These results are based on our legacy PHP analysis, consider migrating to our new PHP analysis engine instead. Learn more
1 | <?php |
||
2 | /** |
||
3 | * @copyright Copyright (c) 2014 Carsten Brandt |
||
4 | * @license https://github.com/cebe/markdown/blob/master/LICENSE |
||
5 | * @link https://github.com/cebe/markdown#readme |
||
6 | */ |
||
7 | |||
8 | namespace cebe\markdown\latex; |
||
9 | |||
10 | use cebe\markdown\block\CodeTrait; |
||
11 | use cebe\markdown\block\HeadlineTrait; |
||
12 | use cebe\markdown\block\ListTrait; |
||
13 | use cebe\markdown\block\QuoteTrait; |
||
14 | use cebe\markdown\block\RuleTrait; |
||
15 | |||
16 | use cebe\markdown\inline\CodeTrait as InlineCodeTrait; |
||
17 | use cebe\markdown\inline\EmphStrongTrait; |
||
18 | use cebe\markdown\inline\LinkTrait; |
||
19 | |||
20 | use MikeVanRiel\TextToLatex; |
||
21 | |||
22 | /** |
||
23 | * Markdown parser for the [initial markdown spec](http://daringfireball.net/projects/markdown/syntax). |
||
24 | * |
||
25 | * @author Carsten Brandt <[email protected]> |
||
26 | */ |
||
27 | class Markdown extends \cebe\markdown\Parser |
||
28 | { |
||
29 | // include block element parsing using traits |
||
30 | use CodeTrait; |
||
31 | use HeadlineTrait; |
||
32 | use ListTrait { |
||
33 | // Check Ul List before headline |
||
34 | identifyUl as protected identifyBUl; |
||
35 | consumeUl as protected consumeBUl; |
||
36 | } |
||
37 | use QuoteTrait; |
||
38 | use RuleTrait { |
||
39 | // Check Hr before checking lists |
||
40 | identifyHr as protected identifyAHr; |
||
41 | consumeHr as protected consumeAHr; |
||
42 | } |
||
43 | |||
44 | // include inline element parsing using traits |
||
45 | use InlineCodeTrait; |
||
46 | use EmphStrongTrait; |
||
47 | use LinkTrait; |
||
48 | |||
49 | /** |
||
50 | * @var string this string will be prefixed to all auto generated labels. |
||
51 | * This can be used to disambiguate labels when combining multiple markdown files into one document. |
||
52 | */ |
||
53 | public $labelPrefix = ''; |
||
54 | |||
55 | /** |
||
56 | * @var array these are "escapeable" characters. When using one of these prefixed with a |
||
57 | * backslash, the character will be outputted without the backslash and is not interpreted |
||
58 | * as markdown. |
||
59 | */ |
||
60 | protected $escapeCharacters = [ |
||
61 | '\\', // backslash |
||
62 | '`', // backtick |
||
63 | '*', // asterisk |
||
64 | '_', // underscore |
||
65 | '{', '}', // curly braces |
||
66 | '[', ']', // square brackets |
||
67 | '(', ')', // parentheses |
||
68 | '#', // hash mark |
||
69 | '+', // plus sign |
||
70 | '-', // minus sign (hyphen) |
||
71 | '.', // dot |
||
72 | '!', // exclamation mark |
||
73 | '<', '>', |
||
74 | ]; |
||
75 | |||
76 | |||
77 | /** |
||
78 | * @inheritDoc |
||
79 | */ |
||
80 | 23 | protected function prepare() |
|
81 | { |
||
82 | // reset references |
||
83 | 23 | $this->references = []; |
|
84 | 23 | } |
|
85 | |||
86 | /** |
||
87 | * Consume lines for a paragraph |
||
88 | * |
||
89 | * Allow headlines and code to break paragraphs |
||
90 | */ |
||
91 | 8 | protected function consumeParagraph($lines, $current) |
|
