diff --git a/lib/pico.php b/lib/pico.php index d2230bd..608c89d 100644 --- a/lib/pico.php +++ b/lib/pico.php @@ -133,6 +133,7 @@ class Pico { $content = preg_replace('#/\*.+?\*/#s', '', $content); // Remove comments and meta $content = str_replace('%base_url%', $this->base_url(), $content); $content = Markdown($content); + if (function_exists('SmartyPants')) $content = SmartyPants($content); return $content; } @@ -336,4 +337,4 @@ class Pico { } -?> \ No newline at end of file +?> diff --git a/plugins/smartypants.php b/plugins/smartypants.php new file mode 100644 index 0000000..0ab2beb --- /dev/null +++ b/plugins/smartypants.php @@ -0,0 +1,763 @@ + +# +# Original SmartyPants +# Copyright (c) 2003-2004 John Gruber +# +# + + +define( 'SMARTYPANTS_VERSION', "1.5.1f" ); # Unreleased + + +# +# Default configuration: +# +# 1 -> "--" for em-dashes; no en-dash support +# 2 -> "---" for em-dashes; "--" for en-dashes +# 3 -> "--" for em-dashes; "---" for en-dashes +# See docs for more configuration options. +# +define( 'SMARTYPANTS_ATTR', 1 ); + + +# SmartyPants will not alter the content of these tags: +define( 'SMARTYPANTS_TAGS_TO_SKIP', 'pre|code|kbd|script|style|math'); + + +### Standard Function Interface ### + +define( 'SMARTYPANTS_PARSER_CLASS', 'SmartyPants_Parser' ); + +function SmartyPants($text, $attr = SMARTYPANTS_ATTR) { +# +# Initialize the parser and return the result of its transform method. +# + # Setup static parser array. + static $parser = array(); + if (!isset($parser[$attr])) { + $parser_class = SMARTYPANTS_PARSER_CLASS; + $parser[$attr] = new $parser_class($attr); + } + + # Transform text using parser. + return $parser[$attr]->transform($text); +} + +function SmartQuotes($text, $attr = null) { + switch ($attr) { + case 0: return $text; + case 2: $attr = 'qb'; break; + default: $attr = 'q'; break; + } + return SmartyPants($text, $attr); +} + +function SmartDashes($text, $attr = null) { + switch ($attr) { + case 0: return $text; + case 2: $attr = 'D'; break; + case 3: $attr = 'i'; break; + default: $attr = 'd'; break; + } + return SmartyPants($text, $attr); +} + +function SmartElipsis($text, $attr = null) { + switch ($attr) { + case 0: return $text; + default: $attr = 'e'; break; + } + return SmartyPants($text, $attr); +} + + +### WordPress Plugin Interface ### + +/* +Plugin Name: SmartyPants +Plugin URI: http://michelf.ca/projects/php-smartypants/ +Description: SmartyPants is a web publishing utility that translates plain ASCII punctuation characters into “smart” typographic punctuation HTML entities. This plugin replace the default WordPress Texturize algorithm for the content and the title of your posts, the comments body and author name, and everywhere else Texturize normally apply. Based on the original Perl version by John Gruber. +Version: 1.5.1f +Author: Michel Fortin +Author URI: http://michelf.ca/ +*/ + +if (isset($wp_version)) { + # Remove default Texturize filter that would conflict with SmartyPants. + remove_filter('category_description', 'wptexturize'); + remove_filter('list_cats', 'wptexturize'); + remove_filter('comment_author', 'wptexturize'); + remove_filter('comment_text', 'wptexturize'); + remove_filter('single_post_title', 'wptexturize'); + remove_filter('the_title', 'wptexturize'); + remove_filter('the_content', 'wptexturize'); + remove_filter('the_excerpt', 'wptexturize'); + remove_filter('the_tags', 'wptexturize'); + # Add SmartyPants filter. + add_filter('category_description', 'SmartyPants', 11); + add_filter('list_cats', 'SmartyPants', 11); + add_filter('comment_author', 'SmartyPants', 