tags.
- $tags_to_skip = "!<(/?)(?:pre|code|kbd|script)[\s>]!";
-
foreach ($tokens as $cur_token) {
if ($cur_token[0] == 'tag') {
$cur_token[1] = str_replace(array('*', '_'),
- array($g_escape_table['*'], $g_escape_table['_']),
+ array($md_escape_table['*'], $md_escape_table['_']),
$cur_token[1]);
$text .= $cur_token[1];
} else {
$t = $cur_token[1];
- if (! $in_pre) {
- $t = _EncodeBackslashEscapes($t);
- # $t =~ s{([a-z])/([a-z])}{$1 / $2}ig;
- }
+ $t = _EncodeBackslashEscapes($t);
$text .= $t;
}
}
@@ -227,48 +278,49 @@ function _EscapeSpecialChars($text) {
function _DoAnchors($text) {
- global $g_nested_brackets;
-
+ global $md_nested_brackets;
+ #
+ # First, handle reference-style links: [link text] [id]
+ #
$text = preg_replace_callback("{
( # wrap whole match in $1
\\[
- ($g_nested_brackets) # link text = $2
+ ($md_nested_brackets) # link text = $2
\\]
[ ]? # one optional space
(?:\\n[ ]*)? # one optional newline followed by spaces
\\[
- (.*?) # id = $3
+ (.*?) # id = $3
\\]
)
}xs",
'_DoAnchors_reference_callback', $text);
-
+
$text = preg_replace_callback("{
( # wrap whole match in $1
\\[
- ($g_nested_brackets) # link text = $2
+ ($md_nested_brackets) # link text = $2
\\]
\\( # literal paren
[ \\t]*
- (.+?) # href = $3
+ ? # href = $3
[ \\t]*
- ( # title = $4
+ ( # $4
(['\"]) # quote char = $5
- .*?
+ (.*?) # Title = $6
\\5 # matching quote
)? # title is optional
\\)
)
}xs",
'_DoAnchors_inline_callback', $text);
-
+
return $text;
}
function _DoAnchors_reference_callback($matches) {
- global $g_urls, $g_titles;
- $result;
+ global $md_urls, $md_titles, $md_escape_table;
$whole_match = $matches[1];
$link_text = $matches[2];
$link_id = strtolower($matches[3]);
@@ -277,15 +329,18 @@ function _DoAnchors_reference_callback($matches) {
$link_id = strtolower($link_text); # for shortcut links like [this][].
}
- if (isset($g_urls[$link_id])) {
- $url = $g_urls[$link_id];
- $url = str_replace(array('*', '_'),
- array('*', '_'), $url);
- $result = "? # src url = $3
[ \\t]*
- ( # title = $4
+ ( # $4
(['\"]) # quote char = $5
- .*?
+ (.*?) # title = $6
\\5 # matching quote
[ \\t]*
)? # title is optional
@@ -362,8 +421,7 @@ function _DoImages($text) {
return $text;
}
function _DoImages_reference_callback($matches) {
- global $g_urls, $g_titles, $g_empty_element_suffix;
- $result;
+ global $md_urls, $md_titles, $md_empty_element_suffix, $md_escape_table;
$whole_match = $matches[1];
$alt_text = $matches[2];
$link_id = strtolower($matches[3]);
@@ -371,43 +429,55 @@ function _DoImages_reference_callback($matches) {
if ($link_id == "") {
$link_id = strtolower($alt_text); # for shortcut links like ![this][].
}
-
- if (isset($g_urls[$link_id])) {
- $url = $g_urls[$link_id];
- $url = str_replace(array('*', '_'),
- array('*', '_'), $url);
+
+ $alt_text = str_replace('"', '"', $alt_text);
+ if (isset($md_urls[$link_id])) {
+ $url = $md_urls[$link_id];
+ # We've got to encode these to avoid conflicting with italics/bold.
