commit 8df6921b7d536c3f4dc02eb4c0274d445fdb7318
parent a94fac99eb926069908c6822ab8d28e75e7888bd
Author: markseu <mark2011@mayberg.se>
Date: Wed, 14 Dec 2016 12:03:29 +0100
System update (latest Markdown)
Diffstat:
1 file changed, 1429 insertions(+), 981 deletions(-)
diff --git a/system/plugins/markdown.php b/system/plugins/markdown.php
@@ -5,7 +5,7 @@
// Markdown plugin
class YellowMarkdown
{
- const VERSION = "0.6.3";
+ const VERSION = "0.6.4";
var $yellow; //access to API
// Handle initialisation
@@ -169,8 +169,8 @@ class YellowMarkdownParser extends MarkdownExtraParser
}
}
-// PHP Markdown
-// Copyright (c) 2004-2015 Michel Fortin
+// PHP Markdown Lib
+// Copyright (c) 2004-2016 Michel Fortin
// <https://michelf.ca/projects/php-markdown/>
//
// Original Markdown
@@ -205,88 +205,145 @@ class YellowMarkdownParser extends MarkdownExtraParser
// software, even if advised of the possibility of such damage.
class MarkdownParser {
-
- ### Version ###
-
- const MARKDOWNLIB_VERSION = "1.6.0";
-
- ### Simple Function Interface ###
-
+ /**
+ * Define the package version
+ * @var string
+ */
+ const MARKDOWNLIB_VERSION = "1.7.0";
+
+ /**
+ * Simple function interface - Initialize the parser and return the result
+ * of its transform method. This will work fine for derived classes too.
+ *
+ * @api
+ *
+ * @param string $text
+ * @return string
+ */
public static function defaultTransform($text) {
- #
- # Initialize the parser and return the result of its transform method.
- # This will work fine for derived classes too.
- #
- # Take parser class on which this function was called.
+ // Take parser class on which this function was called.
$parser_class = \get_called_class();
- # try to take parser from the static parser list
+ // Try to take parser from the static parser list
static $parser_list;
$parser =& $parser_list[$parser_class];
- # create the parser it not already set
- if (!$parser)
+ // Create the parser it not already set
+ if (!$parser) {
$parser = new $parser_class;
+ }
- # Transform text using parser.
+ // Transform text using parser.
return $parser->transform($text);
}
- ### Configuration Variables ###
+ /**
+ * Configuration variables
+ */
- # Change to ">" for HTML output.
+ /**
+ * Change to ">" for HTML output.
+ * @var string
+ */
public $empty_element_suffix = " />";
+
+ /**
+ * The width of indentation of the output markup
+ * @var int
+ */
public $tab_width = 4;
- # Change to `true` to disallow markup or entities.
- public $no_markup = false;
+ /**
+ * Change to `true` to disallow markup or entities.
+ * @var boolean
+ */
+ public $no_markup = false;
public $no_entities = false;
- # Predefined urls and titles for reference links and images.
- public $predef_urls = array();
+
+ /**
+ * Change to `true` to enable line breaks on \n without two trailling spaces
+ * @var boolean
+ */
+ public $hard_wrap = false;
+
+ /**
+ * Predefined URLs and titles for reference links and images.
+ * @var array
+ */
+ public $predef_urls = array();
public $predef_titles = array();
- # Optional filter function for URLs
+ /**
+ * Optional filter function for URLs
+ * @var callable
+ */
public $url_filter_func = null;
- # Optional header id="" generation callback function.
+ /**
+ * Optional header id="" generation callback function.
+ * @var callable
+ */
public $header_id_func = null;
- # Optional function for converting code block content to HTML
+ /**
+ * Optional function for converting code block content to HTML
+ * @var callable
+ */
public $code_block_content_func = null;
- # Class attribute to toggle "enhanced ordered list" behaviour
- # setting this to true will allow ordered lists to start from the index
- # number that is defined first. For example:
- # 2. List item two
- # 3. List item three
- #
- # becomes
- # <ol start="2">
- # <li>List item two</li>
- # <li>List item three</li>
- # </ol>
+ /**
+ * Optional function for converting code span content to HTML.
+ * @var callable
+ */
+ public $code_span_content_func = null;
+
+ /**
+ * Class attribute to toggle "enhanced ordered list" behaviour
+ * setting this to true will allow ordered lists to start from the index
+ * number that is defined first.
+ *
+ * For example:
+ * 2. List item two
+ * 3. List item three
+ *
+ * Becomes:
+ * <ol start="2">
+ * <li>List item two</li>
+ * <li>List item three</li>
+ * </ol>
+ *
+ * @var bool
+ */
public $enhanced_ordered_list = false;
- ### Parser Implementation ###
+ /**
+ * Parser implementation
+ */
- # Regex to match balanced [brackets].
- # Needed to insert a maximum bracked depth while converting to PHP.
+ /**
+ * Regex to match balanced [brackets].
+ * Needed to insert a maximum bracked depth while converting to PHP.
+ * @var int
+ */
protected $nested_brackets_depth = 6;
protected $nested_brackets_re;
-
+
protected $nested_url_parenthesis_depth = 4;
protected $nested_url_parenthesis_re;
- # Table of hash values for escaped characters:
+ /**
+ * Table of hash values for escaped characters:
+ * @var string
+ */
protected $escape_chars = '\`*_{}[]()>#+-.!';
protected $escape_chars_re;
-
+ /**
+ * Constructor function. Initialize appropriate member variables.
+ * @return void
+ */
public function __construct() {
- #
- # Constructor function. Initialize appropriate member variables.
- #
$this->_initDetab();
$this->prepareItalicsAndBold();
@@ -300,51 +357,60 @@ class MarkdownParser {
$this->escape_chars_re = '['.preg_quote($this->escape_chars).']';
- # Sort document, block, and span gamut in ascendent priority order.
+ // Sort document, block, and span gamut in ascendent priority order.
asort($this->document_gamut);
asort($this->block_gamut);
asort($this->span_gamut);
}
- # Internal hashes used during transformation.
- protected $urls = array();
- protected $titles = array();
+ /**
+ * Internal hashes used during transformation.
+ * @var array
+ */
+ protected $urls = array();
+ protected $titles = array();
protected $html_hashes = array();
- # Status flag to avoid invalid nesting.
+ /**
+ * Status flag to avoid invalid nesting.
+ * @var boolean
+ */
protected $in_anchor = false;
-
+ /**
+ * Called before the transformation process starts to setup parser states.
+ * @return void
+ */
protected function setup() {
- #
- # Called before the transformation process starts to setup parser
- # states.
- #
- # Clear global hashes.
- $this->urls = $this->predef_urls;
- $this->titles = $this->predef_titles;
+ // Clear global hashes.
+ $this->urls = $this->predef_urls;
+ $this->titles = $this->predef_titles;
$this->html_hashes = array();
-
- $this->in_anchor = false;
+ $this->in_anchor = false;
}
+ /**
+ * Called after the transformation process to clear any variable which may
+ * be taking up memory unnecessarly.
+ * @return void
+ */
protected function teardown() {
- #
- # Called after the transformation process to clear any variable
- # which may be taking up memory unnecessarly.
- #
- $this->urls = array();
- $this->titles = array();
+ $this->urls = array();
+ $this->titles = array();
$this->html_hashes = array();
}
-
+ /**
+ * Main function. Performs some preprocessing on the input text and pass
+ * it through the document gamut.
+ *
+ * @api
+ *
+ * @param string $text
+ * @return string
+ */
public function transform($text) {
- #
- # Main function. Performs some preprocessing on the input text
- # and pass it through the document gamut.
- #
$this->setup();
# Remove UTF-8 BOM and marker character in input, if present.
@@ -378,23 +444,28 @@ class MarkdownParser {
return $text . "\n";
}
-
+
+ /**
+ * Define the document gamut
+ * @var array
+ */
protected $document_gamut = array(
- # Strip link definitions, store in hashes.
+ // Strip link definitions, store in hashes.
"stripLinkDefinitions" => 20,
-
"runBasicBlockGamut" => 30,
- );
-
-
+ );
+
+ /**
+ * Strips link definitions from text, stores the URLs and titles in
+ * hash references
+ * @param string $text
+ * @return string
+ */
protected function stripLinkDefinitions($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
+
$less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: ^[id]: url "optional title"
+ // Link defs are in the form: ^[id]: url "optional title"
$text = preg_replace_callback('{
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
[ ]*
@@ -418,43 +489,58 @@ class MarkdownParser {
(?:\n+|\Z)
}xm',
array($this, '_stripLinkDefinitions_callback'),
- $text);
+ $text
+ );
return $text;
}
+
+ /**
+ * The callback to strip link definitions
+ * @param array $matches
+ * @return string
+ */
protected function _stripLinkDefinitions_callback($matches) {
$link_id = strtolower($matches[1]);
$url = $matches[2] == '' ? $matches[3] : $matches[2];
$this->urls[$link_id] = $url;
$this->titles[$link_id] =& $matches[4];
- return ''; # String that will replace the block
+ return ''; // String that will replace the block
}
-
+ /**
+ * Hashify HTML blocks
+ * @param string $text
+ * @return string
+ */
protected function hashHTMLBlocks($text) {
- if ($this->no_markup) return $text;
+ if ($this->no_markup) {
+ return $text;
+ }
$less_than_tab = $this->tab_width - 1;
- # Hashify HTML blocks:
- # We only want to do this for block-level HTML tags, such as headers,
- # lists, and tables. That's because we still want to wrap <p>s around
- # "paragraphs" that are wrapped in non-block-level tags, such as anchors,
- # phrase emphasis, and spans. The list of tags we're looking for is
- # hard-coded:
- #
- # * List "a" is made of tags which can be both inline or block-level.
- # These will be treated block-level when the start tag is alone on
- # its line, otherwise they're not matched here and will be taken as
- # inline later.
- # * List "b" is made of tags which are always block-level;
- #
+ /**
+ * Hashify HTML blocks:
+ *
+ * We only want to do this for block-level HTML tags, such as headers,
+ * lists, and tables. That's because we still want to wrap <p>s around
+ * "paragraphs" that are wrapped in non-block-level tags, such as
+ * anchors, phrase emphasis, and spans. The list of tags we're looking
+ * for is hard-coded:
+ *
+ * * List "a" is made of tags which can be both inline or block-level.
+ * These will be treated block-level when the start tag is alone on
+ * its line, otherwise they're not matched here and will be taken as
+ * inline later.
+ * * List "b" is made of tags which are always block-level;
+ */
$block_tags_a_re = 'ins|del';
$block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'.
'script|noscript|style|form|fieldset|iframe|math|svg|'.
'article|section|nav|aside|hgroup|header|footer|'.
'figure';
- # Regular expression for the content of a block tag.
+ // Regular expression for the content of a block tag.
$nested_tags_level = 4;
$attr = '
(?> # optional tag attributes
@@ -480,8 +566,8 @@ class MarkdownParser {
(?>
/>
|
- >', $nested_tags_level). # end of opening tag
- '.*?'. # last level nested tag content
+ >', $nested_tags_level). // end of opening tag
+ '.*?'. // last level nested tag content
str_repeat('
</\2\s*> # closing nested tag
)
@@ -492,17 +578,20 @@ class MarkdownParser {
$nested_tags_level);
$content2 = str_replace('\2', '\3', $content);
- # First, look for nested blocks, e.g.:
- # <div>
- # <div>
- # tags for inner block must be indented.
- # </div>
- # </div>
- #
- # The outermost tags must start at the left margin for this to match, and
- # the inner nested divs must be indented.
- # We need to do this before the next, more liberal match, because the next
- # match will start at the first `<div>` and stop at the first `</div>`.
+ /**
+ * First, look for nested blocks, e.g.:
+ * <div>
+ * <div>
+ * tags for inner block must be indented.
+ * </div>
+ * </div>
+ *
+ * The outermost tags must start at the left margin for this to match,
+ * and the inner nested divs must be indented.
+ * We need to do this before the next, more liberal match, because the
+ * next match will start at the first `<div>` and stop at the
+ * first `</div>`.
+ */
$text = preg_replace_callback('{(?>
(?>
(?<=\n) # Starting on its own line
@@ -565,94 +654,114 @@ class MarkdownParser {
)
)}Sxmi',
array($this, '_hashHTMLBlocks_callback'),
- $text);
+ $text
+ );
return $text;
}
+
+ /**
+ * The callback for hashing HTML blocks
+ * @param string $matches
+ * @return string
+ */
protected function _hashHTMLBlocks_callback($matches) {
$text = $matches[1];
$key = $this->hashBlock($text);
return "\n\n$key\n\n";
}
-
+ /**
+ * Called whenever a tag must be hashed when a function insert an atomic
+ * element in the text stream. Passing $text to through this function gives
+ * a unique text-token which will be reverted back when calling unhash.
+ *
+ * The $boundary argument specify what character should be used to surround
+ * the token. By convension, "B" is used for block elements that needs not
+ * to be wrapped into paragraph tags at the end, ":" is used for elements
+ * that are word separators and "X" is used in the general case.
+ *
+ * @param string $text
+ * @param string $boundary
+ * @return string
+ */
protected function hashPart($text, $boundary = 'X') {
- #
- # Called whenever a tag must be hashed when a function insert an atomic
- # element in the text stream. Passing $text to through this function gives
- # a unique text-token which will be reverted back when calling unhash.
- #
- # The $boundary argument specify what character should be used to surround
- # the token. By convension, "B" is used for block elements that needs not
- # to be wrapped into paragraph tags at the end, ":" is used for elements
- # that are word separators and "X" is used in the general case.
- #
- # Swap back any tag hash found in $text so we do not have to `unhash`
- # multiple times at the end.
+ // Swap back any tag hash found in $text so we do not have to `unhash`
+ // multiple times at the end.
$text = $this->unhash($text);
- # Then hash the block.
+ // Then hash the block.
static $i = 0;
$key = "$boundary\x1A" . ++$i . $boundary;
$this->html_hashes[$key] = $text;
- return $key; # String that will replace the tag.
+ return $key; // String that will replace the tag.
}
-
+ /**
+ * Shortcut function for hashPart with block-level boundaries.
+ * @param string $text
+ * @return string
+ */
protected function hashBlock($text) {
- #
- # Shortcut function for hashPart with block-level boundaries.
- #
return $this->hashPart($text, 'B');
}
-
+ /**
+ * Define the block gamut - these are all the transformations that form
+ * block-level tags like paragraphs, headers, and list items.
+ * @var array
+ */
protected $block_gamut = array(
- #
- # These are all the transformations that form block-level
- # tags like paragraphs, headers, and list items.
- #
"doHeaders" => 10,
"doHorizontalRules" => 20,
-
"doLists" => 40,
"doCodeBlocks" => 50,
"doBlockQuotes" => 60,
- );
-
+ );
+
+ /**
+ * Run block gamut tranformations.
+ *
+ * We need to escape raw HTML in Markdown source before doing anything
+ * else. This need to be done for each block, and not only at the
+ * begining in the Markdown function since hashed blocks can be part of
+ * list items and could have been indented. Indented blocks would have
+ * been seen as a code block in a previous pass of hashHTMLBlocks.