11); + add_filter('comment_text', 'SmartyPants', 11); + add_filter('single_post_title', 'SmartyPants', 11); + add_filter('the_title', 'SmartyPants', 11); + add_filter('the_content', 'SmartyPants', 11); + add_filter('the_excerpt', 'SmartyPants', 11); + add_filter('the_tags', 'SmartyPants', 11); +} + + +### Smarty Modifier Interface ### + +function smarty_modifier_smartypants($text, $attr = NULL) { + return SmartyPants($text, $attr); +} + + +# +# SmartyPants Parser +# + +class SmartyPants_Parser { + + # Options to specify which transformations to make: + var $do_nothing = 0; + var $do_quotes = 0; + var $do_backticks = 0; + var $do_dashes = 0; + var $do_ellipses = 0; + var $do_stupefy = 0; + var $convert_quot = 0; # should we translate " entities into normal quotes? + + function SmartyPants_Parser($attr = SMARTYPANTS_ATTR) { + # + # Initialize a SmartyPants_Parser with certain attributes. + # + # Parser attributes: + # 0 : do nothing + # 1 : set all + # 2 : set all, using old school en- and em- dash shortcuts + # 3 : set all, using inverted old school en and em- dash shortcuts + # + # q : quotes + # b : backtick quotes (``double'' only) + # B : backtick quotes (``double'' and `single') + # d : dashes + # D : old school dashes + # i : inverted old school dashes + # e : ellipses + # w : convert " entities to " for Dreamweaver users + # + if ($attr == "0") { + $this->do_nothing = 1; + } + else if ($attr == "1") { + # Do everything, turn all options on. + $this->do_quotes = 1; + $this->do_backticks = 1; + $this->do_dashes = 1; + $this->do_ellipses = 1; + } + else if ($attr == "2") { + # Do everything, turn all options on, use old school dash shorthand. + $this->do_quotes = 1; + $this->do_backticks = 1; + $this->do_dashes = 2; + $this->do_ellipses = 1; + } + else if ($attr == "3") { + # Do everything, turn all options on, use inverted old school dash shorthand. + $this->do_quotes = 1; + $this->do_backticks = 1; + $this->do_dashes = 3; + $this->do_ellipses = 1; + } + else if ($attr == "-1") { + # Special "stupefy" mode. + $this->do_stupefy = 1; + } + else { + $chars = preg_split('//', $attr); + foreach ($chars as $c){ + if ($c == "q") { $this->do_quotes = 1; } + else if ($c == "b") { $this->do_backticks = 1; } + else if ($c == "B") { $this->do_backticks = 2; } + else if ($c == "d") { $this->do_dashes = 1; } + else if ($c == "D") { $this->do_dashes = 2; } + else if ($c == "i") { $this->do_dashes = 3; } + else if ($c == "e") { $this->do_ellipses = 1; } + else if ($c == "w") { $this->convert_quot = 1; } + else { + # Unknown attribute option, ignore. + } + } + } + } + + function transform($text) { + + if ($this->do_nothing) { + return $text; + } + + $tokens = $this->tokenizeHTML($text); + $result = ''; + $in_pre = 0; # Keep track of when we're inside 
 or  tags.
+
+		$prev_token_last_char = ""; # This is a cheat, used to get some context
+									# for one-character tokens that consist of 
+									# just a quote char. What we do is remember
+									# the last character of the previous text
+									# token, to use as context to curl single-
+									# character quote tokens correctly.
+
+		foreach ($tokens as $cur_token) {
+			if ($cur_token[0] == "tag") {
+				# Don't mess with quotes inside tags.
+				$result .= $cur_token[1];
+				if (preg_match('@<(/?)(?:'.SMARTYPANTS_TAGS_TO_SKIP.')[\s>]@', $cur_token[1], $matches)) {
+					$in_pre = isset($matches[1]) && $matches[1] == '/' ? 0 : 1;
+				}
+			} else {
+				$t = $cur_token[1];
+				$last_char = substr($t, -1); # Remember last char of this token before processing.