+ $url = str_replace(array('*', '_'),
+ array($md_escape_table['*'], $md_escape_table['_']),
+ $url);
$result = "![\"$alt_text\"";](\"$url\")
\n";
+ $result = _ProcessListItems($list, $marker_any);
+ $result = "<$list_type>\n" . $result . "\n\n";
return $result;
}
-function _ProcessListItems($list_str) {
+function _ProcessListItems($list_str, $marker_any) {
# trim trailing blank lines:
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
$list_str = preg_replace_callback('{
(\n)? # leading line = $1
(^[ \t]*) # leading whitespace = $2
- (\*|\d+[.]) [ \t]+ # list marker = $3
+ ('.$marker_any.') [ \t]+ # list marker = $3
((?s:.+?) # list item text = $4
(\n{1,2}))
- (?= \n* (\z | \2 (\*|\d+[.]) [ \t]+))
+ (?= \n* (\z | \2 ('.$marker_any.') [ \t]+))
}xm',
'_ProcessListItems_callback', $list_str);
@@ -508,41 +596,30 @@ function _ProcessListItems_callback($matches) {
function _DoCodeBlocks($text) {
- global $g_tab_width;
+ global $md_tab_width;
$text = preg_replace_callback("{
- (.?) # $1 = preceding character
- (:) # $2 = colon delimiter
- (\\n+) # $3 = newlines after colon
- ( # $4 = the code block -- one or more lines, starting with a space/tab
+ (?:\\n\\n|\\A)
+ ( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
- (?:[ ]\{$g_tab_width} | \\t) # Lines must start with a tab or a tab-width of spaces
- .*\\n+
+ (?:[ ]\{$md_tab_width} | \\t) # Lines must start with a tab or a tab-width of spaces
+ .*\\n+
)+
)
- ((?=^[ ]{0,$g_tab_width}\\S)|\\Z) # Lookahead for non-space at line-start, or end of doc
+ ((?=^[ ]{0,$md_tab_width}\\S)|\\Z) # Lookahead for non-space at line-start, or end of doc
}xm",
'_DoCodeBlocks_callback', $text);
return $text;
}
function _DoCodeBlocks_callback($matches) {
- $prevchar = $matches[1];
- $newlines = $matches[2];
- $codeblock = $matches[4];
+ $codeblock = $matches[1];
- $result; # return value
-
-
- $prefix = "";
- if (!(preg_match('/\s/', $prevchar) || ($prevchar == ""))) {
- $prefix = "$prevchar:";
- }
$codeblock = _EncodeCode(_Outdent($codeblock));
$codeblock = _Detab($codeblock);
# trim leading newlines and trailing whitespace
$codeblock = preg_replace(array('/\A\n+/', '/\s+\z/'), '', $codeblock);
-
- $result = $prefix . "\n\n" . $codeblock . "\n
\n\n";
+
+ $result = "\n\n" . $codeblock . "\n
\n\n";
return $result;
}
@@ -550,8 +627,8 @@ function _DoCodeBlocks_callback($matches) {
function _DoCodeSpans($text) {
$text = preg_replace_callback("@
- (`+) # Opening run of `
- (.+?) # the code block
+ (`+) # $1 = Opening run of `
+ (.+?) # $2 = The code block
(?'),
array('<', '>'), $_);
- # Now, escape characters that are magic in Markdown:
- $_ = str_replace(array_keys($g_escape_table),
- array_values($g_escape_table), $_);
+ $_ = str_replace(array_keys($md_escape_table),
+ array_values($md_escape_table), $_);
return $_;
}
@@ -618,26 +690,35 @@ function _DoBlockQuotes($text) {
}
function _DoBlockQuotes_callback($matches) {
$bq = $matches[1];
- $bq = preg_replace('/^[ \t]*>[ \t]?/m', '', $bq);
+ # trim one level of quoting - trim whitespace-only lines
+ $bq = preg_replace(array('/^[ \t]*>[ \t]?/m', '/^[ \t]+$/m'), '', $bq);
$bq = _RunBlockGamut($bq); # recurse
- $bq = preg_replace('/^/m', "\t", $bq);
-
+
+ $bq = preg_replace('/^/m', " ", $bq);
+ # These leading spaces screw with content, so we need to fix that:
+ $bq = preg_replace_callback('{(\s*.+?
)}sx',
+ '_DoBlockQuotes_callback2', $bq);
+
return "\n$bq\n
\n\n";
}
+function _DoBlockQuotes_callback2($matches) {
+ $pre = $matches[1];
+ $pre = preg_replace('/^ /m', '', $pre);
+ return $pre;
+}
function _FormParagraphs($text) {
- global $g_html_blocks;
+ global $md_html_blocks;
# Strip leading and trailing lines:
$text = preg_replace(array('/\A\n+/', '/\n+\z/'), '', $text);
- $grafs = preg_split('/\n{2,}/', $text);
- $count = count($graph);
-
+ $grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
+ $count = count($grafs);
foreach ($grafs as $key => $value) {
- if (!isset( $g_html_blocks[$value] )) {
+ if (!isset( $md_html_blocks[$value] )) {
$value = _RunSpanGamut($value);
$value = preg_replace('/^([ \t]*)/', '', $value);
$value .= "
";
@@ -645,10 +726,9 @@ function _FormParagraphs($text) {
}
}
-
foreach ($grafs as $key => $value) {
- if (isset( $g_html_blocks[$value] )) {
- $grafs[$key] = $g_html_blocks[$value];
+ if (isset( $md_html_blocks[$value] )) {
+ $grafs[$key] = $md_html_blocks[$value];
}
}
@@ -657,7 +737,7 @@ function _FormParagraphs($text) {
function _EncodeAmpsAndAngles($text) {
- $text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w{1,8});)/',
+ $text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
'&', $text);;
# Encode naked <'s
@@ -668,17 +748,17 @@ function _EncodeAmpsAndAngles($text) {
function _EncodeBackslashEscapes($text) {
- global $g_escape_table, $g_backslash_escape_table;
+ global $md_escape_table, $md_backslash_escape_table;
