 209       // 4. append the $content to the finalContent
 210       $start = strpos($content, $dataMap['startTag']);
 211       $content = substr($content, $start);
 212       $content = str_replace($dataMap['startTag'], $dataMap['pageBreak'], $content);
 213       $finalContent = str_replace($dataMap['endTag'], $content, $finalContent);
 214     }
 215
 216     if ($returnFinalContent) {
 217       return $finalContent;
 218     }
 219
 220     // Replace the loaded document file content located at $filePath with $finaContent
 221     $zip->FileReplace($dataMap['dataFile'], $finalContent, TBSZIP_STRING);
 222
 223     $zip->Flush(TBSZIP_DOWNLOAD, $fileName);
 224   }
 225
 226 }