|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* This file is part of PHP-Typography. |
|
4
|
|
|
* |
|
5
|
|
|
* Copyright 2017-2019 Peter Putzer. |
|
6
|
|
|
* |
|
7
|
|
|
* This program is free software; you can redistribute it and/or modify |
|
8
|
|
|
* it under the terms of the GNU General Public License as published by |
|
9
|
|
|
* the Free Software Foundation; either version 2 of the License, or |
|
10
|
|
|
* (at your option) any later version. |
|
11
|
|
|
* |
|
12
|
|
|
* This program is distributed in the hope that it will be useful, |
|
13
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
14
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
15
|
|
|
* GNU General Public License for more details. |
|
16
|
|
|
* |
|
17
|
|
|
* You should have received a copy of the GNU General Public License along |
|
18
|
|
|
* with this program; if not, write to the Free Software Foundation, Inc., |
|
19
|
|
|
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
|
20
|
|
|
* |
|
21
|
|
|
* *** |
|
22
|
|
|
* |
|
23
|
|
|
* @package mundschenk-at/php-typography |
|
24
|
|
|
* @license http://www.gnu.org/licenses/gpl-2.0.html |
|
25
|
|
|
*/ |
|
26
|
|
|
|
|
27
|
|
|
namespace PHP_Typography\Text_Parser; |
|
28
|
|
|
|
|
29
|
|
|
/** |
|
30
|
|
|
* Tokenized text. |
|
31
|
|
|
* |
|
32
|
|
|
* Multibyte characters are assumed to be encoded as UTF-8. |
|
33
|
|
|
* |
|
34
|
|
|
* @since 5.0.0 |
|
35
|
|
|
* |
|
36
|
|
|
* @author Peter Putzer <[email protected]> |
|
37
|
|
|
* |
|
38
|
|
|
* @property-read string $value The token value. |
|
39
|
|
|
* @property-read int $type The token type. Can be any of the following constants: |
|
40
|
|
|
* - Token::SPACE |
|
41
|
|
|
* - Token::PUNCTUATION |
|
42
|
|
|
* - Token::WORD |
|
43
|
|
|
* - Token::OTHER |
|
44
|
|
|
* @property-read bool $mutable Wether the properties of the object can be modified. |
|
45
|
|
|
*/ |
|
46
|
|
|
final class Token { |
|
47
|
|
|
const SPACE = 1; |
|
48
|
|
|
const PUNCTUATION = 2; |
|
49
|
|
|
const WORD = 3; |
|
50
|
|
|
const OTHER = 4; |
|
51
|
|
|
|
|
52
|
|
|
/** |
|
53
|
|
|
* The token type. Can be any of the following constants: |
|
54
|
|
|
* - Token::SPACE |
|
55
|
|
|
* - Token::PUNCTUATION |
|
56
|
|
|
* - Token::WORD |
|
57
|
|
|
* - Token::OTHER |
|
58
|
|
|
* |
|
59
|
|
|
* @var int |
|
60
|
|
|
*/ |
|
61
|
|
|
private $type; |
|
62
|
|
|
|
|
63
|
|
|
/** |
|
64
|
|
|
* The token value. |
|
65
|
|
|
* |
|
66
|
|
|
* @var string |
|
67
|
|
|
*/ |
|
68
|
|
|
private $value; |
|
69
|
|
|
|
|
70
|
|
|
/** |
|
71
|
|
|
* Ensure that properties can only be set once via the constructor. |
|
72
|
|
|
* |
|
73
|
|
|
* @var boolean |
|
74
|
|
|
*/ |
|
75
|
|
|
private $mutable = true; |
|
76
|
|
|
|
|
77
|
|
|
/** |
|
78
|
|
|
* Creates a new token. |
|
79
|
|
|
* |
|
80
|
|
|
* @param string $value The token value. |
|
81
|
|
|
* @param int $type Optional. Default Token::WORD. |
|
82
|
|
|
* |
|
83
|
|
|
* @throws \BadMethodCallException If the constructor is called twice. |
|
84
|
|
|
* @throws \UnexpectedValueException If the type attribute is outside the allowed range. |