+ *
+ * @param string $text
+ * @return string
+ */
protected function runBlockGamut($text) {
- #
- # Run block gamut tranformations.
- #
- # We need to escape raw HTML in Markdown source before doing anything
- # else. This need to be done for each block, and not only at the
- # begining in the Markdown function since hashed blocks can be part of
- # list items and could have been indented. Indented blocks would have
- # been seen as a code block in a previous pass of hashHTMLBlocks.
$text = $this->hashHTMLBlocks($text);
-
return $this->runBasicBlockGamut($text);
}
-
+
+ /**
+ * Run block gamut tranformations, without hashing HTML blocks. This is
+ * useful when HTML blocks are known to be already hashed, like in the first
+ * whole-document pass.
+ *
+ * @param string $text
+ * @return string
+ */
protected function runBasicBlockGamut($text) {
- #
- # Run block gamut tranformations, without hashing HTML blocks. This is
- # useful when HTML blocks are known to be already hashed, like in the first
- # whole-document pass.
- #
+
foreach ($this->block_gamut as $method => $priority) {
$text = $this->$method($text);
}
- # Finally form paragraph and restore hashed blocks.
+ // Finally form paragraph and restore hashed blocks.
$text = $this->formParagraphs($text);
return $text;
}
-
-
+
+ /**
+ * Convert horizontal rules
+ * @param string $text
+ * @return string
+ */
protected function doHorizontalRules($text) {
- # Do Horizontal Rules:
return preg_replace(
'{
^[ ]{0,3} # Leading space
@@ -665,66 +774,81 @@ class MarkdownParser {
$ # End of line.
}mx',
"\n".$this->hashBlock("<hr$this->empty_element_suffix")."\n",
- $text);
+ $text
+ );
}
-
+ /**
+ * These are all the transformations that occur *within* block-level
+ * tags like paragraphs, headers, and list items.
+ * @var array
+ */
protected $span_gamut = array(
- #
- # These are all the transformations that occur *within* block-level
- # tags like paragraphs, headers, and list items.
- #
- # Process character escapes, code spans, and inline HTML
- # in one shot.
+ // Process character escapes, code spans, and inline HTML
+ // in one shot.
"parseSpan" => -30,
-
- # Process anchor and image tags. Images must come first,
- # because ![foo][f] looks like an anchor.
+ // Process anchor and image tags. Images must come first,
+ // because ![foo][f] looks like an anchor.
"doImages" => 10,
"doAnchors" => 20,
-
- # Make links out of things like `<https://example.com/>`
- # Must come after doAnchors, because you can use < and >
- # delimiters in inline links like [this](<url>).
+ // Make links out of things like `<https://example.com/>`
+ // Must come after doAnchors, because you can use < and >
+ // delimiters in inline links like [this](<url>).
"doAutoLinks" => 30,
"encodeAmpsAndAngles" => 40,
-
"doItalicsAndBold" => 50,
"doHardBreaks" => 60,
- );
+ );
+ /**
+ * Run span gamut transformations
+ * @param string $text
+ * @return string
+ */
protected function runSpanGamut($text) {
- #
- # Run span gamut tranformations.
- #
foreach ($this->span_gamut as $method => $priority) {
$text = $this->$method($text);
}
return $text;
}
-
-
+
+ /**
+ * Do hard breaks
+ * @param string $text
+ * @return string
+ */
protected function doHardBreaks($text) {
- # Do hard breaks:
- return preg_replace_callback('/ {2,}\n/',
- array($this, '_doHardBreaks_callback'), $text);
+ if ($this->hard_wrap) {
+ return preg_replace_callback('/ *\n/',
+ array($this, '_doHardBreaks_callback'), $text);
+ } else {
+ return preg_replace_callback('/ {2,}\n/',
+ array($this, '_doHardBreaks_callback'), $text);
+ }
}
+
+ /**
+ * Trigger part hashing for the hard break (callback method)
+ * @param array $matches
+ * @return string
+ */
protected function _doHardBreaks_callback($matches) {
return $this->hashPart("<br$this->empty_element_suffix\n");
}
-
+ /**
+ * Turn Markdown link shortcuts into XHTML <a> tags.
+ * @param string $text
+ * @return string
+ */
protected function doAnchors($text) {
- #
- # Turn Markdown link shortcuts into XHTML <a> tags.
- #
- if ($this->in_anchor) return $text;
+ if ($this->in_anchor) {
+ return $text;
+ }
$this->in_anchor = true;
- #
- # First, handle reference-style links: [link text] [id]
- #
+ // First, handle reference-style links: [link text] [id]
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
@@ -741,9 +865,7 @@ class MarkdownParser {
}xs',
array($this, '_doAnchors_reference_callback'), $text);
- #
- # Next, inline-style links: [link text](url "optional title")
- #
+ // Next, inline-style links: [link text](url "optional title")
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
@@ -768,11 +890,9 @@ class MarkdownParser {
}xs',
array($this, '_doAnchors_inline_callback'), $text);
- #
- # Last, handle reference-style shortcuts: [link text]
- # These must come last in case you've also got [link text][1]
- # or [link text](/foo)
- #
+ // Last, handle reference-style shortcuts: [link text]
+ // These must come last in case you've also got [link text][1]
+ // or [link text](/foo)
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
@@ -785,17 +905,23 @@ class MarkdownParser {
$this->in_anchor = false;
return $text;
}
+
+ /**
+ * Callback method to parse referenced anchors
+ * @param string $matches
+ * @return string
+ */
protected function _doAnchors_reference_callback($matches) {
$whole_match = $matches[1];
$link_text = $matches[2];
$link_id =& $matches[3];
if ($link_id == "") {
- # for shortcut links like [this][] or [this].
+ // for shortcut links like [this][] or [this].
$link_id = $link_text;
}
- # lower-case and turn embedded newlines into spaces
+ // lower-case and turn embedded newlines into spaces
$link_id = strtolower($link_id);
$link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
@@ -813,20 +939,26 @@ class MarkdownParser {
$link_text = $this->runSpanGamut($link_text);
$result .= ">$link_text</a>";
$result = $this->hashPart($result);
- }
- else {
+ } else {
$result = $whole_match;
}
return $result;
}
+
+ /**
+ * Callback method to parse inline anchors
+ * @param string $matches
+ * @return string
+ */
protected function _doAnchors_inline_callback($matches) {
$whole_match = $matches[1];
$link_text = $this->runSpanGamut($matches[2]);
$url = $matches[3] == '' ? $matches[4] : $matches[3];
$title =& $matches[7];
- // if the URL was of the form <s p a c e s> it got caught by the HTML
- // tag parser and hashed. Need to reverse the process before using the URL.
+ // If the URL was of the form <s p a c e s> it got caught by the HTML
+ // tag parser and hashed. Need to reverse the process before using
+ // the URL.
$unhashed = $this->unhash($url);
if ($unhashed != $url)
$url = preg_replace('/^<(.*)>$/', '\1', $unhashed);
@@ -845,14 +977,13 @@ class MarkdownParser {
return $this->hashPart($result);
}
-
+ /**
+ * Turn Markdown image shortcuts into <img> tags.
+ * @param string $text
+ * @return string
+ */
protected function doImages($text) {
- #
- # Turn Markdown image shortcuts into <img> tags.
- #
- #
- # First, handle reference-style labeled images: ![alt text][id]
- #
+ // First, handle reference-style labeled images: ![alt text][id]
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
@@ -870,10 +1001,8 @@ class MarkdownParser {
}xs',
array($this, '_doImages_reference_callback'), $text);
- #
- # Next, handle inline images: 
- # Don't forget: encode * and _
- #
+ // Next, handle inline images: 
+ // Don't forget: encode * and _
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
@@ -901,13 +1030,19 @@ class MarkdownParser {
return $text;
}
+
+ /**
+ * Callback to parse references image tags
+ * @param array $matches
+ * @return string
+ */
protected function _doImages_reference_callback($matches) {
$whole_match = $matches[1];
$alt_text = $matches[2];
$link_id = strtolower($matches[3]);
if ($link_id == "") {
- $link_id = strtolower($alt_text); # for shortcut links like ![this][].
+ $link_id = strtolower($alt_text); // for shortcut links like ![this][].
}
$alt_text = $this->encodeAttribute($alt_text);
@@ -921,14 +1056,19 @@ class MarkdownParser {
}
$result .= $this->empty_element_suffix;
$result = $this->hashPart($result);
- }
- else {
- # If there's no such link ID, leave intact:
+ } else {
+ // If there's no such link ID, leave intact:
$result = $whole_match;
}
return $result;
}
+
+ /**
+ * Callback to parse inline image tags
+ * @param array $matches
+ * @return string
+ */
protected function _doImages_inline_callback($matches) {
$whole_match = $matches[1];
$alt_text = $matches[2];
@@ -940,32 +1080,38 @@ class MarkdownParser {
$result = "<img src=\"$url\" alt=\"$alt_text\"";
if (isset($title)) {
$title = $this->encodeAttribute($title);
- $result .= " title=\"$title\""; # $title already quoted
+ $result .= " title=\"$title\""; // $title already quoted
}
$result .= $this->empty_element_suffix;
return $this->hashPart($result);
}
-
+ /**
+ * Parse Markdown heading elements to HTML
+ * @param string $text
+ * @return string
+ */
protected function doHeaders($text) {
- # Setext-style headers:
- # Header 1
- # ========
- #
- # Header 2
- # --------
- #
+ /**
+ * Setext-style headers:
+ * Header 1
+ * ========
+ *
+ * Header 2
+ * --------
+ */
$text = preg_replace_callback('{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx',
array($this, '_doHeaders_callback_setext'), $text);
- # atx-style headers:
- # # Header 1
- # ## Header 2
- # ## Header 2 with closing hashes ##
- # ...
- # ###### Header 6
- #
+ /**
+ * atx-style headers:
+ * # Header 1
+ * ## Header 2
+ * ## Header 2 with closing hashes ##
+ * ...
+ * ###### Header 6
+ */
$text = preg_replace_callback('{
^(\#{1,6}) # $1 = string of #\'s
[ ]*
@@ -979,22 +1125,33 @@ class MarkdownParser {
return $text;
}
+ /**
+ * Setext header parsing callback
+ * @param array $matches
+ * @return string
+ */
protected function _doHeaders_callback_setext($matches) {
- # Terrible hack to check we haven't found an empty list item.
- if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1]))
+ // Terrible hack to check we haven't found an empty list item.
+ if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1])) {
return $matches[0];
+ }
$level = $matches[2]{0} == '=' ? 1 : 2;
- # id attribute generation
+ // ID attribute generation
$idAtt = $this->_generateIdFromHeaderValue($matches[1]);
$block = "<h$level$idAtt>".$this->runSpanGamut($matches[1])."</h$level>";
return "\n" . $this->hashBlock($block) . "\n\n";
}
- protected function _doHeaders_callback_atx($matches) {
- # id attribute generation
+ /**
+ * ATX header parsing callback
+ * @param array $matches
+ * @return string
+ */
+ protected function _doHeaders_callback_atx($matches) {
+ // ID attribute generation
$idAtt = $this->_generateIdFromHeaderValue($matches[2]);
$level = strlen($matches[1]);
@@ -1002,30 +1159,37 @@ class MarkdownParser {
return "\n" . $this->hashBlock($block) . "\n\n";
}
- protected function _generateIdFromHeaderValue($headerValue) {
-
- # if a header_id_func property is set, we can use it to automatically
- # generate an id attribute.
- #
- # This method returns a string in the form id="foo", or an empty string
- # otherwise.
+ /**
+ * If a header_id_func property is set, we can use it to automatically
+ * generate an id attribute.
+ *
+ * This method returns a string in the form id="foo", or an empty string
+ * otherwise.
+ * @param string $headerValue
+ * @return string
+ */
+ protected function _generateIdFromHeaderValue($headerValue) {
if (!is_callable($this->header_id_func)) {
return "";
}
+
$idValue = call_user_func($this->header_id_func, $headerValue);
- if (!$idValue) return "";
+ if (!$idValue) {
+ return "";
+ }
return ' id="' . $this->encodeAttribute($idValue) . '"';
-
}
+ /**
+ * Form HTML ordered (numbered) and unordered (bulleted) lists.
+ * @param string $text
+ * @return string
+ */
protected function doLists($text) {
- #
- # Form HTML ordered (numbered) and unordered (bulleted) lists.
- #
$less_than_tab = $this->tab_width - 1;
- # Re-usable patterns to match list item bullets and number markers:
+ // Re-usable patterns to match list item bullets and number markers:
$marker_ul_re = '[*+-]';
$marker_ol_re = '\d+[\.]';
@@ -1035,7 +1199,7 @@ class MarkdownParser {
);
foreach ($markers_relist as $marker_re => $other_marker_re) {
- # Re-usable pattern to match any entirel ul or ol list:
+ // Re-usable pattern to match any entirel ul or ol list:
$whole_list_re = '
( # $1 = whole list
( # $2
@@ -1063,8 +1227,8 @@ class MarkdownParser {
)
'; // mx
- # We use a different prefix before nested lists than top-level lists.
- # See extended comment in _ProcessListItems().
+ // We use a different prefix before nested lists than top-level lists.
+ //See extended comment in _ProcessListItems().
if ($this->list_level) {
$text = preg_replace_callback('{
@@ -1072,8 +1236,7 @@ class MarkdownParser {
'.$whole_list_re.'
}mx',
array($this, '_doLists_callback'), $text);
- }
- else {
+ } else {
$text = preg_replace_callback('{
(?:(?<=\n)\n|\A\n?) # Must eat the newline
'.$whole_list_re.'
@@ -1084,8 +1247,14 @@ class MarkdownParser {
return $text;
}
+
+ /**
+ * List parsing callback
+ * @param array $matches
+ * @return string
+ */
protected function _doLists_callback($matches) {
- # Re-usable patterns to match list item bullets and number markers:
+ // Re-usable patterns to match list item bullets and number markers:
$marker_ul_re = '[*+-]';
$marker_ol_re = '\d+[\.]';
$marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
@@ -1101,7 +1270,7 @@ class MarkdownParser {
$ol_start = 1;
if ($this->enhanced_ordered_list) {
- # Get the start number for ordered list.
+ // Get the start number for ordered list.
if ($list_type == 'ol') {
$ol_start_array = array();
$ol_start_check = preg_match("/$marker_ol_start_re/", $matches[4], $ol_start_array);
@@ -1119,37 +1288,45 @@ class MarkdownParser {
return "\n". $result ."\n\n";
}
+ /**
+ * Nesting tracker for list levels
+ * @var integer
+ */
protected $list_level = 0;
+ /**
+ * Process the contents of a single ordered or unordered list, splitting it
+ * into individual list items.
+ * @param string $list_str
+ * @param string $marker_any_re
+ * @return string
+ */
protected function processListItems($list_str, $marker_any_re) {
- #
- # Process the contents of a single ordered or unordered list, splitting it
- # into individual list items.
