summaryrefslogtreecommitdiffstats
path: root/Mustache/Tokenizer.php
blob: fd866e30f25a35ec5185c12b41cae43f083e64f0 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
<?php

/*
 * This file is part of Mustache.php.
 *
 * (c) 2012 Justin Hileman
 *
 * For the full copyright and license information, please view the LICENSE
 * file that was distributed with this source code.
 */

/**
 * Mustache Tokenizer class.
 *
 * This class is responsible for turning raw template source into a set of Mustache tokens.
 */
class Mustache_Tokenizer
{

    // Finite state machine states
    const IN_TEXT     = 0;
    const IN_TAG_TYPE = 1;
    const IN_TAG      = 2;

    // Token types
    const T_SECTION      = '#';
    const T_INVERTED     = '^';
    const T_END_SECTION  = '/';
    const T_COMMENT      = '!';
    const T_PARTIAL      = '>';
    const T_PARTIAL_2    = '<';
    const T_DELIM_CHANGE = '=';
    const T_ESCAPED      = '_v';
    const T_UNESCAPED    = '{';
    const T_UNESCAPED_2  = '&';
    const T_TEXT         = '_t';

    // Valid token types
    private static $tagTypes = array(
        self::T_SECTION      => true,
        self::T_INVERTED     => true,
        self::T_END_SECTION  => true,
        self::T_COMMENT      => true,
        self::T_PARTIAL      => true,
        self::T_PARTIAL_2    => true,
        self::T_DELIM_CHANGE => true,
        self::T_ESCAPED      => true,
        self::T_UNESCAPED    => true,
        self::T_UNESCAPED_2  => true,
    );

    // Interpolated tags
    private static $interpolatedTags = array(
        self::T_ESCAPED      => true,
        self::T_UNESCAPED    => true,
        self::T_UNESCAPED_2  => true,
    );

    // Token properties
    const TYPE   = 'type';
    const NAME   = 'name';
    const OTAG   = 'otag';
    const CTAG   = 'ctag';
    const INDEX  = 'index';
    const END    = 'end';
    const INDENT = 'indent';
    const NODES  = 'nodes';
    const VALUE  = 'value';

    private $state;
    private $tagType;
    private $tag;
    private $buffer;
    private $tokens;
    private $seenTag;
    private $lineStart;
    private $otag;
    private $ctag;

    /**
     * Scan and tokenize template source.
     *
     * @param string $text       Mustache template source to tokenize
     * @param string $delimiters Optionally, pass initial opening and closing delimiters (default: null)
     *
     * @return array Set of Mustache tokens
     */
    public function scan($text, $delimiters = null)
    {
        $this->reset();

        if ($delimiters = trim($delimiters)) {
            list($otag, $ctag) = explode(' ', $delimiters);
            $this->otag = $otag;
            $this->ctag = $ctag;
        }

        $len = strlen($text);
        for ($i = 0; $i < $len; $i++) {
            switch ($this->state) {
                case self::IN_TEXT:
                    if ($this->tagChange($this->otag, $text, $i)) {
                        $i--;
                        $this->flushBuffer();
                        $this->state = self::IN_TAG_TYPE;
                    } else {
                        if ($text[$i] == "\n") {
                            $this->filterLine();
                        } else {
                            $this->buffer .= $text[$i];
                        }
                    }
                    break;

                case self::IN_TAG_TYPE:

                    $i += strlen($this->otag) - 1;
                    if (isset(self::$tagTypes[$text[$i + 1]])) {
                        $tag = $text[$i + 1];
                        $this->tagType = $tag;
                    } else {
                        $tag = null;
                        $this->tagType = self::T_ESCAPED;
                    }

                    if ($this->tagType === self::T_DELIM_CHANGE) {
                        $i = $this->changeDelimiters($text, $i);
                        $this->state = self::IN_TEXT;
                    } else {
                        if ($tag !== null) {
                            $i++;
                        }
                        $this->state = self::IN_TAG;
                    }
                    $this->seenTag = $i;
                    break;

                default:
                    if ($this->tagChange($this->ctag, $text, $i)) {
                        $this->tokens[] = array(
                            self::TYPE  => $this->tagType,
                            self::NAME  => trim($this->buffer),
                            self::OTAG  => $this->otag,
                            self::CTAG  => $this->ctag,
                            self::INDEX => ($this->tagType == self::T_END_SECTION) ? $this->seenTag - strlen($this->otag) : $i + strlen($this->ctag)
                        );

