CRM/Utils/PDF/Document.php

   1 <?php
   2 /*
   3  +--------------------------------------------------------------------+
   4  | CiviCRM version 4.7                                                |
   5  +--------------------------------------------------------------------+
   6  | Copyright CiviCRM LLC (c) 2004-2017                                |
   7  +--------------------------------------------------------------------+
   8  | This file is a part of CiviCRM.                                    |
   9  |                                                                    |
  10  | CiviCRM is free software; you can copy, modify, and distribute it  |
  11  | under the terms of the GNU Affero General Public License           |
  12  | Version 3, 19 November 2007 and the CiviCRM Licensing Exception.   |
  13  |                                                                    |
  14  | CiviCRM is distributed in the hope that it will be useful, but     |
  15  | WITHOUT ANY WARRANTY; without even the implied warranty of         |
  16  | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.               |
  17  | See the GNU Affero General Public License for more details.        |
  18  |                                                                    |
  19  | You should have received a copy of the GNU Affero General Public   |
  20  | License and the CiviCRM Licensing Exception along                  |
  21  | with this program; if not, contact CiviCRM LLC                     |
  22  | at info[AT]civicrm[DOT]org. If you have questions about the        |
  23  | GNU Affero General Public License or the licensing of CiviCRM,     |
  24  | see the CiviCRM license FAQ at http://civicrm.org/licensing        |
  25  +--------------------------------------------------------------------+
  26  */
  27
  28 /**
  29  *
  30  * @package CRM
  31  * @copyright CiviCRM LLC (c) 2004-2017
  32  */
  33
  34 require_once 'TbsZip/tbszip.php';
  35
  36 /**
  37  * Class CRM_Utils_PDF_Document.
  38  */
  39 class CRM_Utils_PDF_Document {
  40
  41   public static $ooxmlMap = array(
  42     'docx' => array(
  43       'dataFile' => 'word/document.xml',
  44       'startTag' => '<w:body>',
  45       '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>',
  46       'endTag' => '</w:body></w:document>',
  47     ),
  48     'odt' => array(
  49       'dataFile' => 'content.xml',
  50       'startTag' => '<office:body>',
  51       'pageBreak' => '<text:p text:style-name="Standard"></text:p>',
  52       'endTag' => '</office:body></office:document-content>',
  53     ),
  54   );
  55
  56   /**
  57    * Convert html to a Doc file.
  58    *
  59    * @param array $pages
  60    * @param string $fileName
  61    * @param array|int $format
  62    */
  63   public static function html2doc($pages, $fileName, $format = array()) {
  64     if (is_array($format)) {
  65       // PDF Page Format parameters passed in - merge with defaults
  66       $format += CRM_Core_BAO_PdfFormat::getDefaultValues();
  67     }
  68     else {
  69       // PDF Page Format ID passed in
  70       $format = CRM_Core_BAO_PdfFormat::getById($format);
  71     }
  72     $paperSize = CRM_Core_BAO_PaperSize::getByName($format['paper_size']);
  73
  74     $metric = CRM_Core_BAO_PdfFormat::getValue('metric', $format);
  75     $pageStyle = array(
  76       'orientation' => CRM_Core_BAO_PdfFormat::getValue('orientation', $format),
  77       'pageSizeW' => self::toTwip($paperSize['width'], $paperSize['metric']),
  78       'pageSizeH' => self::toTwip($paperSize['height'], $paperSize['metric']),
  79       'marginTop' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_top', $format), $metric),
  80       'marginRight' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_right', $format), $metric),
  81       'marginBottom' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_bottom', $format), $metric),
  82       'marginLeft' => self::toTwip(CRM_Core_BAO_PdfFormat::getValue('margin_left', $format), $metric),
  83     );
  84
  85     $ext = pathinfo($fileName, PATHINFO_EXTENSION);
  86
  87     $phpWord = new \PhpOffice\PhpWord\PhpWord();
  88
  89     $phpWord->getDocInfo()
  90       ->setCreator(CRM_Core_DAO::getFieldValue('CRM_Contact_BAO_Contact', CRM_Core_Session::getLoggedInContactID(), 'display_name'));
  91
  92     foreach ((array) $pages as $page => $html) {
  93       $section = $phpWord->addSection($pageStyle + array('breakType' => 'nextPage'));
  94       \PhpOffice\PhpWord\Shared\Html::addHtml($section, $html);
  95     }
  96
