s around
@@ -270,17 +275,39 @@ function _HashHTMLBlocks($text) {
\A\n? # the beginning of the doc
)
( # save in $1
- [ \t]*
+ [ ]{0,'.$less_than_tab.'}
<(hr) # start tag = $2
\b # word break
([^<>])*? #
/?> # the matching end tag
+ [ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
}x',
'_HashHTMLBlocks_callback',
$text);
+ # Special case for standalone HTML comments:
+ $text = preg_replace_callback('{
+ (?:
+ (?<=\n\n) # Starting after a blank line
+ | # or
+ \A\n? # the beginning of the doc
+ )
+ ( # save in $1
+ [ ]{0,'.$less_than_tab.'}
+ (?s:
+
+ )
+ [ \t]*
+ (?=\n{2,}|\Z) # followed by a blank line or end of document
+ )
+ }x',
+ '_HashHTMLBlocks_callback',
+ $text);
+
return $text;
}
function _HashHTMLBlocks_callback($matches) {
@@ -303,9 +330,9 @@ function _RunBlockGamut($text) {
# Do Horizontal Rules:
$text = preg_replace(
- array('/^( ?\* ?){3,}$/m',
- '/^( ?- ?){3,}$/m',
- '/^( ?_ ?){3,}$/m'),
+ array('{^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$}mx',
+ '{^[ ]{0,2}([ ]? -[ ]?){3,}[ \t]*$}mx',
+ '{^[ ]{0,2}([ ]? _[ ]?){3,}[ \t]*$}mx'),
"\n tags.
@@ -952,6 +1029,7 @@ function _DoAutoLinks($text) {
# Email addresses: '._RunSpanGamut(_UnslashQuotes('\\1')).'
\n\n'"),
$text);
@@ -645,7 +676,7 @@ function _DoLists($text) {
#
# Form HTML ordered (numbered) and unordered (bulleted) lists.
#
- global $md_tab_width;
+ global $md_tab_width, $md_list_level;
$less_than_tab = $md_tab_width - 1;
# Re-usable patterns to match list item bullets and number markers:
@@ -653,27 +684,45 @@ function _DoLists($text) {
$marker_ol = '\d+[.]';
$marker_any = "(?:$marker_ul|$marker_ol)";
- $text = preg_replace_callback("{
- ( # $1
- ( # $2
- ^[ ]{0,$less_than_tab}
- ($marker_any) # $3 - first list item marker
- [ \\t]+
+ # Re-usable pattern to match any entirel ul or ol list:
+ $whole_list = '
+ ( # $1 = whole list
+ ( # $2
+ [ ]{0,'.$less_than_tab.'}
+ ('.$marker_any.') # $3 = first list item marker
+ [ \t]+
+ )
+ (?s:.+?)
+ ( # $4
+ \z
+ |
+ \n{2,}
+ (?=\S)
+ (?! # Negative lookahead for another list item marker
+ [ \t]*
+ '.$marker_any.'[ \t]+
)
- (?s:.+?)
- ( # $4
- \\z
- |
- \\n{2,}
- (?=\\S)
- (?! # Negative lookahead for another list item marker
- [ \\t]*
- {$marker_any}[ \\t]+
- )
- )
- )
- }xm",
- '_DoLists_callback', $text);
+ )
+ )
+ '; // mx
+
+ # We use a different prefix before nested lists than top-level lists.
+ # See extended comment in _ProcessListItems().
+
+ if ($md_list_level) {
+ $text = preg_replace_callback('{
+ ^
+ '.$whole_list.'
+ }mx',
+ '_DoLists_callback', $text);
+ }
+ else {
+ $text = preg_replace_callback('{
+ (?:(?<=\n\n)|\A\n?)
+ '.$whole_list.'
+ }mx',
+ '_DoLists_callback', $text);
+ }
return $text;
}
@@ -684,17 +733,46 @@ function _DoLists_callback($matches) {
$marker_any = "(?:$marker_ul|$marker_ol)";
$list = $matches[1];
- $list_type = preg_match('/[*+-]/', $matches[3]) ? "ul" : "ol";
+ $list_type = preg_match("/$marker_ul/", $matches[3]) ? "ul" : "ol";
# Turn double returns into triple returns, so that we can make a
# paragraph for the last item in a list, if necessary:
$list = preg_replace("/\n{2,}/", "\n\n\n", $list);
$result = _ProcessListItems($list, $marker_any);
- $result = "<$list_type>\n" . $result . "\n\n";
+ $result = "<$list_type>\n" . $result . "\n";
return $result;
}
function _ProcessListItems($list_str, $marker_any) {
+#
+# Process the contents of a single ordered or unordered list, splitting it
+# into individual list items.
