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
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
<?php
/*
* This file is part of Mustache.php.
*
* (c) 2010-2017 Justin Hileman
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
/**
* Mustache Parser class.
*
* This class is responsible for turning a set of Mustache tokens into a parse tree.
*/
class Mustache_Parser
{
private $lineNum;
private $lineTokens;
private $pragmas;
private $defaultPragmas = array();
private $pragmaFilters;
private $pragmaBlocks;
/**
* Process an array of Mustache tokens and convert them into a parse tree.
*
* @param array $tokens Set of Mustache tokens
*
* @return array Mustache token parse tree
*/
public function parse(array $tokens = array())
{
$this->lineNum = -1;
$this->lineTokens = 0;
$this->pragmas = $this->defaultPragmas;
$this->pragmaFilters = isset($this->pragmas[Mustache_Engine::PRAGMA_FILTERS]);
$this->pragmaBlocks = isset($this->pragmas[Mustache_Engine::PRAGMA_BLOCKS]);
return $this->buildTree($tokens);
}
/**
* Enable pragmas across all templates, regardless of the presence of pragma
* tags in the individual templates.
*
* @internal Users should set global pragmas in Mustache_Engine, not here :)
*
* @param string[] $pragmas
*/
public function setPragmas(array $pragmas)
{
$this->pragmas = array();
foreach ($pragmas as $pragma) {
$this->enablePragma($pragma);
}
$this->defaultPragmas = $this->pragmas;
}
/**
* Helper method for recursively building a parse tree.
*
* @throws Mustache_Exception_SyntaxException when nesting errors or mismatched section tags are encountered
*
* @param array &$tokens Set of Mustache tokens
* @param array $parent Parent token (default: null)
*
* @return array Mustache Token parse tree
*/
private function buildTree(array &$tokens, array $parent = null)
{
$nodes = array();
while (!empty($tokens)) {
$token = array_shift($tokens);
if ($token[Mustache_Tokenizer::LINE] === $this->lineNum) {
$this->lineTokens++;
} else {
$this->lineNum = $token[Mustache_Tokenizer::LINE];
$this->lineTokens = 0;
}
if ($this->pragmaFilters && isset($token[Mustache_Tokenizer::NAME])) {
list($name, $filters) = $this->getNameAndFilters($token[Mustache_Tokenizer::NAME]);
if (!empty($filters)) {
$token[Mustache_Tokenizer::NAME] = $name;
$token[Mustache_Tokenizer::FILTERS] = $filters;
}
}
switch ($token[Mustache_Tokenizer::TYPE]) {
case Mustache_Tokenizer::T_DELIM_CHANGE:
$this->checkIfTokenIsAllowedInParent($parent, $token);
$this->clearStandaloneLines($nodes, $tokens);
break;
case Mustache_Tokenizer::T_SECTION:
case Mustache_Tokenizer::T_INVERTED:
$this->checkIfTokenIsAllowedInParent($parent, $token);
$this->clearStandaloneLines($nodes, $tokens);
$nodes[] = $this->buildTree($tokens, $token);
break;
case Mustache_Tokenizer::T_END_SECTION:
if (!isset($parent)) {
$msg = sprintf(
'Unexpected closing tag: /%s on line %d',
$token[Mustache_Tokenizer::NAME],
$token[Mustache_Tokenizer::LINE]
);
throw new Mustache_Exception_SyntaxException($msg, $token);
}
if ($token[Mustache_Tokenizer::NAME] !== $parent[Mustache_Tokenizer::NAME]) {
$msg = sprintf(
'Nesting error: %s (on line %d) vs. %s (on line %d)',
$parent[Mustache_Tokenizer::NAME],
$parent[Mustache_Tokenizer::LINE],
$token[Mustache_Tokenizer::NAME],
$token[Mustache_Tokenizer::LINE]
);
throw new Mustache_Exception_SyntaxException($msg, $token);
}
$this->clearStandaloneLines($nodes, $tokens);
$parent[Mustache_Tokenizer::END] = $token[Mustache_Tokenizer::INDEX];
$parent[Mustache_Tokenizer::NODES] = $nodes;
return $parent;
case Mustache_Tokenizer::T_PARTIAL:
$this->checkIfTokenIsAllowedInParent($parent, $token);
//store the whitespace prefix for laters!
if ($indent = $this->clearStandaloneLines($nodes, $tokens)) {
$token[Mustache_Tokenizer::INDENT] = $indent[Mustache_Tokenizer::VALUE];
}
$nodes[] = $token;
break;
case Mustache_Tokenizer::T_PARENT:
$this->checkIfTokenIsAllowedInParent($parent, $token);
$nodes[] = $this->buildTree($tokens, $token);
break;
case Mustache_Tokenizer::T_BLOCK_VAR:
if ($this->pragmaBlocks) {
// BLOCKS pragma is enabled, let's do this!
if (isset($parent) && $parent[Mustache_Tokenizer::TYPE] === Mustache_Tokenizer::T_PARENT) {
$token[Mustache_Tokenizer::TYPE] = Mustache_Tokenizer::T_BLOCK_ARG;
}
$this->clearStandaloneLines($nodes, $tokens);
$nodes[] = $this->buildTree($tokens, $token);
} else {
// pretend this was just a normal "escaped" token...