92 | { |
||
93 | // consume until newline |
||
94 | 8 | $content = []; |
|
95 | 8 | for ($i = $current, $count = count($lines); $i < $count; $i++) { |
|
96 | 8 | $line = $lines[$i]; |
|
97 | 8 | if (!empty($line) && ltrim($line) !== '' && |
|
98 | 8 | !($line[0] === "\t" || $line[0] === " " && strncmp($line, ' ', 4) === 0) && |
|
99 | 8 | !$this->identifyHeadline($line, $lines, $i)) |
|
100 | 8 | { |
|
101 | 8 | $content[] = $line; |
|
102 | 8 | } else { |
|
103 | 7 | break; |
|
104 | } |
||
105 | 8 | } |
|
106 | $block = [ |
||
107 | 8 | 'paragraph', |
|
108 | 8 | 'content' => $this->parseInline(implode("\n", $content)), |
|
109 | 8 | ]; |
|
110 | 8 | return [$block, --$i]; |
|
111 | } |
||
112 | |||
113 | |||
114 | // rendering adjusted for LaTeX output |
||
115 | |||
116 | |||
117 | /** |
||
118 | * @inheritdoc |
||
119 | */ |
||
120 | 21 | protected function renderParagraph($block) |
|
121 | { |
||
122 | 21 | return $this->renderAbsy($block['content']) . "\n\n"; |
|
123 | } |
||
124 | |||
125 | /** |
||
126 | * @inheritdoc |
||
127 | */ |
||
128 | 2 | protected function renderQuote($block) |
|
129 | { |
||
130 | 2 | return '\begin{quote}' . $this->renderAbsy($block['content']) . "\\end{quote}\n"; |
|
131 | } |
||
132 | |||
133 | /** |
||
134 | * @inheritdoc |
||
135 | */ |
||
136 | 3 | protected function renderCode($block) |
|
137 | { |
||
138 | 3 | $language = isset($block['language']) ? "\\lstset{language={$block['language']}}" : '\lstset{language={}}'; |
|
139 | |||
140 | 3 | $content = $block['content']; |
|
141 | // replace No-Break Space characters in code block, which do not render in LaTeX |
||
142 | 3 | $content = preg_replace("/[\x{00a0}\x{202f}]/u", ' ', $content); |
|
143 | |||
144 | 3 | return "$language\\begin{lstlisting}\n{$content}\n\\end{lstlisting}\n"; |
|
145 | } |
||
146 | |||
147 | /** |
||
148 | * @inheritdoc |
||
149 | */ |
||
150 | 2 | protected function renderList($block) |
|
151 | { |
||
152 | 2 | $type = ($block['list'] === 'ol') ? 'enumerate' : 'itemize'; |
|
153 | 2 | $output = "\\begin{{$type}}\n"; |
|
154 | |||
155 | 2 | foreach ($block['items'] as $item => $itemLines) { |
|
156 | 2 | $output .= '\item ' . $this->renderAbsy($itemLines). "\n"; |
|
157 | 2 | } |
|
158 | |||
159 | 2 | return "$output\\end{{$type}}\n"; |
|
160 | } |
||
161 | |||
162 | /** |
||
163 | * @inheritdoc |
||
164 | */ |
||
165 | 3 | protected function renderHeadline($block) |
|
166 | { |
||
167 | 3 | $content = $this->renderAbsy($block['content']); |
|
168 | 3 | switch($block['level']) { |
|
169 | 3 | case 1: return "\\section{{$content}}\n"; |
|
170 | 3 | case 2: return "\\subsection{{$content}}\n"; |
|
171 | 2 | case 3: return "\\subsubsection{{$content}}\n"; |
|
172 | 2 | default: return "\\paragraph{{$content}}\n"; |
|
173 | 2 | } |
|
174 | } |
||
175 | |||
176 | /** |
||
177 | * @inheritdoc |
||
178 | */ |
||
179 | 2 | protected function renderHr($block) |
|
0 ignored issues
–
show
|
|||
180 | { |
||
181 | 2 | return "\n\\noindent\\rule{\\textwidth}{0.4pt}\n"; |
|
182 | } |
||
183 | |||
184 | /** |
||
185 | * @inheritdoc |
||
186 | */ |
||
187 | 2 | protected function renderLink($block) |
|
188 | { |