- #
- # The $this->list_level global keeps track of when we're inside a list.
- # Each time we enter a list, we increment it; when we leave a list,
- # we decrement. If it's zero, we're not in a list anymore.
- #
- # We do this because when we're not inside a list, we want to treat
- # something like this:
- #
- # I recommend upgrading to version
- # 8. Oops, now this line is treated
- # as a sub-list.
- #
- # As a single paragraph, despite the fact that the second line starts
- # with a digit-period-space sequence.
- #
- # Whereas when we're inside a list (or sub-list), that line will be
- # treated as the start of a sub-list. What a kludge, huh? This is
- # an aspect of Markdown's syntax that's hard to parse perfectly
- # without resorting to mind-reading. Perhaps the solution is to
- # change the syntax rules such that sub-lists must start with a
- # starting cardinal number; e.g. "1." or "a.".
-
+ /**
+ * The $this->list_level global keeps track of when we're inside a list.
+ * Each time we enter a list, we increment it; when we leave a list,
+ * we decrement. If it's zero, we're not in a list anymore.
+ *
+ * We do this because when we're not inside a list, we want to treat
+ * something like this:
+ *
+ * I recommend upgrading to version
+ * 8. Oops, now this line is treated
+ * as a sub-list.
+ *
+ * As a single paragraph, despite the fact that the second line starts
+ * with a digit-period-space sequence.
+ *
+ * Whereas when we're inside a list (or sub-list), that line will be
+ * treated as the start of a sub-list. What a kludge, huh? This is
+ * an aspect of Markdown's syntax that's hard to parse perfectly
+ * without resorting to mind-reading. Perhaps the solution is to
+ * change the syntax rules such that sub-lists must start with a
+ * starting cardinal number; e.g. "1." or "a.".
+ */
$this->list_level++;
- # trim trailing blank lines:
+ // Trim trailing blank lines:
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
$list_str = preg_replace_callback('{
@@ -1167,6 +1344,12 @@ class MarkdownParser {
$this->list_level--;
return $list_str;
}
+
+ /**
+ * List item parsing callback
+ * @param array $matches
+ * @return string
+ */
protected function _processListItems_callback($matches) {
$item = $matches[4];
$leading_line =& $matches[1];
@@ -1177,25 +1360,24 @@ class MarkdownParser {
if ($leading_line || $tailing_blank_line ||
preg_match('/\n{2,}/', $item))
{
- # Replace marker with the appropriate whitespace indentation
+ // Replace marker with the appropriate whitespace indentation
$item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item;
$item = $this->runBlockGamut($this->outdent($item)."\n");
- }
- else {
- # Recursion for sub-lists:
+ } else {
+ // Recursion for sub-lists:
$item = $this->doLists($this->outdent($item));
- $item = preg_replace('/\n+$/', '', $item);
- $item = $this->runSpanGamut($item);
+ $item = $this->formParagraphs($item, false);
}
return "<li>" . $item . "</li>\n";
}
-
+ /**
+ * Process Markdown `<pre><code>` blocks.
+ * @param string $text
+ * @return string
+ */
protected function doCodeBlocks($text) {
- #
- # Process Markdown `<pre><code>` blocks.
- #
$text = preg_replace_callback('{
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
@@ -1210,6 +1392,12 @@ class MarkdownParser {
return $text;
}
+
+ /**
+ * Code block parsing callback
+ * @param array $matches
+ * @return string
+ */
protected function _doCodeBlocks_callback($matches) {
$codeblock = $matches[1];
@@ -1224,44 +1412,68 @@ class MarkdownParser {
$codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock);
$codeblock = "<pre><code>$codeblock\n</code></pre>";
- return "\n\n".$this->hashBlock($codeblock)."\n\n";
+ return "\n\n" . $this->hashBlock($codeblock) . "\n\n";
}
-
+ /**
+ * Create a code span markup for $code. Called from handleSpanToken.
+ * @param string $code
+ * @return string
+ */
protected function makeCodeSpan($code) {
- #
- # Create a code span markup for $code. Called from handleSpanToken.
- #
- $code = htmlspecialchars(trim($code), ENT_NOQUOTES);
+ if ($this->code_span_content_func) {
+ $code = call_user_func($this->code_span_content_func, $code);
+ } else {
+ $code = htmlspecialchars(trim($code), ENT_NOQUOTES);
+ }
return $this->hashPart("<code>$code</code>");
}
-
+ /**
+ * Define the emphasis operators with their regex matches
+ * @var array
+ */
protected $em_relist = array(
'' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?![\.,:;]?\s)',
'*' => '(?<![\s*])\*(?!\*)',
'_' => '(?<![\s_])_(?!_)',
- );
+ );
+
+ /**
+ * Define the strong operators with their regex matches
+ * @var array
+ */
protected $strong_relist = array(
'' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?![\.,:;]?\s)',
'**' => '(?<![\s*])\*\*(?!\*)',
'__' => '(?<![\s_])__(?!_)',
- );
+ );
+
+ /**
+ * Define the emphasis + strong operators with their regex matches
+ * @var array
+ */
protected $em_strong_relist = array(
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?![\.,:;]?\s)',
'***' => '(?<![\s*])\*\*\*(?!\*)',
'___' => '(?<![\s_])___(?!_)',
- );
+ );
+
+ /**
+ * Container for prepared regular expressions
+ * @var array
+ */
protected $em_strong_prepared_relist;
+ /**
+ * Prepare regular expressions for searching emphasis tokens in any
+ * context.
+ * @return void
+ */
protected function prepareItalicsAndBold() {
- #
- # Prepare regular expressions for searching emphasis tokens in any
- # context.
- #
foreach ($this->em_relist as $em => $em_re) {
foreach ($this->strong_relist as $strong => $strong_re) {
- # Construct list of allowed token expressions.
+ // Construct list of allowed token expressions.
$token_relist = array();
if (isset($this->em_strong_relist["$em$strong"])) {
$token_relist[] = $this->em_strong_relist["$em$strong"];
@@ -1269,13 +1481,18 @@ class MarkdownParser {
$token_relist[] = $em_re;
$token_relist[] = $strong_re;
- # Construct master expression from list.
- $token_re = '{('. implode('|', $token_relist) .')}';
+ // Construct master expression from list.
+ $token_re = '{(' . implode('|', $token_relist) . ')}';
$this->em_strong_prepared_relist["$em$strong"] = $token_re;
}
}
}
-
+
+ /**
+ * Convert Markdown italics (emphasis) and bold (strong) to HTML
+ * @param string $text
+ * @return string
+ */
protected function doItalicsAndBold($text) {
$token_stack = array('');
$text_stack = array('');
@@ -1284,24 +1501,20 @@ class MarkdownParser {
$tree_char_em = false;
while (1) {
- #
- # Get prepared regular expression for seraching emphasis tokens
- # in current context.
- #
+ // Get prepared regular expression for seraching emphasis tokens
+ // in current context.
$token_re = $this->em_strong_prepared_relist["$em$strong"];
- #
- # Each loop iteration search for the next emphasis token.
- # Each token is then passed to handleSpanToken.
- #
+ // Each loop iteration search for the next emphasis token.
+ // Each token is then passed to handleSpanToken.
$parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
$text_stack[0] .= $parts[0];
$token =& $parts[1];
$text =& $parts[2];
if (empty($token)) {
- # Reached end of text span: empty stack without emitting.
- # any more emphasis.
+ // Reached end of text span: empty stack without emitting.
+ // any more emphasis.
while ($token_stack[0]) {
$text_stack[1] .= array_shift($token_stack);
$text_stack[0] .= array_shift($text_stack);
@@ -1311,9 +1524,9 @@ class MarkdownParser {
$token_len = strlen($token);
if ($tree_char_em) {
- # Reached closing marker while inside a three-char emphasis.
+ // Reached closing marker while inside a three-char emphasis.
if ($token_len == 3) {
- # Three-char closing marker, close em and strong.
+ // Three-char closing marker, close em and strong.
array_shift($token_stack);
$span = array_shift($text_stack);
$span = $this->runSpanGamut($span);
@@ -1322,21 +1535,21 @@ class MarkdownParser {
$em = '';
$strong = '';
} else {
- # Other closing marker: close one em or strong and
- # change current token state to match the other
+ // Other closing marker: close one em or strong and
+ // change current token state to match the other
$token_stack[0] = str_repeat($token{0}, 3-$token_len);
$tag = $token_len == 2 ? "strong" : "em";
$span = $text_stack[0];
$span = $this->runSpanGamut($span);
$span = "<$tag>$span</$tag>";
$text_stack[0] = $this->hashPart($span);
- $$tag = ''; # $$tag stands for $em or $strong
+ $$tag = ''; // $$tag stands for $em or $strong
}
$tree_char_em = false;
} else if ($token_len == 3) {
if ($em) {
- # Reached closing marker for both em and strong.
- # Closing strong marker:
+ // Reached closing marker for both em and strong.
+ // Closing strong marker:
for ($i = 0; $i < 2; ++$i) {
$shifted_token = array_shift($token_stack);
$tag = strlen($shifted_token) == 2 ? "strong" : "em";
@@ -1344,11 +1557,11 @@ class MarkdownParser {
$span = $this->runSpanGamut($span);
$span = "<$tag>$span</$tag>";
$text_stack[0] .= $this->hashPart($span);
- $$tag = ''; # $$tag stands for $em or $strong
+ $$tag = ''; // $$tag stands for $em or $strong
}
} else {
- # Reached opening three-char emphasis marker. Push on token
- # stack; will be handled by the special condition above.
+ // Reached opening three-char emphasis marker. Push on token
+ // stack; will be handled by the special condition above.
$em = $token{0};
$strong = "$em$em";
array_unshift($token_stack, $token);
@@ -1357,12 +1570,12 @@ class MarkdownParser {
}
} else if ($token_len == 2) {
if ($strong) {
- # Unwind any dangling emphasis marker:
+ // Unwind any dangling emphasis marker:
if (strlen($token_stack[0]) == 1) {
$text_stack[1] .= array_shift($token_stack);
$text_stack[0] .= array_shift($text_stack);
}
- # Closing strong marker:
+ // Closing strong marker:
array_shift($token_stack);
$span = array_shift($text_stack);
$span = $this->runSpanGamut($span);
@@ -1375,10 +1588,10 @@ class MarkdownParser {
$strong = $token;
}
} else {
- # Here $token_len == 1
+ // Here $token_len == 1
if ($em) {
if (strlen($token_stack[0]) == 1) {
- # Closing emphasis marker:
+ // Closing emphasis marker:
array_shift($token_stack);
$span = array_shift($text_stack);
$span = $this->runSpanGamut($span);
@@ -1398,7 +1611,11 @@ class MarkdownParser {
return $text_stack[0];
}
-
+ /**
+ * Parse Markdown blockquotes to HTML
+ * @param string $text
+ * @return string
+ */
protected function doBlockQuotes($text) {
$text = preg_replace_callback('/
( # Wrap whole match in $1
@@ -1414,51 +1631,64 @@ class MarkdownParser {
return $text;
}
+
+ /**
+ * Blockquote parsing callback
+ * @param array $matches
+ * @return string
+ */
protected function _doBlockQuotes_callback($matches) {
$bq = $matches[1];
- # trim one level of quoting - trim whitespace-only lines
+ // trim one level of quoting - trim whitespace-only lines
$bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq);
- $bq = $this->runBlockGamut($bq); # recurse
+ $bq = $this->runBlockGamut($bq); // recurse
$bq = preg_replace('/^/m', " ", $bq);
- # These leading spaces cause problem with <pre> content,
- # so we need to fix that:
+ // These leading spaces cause problem with <pre> content,
+ // so we need to fix that:
$bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx',
array($this, '_doBlockQuotes_callback2'), $bq);
- return "\n". $this->hashBlock("<blockquote>\n$bq\n</blockquote>")."\n\n";
+ return "\n" . $this->hashBlock("<blockquote>\n$bq\n</blockquote>") . "\n\n";
}
+
+ /**
+ * Blockquote parsing callback
+ * @param array $matches
+ * @return string
+ */
protected function _doBlockQuotes_callback2($matches) {
$pre = $matches[1];
$pre = preg_replace('/^ /m', '', $pre);
return $pre;
}
-
- protected function formParagraphs($text) {
- #
- # Params:
- # $text - string to process with html <p> tags
- #
- # Strip leading and trailing lines:
+ /**
+ * Parse paragraphs
+ *
+ * @param string $text String to process in paragraphs
+ * @param boolean $wrap_in_p Whether paragraphs should be wrapped in <p> tags
+ * @return string
+ */
+ protected function formParagraphs($text, $wrap_in_p = true) {
+ // Strip leading and trailing lines:
$text = preg_replace('/\A\n+|\n+\z/', '', $text);
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
- #
- # Wrap <p> tags and unhashify HTML blocks
- #
+ // Wrap <p> tags and unhashify HTML blocks
foreach ($grafs as $key => $value) {
if (!preg_match('/^B\x1A[0-9]+B$/', $value)) {
- # Is a paragraph.
+ // Is a paragraph.
$value = $this->runSpanGamut($value);
- $value = preg_replace('/^([ ]*)/', "<p>", $value);
- $value .= "</p>";
+ if ($wrap_in_p) {
+ $value = preg_replace('/^([ ]*)/', "<p>", $value);
+ $value .= "</p>";
+ }
$grafs[$key] = $this->unhash($value);
- }
- else {
- # Is a block.
- # Modify elements of @grafs in-place...
+ } else {
+ // Is a block.
+ // Modify elements of @grafs in-place...
$graf = $value;
$block = $this->html_hashes[$graf];
$graf = $block;
@@ -1483,11 +1713,11 @@ class MarkdownParser {
// {
// list(, $div_open, , $div_content, $div_close) = $matches;
//
-// # We can't call Markdown(), because that resets the hash;
-// # that initialization code should be pulled into its own sub, though.
+// // We can't call Markdown(), because that resets the hash;
+// // that initialization code should be pulled into its own sub, though.
// $div_content = $this->hashHTMLBlocks($div_content);
//
-// # Run document gamut methods on the content.
+// // Run document gamut methods on the content.
// foreach ($this->document_gamut as $method => $priority) {
// $div_content = $this->$method($div_content);
// }
@@ -1504,37 +1734,39 @@ class MarkdownParser {
return implode("\n\n", $grafs);
}
-
+ /**
+ * Encode text for a double-quoted HTML attribute. This function
+ * is *not* suitable for attributes enclosed in single quotes.
+ * @param string $text
+ * @return string
+ */
protected function encodeAttribute($text) {
- #
- # Encode text for a double-quoted HTML attribute. This function
- # is *not* suitable for attributes enclosed in single quotes.
- #
$text = $this->encodeAmpsAndAngles($text);
$text = str_replace('"', '"', $text);
return $text;
}
-
+ /**
+ * Encode text for a double-quoted HTML attribute containing a URL,
+ * applying the URL filter if set. Also generates the textual
+ * representation for the URL (removing mailto: or tel:) storing it in $text.