                        $this->buffer = '';
                        $i += strlen($this->ctag) - 1;
                        $this->state = self::IN_TEXT;
                        if ($this->tagType == self::T_UNESCAPED) {
                            if ($this->ctag == '}}') {
                                $i++;
                            } else {
                                // Clean up `{{{ tripleStache }}}` style tokens.
                                $lastName = $this->tokens[count($this->tokens) - 1][self::NAME];
                                if (substr($lastName, -1) === '}') {
                                    $this->tokens[count($this->tokens) - 1][self::NAME] = trim(substr($lastName, 0, -1));
                                }
                            }
                        }
                    } else {
                        $this->buffer .= $text[$i];
                    }
                    break;
            }
        }

        $this->filterLine(true);

        return $this->tokens;
    }

    /**
     * Helper function to reset tokenizer internal state.
     */
    private function reset()
    {
        $this->state     = self::IN_TEXT;
        $this->tagType   = null;
        $this->tag       = null;
        $this->buffer    = '';
        $this->tokens    = array();
        $this->seenTag   = false;
        $this->lineStart = 0;
        $this->otag      = '{{';
        $this->ctag      = '}}';
    }

    /**
     * Flush the current buffer to a token.
     */
    private function flushBuffer()
    {
        if (!empty($this->buffer)) {
            $this->tokens[] = array(self::TYPE  => self::T_TEXT, self::VALUE => $this->buffer);
            $this->buffer   = '';
        }
    }

    /**
     * Test whether the current line is entirely made up of whitespace.
     *
     * @return boolean True if the current line is all whitespace
     */
    private function lineIsWhitespace()
    {
        $tokensCount = count($this->tokens);
        for ($j = $this->lineStart; $j < $tokensCount; $j++) {
            $token = $this->tokens[$j];
            if (isset(self::$tagTypes[$token[self::TYPE]])) {
                if (isset(self::$interpolatedTags[$token[self::TYPE]])) {
                    return false;
                }
            } elseif ($token[self::TYPE] == self::T_TEXT) {
                if (preg_match('/\S/', $token[self::VALUE])) {
                    return false;
                }
            }
        }

        return true;
    }

    /**
     * Filter out whitespace-only lines and store indent levels for partials.
     *
     * @param bool $noNewLine Suppress the newline? (default: false)
     */
    private function filterLine($noNewLine = false)
    {
        $this->flushBuffer();
        if ($this->seenTag && $this->lineIsWhitespace()) {
            $tokensCount = count($this->tokens);
            for ($j = $this->lineStart; $j < $tokensCount; $j++) {
                if ($this->tokens[$j][self::TYPE] == self::T_TEXT) {
                    if (isset($this->tokens[$j+1]) && $this->tokens[$j+1][self::TYPE] == self::T_PARTIAL) {
                        $this->tokens[$j+1][self::INDENT] = $this->tokens[$j][self::VALUE];
                    }

                    $this->tokens[$j] = null;
                }
            }
        } elseif (!$noNewLine) {
            $this->tokens[] = array(self::TYPE => self::T_TEXT, self::VALUE => "\n");
        }

        $this->seenTag   = false;
        $this->lineStart = count($this->tokens);
    }

    /**
     * Change the current Mustache delimiters. Set new `otag` and `ctag` values.
     *
     * @param string $text  Mustache template source
     * @param int    $index Current tokenizer index
     *
     * @return int New index value
     */
    private function changeDelimiters($text, $index)
    {
        $startIndex = strpos($text, '=', $index) + 1;
        $close      = '='.$this->ctag;
        $closeIndex = strpos($text, $close, $index);

        list($otag, $ctag) = explode(' ', trim(substr($text, $startIndex, $closeIndex - $startIndex)));
        $this->otag = $otag;
        $this->ctag = $ctag;

        return $closeIndex + strlen($close) - 1;
    }

    /**
     * Test whether it's time to change tags.
     *
     * @param string $tag   Current tag name
     * @param string $text  Mustache template source
     * @param int    $index Current tokenizer index
     *
     * @return boolean True if this is a closing section tag
     */
    private function tagChange($tag, $text, $index)
    {
        return substr($text, $index, strlen($tag)) === $tag;
    }
}