|
1
|
|
|
<?php declare(strict_types = 1); |
|
2
|
|
|
|
|
3
|
|
|
namespace Apicart\FQL\Tokenizer; |
|
4
|
|
|
|
|
5
|
|
|
use Apicart\FQL\Token\Token\Flags; |
|
6
|
|
|
use Apicart\FQL\Token\Token\Phrase; |
|
7
|
|
|
use Apicart\FQL\Token\Token\Range; |
|
8
|
|
|
use Apicart\FQL\Token\Token\Tag; |
|
9
|
|
|
use Apicart\FQL\Token\Token\User; |
|
10
|
|
|
use Apicart\FQL\Token\Token\Word; |
|
11
|
|
|
use Apicart\FQL\Value\Token; |
|
12
|
|
|
use RuntimeException; |
|
13
|
|
|
|
|
14
|
|
|
final class Full extends AbstractTokenExtractor |
|
15
|
|
|
{ |
|
16
|
|
|
|
|
17
|
|
|
/** |
|
18
|
|
|
* Map of regex expressions to Token types. |
|
19
|
|
|
* |
|
20
|
|
|
* @var array |
|
21
|
|
|
*/ |
|
22
|
|
|
private static $expressionTypeMap = [ |
|
23
|
|
|
'/(?<lexeme>[\s]+)/Au' => Tokenizer::TOKEN_WHITESPACE, |
|
24
|
|
|
'/(?<lexeme>\+)/Au' => Tokenizer::TOKEN_MANDATORY, |
|
25
|
|
|
'/(?<lexeme>-)/Au' => Tokenizer::TOKEN_PROHIBITED, |
|
26
|
|
|
'/(?<lexeme>!)/Au' => Tokenizer::TOKEN_LOGICAL_NOT_2, |
|
27
|
|
|
'/(?<lexeme>\))/Au' => Tokenizer::TOKEN_GROUP_END, |
|
28
|
|
|
'/(?<lexeme>NOT)(?:[\s"()+\-!]|$)/Au' => Tokenizer::TOKEN_LOGICAL_NOT, |
|
29
|
|
|
'/(?<lexeme>(?:AND|&&))(?:[\s"()+\-!]|$)/Au' => Tokenizer::TOKEN_LOGICAL_AND, |
|
30
|
|
|
'/(?<lexeme>(?:OR|\|\|))(?:[\s"()+\-!]|$)/Au' => Tokenizer::TOKEN_LOGICAL_OR, |
|
31
|
|
|
'/(?<lexeme>(?:(?<domain>(?:[a-zA-Z_\-.\[\]\*%][a-zA-Z0-9_\-.\[\]\*%]*|\'[^\']+\')):)?(?<delimiter>\())/Au' |
|
32
|
|
|
=> Tokenizer::TOKEN_GROUP_BEGIN, |
|
33
|
|
|
'/(?<lexeme>(?:(?<marker>(?<!\\\\)\#)(?<tag>[a-zA-Z0-9_][a-zA-Z0-9_\-.]*)))(?:[\s"()+!]|$)/Au' |
|
34
|
|
|
=> Tokenizer::TOKEN_TERM, |
|
35
|
|
|
'/(?<lexeme>(?:(?<marker>(?<!\\\\)@)(?<user>[a-zA-Z0-9_][a-zA-Z0-9_\-.]*)))(?:[\s"()+!]|$)/Au' |
|
36
|
|
|
=> Tokenizer::TOKEN_TERM, |
|
37
|
|
|
'/(?<lexeme>(?:(?<domain>(?:[a-zA-Z_\-.\[\]\*%][a-zA-Z0-9_\-.\[\]\*%]*|\'[^\']+\')):)?(?<quote>(?<!\\\\)["])' . |
|
38
|
|
|
'(?<phrase>.*?)(?:(?<!\\\\)(?P=quote))(?:(?<marker>(?<!\\\\)\#)(?<flags>[a-zA-Z0-9_][a-zA-Z0-9_\-.]*))?)/Aus' |
|
39
|
|
|
=> Tokenizer::TOKEN_TERM, |
|
40
|
|
|
'/(?<lexeme>(?:(?<domain>(?:[a-zA-Z_\-.\[\]\*%][a-zA-Z0-9_\-.\[\]\*%]*|\'[^\']+\')):)?(?<rangeStartSymbol>[\[\{])' . |
|
41
|
|
|
'(?<rangeFrom>([a-zA-Z0-9\,\._-]+|\*)|(?<quoteFrom>(?<!\\\\)["]).*?(?:(?<!\\\\)(?P=quoteFrom)))[\s]+TO[\s]+' . |
|
42
|
|
|
'(?<rangeTo>([a-zA-Z0-9\,\._-]+|\*)|(?<quoteTo>(?<!\\\\)["]).*?(?:(?<!\\\\)(?P=quoteTo)))' . |
|
43
|
|
|
'(?<rangeEndSymbol>[\]\}])(?:(?<marker>(?<!\\\\)\#)(?<flags>[a-zA-Z0-9_][a-zA-Z0-9_\-.]*))?)/Aus' |
|
44
|
|
|
=> Tokenizer::TOKEN_TERM, |
|
45
|
|
|
'/(?<lexeme>(?:(?<domain>(?:[a-zA-Z_\-.\[\]\*%][a-zA-Z0-9_\-.\[\]\*%]*|\'[^\']+\')):)?' . |
|
46
|
|
|
'(?<word>(?:\\\\\\\\|\\\\ |\\\\\(|\\\\\)|\\\\"|[^"()\s])+?))' . |
|
47
|
|
|
'(?:(?<marker>(?<!\\\\)\#)(?<flags>[a-zA-Z0-9_][a-zA-Z0-9_\-.]*))?(?:(?<!\\\\)["]|\(|\)|$|\s)/Au' |
|
48
|
320 |