  97     self::printDoc($phpWord, $ext, $fileName);
  98   }
  99
 100   /**
 101    * @param object|string $phpWord
 102    * @param string $ext
 103    * @param string $fileName
 104    */
 105   public static function printDoc($phpWord, $ext, $fileName) {
 106     $formats = array(
 107       'docx' => 'Word2007',
 108       'odt' => 'ODText',
 109       'html' => 'HTML',
 110       // todo
 111       'pdf' => 'PDF',
 112     );
 113
 114     if (realpath($fileName)) {
 115       $phpWord = \PhpOffice\PhpWord\IOFactory::load($fileName, $formats[$ext]);
 116     }
 117
 118     \PhpOffice\PhpWord\Settings::setOutputEscapingEnabled(TRUE); //CRM-20015
 119     $objWriter = \PhpOffice\PhpWord\IOFactory::createWriter($phpWord, $formats[$ext]);
 120
 121     CRM_Utils_System::setHttpHeader('Content-Type', "application/$ext");
 122     CRM_Utils_System::setHttpHeader('Content-Disposition', 'attachment; filename="' . $fileName . '"');
 123     $objWriter->save("php://output");
 124   }
 125
 126   /**
 127    * @param $value
 128    * @param $metric
 129    * @return int
 130    */
 131   public static function toTwip($value, $metric) {
 132     $point = CRM_Utils_PDF_Utils::convertMetric($value, $metric, 'pt');
 133     return \PhpOffice\PhpWord\Shared\Converter::pointToTwip($point);
 134   }
 135
 136   /**
 137    * @param array $path  docx/odt file path
 138    * @param string $type  File type
 139    *
 140    * @return array
 141    *    Return extracted content of document in HTML and document type
 142    */
 143   public static function docReader($path, $type) {
 144     $type = array_search($type, CRM_Core_SelectValues::documentApplicationType());
 145     $fileType = ($type == 'docx') ? 'Word2007' : 'ODText';
 146
 147     $phpWord = \PhpOffice\PhpWord\IOFactory::load($path, $fileType);
 148     $phpWordHTML = new \PhpOffice\PhpWord\Writer\HTML($phpWord);
 149
 150     // return the html content for tokenreplacment and eventually used for document download
 151     return array($phpWordHTML->getWriterPart('Body')->write(), $type);
 152   }
 153
 154   /**
 155    * Extract content of docx/odt file
 156    *
 157    * @param string $filePath  Document file path
 158    * @param string $docType  File type of document
 159    *
 160    * @return array
 161    *   [string, clsTbsZip]
 162    */
 163   public static function unzipDoc($filePath, $docType) {
 164     $dataFile = self::$ooxmlMap[$docType]['dataFile'];
 165
 166     $zip = new clsTbsZip();
 167     $zip->Open($filePath);
 168     $content = $zip->FileRead($dataFile);
 169
 170     return array($content, $zip);
 171   }
 172
 173   /**
 174    * Modify contents of docx/odt file(s) and later merged into one final document
 175    *
 176    * @param string $filePath
 177    *   Document file path
 178    * @param array $contents
 179    *   Content of formatted/token-replaced document
 180    * @param string $docType
 181    *   Document type e.g. odt/docx
 182    * @param clsTbsZip $zip
 183    *   Zip archive
 184    * @param bool $returnFinalContent
 185    *   Return the content of file document as a string used in unit test
 186    *
 187    * @return string
 188    */
 189   public static function printDocuments($filePath, $contents, $docType, $zip, $returnFinalContent = FALSE) {
 190     $dataMap = self::$ooxmlMap[$docType];
 191
 192     $finalContent = $zip->FileRead($dataMap['dataFile']);
 193
 194     // token-replaced document contents of each contact will be merged into final document
 195     foreach ($contents as $key => $content) {
 196       if ($key == 0) {
 197         $finalContent = $content;
 198         continue;
 199       }
 200
 201       // 1. fetch the start position of document body
 202       // 2. later fetch only the body part starting from position $start
 203       // 3. replace closing body tag with pageBreak
 204       // 4. append the $content to the finalContent
 205       $start = strpos($content, $dataMap['startTag']);
 206       $content = substr($content, $start);
 207       $content = str_replace($dataMap['startTag'], $dataMap['pageBreak'], $content);
 208       $finalContent = str_replace($dataMap['endTag'], $content, $finalContent);
 209     }
 210
 211     if ($returnFinalContent) {
 212       return $finalContent;
 213     }
 214
 215     // Replace the loaded document file content located at $filePath with $finaContent
 216     $zip->FileReplace($dataMap['dataFile'], $finalContent, TBSZIP_STRING);
 217
 218     $fileName = pathinfo($filePath, PATHINFO_FILENAME) . '.' . $docType;
 219     $zip->Flush(TBSZIP_DOWNLOAD, $fileName);
 220   }
 221
 222 }