gnh1201/paperless
1
0
Fork 0
mirror of https://codeberg.org/SeedDMS/paperless synced 2025-02-11 09:25:23 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

use text previewer to get content of document

Browse Source
This commit is contained in:
Uwe Steinmann 2023-01-05 10:27:51 +01:00
parent b1e64e8d66
commit c01cfb8491
1 changed files with 28 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
class.paperless.php
View File

@ -57,21 +57,40 @@ class SeedDMS_ExtPaperless_RestAPI_Controller { /* {{{ */
protected function __getDocumentData($document) { /* {{{ */ protected function __getDocumentData($document) { /* {{{ */
$fulltextservice = $this->container->fulltextservice; $fulltextservice = $this->container->fulltextservice;
$settings = $this->container->config;
$conversionmgr = $this->container->conversionmgr;
$lc = $document->getLatestContent();
$content = ''; $content = '';
$index = $fulltextservice->Indexer(); /* The plain text can either be created by the text previewer
if($index) { * or taken from the fulltext index. The text from the fulltext index
$lucenesearch = $fulltextservice->Search(); * does not have stop words anymore if a stop words file was
if($searchhit = $lucenesearch->getDocument($document->getID())) { * configured during indexing.
$idoc = $searchhit->getDocument(); */
try { if(1) {
$content = htmlspecialchars(mb_strimwidth($idoc->getFieldValue('content'), 0, 3000, '...')); $txtpreviewer = new SeedDMS_Preview_TxtPreviewer($settings->_cacheDir, $settings->_cmdTimeout, $settings->_enableXsendfile);
} catch (Exception $e) { $txtpreviewer->setConversionMgr($conversionmgr);
if(!$txtpreviewer->hasPreview($lc))
$txtpreviewer->createPreview($lc);
$file = $txtpreviewer->getFileName($lc).".txt";
if(file_exists($file))
$content = file_get_contents($file);
} else {
$index = $fulltextservice->Indexer();
if($index) {
$lucenesearch = $fulltextservice->Search();
if($searchhit = $lucenesearch->getDocument($document->getID())) {
$idoc = $searchhit->getDocument();
try {
$content = htmlspecialchars(mb_strimwidth($idoc->getFieldValue('content'), 0, 3000, '...'));
} catch (Exception $e) {
}
} }
} }
} }
$lc = $document->getLatestContent();
$cats = $document->getCategories(); $cats = $document->getCategories();
$tags = array(); $tags = array();
foreach($cats as $cat) foreach($cats as $cat)