PHP code example of centertap / tika-all-the-files

1. Go to this page and download the library: Download centertap/tika-all-the-files library. Choose the download type require.

2. Extract the ZIP file and open the index.php.

3. Add this code to the index.php. 
    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

centertap / tika-all-the-files example snippets


   ...
   wfLoadExtension( 'TikaAllTheFiles' );
   ...
   

     [
        'defaults' => [
                        'handler_strategy' => 'fallback',
                        'allow_ocr' => false,
                        'ocr_languages' => '',
                        'content_strategy' => 'combine',
                        'content_composition' => 'text',
                        'metadata_strategy' => 'prefer_other',
                        'ignore_content_service_errors' => false,
                        'ignore_content_parsing_errors' => false,
                        'ignore_metadata_service_errors' => false,
                        'ignore_metadata_parsing_errors' => false,
                        'cache_expire_success_before': false,
                        'cache_expire_failure_before': false,
                        'cache_file_backend': false,
                      ],
        '*' => 'defaults',
     ]
     

$wgTikaAllTheFiles_MimeTypeProfiles['*'] = [
    'inherit' => 'defaults',
    'handler_strategy' => 'wrapping',
    'allow_ocr' => true,
    'content_composition' => 'text_and_metadata',
    'metadata_strategy' => 'combine',
    'cache_file_backend' => 'my-tatf-cache',
    ];

$wgTikaAllTheFiles_MimeTypeProfiles['application/pdf'] = [
    'inherit' => '*',
    'allow_ocr' => false,
    ];


$wgTikaAllTheFiles_PropertyMap['dc:language'] = true;
$wgTikaAllTheFiles_PropertyMap['!'] = false;


     $wgLockManagers[] = [
         'name' => 'my-tatf-lock-manager',
         'class' => FSLockManager::class,
         'lockDirectory' => "/somewhere/on/disk/amazing-tatf-cache/lockdir",
     ];
     

     $wgFileBackends[] = [
         'name' => 'my-tatf-cache',
         'class' => FSFileBackend::class,
         'domainId' => '',
         'lockManager' => 'my-tatf-lock-manager',
         'basePath' => "/somewhere/on/disk/amazing-tatf-cache",
         'fileMode' => 0644,
         'directoryMode' => 0755,
     ];

     

$ cd YOUR-WIKI-INSTALL-DIRECTORY/maintenance
$ php refreshImageMetadata.php --force


$ cd YOUR-WIKI-INSTALL-DIRECTORY/extensions/CirrusSearch/maintenance/
$ php ForceSearchIndex.php


   unset( $wgPdftoText )