|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/* |
|
4
|
|
|
* This file is part of the TYPO3 CMS project. |
|
5
|
|
|
* |
|
6
|
|
|
* It is free software; you can redistribute it and/or modify it under |
|
7
|
|
|
* the terms of the GNU General Public License, either version 2 |
|
8
|
|
|
* of the License, or any later version. |
|
9
|
|
|
* |
|
10
|
|
|
* For the full copyright and license information, please read the |
|
11
|
|
|
* LICENSE.txt file that was distributed with this source code. |
|
12
|
|
|
* |
|
13
|
|
|
* The TYPO3 project - inspiring people to share! |
|
14
|
|
|
*/ |
|
15
|
|
|
|
|
16
|
|
|
namespace ApacheSolrForTypo3\Solr; |
|
17
|
|
|
|
|
18
|
|
|
use ApacheSolrForTypo3\Solr\System\Logging\SolrLogManager; |
|
19
|
|
|
use DOMDocument; |
|
20
|
|
|
use DOMXPath; |
|
21
|
|
|
use function libxml_use_internal_errors; |
|
22
|
|
|
use TYPO3\CMS\Core\Utility\GeneralUtility; |
|
23
|
|
|
|
|
24
|
|
|
/** |
|
25
|
|
|
* Content extraction class for TYPO3 pages. |
|
26
|
|
|
* |
|
27
|
|
|
* @author Ingo Renner <[email protected]> |
|
28
|
|
|
*/ |
|
29
|
|
|
class Typo3PageContentExtractor extends HtmlContentExtractor |
|
30
|
|
|
{ |
|
31
|
|
|
/** |
|
32
|
|
|
* @var SolrLogManager|null |
|
33
|
|
|
*/ |
|
34
|
|
|
protected ?SolrLogManager $logger; |
|
35
|
|
|
|
|
36
|
|
|
/** |
|
37
|
|
|
* Shortcut method to retrieve the raw content marked for indexing. |
|
38
|
|
|
* |
|
39
|
|
|
* @return string Content marked for indexing. |
|
40
|
|
|
*/ |
|
41
|
69 |
|
public function getContentMarkedForIndexing(): string |
|
42
|
|
|
{ |
|
43
|
69 |
|
return $this->extractContentMarkedForIndexing($this->content); |
|
44
|
|
|
} |
|
45
|
|
|
|
|
46
|
|
|
/** |
|
47
|
|
|
* Extracts the markup wrapped with TYPO3SEARCH_begin and TYPO3SEARCH_end |
|
48
|
|
|
* markers. |
|
49
|
|
|
* |
|
50
|
|
|
* @param string $html HTML markup with TYPO3SEARCH markers for content that should be indexed |
|
51
|
|
|
* @return string HTML markup found between TYPO3SEARCH markers |
|
52
|
|
|
*/ |
|
53
|
78 |
|
protected function extractContentMarkedForIndexing(string $html): string |
|
54
|
|
|
{ |
|
55
|
78 |
|
preg_match_all( |
|
56
|
|
|
'/<!--\s*?TYPO3SEARCH_begin\s*?-->.*?<!--\s*?TYPO3SEARCH_end\s*?-->/mis', |
|
57
|
|
|
$html, |
|
58
|
|
|
$indexableContents |
|
59
|
|
|
); |
|
60
|
78 |
|
$indexableContent = implode('', $indexableContents[0]); |
|
61
|
|
|
|
|
62
|
78 |
|
$indexableContent = $this->excludeContentByClass($indexableContent); |
|
63
|
78 |
|
if (empty($indexableContent) && $this->getConfiguration()->getLoggingIndexingMissingTypo3SearchMarkers()) { |
|
64
|
19 |
|
$this->logger = GeneralUtility::makeInstance(SolrLogManager::class, /** @scrutinizer ignore-type */ __CLASS__); |
|
65
|
19 |
|
$this->logger->log(SolrLogManager::WARNING, 'No TYPO3SEARCH markers found.'); |
|
|
|
|
|
|
66
|
|
|
} |
|
67
|
|
|
|
|
68
|
78 |
|
return $indexableContent; |
|
69
|
|
|
} |
|
70
|
|
|
|
|
71
|
|
|
/** |
|
72
|
|
|
* Exclude some html parts by class inside content wrapped with TYPO3SEARCH_begin and TYPO3SEARCH_end |
|
73
|
|
|
* markers. |
|
74
|
|
|
* |
|
75
|
|
|
* @param string $indexableContent HTML markup |
|
76
|
|
|
* @return string HTML |
|
77
|
|
|
*/ |
|
78
|
81 |
|
public function excludeContentByClass(string $indexableContent): string |
|
79
|
|
|
{ |
|
80
|
81 |
|
if (empty(trim($indexableContent))) { |
|
81
|
19 |
|
return $indexableContent; |
|
82
|
|
|
} |
|
83
|
|
|
|
|
84
|
64 |
|
$excludeClasses = $this->getConfiguration()->getIndexQueuePagesExcludeContentByClassArray(); |