+ * This function is *not* suitable for attributes enclosed in single quotes.
+ *
+ * @param string $url
+ * @param string &$text Passed by reference
+ * @return string URL
+ */
protected function encodeURLAttribute($url, &$text = null) {
- #
- # Encode text for a double-quoted HTML attribute containing a URL,
- # applying the URL filter if set. Also generates the textual
- # representation for the URL (removing mailto: or tel:) storing it in $text.
- # This function is *not* suitable for attributes enclosed in single quotes.
- #
- if ($this->url_filter_func)
+ if ($this->url_filter_func) {
$url = call_user_func($this->url_filter_func, $url);
+ }
- if (preg_match('{^mailto:}i', $url))
+ if (preg_match('{^mailto:}i', $url)) {
$url = $this->encodeEntityObfuscatedAttribute($url, $text, 7);
- else if (preg_match('{^tel:}i', $url))
- {
+ } else if (preg_match('{^tel:}i', $url)) {
$url = $this->encodeAttribute($url);
$text = substr($url, 4);
- }
- else
- {
+ } else {
$url = $this->encodeAttribute($url);
$text = $url;
}
@@ -1542,33 +1774,38 @@ class MarkdownParser {
return $url;
}
-
+ /**
+ * Smart processing for ampersands and angle brackets that need to
+ * be encoded. Valid character entities are left alone unless the
+ * no-entities mode is set.
+ * @param string $text
+ * @return string
+ */
protected function encodeAmpsAndAngles($text) {
- #
- # Smart processing for ampersands and angle brackets that need to
- # be encoded. Valid character entities are left alone unless the
- # no-entities mode is set.
- #
if ($this->no_entities) {
$text = str_replace('&', '&', $text);
} else {
- # Ampersand-encoding based entirely on Nat Irons's Amputator
- # MT plugin: <http://bumppo.net/projects/amputator/>
+ // Ampersand-encoding based entirely on Nat Irons's Amputator
+ // MT plugin: <http://bumppo.net/projects/amputator/>
$text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
'&', $text);
}
- # Encode remaining <'s
+ // Encode remaining <'s
$text = str_replace('<', '<', $text);
return $text;
}
-
+ /**
+ * Parse Markdown automatic links to anchor HTML tags
+ * @param string $text
+ * @return string
+ */
protected function doAutoLinks($text) {
$text = preg_replace_callback('{<((https?|ftp|dict|tel):[^\'">\s]+)>}i',
array($this, '_doAutoLinks_url_callback'), $text);
- # Email addresses: <address@domain.foo>
+ // Email addresses: <address@domain.foo>
$text = preg_replace_callback('{
<
(?:mailto:)?
@@ -1591,11 +1828,23 @@ class MarkdownParser {
return $text;
}
+
+ /**
+ * Parse URL callback
+ * @param array $matches
+ * @return string
+ */
protected function _doAutoLinks_url_callback($matches) {
$url = $this->encodeURLAttribute($matches[1], $text);
$link = "<a href=\"$url\">$text</a>";
return $this->hashPart($link);
}
+
+ /**
+ * Parse email address callback
+ * @param array $matches
+ * @return string
+ */
protected function _doAutoLinks_email_callback($matches) {
$addr = $matches[1];
$url = $this->encodeURLAttribute("mailto:$addr", $text);
@@ -1603,42 +1852,52 @@ class MarkdownParser {
return $this->hashPart($link);
}
-
+ /**
+ * Input: some text to obfuscate, e.g. "mailto:foo@example.com"
+ *
+ * Output: the same text but with most characters encoded as either a
+ * decimal or hex entity, in the hopes of foiling most address
+ * harvesting spam bots. E.g.:
+ *
+ * mailto:foo
+ * @example.co
+ * m
+ *
+ * Note: the additional output $tail is assigned the same value as the
+ * ouput, minus the number of characters specified by $head_length.
+ *
+ * Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
+ * With some optimizations by Milian Wolff. Forced encoding of HTML
+ * attribute special characters by Allan Odgaard.
+ *
+ * @param string $text
+ * @param string &$tail
+ * @param integer $head_length
+ * @return string
+ */
protected function encodeEntityObfuscatedAttribute($text, &$tail = null, $head_length = 0) {
- #
- # Input: some text to obfuscate, e.g. "mailto:foo@example.com"
- #
- # Output: the same text but with most characters encoded as either a
- # decimal or hex entity, in the hopes of foiling most address
- # harvesting spam bots. E.g.:
- #
- # mailto:foo
- # @example.co
- # m
- #
- # Note: the additional output $tail is assigned the same value as the
- # ouput, minus the number of characters specified by $head_length.
- #
- # Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
- # With some optimizations by Milian Wolff. Forced encoding of HTML
- # attribute special characters by Allan Odgaard.
- #
- if ($text == "") return $tail = "";
+ if ($text == "") {
+ return $tail = "";
+ }
$chars = preg_split('/(?<!^)(?!$)/', $text);
- $seed = (int)abs(crc32($text) / strlen($text)); # Deterministic seed.
+ $seed = (int)abs(crc32($text) / strlen($text)); // Deterministic seed.
foreach ($chars as $key => $char) {
$ord = ord($char);
- # Ignore non-ascii chars.
+ // Ignore non-ascii chars.
if ($ord < 128) {
- $r = ($seed * (1 + $key)) % 100; # Pseudo-random function.
- # roughly 10% raw, 45% hex, 45% dec
- # '@' *must* be encoded. I insist.
- # '"' and '>' have to be encoded inside the attribute
- if ($r > 90 && strpos('@"&>', $char) === false) /* do nothing */;
- else if ($r < 45) $chars[$key] = '&#x'.dechex($ord).';';
- else $chars[$key] = '&#'.$ord.';';
+ $r = ($seed * (1 + $key)) % 100; // Pseudo-random function.
+ // roughly 10% raw, 45% hex, 45% dec
+ // '@' *must* be encoded. I insist.
+ // '"' and '>' have to be encoded inside the attribute
+ if ($r > 90 && strpos('@"&>', $char) === false) {
+ /* do nothing */
+ } else if ($r < 45) {
+ $chars[$key] = '&#x'.dechex($ord).';';
+ } else {
+ $chars[$key] = '&#'.$ord.';';
+ }
}
}
@@ -1648,12 +1907,13 @@ class MarkdownParser {
return $text;
}
-
+ /**
+ * Take the string $str and parse it into tokens, hashing embeded HTML,
+ * escaped characters and handling code spans.
+ * @param string $str
+ * @return string
+ */
protected function parseSpan($str) {
- #
- # Take the string $str and parse it into tokens, hashing embeded HTML,
- # escaped characters and handling code spans.
- #
$output = '';
$span_re = '{
@@ -1683,42 +1943,41 @@ class MarkdownParser {
}xs';
while (1) {
- #
- # Each loop iteration seach for either the next tag, the next
- # openning code span marker, or the next escaped character.
- # Each token is then passed to handleSpanToken.
- #
+ // Each loop iteration seach for either the next tag, the next
+ // openning code span marker, or the next escaped character.
+ // Each token is then passed to handleSpanToken.
$parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
- # Create token from text preceding tag.
+ // Create token from text preceding tag.
if ($parts[0] != "") {
$output .= $parts[0];
}
- # Check if we reach the end.
+ // Check if we reach the end.
if (isset($parts[1])) {
$output .= $this->handleSpanToken($parts[1], $parts[2]);
$str = $parts[2];
- }
- else {
+ } else {
break;
}
}
return $output;
}
-
-
+
+ /**
+ * Handle $token provided by parseSpan by determining its nature and
+ * returning the corresponding value that should replace it.
+ * @param string $token
+ * @param string &$str
+ * @return string
+ */
protected function handleSpanToken($token, &$str) {
- #
- # Handle $token provided by parseSpan by determining its nature and
- # returning the corresponding value that should replace it.
- #
switch ($token{0}) {
case "\\":
return $this->hashPart("&#". ord($token{1}). ";");
case "`":
- # Search for end marker in remaining text.
+ // Search for end marker in remaining text.
if (preg_match('/^(.*?[^`])'.preg_quote($token).'(?!`)(.*)$/sm',
$str, $matches))
{
@@ -1726,165 +1985,225 @@ class MarkdownParser {
$codespan = $this->makeCodeSpan($matches[1]);
return $this->hashPart($codespan);
}
- return $token; // return as text since no ending marker found.
+ return $token; // Return as text since no ending marker found.
default:
return $this->hashPart($token);
}
}
-
+ /**
+ * Remove one level of line-leading tabs or spaces
+ * @param string $text
+ * @return string
+ */
protected function outdent($text) {
- #
- # Remove one level of line-leading tabs or spaces
- #
- return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text);
+ return preg_replace('/^(\t|[ ]{1,' . $this->tab_width . '})/m', '', $text);
}
- # String length function for detab. `_initDetab` will create a function to
- # hanlde UTF-8 if the default function does not exist.
+ /**
+ * String length function for detab. `_initDetab` will create a function to
+ * handle UTF-8 if the default function does not exist.
+ * @var string
+ */
protected $utf8_strlen = 'mb_strlen';
-
- protected function detab($text) {
- #
- # Replace tabs with the appropriate amount of space.
- #
- # For each line we separate the line in blocks delemited by
- # tab characters. Then we reconstruct every line by adding the
- # appropriate number of space between each blocks.
-
+
+ /**
+ * Replace tabs with the appropriate amount of spaces.
+ *
+ * For each line we separate the line in blocks delemited by tab characters.
+ * Then we reconstruct every line by adding the appropriate number of space
+ * between each blocks.
+ *
+ * @param string $text
+ * @return string
+ */
+ protected function detab($text) {
$text = preg_replace_callback('/^.*\t.*$/m',
array($this, '_detab_callback'), $text);
return $text;
}
+
+ /**
+ * Replace tabs callback
+ * @param string $matches
+ * @return string
+ */
protected function _detab_callback($matches) {
$line = $matches[0];
- $strlen = $this->utf8_strlen; # strlen function for UTF-8.
+ $strlen = $this->utf8_strlen; // strlen function for UTF-8.
- # Split in blocks.
+ // Split in blocks.
$blocks = explode("\t", $line);
- # Add each blocks to the line.
+ // Add each blocks to the line.
$line = $blocks[0];
- unset($blocks[0]); # Do not add first block twice.
+ unset($blocks[0]); // Do not add first block twice.
foreach ($blocks as $block) {
- # Calculate amount of space, insert spaces, insert block.
+ // Calculate amount of space, insert spaces, insert block.
$amount = $this->tab_width -
$strlen($line, 'UTF-8') % $this->tab_width;
$line .= str_repeat(" ", $amount) . $block;
}
return $line;
}
+
+ /**
+ * Check for the availability of the function in the `utf8_strlen` property
+ * (initially `mb_strlen`). If the function is not available, create a
+ * function that will loosely count the number of UTF-8 characters with a
+ * regular expression.
+ * @return void
+ */
protected function _initDetab() {
- #
- # Check for the availability of the function in the `utf8_strlen` property
- # (initially `mb_strlen`). If the function is not available, create a
- # function that will loosely count the number of UTF-8 characters with a
- # regular expression.
- #
- if (function_exists($this->utf8_strlen)) return;
+
+ if (function_exists($this->utf8_strlen)) {
+ return;
+ }
+
$this->utf8_strlen = create_function('$text', 'return preg_match_all(
"/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/",
$text, $m);');
}
-
+ /**
+ * Swap back in all the tags hashed by _HashHTMLBlocks.
+ * @param string $text
+ * @return string
+ */
protected function unhash($text) {
- #
- # Swap back in all the tags hashed by _HashHTMLBlocks.
- #
return preg_replace_callback('/(.)\x1A[0-9]+\1/',
array($this, '_unhash_callback'), $text);
}
+
+ /**
+ * Unhashing callback
+ * @param array $matches
+ * @return string
+ */
protected function _unhash_callback($matches) {
return $this->html_hashes[$matches[0]];
}
-
}
class MarkdownExtraParser extends MarkdownParser {
-
- ### Configuration Variables ###
-
- # Prefix for footnote ids.
+ /**
+ * Configuration variables
+ */
+
+ /**
+ * Prefix for footnote ids.
+ * @var string
+ */
public $fn_id_prefix = "";
- # Optional title attribute for footnote links and backlinks.
- public $fn_link_title = "";
+ /**
+ * Optional title attribute for footnote links and backlinks.
+ * @var string
+ */
+ public $fn_link_title = "";
public $fn_backlink_title = "";
- # Optional class attribute for footnote links and backlinks.
- public $fn_link_class = "footnote-ref";
+ /**
+ * Optional class attribute for footnote links and backlinks.
+ * @var string
+ */
+ public $fn_link_class = "footnote-ref";
public $fn_backlink_class = "footnote-backref";
- # Content to be displayed within footnote backlinks. The default is '↩';
- # the U+FE0E on the end is a Unicode variant selector used to prevent iOS
- # from displaying the arrow character as an emoji.
+ /**
+ * Content to be displayed within footnote backlinks. The default is '↩';
+ * the U+FE0E on the end is a Unicode variant selector used to prevent iOS
+ * from displaying the arrow character as an emoji.
+ * @var string
+ */
public $fn_backlink_html = '↩︎';
- # Class name for table cell alignment (%% replaced left/center/right)
- # For instance: 'go-%%' becomes 'go-left' or 'go-right' or 'go-center'
- # If empty, the align attribute is used instead of a class name.
+ /**
+ * Class name for table cell alignment (%% replaced left/center/right)
+ * For instance: 'go-%%' becomes 'go-left' or 'go-right' or 'go-center'
+ * If empty, the align attribute is used instead of a class name.
+ * @var string
+ */
public $table_align_class_tmpl = '';
- # Optional class prefix for fenced code block.
+ /**
+ * Optional class prefix for fenced code block.
+ * @var string
+ */
public $code_class_prefix = "";
- # Class attribute for code blocks goes on the `code` tag;
- # setting this to true will put attributes on the `pre` tag instead.
+
+ /**
+ * Class attribute for code blocks goes on the `code` tag;
+ * setting this to true will put attributes on the `pre` tag instead.
+ * @var boolean
+ */
public $code_attr_on_pre = false;
- # Predefined abbreviations.
+ /**
+ * Predefined abbreviations.
+ * @var array
+ */
public $predef_abbr = array();
- ### Parser Implementation ###
-
+ /**
+ * Parser implementation
+ */
+
+ /**
+ * Constructor function. Initialize the parser object.
+ * @return void
+ */
public function __construct() {
- #
- # Constructor function. Initialize the parser object.
- #
- # Add extra escapable characters before parent constructor
- # initialize the table.
+ // Add extra escapable characters before parent constructor
+ // initialize the table.
$this->escape_chars .= ':|';
- # Insert extra document, block, and span transformations.
- # Parent constructor will do the sorting.
+ // Insert extra document, block, and span transformations.
+ // Parent constructor will do the sorting.
