|
1
|
|
|
<?php declare(strict_types=1); |
|
2
|
|
|
/* |
|
3
|
|
|
* This file is part of the feed-io package. |
|
4
|
|
|
* |
|
5
|
|
|
* (c) Alexandre Debril <[email protected]> |
|
6
|
|
|
* |
|
7
|
|
|
* For the full copyright and license information, please view the LICENSE |
|
8
|
|
|
* file that was distributed with this source code. |
|
9
|
|
|
*/ |
|
10
|
|
|
|
|
11
|
|
|
namespace FeedIo; |
|
12
|
|
|
|
|
13
|
|
|
use FeedIo\ParserAbstract; |
|
14
|
|
|
use FeedIo\Adapter\ClientInterface; |
|
15
|
|
|
use FeedIo\Adapter\ResponseInterface; |
|
16
|
|
|
use FeedIo\Reader\Document; |
|
17
|
|
|
use FeedIo\Reader\ReadErrorException; |
|
18
|
|
|
use FeedIo\Reader\Result; |
|
19
|
|
|
use FeedIo\Reader\NoAccurateParserException; |
|
20
|
|
|
use Psr\Log\LoggerInterface; |
|
21
|
|
|
|
|
22
|
|
|
/** |
|
23
|
|
|
* Consumes feeds and return corresponding Result instances |
|
24
|
|
|
* |
|
25
|
|
|
* Depends on : |
|
26
|
|
|
* - FeedIo\Adapter\ClientInterface |
|
27
|
|
|
* - Psr\Log\LoggerInterface |
|
28
|
|
|
* |
|
29
|
|
|
* A Reader instance MUST have at least one parser added with the addParser() method to read feeds |
|
30
|
|
|
* It will throw a NoAccurateParserException if it cannot find a suitable parser for the feed. |
|
31
|
|
|
*/ |
|
32
|
|
|
class Reader |
|
33
|
|
|
{ |
|
34
|
|
|
/** |
|
35
|
|
|
* @var \FeedIo\Adapter\ClientInterface; |
|
36
|
|
|
*/ |
|
37
|
|
|
protected $client; |
|
38
|
|
|
|
|
39
|
|
|
/** |
|
40
|
|
|
* @var \Psr\Log\LoggerInterface |
|
41
|
|
|
*/ |
|
42
|
|
|
protected $logger; |
|
43
|
|
|
|
|
44
|
|
|
/** |
|
45
|
|
|
* @var array |
|
46
|
|
|
*/ |
|
47
|
|
|
protected $parsers = array(); |
|
48
|
|
|
|
|
49
|
|
|
/** |
|
50
|
|
|
* @param ClientInterface $client |
|
51
|
|
|
* @param LoggerInterface $logger |
|
52
|
|
|
*/ |
|
53
|
20 |
|
public function __construct(ClientInterface $client, LoggerInterface $logger) |
|
54
|
|
|
{ |
|
55
|
20 |
|
$this->client = $client; |
|
56
|
20 |
|
$this->logger = $logger; |
|
57
|
20 |
|
} |
|
58
|
|
|
|
|
59
|
|
|
/** |
|
60
|
|
|
* @return ClientInterface |
|
61
|
|
|
*/ |
|
62
|
|
|
public function getClient(): ClientInterface |
|
63
|
|
|
{ |
|
64
|
|
|
return $this->client; |
|
65
|
|
|
} |
|
66
|
|
|
|
|
67
|
|
|
/** |
|
68
|
|
|
* @param ParserAbstract $parser |
|
69
|
|
|
* @return Reader |
|
70
|
|
|
*/ |
|
71
|
17 |
|
public function addParser(ParserAbstract $parser) : Reader |
|
72
|
|
|
{ |
|
73
|
17 |
|
$this->logger->debug("new parser added : ".get_class($parser->getStandard())); |
|
74
|
17 |
|
$this->parsers[] = $parser; |
|
75
|
|
|
|
|
76
|
17 |
|
return $this; |
|
77
|
|
|
} |
|
78
|
|
|
|
|
79
|
|
|
/** |
|
80
|
|
|
* adds a filter to every parsers |
|
81
|
|
|
* |
|
82
|
|
|
* @param \FeedIo\FilterInterface $filter |
|
83
|
|
|
* @return Reader |
|
84
|
|
|
*/ |
|
85
|
2 |
|
public function addFilter(FilterInterface $filter) : Reader |
|
86
|
|
|
{ |
|
87
|
2 |
|
foreach ($this->parsers as $parser) { |
|
88
|
2 |
|
$parser->addFilter($filter); |
|
89
|
|
|
} |
|
90
|
|
|
|
|
91
|
2 |
|
return $this; |
|
92
|
|
|
} |
|
93
|
|
|
|
|
94
|
|
|
/** |
|
95
|
|
|
* Reset filters on every parsers |
|
96
|
|
|
* @return Reader |
|
97
|
|
|
*/ |
|
98
|
2 |
|
public function resetFilters() : Reader |
|
99
|
|
|
{ |
|
100
|
2 |
|
foreach ($this->parsers as $parser) { |
|
101
|
2 |
|
$parser->resetFilters(); |
|
102
|
|
|
} |
