3 +--------------------------------------------------------------------+
4 | Copyright CiviCRM LLC. All rights reserved. |
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 +--------------------------------------------------------------------+
15 * @copyright CiviCRM LLC https://civicrm.org/licensing
18 require_once 'TbsZip/tbszip.php';
21 * Class CRM_Utils_PDF_Document.
23 class CRM_Utils_PDF_Document
{
25 public static $ooxmlMap = [
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>',
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>',
41 * Convert html to a Doc file.
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 $format
50 public static function html2doc($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();
56 // PDF Page Format ID passed in
57 $format = CRM_Core_BAO_PdfFormat
::getById($format);
59 $paperSize = CRM_Core_BAO_PaperSize
::getByName($format['paper_size']);
61 $metric = CRM_Core_BAO_PdfFormat
::getValue('metric', $format);
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),
71 if (CIVICRM_UF
=== 'UnitTests' && headers_sent()) {
72 // Streaming content will 'die' in unit tests unless ob_start()
74 throw new CRM_Core_Exception_PrematureExitException('_html2doc called', [
76 'fileName' => $fileName,
77 'pageStyle' => $pageStyle,
81 $ext = pathinfo($fileName, PATHINFO_EXTENSION
);
83 $phpWord = new \PhpOffice\PhpWord\
PhpWord();
85 $phpWord->getDocInfo()
86 ->setCreator(CRM_Core_DAO
::getFieldValue('CRM_Contact_BAO_Contact', CRM_Core_Session
::getLoggedInContactID(), 'display_name'));
88 foreach ((array) $pages as $page => $html) {
89 $section = $phpWord->addSection($pageStyle +
['breakType' => 'nextPage']);
90 \PhpOffice\PhpWord\Shared\Html
::addHtml($section, $html);
93 self
::printDoc($phpWord, $ext, $fileName);
97 * @param object|string $phpWord
99 * File extension/type.
100 * Ex: docx, odt, html.
101 * @param string $fileName
102 * The logical filename to return to client.
103 * Ex: "HelloWorld.odt".
104 * Alternatively, a full path of a file to display. This seems sketchy.
105 * Ex: "/var/lib/data/HelloWorld.odt".
107 public static function printDoc($phpWord, $ext, $fileName) {
109 'docx' => 'Word2007',
116 if (realpath($fileName)) {
117 $phpWord = \PhpOffice\PhpWord\IOFactory
::load($fileName, $formats[$ext]);
121 \PhpOffice\PhpWord\Settings
::setOutputEscapingEnabled(TRUE);
122 $objWriter = \PhpOffice\PhpWord\IOFactory
::createWriter($phpWord, $formats[$ext]);
124 CRM_Utils_System
::setHttpHeader('Content-Type', "application/$ext");
125 CRM_Utils_System
::setHttpHeader('Content-Disposition', 'attachment; filename="' . $fileName . '"');
126 $objWriter->save("php://output");
131 * @param string $metric
134 public static function toTwip($value, $metric) {
135 $point = CRM_Utils_PDF_Utils
::convertMetric($value, $metric, 'pt');
136 return \PhpOffice\PhpWord\Shared\Converter
::pointToTwip($point);
140 * @param array $path docx/odt file path
141 * @param string $type File type
144 * Return extracted content of document in HTML and document type
146 public static function docReader($path, $type) {
147 $type = array_search($type, CRM_Core_SelectValues
::documentApplicationType());
148 $fileType = ($type == 'docx') ?
'Word2007' : 'ODText';
150 $phpWord = \PhpOffice\PhpWord\IOFactory
::load($path, $fileType);
151 $phpWordHTML = new \PhpOffice\PhpWord\Writer\
HTML($phpWord);
153 // return the html content for tokenreplacment and eventually used for document download
154 return [$phpWordHTML->getWriterPart('Body')->write(), $type];
158 * Extract content of docx/odt file
160 * @param string $filePath Document file path
161 * @param string $docType File type of document
164 * [string, clsTbsZip]
166 public static function unzipDoc($filePath, $docType) {
167 $dataFile = self
::$ooxmlMap[$docType]['dataFile'];
169 $zip = new clsTbsZip();
170 $zip->Open($filePath);
171 $content = $zip->FileRead($dataFile);
173 return [$content, $zip];
177 * Modify contents of docx/odt file(s) and later merged into one final document
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
189 * @param bool $returnFinalContent
190 * Return the content of file document as a string used in unit test
194 public static function printDocuments($contents, $fileName, $docType, $zip, $returnFinalContent = FALSE) {
195 $dataMap = self
::$ooxmlMap[$docType];
197 $finalContent = $zip->FileRead($dataMap['dataFile']);
199 // token-replaced document contents of each contact will be merged into final document
200 foreach ($contents as $key => $content) {
202 $finalContent = $content;
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, $finalContent);
216 if ($returnFinalContent) {
217 return $finalContent;
220 // Replace the loaded document file content located at $filePath with $finaContent
221 $zip->FileReplace($dataMap['dataFile'], $finalContent, TBSZIP_STRING
);
223 $zip->Flush(TBSZIP_DOWNLOAD
, $fileName);