||
189 | 2 | View Code Duplication | if (isset($block['refkey'])) { |
190 | if (($ref = $this->lookupReference($block['refkey'])) !== false) { |
||
191 | $block = array_merge($block, $ref); |
||
192 | } else { |
||
193 | return $block['orig']; |
||
194 | } |
||
195 | } |
||
196 | |||
197 | 2 | $url = $block['url']; |
|
198 | 2 | $text = $this->renderAbsy($block['text']); |
|
199 | 2 | if (strpos($url, '://') === false) { |
|
200 | // consider all non absolute links as relative in the document |
||
201 | // $title is ignored in this case. |
||
202 | if (isset($url[0]) && $url[0] === '#') { |
||
203 | $url = $this->labelPrefix . $url; |
||
204 | } |
||
205 | return '\hyperref['.str_replace('#', '::', $url).']{' . $text . '}'; |
||
206 | } else { |
||
207 | 2 | return $text . '\\footnote{' . (empty($block['title']) ? '' : $this->escapeLatex($block['title']) . ': ') . '\url{' . $this->escapeUrl($url) . '}}'; |
|
208 | } |
||
209 | } |
||
210 | |||
211 | /** |
||
212 | * @inheritdoc |
||
213 | */ |
||
214 | 2 | protected function renderImage($block) |
|
215 | { |
||
216 | 2 | View Code Duplication | if (isset($block['refkey'])) { |
217 | if (($ref = $this->lookupReference($block['refkey'])) !== false) { |
||
218 | $block = array_merge($block, $ref); |
||
219 | } else { |
||
220 | return $block['orig']; |
||
221 | } |
||
222 | } |
||
223 | |||
224 | // TODO create figure with caption with title |
||
225 | $replaces = [ |
||
226 | 2 | '%' => '\\%', |
|
227 | 2 | '{' => '\\%7B', |
|
228 | 2 | '}' => '\\%7D', |
|
229 | 2 | '\\' => '\\\\', |
|
230 | 2 | '#' => '\\#', |
|
231 | 2 | '$' => '\\%24', |
|
232 | 2 | ]; |
|
233 | 2 | $url = str_replace(array_keys($replaces), array_values($replaces), $block['url']); |
|
234 | 2 | return "\\noindent\\includegraphics[width=\\textwidth]{{$url}}"; |
|
235 | } |
||
236 | |||
237 | /** |
||
238 | * Parses <a name="..."></a> tags as reference labels |
||
239 | */ |
||
240 | 2 | private function parseInlineHtml($text) |
|
241 | { |
||
242 | 2 | if (strpos($text, '>') !== false) { |
|
243 | // convert a name markers to \labels |
||
244 | 2 | if (preg_match('~^<((a|span)) (name|id)="(.*?)">.*?</\1>~i', $text, $matches)) { |
|
245 | return [ |
||
246 | 2 | ['label', 'name' => str_replace('#', '::', $this->labelPrefix . $matches[4])], |
|
247 | 2 | strlen($matches[0]) |
|
248 | 2 | ]; |
|
249 | } |
||
250 | } |
||
251 | return [['text', '<'], 1]; |
||
252 | } |
||
253 | |||
254 | /** |
||
255 | * renders a reference label |
||
256 | */ |
||
257 | 2 | protected function renderLabel($block) |
|
258 | { |
||
259 | 2 | return "\\label{{$block['name']}}"; |
|
260 | } |
||
261 | |||
262 | /** |
||
263 | * @inheritdoc |
||
264 | */ |
||
265 | 2 | protected function renderEmail($block) |
|
266 | { |
||
267 | 2 | $email = $this->escapeUrl($block[1]); |
|
268 | 2 | return "\\href{mailto:{$email}}{{$email}}"; |
|
269 | } |
||
270 | |||
271 | /** |
||
272 | * @inheritdoc |
||
273 | */ |
||
274 | 2 | protected function renderUrl($block) |
|
275 | { |
||
276 | 2 | return '\url{' . $this->escapeUrl($block[1]) . '}'; |
|
277 | } |
||
278 | |||
279 | /** |
||
280 | * @inheritdoc |
||
281 | */ |
||