$this->document_gamut += array(
"doFencedCodeBlocks" => 5,
"stripFootnotes" => 15,
"stripAbbreviations" => 25,
"appendFootnotes" => 50,
- );
+ );
$this->block_gamut += array(
"doFencedCodeBlocks" => 5,
"doTables" => 15,
"doDefLists" => 45,
- );
+ );
$this->span_gamut += array(
"doFootnotes" => 5,
"doAbbreviations" => 70,
- );
+ );
$this->enhanced_ordered_list = true;
parent::__construct();
}
- # Extra variables used during extra transformations.
+ /**
+ * Extra variables used during extra transformations.
+ * @var array
+ */
protected $footnotes = array();
protected $footnotes_ordered = array();
protected $footnotes_ref_count = array();
protected $footnotes_numbers = array();
protected $abbr_desciptions = array();
+ /** @var string */
protected $abbr_word_re = '';
- # Give the current footnote number.
+ /**
+ * Give the current footnote number.
+ * @var integer
+ */
protected $footnote_counter = 1;
-
+ /**
+ * Setting up Extra-specific variables.
+ */
protected function setup() {
- #
- # Setting up Extra-specific variables.
- #
parent::setup();
$this->footnotes = array();
@@ -1902,11 +2221,11 @@ class MarkdownExtraParser extends MarkdownParser {
$this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
}
}
-
+
+ /**
+ * Clearing Extra-specific variables.
+ */
protected function teardown() {
- #
- # Clearing Extra-specific variables.
- #
$this->footnotes = array();
$this->footnotes_ordered = array();
$this->footnotes_ref_count = array();
@@ -1918,30 +2237,45 @@ class MarkdownExtraParser extends MarkdownParser {
}
- ### Extra Attribute Parser ###
-
- # Expression to use to catch attributes (includes the braces)
+ /**
+ * Extra attribute parser
+ */
+
+ /**
+ * Expression to use to catch attributes (includes the braces)
+ * @var string
+ */
protected $id_class_attr_catch_re = '\{((?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,})[ ]*\}';
- # Expression to use when parsing in a context when no capture is desired
+
+ /**
+ * Expression to use when parsing in a context when no capture is desired
+ * @var string
+ */
protected $id_class_attr_nocatch_re = '\{(?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,}[ ]*\}';
+ /**
+ * Parse attributes caught by the $this->id_class_attr_catch_re expression
+ * and return the HTML-formatted list of attributes.
+ *
+ * Currently supported attributes are .class and #id.
+ *
+ * In addition, this method also supports supplying a default Id value,
+ * which will be used to populate the id attribute in case it was not
+ * overridden.
+ * @param string $tag_name
+ * @param string $attr
+ * @param mixed $defaultIdValue
+ * @param array $classes
+ * @return string
+ */
protected function doExtraAttributes($tag_name, $attr, $defaultIdValue = null, $classes = array()) {
- #
- # Parse attributes caught by the $this->id_class_attr_catch_re expression
- # and return the HTML-formatted list of attributes.
- #
- # Currently supported attributes are .class and #id.
- #
- # In addition, this method also supports supplying a default Id value,
- # which will be used to populate the id attribute in case it was not
- # overridden.
if (empty($attr) && !$defaultIdValue && empty($classes)) return "";
- # Split on components
+ // Split on components
preg_match_all('/[#.a-z][-_:a-zA-Z0-9=]+/', $attr, $matches);
$elements = $matches[0];
- # handle classes and ids (only first id taken into account)
+ // Handle classes and IDs (only first ID taken into account)
$attributes = array();
$id = false;
foreach ($elements as $element) {
@@ -1957,7 +2291,7 @@ class MarkdownExtraParser extends MarkdownParser {
if (!$id) $id = $defaultIdValue;
- # compose attributes as string
+ // Compose attributes as string
$attr_str = "";
if (!empty($id)) {
$attr_str .= ' id="'.$this->encodeAttribute($id) .'"';
@@ -1971,15 +2305,16 @@ class MarkdownExtraParser extends MarkdownParser {
return $attr_str;
}
-
+ /**
+ * Strips link definitions from text, stores the URLs and titles in
+ * hash references.
+ * @param string $text
+ * @return string
+ */
protected function stripLinkDefinitions($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
$less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: ^[id]: url "optional title"
+ // Link defs are in the form: ^[id]: url "optional title"
$text = preg_replace_callback('{
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
[ ]*
@@ -2007,91 +2342,123 @@ class MarkdownExtraParser extends MarkdownParser {
$text);
return $text;
}
+
+ /**
+ * Strip link definition callback
+ * @param array $matches
+ * @return string
+ */
protected function _stripLinkDefinitions_callback($matches) {
$link_id = strtolower($matches[1]);
$url = $matches[2] == '' ? $matches[3] : $matches[2];
$this->urls[$link_id] = $url;
$this->titles[$link_id] =& $matches[4];
$this->ref_attr[$link_id] = $this->doExtraAttributes("", $dummy =& $matches[5]);
- return ''; # String that will replace the block
+ return ''; // String that will replace the block
}
- ### HTML Block Parser ###
+ /**
+ * HTML block parser
+ */
- # Tags that are always treated as block tags:
+ /**
+ * Tags that are always treated as block tags
+ * @var string
+ */
protected $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend|article|section|nav|aside|hgroup|header|footer|figcaption|figure';
- # Tags treated as block tags only if the opening tag is alone on its line:
+ /**
+ * Tags treated as block tags only if the opening tag is alone on its line
+ * @var string
+ */
protected $context_block_tags_re = 'script|noscript|style|ins|del|iframe|object|source|track|param|math|svg|canvas|audio|video';
- # Tags where markdown="1" default to span mode:
+ /**
+ * Tags where markdown="1" default to span mode:
+ * @var string
+ */
protected $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
- # Tags which must not have their contents modified, no matter where
- # they appear:
+ /**
+ * Tags which must not have their contents modified, no matter where
+ * they appear
+ * @var string
+ */
protected $clean_tags_re = 'script|style|math|svg';
- # Tags that do not need to be closed.
+ /**
+ * Tags that do not need to be closed.
+ * @var string
+ */
protected $auto_close_tags_re = 'hr|img|param|source|track';
-
+ /**
+ * Hashify HTML Blocks and "clean tags".
+ *
+ * We only want to do this for block-level HTML tags, such as headers,
+ * lists, and tables. That's because we still want to wrap <p>s around
+ * "paragraphs" that are wrapped in non-block-level tags, such as anchors,
+ * phrase emphasis, and spans. The list of tags we're looking for is
+ * hard-coded.
+ *
+ * This works by calling _HashHTMLBlocks_InMarkdown, which then calls
+ * _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1"
+ * attribute is found within a tag, _HashHTMLBlocks_InHTML calls back
+ * _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag.
+ * These two functions are calling each other. It's recursive!
+ * @param string $text
+ * @return string
+ */
protected function hashHTMLBlocks($text) {
- #
- # Hashify HTML Blocks and "clean tags".
- #
- # We only want to do this for block-level HTML tags, such as headers,
- # lists, and tables. That's because we still want to wrap <p>s around
- # "paragraphs" that are wrapped in non-block-level tags, such as anchors,
- # phrase emphasis, and spans. The list of tags we're looking for is
- # hard-coded.
- #
- # This works by calling _HashHTMLBlocks_InMarkdown, which then calls
- # _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1"
- # attribute is found within a tag, _HashHTMLBlocks_InHTML calls back
- # _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag.
- # These two functions are calling each other. It's recursive!
- #
- if ($this->no_markup) return $text;
-
- #
- # Call the HTML-in-Markdown hasher.
- #
+ if ($this->no_markup) {
+ return $text;
+ }
+
+ // Call the HTML-in-Markdown hasher.
list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text);
return $text;
}
+
+ /**
+ * Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
+ *
+ * * $indent is the number of space to be ignored when checking for code
+ * blocks. This is important because if we don't take the indent into
+ * account, something like this (which looks right) won't work as expected:
+ *
+ * <div>
+ * <div markdown="1">
+ * Hello World. <-- Is this a Markdown code block or text?
+ * </div> <-- Is this a Markdown code block or a real tag?
+ * <div>
+ *
+ * If you don't like this, just don't indent the tag on which
+ * you apply the markdown="1" attribute.
+ *
+ * * If $enclosing_tag_re is not empty, stops at the first unmatched closing
+ * tag with that name. Nested tags supported.
+ *
+ * * If $span is true, text inside must treated as span. So any double
+ * newline will be replaced by a single newline so that it does not create
+ * paragraphs.
+ *
+ * Returns an array of that form: ( processed text , remaining text )
+ *
+ * @param string $text
+ * @param integer $indent
+ * @param string $enclosing_tag_re
+ * @param boolean $span
+ * @return array
+ */
protected function _hashHTMLBlocks_inMarkdown($text, $indent = 0,
$enclosing_tag_re = '', $span = false)
{
- #
- # Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
- #
- # * $indent is the number of space to be ignored when checking for code
- # blocks. This is important because if we don't take the indent into
- # account, something like this (which looks right) won't work as expected:
- #
- # <div>
- # <div markdown="1">
- # Hello World. <-- Is this a Markdown code block or text?
- # </div> <-- Is this a Markdown code block or a real tag?
- # <div>
- #
- # If you don't like this, just don't indent the tag on which
- # you apply the markdown="1" attribute.
- #
- # * If $enclosing_tag_re is not empty, stops at the first unmatched closing
- # tag with that name. Nested tags supported.
- #
- # * If $span is true, text inside must treated as span. So any double
- # newline will be replaced by a single newline so that it does not create
- # paragraphs.
- #
- # Returns an array of that form: ( processed text , remaining text )
- #
+
if ($text === '') return array('', '');
- # Regex to check for the presense of newlines around a block tag.
+ // Regex to check for the presense of newlines around a block tag.
$newline_before_re = '/(?:^\n?|\n\n)*$/';
$newline_after_re =
'{
@@ -2100,16 +2467,16 @@ class MarkdownExtraParser extends MarkdownParser {
[ ]*\n # Must be followed by newline.
}xs';
- # Regex to match any tag.
+ // Regex to match any tag.
$block_tag_re =
'{
( # $2: Capture whole tag.
</? # Any opening or closing tag.
(?> # Tag name.
- '.$this->block_tags_re.' |
- '.$this->context_block_tags_re.' |
- '.$this->clean_tags_re.' |
- (?!\s)'.$enclosing_tag_re.'
+ ' . $this->block_tags_re . ' |
+ ' . $this->context_block_tags_re . ' |
+ ' . $this->clean_tags_re . ' |
+ (?!\s)'.$enclosing_tag_re . '
)
(?:
(?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
@@ -2126,25 +2493,25 @@ class MarkdownExtraParser extends MarkdownParser {
<\?.*?\?> | <%.*?%> # Processing instruction
|
<!\[CDATA\[.*?\]\]> # CData Block
- '. ( !$span ? ' # If not in span.
+ ' . ( !$span ? ' # If not in span.
|
# Indented code block
(?: ^[ ]*\n | ^ | \n[ ]*\n )
- [ ]{'.($indent+4).'}[^\n]* \n
+ [ ]{' . ($indent + 4) . '}[^\n]* \n
(?>
- (?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n
+ (?: [ ]{' . ($indent + 4) . '}[^\n]* | [ ]* ) \n
)*
|
# Fenced code block marker
(?<= ^ | \n )
- [ ]{0,'.($indent+3).'}(?:~{3,}|`{3,})
+ [ ]{0,' . ($indent + 3) . '}(?:~{3,}|`{3,})
[ ]*
(?: \.?[-_:a-zA-Z0-9]+ )? # standalone class name
[ ]*
- (?: '.$this->id_class_attr_nocatch_re.' )? # extra attributes
+ (?: ' . $this->id_class_attr_nocatch_re . ' )? # extra attributes
[ ]*
(?= \n )
- ' : '' ). ' # End (if not is span).
+ ' : '' ) . ' # End (if not is span).
|
# Code span marker
# Note, this regex needs to go after backtick fenced
@@ -2155,141 +2522,121 @@ class MarkdownExtraParser extends MarkdownParser {
}xs';
- $depth = 0; # Current depth inside the tag tree.
- $parsed = ""; # Parsed text that will be returned.
+ $depth = 0; // Current depth inside the tag tree.
+ $parsed = ""; // Parsed text that will be returned.
- #
- # Loop through every tag until we find the closing tag of the parent
- # or loop until reaching the end of text if no parent tag specified.
- #
+ // Loop through every tag until we find the closing tag of the parent
+ // or loop until reaching the end of text if no parent tag specified.
do {
- #
- # Split the text using the first $tag_match pattern found.
- # Text before pattern will be first in the array, text after
- # pattern will be at the end, and between will be any catches made
- # by the pattern.
- #
+ // Split the text using the first $tag_match pattern found.
+ // Text before pattern will be first in the array, text after
+ // pattern will be at the end, and between will be any catches made
+ // by the pattern.
$parts = preg_split($block_tag_re, $text, 2,
PREG_SPLIT_DELIM_CAPTURE);
- # If in Markdown span mode, add a empty-string span-level hash
- # after each newline to prevent triggering any block element.
+ // If in Markdown span mode, add a empty-string span-level hash
+ // after each newline to prevent triggering any block element.
if ($span) {
$void = $this->hashPart("", ':');
- $newline = "$void\n";
+ $newline = "\n$void";
$parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void;
}
- $parsed .= $parts[0]; # Text before current tag.
+ $parsed .= $parts[0]; // Text before current tag.
- # If end of $text has been reached. Stop loop.
+ // If end of $text has been reached. Stop loop.
if (count($parts) < 3) {
$text = "";
break;
}
- $tag = $parts[1]; # Tag to handle.
- $text = $parts[2]; # Remaining text after current tag.
- $tag_re = preg_quote($tag); # For use in a regular expression.
+ $tag = $parts[1]; // Tag to handle.
+ $text = $parts[2]; // Remaining text after current tag.
+ $tag_re = preg_quote($tag); // For use in a regular expression.
- #
- # Check for: Fenced code block marker.
- # Note: need to recheck the whole tag to disambiguate backtick
- # fences from code spans
- #
- if (preg_match('{^\n?([ ]{0,'.($indent+3).'})(~{3,}|`{3,})[ ]*(?:\.?[-_:a-zA-Z0-9]+)?[ ]*(?:'.$this->id_class_attr_nocatch_re.')?[ ]*\n?$}', $tag, $capture)) {
- # Fenced code block marker: find matching end marker.
- $fence_indent = strlen($capture[1]); # use captured indent in re
- $fence_re = $capture[2]; # use captured fence in re
- if (preg_match('{^(?>.*\n)*?[ ]{'.($fence_indent).'}'.$fence_re.'[ ]*(?:\n|$)}', $text,
+ // Check for: Fenced code block marker.
+ // Note: need to recheck the whole tag to disambiguate backtick
+ // fences from code spans
+ if (preg_match('{^\n?([ ]{0,' . ($indent + 3) . '})(~{3,}|`{3,})[ ]*(?:\.?[-_:a-zA-Z0-9]+)?[ ]*(?:' . $this->id_class_attr_nocatch_re . ')?[ ]*\n?$}', $tag, $capture)) {
+ // Fenced code block marker: find matching end marker.
