Verzeichnisstruktur phpBB-3.3.15
- Veröffentlicht
- 28.08.2024
So funktioniert es
|
|
Auf das letzte Element klicken. Dies geht jeweils ein Schritt zurück |
Auf das Icon klicken, dies öffnet das Verzeichnis. Nochmal klicken schließt das Verzeichnis. |
|
|
(Beispiel Datei-Icons)
|
Auf das Icon klicken um den Quellcode anzuzeigen |
Parser.php
001 <?php
002
003 /**
004 * @package s9e\TextFormatter
005 * @copyright Copyright (c) 2010-2022 The s9e authors
006 * @license http://www.opensource.org/licenses/mit-license.php The MIT License
007 */
008 namespace s9e\TextFormatter\Plugins\FancyPants;
009
010 use s9e\TextFormatter\Plugins\ParserBase;
011
012 class Parser extends ParserBase
013 {
014 /**
015 * @var bool Whether currrent test contains a double quote character
016 */
017 protected $hasDoubleQuote;
018
019 /**
020 * @var bool Whether currrent test contains a single quote character
021 */
022 protected $hasSingleQuote;
023
024 /**
025 * @var string Text being parsed
026 */
027 protected $text;
028
029 /**
030 * {@inheritdoc}
031 */
032 public function parse($text, array $matches)
033 {
034 $this->text = $text;
035 $this->hasSingleQuote = (strpos($text, "'") !== false);
036 $this->hasDoubleQuote = (strpos($text, '"') !== false);
037
038 if (empty($this->config['disableQuotes']))
039 {
040 $this->parseSingleQuotes();
041 $this->parseSingleQuotePairs();
042 $this->parseDoubleQuotePairs();
043 }
044 if (empty($this->config['disableGuillemets']))
045 {
046 $this->parseGuillemets();
047 }
048 if (empty($this->config['disableMathSymbols']))
049 {
050 $this->parseNotEqualSign();
051 $this->parseSymbolsAfterDigits();
052 $this->parseFractions();
053 }
054 if (empty($this->config['disablePunctuation']))
055 {
056 $this->parseDashesAndEllipses();
057 }
058 if (empty($this->config['disableSymbols']))
059 {
060 $this->parseSymbolsInParentheses();
061 }
062
063 unset($this->text);
064 }
065
066 /**
067 * Add a fancy replacement tag
068 *
069 * @param integer $tagPos Position of the tag in the text
070 * @param integer $tagLen Length of text consumed by the tag
071 * @param string $chr Replacement character
072 * @param integer $prio Tag's priority
073 * @return \s9e\TextFormatter\Parser\Tag
074 */
075 protected function addTag($tagPos, $tagLen, $chr, $prio = 0)
076 {
077 $tag = $this->parser->addSelfClosingTag($this->config['tagName'], $tagPos, $tagLen, $prio);
078 $tag->setAttribute($this->config['attrName'], $chr);
079
080 return $tag;
081 }
082
083 /**
084 * Parse dashes and ellipses
085 *
086 * Does en dash –, em dash — and ellipsis …
087 *
088 * @return void
089 */
090 protected function parseDashesAndEllipses()
091 {
092 if (strpos($this->text, '...') === false && strpos($this->text, '--') === false)
093 {
094 return;
095 }
096
097 $chrs = [
098 '--' => "\xE2\x80\x93",
099 '---' => "\xE2\x80\x94",
100 '...' => "\xE2\x80\xA6"
101 ];
102 $regexp = '/---?|\\.\\.\\./S';
103 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
104 foreach ($matches[0] as $m)
105 {
