1
|
|
|
<?php |
2
|
|
|
namespace AOE\Crawler\Task; |
3
|
|
|
|
4
|
|
|
/*************************************************************** |
5
|
|
|
* Copyright notice |
6
|
|
|
* |
7
|
|
|
* (c) 2016 AOE GmbH <[email protected]> |
8
|
|
|
* |
9
|
|
|
* All rights reserved |
10
|
|
|
* |
11
|
|
|
* This script is part of the TYPO3 project. The TYPO3 project is |
12
|
|
|
* free software; you can redistribute it and/or modify |
13
|
|
|
* it under the terms of the GNU General Public License as published by |
14
|
|
|
* the Free Software Foundation; either version 3 of the License, or |
15
|
|
|
* (at your option) any later version. |
16
|
|
|
* |
17
|
|
|
* The GNU General Public License can be found at |
18
|
|
|
* http://www.gnu.org/copyleft/gpl.html. |
19
|
|
|
* |
20
|
|
|
* This script is distributed in the hope that it will be useful, |
21
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
22
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
23
|
|
|
* GNU General Public License for more details. |
24
|
|
|
* |
25
|
|
|
* This copyright notice MUST APPEAR in all copies of the script! |
26
|
|
|
***************************************************************/ |
27
|
|
|
|
28
|
|
|
use TYPO3\CMS\Core\Utility\GeneralUtility; |
|
|
|
|
29
|
|
|
use TYPO3\CMS\Scheduler\Task\AbstractTask; |
|
|
|
|
30
|
|
|
|
31
|
|
|
/** |
32
|
|
|
* Class CrawlerQueueTask |
33
|
|
|
* |
34
|
|
|
* @package AOE\Crawler\Task |
35
|
|
|
* @codeCoverageIgnore |
36
|
|
|
*/ |
37
|
|
|
class CrawlerQueueTask extends AbstractTask |
38
|
|
|
{ |
39
|
|
|
/** |
40
|
|
|
* Define the current mode to process the crawler |
41
|
|
|
* |
42
|
|
|
* @var string |
43
|
|
|
*/ |
44
|
|
|
const MODE = 'queue'; |
45
|
|
|
|
46
|
|
|
/** |
47
|
|
|
* Depth to run the crawler |
48
|
|
|
* |
49
|
|
|
* @var integer |
50
|
|
|
*/ |
51
|
|
|
public $depth; |
52
|
|
|
|
53
|
|
|
/** |
54
|
|
|
* Startpage for the crawler |
55
|
|
|
* |
56
|
|
|
* @var integer |
57
|
|
|
*/ |
58
|
|
|
public $startPage; |
59
|
|
|
|
60
|
|
|
/** |
61
|
|
|
* Configuration to run (comma separated list) |
62
|
|
|
* |
63
|
|
|
* @var string |
64
|
|
|
*/ |
65
|
|
|
public $configuration; |
66
|
|
|
|
67
|
|
|
/** |
68
|
|
|
* Function executed from the Scheduler. |
69
|
|
|
* |
70
|
|
|
* @return bool |
71
|
|
|
*/ |
72
|
|
|
public function execute() |
73
|
|
|
{ |
74
|
|
|
$this->setCliArguments(); |
75
|
|
|
|
76
|
|
|
/* @var $crawlerObject \tx_crawler_lib */ |
77
|
|
|
$crawlerObject = GeneralUtility::makeInstance('tx_crawler_lib'); |
78
|
|
|
$crawlerObject->CLI_main_im(); |
79
|
|
|
return true; |
80
|
|
|
} |
81
|
|
|
|
82
|
|
|
/** |
83
|
|
|
* Simulate cli call with setting the required options to the $_SERVER['argv'] |
84
|
|
|
* |
85
|
|
|
* @return void |
86
|
|
|
*/ |
87
|
|
|
protected function setCliArguments() |
88
|
|
|
{ |
89
|
|
|
// Make it backwards compatible. |
90
|
|
|
if (is_null($this->startPage)) { |
91
|
|
|
$this->startPage = 0; |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
$_SERVER['argv'] = [$_SERVER['argv'][0], $this->startPage,'-ss', '-d', $this->depth, '-o', self::MODE, '-conf', implode(',', $this->configuration)]; |
|
|
|
|
95
|
|
|
} |
96
|
|
|
|
97
|
|
|
/** |
98
|
|
|
* Retrieve some details about current scheduler task |
99
|
|
|
* to make the list view more useful. |
100
|
|
|
* |
101
|
|
|
* @return string |
102
|
|
|
*/ |
103
|
|
|
public function getAdditionalInformation() |
104
|
|
|
{ |
105
|
|
|
// Make it backwards compatible. |
106
|
|
|
if (is_null($this->startPage)) { |
107
|
|
|
$this->startPage = 0; |
108
|
|
|
} |
109
|
|
|
|
110
|
|
|
return implode(',', $this->configuration) . ' (depth: ' . $this->depth . ', startPage:' . $this->startPage . ')'; |
|
|
|
|
111
|
|
|
} |
112
|
|
|
} |
113
|
|
|
|
The issue could also be caused by a filter entry in the build configuration. If the path has been excluded in your configuration, e.g.
excluded_paths: ["lib/*"]
, you can move it to the dependency path list as follows:For further information see https://scrutinizer-ci.com/docs/tools/php/php-scrutinizer/#list-dependency-paths