|
1
|
|
|
<?php |
|
2
|
|
|
namespace ApacheSolrForTypo3\Solr; |
|
3
|
|
|
|
|
4
|
|
|
/*************************************************************** |
|
5
|
|
|
* Copyright notice |
|
6
|
|
|
* |
|
7
|
|
|
* (c) 2010-2015 Ingo Renner <[email protected]> |
|
8
|
|
|
* All rights reserved |
|
9
|
|
|
* |
|
10
|
|
|
* This script is part of the TYPO3 project. The TYPO3 project is |
|
11
|
|
|
* free software; you can redistribute it and/or modify |
|
12
|
|
|
* it under the terms of the GNU General Public License as published by |
|
13
|
|
|
* the Free Software Foundation; either version 2 of the License, or |
|
14
|
|
|
* (at your option) any later version. |
|
15
|
|
|
* |
|
16
|
|
|
* The GNU General Public License can be found at |
|
17
|
|
|
* http://www.gnu.org/copyleft/gpl.html. |
|
18
|
|
|
* |
|
19
|
|
|
* This script is distributed in the hope that it will be useful, |
|
20
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
21
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
22
|
|
|
* GNU General Public License for more details. |
|
23
|
|
|
* |
|
24
|
|
|
* This copyright notice MUST APPEAR in all copies of the script! |
|
25
|
|
|
***************************************************************/ |
|
26
|
|
|
|
|
27
|
|
|
use ApacheSolrForTypo3\Solr\System\Logging\SolrLogManager; |
|
28
|
|
|
use TYPO3\CMS\Core\Utility\GeneralUtility; |
|
29
|
|
|
|
|
30
|
|
|
/** |
|
31
|
|
|
* Content extraction class for TYPO3 pages. |
|
32
|
|
|
* |
|
33
|
|
|
* @author Ingo Renner <[email protected]> |
|
34
|
|
|
*/ |
|
35
|
|
|
class Typo3PageContentExtractor extends HtmlContentExtractor |
|
36
|
|
|
{ |
|
37
|
|
|
|
|
38
|
|
|
/** |
|
39
|
|
|
* @var \ApacheSolrForTypo3\Solr\System\Logging\SolrLogManager |
|
40
|
|
|
*/ |
|
41
|
|
|
protected $logger = null; |
|
42
|
|
|
|
|
43
|
|
|
/** |
|
44
|
|
|
* Shortcut method to retrieve the raw content marked for indexing. |
|
45
|
|
|
* |
|
46
|
|
|
* @return string Content marked for indexing. |
|
47
|
|
|
*/ |
|
48
|
45 |
|
public function getContentMarkedForIndexing() |
|
49
|
|
|
{ |
|
50
|
45 |
|
return $this->extractContentMarkedForIndexing($this->content); |
|
51
|
|
|
} |
|
52
|
|
|
|
|
53
|
|
|
/** |
|
54
|
|
|
* Extracts the markup wrapped with TYPO3SEARCH_begin and TYPO3SEARCH_end |
|
55
|
|
|
* markers. |
|
56
|
|
|
* |
|
57
|
|
|
* @param string $html HTML markup with TYPO3SEARCH markers for content that should be indexed |
|
58
|
|
|
* @return string HTML markup found between TYPO3SEARCH markers |
|
59
|
|
|
*/ |
|
60
|
46 |
|
protected function extractContentMarkedForIndexing($html) |
|
61
|
|
|
{ |
|
62
|
46 |
|
preg_match_all('/<!--\s*?TYPO3SEARCH_begin\s*?-->.*?<!--\s*?TYPO3SEARCH_end\s*?-->/mis', |
|
63
|
46 |
|
$html, $indexableContents); |
|
64
|
46 |
|
$indexableContent = implode($indexableContents[0], ''); |
|
65
|
|
|
|
|
66
|
46 |
|
$indexableContent = $this->excludeContentByClass($indexableContent); |
|
67
|
46 |
|
if (empty($indexableContent) && $this->getConfiguration()->getLoggingIndexingMissingTypo3SearchMarkers()) { |
|
68
|
7 |
|
$this->logger = GeneralUtility::makeInstance(SolrLogManager::class, __CLASS__); |
|
69
|
7 |
|
$this->logger->log( |
|
70
|
7 |
|
SolrLogManager::WARNING, |
|
71
|
|
|
'No TYPO3SEARCH markers found.' |
|
72
|
7 |
|
); |
|
73
|
7 |
|
} |
|
74
|
|
|
|
|
75
|
46 |
|
return $indexableContent; |
|
76
|
|
|
} |
|
77
|
|
|
|
|
78
|
|
|
/** |
|
79
|
|
|
* Exclude some html parts by class inside content wrapped with TYPO3SEARCH_begin and TYPO3SEARCH_end |
|
80
|
|
|
* markers. |
|
81
|
|
|
* |
|
82
|
|
|
* @param string $indexableContent HTML markup |
|
83
|
|
|
* @return string HTML |
|
84
|
|
|
*/ |
|
85
|
49 |
|
public function excludeContentByClass($indexableContent) |
