Builder
2 weeks ago
I18n
2 weeks ago
Migrate-ACF
2 weeks ago
Migrate-CPTUI
2 weeks ago
Migrate-Packages
2 weeks ago
Roles
2 weeks ago
Templates
2 weeks ago
Advanced-Content-Types.php
2 weeks ago
Advanced-Relationships.php
2 weeks ago
Markdown.php
2 weeks ago
Pages.php
2 weeks ago
Table-Storage.php
2 weeks ago
Markdown.php
2109 lines
| 1 | <?php |
| 2 | /** |
| 3 | * ID: markdown-syntax |
| 4 | * |
| 5 | * Name: Markdown Syntax |
| 6 | * |
| 7 | * Description: Integration with Markdown (http://michelf.com/projects/php-markdown/); Adds an option to enable Markdown syntax for Paragraph text fields. |
| 8 | * |
| 9 | * Version: 1.0 |
| 10 | * |
| 11 | * Category: Field Types |
| 12 | * |
| 13 | * @package Pods\Components |
| 14 | * @subpackage Markdown |
| 15 | */ |
| 16 | |
| 17 | if ( ! function_exists( 'Markdown' ) ) : |
| 18 | // |
| 19 | // Markdown - A text-to-HTML conversion tool for web writers |
| 20 | // |
| 21 | // PHP Markdown |
| 22 | // Copyright (c) 2004-2013 Michel Fortin |
| 23 | // <http://michelf.ca/projects/php-markdown/> |
| 24 | // |
| 25 | // Original Markdown |
| 26 | // Copyright (c) 2004-2006 John Gruber |
| 27 | // <http://daringfireball.net/projects/markdown/> |
| 28 | // |
| 29 | define( 'MARKDOWN_VERSION', '1.0.2' ); |
| 30 | // 29 Nov 2013 |
| 31 | // |
| 32 | // Global default settings: |
| 33 | // |
| 34 | // Change to ">" for HTML output |
| 35 | @define( 'MARKDOWN_EMPTY_ELEMENT_SUFFIX', ' />' ); |
| 36 | |
| 37 | // Define the width of a tab for code blocks. |
| 38 | @define( 'MARKDOWN_TAB_WIDTH', 4 ); |
| 39 | |
| 40 | // |
| 41 | // WordPress settings: |
| 42 | // |
| 43 | // Change to false to remove Markdown from posts and/or comments. |
| 44 | @define( 'MARKDOWN_WP_POSTS', true ); |
| 45 | @define( 'MARKDOWN_WP_COMMENTS', true ); |
| 46 | |
| 47 | // Standard Function Interface ### |
| 48 | @define( 'MARKDOWN_PARSER_CLASS', 'Markdown_Parser' ); |
| 49 | |
| 50 | /** |
| 51 | * @param $text |
| 52 | * |
| 53 | * @return mixed |
| 54 | */ |
| 55 | function Markdown( $text ) { |
| 56 | |
| 57 | // |
| 58 | // Initialize the parser and return the result of its transform method. |
| 59 | // |
| 60 | // Setup static parser variable. |
| 61 | static $parser; |
| 62 | if ( ! isset( $parser ) ) { |
| 63 | $parser_class = MARKDOWN_PARSER_CLASS; |
| 64 | $parser = new $parser_class(); |
| 65 | } |
| 66 | |
| 67 | // Transform text using parser. |
| 68 | return $parser->transform( $text ); |
| 69 | } |
| 70 | |
| 71 | // WordPress Plugin Interface ### |
| 72 | if ( isset( $wp_version ) ) { |
| 73 | // More details about how it works here: |
| 74 | // <http://michelf.ca/weblog/2005/wordpress-text-flow-vs-markdown/> |
| 75 | // Post content and excerpts |
| 76 | // - Remove WordPress paragraph generator. |
| 77 | // - Run Markdown on excerpt, then remove all tags. |
| 78 | // - Add paragraph tag around the excerpt, but remove it for the excerpt rss. |
| 79 | if ( MARKDOWN_WP_POSTS ) { |
| 80 | remove_filter( 'the_content', 'wpautop' ); |
| 81 | remove_filter( 'the_content_rss', 'wpautop' ); |
| 82 | remove_filter( 'the_excerpt', 'wpautop' ); |
| 83 | add_filter( 'the_content', 'Markdown', 6 ); |
| 84 | add_filter( 'the_content_rss', 'Markdown', 6 ); |
| 85 | add_filter( 'get_the_excerpt', 'Markdown', 6 ); |
| 86 | add_filter( 'get_the_excerpt', 'trim', 7 ); |
| 87 | add_filter( 'the_excerpt', 'mdwp_add_p' ); |
| 88 | add_filter( 'the_excerpt_rss', 'mdwp_strip_p' ); |
| 89 | |
| 90 | remove_filter( 'content_save_pre', 'balanceTags', 50 ); |
| 91 | remove_filter( 'excerpt_save_pre', 'balanceTags', 50 ); |
| 92 | add_filter( 'the_content', 'balanceTags', 50 ); |
| 93 | add_filter( 'get_the_excerpt', 'balanceTags', 9 ); |
| 94 | } |
| 95 | |
| 96 | // Comments |
| 97 | // - Remove WordPress paragraph generator. |
| 98 | // - Remove WordPress auto-link generator. |
| 99 | // - Scramble important tags before passing them to the kses filter. |
| 100 | // - Run Markdown on excerpt then remove paragraph tags. |
| 101 | if ( MARKDOWN_WP_COMMENTS ) { |
| 102 | remove_filter( 'comment_text', 'wpautop', 30 ); |
| 103 | remove_filter( 'comment_text', 'make_clickable' ); |
| 104 | add_filter( 'pre_comment_content', 'Markdown', 6 ); |
| 105 | add_filter( 'pre_comment_content', 'mdwp_hide_tags', 8 ); |
| 106 | add_filter( 'pre_comment_content', 'mdwp_show_tags', 12 ); |
| 107 | add_filter( 'get_comment_text', 'Markdown', 6 ); |
| 108 | add_filter( 'get_comment_excerpt', 'Markdown', 6 ); |
| 109 | add_filter( 'get_comment_excerpt', 'mdwp_strip_p', 7 ); |
| 110 | |
| 111 | global $mdwp_hidden_tags, $mdwp_placeholders; |
| 112 | $mdwp_hidden_tags = explode( ' ', '<p> </p> <pre> </pre> <ol> </ol> <ul> </ul> <li> </li>' ); |
| 113 | $mdwp_placeholders = explode( ' ', str_rot13( 'pEj07ZbbBZ U1kqgh4w4p pre2zmeN6K QTi31t9pre ol0MP1jzJR ' . 'ML5IjmbRol ulANi1NsGY J7zRLJqPul liA8ctl16T K9nhooUHli' ) ); |
| 114 | } |
| 115 | |
| 116 | /** |
| 117 | * @param $text |
| 118 | * |
| 119 | * @return mixed|string |
| 120 | */ |
| 121 | function mdwp_add_p( $text ) { |
| 122 | |
| 123 | if ( ! preg_match( '{^$|^<(p|ul|ol|dl|pre|blockquote)>}i', $text ) ) { |
| 124 | $text = '<p>' . $text . '</p>'; |
| 125 | $text = preg_replace( '{\n{2,}}', "</p>\n\n<p>", $text ); |
| 126 | } |
| 127 | |
| 128 | return $text; |
| 129 | } |
| 130 | |
| 131 | /** |
| 132 | * @param $t |
| 133 | * |
| 134 | * @return mixed |
| 135 | */ |
| 136 | function mdwp_strip_p( $t ) { |
| 137 | |
| 138 | return preg_replace( '{</?p>}i', '', $t ); |
| 139 | } |
| 140 | |
| 141 | /** |
| 142 | * @param $text |
| 143 | * |
| 144 | * @return mixed |
| 145 | */ |
| 146 | function mdwp_hide_tags( $text ) { |
| 147 | |
| 148 | global $mdwp_hidden_tags, $mdwp_placeholders; |
| 149 | |
| 150 | return str_replace( $mdwp_hidden_tags, $mdwp_placeholders, $text ); |
| 151 | } |
| 152 | |
| 153 | /** |
| 154 | * @param $text |
| 155 | * |
| 156 | * @return mixed |
| 157 | */ |
| 158 | function mdwp_show_tags( $text ) { |
| 159 | |
| 160 | global $mdwp_hidden_tags, $mdwp_placeholders; |
| 161 | |
| 162 | return str_replace( $mdwp_placeholders, $mdwp_hidden_tags, $text ); |
| 163 | } |
| 164 | }//end if |
| 165 | |
| 166 | // bBlog Plugin Info ### |
| 167 | /** |
| 168 | * @return array |
| 169 | */ |
| 170 | function identify_modifier_markdown() { |
| 171 | |
| 172 | return array( |
| 173 | 'name' => 'markdown', |
| 174 | 'type' => 'modifier', |
| 175 | 'nicename' => 'Markdown', |
| 176 | 'description' => 'A text-to-HTML conversion tool for web writers', |
| 177 | 'authors' => 'Michel Fortin and John Gruber', |
| 178 | 'licence' => 'BSD-like', |
| 179 | 'version' => MARKDOWN_VERSION, |
| 180 | 'help' => '<a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.ca/projects/php-markdown/">More...</a>', |
| 181 | ); |
| 182 | } |
| 183 | |
| 184 | // Smarty Modifier Interface ### |
| 185 | /** |
| 186 | * @param $text |
| 187 | * |
| 188 | * @return mixed |
| 189 | */ |
| 190 | function smarty_modifier_markdown( $text ) { |
| 191 | |
| 192 | return Markdown( $text ); |
| 193 | } |
| 194 | |
| 195 | // Textile Compatibility Mode ### |
| 196 | // Rename this file to "classTextile.php" and it can replace Textile everywhere. |
| 197 | if ( strcasecmp( substr( __FILE__, - 16 ), 'classTextile.php' ) == 0 ) { |
| 198 | // Try to include PHP SmartyPants. Should be in the same directory. |
| 199 | @include_once 'smartypants.php'; |
| 200 | |
| 201 | // Fake Textile class. It calls Markdown instead. |
| 202 | |
| 203 | /** |
| 204 | * Class Textile |
| 205 | */ |
| 206 | class Textile { |
| 207 | |
| 208 | /** |
| 209 | * @param $text |
| 210 | * @param string $lite |
| 211 | * @param string $encode |
| 212 | * |
| 213 | * @return mixed |
| 214 | */ |
| 215 | public function TextileThis( $text, $lite = '', $encode = '' ) { |
| 216 | |
| 217 | if ( $lite == '' && $encode == '' ) { |
| 218 | $text = Markdown( $text ); |
| 219 | } |
| 220 | if ( function_exists( 'SmartyPants' ) ) { |
| 221 | $text = SmartyPants( $text ); |
| 222 | } |
| 223 | |
| 224 | return $text; |
| 225 | } |
| 226 | |
| 227 | // Fake restricted version: restrictions are not supported for now. |
| 228 | |
| 229 | /** |
| 230 | * @param $text |
| 231 | * @param string $lite |
| 232 | * @param string $noimage |
| 233 | * |
| 234 | * @return mixed |
| 235 | */ |
| 236 | public function TextileRestricted( $text, $lite = '', $noimage = '' ) { |
| 237 | |
| 238 | return $this->TextileThis( $text, $lite ); |
| 239 | } |
| 240 | |
| 241 | // Workaround to ensure compatibility with TextPattern 4.0.3. |
| 242 | |
| 243 | /** |
| 244 | * @param $text |
| 245 | * |
| 246 | * @return mixed |
| 247 | */ |
| 248 | public function blockLite( $text ) { |
| 249 | |
| 250 | return $text; |
| 251 | } |
| 252 | } |
| 253 | }//end if |
| 254 | |
| 255 | // |
| 256 | // Markdown Parser Class |
| 257 | // |
| 258 | |
| 259 | /** |
