|
1
|
|
|
<?php declare(strict_types = 1); |
|
2
|
|
|
|
|
3
|
|
|
namespace Apicart\FQL\Tokenizer; |
|
4
|
|
|
|
|
5
|
|
|
use Apicart\FQL\Token\Token\GroupBegin; |
|
6
|
|
|
use Apicart\FQL\Token\Token\Phrase; |
|
7
|
|
|
use Apicart\FQL\Token\Token\Word; |
|
8
|
|
|
use Apicart\FQL\Value\Token; |
|
9
|
|
|
use RuntimeException; |
|
10
|
|
|
|
|
11
|
|
|
final class Text extends AbstractTokenExtractor |
|
12
|
|
|
{ |
|
13
|
|
|
/** |
|
14
|
|
|
* Map of regex expressions to Token types. |
|
15
|
|
|
* |
|
16
|
|
|
* @var array |
|
17
|
|
|
*/ |
|
18
|
|
|
private static $expressionTypeMap = [ |
|
19
|
|
|
'/(?<lexeme>[\s]+)/Au' => Tokenizer::TOKEN_WHITESPACE, |
|
20
|
|
|
'/(?<lexeme>\+)/Au' => Tokenizer::TOKEN_MANDATORY, |
|
21
|
|
|
'/(?<lexeme>-)/Au' => Tokenizer::TOKEN_PROHIBITED, |
|
22
|
|
|
'/(?<lexeme>!)/Au' => Tokenizer::TOKEN_LOGICAL_NOT_2, |
|
23
|
|
|
'/(?<lexeme>\))/Au' => Tokenizer::TOKEN_GROUP_END, |
|
24
|
|
|
'/(?<lexeme>NOT)(?:[\s"()+\-!]|$)/Au' => Tokenizer::TOKEN_LOGICAL_NOT, |
|
25
|
|
|
'/(?<lexeme>(?:AND|&&))(?:[\s"()+\-!]|$)/Au' => Tokenizer::TOKEN_LOGICAL_AND, |
|
26
|
|
|
'/(?<lexeme>(?:OR|\|\|))(?:[\s"()+\-!]|$)/Au' => Tokenizer::TOKEN_LOGICAL_OR, |
|
27
|
|
|
'/(?<lexeme>\()/Au' => Tokenizer::TOKEN_GROUP_BEGIN, |
|
28
|
|
|
'/(?<lexeme>(?<quote>(?<!\\\\)["])(?<phrase>.*?)(?:(?<!\\\\)(?P=quote)))/Aus' => Tokenizer::TOKEN_TERM, |
|
29
|
|
|
'/(?<lexeme>(?<word>(?:\\\\\\\\|\\\\ |\\\\\(|\\\\\)|\\\\"|[^"()\s])+?))(?:(?<!\\\\)["]|\(|\)|$|\s)/Au' |
|
30
|
|
|
=> Tokenizer::TOKEN_TERM, |
|
31
|
|
|
]; |
|
32
|
|
|
|
|
33
|
|
|
|
|
34
|
186 |
|
protected function getExpressionTypeMap(): array |
|
35
|
|
|
{ |
|
36
|
186 |
|
return self::$expressionTypeMap; |
|
37
|
|
|
} |
|
38
|
|
|
|
|
39
|
|
|
|
|
40
|
143 |
|
protected function createTermToken(int $position, array $data): Token |
|
41
|
|
|
{ |
|
42
|
143 |
|
$lexeme = $data['lexeme']; |
|
43
|
|
|
switch (true) { |
|
44
|
143 |
|
case isset($data['word']): |
|
45
|
135 |
|
return new Word( |
|
46
|
135 |
|
$lexeme, |
|
47
|
135 |
|
$position, |
|
48
|
135 |
|
'', |
|
49
|
|
|
// un-backslash special chars |
|
50
|
135 |
|
preg_replace('/(?:\\\\(\\\\|(["+\-!() ])))/', '$1', $data['word']) |
|
51
|
|
|
); |
|
52
|
11 |
|
case isset($data['phrase']): |
|
53
|
10 |
|
$quote = $data['quote']; |
|
54
|
10 |
|
return new Phrase( |
|
55
|
10 |
|
$lexeme, |
|
56
|
10 |
|
$position, |
|
57
|
10 |
|
'', |
|
58
|
10 |
|
$quote, |
|
59
|
|
|
// un-backslash quote |
|
60
|
10 |
|
preg_replace('/(?:\\\\([' . $quote . ']))/', '$1', $data['phrase']) |
|
61
|
|
|
); |
|
62
|
|
|
} |
|
63
|
1 |
|
throw new RuntimeException('Could not extract term token from the given data'); |
|
64
|
|
|
} |
|
65
|
|
|
|
|
66
|
|
|
|
|
67
|
14 |
|
protected function createGroupBeginToken(int $position, array $data): GroupBegin |
|
68
|
|
|
{ |
|
69
|
14 |
|
return new GroupBegin($data['lexeme'], $position, $data['lexeme'], ''); |
|
70
|
|
|
} |
|
71
|
|
|
|
|
72
|
|
|
} |
|
73
|
|
|
|
apicart /
fql