|
85
|
64 |
|
if (count($excludeClasses) === 0) { |
|
86
|
|
|
return $indexableContent; |
|
87
|
|
|
} |
|
88
|
|
|
|
|
89
|
64 |
|
$isInContent = Util::containsOneOfTheStrings($indexableContent, $excludeClasses); |
|
90
|
64 |
|
if (!$isInContent) { |
|
91
|
61 |
|
return $indexableContent; |
|
92
|
|
|
} |
|
93
|
|
|
|
|
94
|
3 |
|
$doc = new DOMDocument('1.0', 'UTF-8'); |
|
95
|
3 |
|
libxml_use_internal_errors(true); |
|
96
|
3 |
|
$doc->loadHTML('<?xml version="1.0" encoding="UTF-8"?>' . PHP_EOL . $indexableContent); |
|
97
|
3 |
|
$xpath = new DOMXPath($doc); |
|
98
|
3 |
|
foreach ($excludeClasses as $excludePart) { |
|
99
|
3 |
|
$elements = $xpath->query("//*[contains(@class,'" . $excludePart . "')]"); |
|
100
|
3 |
|
if (count($elements) == 0) { |
|
101
|
|
|
continue; |
|
102
|
|
|
} |
|
103
|
|
|
|
|
104
|
3 |
|
foreach ($elements as $element) { |
|
105
|
3 |
|
$element->parentNode->removeChild($element); |
|
106
|
|
|
} |
|
107
|
|
|
} |
|
108
|
3 |
|
$html = $doc->saveHTML($doc->documentElement->parentNode); |
|
109
|
|
|
// remove XML-Preamble, newlines and doctype |
|
110
|
3 |
|
$html = preg_replace('/(<\?xml[^>]+\?>|\r?\n|<!DOCTYPE.+?>)/imS', '', $html); |
|
111
|
3 |
|
return str_replace(['<html>', '</html>', '<body>', '</body>'], ['', '', '', ''], $html); |
|
112
|
|
|
} |
|
113
|
|
|
|
|
114
|
|
|
/** |
|
115
|
|
|
* Returns the cleaned indexable content from the page's HTML markup. |
|
116
|
|
|
* |
|
117
|
|
|
* The content is cleaned from HTML tags and control chars Solr could |
|
118
|
|
|
* stumble on. |
|
119
|
|
|
* |
|
120
|
|
|
* @return string Indexable, cleaned content ready for indexing. |
|
121
|
|
|
*/ |
|
122
|
78 |
|
public function getIndexableContent(): string |
|
123
|
|
|
{ |
|
124
|
|
|
// @extensionScannerIgnoreLine |
|
125
|
78 |
|
$content = $this->extractContentMarkedForIndexing($this->content); |
|
126
|
|
|
|
|
127
|
|
|
// clean content |
|
128
|
78 |
|
$content = self::cleanContent($content); |
|
129
|
78 |
|
$content = trim($content); |
|
130
|
|
|
// reduce multiple spaces to one space and return |
|
131
|
78 |
|
return preg_replace('!\s+!u', ' ', $content); |
|
132
|
|
|
} |
|
133
|
|
|
|
|
134
|
|
|
/** |
|
135
|
|
|
* Retrieves the page's title by checking the indexedDocTitle, altPageTitle, |
|
136
|
|
|
* and regular page title - in that order. |
|
137
|
|
|
* |
|
138
|
|
|
* @return string the page's title |
|
139
|
|
|
*/ |
|
140
|
69 |
|
public function getPageTitle(): string |
|
141
|
|
|
{ |
|
142
|
69 |
|
$page = $GLOBALS['TSFE']; |
|
143
|
|
|
|
|
144
|
69 |
|
if ($page->indexedDocTitle) { |
|
145
|
52 |
|
$pageTitle = $page->indexedDocTitle; |
|
146
|
17 |
|
} elseif ($page->altPageTitle) { |
|
147
|
|
|
$pageTitle = $page->altPageTitle; |
|
148
|
|
|
} else { |
|
149
|
17 |
|
$pageTitle = $page->page['title']; |
|
150
|
|
|
} |
|
151
|
|
|
|
|
152
|
69 |
|
return $pageTitle ?? ''; |
|
153
|
|
|
} |
|
154
|
|
|
|
|
155
|
|
|
/** |
|
156
|
|
|
* Retrieves the page's body |
|
157
|
|
|
* |
|
158
|
|
|
* @return string the page's body |
|
159
|
|
|
*/ |
|
160
|
|
|
public function getPageBody(): string |
|
161
|
|
|
{ |
|
162
|
|
|
return stristr($this->content, '<body'); |
|
163
|
|
|
} |
|
164
|
|
|
} |
|
165
|
|
|
|
TYPO3-Solr /
ext-solr
This check looks for calls to methods that do not seem to exist on a given type. It looks for the method on the type itself as well as in inherited classes or implemented interfaces.
This is most likely a typographical error or the method has been renamed.