| 260 | * Class Markdown_Parser |
| 261 | */ |
| 262 | class Markdown_Parser { |
| 263 | |
| 264 | // Configuration Variables ### |
| 265 | // Change to ">" for HTML output. |
| 266 | public $empty_element_suffix = MARKDOWN_EMPTY_ELEMENT_SUFFIX; |
| 267 | public $tab_width = MARKDOWN_TAB_WIDTH; |
| 268 | |
| 269 | // Change to `true` to disallow markup or entities. |
| 270 | public $no_markup = false; |
| 271 | public $no_entities = false; |
| 272 | |
| 273 | // Predefined urls and titles for reference links and images. |
| 274 | public $predef_urls = array(); |
| 275 | public $predef_titles = array(); |
| 276 | |
| 277 | // Parser Implementation ### |
| 278 | // Regex to match balanced [brackets]. |
| 279 | // Needed to insert a maximum bracked depth while converting to PHP. |
| 280 | public $nested_brackets_depth = 6; |
| 281 | public $nested_brackets_re; |
| 282 | |
| 283 | public $nested_url_parenthesis_depth = 4; |
| 284 | public $nested_url_parenthesis_re; |
| 285 | |
| 286 | // Table of hash values for escaped characters: |
| 287 | public $escape_chars = '\`*_{}[]()>#+-.!'; |
| 288 | public $escape_chars_re; |
| 289 | |
| 290 | /** |
| 291 | * Markdown_Parser constructor. |
| 292 | */ |
| 293 | public function __construct() { |
| 294 | |
| 295 | // |
| 296 | // Constructor function. Initialize appropriate member variables. |
| 297 | // |
| 298 | $this->_initDetab(); |
| 299 | $this->prepareItalicsAndBold(); |
| 300 | |
| 301 | $this->nested_brackets_re = str_repeat( '(?>[^\[\]]+|\[', $this->nested_brackets_depth ) . str_repeat( '\])*', $this->nested_brackets_depth ); |
| 302 | |
| 303 | $this->nested_url_parenthesis_re = str_repeat( '(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth ) . str_repeat( '(?>\)))*', $this->nested_url_parenthesis_depth ); |
| 304 | |
| 305 | $this->escape_chars_re = '[' . preg_quote( $this->escape_chars ) . ']'; |
| 306 | |
| 307 | // Sort document, block, and span gamut in ascendent priority order. |
| 308 | asort( $this->document_gamut ); |
| 309 | asort( $this->block_gamut ); |
| 310 | asort( $this->span_gamut ); |
| 311 | } |
| 312 | |
| 313 | // Internal hashes used during transformation. |
| 314 | public $urls = array(); |
| 315 | public $titles = array(); |
| 316 | public $html_hashes = array(); |
| 317 | |
| 318 | // Status flag to avoid invalid nesting. |
| 319 | public $in_anchor = false; |
| 320 | |
| 321 | public function setup() { |
| 322 | |
| 323 | // |
| 324 | // Called before the transformation process starts to setup parser |
| 325 | // states. |
| 326 | // |
| 327 | // Clear global hashes. |
| 328 | $this->urls = $this->predef_urls; |
| 329 | $this->titles = $this->predef_titles; |
| 330 | $this->html_hashes = array(); |
| 331 | |
| 332 | $this->in_anchor = false; |
| 333 | } |
| 334 | |
| 335 | public function teardown() { |
| 336 | |
| 337 | // |
| 338 | // Called after the transformation process to clear any variable |
| 339 | // which may be taking up memory unnecessarly. |
| 340 | // |
| 341 | $this->urls = array(); |
| 342 | $this->titles = array(); |
| 343 | $this->html_hashes = array(); |
| 344 | } |
| 345 | |
| 346 | /** |
| 347 | * @param $text |
| 348 | * |
| 349 | * @return string |
| 350 | */ |
| 351 | public function transform( $text ) { |
| 352 | |
| 353 | // |
| 354 | // Main function. Performs some preprocessing on the input text |
| 355 | // and pass it through the document gamut. |
| 356 | // |
| 357 | $this->setup(); |
| 358 | |
| 359 | // Remove UTF-8 BOM and marker character in input, if present. |
| 360 | $text = preg_replace( '{^\xEF\xBB\xBF|\x1A}', '', $text ); |
| 361 | |
| 362 | // Standardize line endings: |
| 363 | // DOS to Unix and Mac to Unix |
| 364 | $text = preg_replace( '{\r\n?}', "\n", $text ); |
| 365 | |
| 366 | // Make sure $text ends with a couple of newlines: |
| 367 | $text .= "\n\n"; |
| 368 | |
| 369 | // Convert all tabs to spaces. |
| 370 | $text = $this->detab( $text ); |
| 371 | |
| 372 | // Turn block-level HTML blocks into hash entries |
| 373 | $text = $this->hashHTMLBlocks( $text ); |
| 374 | |
| 375 | // Strip any lines consisting only of spaces and tabs. |
| 376 | // This makes subsequent regexen easier to write, because we can |
| 377 | // match consecutive blank lines with /\n+/ instead of something |
| 378 | // contorted like /[ ]*\n+/ . |
| 379 | $text = preg_replace( '/^[ ]+$/m', '', $text ); |
| 380 | |
| 381 | // Run document gamut methods. |
| 382 | foreach ( $this->document_gamut as $method => $priority ) { |
| 383 | $text = $this->$method( $text ); |
| 384 | } |
| 385 | |
| 386 | $this->teardown(); |
| 387 | |
| 388 | return $text . "\n"; |
| 389 | } |
| 390 | |
| 391 | public $document_gamut = array( |
| 392 | // Strip link definitions, store in hashes. |
| 393 | 'stripLinkDefinitions' => 20, |
| 394 | |
| 395 | 'runBasicBlockGamut' => 30, |
| 396 | ); |
| 397 | |
| 398 | /** |
| 399 | * @param $text |
| 400 | * |
| 401 | * @return mixed |
| 402 | */ |
| 403 | public function stripLinkDefinitions( $text ) { |
| 404 | |
| 405 | // |
| 406 | // Strips link definitions from text, stores the URLs and titles in |
| 407 | // hash references. |
| 408 | // |
| 409 | $less_than_tab = $this->tab_width - 1; |
| 410 | |
| 411 | // Link defs are in the form: ^[id]: url "optional title" |
| 412 | $text = preg_replace_callback( '{ |
| 413 | ^[ ]{0,' . $less_than_tab . '}\[(.+)\][ ]?: # id = $1 |
| 414 | [ ]* |
| 415 | \n? # maybe *one* newline |
| 416 | [ ]* |
| 417 | (?: |
| 418 | <(.+?)> # url = $2 |
| 419 | | |
| 420 | (\S+?) # url = $3 |
| 421 | ) |
| 422 | [ ]* |
| 423 | \n? # maybe one newline |
| 424 | [ ]* |
| 425 | (?: |
| 426 | (?<=\s) # lookbehind for whitespace |
| 427 | ["(] |
| 428 | (.*?) # title = $4 |
| 429 | [")] |
| 430 | [ ]* |
| 431 | )? # title is optional |
| 432 | (?:\n+|\Z) |
| 433 | }xm', array( &$this, '_stripLinkDefinitions_callback' ), $text ); |
| 434 | |
| 435 | return $text; |
| 436 | } |
| 437 | |
| 438 | /** |
| 439 | * @param $matches |
| 440 | * |
| 441 | * @return string |
| 442 | */ |
| 443 | public function _stripLinkDefinitions_callback( $matches ) { |
| 444 | |
| 445 | $link_id = strtolower( $matches[1] ); |
| 446 | $url = $matches[2] == '' ? $matches[3] : $matches[2]; |
| 447 | $this->urls[ $link_id ] = $url; |
| 448 | $this->titles[ $link_id ] =& $matches[4]; |
| 449 | |
| 450 | return ''; |
| 451 | // String that will replace the block |
| 452 | } |
| 453 | |
| 454 | /** |
| 455 | * @param $text |
| 456 | * |
| 457 | * @return mixed |
| 458 | */ |
| 459 | public function hashHTMLBlocks( $text ) { |
| 460 | |
| 461 | if ( $this->no_markup ) { |
| 462 | return $text; |
| 463 | } |
| 464 | |
| 465 | $less_than_tab = $this->tab_width - 1; |
| 466 | |
| 467 | // Hashify HTML blocks: |
| 468 | // We only want to do this for block-level HTML tags, such as headers, |
| 469 | // lists, and tables. That's because we still want to wrap <p>s around |
| 470 | // "paragraphs" that are wrapped in non-block-level tags, such as anchors, |
| 471 | // phrase emphasis, and spans. The list of tags we're looking for is |
| 472 | // hard-coded: |
| 473 | // |
| 474 | // * List "a" is made of tags which can be both inline or block-level. |
| 475 | // These will be treated block-level when the start tag is alone on |
| 476 | // its line, otherwise they're not matched here and will be taken as |
| 477 | // inline later. |
| 478 | // * List "b" is made of tags which are always block-level; |
| 479 | // |
| 480 | $block_tags_a_re = 'ins|del'; |
| 481 | $block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|' . 'script|noscript|form|fieldset|iframe|math|svg|' . 'article|section|nav|aside|hgroup|header|footer|' . 'figure'; |
| 482 | |
| 483 | // Regular expression for the content of a block tag. |
| 484 | $nested_tags_level = 4; |
| 485 | $attr = ' |
| 486 | (?> # optional tag attributes |
| 487 | \s # starts with whitespace |
| 488 | (?> |
| 489 | [^>"/]+ # text outside quotes |
| 490 | | |
| 491 | /+(?!>) # slash not followed by ">" |
| 492 | | |
| 493 | "[^"]*" # text inside double quotes (tolerate ">") |
| 494 | | |
| 495 | \'[^\']*\' # text inside single quotes (tolerate ">") |
| 496 | )* |
| 497 | )? |
| 498 | '; |
| 499 | $content = str_repeat( ' |
| 500 | (?> |
| 501 | [^<]+ # content without tag |
| 502 | | |
| 503 | <\2 # nested opening tag |
| 504 | ' . $attr . ' # attributes |
| 505 | (?> |
| 506 | /> |
| 507 | | |
| 508 | >', $nested_tags_level ) . // end of opening tag |
| 509 | '.*?' . // last level nested tag content |
| 510 | str_repeat( ' |
| 511 | </\2\s*> # closing nested tag |
| 512 | ) |
| 513 | | |
| 514 | <(?!/\2\s*> # other tags with a different name |
| 515 | ) |
| 516 | )*', $nested_tags_level ); |
| 517 | $content2 = str_replace( '\2', '\3', $content ); |
| 518 | |
| 519 | // First, look for nested blocks, e.g.: |
| 520 | // <div> |
| 521 | // <div> |