282 | 1 | protected function renderInlineCode($block) |
|
283 | { |
||
284 | // replace No-Break Space characters in code block, which do not render in LaTeX |
||
285 | 1 | $content = preg_replace("/[\x{00a0}\x{202f}]/u", ' ', $block[1]); |
|
286 | |||
287 | 1 | if (strpos($content, '|') !== false) { |
|
288 | 1 | return '\\lstinline`' . str_replace("\n", ' ', $content) . '`'; // TODO make this more robust against code containing backticks |
|
289 | } else { |
||
290 | return '\\lstinline|' . str_replace("\n", ' ', $content) . '|'; |
||
291 | } |
||
292 | } |
||
293 | |||
294 | /** |
||
295 | * @inheritdoc |
||
296 | */ |
||
297 | 1 | protected function renderStrong($block) |
|
298 | { |
||
299 | 1 | return '\textbf{' . $this->renderAbsy($block[1]) . '}'; |
|
300 | } |
||
301 | |||
302 | /** |
||
303 | * @inheritdoc |
||
304 | */ |
||
305 | 1 | protected function renderEmph($block) |
|
306 | { |
||
307 | 1 | return '\textit{' . $this->renderAbsy($block[1]) . '}'; |
|
308 | } |
||
309 | |||
310 | /** |
||
311 | * Parses escaped special characters. |
||
312 | * This allow a backslash to be interpreted as LaTeX |
||
313 | * @marker \ |
||
314 | */ |
||
315 | 1 | protected function parseEscape($text) |
|
316 | { |
||
317 | 1 | if (isset($text[1]) && in_array($text[1], $this->escapeCharacters)) { |
|
318 | 1 | if ($text[1] === '\\') { |
|
319 | return [['backslash'], 2]; |
||
320 | } |
||
321 | 1 | return [['text', $text[1]], 2]; |
|
322 | } |
||
323 | return [['text', $text[0]], 1]; |
||
324 | } |
||
325 | |||
326 | protected function renderBackslash() |
||
327 | { |
||
328 | return '\\'; |
||
329 | } |
||
330 | |||
331 | private $_escaper; |
||
332 | |||
333 | /** |
||
334 | * Escape special characters in URLs |
||
335 | */ |
||
336 | 4 | protected function escapeUrl($string) |
|
337 | { |
||
338 | 4 | return str_replace('%', '\\%', $this->escapeLatex($string)); |
|
339 | } |
||
340 | |||
341 | /** |
||
342 | * Escape special LaTeX characters |
||
343 | */ |
||
344 | 21 | protected function escapeLatex($string) |
|
345 | { |
||
346 | 21 | if ($this->_escaper === null) { |
|
347 | 21 | $this->_escaper = new TextToLatex(); |
|
348 | 21 | } |
|
349 | 21 | return $this->_escaper->convert($string); |
|
350 | } |
||
351 | |||
352 | /** |
||
353 | * @inheritdocs |
||
354 | * |
||
355 | * Parses a newline indicated by two spaces on the end of a markdown line. |
||
356 | */ |
||
357 | 21 | protected function renderText($text) |
|
358 | { |
||
359 | 21 | $output = str_replace(" \n", "\\\\\n", $this->escapeLatex($text[1])); |
|
360 | // support No-Break Space in LaTeX |
||
361 | 21 | $output = preg_replace("/\x{00a0}/u", '~', $output); |
|
362 | // support Narrow No-Break Space spaces in LaTeX |
||
363 | // http://unicode-table.com/en/202F/ |
||
364 | // http://tex.stackexchange.com/questions/76132/how-to-typeset-a-small-non-breaking-space |
||
365 | 21 | $output = preg_replace("/\x{202f}/u", '\nobreak\hspace{.16667em plus .08333em}', $output); |
|
366 | 21 | return $output; |
|
367 | } |
||
368 | } |
||
369 |
This check looks from parameters that have been defined for a function or method, but which are not used in the method body.