|
85
|
|
|
*/ |
|
86
|
23 |
|
public function __construct( $value, $type = self::WORD ) { |
|
87
|
23 |
|
if ( false === $this->mutable ) { |
|
88
|
4 |
|
throw new \BadMethodCallException( 'Constructor called twice.' ); |
|
89
|
|
|
} |
|
90
|
|
|
|
|
91
|
|
|
switch ( $type ) { |
|
92
|
23 |
|
case self::SPACE: |
|
93
|
21 |
|
case self::PUNCTUATION: |
|
94
|
18 |
|
case self::WORD: |
|
95
|
3 |
|
case self::OTHER: |
|
96
|
20 |
|
$this->type = $type; |
|
|
|
|
|
|
97
|
20 |
|
break; |
|
98
|
|
|
|
|
99
|
|
|
default: |
|
100
|
3 |
|
throw new \UnexpectedValueException( "Invalid type $type." ); |
|
101
|
|
|
} |
|
102
|
|
|
|
|
103
|
20 |
|
if ( ! \is_string( $value ) ) { |
|
|
|
|
|
|
104
|
1 |
|
throw new \UnexpectedValueException( 'Value has to be a string.' ); |
|
105
|
|
|
} else { |
|
106
|
19 |
|
$this->value = $value; |
|
|
|
|
|
|
107
|
|
|
} |
|
108
|
|
|
|
|
109
|
19 |
|
$this->mutable = false; |
|
|
|
|
|
|
110
|
19 |
|
} |
|
111
|
|
|
|
|
112
|
|
|
/** |
|
113
|
|
|
* Provide read-only access to properties. |
|
114
|
|
|
* |
|
115
|
|
|
* @param string $property The property name. |
|
116
|
|
|
* |
|
117
|
|
|
* @return mixed |
|
118
|
|
|
*/ |
|
119
|
7 |
|
public function __get( $property ) { |
|
120
|
7 |
|
if ( \property_exists( $this, $property ) ) { |
|
121
|
6 |
|
return $this->$property; |
|
122
|
|
|
} |
|
123
|
1 |
|
} |
|
124
|
|
|
|
|
125
|
|
|
/** |
|
126
|
|
|
* Prevent setting undeclared properties. |
|
127
|
|
|
* |
|
128
|
|
|
* @param string $id The property name. |
|
129
|
|
|
* @param mixed $val The value. |
|
130
|
|
|
* @return void |
|
131
|
|
|
* |
|
132
|
|
|
* @throws \BadMethodCallException The Token class is immutable. |
|
133
|
|
|
*/ |
|
134
|
4 |
|
public function __set( $id, $val ) { |
|
135
|
4 |
|
throw new \BadMethodCallException( 'Object of class Text_Parser\Token is immutable.' ); |
|
136
|
|
|
} |
|
137
|
|
|
|
|
138
|
|
|
/** |
|
139
|
|
|
* Prevent un-setting of properties. |
|
140
|
|
|
* |
|
141
|
|
|
* @param string $id The property name. |
|
142
|
|
|
* @return void |
|
143
|
|
|
* |
|
144
|
|
|
* @throws \BadMethodCallException The Token class is immutable. |
|
145
|
|
|
*/ |
|
146
|
4 |
|
public function __unset( $id ) { |
|
147
|
4 |
|
throw new \BadMethodCallException( 'Object of class Text_Parser\Token is immutable.' ); |
|
148
|
|
|
} |
|
149
|
|
|
|
|
150
|
|
|
/** |
|
151
|
|
|
* Create a new token with the same type, but a different value. |
|
152
|
|
|
* If the value is unchanged, the original token is returned. |
|
153
|
|
|
* |
|
154
|
|
|
* @param string $value The value attribute. |
|
155
|
|
|
* |
|
156
|
|
|
* @return Token |
|
157
|
|
|
*/ |
|
158
|
3 |
|
public function with_value( $value ) { |
|
159
|
3 |
|
if ( $this->value === $value ) { |
|
160
|
1 |
|
return $this; |
|
161
|
|
|
} |
|
162
|
|
|
|
|
163
|
2 |
|
$cloned_token = clone $this; |
|
164
|
2 |
|
$cloned_token->value = $value; |
|
|
|
|
|
|
165
|
|
|
|
|
166
|
2 |
|
return $cloned_token; |
|
167
|
|
|
} |
|
168
|
|
|
|
|
169
|
|
|
} |
|
170
|
|
|
|
mundschenk-at /
php-typography
Loading history...