| 522 | // tags for inner block must be indented. |
| 523 | // </div> |
| 524 | // </div> |
| 525 | // |
| 526 | // The outermost tags must start at the left margin for this to match, and |
| 527 | // the inner nested divs must be indented. |
| 528 | // We need to do this before the next, more liberal match, because the next |
| 529 | // match will start at the first `<div>` and stop at the first `</div>`. |
| 530 | $text = preg_replace_callback( '{(?> |
| 531 | (?> |
| 532 | (?<=\n\n) # Starting after a blank line |
| 533 | | # or |
| 534 | \A\n? # the beginning of the doc |
| 535 | ) |
| 536 | ( # save in $1 |
| 537 | |
| 538 | # Match from `\n<tag>` to `</tag>\n`, handling nested tags |
| 539 | # in between. |
| 540 | |
| 541 | [ ]{0,' . $less_than_tab . '} |
| 542 | <(' . $block_tags_b_re . ')# start tag = $2 |
| 543 | ' . $attr . '> # attributes followed by > and \n |
| 544 | ' . $content . ' # content, support nesting |
| 545 | </\2> # the matching end tag |
| 546 | [ ]* # trailing spaces/tabs |
| 547 | (?=\n+|\Z) # followed by a newline or end of document |
| 548 | |
| 549 | | # Special version for tags of group a. |
| 550 | |
| 551 | [ ]{0,' . $less_than_tab . '} |
| 552 | <(' . $block_tags_a_re . ')# start tag = $3 |
| 553 | ' . $attr . '>[ ]*\n # attributes followed by > |
| 554 | ' . $content2 . ' # content, support nesting |
| 555 | </\3> # the matching end tag |
| 556 | [ ]* # trailing spaces/tabs |
| 557 | (?=\n+|\Z) # followed by a newline or end of document |
| 558 | |
| 559 | | # Special case just for <hr />. It was easier to make a special |
| 560 | # case than to make the other regex more complicated. |
| 561 | |
| 562 | [ ]{0,' . $less_than_tab . '} |
| 563 | <(hr) # start tag = $2 |
| 564 | ' . $attr . ' # attributes |
| 565 | /?> # the matching end tag |
| 566 | [ ]* |
| 567 | (?=\n{2,}|\Z) # followed by a blank line or end of document |
| 568 | |
| 569 | | # Special case for standalone HTML comments: |
| 570 | |
| 571 | [ ]{0,' . $less_than_tab . '} |
| 572 | (?s: |
| 573 | <!-- .*? --> |
| 574 | ) |
| 575 | [ ]* |
| 576 | (?=\n{2,}|\Z) # followed by a blank line or end of document |
| 577 | |
| 578 | | # PHP and ASP-style processor instructions (<? and <%) |
| 579 | |
| 580 | [ ]{0,' . $less_than_tab . '} |
| 581 | (?s: |
| 582 | <([?%]) # $2 |
| 583 | .*? |
| 584 | \2> |
| 585 | ) |
| 586 | [ ]* |
| 587 | (?=\n{2,}|\Z) # followed by a blank line or end of document |
| 588 | |
| 589 | ) |
| 590 | )}Sxmi', array( &$this, '_hashHTMLBlocks_callback' ), $text ); |
| 591 | |
| 592 | return $text; |
| 593 | } |
| 594 | |
| 595 | /** |
| 596 | * @param $matches |
| 597 | * |
| 598 | * @return string |
| 599 | */ |
| 600 | public function _hashHTMLBlocks_callback( $matches ) { |
| 601 | |
| 602 | $text = $matches[1]; |
| 603 | $key = $this->hashBlock( $text ); |
| 604 | |
| 605 | return "\n\n$key\n\n"; |
| 606 | } |
| 607 | |
| 608 | /** |
| 609 | * @param $text |
| 610 | * @param string $boundary |
| 611 | * |
| 612 | * @return string |
| 613 | */ |
| 614 | public function hashPart( $text, $boundary = 'X' ) { |
| 615 | |
| 616 | // |
| 617 | // Called whenever a tag must be hashed when a function insert an atomic |
| 618 | // element in the text stream. Passing $text to through this function gives |
| 619 | // a unique text-token which will be reverted back when calling unhash. |
| 620 | // |
| 621 | // The $boundary argument specify what character should be used to surround |
| 622 | // the token. By convension, "B" is used for block elements that needs not |
| 623 | // to be wrapped into paragraph tags at the end, ":" is used for elements |
| 624 | // that are word separators and "X" is used in the general case. |
| 625 | // |
| 626 | // Swap back any tag hash found in $text so we do not have to `unhash` |
| 627 | // multiple times at the end. |
| 628 | $text = $this->unhash( $text ); |
| 629 | |
| 630 | // Then hash the block. |
| 631 | static $i = 0; |
| 632 | $key = "$boundary\x1A" . ++ $i . $boundary; |
| 633 | $this->html_hashes[ $key ] = $text; |
| 634 | |
| 635 | return $key; |
| 636 | // String that will replace the tag. |
| 637 | } |
| 638 | |
| 639 | /** |
| 640 | * @param $text |
| 641 | * |
| 642 | * @return string |
| 643 | */ |
| 644 | public function hashBlock( $text ) { |
| 645 | |
| 646 | // |
| 647 | // Shortcut function for hashPart with block-level boundaries. |
| 648 | // |
| 649 | return $this->hashPart( $text, 'B' ); |
| 650 | } |
| 651 | |
| 652 | public $block_gamut = array( |
| 653 | // |
| 654 | // These are all the transformations that form block-level |
| 655 | // tags like paragraphs, headers, and list items. |
| 656 | // |
| 657 | 'doHeaders' => 10, |
| 658 | 'doHorizontalRules' => 20, |
| 659 | |
| 660 | 'doLists' => 40, |
| 661 | 'doCodeBlocks' => 50, |
| 662 | 'doBlockQuotes' => 60, |
| 663 | ); |
| 664 | |
| 665 | /** |
| 666 | * @param $text |
| 667 | * |
| 668 | * @return string |
| 669 | */ |
| 670 | public function runBlockGamut( $text ) { |
| 671 | |
| 672 | // |
| 673 | // Run block gamut tranformations. |
| 674 | // |
| 675 | // We need to escape raw HTML in Markdown source before doing anything |
| 676 | // else. This need to be done for each block, and not only at the |
| 677 | // begining in the Markdown function since hashed blocks can be part of |
| 678 | // list items and could have been indented. Indented blocks would have |
| 679 | // been seen as a code block in a previous pass of hashHTMLBlocks. |
| 680 | $text = $this->hashHTMLBlocks( $text ); |
| 681 | |
| 682 | return $this->runBasicBlockGamut( $text ); |
| 683 | } |
| 684 | |
| 685 | /** |
| 686 | * @param $text |
| 687 | * |
| 688 | * @return string |
| 689 | */ |
| 690 | public function runBasicBlockGamut( $text ) { |
| 691 | |
| 692 | // |
| 693 | // Run block gamut tranformations, without hashing HTML blocks. This is |
| 694 | // useful when HTML blocks are known to be already hashed, like in the first |
| 695 | // whole-document pass. |
| 696 | // |
| 697 | foreach ( $this->block_gamut as $method => $priority ) { |
| 698 | $text = $this->$method( $text ); |
| 699 | } |
| 700 | |
| 701 | // Finally form paragraph and restore hashed blocks. |
| 702 | $text = $this->formParagraphs( $text ); |
| 703 | |
| 704 | return $text; |
| 705 | } |
| 706 | |
| 707 | /** |
| 708 | * @param $text |
| 709 | * |
| 710 | * @return mixed |
| 711 | */ |
| 712 | public function doHorizontalRules( $text ) { |
| 713 | |
| 714 | // Do Horizontal Rules: |
| 715 | return preg_replace( '{ |
| 716 | ^[ ]{0,3} # Leading space |
| 717 | ([-*_]) # $1: First marker |
| 718 | (?> # Repeated marker group |
| 719 | [ ]{0,2} # Zero, one, or two spaces. |
| 720 | \1 # Marker character |
| 721 | ){2,} # Group repeated at least twice |
| 722 | [ ]* # Tailing spaces |
| 723 | $ # End of line. |
| 724 | }mx', "\n" . $this->hashBlock( "<hr$this->empty_element_suffix" ) . "\n", $text ); |
| 725 | } |
| 726 | |
| 727 | public $span_gamut = array( |
| 728 | // |
| 729 | // These are all the transformations that occur *within* block-level |
| 730 | // tags like paragraphs, headers, and list items. |
| 731 | // |
| 732 | // Process character escapes, code spans, and inline HTML |
| 733 | // in one shot. |
| 734 | 'parseSpan' => - 30, |
| 735 | |
| 736 | // Process anchor and image tags. Images must come first, |
| 737 | // because ![foo][f] looks like an anchor. |
| 738 | 'doImages' => 10, |
| 739 | 'doAnchors' => 20, |
| 740 | |
| 741 | // Make links out of things like `<http://example.com/>` |
| 742 | // Must come after doAnchors, because you can use < and > |
| 743 | // delimiters in inline links like [this](<url>). |
| 744 | 'doAutoLinks' => 30, |
| 745 | 'encodeAmpsAndAngles' => 40, |
| 746 | |
| 747 | 'doItalicsAndBold' => 50, |
| 748 | 'doHardBreaks' => 60, |
| 749 | ); |
| 750 | |
| 751 | /** |
| 752 | * @param $text |
| 753 | * |
| 754 | * @return mixed |
| 755 | */ |
| 756 | public function runSpanGamut( $text ) { |
| 757 | |
| 758 | // |
| 759 | // Run span gamut tranformations. |
| 760 | // |
| 761 | foreach ( $this->span_gamut as $method => $priority ) { |
| 762 | $text = $this->$method( $text ); |
| 763 | } |
| 764 | |
| 765 | return $text; |
| 766 | } |
| 767 | |
| 768 | /** |
| 769 | * @param $text |
| 770 | * |
| 771 | * @return mixed |
| 772 | */ |
| 773 | public function doHardBreaks( $text ) { |
| 774 | |
| 775 | // Do hard breaks: |
| 776 | return preg_replace_callback( '/ {2,}\n/', array( &$this, '_doHardBreaks_callback' ), $text ); |
| 777 | } |
| 778 | |
| 779 | /** |
| 780 | * @param $matches |
| 781 | * |
| 782 | * @return string |
| 783 | */ |
| 784 | public function _doHardBreaks_callback( $matches ) { |
| 785 | |
| 786 | return $this->hashPart( "<br$this->empty_element_suffix\n" ); |
| 787 | } |
| 788 | |
| 789 | /** |
| 790 | * @param $text |
| 791 | * |
| 792 | * @return mixed |
| 793 | */ |