# Must process escaped backslashes first.
- return str_replace(array_keys($g_backslash_escape_table),
- array_values($g_backslash_escape_table), $text);
+ return str_replace(array_keys($md_backslash_escape_table),
+ array_values($md_backslash_escape_table), $text);
}
function _DoAutoLinks($text) {
$text = preg_replace("!<((https?|ftp):[^'\">\\s]+)>!",
'\1', $text);
-
+
# Email addresses:
$text = preg_replace('{
<
@@ -691,7 +771,7 @@ function _DoAutoLinks($text) {
}exi',
"_EncodeEmailAddress(_UnescapeSpecialChars(_UnslashQuotes('\\1')))",
$text);
-
+
return $text;
}
@@ -700,10 +780,12 @@ function _EncodeEmailAddress($addr) {
$addr = "mailto:" . $addr;
$length = strlen($addr);
+ # leave ':' alone (to spot mailto: later)
$addr = preg_replace_callback('/([^\:])/',
'_EncodeEmailAddress_callback', $addr);
$addr = "$addr";
+ # strip the mailto: from the visible part
$addr = preg_replace('/">.+?:/', '">', $addr);
return $addr;
@@ -711,6 +793,8 @@ function _EncodeEmailAddress($addr) {
function _EncodeEmailAddress_callback($matches) {
$char = $matches[1];
$r = rand(0, 100);
+ # roughly 10% raw, 45% hex, 45% dec
+ # '@' *must* be encoded. I insist.
if ($r > 90 && $char != '@') return $char;
if ($r < 45) return '&#x'.dechex(ord($char)).';';
return '&#'.ord($char).';';
@@ -718,57 +802,49 @@ function _EncodeEmailAddress_callback($matches) {
function _UnescapeSpecialChars($text) {
- global $g_escape_table;
- return str_replace(array_values($g_escape_table),
- array_keys($g_escape_table), $text);
+ global $md_escape_table;
+ return str_replace(array_values($md_escape_table),
+ array_keys($md_escape_table), $text);
}
-function _TokenizeHTML($str) {
- $pos = 0;
- $len = strlen($str);
- $tokens = array();
+if (!function_exists('_TokenizeHTML')) {
+ function _TokenizeHTML($str) {
+ $index = 0;
+ $tokens = array();
- $depth = 6;
- $nested_tags = str_repeat('(?:<[a-z\/!$](?:[^<>]|',$depth)
- .str_repeat(')*>)', $depth);
- $match = "(?s:)|". # comment
- "(?s:<\?.*?\?>)|". # processing instruction
- "$nested_tags"; # nested tags
-
- preg_match_all("/($match)/", $str, $matches,
- PREG_SET_ORDER | PREG_OFFSET_CAPTURE);
+ $depth = 6;
+ $nested_tags = str_repeat('(?:<[a-z\/!$](?:[^<>]|',$depth)
+ .str_repeat(')*>)', $depth);
+ $match = "(?s:)|". # comment
+ "(?s:<\?.*?\?>)|". # processing instruction
+ "$nested_tags"; # nested tags
- foreach ($matches as $element) {
- $whole_tag = $element[0][0];
- $tag_start = $element[0][1];
- $sec_start = $tag_start + strlen($whole_tag);
- if ($pos < $tag_start) {
- array_push($tokens, array('text',
- substr($str, $pos, $tag_start - $pos)));
+ $parts = preg_split("/($match)/", $str, -1, PREG_SPLIT_DELIM_CAPTURE);
+
+ foreach ($parts as $part) {
+ if (++$index % 2 && $part != '')
+ array_push($tokens, array('text', $part));
+ else
+ array_push($tokens, array('tag', $part));
}
- array_push($tokens, array('tag', $whole_tag));
- $pos = $sec_start;
+
+ return $tokens;
}
-
- if ($pos < $len)
- array_push($tokens, array('text',
- substr($str, $pos, $len - $pos)));
- return $tokens;
}
function _Outdent($text) {
- global $g_tab_width;
- return preg_replace("/^(\\t|[ ]{1,$g_tab_width})/m", "", $text);
+ global $md_tab_width;
+ return preg_replace("/^(\\t|[ ]{1,$md_tab_width})/m", "", $text);
}
function _Detab($text) {
- global $g_tab_width;
+ global $md_tab_width;
$text = preg_replace(
"/(.*?)\t/e",
- "'\\1'.str_repeat(' ', $g_tab_width - strlen('\\1') % $g_tab_width)",
+ "'\\1'.str_repeat(' ', $md_tab_width - strlen('\\1') % $md_tab_width)",
$text);
return $text;
}
@@ -778,13 +854,4 @@ function _UnslashQuotes($text) {
return str_replace('\"', '"', $text);
}
-// And now for the filters
-remove_filter('the_content', 'wpautop');
-remove_filter('the_excerpt', 'wpautop');
-remove_filter('comment_text', 'wpautop');
-
-add_filter('the_content', 'Markdown');
-add_filter('the_excerpt', 'Markdown');
-remove_filter('comment_text', 'Markdown');
-
?>
\ No newline at end of file