106 $this->addTag($m[1], strlen($m[0]), $chrs[$m[0]]);
107 }
108 }
109
110 /**
111 * Parse pairs of double quotes
112 *
113 * Does quote pairs “” -- must be done separately to handle nesting
114 *
115 * @return void
116 */
117 protected function parseDoubleQuotePairs()
118 {
119 if ($this->hasDoubleQuote)
120 {
121 $this->parseQuotePairs(
122 '/(?<![0-9\\pL])"[^"\\n]+"(?![0-9\\pL])/uS',
123 "\xE2\x80\x9C",
124 "\xE2\x80\x9D"
125 );
126 }
127 }
128
129 /**
130 * Parse vulgar fractions
131 *
132 * @return void
133 */
134 protected function parseFractions()
135 {
136 if (strpos($this->text, '/') === false)
137 {
138 return;
139 }
140
141 $map = [
142 '1/4' => "\xC2\xBC",
143 '1/2' => "\xC2\xBD",
144 '3/4' => "\xC2\xBE",
145 '1/7' => "\xE2\x85\x90",
146 '1/9' => "\xE2\x85\x91",
147 '1/10' => "\xE2\x85\x92",
148 '1/3' => "\xE2\x85\x93",
149 '2/3' => "\xE2\x85\x94",
150 '1/5' => "\xE2\x85\x95",
151 '2/5' => "\xE2\x85\x96",
152 '3/5' => "\xE2\x85\x97",
153 '4/5' => "\xE2\x85\x98",
154 '1/6' => "\xE2\x85\x99",
155 '5/6' => "\xE2\x85\x9A",
156 '1/8' => "\xE2\x85\x9B",
157 '3/8' => "\xE2\x85\x9C",
158 '5/8' => "\xE2\x85\x9D",
159 '7/8' => "\xE2\x85\x9E",
160 '0/3' => "\xE2\x86\x89"
161 ];
162
163 $regexp = '/\\b(?:0\\/3|1\\/(?:[2-9]|10)|2\\/[35]|3\\/[458]|4\\/5|5\\/[68]|7\\/8)\\b/S';
164 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
165 foreach ($matches[0] as $m)
166 {
167 $this->addTag($m[1], strlen($m[0]), $map[$m[0]]);
168 }
169 }
170
171 /**
172 * Parse guillemets-style quotation marks
173 *
174 * @return void
175 */
176 protected function parseGuillemets()
177 {
178 if (strpos($this->text, '<<') === false)
179 {
180 return;
181 }
182
183 $regexp = '/<<( ?)(?! )[^\\n<>]*?[^\\n <>]\\1>>(?!>)/';
184 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
185 foreach ($matches[0] as $m)
186 {
187 $left = $this->addTag($m[1], 2, "\xC2\xAB");
188 $right = $this->addTag($m[1] + strlen($m[0]) - 2, 2, "\xC2\xBB");
189
190 $left->cascadeInvalidationTo($right);
191 }
192 }
193
194 /**
195 * Parse the not equal sign
196 *
197 * Supports != and =/=
198 *
199 * @return void
200 */
201 protected function parseNotEqualSign()
202 {
203 if (strpos($this->text, '!=') === false && strpos($this->text, '=/=') === false)
204 {
205 return;
206 }
207
208 $regexp = '/\\b (?:!|=\\/)=(?= \\b)/';
209 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
210 foreach ($matches[0] as $m)
211 {
212 $this->addTag($m[1] + 1, strlen($m[0]) - 1, "\xE2\x89\xA0");
213 }
214 }
215
216 /**
217 * Parse pairs of quotes
218 *
219 * @param string $regexp Regexp used to identify quote pairs
220 * @param string $leftQuote Fancy replacement for left quote
221 * @param string $rightQuote Fancy replacement for right quote
222 * @return void
223 */
224 protected function parseQuotePairs($regexp, $leftQuote, $rightQuote)
225 {
226 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
227 foreach ($matches[0] as $m)
228 {
229 $left = $this->addTag($m[1], 1, $leftQuote);
230 $right = $this->addTag($m[1] + strlen($m[0]) - 1, 1, $rightQuote);