$token[Mustache_Tokenizer::TYPE] = Mustache_Tokenizer::T_ESCAPED;
// TODO: figure out how to figure out if there was a space after this dollar:
$token[Mustache_Tokenizer::NAME] = '$' . $token[Mustache_Tokenizer::NAME];
$nodes[] = $token;
}
break;
case Mustache_Tokenizer::T_PRAGMA:
$this->enablePragma($token[Mustache_Tokenizer::NAME]);
// no break
case Mustache_Tokenizer::T_COMMENT:
$this->clearStandaloneLines($nodes, $tokens);
$nodes[] = $token;
break;
default:
$nodes[] = $token;
break;
}
}
if (isset($parent)) {
$msg = sprintf(
'Missing closing tag: %s opened on line %d',
$parent[Mustache_Tokenizer::NAME],
$parent[Mustache_Tokenizer::LINE]
);
throw new Mustache_Exception_SyntaxException($msg, $parent);
}
return $nodes;
}
/**
* Clear standalone line tokens.
*
* Returns a whitespace token for indenting partials, if applicable.
*
* @param array $nodes Parsed nodes
* @param array $tokens Tokens to be parsed
*
* @return array|null Resulting indent token, if any
*/
private function clearStandaloneLines(array &$nodes, array &$tokens)
{
if ($this->lineTokens > 1) {
// this is the third or later node on this line, so it can't be standalone
return;
}
$prev = null;
if ($this->lineTokens === 1) {
// this is the second node on this line, so it can't be standalone
// unless the previous node is whitespace.
if ($prev = end($nodes)) {
if (!$this->tokenIsWhitespace($prev)) {
return;
}
}
}
if ($next = reset($tokens)) {
// If we're on a new line, bail.
if ($next[Mustache_Tokenizer::LINE] !== $this->lineNum) {
return;
}
// If the next token isn't whitespace, bail.
if (!$this->tokenIsWhitespace($next)) {
return;
}
if (count($tokens) !== 1) {
// Unless it's the last token in the template, the next token
// must end in newline for this to be standalone.
if (substr($next[Mustache_Tokenizer::VALUE], -1) !== "\n") {
return;
}
}
// Discard the whitespace suffix
array_shift($tokens);
}
if ($prev) {
// Return the whitespace prefix, if any
return array_pop($nodes);
}
}
/**
* Check whether token is a whitespace token.
*
* True if token type is T_TEXT and value is all whitespace characters.
*
* @param array $token
*
* @return bool True if token is a whitespace token
*/
private function tokenIsWhitespace(array $token)
{
if ($token[Mustache_Tokenizer::TYPE] === Mustache_Tokenizer::T_TEXT) {
return preg_match('/^\s*$/', $token[Mustache_Tokenizer::VALUE]);
}
return false;
}
/**
* Check whether a token is allowed inside a parent tag.
*
* @throws Mustache_Exception_SyntaxException if an invalid token is found inside a parent tag
*
* @param array|null $parent
* @param array $token
*/
private function checkIfTokenIsAllowedInParent($parent, array $token)
{
if (isset($parent) && $parent[Mustache_Tokenizer::TYPE] === Mustache_Tokenizer::T_PARENT) {
throw new Mustache_Exception_SyntaxException('Illegal content in < parent tag', $token);
}
}
/**
* Split a tag name into name and filters.
*
* @param string $name
*
* @return array [Tag name, Array of filters]
*/
private function getNameAndFilters($name)
{
$filters = array_map('trim', explode('|', $name));
$name = array_shift($filters);
return array($name, $filters);
}
/**
* Enable a pragma.
*
* @param string $name
*/
private function enablePragma($name)
{
$this->pragmas[$name] = true;
switch ($name) {
case Mustache_Engine::PRAGMA_BLOCKS:
$this->pragmaBlocks = true;
break;
case Mustache_Engine::PRAGMA_FILTERS:
$this->pragmaFilters = true;
break;
}
}
}