| 794 | public function doAnchors( $text ) { |
| 795 | |
| 796 | // |
| 797 | // Turn Markdown link shortcuts into XHTML <a> tags. |
| 798 | // |
| 799 | if ( $this->in_anchor ) { |
| 800 | return $text; |
| 801 | } |
| 802 | $this->in_anchor = true; |
| 803 | |
| 804 | // |
| 805 | // First, handle reference-style links: [link text] [id] |
| 806 | // |
| 807 | $text = preg_replace_callback( '{ |
| 808 | ( # wrap whole match in $1 |
| 809 | \[ |
| 810 | (' . $this->nested_brackets_re . ') # link text = $2 |
| 811 | \] |
| 812 | |
| 813 | [ ]? # one optional space |
| 814 | (?:\n[ ]*)? # one optional newline followed by spaces |
| 815 | |
| 816 | \[ |
| 817 | (.*?) # id = $3 |
| 818 | \] |
| 819 | ) |
| 820 | }xs', array( &$this, '_doAnchors_reference_callback' ), $text ); |
| 821 | |
| 822 | // |
| 823 | // Next, inline-style links: [link text](url "optional title") |
| 824 | // |
| 825 | $text = preg_replace_callback( '{ |
| 826 | ( # wrap whole match in $1 |
| 827 | \[ |
| 828 | (' . $this->nested_brackets_re . ') # link text = $2 |
| 829 | \] |
| 830 | \( # literal paren |
| 831 | [ \n]* |
| 832 | (?: |
| 833 | <(.+?)> # href = $3 |
| 834 | | |
| 835 | (' . $this->nested_url_parenthesis_re . ') # href = $4 |
| 836 | ) |
| 837 | [ \n]* |
| 838 | ( # $5 |
| 839 | ([\'"]) # quote char = $6 |
| 840 | (.*?) # Title = $7 |
| 841 | \6 # matching quote |
| 842 | [ \n]* # ignore any spaces/tabs between closing quote and ) |
| 843 | )? # title is optional |
| 844 | \) |
| 845 | ) |
| 846 | }xs', array( &$this, '_doAnchors_inline_callback' ), $text ); |
| 847 | |
| 848 | // |
| 849 | // Last, handle reference-style shortcuts: [link text] |
| 850 | // These must come last in case you've also got [link text][1] |
| 851 | // or [link text](/foo) |
| 852 | // |
| 853 | $text = preg_replace_callback( '{ |
| 854 | ( # wrap whole match in $1 |
| 855 | \[ |
| 856 | ([^\[\]]+) # link text = $2; can\'t contain [ or ] |
| 857 | \] |
| 858 | ) |
| 859 | }xs', array( &$this, '_doAnchors_reference_callback' ), $text ); |
| 860 | |
| 861 | $this->in_anchor = false; |
| 862 | |
| 863 | return $text; |
| 864 | } |
| 865 | |
| 866 | /** |
| 867 | * @param $matches |
| 868 | * |
| 869 | * @return string |
| 870 | */ |
| 871 | public function _doAnchors_reference_callback( $matches ) { |
| 872 | |
| 873 | $whole_match = $matches[1]; |
| 874 | $link_text = $matches[2]; |
| 875 | $link_id =& $matches[3]; |
| 876 | |
| 877 | if ( $link_id == '' ) { |
| 878 | // for shortcut links like [this][] or [this]. |
| 879 | $link_id = $link_text; |
| 880 | } |
| 881 | |
| 882 | // lower-case and turn embedded newlines into spaces |
| 883 | $link_id = strtolower( $link_id ); |
| 884 | $link_id = preg_replace( '{[ ]?\n}', ' ', $link_id ); |
| 885 | |
| 886 | if ( isset( $this->urls[ $link_id ] ) ) { |
| 887 | $url = $this->urls[ $link_id ]; |
| 888 | $url = $this->encodeAttribute( $url ); |
| 889 | |
| 890 | $result = "<a href=\"$url\""; |
| 891 | if ( isset( $this->titles[ $link_id ] ) ) { |
| 892 | $title = $this->titles[ $link_id ]; |
| 893 | $title = $this->encodeAttribute( $title ); |
| 894 | $result .= " title=\"$title\""; |
| 895 | } |
| 896 | |
| 897 | $link_text = $this->runSpanGamut( $link_text ); |
| 898 | $result .= ">$link_text</a>"; |
| 899 | $result = $this->hashPart( $result ); |
| 900 | } else { |
| 901 | $result = $whole_match; |
| 902 | } |
| 903 | |
| 904 | return $result; |
| 905 | } |
| 906 | |
| 907 | /** |
| 908 | * @param $matches |
| 909 | * |
| 910 | * @return string |
| 911 | */ |
| 912 | public function _doAnchors_inline_callback( $matches ) { |
| 913 | |
| 914 | $whole_match = $matches[1]; |
| 915 | $link_text = $this->runSpanGamut( $matches[2] ); |
| 916 | $url = $matches[3] == '' ? $matches[4] : $matches[3]; |
| 917 | $title =& $matches[7]; |
| 918 | |
| 919 | $url = $this->encodeAttribute( $url ); |
| 920 | |
| 921 | $result = "<a href=\"$url\""; |
| 922 | if ( isset( $title ) ) { |
| 923 | $title = $this->encodeAttribute( $title ); |
| 924 | $result .= " title=\"$title\""; |
| 925 | } |
| 926 | |
| 927 | $link_text = $this->runSpanGamut( $link_text ); |
| 928 | $result .= ">$link_text</a>"; |
| 929 | |
| 930 | return $this->hashPart( $result ); |
| 931 | } |
| 932 | |
| 933 | /** |
| 934 | * @param $text |
| 935 | * |
| 936 | * @return mixed |
| 937 | */ |
| 938 | public function doImages( $text ) { |
| 939 | |
| 940 | // |
| 941 | // Turn Markdown image shortcuts into <img> tags. |
| 942 | // |
| 943 | // |
| 944 | // First, handle reference-style labeled images: ![alt text][id] |
| 945 | // |
| 946 | $text = preg_replace_callback( '{ |
| 947 | ( # wrap whole match in $1 |
| 948 | !\[ |
| 949 | (' . $this->nested_brackets_re . ') # alt text = $2 |
| 950 | \] |
| 951 | |
| 952 | [ ]? # one optional space |
| 953 | (?:\n[ ]*)? # one optional newline followed by spaces |
| 954 | |
| 955 | \[ |
| 956 | (.*?) # id = $3 |
| 957 | \] |
| 958 | |
| 959 | ) |
| 960 | }xs', array( &$this, '_doImages_reference_callback' ), $text ); |
| 961 | |
| 962 | // |
| 963 | // Next, handle inline images:  |
| 964 | // Don't forget: encode * and _ |
| 965 | // |
| 966 | $text = preg_replace_callback( '{ |
| 967 | ( # wrap whole match in $1 |
| 968 | !\[ |
| 969 | (' . $this->nested_brackets_re . ') # alt text = $2 |
| 970 | \] |
| 971 | \s? # One optional whitespace character |
| 972 | \( # literal paren |
| 973 | [ \n]* |
| 974 | (?: |
| 975 | <(\S*)> # src url = $3 |
| 976 | | |
| 977 | (' . $this->nested_url_parenthesis_re . ') # src url = $4 |
| 978 | ) |
| 979 | [ \n]* |
| 980 | ( # $5 |
| 981 | ([\'"]) # quote char = $6 |
| 982 | (.*?) # title = $7 |
| 983 | \6 # matching quote |
| 984 | [ \n]* |
| 985 | )? # title is optional |
| 986 | \) |
| 987 | ) |
| 988 | }xs', array( &$this, '_doImages_inline_callback' ), $text ); |
| 989 | |
| 990 | return $text; |
| 991 | } |
| 992 | |
| 993 | /** |
| 994 | * @param $matches |
| 995 | * |
| 996 | * @return string |
| 997 | */ |
| 998 | public function _doImages_reference_callback( $matches ) { |
| 999 | |
| 1000 | $whole_match = $matches[1]; |
| 1001 | $alt_text = $matches[2]; |
| 1002 | $link_id = strtolower( $matches[3] ); |
| 1003 | |
| 1004 | if ( $link_id == '' ) { |
| 1005 | $link_id = strtolower( $alt_text ); |
| 1006 | // for shortcut links like ![this][]. |
| 1007 | } |
| 1008 | |
| 1009 | $alt_text = $this->encodeAttribute( $alt_text ); |
| 1010 | if ( isset( $this->urls[ $link_id ] ) ) { |
| 1011 | $url = $this->encodeAttribute( $this->urls[ $link_id ] ); |
| 1012 | $result = "<img src=\"$url\" alt=\"$alt_text\""; |
| 1013 | if ( isset( $this->titles[ $link_id ] ) ) { |
| 1014 | $title = $this->titles[ $link_id ]; |
| 1015 | $title = $this->encodeAttribute( $title ); |
| 1016 | $result .= " title=\"$title\""; |
| 1017 | } |
| 1018 | $result .= $this->empty_element_suffix; |
| 1019 | $result = $this->hashPart( $result ); |
| 1020 | } else { |
| 1021 | // If there's no such link ID, leave intact: |
| 1022 | $result = $whole_match; |
| 1023 | } |
| 1024 | |
| 1025 | return $result; |
| 1026 | } |
| 1027 | |
| 1028 | /** |
| 1029 | * @param $matches |
| 1030 | * |
| 1031 | * @return string |
| 1032 | */ |
| 1033 | public function _doImages_inline_callback( $matches ) { |
| 1034 | |
| 1035 | $whole_match = $matches[1]; |
| 1036 | $alt_text = $matches[2]; |
| 1037 | $url = $matches[3] == '' ? $matches[4] : $matches[3]; |
| 1038 | $title =& $matches[7]; |
| 1039 | |
| 1040 | $alt_text = $this->encodeAttribute( $alt_text ); |
| 1041 | $url = $this->encodeAttribute( $url ); |
| 1042 | $result = "<img src=\"$url\" alt=\"$alt_text\""; |
| 1043 | if ( isset( $title ) ) { |
| 1044 | $title = $this->encodeAttribute( $title ); |
| 1045 | $result .= " title=\"$title\""; |
| 1046 | // $title already quoted |
| 1047 | } |
| 1048 | $result .= $this->empty_element_suffix; |
| 1049 | |
| 1050 | return $this->hashPart( $result ); |
| 1051 | } |
| 1052 | |
| 1053 | /** |
| 1054 | * @param $text |
| 1055 | * |
| 1056 | * @return mixed |
| 1057 | */ |
| 1058 | public function doHeaders( $text ) { |
| 1059 | |
| 1060 | // Setext-style headers: |
| 1061 | // Header 1 |
| 1062 | // ======== |
| 1063 | // |
| 1064 | // Header 2 |
| 1065 | // -------- |
| 1066 | // |
| 1067 | $text = preg_replace_callback( '{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx', array( |
| 1068 | &$this, |
| 1069 | '_doHeaders_callback_setext', |
| 1070 | ), $text ); |
| 1071 | |
| 1072 | // atx-style headers: |
| 1073 | // Header 1 |
| 1074 | // Header 2 |
| 1075 | // Header 2 with closing hashes ## |
| 1076 | // ... |
| 1077 | // Header 6 |
| 1078 | // |
| 1079 | $text = preg_replace_callback( '{ |
| 1080 | ^(\#{1,6}) # $1 = string of #\'s |
| 1081 | [ ]* |
| 1082 | (.+?) # $2 = Header text |
| 1083 | [ ]* |
| 1084 | \#* # optional closing #\'s (not counted) |
| 1085 | \n+ |
| 1086 | }xm', array( &$this, '_doHeaders_callback_atx' ), $text ); |