+ $fence_indent = strlen($capture[1]); // use captured indent in re
+ $fence_re = $capture[2]; // use captured fence in re
+ if (preg_match('{^(?>.*\n)*?[ ]{' . ($fence_indent) . '}' . $fence_re . '[ ]*(?:\n|$)}', $text,
$matches))
{
- # End marker found: pass text unchanged until marker.
+ // End marker found: pass text unchanged until marker.
$parsed .= $tag . $matches[0];
$text = substr($text, strlen($matches[0]));
}
else {
- # No end marker: just skip it.
+ // No end marker: just skip it.
$parsed .= $tag;
}
}
- #
- # Check for: Indented code block.
- #
+ // Check for: Indented code block.
else if ($tag{0} == "\n" || $tag{0} == " ") {
- # Indented code block: pass it unchanged, will be handled
- # later.
+ // Indented code block: pass it unchanged, will be handled
+ // later.
$parsed .= $tag;
}
- #
- # Check for: Code span marker
- # Note: need to check this after backtick fenced code blocks
- #
+ // Check for: Code span marker
+ // Note: need to check this after backtick fenced code blocks
else if ($tag{0} == "`") {
- # Find corresponding end marker.
+ // Find corresponding end marker.
$tag_re = preg_quote($tag);
- if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)'.$tag_re.'(?!`)}',
+ if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)' . $tag_re . '(?!`)}',
$text, $matches))
{
- # End marker found: pass text unchanged until marker.
+ // End marker found: pass text unchanged until marker.
$parsed .= $tag . $matches[0];
$text = substr($text, strlen($matches[0]));
}
else {
- # Unmatched marker: just skip it.
+ // Unmatched marker: just skip it.
$parsed .= $tag;
}
}
- #
- # Check for: Opening Block level tag or
- # Opening Context Block tag (like ins and del)
- # used as a block tag (tag is alone on it's line).
- #
- else if (preg_match('{^<(?:'.$this->block_tags_re.')\b}', $tag) ||
- ( preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) &&
+ // Check for: Opening Block level tag or
+ // Opening Context Block tag (like ins and del)
+ // used as a block tag (tag is alone on it's line).
+ else if (preg_match('{^<(?:' . $this->block_tags_re . ')\b}', $tag) ||
+ ( preg_match('{^<(?:' . $this->context_block_tags_re . ')\b}', $tag) &&
preg_match($newline_before_re, $parsed) &&
preg_match($newline_after_re, $text) )
)
{
- # Need to parse tag and following text using the HTML parser.
+ // Need to parse tag and following text using the HTML parser.
list($block_text, $text) =
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true);
- # Make sure it stays outside of any paragraph by adding newlines.
+ // Make sure it stays outside of any paragraph by adding newlines.
$parsed .= "\n\n$block_text\n\n";
}
- #
- # Check for: Clean tag (like script, math)
- # HTML Comments, processing instructions.
- #
- else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
+ // Check for: Clean tag (like script, math)
+ // HTML Comments, processing instructions.
+ else if (preg_match('{^<(?:' . $this->clean_tags_re . ')\b}', $tag) ||
$tag{1} == '!' || $tag{1} == '?')
{
- # Need to parse tag and following text using the HTML parser.
- # (don't check for markdown attribute)
+ // Need to parse tag and following text using the HTML parser.
+ // (don't check for markdown attribute)
list($block_text, $text) =
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false);
$parsed .= $block_text;
}
- #
- # Check for: Tag with same name as enclosing tag.
- #
+ // Check for: Tag with same name as enclosing tag.
else if ($enclosing_tag_re !== '' &&
- # Same name as enclosing tag.
- preg_match('{^</?(?:'.$enclosing_tag_re.')\b}', $tag))
+ // Same name as enclosing tag.
+ preg_match('{^</?(?:' . $enclosing_tag_re . ')\b}', $tag))
{
- #
- # Increase/decrease nested tag count.
- #
+ // Increase/decrease nested tag count.
if ($tag{1} == '/') $depth--;
else if ($tag{strlen($tag)-2} != '/') $depth++;
if ($depth < 0) {
- #
- # Going out of parent element. Clean up and break so we
- # return to the calling function.
- #
+ // Going out of parent element. Clean up and break so we
+ // return to the calling function.
$text = $tag . $text;
break;
}
@@ -2303,20 +2650,25 @@ class MarkdownExtraParser extends MarkdownParser {
return array($parsed, $text);
}
+
+ /**
+ * Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags.
+ *
+ * * Calls $hash_method to convert any blocks.
+ * * Stops when the first opening tag closes.
+ * * $md_attr indicate if the use of the `markdown="1"` attribute is allowed.
+ * (it is not inside clean tags)
+ *
+ * Returns an array of that form: ( processed text , remaining text )
+ * @param string $text
+ * @param string $hash_method
+ * @param string $md_attr
+ * @return array
+ */
protected function _hashHTMLBlocks_inHTML($text, $hash_method, $md_attr) {
- #
- # Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags.
- #
- # * Calls $hash_method to convert any blocks.
- # * Stops when the first opening tag closes.
- # * $md_attr indicate if the use of the `markdown="1"` attribute is allowed.
- # (it is not inside clean tags)
- #
- # Returns an array of that form: ( processed text , remaining text )
- #
if ($text === '') return array('', '');
- # Regex to match `markdown` attribute inside of a tag.
+ // Regex to match `markdown` attribute inside of a tag.
$markdown_attr_re = '
{
\s* # Eat whitespace before the `markdown` attribute
@@ -2332,7 +2684,7 @@ class MarkdownExtraParser extends MarkdownParser {
() # $4: make $3 always defined (avoid warnings)
}xs';
- # Regex to match any tag.
+ // Regex to match any tag.
$tag_re = '{
( # $2: Capture whole tag.
</? # Any opening or closing tag.
@@ -2355,81 +2707,67 @@ class MarkdownExtraParser extends MarkdownParser {
)
}xs';
- $original_text = $text; # Save original text in case of faliure.
+ $original_text = $text; // Save original text in case of faliure.
- $depth = 0; # Current depth inside the tag tree.
- $block_text = ""; # Temporary text holder for current text.
- $parsed = ""; # Parsed text that will be returned.
-
- #
- # Get the name of the starting tag.
- # (This pattern makes $base_tag_name_re safe without quoting.)
- #
+ $depth = 0; // Current depth inside the tag tree.
+ $block_text = ""; // Temporary text holder for current text.
+ $parsed = ""; // Parsed text that will be returned.
+
+ // Get the name of the starting tag.
+ // (This pattern makes $base_tag_name_re safe without quoting.)
if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
$base_tag_name_re = $matches[1];
- #
- # Loop through every tag until we find the corresponding closing tag.
- #
+ // Loop through every tag until we find the corresponding closing tag.
do {
- #
- # Split the text using the first $tag_match pattern found.
- # Text before pattern will be first in the array, text after
- # pattern will be at the end, and between will be any catches made
- # by the pattern.
- #
+ // Split the text using the first $tag_match pattern found.
+ // Text before pattern will be first in the array, text after
+ // pattern will be at the end, and between will be any catches made
+ // by the pattern.
$parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
if (count($parts) < 3) {
- #
- # End of $text reached with unbalenced tag(s).
- # In that case, we return original text unchanged and pass the
- # first character as filtered to prevent an infinite loop in the
- # parent function.
- #
+ // End of $text reached with unbalenced tag(s).
+ // In that case, we return original text unchanged and pass the
+ // first character as filtered to prevent an infinite loop in the
+ // parent function.
return array($original_text{0}, substr($original_text, 1));
}
- $block_text .= $parts[0]; # Text before current tag.
- $tag = $parts[1]; # Tag to handle.
- $text = $parts[2]; # Remaining text after current tag.
+ $block_text .= $parts[0]; // Text before current tag.
+ $tag = $parts[1]; // Tag to handle.
+ $text = $parts[2]; // Remaining text after current tag.
- #
- # Check for: Auto-close tag (like <hr/>)
- # Comments and Processing Instructions.
- #
- if (preg_match('{^</?(?:'.$this->auto_close_tags_re.')\b}', $tag) ||
+ // Check for: Auto-close tag (like <hr/>)
+ // Comments and Processing Instructions.
+ if (preg_match('{^</?(?:' . $this->auto_close_tags_re . ')\b}', $tag) ||
$tag{1} == '!' || $tag{1} == '?')
{
- # Just add the tag to the block as if it was text.
+ // Just add the tag to the block as if it was text.
$block_text .= $tag;
}
else {
- #
- # Increase/decrease nested tag count. Only do so if
- # the tag's name match base tag's.
- #
- if (preg_match('{^</?'.$base_tag_name_re.'\b}', $tag)) {
+ // Increase/decrease nested tag count. Only do so if
+ // the tag's name match base tag's.
+ if (preg_match('{^</?' . $base_tag_name_re . '\b}', $tag)) {
if ($tag{1} == '/') $depth--;
else if ($tag{strlen($tag)-2} != '/') $depth++;
}
- #
- # Check for `markdown="1"` attribute and handle it.
- #
+ // Check for `markdown="1"` attribute and handle it.
if ($md_attr &&
preg_match($markdown_attr_re, $tag, $attr_m) &&
preg_match('/^1|block|span$/', $attr_m[2] . $attr_m[3]))
{
- # Remove `markdown` attribute from opening tag.
+ // Remove `markdown` attribute from opening tag.
$tag = preg_replace($markdown_attr_re, '', $tag);
- # Check if text inside this tag must be parsed in span mode.
+ // Check if text inside this tag must be parsed in span mode.
$this->mode = $attr_m[2] . $attr_m[3];
$span_mode = $this->mode == 'span' || $this->mode != 'block' &&
- preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
+ preg_match('{^<(?:' . $this->contain_span_tags_re . ')\b}', $tag);
- # Calculate indent before tag.
+ // Calculate indent before tag.
if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) {
$strlen = $this->utf8_strlen;
$indent = $strlen($matches[1], 'UTF-8');
@@ -2437,31 +2775,31 @@ class MarkdownExtraParser extends MarkdownParser {
$indent = 0;
}
- # End preceding block with this tag.
+ // End preceding block with this tag.
$block_text .= $tag;
$parsed .= $this->$hash_method($block_text);
- # Get enclosing tag name for the ParseMarkdown function.
- # (This pattern makes $tag_name_re safe without quoting.)
+ // Get enclosing tag name for the ParseMarkdown function.
+ // (This pattern makes $tag_name_re safe without quoting.)
preg_match('/^<([\w:$]*)\b/', $tag, $matches);
$tag_name_re = $matches[1];
- # Parse the content using the HTML-in-Markdown parser.
+ // Parse the content using the HTML-in-Markdown parser.
list ($block_text, $text)
= $this->_hashHTMLBlocks_inMarkdown($text, $indent,
$tag_name_re, $span_mode);
- # Outdent markdown text.
+ // Outdent markdown text.
if ($indent > 0) {
$block_text = preg_replace("/^[ ]{1,$indent}/m", "",
$block_text);
}
- # Append tag content to parsed text.
+ // Append tag content to parsed text.
if (!$span_mode) $parsed .= "\n\n$block_text\n\n";
else $parsed .= "$block_text";
- # Start over with a new block.
+ // Start over with a new block.
$block_text = "";
}
else $block_text .= $tag;
@@ -2469,39 +2807,39 @@ class MarkdownExtraParser extends MarkdownParser {
} while ($depth > 0);
- #
- # Hash last block text that wasn't processed inside the loop.
- #
+ // Hash last block text that wasn't processed inside the loop.
$parsed .= $this->$hash_method($block_text);
return array($parsed, $text);
}
-
+ /**
+ * Called whenever a tag must be hashed when a function inserts a "clean" tag
+ * in $text, it passes through this function and is automaticaly escaped,
+ * blocking invalid nested overlap.
+ * @param string $text
+ * @return string
+ */
protected function hashClean($text) {
- #
- # Called whenever a tag must be hashed when a function inserts a "clean" tag
- # in $text, it passes through this function and is automaticaly escaped,
- # blocking invalid nested overlap.
- #
return $this->hashPart($text, 'C');
}
-
+ /**
+ * Turn Markdown link shortcuts into XHTML <a> tags.
+ * @param string $text
+ * @return string
+ */
protected function doAnchors($text) {
- #
- # Turn Markdown link shortcuts into XHTML <a> tags.
- #
- if ($this->in_anchor) return $text;
+ if ($this->in_anchor) {
+ return $text;
+ }
$this->in_anchor = true;
-
- #
- # First, handle reference-style links: [link text] [id]
- #
+
+ // First, handle reference-style links: [link text] [id]
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
- ('.$this->nested_brackets_re.') # link text = $2
+ (' . $this->nested_brackets_re . ') # link text = $2
\]
[ ]? # one optional space
@@ -2514,20 +2852,18 @@ class MarkdownExtraParser extends MarkdownParser {
}xs',
array($this, '_doAnchors_reference_callback'), $text);
- #
- # Next, inline-style links: [link text](url "optional title")
- #
+ // Next, inline-style links: [link text](url "optional title")
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
- ('.$this->nested_brackets_re.') # link text = $2
+ (' . $this->nested_brackets_re . ') # link text = $2
\]
\( # literal paren
[ \n]*
(?:
<(.+?)> # href = $3
|
- ('.$this->nested_url_parenthesis_re.') # href = $4
+ (' . $this->nested_url_parenthesis_re . ') # href = $4
)
[ \n]*
( # $5
@@ -2537,16 +2873,14 @@ class MarkdownExtraParser extends MarkdownParser {
[ \n]* # ignore any spaces/tabs between closing quote and )
)? # title is optional
\)
- (?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
+ (?:[ ]? ' . $this->id_class_attr_catch_re . ' )? # $8 = id/class attributes
)
}xs',
array($this, '_doAnchors_inline_callback'), $text);
- #
- # Last, handle reference-style shortcuts: [link text]
- # These must come last in case you've also got [link text][1]
- # or [link text](/foo)
- #
+ // Last, handle reference-style shortcuts: [link text]
+ // These must come last in case you've also got [link text][1]
+ // or [link text](/foo)
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
@@ -2559,17 +2893,23 @@ class MarkdownExtraParser extends MarkdownParser {
$this->in_anchor = false;
return $text;
}
+
+ /**
+ * Callback for reference anchors
+ * @param array $matches
+ * @return string
+ */
protected function _doAnchors_reference_callback($matches) {
$whole_match = $matches[1];
$link_text = $matches[2];
$link_id =& $matches[3];
if ($link_id == "") {
- # for shortcut links like [this][] or [this].
+ // for shortcut links like [this][] or [this].