+#
+ global $md_list_level;
+
+ # The $md_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.".
+
+ $md_list_level++;
+
# trim trailing blank lines:
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
@@ -708,16 +786,16 @@ function _ProcessListItems($list_str, $marker_any) {
}xm',
'_ProcessListItems_callback', $list_str);
+ $md_list_level--;
return $list_str;
}
function _ProcessListItems_callback($matches) {
$item = $matches[4];
- $leading_line = $matches[1];
- $leading_space = $matches[2];
+ $leading_line =& $matches[1];
+ $leading_space =& $matches[2];
if ($leading_line || preg_match('/\n{2,}/', $item)) {
$item = _RunBlockGamut(_Outdent($item));
- #$item =~ s/\n+/\n/g;
}
else {
# Recursion for sub-lists:
@@ -753,7 +831,7 @@ function _DoCodeBlocks_callback($matches) {
$codeblock = $matches[1];
$codeblock = _EncodeCode(_Outdent($codeblock));
- $codeblock = _Detab($codeblock);
+// $codeblock = _Detab($codeblock);
# trim leading newlines and trailing whitespace
$codeblock = preg_replace(array('/\A\n+/', '/\s+\z/'), '', $codeblock);
@@ -834,7 +912,7 @@ function _EncodeCode($_) {
function _DoItalicsAndBold($text) {
# must go first:
- $text = preg_replace('{ (\*\*|__) (?=\S) (.+?) (?<=\S) \1 }sx',
+ $text = preg_replace('{ (\*\*|__) (?=\S) (.+?[*_]*) (?<=\S) \1 }sx',
'\2', $text);
# Then :
$text = preg_replace('{ (\*|_) (?=\S) (.+?) (?<=\S) \1 }sx',
@@ -890,7 +968,6 @@ function _FormParagraphs($text) {
$text = preg_replace(array('/\A\n+/', '/\n+\z/'), '', $text);
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
- $count = count($grafs);
#
# Wrap ` tags inside `
` are no longer
- indented in the HTML output.
-
-* PHP Markdown can now be used as a modifier by the Smarty
- templating engine. Rename the file to "modifier.markdown.php"
- and put it in your smarty plugins folder.
-
-* Now works as a bBlog formatter. Rename the file to
- "modifier.markdown.php" and place it in the "bBlog_plugins"
- folder.
-
-
-1.0fc1: Wed 8 Jul 2004
-
-* Greatly simplified the rules for code blocks. No more colons
- necessary; if it's indented (4 spaces or 1 tab), it's a code block.
-
-* Unordered list items can now be denoted by any of the following
- bullet markers: [*+-]
-
-* Replacing `"` with `"` to fix literal quotes within title
- attributes.
-
-
-1.0b9: Sun 27 Jun 2004
-
-* Replacing `"` with `"` to fix literal quotes within img alt
- attributes.
-
-
-1.0b8: Wed 23 Jun 2004
-
-* In WordPress, solved a bug where PHP Markdown did not deactivate
- the paragraph filter, converting all returns to a line break.
- The "texturize" filter was being disabled instead.
-
-* Added 'math' tags to block-level tag patterns in `_HashHTMLBlocks()`.
- Please disregard all the 'math'-tag related items in 1.0b7.
-
-* Commented out some vestigial code in `_EscapeSpecialChars()`
-
-
-1.0b7: Sat 12 Jun 2004
-
-* Added 'math' to `$tags_to_skip` pattern, for MathML users.
-
-* Tweaked regex for identifying HTML entities in
- `_EncodeAmpsAndAngles()`, so as to allow for the very long entity
- names used by MathML. (Thanks to Jacques Distler for the patch.)
-
-* Changed the internals of `_TokenizeHTML` to lower the PHP version
- requirement to PHP 4.0.5.
-
-
-1.0b6: Sun 6 Jun 2004
-
-* Added a WordPress plugin interface. This means that you can
- directly put the "markdown.php" file into the "wp-content/plugins"
- directory and then activate it from the administrative interface.
-
-* Added a Textile compatibility interface. Rename this file to
- "classTextile.php" and it can replace Textile anywhere.
-
-* The title attribute of reference-style links were ignored.
- This is now fixed.
-
-* Changed internal variables names so that they begin with `md_`
- instead of `g_`. This should reduce the risk of name collision with
- other programs.
-
-
-1.0b5: Sun 2 May 2004
-
-* Workaround for supporting `` and `
` as block-level tags.
- This only works if the start and end tags are on lines by
- themselves.
-
-* Three or more underscores can now be used for horizontal rules.
-
-* Lines containing only whitespace are trimmed from blockquotes.
-
-* You can now optionally wrap URLs with angle brackets -- like so:
- `