| 1087 | |
| 1088 | return $text; |
| 1089 | } |
| 1090 | |
| 1091 | /** |
| 1092 | * @param $matches |
| 1093 | * |
| 1094 | * @return string |
| 1095 | */ |
| 1096 | public function _doHeaders_callback_setext( $matches ) { |
| 1097 | |
| 1098 | // Terrible hack to check we haven't found an empty list item. |
| 1099 | if ( $matches[2] == '-' && preg_match( '{^-(?: |$)}', $matches[1] ) ) { |
| 1100 | return $matches[0]; |
| 1101 | } |
| 1102 | |
| 1103 | $level = $matches[2][0] == '=' ? 1 : 2; |
| 1104 | $block = "<h$level>" . $this->runSpanGamut( $matches[1] ) . "</h$level>"; |
| 1105 | |
| 1106 | return "\n" . $this->hashBlock( $block ) . "\n\n"; |
| 1107 | } |
| 1108 | |
| 1109 | /** |
| 1110 | * @param $matches |
| 1111 | * |
| 1112 | * @return string |
| 1113 | */ |
| 1114 | public function _doHeaders_callback_atx( $matches ) { |
| 1115 | |
| 1116 | $level = strlen( $matches[1] ); |
| 1117 | $block = "<h$level>" . $this->runSpanGamut( $matches[2] ) . "</h$level>"; |
| 1118 | |
| 1119 | return "\n" . $this->hashBlock( $block ) . "\n\n"; |
| 1120 | } |
| 1121 | |
| 1122 | /** |
| 1123 | * @param $text |
| 1124 | * |
| 1125 | * @return mixed |
| 1126 | */ |
| 1127 | public function doLists( $text ) { |
| 1128 | |
| 1129 | // |
| 1130 | // Form HTML ordered (numbered) and unordered (bulleted) lists. |
| 1131 | // |
| 1132 | $less_than_tab = $this->tab_width - 1; |
| 1133 | |
| 1134 | // Re-usable patterns to match list item bullets and number markers: |
| 1135 | $marker_ul_re = '[*+-]'; |
| 1136 | $marker_ol_re = '\d+[\.]'; |
| 1137 | $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)"; |
| 1138 | |
| 1139 | $markers_relist = array( |
| 1140 | $marker_ul_re => $marker_ol_re, |
| 1141 | $marker_ol_re => $marker_ul_re, |
| 1142 | ); |
| 1143 | |
| 1144 | foreach ( $markers_relist as $marker_re => $other_marker_re ) { |
| 1145 | // Re-usable pattern to match any entirel ul or ol list: |
| 1146 | $whole_list_re = ' |
| 1147 | ( # $1 = whole list |
| 1148 | ( # $2 |
| 1149 | ([ ]{0,' . $less_than_tab . '}) # $3 = number of spaces |
| 1150 | (' . $marker_re . ') # $4 = first list item marker |
| 1151 | [ ]+ |
| 1152 | ) |
| 1153 | (?s:.+?) |
| 1154 | ( # $5 |
| 1155 | \z |
| 1156 | | |
| 1157 | \n{2,} |
| 1158 | (?=\S) |
| 1159 | (?! # Negative lookahead for another list item marker |
| 1160 | [ ]* |
| 1161 | ' . $marker_re . '[ ]+ |
| 1162 | ) |
| 1163 | | |
| 1164 | (?= # Lookahead for another kind of list |
| 1165 | \n |
| 1166 | \3 # Must have the same indentation |
| 1167 | ' . $other_marker_re . '[ ]+ |
| 1168 | ) |
| 1169 | ) |
| 1170 | ) |
| 1171 | '; |
| 1172 | // mx |
| 1173 | // We use a different prefix before nested lists than top-level lists. |
| 1174 | // See extended comment in _ProcessListItems(). |
| 1175 | if ( $this->list_level ) { |
| 1176 | $text = preg_replace_callback( '{ |
| 1177 | ^ |
| 1178 | ' . $whole_list_re . ' |
| 1179 | }mx', array( &$this, '_doLists_callback' ), $text ); |
| 1180 | } else { |
| 1181 | $text = preg_replace_callback( '{ |
| 1182 | (?:(?<=\n)\n|\A\n?) # Must eat the newline |
| 1183 | ' . $whole_list_re . ' |
| 1184 | }mx', array( &$this, '_doLists_callback' ), $text ); |
| 1185 | } |
| 1186 | }//end foreach |
| 1187 | |
| 1188 | return $text; |
| 1189 | } |
| 1190 | |
| 1191 | /** |
| 1192 | * @param $matches |
| 1193 | * |
| 1194 | * @return string |
| 1195 | */ |
| 1196 | public function _doLists_callback( $matches ) { |
| 1197 | |
| 1198 | // Re-usable patterns to match list item bullets and number markers: |
| 1199 | $marker_ul_re = '[*+-]'; |
| 1200 | $marker_ol_re = '\d+[\.]'; |
| 1201 | $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)"; |
| 1202 | |
| 1203 | $list = $matches[1]; |
| 1204 | $list_type = preg_match( "/$marker_ul_re/", $matches[4] ) ? 'ul' : 'ol'; |
| 1205 | |
| 1206 | $marker_any_re = ( $list_type == 'ul' ? $marker_ul_re : $marker_ol_re ); |
| 1207 | |
| 1208 | $list .= "\n"; |
| 1209 | $result = $this->processListItems( $list, $marker_any_re ); |
| 1210 | |
| 1211 | $result = $this->hashBlock( "<$list_type>\n" . $result . "</$list_type>" ); |
| 1212 | |
| 1213 | return "\n" . $result . "\n\n"; |
| 1214 | } |
| 1215 | |
| 1216 | public $list_level = 0; |
| 1217 | |
| 1218 | /** |
| 1219 | * @param $list_str |
| 1220 | * @param $marker_any_re |
| 1221 | * |
| 1222 | * @return mixed |
| 1223 | */ |
| 1224 | public function processListItems( $list_str, $marker_any_re ) { |
| 1225 | |
| 1226 | // |
| 1227 | // Process the contents of a single ordered or unordered list, splitting it |
| 1228 | // into individual list items. |
| 1229 | // |
| 1230 | // The $this->list_level global keeps track of when we're inside a list. |
| 1231 | // Each time we enter a list, we increment it; when we leave a list, |
| 1232 | // we decrement. If it's zero, we're not in a list anymore. |
| 1233 | // |
| 1234 | // We do this because when we're not inside a list, we want to treat |
| 1235 | // something like this: |
| 1236 | // |
| 1237 | // I recommend upgrading to version |
| 1238 | // 8. Oops, now this line is treated |
| 1239 | // as a sub-list. |
| 1240 | // |
| 1241 | // As a single paragraph, despite the fact that the second line starts |
| 1242 | // with a digit-period-space sequence. |
| 1243 | // |
| 1244 | // Whereas when we're inside a list (or sub-list), that line will be |
| 1245 | // treated as the start of a sub-list. What a kludge, huh? This is |
| 1246 | // an aspect of Markdown's syntax that's hard to parse perfectly |
| 1247 | // without resorting to mind-reading. Perhaps the solution is to |
| 1248 | // change the syntax rules such that sub-lists must start with a |
| 1249 | // starting cardinal number; e.g. "1." or "a.". |
| 1250 | $this->list_level ++; |
| 1251 | |
| 1252 | // trim trailing blank lines: |
| 1253 | $list_str = preg_replace( "/\n{2,}\\z/", "\n", $list_str ); |
| 1254 | |
| 1255 | $list_str = preg_replace_callback( '{ |
| 1256 | (\n)? # leading line = $1 |
| 1257 | (^[ ]*) # leading whitespace = $2 |
| 1258 | (' . $marker_any_re . ' # list marker and space = $3 |
| 1259 | (?:[ ]+|(?=\n)) # space only required if item is not empty |
| 1260 | ) |
| 1261 | ((?s:.*?)) # list item text = $4 |
| 1262 | (?:(\n+(?=\n))|\n) # tailing blank line = $5 |
| 1263 | (?= \n* (\z | \2 (' . $marker_any_re . ') (?:[ ]+|(?=\n)))) |
| 1264 | }xm', array( &$this, '_processListItems_callback' ), $list_str ); |
| 1265 | |
| 1266 | $this->list_level --; |
| 1267 | |
| 1268 | return $list_str; |
| 1269 | } |
| 1270 | |
| 1271 | /** |
| 1272 | * @param $matches |
| 1273 | * |
| 1274 | * @return string |
| 1275 | */ |
| 1276 | public function _processListItems_callback( $matches ) { |
| 1277 | |
| 1278 | $item = $matches[4]; |
| 1279 | $leading_line =& $matches[1]; |
| 1280 | $leading_space =& $matches[2]; |
| 1281 | $marker_space = $matches[3]; |
| 1282 | $tailing_blank_line =& $matches[5]; |
| 1283 | |
| 1284 | if ( $leading_line || $tailing_blank_line || preg_match( '/\n{2,}/', $item ) ) { |
| 1285 | // Replace marker with the appropriate whitespace indentation |
| 1286 | $item = $leading_space . str_repeat( ' ', strlen( $marker_space ) ) . $item; |
| 1287 | $item = $this->runBlockGamut( $this->outdent( $item ) . "\n" ); |
| 1288 | } else { |
| 1289 | // Recursion for sub-lists: |
| 1290 | $item = $this->doLists( $this->outdent( $item ) ); |
| 1291 | $item = preg_replace( '/\n+$/', '', $item ); |
| 1292 | $item = $this->runSpanGamut( $item ); |
| 1293 | } |
| 1294 | |
| 1295 | return '<li>' . $item . "</li>\n"; |
| 1296 | } |
| 1297 | |
| 1298 | /** |
| 1299 | * @param $text |
| 1300 | * |
| 1301 | * @return mixed |
| 1302 | */ |
| 1303 | public function doCodeBlocks( $text ) { |
| 1304 | |
| 1305 | // |
| 1306 | // Process Markdown `<pre><code>` blocks. |
| 1307 | // |
| 1308 | $text = preg_replace_callback( '{ |
| 1309 | (?:\n\n|\A\n?) |
| 1310 | ( # $1 = the code block -- one or more lines, starting with a space/tab |
| 1311 | (?> |
| 1312 | [ ]{' . $this->tab_width . '} # Lines must start with a tab or a tab-width of spaces |
| 1313 | .*\n+ |
| 1314 | )+ |
| 1315 | ) |
| 1316 | ((?=^[ ]{0,' . $this->tab_width . '}\S)|\Z) # Lookahead for non-space at line-start, or end of doc |
| 1317 | }xm', array( &$this, '_doCodeBlocks_callback' ), $text ); |
| 1318 | |
| 1319 | return $text; |
| 1320 | } |
| 1321 | |
| 1322 | /** |
| 1323 | * @param $matches |
| 1324 | * |
| 1325 | * @return string |
| 1326 | */ |
| 1327 | public function _doCodeBlocks_callback( $matches ) { |
| 1328 | |
| 1329 | $codeblock = $matches[1]; |
| 1330 | |
| 1331 | $codeblock = $this->outdent( $codeblock ); |
| 1332 | $codeblock = htmlspecialchars( $codeblock, ENT_NOQUOTES ); |
| 1333 | |
| 1334 | // trim leading newlines and trailing newlines |
| 1335 | $codeblock = preg_replace( '/\A\n+|\n+\z/', '', $codeblock ); |
| 1336 | |
| 1337 | $codeblock = "<pre><code>$codeblock\n</code></pre>"; |
