|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* Copyright (C) 2013-2020 |
|
4
|
|
|
* Piotr Olaszewski <[email protected]> |
|
5
|
|
|
* |
|
6
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy |
|
7
|
|
|
* of this software and associated documentation files (the "Software"), to deal |
|
8
|
|
|
* in the Software without restriction, including without limitation the rights |
|
9
|
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
|
10
|
|
|
* copies of the Software, and to permit persons to whom the Software is |
|
11
|
|
|
* furnished to do so, subject to the following conditions: |
|
12
|
|
|
* |
|
13
|
|
|
* The above copyright notice and this permission notice shall be included in |
|
14
|
|
|
* all copies or substantial portions of the Software. |
|
15
|
|
|
* |
|
16
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
|
17
|
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
|
18
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
|
19
|
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
|
20
|
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
|
21
|
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE |
|
22
|
|
|
* SOFTWARE. |
|
23
|
|
|
*/ |
|
24
|
|
|
namespace WSDL\Lexer; |
|
25
|
|
|
|
|
26
|
|
|
use Exception; |
|
27
|
|
|
|
|
28
|
|
|
/** |
|
29
|
|
|
* Tokenizer |
|
30
|
|
|
* |
|
31
|
|
|
* @author Piotr Olaszewski <[email protected]> |
|
32
|
|
|
*/ |
|
33
|
|
|
final class Tokenizer |
|
34
|
|
|
{ |
|
35
|
|
|
/** |
|
36
|
|
|
* @var array |
|
37
|
|
|
*/ |
|
38
|
|
|
private static $tokenMap = [ |
|
39
|
|
|
'/\s*((?:[\\\]{1,2}\w+|\w+[\\\]{1,2})(?:\w+[\\\]{0,2})+)\s*/Am' => Token::CLASS_NAME, |
|
40
|
|
|
'/\s*\w+\s*/Am' => Token::TYPE, |
|
41
|
|
|
'/\s*\$\w+\s*/Am' => Token::NAME, |
|
42
|
|
|
'/\s*\[\]\s*/Am' => Token::ARRAYS, |
|
43
|
|
|
'/\s*\{\s*/Am' => Token::OPEN_OBJECT, |
|
44
|
|
|
'/\s*\}\s*/Am' => Token::CLOSE_OBJECT |
|
45
|
|
|
]; |
|
46
|
|
|
|
|
47
|
|
|
/** |
|
48
|
|
|
* @param string $string |
|
49
|
|
|
* @return TokenObject[] |
|
50
|
|
|
*/ |
|
51
|
|
|
public function lex(string $string): array |
|
52
|
35 |
|
{ |
|
53
|
|
|
$tokens = []; |
|
54
|
35 |
|
$offset = 0; |
|
55
|
35 |
|
while (isset($string[$offset])) { |
|
56
|
35 |
|
foreach (self::$tokenMap as $regex => $token) { |
|
57
|
35 |
|
if (preg_match($regex, $string, $matches, null, $offset)) { |
|
58
|
35 |
|
$tokens[] = TokenObject::create($token, trim($matches[0])); |
|
59
|
35 |
|
$offset += strlen($matches[0]); |
|
60
|
35 |
|
continue 2; |
|
61
|
35 |
|
} |
|
62
|
|
|
} |
|
63
|
35 |
|
throw new Exception(sprintf('Unexpected character: >%s< offset >%d<', $string[$offset], $offset)); |
|
64
|
1 |
|
} |
|
65
|
|
|
$tokens[] = TokenObject::create(Token::EOF, 'eof'); |
|
66
|
34 |
|
|
|
67
|
34 |
|
return $tokens; |
|
68
|
|
|
} |
|
69
|
|
|
} |
|
70
|
|
|
|
piotrooo /
wsdl-creator