|
=> Tokenizer::TOKEN_TERM, |
|
49
|
|
|
]; |
|
50
|
320 |
|
|
|
51
|
|
|
|
|
52
|
|
|
protected function getExpressionTypeMap(): array |
|
53
|
|
|
{ |
|
54
|
277 |
|
return self::$expressionTypeMap; |
|
55
|
|
|
} |
|
56
|
277 |
|
|
|
57
|
|
|
|
|
58
|
277 |
|
protected function createTermToken(int $position, array $data): Token |
|
59
|
8 |
|
{ |
|
60
|
8 |
|
$lexeme = $data['lexeme']; |
|
61
|
|
|
switch (true) { |
|
62
|
8 |
|
case isset($data['rangeStartSymbol']) && isset($data['rangeEndSymbol']): |
|
63
|
8 |
|
$startValue = str_replace(',', '.', str_replace('"', '', $data['rangeFrom'])); |
|
64
|
8 |
|
$endValue = str_replace(',', '.', str_replace('"', '', $data['rangeTo'])); |
|
65
|
8 |
|
|
|
66
|
8 |
|
return new Range( |
|
67
|
8 |
|
$lexeme, |
|
68
|
8 |
|
$position, |
|
69
|
8 |
|
$data['domain'], |
|
70
|
|
|
is_array($startValue) ? reset($startValue) : $startValue, |
|
71
|
|
|
is_array($endValue) ? reset($endValue) : $endValue, |
|
72
|
270 |
|
$this->getRangeTypeBySymbol($data['rangeStartSymbol']), |
|
73
|
241 |
|
$this->getRangeTypeBySymbol($data['rangeEndSymbol']), |
|
74
|
241 |
|
isset($data['marker'], $data['flags']) ? new Flags($data['marker'], $data['flags']) : null |
|
75
|
241 |
|
); |
|
76
|
241 |
|
|
|
77
|
|
|
case isset($data['word']): |
|
78
|
241 |
|
return new Word( |
|
79
|
|
|
$lexeme, |
|
80
|
|
|
$position, |
|
81
|
34 |
|
$data['domain'], |
|
82
|
12 |
|
// un-backslash special characters |
|
83
|
12 |
|
preg_replace('/(?:\\\\(\\\\|(["+\-!():#@ ])))/', '$1', $data['word']), |
|
84
|
12 |
|
isset($data['marker'], $data['flags']) ? new Flags($data['marker'], $data['flags']) : null |
|
85
|
12 |
|
); |
|
86
|
12 |
|
|
|
87
|
12 |
|
case isset($data['phrase']): |
|
88
|
|
|
$quote = $data['quote']; |
|
89
|
12 |
|
return new Phrase( |
|
90
|
|
|
$lexeme, |
|
91
|
|
|
$position, |
|
92
|
22 |
|
$data['domain'], |
|
93
|
10 |
|
$quote, |
|
94
|
|
|
// un-backslash quote |
|
95
|
12 |
|
preg_replace('/(?:\\\\([' . $quote . ']))/', '$1', $data['phrase']), |
|
96
|
11 |
|
isset($data['marker'], $data['flags']) ? new Flags($data['marker'], $data['flags']) : null |
|
97
|
|
|
); |
|
98
|
1 |
|
|
|
99
|
|
|
case isset($data['tag']): |
|
100
|
|
|
return new Tag($lexeme, $position, $data['marker'], $data['tag']); |
|
101
|
|
|
|
|
102
|
8 |
|
case isset($data['user']): |
|
103
|
|
|
return new User($lexeme, $position, $data['marker'], $data['user']); |
|
104
|
8 |
|
} |
|
105
|
4 |
|
throw new RuntimeException('Could not extract term token from the given data'); |
|
106
|
|
|
} |
|
107
|
7 |
|
|
|
108
|
|
|
|
|
109
|
|
|
protected function getRangeTypeBySymbol(string $symbol): string |
|
110
|
|
|
{ |
|
111
|
|
|
if (in_array($symbol, ['{', '}'], true)) { |
|
112
|
|
|
return Range::TYPE_EXCLUSIVE; |
|
113
|
|
|
} |
|
114
|
|
|
return Range::TYPE_INCLUSIVE; |
|
115
|
|
|
} |
|
116
|
|
|
|
|
117
|
|
|
} |
|
118
|
|
|
|
apicart /
fql