| 1338 | |
| 1339 | return "\n\n" . $this->hashBlock( $codeblock ) . "\n\n"; |
| 1340 | } |
| 1341 | |
| 1342 | /** |
| 1343 | * @param $code |
| 1344 | * |
| 1345 | * @return string |
| 1346 | */ |
| 1347 | public function makeCodeSpan( $code ) { |
| 1348 | |
| 1349 | // |
| 1350 | // Create a code span markup for $code. Called from handleSpanToken. |
| 1351 | // |
| 1352 | $code = htmlspecialchars( trim( $code ), ENT_NOQUOTES ); |
| 1353 | |
| 1354 | return $this->hashPart( "<code>$code</code>" ); |
| 1355 | } |
| 1356 | |
| 1357 | public $em_relist = array( |
| 1358 | '' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?=\S|$)(?![\.,:;]\s)', |
| 1359 | '*' => '(?<=\S|^)(?<!\*)\*(?!\*)', |
| 1360 | '_' => '(?<=\S|^)(?<!_)_(?!_)', |
| 1361 | ); |
| 1362 | public $strong_relist = array( |
| 1363 | '' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?=\S|$)(?![\.,:;]\s)', |
| 1364 | '**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)', |
| 1365 | '__' => '(?<=\S|^)(?<!_)__(?!_)', |
| 1366 | ); |
| 1367 | public $em_strong_relist = array( |
| 1368 | '' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?=\S|$)(?![\.,:;]\s)', |
| 1369 | '***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)', |
| 1370 | '___' => '(?<=\S|^)(?<!_)___(?!_)', |
| 1371 | ); |
| 1372 | public $em_strong_prepared_relist; |
| 1373 | |
| 1374 | public function prepareItalicsAndBold() { |
| 1375 | |
| 1376 | // |
| 1377 | // Prepare regular expressions for searching emphasis tokens in any |
| 1378 | // context. |
| 1379 | // |
| 1380 | foreach ( $this->em_relist as $em => $em_re ) { |
| 1381 | foreach ( $this->strong_relist as $strong => $strong_re ) { |
| 1382 | // Construct list of allowed token expressions. |
| 1383 | $token_relist = array(); |
| 1384 | if ( isset( $this->em_strong_relist["$em$strong"] ) ) { |
| 1385 | $token_relist[] = $this->em_strong_relist["$em$strong"]; |
| 1386 | } |
| 1387 | $token_relist[] = $em_re; |
| 1388 | $token_relist[] = $strong_re; |
| 1389 | |
| 1390 | // Construct master expression from list. |
| 1391 | $token_re = '{(' . implode( '|', $token_relist ) . ')}'; |
| 1392 | $this->em_strong_prepared_relist["$em$strong"] = $token_re; |
| 1393 | } |
| 1394 | } |
| 1395 | } |
| 1396 | |
| 1397 | /** |
| 1398 | * @param $text |
| 1399 | * |
| 1400 | * @return string |
| 1401 | */ |
| 1402 | public function doItalicsAndBold( $text ) { |
| 1403 | |
| 1404 | $token_stack = array( '' ); |
| 1405 | $text_stack = array( '' ); |
| 1406 | $em = ''; |
| 1407 | $strong = ''; |
| 1408 | $tree_char_em = false; |
| 1409 | |
| 1410 | while ( 1 ) { |
| 1411 | // |
| 1412 | // Get prepared regular expression for seraching emphasis tokens |
| 1413 | // in current context. |
| 1414 | // |
| 1415 | $token_re = $this->em_strong_prepared_relist["$em$strong"]; |
| 1416 | |
| 1417 | // |
| 1418 | // Each loop iteration search for the next emphasis token. |
| 1419 | // Each token is then passed to handleSpanToken. |
| 1420 | // |
| 1421 | $parts = preg_split( $token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE ); |
| 1422 | $text_stack[0] .= $parts[0]; |
| 1423 | $token =& $parts[1]; |
| 1424 | $text =& $parts[2]; |
| 1425 | |
| 1426 | if ( empty( $token ) ) { |
| 1427 | // Reached end of text span: empty stack without emitting. |
| 1428 | // any more emphasis. |
| 1429 | while ( $token_stack[0] ) { |
| 1430 | $text_stack[1] .= array_shift( $token_stack ); |
| 1431 | $text_stack[0] .= array_shift( $text_stack ); |
| 1432 | } |
| 1433 | break; |
| 1434 | } |
| 1435 | |
| 1436 | $token_len = strlen( $token ); |
| 1437 | if ( $tree_char_em ) { |
| 1438 | // Reached closing marker while inside a three-char emphasis. |
| 1439 | if ( $token_len == 3 ) { |
| 1440 | // Three-char closing marker, close em and strong. |
| 1441 | array_shift( $token_stack ); |
| 1442 | $span = array_shift( $text_stack ); |
| 1443 | $span = $this->runSpanGamut( $span ); |
| 1444 | $span = "<strong><em>$span</em></strong>"; |
| 1445 | $text_stack[0] .= $this->hashPart( $span ); |
| 1446 | $em = ''; |
| 1447 | $strong = ''; |
| 1448 | } else { |
| 1449 | // Other closing marker: close one em or strong and |
| 1450 | // change current token state to match the other |
| 1451 | $token_stack[0] = str_repeat( $token[0], 3 - $token_len ); |
| 1452 | $tag = $token_len == 2 ? 'strong' : 'em'; |
| 1453 | $span = $text_stack[0]; |
| 1454 | $span = $this->runSpanGamut( $span ); |
| 1455 | $span = "<$tag>$span</$tag>"; |
| 1456 | $text_stack[0] = $this->hashPart( $span ); |
| 1457 | $$tag = ''; |
| 1458 | // $$tag stands for $em or $strong |
| 1459 | }//end if |
| 1460 | $tree_char_em = false; |
| 1461 | } elseif ( $token_len == 3 ) { |
| 1462 | if ( $em ) { |
| 1463 | // Reached closing marker for both em and strong. |
| 1464 | // Closing strong marker: |
| 1465 | for ( $i = 0; $i < 2; ++ $i ) { |
| 1466 | $shifted_token = array_shift( $token_stack ); |
| 1467 | $tag = strlen( $shifted_token ) == 2 ? 'strong' : 'em'; |
| 1468 | $span = array_shift( $text_stack ); |
| 1469 | $span = $this->runSpanGamut( $span ); |
| 1470 | $span = "<$tag>$span</$tag>"; |
| 1471 | $text_stack[0] .= $this->hashPart( $span ); |
| 1472 | $$tag = ''; |
| 1473 | // $$tag stands for $em or $strong |
| 1474 | } |
| 1475 | } else { |
| 1476 | // Reached opening three-char emphasis marker. Push on token |
| 1477 | // stack; will be handled by the special condition above. |
| 1478 | $em = $token[0]; |
| 1479 | $strong = "$em$em"; |
| 1480 | array_unshift( $token_stack, $token ); |
| 1481 | array_unshift( $text_stack, '' ); |
| 1482 | $tree_char_em = true; |
| 1483 | }//end if |
| 1484 | } elseif ( $token_len == 2 ) { |
| 1485 | if ( $strong ) { |
| 1486 | // Unwind any dangling emphasis marker: |
| 1487 | if ( strlen( $token_stack[0] ) == 1 ) { |
| 1488 | $text_stack[1] .= array_shift( $token_stack ); |
| 1489 | $text_stack[0] .= array_shift( $text_stack ); |
| 1490 | } |
| 1491 | // Closing strong marker: |
| 1492 | array_shift( $token_stack ); |
| 1493 | $span = array_shift( $text_stack ); |
| 1494 | $span = $this->runSpanGamut( $span ); |
| 1495 | $span = "<strong>$span</strong>"; |
| 1496 | $text_stack[0] .= $this->hashPart( $span ); |
| 1497 | $strong = ''; |
| 1498 | } else { |
| 1499 | array_unshift( $token_stack, $token ); |
| 1500 | array_unshift( $text_stack, '' ); |
| 1501 | $strong = $token; |
| 1502 | } |
| 1503 | } else { |
| 1504 | // Here $token_len == 1 |
| 1505 | if ( $em ) { |
| 1506 | if ( strlen( $token_stack[0] ) == 1 ) { |
| 1507 | // Closing emphasis marker: |
| 1508 | array_shift( $token_stack ); |
| 1509 | $span = array_shift( $text_stack ); |
| 1510 | $span = $this->runSpanGamut( $span ); |
| 1511 | $span = "<em>$span</em>"; |
| 1512 | $text_stack[0] .= $this->hashPart( $span ); |
| 1513 | $em = ''; |
| 1514 | } else { |
| 1515 | $text_stack[0] .= $token; |
| 1516 | } |
| 1517 | } else { |
| 1518 | array_unshift( $token_stack, $token ); |
| 1519 | array_unshift( $text_stack, '' ); |
| 1520 | $em = $token; |
| 1521 | } |
| 1522 | }//end if |
| 1523 | }//end while |
| 1524 | |
| 1525 | return $text_stack[0]; |
| 1526 | } |
| 1527 | |
| 1528 | /** |
| 1529 | * @param $text |
| 1530 | * |
| 1531 | * @return mixed |
| 1532 | */ |
| 1533 | public function doBlockQuotes( $text ) { |
| 1534 | |
| 1535 | $text = preg_replace_callback( '/ |
| 1536 | ( # Wrap whole match in $1 |
| 1537 | (?> |
| 1538 | ^[ ]*>[ ]? # ">" at the start of a line |
| 1539 | .+\n # rest of the first line |
| 1540 | (.+\n)* # subsequent consecutive lines |
| 1541 | \n* # blanks |
| 1542 | )+ |
| 1543 | ) |
| 1544 | /xm', array( &$this, '_doBlockQuotes_callback' ), $text ); |
| 1545 | |
| 1546 | return $text; |
| 1547 | } |
| 1548 | |
| 1549 | /** |
| 1550 | * @param $matches |
| 1551 | * |
| 1552 | * @return string |
| 1553 | */ |
| 1554 | public function _doBlockQuotes_callback( $matches ) { |
| 1555 | |
| 1556 | $bq = $matches[1]; |
| 1557 | // trim one level of quoting - trim whitespace-only lines |
| 1558 | $bq = preg_replace( '/^[ ]*>[ ]?|^[ ]+$/m', '', $bq ); |
| 1559 | $bq = $this->runBlockGamut( $bq ); |
| 1560 | // recurse |
| 1561 | $bq = preg_replace( '/^/m', ' ', $bq ); |
| 1562 | // These leading spaces cause problem with <pre> content, |
| 1563 | // so we need to fix that: |
| 1564 | $bq = preg_replace_callback( '{(\s*<pre>.+?</pre>)}sx', array( &$this, '_doBlockQuotes_callback2' ), $bq ); |
| 1565 | |
| 1566 | return "\n" . $this->hashBlock( "<blockquote>\n$bq\n</blockquote>" ) . "\n\n"; |
| 1567 | } |
| 1568 | |
| 1569 | /** |
| 1570 | * @param $matches |
| 1571 | * |
| 1572 | * @return mixed |
| 1573 | */ |
| 1574 | public function _doBlockQuotes_callback2( $matches ) { |
| 1575 | |
| 1576 | $pre = $matches[1]; |
| 1577 | $pre = preg_replace( '/^ /m', '', $pre ); |
| 1578 | |
| 1579 | return $pre; |
| 1580 | } |
| 1581 | |
| 1582 | /** |
| 1583 | * @param $text |