$link_id = $link_text;
}
- # lower-case and turn embedded newlines into spaces
+ // lower-case and turn embedded newlines into spaces
$link_id = strtolower($link_id);
$link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
@@ -2595,6 +2935,12 @@ class MarkdownExtraParser extends MarkdownParser {
}
return $result;
}
+
+ /**
+ * Callback for inline anchors
+ * @param array $matches
+ * @return string
+ */
protected function _doAnchors_inline_callback($matches) {
$whole_match = $matches[1];
$link_text = $this->runSpanGamut($matches[2]);
@@ -2623,18 +2969,17 @@ class MarkdownExtraParser extends MarkdownParser {
return $this->hashPart($result);
}
-
+ /**
+ * Turn Markdown image shortcuts into <img> tags.
+ * @param string $text
+ * @return string
+ */
protected function doImages($text) {
- #
- # Turn Markdown image shortcuts into <img> tags.
- #
- #
- # First, handle reference-style labeled images: ![alt text][id]
- #
+ // First, handle reference-style labeled images: ![alt text][id]
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
- ('.$this->nested_brackets_re.') # alt text = $2
+ (' . $this->nested_brackets_re . ') # alt text = $2
\]
[ ]? # one optional space
@@ -2648,14 +2993,12 @@ class MarkdownExtraParser extends MarkdownParser {
}xs',
array($this, '_doImages_reference_callback'), $text);
- #
- # Next, handle inline images: 
- # Don't forget: encode * and _
- #
+ // Next, handle inline images: 
+ // Don't forget: encode * and _
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
- ('.$this->nested_brackets_re.') # alt text = $2
+ (' . $this->nested_brackets_re . ') # alt text = $2
\]
\s? # One optional whitespace character
\( # literal paren
@@ -2663,7 +3006,7 @@ class MarkdownExtraParser extends MarkdownParser {
(?:
<(\S*)> # src url = $3
|
- ('.$this->nested_url_parenthesis_re.') # src url = $4
+ (' . $this->nested_url_parenthesis_re . ') # src url = $4
)
[ \n]*
( # $5
@@ -2673,20 +3016,26 @@ class MarkdownExtraParser extends MarkdownParser {
[ \n]*
)? # title is optional
\)
- (?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
+ (?:[ ]? ' . $this->id_class_attr_catch_re . ' )? # $8 = id/class attributes
)
}xs',
array($this, '_doImages_inline_callback'), $text);
return $text;
}
+
+ /**
+ * Callback for referenced images
+ * @param array $matches
+ * @return string
+ */
protected function _doImages_reference_callback($matches) {
$whole_match = $matches[1];
$alt_text = $matches[2];
$link_id = strtolower($matches[3]);
if ($link_id == "") {
- $link_id = strtolower($alt_text); # for shortcut links like ![this][].
+ $link_id = strtolower($alt_text); // for shortcut links like ![this][].
}
$alt_text = $this->encodeAttribute($alt_text);
@@ -2704,12 +3053,18 @@ class MarkdownExtraParser extends MarkdownParser {
$result = $this->hashPart($result);
}
else {
- # If there's no such link ID, leave intact:
+ // If there's no such link ID, leave intact:
$result = $whole_match;
}
return $result;
}
+
+ /**
+ * Callback for inline images
+ * @param array $matches
+ * @return string
+ */
protected function _doImages_inline_callback($matches) {
$whole_match = $matches[1];
$alt_text = $matches[2];
@@ -2722,7 +3077,7 @@ class MarkdownExtraParser extends MarkdownParser {
$result = "<img src=\"$url\" alt=\"$alt_text\"";
if (isset($title)) {
$title = $this->encodeAttribute($title);
- $result .= " title=\"$title\""; # $title already quoted
+ $result .= " title=\"$title\""; // $title already quoted
}
$result .= $attr;
$result .= $this->empty_element_suffix;
@@ -2730,40 +3085,41 @@ class MarkdownExtraParser extends MarkdownParser {
return $this->hashPart($result);
}
-
+ /**
+ * Process markdown headers. Redefined to add ID and class attribute support.
+ * @param string $text
+ * @return string
+ */
protected function doHeaders($text) {
- #
- # Redefined to add id and class attribute support.
- #
- # Setext-style headers:
- # Header 1 {#header1}
- # ========
- #
- # Header 2 {#header2 .class1 .class2}
- # --------
- #
+ // Setext-style headers:
+ // Header 1 {#header1}
+ // ========
+ //
+ // Header 2 {#header2 .class1 .class2}
+ // --------
+ //
$text = preg_replace_callback(
'{
(^.+?) # $1: Header text
- (?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
+ (?:[ ]+ ' . $this->id_class_attr_catch_re . ' )? # $3 = id/class attributes
[ ]*\n(=+|-+)[ ]*\n+ # $3: Header footer
}mx',
array($this, '_doHeaders_callback_setext'), $text);
- # atx-style headers:
- # # Header 1 {#header1}
- # ## Header 2 {#header2}
- # ## Header 2 with closing hashes ## {#header3.class1.class2}
- # ...
- # ###### Header 6 {.class2}
- #
+ // atx-style headers:
+ // # Header 1 {#header1}
+ // ## Header 2 {#header2}
+ // ## Header 2 with closing hashes ## {#header3.class1.class2}
+ // ...
+ // ###### Header 6 {.class2}
+ //
$text = preg_replace_callback('{
^(\#{1,6}) # $1 = string of #\'s
[ ]*
(.+?) # $2 = Header text
[ ]*
\#* # optional closing #\'s (not counted)
- (?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
+ (?:[ ]+ ' . $this->id_class_attr_catch_re . ' )? # $3 = id/class attributes
[ ]*
\n+
}xm',
@@ -2771,49 +3127,61 @@ class MarkdownExtraParser extends MarkdownParser {
return $text;
}
+
+ /**
+ * Callback for setext headers
+ * @param array $matches
+ * @return string
+ */
protected function _doHeaders_callback_setext($matches) {
- if ($matches[3] == '-' && preg_match('{^- }', $matches[1]))
+ if ($matches[3] == '-' && preg_match('{^- }', $matches[1])) {
return $matches[0];
+ }
$level = $matches[3]{0} == '=' ? 1 : 2;
$defaultId = is_callable($this->header_id_func) ? call_user_func($this->header_id_func, $matches[1]) : null;
$attr = $this->doExtraAttributes("h$level", $dummy =& $matches[2], $defaultId);
- $block = "<h$level$attr>".$this->runSpanGamut($matches[1])."</h$level>";
+ $block = "<h$level$attr>" . $this->runSpanGamut($matches[1]) . "</h$level>";
return "\n" . $this->hashBlock($block) . "\n\n";
}
+
+ /**
+ * Callback for atx headers
+ * @param array $matches
+ * @return string
+ */
protected function _doHeaders_callback_atx($matches) {
$level = strlen($matches[1]);
$defaultId = is_callable($this->header_id_func) ? call_user_func($this->header_id_func, $matches[2]) : null;
$attr = $this->doExtraAttributes("h$level", $dummy =& $matches[3], $defaultId);
- $block = "<h$level$attr>".$this->runSpanGamut($matches[2])."</h$level>";
+ $block = "<h$level$attr>" . $this->runSpanGamut($matches[2]) . "</h$level>";
return "\n" . $this->hashBlock($block) . "\n\n";
}
-
+ /**
+ * Form HTML tables.
+ * @param string $text
+ * @return string
+ */
protected function doTables($text) {
- #
- # Form HTML tables.
- #
$less_than_tab = $this->tab_width - 1;
- #
- # Find tables with leading pipe.
- #
- # | Header 1 | Header 2
- # | -------- | --------
- # | Cell 1 | Cell 2
- # | Cell 3 | Cell 4
- #
+ // Find tables with leading pipe.
+ //
+ // | Header 1 | Header 2
+ // | -------- | --------
+ // | Cell 1 | Cell 2
+ // | Cell 3 | Cell 4
$text = preg_replace_callback('
{
^ # Start of a line
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
+ [ ]{0,' . $less_than_tab . '} # Allowed whitespace.
[|] # Optional leading pipe (present)
(.+) \n # $1: Header row (at least one pipe)
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
+ [ ]{0,' . $less_than_tab . '} # Allowed whitespace.
[|] ([ ]*[-:]+[-| :]*) \n # $2: Header underline
( # $3: Cells
@@ -2825,22 +3193,20 @@ class MarkdownExtraParser extends MarkdownParser {
(?=\n|\Z) # Stop at final double newline.
}xm',
array($this, '_doTable_leadingPipe_callback'), $text);
-
- #
- # Find tables without leading pipe.
- #
- # Header 1 | Header 2
- # -------- | --------
- # Cell 1 | Cell 2
- # Cell 3 | Cell 4
- #
+
+ // Find tables without leading pipe.
+ //
+ // Header 1 | Header 2
+ // -------- | --------
+ // Cell 1 | Cell 2
+ // Cell 3 | Cell 4
$text = preg_replace_callback('
{
^ # Start of a line
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
+ [ ]{0,' . $less_than_tab . '} # Allowed whitespace.
(\S.*[|].*) \n # $1: Header row (at least one pipe)
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
+ [ ]{0,' . $less_than_tab . '} # Allowed whitespace.
([-:]+[ ]*[|][-| :]*) \n # $2: Header underline
( # $3: Cells
@@ -2854,35 +3220,53 @@ class MarkdownExtraParser extends MarkdownParser {
return $text;
}
+
+ /**
+ * Callback for removing the leading pipe for each row
+ * @param array $matches
+ * @return string
+ */
protected function _doTable_leadingPipe_callback($matches) {
$head = $matches[1];
$underline = $matches[2];
$content = $matches[3];
-
- # Remove leading pipe for each row.
+
$content = preg_replace('/^ *[|]/m', '', $content);
return $this->_doTable_callback(array($matches[0], $head, $underline, $content));
}
+
+ /**
+ * Make the align attribute in a table
+ * @param string $alignname
+ * @return string
+ */
protected function _doTable_makeAlignAttr($alignname)
{
- if (empty($this->table_align_class_tmpl))
+ if (empty($this->table_align_class_tmpl)) {
return " align=\"$alignname\"";
+ }
$classname = str_replace('%%', $alignname, $this->table_align_class_tmpl);
return " class=\"$classname\"";
}
+
+ /**
+ * Calback for processing tables
+ * @param array $matches
+ * @return string
+ */
protected function _doTable_callback($matches) {
$head = $matches[1];
$underline = $matches[2];
$content = $matches[3];
- # Remove any tailing pipes for each line.
+ // Remove any tailing pipes for each line.
$head = preg_replace('/[|] *$/m', '', $head);
$underline = preg_replace('/[|] *$/m', '', $underline);
$content = preg_replace('/[|] *$/m', '', $content);
- # Reading alignement from header underline.
+ // Reading alignement from header underline.
$separators = preg_split('/ *[|] */', $underline);
foreach ($separators as $n => $s) {
if (preg_match('/^ *-+: *$/', $s))
@@ -2895,38 +3279,38 @@ class MarkdownExtraParser extends MarkdownParser {
$attr[$n] = '';
}
- # Parsing span elements, including code spans, character escapes,
- # and inline HTML tags, so that pipes inside those gets ignored.
+ // Parsing span elements, including code spans, character escapes,
+ // and inline HTML tags, so that pipes inside those gets ignored.
$head = $this->parseSpan($head);
$headers = preg_split('/ *[|] */', $head);
$col_count = count($headers);
$attr = array_pad($attr, $col_count, '');
- # Write column headers.
+ // Write column headers.
$text = "<table>\n";
$text .= "<thead>\n";
$text .= "<tr>\n";
foreach ($headers as $n => $header)
- $text .= " <th$attr[$n]>".$this->runSpanGamut(trim($header))."</th>\n";
+ $text .= " <th$attr[$n]>" . $this->runSpanGamut(trim($header)) . "</th>\n";
$text .= "</tr>\n";
$text .= "</thead>\n";
- # Split content by row.
+ // Split content by row.
$rows = explode("\n", trim($content, "\n"));
$text .= "<tbody>\n";
foreach ($rows as $row) {
- # Parsing span elements, including code spans, character escapes,
- # and inline HTML tags, so that pipes inside those gets ignored.
+ // Parsing span elements, including code spans, character escapes,
+ // and inline HTML tags, so that pipes inside those gets ignored.
$row = $this->parseSpan($row);
- # Split row by cell.
+ // Split row by cell.
$row_cells = preg_split('/ *[|] */', $row, $col_count);
$row_cells = array_pad($row_cells, $col_count, '');
$text .= "<tr>\n";
foreach ($row_cells as $n => $cell)
- $text .= " <td$attr[$n]>".$this->runSpanGamut(trim($cell))."</td>\n";
+ $text .= " <td$attr[$n]>" . $this->runSpanGamut(trim($cell)) . "</td>\n";
$text .= "</tr>\n";
}
$text .= "</tbody>\n";
@@ -2935,21 +3319,22 @@ class MarkdownExtraParser extends MarkdownParser {
return $this->hashBlock($text) . "\n";
}
-
+ /**
+ * Form HTML definition lists.
+ * @param string $text
+ * @return string
+ */
protected function doDefLists($text) {
- #
- # Form HTML definition lists.
- #
$less_than_tab = $this->tab_width - 1;
- # Re-usable pattern to match any entire dl list:
+ // Re-usable pattern to match any entire dl list:
$whole_list_re = '(?>
( # $1 = whole list
( # $2
- [ ]{0,'.$less_than_tab.'}
+ [ ]{0,' . $less_than_tab . '}
((?>.*\S.*\n)+) # $3 = defined term
\n?
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
+ [ ]{0,' . $less_than_tab . '}:[ ]+ # colon starting definition
)
(?s:.+?)
( # $4
@@ -2958,13 +3343,13 @@ class MarkdownExtraParser extends MarkdownParser {
\n{2,}
(?=\S)
(?! # Negative lookahead for another term
- [ ]{0,'.$less_than_tab.'}
+ [ ]{0,' . $less_than_tab . '}
(?: \S.*\n )+? # defined term
\n?
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
+ [ ]{0,' . $less_than_tab . '}:[ ]+ # colon starting definition
)
(?! # Negative lookahead for another definition
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
+ [ ]{0,' . $less_than_tab . '}:[ ]+ # colon starting definition
)
)
)
@@ -2972,59 +3357,67 @@ class MarkdownExtraParser extends MarkdownParser {
$text = preg_replace_callback('{
(?>\A\n?|(?<=\n\n))
- '.$whole_list_re.'
+ ' . $whole_list_re . '
}mx',
array($this, '_doDefLists_callback'), $text);
return $text;
}
+
+ /**
+ * Callback for processing definition lists
+ * @param array $matches
+ * @return string
+ */
protected function _doDefLists_callback($matches) {
- # Re-usable patterns to match list item bullets and number markers:
+ // Re-usable patterns to match list item bullets and number markers:
$list = $matches[1];
- # Turn double returns into triple returns, so that we can make a
- # paragraph for the last item in a list, if necessary:
+ // Turn double returns into triple returns, so that we can make a
+ // paragraph for the last item in a list, if necessary:
$result = trim($this->processDefListItems($list));
$result = "<dl>\n" . $result . "\n</dl>";
return $this->hashBlock($result) . "\n\n";
}
-
+ /**
+ * Process the contents of a single definition list, splitting it
+ * into individual term and definition list items.