|
86
|
|
|
{ |
|
87
|
49 |
|
if (empty(trim($indexableContent))) { |
|
88
|
7 |
|
return html_entity_decode($indexableContent); |
|
89
|
|
|
} |
|
90
|
|
|
|
|
91
|
42 |
|
$excludeClasses = $this->getConfiguration()->getIndexQueuePagesExcludeContentByClassArray(); |
|
92
|
42 |
|
if (count($excludeClasses) === 0) { |
|
93
|
7 |
|
return html_entity_decode($indexableContent); |
|
94
|
|
|
} |
|
95
|
|
|
|
|
96
|
35 |
|
$isInContent = Util::containsOneOfTheStrings($indexableContent, $excludeClasses); |
|
97
|
35 |
|
if (!$isInContent) { |
|
98
|
32 |
|
return html_entity_decode($indexableContent); |
|
99
|
|
|
} |
|
100
|
|
|
|
|
101
|
3 |
|
$doc = new \DOMDocument('1.0', 'UTF-8'); |
|
102
|
3 |
|
libxml_use_internal_errors(true); |
|
103
|
3 |
|
$doc->loadHTML('<?xml version="1.0" encoding="UTF-8"?>' . PHP_EOL . $indexableContent); |
|
104
|
3 |
|
$xpath = new \DOMXPath($doc); |
|
105
|
3 |
|
foreach ($excludeClasses as $excludePart) { |
|
106
|
3 |
|
$elements = $xpath->query("//*[contains(@class,'" . $excludePart . "')]"); |
|
107
|
3 |
|
if (count($elements) == 0) { |
|
108
|
|
|
continue; |
|
109
|
|
|
} |
|
110
|
|
|
|
|
111
|
3 |
|
foreach ($elements as $element) { |
|
112
|
3 |
|
$element->parentNode->removeChild($element); |
|
113
|
3 |
|
} |
|
114
|
3 |
|
} |
|
115
|
3 |
|
$html = $doc->saveHTML($doc->documentElement->parentNode); |
|
116
|
|
|
// remove XML-Preamble, newlines and doctype |
|
117
|
3 |
|
$html = preg_replace('/(<\?xml[^>]+\?>|\r?\n|<!DOCTYPE.+?>)/imS', '', $html); |
|
118
|
3 |
|
$html = str_replace(['<html>', '</html>', '<body>', '</body>'], ['', '', '', ''], $html); |
|
119
|
|
|
|
|
120
|
3 |
|
return $html; |
|
121
|
|
|
} |
|
122
|
|
|
|
|
123
|
|
|
/** |
|
124
|
|
|
* Returns the cleaned indexable content from the page's HTML markup. |
|
125
|
|
|
* |
|
126
|
|
|
* The content is cleaned from HTML tags and control chars Solr could |
|
127
|
|
|
* stumble on. |
|
128
|
|
|
* |
|
129
|
|
|
* @return string Indexable, cleaned content ready for indexing. |
|
130
|
|
|
*/ |
|
131
|
46 |
|
public function getIndexableContent() |
|
132
|
|
|
{ |
|
133
|
46 |
|
$content = $this->extractContentMarkedForIndexing($this->content); |
|
134
|
|
|
|
|
135
|
|
|
// clean content |
|
136
|
46 |
|
$content = self::cleanContent($content); |
|
137
|
46 |
|
$content = html_entity_decode($content, ENT_QUOTES, 'UTF-8'); |
|
138
|
46 |
|
$content = strip_tags($content); // after entity decoding we might have tags again |
|
139
|
46 |
|
$content = trim($content); |
|
140
|
|
|
|
|
141
|
46 |
|
return $content; |
|
142
|
|
|
} |
|
143
|
|
|
|
|
144
|
|
|
/** |
|
145
|
|
|
* Retrieves the page's title by checking the indexedDocTitle, altPageTitle, |
|
146
|
|
|
* and regular page title - in that order. |
|
147
|
|
|
* |
|
148
|
|
|
* @return string the page's title |
|
149
|
|
|
*/ |
|
150
|
45 |
|
public function getPageTitle() |
|
151
|
|
|
{ |
|
152
|
45 |
|
$page = $GLOBALS['TSFE']; |
|
153
|
|
|
|
|
154
|
45 |
|
if ($page->indexedDocTitle) { |
|
155
|
38 |
|
$pageTitle = $page->indexedDocTitle; |
|
156
|
45 |
|
} elseif ($page->altPageTitle) { |
|
157
|
|
|
$pageTitle = $page->altPageTitle; |
|
158
|
|
|
} else { |
|
159
|
7 |
|
$pageTitle = $page->page['title']; |
|
160
|
|
|
} |
|
161
|
|
|
|
|
162
|
45 |
|
return $pageTitle; |
|
163
|
|
|
} |
|
164
|
|
|
|
|
165
|
|
|
/** |
|
166
|
|
|
* Retrieves the page's body |
|
167
|
|
|
* |
|
168
|
|
|
* @return string the page's body |
|
169
|
|
|
*/ |
|
170
|
|
|
public function getPageBody() |
|
171
|
|
|
{ |
|
172
|
|
|
$pageContent = $this->content; |
|
173
|
|
|
|
|
174
|
|
|
return stristr($pageContent, '<body'); |
|
175
|
|
|
} |
|
176
|
|
|
} |
|
177
|
|
|
|
TYPO3-Solr /
ext-solr