| 1584 | * |
| 1585 | * @return string |
| 1586 | */ |
| 1587 | public function formParagraphs( $text ) { |
| 1588 | |
| 1589 | // |
| 1590 | // Params: |
| 1591 | // $text - string to process with html <p> tags |
| 1592 | // |
| 1593 | // Strip leading and trailing lines: |
| 1594 | $text = preg_replace( '/\A\n+|\n+\z/', '', $text ); |
| 1595 | |
| 1596 | $grafs = preg_split( '/\n{2,}/', $text, - 1, PREG_SPLIT_NO_EMPTY ); |
| 1597 | |
| 1598 | // |
| 1599 | // Wrap <p> tags and unhashify HTML blocks |
| 1600 | // |
| 1601 | foreach ( $grafs as $key => $value ) { |
| 1602 | if ( ! preg_match( '/^B\x1A[0-9]+B$/', $value ) ) { |
| 1603 | // Is a paragraph. |
| 1604 | $value = $this->runSpanGamut( $value ); |
| 1605 | $value = preg_replace( '/^([ ]*)/', '<p>', $value ); |
| 1606 | $value .= '</p>'; |
| 1607 | $grafs[ $key ] = $this->unhash( $value ); |
| 1608 | } else { |
| 1609 | // Is a block. |
| 1610 | // Modify elements of @grafs in-place... |
| 1611 | $graf = $value; |
| 1612 | $block = $this->html_hashes[ $graf ]; |
| 1613 | $graf = $block; |
| 1614 | // if (preg_match('{ |
| 1615 | // \A |
| 1616 | // ( # $1 = <div> tag |
| 1617 | // <div \s+ |
| 1618 | // [^>]* |
| 1619 | // \b |
| 1620 | // markdown\s*=\s* ([\'"]) # $2 = attr quote char |
| 1621 | // 1 |
| 1622 | // \2 |
| 1623 | // [^>]* |
| 1624 | // > |
| 1625 | // ) |
| 1626 | // ( # $3 = contents |
| 1627 | // .* |
| 1628 | // ) |
| 1629 | // (</div>) # $4 = closing tag |
| 1630 | // \z |
| 1631 | // }xs', $block, $matches)) |
| 1632 | // { |
| 1633 | // list(, $div_open, , $div_content, $div_close) = $matches; |
| 1634 | // |
| 1635 | // # We can't call Markdown(), because that resets the hash; |
| 1636 | // # that initialization code should be pulled into its own sub, though. |
| 1637 | // $div_content = $this->hashHTMLBlocks($div_content); |
| 1638 | // |
| 1639 | // # Run document gamut methods on the content. |
| 1640 | // foreach ($this->document_gamut as $method => $priority) { |
| 1641 | // $div_content = $this->$method($div_content); |
| 1642 | // } |
| 1643 | // |
| 1644 | // $div_open = preg_replace( |
| 1645 | // '{\smarkdown\s*=\s*([\'"]).+?\1}', '', $div_open); |
| 1646 | // |
| 1647 | // $graf = $div_open . "\n" . $div_content . "\n" . $div_close; |
| 1648 | // } |
| 1649 | $grafs[ $key ] = $graf; |
| 1650 | }//end if |
| 1651 | }//end foreach |
| 1652 | |
| 1653 | return implode( "\n\n", $grafs ); |
| 1654 | } |
| 1655 | |
| 1656 | /** |
| 1657 | * @param $text |
| 1658 | * |
| 1659 | * @return mixed |
| 1660 | */ |
| 1661 | public function encodeAttribute( $text ) { |
| 1662 | |
| 1663 | // |
| 1664 | // Encode text for a double-quoted HTML attribute. This function |
| 1665 | // is *not* suitable for attributes enclosed in single quotes. |
| 1666 | // |
| 1667 | $text = $this->encodeAmpsAndAngles( $text ); |
| 1668 | $text = str_replace( '"', '"', $text ); |
| 1669 | |
| 1670 | return $text; |
| 1671 | } |
| 1672 | |
| 1673 | /** |
| 1674 | * @param $text |
| 1675 | * |
| 1676 | * @return mixed |
| 1677 | */ |
| 1678 | public function encodeAmpsAndAngles( $text ) { |
| 1679 | |
| 1680 | // |
| 1681 | // Smart processing for ampersands and angle brackets that need to |
| 1682 | // be encoded. Valid character entities are left alone unless the |
| 1683 | // no-entities mode is set. |
| 1684 | // |
| 1685 | if ( $this->no_entities ) { |
| 1686 | $text = str_replace( '&', '&', $text ); |
| 1687 | } else { |
| 1688 | // Ampersand-encoding based entirely on Nat Irons's Amputator |
| 1689 | // MT plugin: <http://bumppo.net/projects/amputator/> |
| 1690 | $text = preg_replace( '/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/', '&', $text ); |
| 1691 | } |
| 1692 | // Encode remaining <'s |
| 1693 | $text = str_replace( '<', '<', $text ); |
| 1694 | |
| 1695 | return $text; |
| 1696 | } |
| 1697 | |
| 1698 | /** |
| 1699 | * @param $text |
| 1700 | * |
| 1701 | * @return mixed |
| 1702 | */ |
| 1703 | public function doAutoLinks( $text ) { |
| 1704 | |
| 1705 | $text = preg_replace_callback( '{<((https?|ftp|dict):[^\'">\s]+)>}i', array( |
| 1706 | &$this, |
| 1707 | '_doAutoLinks_url_callback', |
| 1708 | ), $text ); |
| 1709 | |
| 1710 | // Email addresses: <address@domain.foo> |
| 1711 | $text = preg_replace_callback( '{ |
| 1712 | < |
| 1713 | (?:mailto:)? |
| 1714 | ( |
| 1715 | (?: |
| 1716 | [-!#$%&\'*+/=?^_`.{|}~\w\x80-\xFF]+ |
| 1717 | | |
| 1718 | ".*?" |
| 1719 | ) |
| 1720 | \@ |
| 1721 | (?: |
| 1722 | [-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+ |
| 1723 | | |
| 1724 | \[[\d.a-fA-F:]+\] # IPv4 & IPv6 |
| 1725 | ) |
| 1726 | ) |
| 1727 | > |
| 1728 | }xi', array( &$this, '_doAutoLinks_email_callback' ), $text ); |
| 1729 | $text = preg_replace_callback( '{<(tel:([^\'">\s]+))>}i', array( |
| 1730 | &$this, |
| 1731 | '_doAutoLinks_tel_callback', |
| 1732 | ), $text ); |
| 1733 | |
| 1734 | return $text; |
| 1735 | } |
| 1736 | |
| 1737 | /** |
| 1738 | * @param $matches |
| 1739 | * |
| 1740 | * @return string |
| 1741 | */ |
| 1742 | public function _doAutoLinks_tel_callback( $matches ) { |
| 1743 | |
| 1744 | $url = $this->encodeAttribute( $matches[1] ); |
| 1745 | $tel = $this->encodeAttribute( $matches[2] ); |
| 1746 | $link = "<a href=\"$url\">$tel</a>"; |
| 1747 | |
| 1748 | return $this->hashPart( $link ); |
| 1749 | } |
| 1750 | |
| 1751 | /** |
| 1752 | * @param $matches |
| 1753 | * |
| 1754 | * @return string |
| 1755 | */ |
| 1756 | public function _doAutoLinks_url_callback( $matches ) { |
| 1757 | |
| 1758 | $url = $this->encodeAttribute( $matches[1] ); |
| 1759 | $link = "<a href=\"$url\">$url</a>"; |
| 1760 | |
| 1761 | return $this->hashPart( $link ); |
| 1762 | } |
| 1763 | |
| 1764 | /** |
| 1765 | * @param $matches |
| 1766 | * |
| 1767 | * @return string |
| 1768 | */ |
| 1769 | public function _doAutoLinks_email_callback( $matches ) { |
| 1770 | |
| 1771 | $address = $matches[1]; |
| 1772 | $link = $this->encodeEmailAddress( $address ); |
| 1773 | |
| 1774 | return $this->hashPart( $link ); |
| 1775 | } |
| 1776 | |
| 1777 | /** |
| 1778 | * @param $addr |
| 1779 | * |
| 1780 | * @return string |
| 1781 | */ |
| 1782 | public function encodeEmailAddress( $addr ) { |
| 1783 | |
| 1784 | // |
| 1785 | // Input: an email address, e.g. "foo@example.com" |
| 1786 | // |
| 1787 | // Output: the email address as a mailto link, with each character |
| 1788 | // of the address encoded as either a decimal or hex entity, in |
| 1789 | // the hopes of foiling most address harvesting spam bots. E.g.: |
| 1790 | // |
| 1791 | // <p><a href="mailto:foo |
| 1792 | // @example.co |
| 1793 | // m">foo@exampl |
| 1794 | // e.com</a></p> |
| 1795 | // |
| 1796 | // Based by a filter by Matthew Wickline, posted to BBEdit-Talk. |
| 1797 | // With some optimizations by Milian Wolff. |
| 1798 | // |
| 1799 | $addr = 'mailto:' . $addr; |
| 1800 | $chars = preg_split( '/(?<!^)(?!$)/', $addr ); |
| 1801 | $seed = (int) abs( crc32( $addr ) / strlen( $addr ) ); |
| 1802 | // Deterministic seed. |
| 1803 | foreach ( $chars as $key => $char ) { |
| 1804 | $ord = ord( $char ); |
| 1805 | // Ignore non-ascii chars. |
| 1806 | if ( $ord < 128 ) { |
| 1807 | $r = ( $seed * ( 1 + $key ) ) % 100; |
| 1808 | // Pseudo-random function. |
| 1809 | // roughly 10% raw, 45% hex, 45% dec |
| 1810 | // '@' *must* be encoded. I insist. |
| 1811 | if ( $r > 90 && $char != '@' ) { /* do nothing */ |
| 1812 | } elseif ( $r < 45 ) { |
| 1813 | $chars[ $key ] = '&#x' . dechex( $ord ) . ';'; |
| 1814 | } else { |
| 1815 | $chars[ $key ] = '&#' . $ord . ';'; |
| 1816 | } |
| 1817 | } |
| 1818 | } |
| 1819 | |
| 1820 | $addr = implode( '', $chars ); |
| 1821 | $text = implode( '', array_slice( $chars, 7 ) ); |
| 1822 | // text without `mailto:` |
| 1823 | $addr = "<a href=\"$addr\">$text</a>"; |
| 1824 | |
| 1825 | return $addr; |
| 1826 | } |
| 1827 | |
| 1828 | /** |
| 1829 | * @param $str |
| 1830 | * |
| 1831 | * @return string |
| 1832 | */ |
| 1833 | public function parseSpan( $str ) { |
| 1834 | |
| 1835 | // |
| 1836 | // Take the string $str and parse it into tokens, hashing embeded HTML, |
| 1837 | // escaped characters and handling code spans. |
| 1838 | // |
| 1839 | $output = ''; |
| 1840 | |
| 1841 | $span_re = '{ |
| 1842 | ( |
| 1843 | \\\\' . $this->escape_chars_re . ' |
| 1844 | | |
| 1845 | (?<![`\\\\]) |
| 1846 | `+ # code span marker |
| 1847 | ' . ( $this->no_markup ? '' : ' |
| 1848 | | |
| 1849 | <!-- .*? --> # comment |
| 1850 | | |
| 1851 | <\?.*?\?> | <%.*?%> # processing instruction |
| 1852 | | |
| 1853 | <[!$]?[-a-zA-Z0-9:_]+ # regular tags |
| 1854 | (?> |
| 1855 | \s |
| 1856 | (?>[^"\'>]+|"[^"]*"|\'[^\']*\')* |
| 1857 | )? |
| 1858 | > |
| 1859 | | |
| 1860 | <[-a-zA-Z0-9:_]+\s*/> # xml-style empty tag |
| 1861 | | |
| 1862 | </[-a-zA-Z0-9:_]+\s*> # closing tag |
| 1863 | ' ) . ' |
| 1864 | ) |
| 1865 | }xs'; |