+ * @param string $list_str
+ * @return string
+ */
protected function processDefListItems($list_str) {
- #
- # Process the contents of a single definition list, splitting it
- # into individual term and definition list items.
- #
+
$less_than_tab = $this->tab_width - 1;
- # trim trailing blank lines:
+ // Trim trailing blank lines:
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
- # Process definition terms.
+ // Process definition terms.
$list_str = preg_replace_callback('{
- (?>\A\n?|\n\n+) # leading line
- ( # definition terms = $1
- [ ]{0,'.$less_than_tab.'} # leading whitespace
- (?!\:[ ]|[ ]) # negative lookahead for a definition
- # mark (colon) or more whitespace.
- (?> \S.* \n)+? # actual term (not whitespace).
+ (?>\A\n?|\n\n+) # leading line
+ ( # definition terms = $1
+ [ ]{0,' . $less_than_tab . '} # leading whitespace
+ (?!\:[ ]|[ ]) # negative lookahead for a definition
+ # mark (colon) or more whitespace.
+ (?> \S.* \n)+? # actual term (not whitespace).
)
- (?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed
- # with a definition mark.
+ (?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed
+ # with a definition mark.
}xm',
array($this, '_processDefListItems_callback_dt'), $list_str);
- # Process actual definitions.
+ // Process actual definitions.
$list_str = preg_replace_callback('{
- \n(\n+)? # leading line = $1
- ( # marker space = $2
- [ ]{0,'.$less_than_tab.'} # whitespace before colon
- \:[ ]+ # definition mark (colon)
+ \n(\n+)? # leading line = $1
+ ( # marker space = $2
+ [ ]{0,' . $less_than_tab . '} # whitespace before colon
+ \:[ ]+ # definition mark (colon)
)
- ((?s:.+?)) # definition text = $3
- (?= \n+ # stop at next definition mark,
- (?: # next term or end of text
- [ ]{0,'.$less_than_tab.'} \:[ ] |
+ ((?s:.+?)) # definition text = $3
+ (?= \n+ # stop at next definition mark,
+ (?: # next term or end of text
+ [ ]{0,' . $less_than_tab . '} \:[ ] |
<dt> | \z
)
)
@@ -3033,6 +3426,12 @@ class MarkdownExtraParser extends MarkdownParser {
return $list_str;
}
+
+ /**
+ * Callback for <dt> elements in definition lists
+ * @param array $matches
+ * @return string
+ */
protected function _processDefListItems_callback_dt($matches) {
$terms = explode("\n", trim($matches[1]));
$text = '';
@@ -3042,13 +3441,19 @@ class MarkdownExtraParser extends MarkdownParser {
}
return $text . "\n";
}
+
+ /**
+ * Callback for <dd> elements in definition lists
+ * @param array $matches
+ * @return string
+ */
protected function _processDefListItems_callback_dd($matches) {
$leading_line = $matches[1];
$marker_space = $matches[2];
$def = $matches[3];
if ($leading_line || preg_match('/\n{2,}/', $def)) {
- # Replace marker with the appropriate whitespace indentation
+ // Replace marker with the appropriate whitespace indentation
$def = str_repeat(' ', strlen($marker_space)) . $def;
$def = $this->runBlockGamut($this->outdent($def . "\n\n"));
$def = "\n". $def ."\n";
@@ -3061,15 +3466,18 @@ class MarkdownExtraParser extends MarkdownParser {
return "\n<dd>" . $def . "</dd>\n";
}
-
+ /**
+ * Adding the fenced code block syntax to regular Markdown:
+ *
+ * ~~~
+ * Code block
+ * ~~~
+ *
+ * @param string $text
+ * @return string
+ */
protected function doFencedCodeBlocks($text) {
- #
- # Adding the fenced code block syntax to regular Markdown:
- #
- # ~~~
- # Code block
- # ~~~
- #
+
$less_than_tab = $this->tab_width;
$text = preg_replace_callback('{
@@ -3084,7 +3492,7 @@ class MarkdownExtraParser extends MarkdownParser {
)?
[ ]*
(?:
- '.$this->id_class_attr_catch_re.' # 3: Extra attributes
+ ' . $this->id_class_attr_catch_re . ' # 3: Extra attributes
)?
[ ]* \n # Whitespace and newline following marker.
@@ -3103,6 +3511,12 @@ class MarkdownExtraParser extends MarkdownParser {
return $text;
}
+
+ /**
+ * Callback to process fenced code blocks
+ * @param array $matches
+ * @return string
+ */
protected function _doFencedCodeBlocks_callback($matches) {
$classname =& $matches[2];
$attrs =& $matches[3];
@@ -3121,7 +3535,7 @@ class MarkdownExtraParser extends MarkdownParser {
if ($classname != "") {
if ($classname{0} == '.')
$classname = substr($classname, 1);
- $classes[] = $this->code_class_prefix.$classname;
+ $classes[] = $this->code_class_prefix . $classname;
}
$attr_str = $this->doExtraAttributes($this->code_attr_on_pre ? "pre" : "code", $attrs, null, $classes);
$pre_attr_str = $this->code_attr_on_pre ? $attr_str : '';
@@ -3130,52 +3544,57 @@ class MarkdownExtraParser extends MarkdownParser {
return "\n\n".$this->hashBlock($codeblock)."\n\n";
}
+
+ /**
+ * Replace new lines in fenced code blocks
+ * @param array $matches
+ * @return string
+ */
protected function _doFencedCodeBlocks_newlines($matches) {
return str_repeat("<br$this->empty_element_suffix",
strlen($matches[0]));
}
-
- #
- # Redefining emphasis markers so that emphasis by underscore does not
- # work in the middle of a word.
- #
+ /**
+ * Redefining emphasis markers so that emphasis by underscore does not
+ * work in the middle of a word.
+ * @var array
+ */
protected $em_relist = array(
'' => '(?:(?<!\*)\*(?!\*)|(?<![a-zA-Z0-9_])_(?!_))(?![\.,:;]?\s)',
'*' => '(?<![\s*])\*(?!\*)',
'_' => '(?<![\s_])_(?![a-zA-Z0-9_])',
- );
+ );
protected $strong_relist = array(
'' => '(?:(?<!\*)\*\*(?!\*)|(?<![a-zA-Z0-9_])__(?!_))(?![\.,:;]?\s)',
'**' => '(?<![\s*])\*\*(?!\*)',
'__' => '(?<![\s_])__(?![a-zA-Z0-9_])',
- );
+ );
protected $em_strong_relist = array(
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<![a-zA-Z0-9_])___(?!_))(?![\.,:;]?\s)',
'***' => '(?<![\s*])\*\*\*(?!\*)',
'___' => '(?<![\s_])___(?![a-zA-Z0-9_])',
- );
-
-
- protected function formParagraphs($text) {
- #
- # Params:
- # $text - string to process with html <p> tags
- #
- # Strip leading and trailing lines:
+ );
+
+ /**
+ * Parse text into paragraphs
+ * @param string $text String to process in paragraphs
+ * @param boolean $wrap_in_p Whether paragraphs should be wrapped in <p> tags
+ * @return string HTML output
+ */
+ protected function formParagraphs($text, $wrap_in_p = true) {
+ // Strip leading and trailing lines:
$text = preg_replace('/\A\n+|\n+\z/', '', $text);
-
+
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
- #
- # Wrap <p> tags and unhashify HTML blocks
- #
+ // Wrap <p> tags and unhashify HTML blocks
foreach ($grafs as $key => $value) {
$value = trim($this->runSpanGamut($value));
- # Check if this should be enclosed in a paragraph.
- # Clean tag hashes & block tag hashes are left alone.
- $is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
+ // Check if this should be enclosed in a paragraph.
+ // Clean tag hashes & block tag hashes are left alone.
+ $is_p = $wrap_in_p && !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
if ($is_p) {
$value = "<p>$value</p>";
@@ -3183,28 +3602,28 @@ class MarkdownExtraParser extends MarkdownParser {
$grafs[$key] = $value;
}
- # Join grafs in one text, then unhash HTML tags.
+ // Join grafs in one text, then unhash HTML tags.
$text = implode("\n\n", $grafs);
- # Finish by removing any tag hashes still present in $text.
+ // Finish by removing any tag hashes still present in $text.
$text = $this->unhash($text);
return $text;
}
- ### Footnotes
-
+ /**
+ * Footnotes - Strips link definitions from text, stores the URLs and
+ * titles in hash references.
+ * @param string $text
+ * @return string
+ */
protected function stripFootnotes($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
$less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: [^id]: url "optional title"
+ // Link defs are in the form: [^id]: url "optional title"
$text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\[\^(.+?)\][ ]?: # note_id = $1
+ ^[ ]{0,' . $less_than_tab . '}\[\^(.+?)\][ ]?: # note_id = $1
[ ]*
\n? # maybe *one* newline
( # text = $2 (no blank lines allowed)
@@ -3222,36 +3641,44 @@ class MarkdownExtraParser extends MarkdownParser {
$text);
return $text;
}
+
+ /**
+ * Callback for stripping footnotes
+ * @param array $matches
+ * @return string
+ */
protected function _stripFootnotes_callback($matches) {
$note_id = $this->fn_id_prefix . $matches[1];
$this->footnotes[$note_id] = $this->outdent($matches[2]);
- return ''; # String that will replace the block
+ return ''; // String that will replace the block
}
-
+ /**
+ * Replace footnote references in $text [^id] with a special text-token
+ * which will be replaced by the actual footnote marker in appendFootnotes.
+ * @param string $text
+ * @return string
+ */
protected function doFootnotes($text) {
- #
- # Replace footnote references in $text [^id] with a special text-token
- # which will be replaced by the actual footnote marker in appendFootnotes.
- #
if (!$this->in_anchor) {
$text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text);
}
return $text;
}
-
+ /**
+ * Append footnote list to text
+ * @param string $text
+ * @return string
+ */
protected function appendFootnotes($text) {
- #
- # Append footnote list to text.
- #
$text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
array($this, '_appendFootnotes_callback'), $text);
if (!empty($this->footnotes_ordered)) {
$text .= "\n\n";
$text .= "<div class=\"footnotes\">\n";
- $text .= "<hr". $this->empty_element_suffix ."\n";
+ $text .= "<hr" . $this->empty_element_suffix . "\n";
$text .= "<ol>\n\n";
$attr = "";
@@ -3276,7 +3703,7 @@ class MarkdownExtraParser extends MarkdownParser {
unset($this->footnotes_ref_count[$note_id]);
unset($this->footnotes[$note_id]);
- $footnote .= "\n"; # Need to append newline before parsing.
+ $footnote .= "\n"; // Need to append newline before parsing.
$footnote = $this->runBlockGamut("$footnote\n");
$footnote = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
array($this, '_appendFootnotes_callback'), $footnote);
@@ -3284,12 +3711,12 @@ class MarkdownExtraParser extends MarkdownParser {
$attr = str_replace("%%", ++$num, $attr);
$note_id = $this->encodeAttribute($note_id);
- # Prepare backlink, multiple backlinks if multiple references
+ // Prepare backlink, multiple backlinks if multiple references
$backlink = "<a href=\"#fnref:$note_id\"$attr>$backlink_text</a>";
for ($ref_num = 2; $ref_num <= $ref_count; ++$ref_num) {
$backlink .= " <a href=\"#fnref$ref_num:$note_id\"$attr>$backlink_text</a>";
}
- # Add backlink to last paragraph; create new paragraph if needed.
+ // Add backlink to last paragraph; create new paragraph if needed.
if (preg_match('{</p>$}', $footnote)) {
$footnote = substr($footnote, 0, -4) . " $backlink</p>";
} else {
@@ -3306,16 +3733,22 @@ class MarkdownExtraParser extends MarkdownParser {
}
return $text;
}
+
+ /**
+ * Callback for appending footnotes
+ * @param array $matches
+ * @return string
+ */
protected function _appendFootnotes_callback($matches) {
$node_id = $this->fn_id_prefix . $matches[1];
- # Create footnote marker only if it has a corresponding footnote *and*
- # the footnote hasn't been used by another marker.
+ // Create footnote marker only if it has a corresponding footnote *and*
+ // the footnote hasn't been used by another marker.
if (isset($this->footnotes[$node_id])) {
$num =& $this->footnotes_numbers[$node_id];
if (!isset($num)) {
- # Transfer footnote content to the ordered list and give it its
- # number
+ // Transfer footnote content to the ordered list and give it its
+ // number
$this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
$this->footnotes_ref_count[$node_id] = 1;
$num = $this->footnote_counter++;
@@ -3345,54 +3778,69 @@ class MarkdownExtraParser extends MarkdownParser {
"</sup>";
}
- return "[^".$matches[1]."]";
+ return "[^" . $matches[1] . "]";
}
- ### Abbreviations ###
-
+ /**
+ * Abbreviations - strips abbreviations from text, stores titles in hash
+ * references.
+ * @param string $text
+ * @return string
+ */
protected function stripAbbreviations($text) {
- #
- # Strips abbreviations from text, stores titles in hash references.
- #
$less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: [id]*: url "optional title"
+ // Link defs are in the form: [id]*: url "optional title"
$text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\*\[(.+?)\][ ]?: # abbr_id = $1
+ ^[ ]{0,' . $less_than_tab . '}\*\[(.+?)\][ ]?: # abbr_id = $1
(.*) # text = $2 (no blank lines allowed)
}xm',
array($this, '_stripAbbreviations_callback'),
$text);
return $text;
}
+
+ /**
+ * Callback for stripping abbreviations
+ * @param array $matches
+ * @return string
+ */
protected function _stripAbbreviations_callback($matches) {
$abbr_word = $matches[1];
$abbr_desc = $matches[2];
- if ($this->abbr_word_re)
+ if ($this->abbr_word_re) {
$this->abbr_word_re .= '|';
+ }
$this->abbr_word_re .= preg_quote($abbr_word);
$this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
- return ''; # String that will replace the block
+ return ''; // String that will replace the block
}
-
-
+
+ /**
+ * Find defined abbreviations in text and wrap them in <abbr> elements.
+ * @param string $text
+ * @return string
+ */
protected function doAbbreviations($text) {
- #
- # Find defined abbreviations in text and wrap them in <abbr> elements.
- #
if ($this->abbr_word_re) {
// cannot use the /x modifier because abbr_word_re may
// contain significant spaces:
- $text = preg_replace_callback('{'.
- '(?<![\w\x1A])'.
- '(?:'.$this->abbr_word_re.')'.
- '(?![\w\x1A])'.
- '}',
+ $text = preg_replace_callback('{' .
+ '(?<![\w\x1A])' .
+ '(?:' . $this->abbr_word_re . ')' .
+ '(?![\w\x1A])' .
+ '}',
array($this, '_doAbbreviations_callback'), $text);
}
return $text;
}
+
+ /**
+ * Callback for processing abbreviations
+ * @param array $matches
+ * @return string
+ */
protected function _doAbbreviations_callback($matches) {
$abbr = $matches[0];
if (isset($this->abbr_desciptions[$abbr])) {