|
103
|
|
|
|
|
104
|
2 |
|
return $this; |
|
105
|
|
|
} |
|
106
|
|
|
|
|
107
|
|
|
/** |
|
108
|
|
|
* @param string $url |
|
109
|
|
|
* @param FeedInterface $feed |
|
110
|
|
|
* @param \DateTime $modifiedSince |
|
111
|
|
|
* @return \FeedIo\Reader\Result |
|
112
|
|
|
* @throws ReadErrorException |
|
113
|
|
|
*/ |
|
114
|
4 |
|
public function read(string $url, FeedInterface $feed, \DateTime $modifiedSince = null) : Result |
|
115
|
|
|
{ |
|
116
|
4 |
|
$this->logger->debug("start reading {$url}"); |
|
117
|
4 |
|
if (is_null($modifiedSince)) { |
|
118
|
2 |
|
$this->logger->notice("no 'modifiedSince' parameter given, setting it to 01/01/1970"); |
|
119
|
2 |
|
$modifiedSince = new \DateTime('1800-01-01'); |
|
120
|
|
|
} |
|
121
|
|
|
|
|
122
|
|
|
try { |
|
123
|
4 |
|
$this->logger->info("hitting {$url}"); |
|
124
|
4 |
|
$response = $this->client->getResponse($url, $modifiedSince); |
|
125
|
3 |
|
$document = $this->handleResponse($response, $feed); |
|
126
|
|
|
|
|
127
|
3 |
|
return new Result($document, $feed, $modifiedSince, $response, $url); |
|
128
|
1 |
|
} catch (\Exception $e) { |
|
129
|
1 |
|
$this->logger->warning("{$url} read error : {$e->getMessage()}"); |
|
130
|
1 |
|
throw new ReadErrorException($e->getMessage(), $e->getCode(), $e); |
|
131
|
|
|
} |
|
132
|
|
|
} |
|
133
|
|
|
|
|
134
|
|
|
/** |
|
135
|
|
|
* @param ResponseInterface $response |
|
136
|
|
|
* @param FeedInterface $feed |
|
137
|
|
|
* @return Document |
|
138
|
|
|
*/ |
|
139
|
5 |
|
public function handleResponse(ResponseInterface $response, FeedInterface $feed) : Document |
|
140
|
|
|
{ |
|
141
|
5 |
|
$this->logger->debug("response ok, now turning it into a document"); |
|
142
|
5 |
|
$document = new Document($response->getBody()); |
|
143
|
|
|
|
|
144
|
5 |
|
if ($response->isModified()) { |
|
145
|
4 |
|
$this->logger->info("the stream is modified, parsing it"); |
|
146
|
4 |
|
$this->parseDocument($document, $feed); |
|
147
|
|
|
} |
|
148
|
|
|
|
|
149
|
5 |
|
return $document; |
|
150
|
|
|
} |
|
151
|
|
|
|
|
152
|
|
|
/** |
|
153
|
|
|
* @param Document $document |
|
154
|
|
|
* @param FeedInterface $feed |
|
155
|
|
|
* @return FeedInterface |
|
156
|
|
|
* @throws Parser\UnsupportedFormatException |
|
157
|
|
|
* @throws Reader\NoAccurateParserException |
|
158
|
|
|
*/ |
|
159
|
5 |
|
public function parseDocument(Document $document, FeedInterface $feed) : FeedInterface |
|
160
|
|
|
{ |
|
161
|
5 |
|
$parser = $this->getAccurateParser($document); |
|
162
|
5 |
|
$this->logger->debug("accurate parser : ".get_class($parser)); |
|
163
|
|
|
|
|
164
|
5 |
|
return $parser->parse($document, $feed); |
|
165
|
|
|
} |
|
166
|
|
|
|
|
167
|
|
|
/** |
|
168
|
|
|
* @param Document $document |
|
169
|
|
|
* @return ParserAbstract |
|
170
|
|
|
* @throws Reader\NoAccurateParserException |
|
171
|
|
|
*/ |
|
172
|
7 |
|
public function getAccurateParser(Document $document) : ParserAbstract |
|
173
|
|
|
{ |
|
174
|
7 |
|
foreach ($this->parsers as $parser) { |
|
175
|
6 |
|
if ($parser->getStandard()->canHandle($document)) { |
|
176
|
6 |
|
return $parser; |
|
177
|
|
|
} |
|
178
|
|
|
} |
|
179
|
|
|
|
|
180
|
1 |
|
$message = 'No parser can handle this stream'; |
|
181
|
1 |
|
$this->logger->error($message); |
|
182
|
1 |
|
throw new NoAccurateParserException($message); |
|
183
|
|
|
} |
|
184
|
|
|
} |
|
185
|
|
|
|