| 1866 | |
| 1867 | while ( 1 ) { |
| 1868 | // |
| 1869 | // Each loop iteration seach for either the next tag, the next |
| 1870 | // openning code span marker, or the next escaped character. |
| 1871 | // Each token is then passed to handleSpanToken. |
| 1872 | // |
| 1873 | $parts = preg_split( $span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE ); |
| 1874 | |
| 1875 | // Create token from text preceding tag. |
| 1876 | if ( $parts[0] != '' ) { |
| 1877 | $output .= $parts[0]; |
| 1878 | } |
| 1879 | |
| 1880 | // Check if we reach the end. |
| 1881 | if ( isset( $parts[1] ) ) { |
| 1882 | $output .= $this->handleSpanToken( $parts[1], $parts[2] ); |
| 1883 | $str = $parts[2]; |
| 1884 | } else { |
| 1885 | break; |
| 1886 | } |
| 1887 | }//end while |
| 1888 | |
| 1889 | return $output; |
| 1890 | } |
| 1891 | |
| 1892 | /** |
| 1893 | * @param $token |
| 1894 | * @param $str |
| 1895 | * |
| 1896 | * @return string |
| 1897 | */ |
| 1898 | public function handleSpanToken( $token, &$str ) { |
| 1899 | |
| 1900 | // |
| 1901 | // Handle $token provided by parseSpan by determining its nature and |
| 1902 | // returning the corresponding value that should replace it. |
| 1903 | // |
| 1904 | switch ( $token[0] ) { |
| 1905 | case '\\': |
| 1906 | return $this->hashPart( '&#' . ord( $token[1] ) . ';' ); |
| 1907 | case '`': |
| 1908 | // Search for end marker in remaining text. |
| 1909 | if ( preg_match( '/^(.*?[^`])' . preg_quote( $token ) . '(?!`)(.*)$/sm', $str, $matches ) ) { |
| 1910 | $str = $matches[2]; |
| 1911 | $codespan = $this->makeCodeSpan( $matches[1] ); |
| 1912 | |
| 1913 | return $this->hashPart( $codespan ); |
| 1914 | } |
| 1915 | |
| 1916 | return $token; |
| 1917 | // return as text since no ending marker found. |
| 1918 | default: |
| 1919 | return $this->hashPart( $token ); |
| 1920 | } |
| 1921 | } |
| 1922 | |
| 1923 | /** |
| 1924 | * @param $text |
| 1925 | * |
| 1926 | * @return mixed |
| 1927 | */ |
| 1928 | public function outdent( $text ) { |
| 1929 | |
| 1930 | // |
| 1931 | // Remove one level of line-leading tabs or spaces |
| 1932 | // |
| 1933 | return preg_replace( '/^(\t|[ ]{1,' . $this->tab_width . '})/m', '', $text ); |
| 1934 | } |
| 1935 | |
| 1936 | |
| 1937 | // String length function for detab. `_initDetab` will create a function to |
| 1938 | // hanlde UTF-8 if the default function does not exist. |
| 1939 | public $utf8_strlen = 'mb_strlen'; |
| 1940 | |
| 1941 | /** |
| 1942 | * @param $text |
| 1943 | * |
| 1944 | * @return mixed |
| 1945 | */ |
| 1946 | public function detab( $text ) { |
| 1947 | |
| 1948 | // |
| 1949 | // Replace tabs with the appropriate amount of space. |
| 1950 | // |
| 1951 | // For each line we separate the line in blocks delemited by |
| 1952 | // tab characters. Then we reconstruct every line by adding the |
| 1953 | // appropriate number of space between each blocks. |
| 1954 | $text = preg_replace_callback( '/^.*\t.*$/m', array( &$this, '_detab_callback' ), $text ); |
| 1955 | |
| 1956 | return $text; |
| 1957 | } |
| 1958 | |
| 1959 | /** |
| 1960 | * @param $matches |
| 1961 | * |
| 1962 | * @return string |
| 1963 | */ |
| 1964 | public function _detab_callback( $matches ) { |
| 1965 | |
| 1966 | $line = $matches[0]; |
| 1967 | $strlen = $this->utf8_strlen; |
| 1968 | // strlen function for UTF-8. |
| 1969 | // Split in blocks. |
| 1970 | $blocks = explode( "\t", $line ); |
| 1971 | // Add each blocks to the line. |
| 1972 | $line = $blocks[0]; |
| 1973 | unset( $blocks[0] ); |
| 1974 | // Do not add first block twice. |
| 1975 | foreach ( $blocks as $block ) { |
| 1976 | // Calculate amount of space, insert spaces, insert block. |
| 1977 | $amount = $this->tab_width - $strlen( $line, 'UTF-8' ) % $this->tab_width; |
| 1978 | $line .= str_repeat( ' ', $amount ) . $block; |
| 1979 | } |
| 1980 | |
| 1981 | return $line; |
| 1982 | } |
| 1983 | |
| 1984 | public function _initDetab() { |
| 1985 | |
| 1986 | // |
| 1987 | // Check for the availability of the function in the `utf8_strlen` property |
| 1988 | // (initially `mb_strlen`). If the function is not available, create a |
| 1989 | // function that will loosely count the number of UTF-8 characters with a |
| 1990 | // regular expression. |
| 1991 | // |
| 1992 | if ( function_exists( $this->utf8_strlen ) ) { |
| 1993 | return; |
| 1994 | } |
| 1995 | $this->utf8_strlen = create_function( '$text', 'return preg_match_all( |
| 1996 | "/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/", |
| 1997 | $text, $m);' ); |
| 1998 | } |
| 1999 | |
| 2000 | /** |
| 2001 | * @param $text |
| 2002 | * |
| 2003 | * @return mixed |
| 2004 | */ |
| 2005 | public function unhash( $text ) { |
| 2006 | |
| 2007 | // |
| 2008 | // Swap back in all the tags hashed by _HashHTMLBlocks. |
| 2009 | // |
| 2010 | return preg_replace_callback( '/(.)\x1A[0-9]+\1/', array( &$this, '_unhash_callback' ), $text ); |
| 2011 | } |
| 2012 | |
| 2013 | /** |
| 2014 | * @param $matches |
| 2015 | * |
| 2016 | * @return mixed |
| 2017 | */ |
| 2018 | public function _unhash_callback( $matches ) { |
| 2019 | |
| 2020 | return $this->html_hashes[ $matches[0] ]; |
| 2021 | } |
| 2022 | |
| 2023 | } |
| 2024 | |
| 2025 | /* |
| 2026 | PHP Markdown |
| 2027 | ============ |
| 2028 | |
| 2029 | Description |
| 2030 | ----------- |
| 2031 | |
| 2032 | This is a PHP translation of the original Markdown formatter written in |
| 2033 | Perl by John Gruber. |
| 2034 | |
| 2035 | Markdown is a text-to-HTML filter; it translates an easy-to-read / |
| 2036 | easy-to-write structured text format into HTML. Markdown's text format |
| 2037 | is mostly similar to that of plain text email, and supports features such |
| 2038 | as headers, *emphasis*, code blocks, blockquotes, and links. |
| 2039 | |
| 2040 | Markdown's syntax is designed not as a generic markup language, but |
| 2041 | specifically to serve as a front-end to (X)HTML. You can use span-level |
| 2042 | HTML tags anywhere in a Markdown document, and you can use block level |
| 2043 | HTML tags (like <div> and <table> as well). |
| 2044 | |
| 2045 | For more information about Markdown's syntax, see: |
| 2046 | |
| 2047 | <http://daringfireball.net/projects/markdown/> |
| 2048 | |
| 2049 | |
| 2050 | Bugs |
| 2051 | ---- |
| 2052 | |
| 2053 | To file bug reports please send email to: |
| 2054 | |
| 2055 | <michel.fortin@michelf.ca> |
| 2056 | |
| 2057 | Please include with your report: (1) the example input; (2) the output you |
| 2058 | expected; (3) the output Markdown actually produced. |
| 2059 | |
| 2060 | |
| 2061 | Version History |
| 2062 | --------------- |
| 2063 | |
| 2064 | See the readme file for detailed release notes for this version. |
| 2065 | |
| 2066 | |
| 2067 | Copyright and License |
| 2068 | --------------------- |
| 2069 | |
| 2070 | PHP Markdown |
| 2071 | Copyright (c) 2004-2013 Michel Fortin |
| 2072 | <http://michelf.ca/> |
| 2073 | All rights reserved. |
| 2074 | |
| 2075 | Based on Markdown |
| 2076 | Copyright (c) 2003-2006 John Gruber |
| 2077 | <http://daringfireball.net/> |
| 2078 | All rights reserved. |
| 2079 | |
| 2080 | Redistribution and use in source and binary forms, with or without |
| 2081 | modification, are permitted provided that the following conditions are |
| 2082 | met: |
| 2083 | |
| 2084 | * Redistributions of source code must retain the above copyright notice, |
| 2085 | this list of conditions and the following disclaimer. |
| 2086 | |
| 2087 | * Redistributions in binary form must reproduce the above copyright |
| 2088 | notice, this list of conditions and the following disclaimer in the |
| 2089 | documentation and/or other materials provided with the distribution. |
| 2090 | |
| 2091 | * Neither the name "Markdown" nor the names of its contributors may |
| 2092 | be used to endorse or promote products derived from this software |
| 2093 | without specific prior written permission. |
| 2094 | |
| 2095 | This software is provided by the copyright holders and contributors "as |
| 2096 | is" and any express or implied warranties, including, but not limited |
| 2097 | to, the implied warranties of merchantability and fitness for a |
| 2098 | particular purpose are disclaimed. In no event shall the copyright owner |
| 2099 | or contributors be liable for any direct, indirect, incidental, special, |
| 2100 | exemplary, or consequential damages (including, but not limited to, |
| 2101 | procurement of substitute goods or services; loss of use, data, or |
| 2102 | profits; or business interruption) however caused and on any theory of |
| 2103 | liability, whether in contract, strict liability, or tort (including |
| 2104 | negligence or otherwise) arising in any way out of the use of this |
| 2105 | software, even if advised of the possibility of such damage. |
| 2106 | |
| 2107 | */ |
| 2108 | endif; |
| 2109 |