231
232 // Cascade left tag's invalidation to the right so that if we skip the left quote,
233 // the right quote remains untouched
234 $left->cascadeInvalidationTo($right);
235 }
236 }
237
238 /**
239 * Parse pairs of single quotes
240 *
241 * Does quote pairs ‘’ must be done separately to handle nesting
242 *
243 * @return void
244 */
245 protected function parseSingleQuotePairs()
246 {
247 if ($this->hasSingleQuote)
248 {
249 $this->parseQuotePairs(
250 "/(?<![0-9\\pL])'[^'\\n]+'(?![0-9\\pL])/uS",
251 "\xE2\x80\x98",
252 "\xE2\x80\x99"
253 );
254 }
255 }
256
257 /**
258 * Parse single quotes in general
259 *
260 * Does apostrophes ’ after a letter or at the beginning of a word or a couple of digits
261 *
262 * @return void
263 */
264 protected function parseSingleQuotes()
265 {
266 if (!$this->hasSingleQuote)
267 {
268 return;
269 }
270
271 $regexp = "/(?<=\\pL)'|(?<!\\S)'(?=\\pL|[0-9]{2})/uS";
272 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
273 foreach ($matches[0] as $m)
274 {
275 // Give this tag a worse priority than default so that quote pairs take precedence
276 $this->addTag($m[1], 1, "\xE2\x80\x99", 10);
277 }
278 }
279
280 /**
281 * Parse symbols found after digits
282 *
283 * Does symbols found after a digit:
284 * - apostrophe ’ if it's followed by an "s" as in 80's
285 * - prime ′ and double prime ″
286 * - multiply sign × if it's followed by an optional space and another digit
287 *
288 * @return void
289 */
290 protected function parseSymbolsAfterDigits()
291 {
292 if (!$this->hasSingleQuote && !$this->hasDoubleQuote && strpos($this->text, 'x') === false)
293 {
294 return;
295 }
296
297 $map = [
298 // 80's -- use an apostrophe
299 "'s" => "\xE2\x80\x99",
300 // 12' or 12" -- use a prime
301 "'" => "\xE2\x80\xB2",
302 "' " => "\xE2\x80\xB2",
303 "'x" => "\xE2\x80\xB2",
304 '"' => "\xE2\x80\xB3",
305 '" ' => "\xE2\x80\xB3",
306 '"x' => "\xE2\x80\xB3"
307 ];
308
309 $regexp = "/[0-9](?>'s|[\"']? ?x(?= ?[0-9])|[\"'])/S";
310 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
311 foreach ($matches[0] as $m)
312 {
313 // Test for a multiply sign at the end
314 if (substr($m[0], -1) === 'x')
315 {
316 $this->addTag($m[1] + strlen($m[0]) - 1, 1, "\xC3\x97");
317 }
318
319 // Test for an apostrophe/prime right after the digit
320 $str = substr($m[0], 1, 2);
321 if (isset($map[$str]))
322 {
323 $this->addTag($m[1] + 1, 1, $map[$str]);
324 }
325 }
326 }
327
328 /**
329 * Parse symbols found in parentheses such as (c)
330 *
331 * Does symbols ©, ® and ™
332 *
333 * @return void
334 */
335 protected function parseSymbolsInParentheses()
336 {
337 if (strpos($this->text, '(') === false)
338 {
339 return;
340 }
341
342 $chrs = [
343 '(c)' => "\xC2\xA9",
344 '(r)' => "\xC2\xAE",
345 '(tm)' => "\xE2\x84\xA2"
346 ];
347 $regexp = '/\\((?>c|r|tm)\\)/i';
348 preg_match_all($regexp, $this->text, $matches, PREG_OFFSET_CAPTURE);
349 foreach ($matches[0] as $m)
350 {
351 $this->addTag($m[1], strlen($m[0]), $chrs[strtr($m[0], 'CMRT', 'cmrt')]);
352 }
353 }
354 }