+				if (! $in_pre) {
+					$t = $this->educate($t, $prev_token_last_char);
+				}
+				$prev_token_last_char = $last_char;
+				$result .= $t;
+			}
+		}
+
+		return $result;
+	}
+
+
+	function educate($t, $prev_token_last_char) {
+		$t = $this->processEscapes($t);
+
+		if ($this->convert_quot) {
+			$t = preg_replace('/"/', '"', $t);
+		}
+
+		if ($this->do_dashes) {
+			if ($this->do_dashes == 1) $t = $this->educateDashes($t);
+			if ($this->do_dashes == 2) $t = $this->educateDashesOldSchool($t);
+			if ($this->do_dashes == 3) $t = $this->educateDashesOldSchoolInverted($t);
+		}
+
+		if ($this->do_ellipses) $t = $this->educateEllipses($t);
+
+		# Note: backticks need to be processed before quotes.
+		if ($this->do_backticks) {
+			$t = $this->educateBackticks($t);
+			if ($this->do_backticks == 2) $t = $this->educateSingleBackticks($t);
+		}
+
+		if ($this->do_quotes) {
+			if ($t == "'") {
+				# Special case: single-character ' token
+				if (preg_match('/\S/', $prev_token_last_char)) {
+					$t = "’";
+				}
+				else {
+					$t = "‘";
+				}
+			}
+			else if ($t == '"') {
+				# Special case: single-character " token
+				if (preg_match('/\S/', $prev_token_last_char)) {
+					$t = "”";
+				}
+				else {
+					$t = "“";
+				}
+			}
+			else {
+				# Normal case:
+				$t = $this->educateQuotes($t);
+			}
+		}
+
+		if ($this->do_stupefy) $t = $this->stupefyEntities($t);
+		
+		return $t;
+	}
+
+
+	function educateQuotes($_) {
+	#
+	#   Parameter:  String.
+	#
+	#   Returns:    The string, with "educated" curly quote HTML entities.
+	#
+	#   Example input:  "Isn't this fun?"
+	#   Example output: “Isn’t this fun?”
+	#
+		# Make our own "punctuation" character class, because the POSIX-style
+		# [:PUNCT:] is only available in Perl 5.6 or later:
+		$punct_class = "[!\"#\\$\\%'()*+,-.\\/:;<=>?\\@\\[\\\\\]\\^_`{|}~]";
+
+		# Special case if the very first character is a quote
+		# followed by punctuation at a non-word-break. Close the quotes by brute force:
+		$_ = preg_replace(
+			array("/^'(?=$punct_class\\B)/", "/^\"(?=$punct_class\\B)/"),
+			array('’',                 '”'), $_);
+
+
+		# Special case for double sets of quotes, e.g.:
+		#   
He said, "'Quoted' words in a larger quote."

+		$_ = preg_replace(
+			array("/\"'(?=\w)/",    "/'\"(?=\w)/"),
+			array('“‘', '‘“'), $_);
+
+		# Special case for decade abbreviations (the '80s):
+		$_ = preg_replace("/'(?=\\d{2}s)/", '’', $_);
+
+		$close_class = '[^\ \t\r\n\[\{\(\-]';
+		$dec_dashes = '&\#8211;|&\#8212;';
+
+		# Get most opening single quotes:
+		$_ = preg_replace("{
+			(
+				\\s          |   # a whitespace char, or
+				       |   # a non-breaking space entity, or
+				--          |   # dashes, or
+				&[mn]dash;  |   # named dash entities
+				$dec_dashes |   # or decimal entities
+				&\\#x201[34];    # or hex
+			)
+			'                   # the quote
+			(?=\\w)              # followed by a word character
+			}x", '\1‘', $_);
+		# Single closing quotes:
+		$_ = preg_replace("{
+			($close_class)?
+			'
+			(?(1)|          # If $1 captured, then do nothing;
+			  (?=\\s | s\\b)  # otherwise, positive lookahead for a whitespace
+			)               # char or an 's' at a word ending position. This
+							# is a special case to handle something like:
+							# \"Custer's Last Stand.\"
+			}xi", '\1’', $_);
+
+		# Any remaining single quotes should be opening ones:
+		$_ = str_replace("'", '‘', $_);
+
+
+		# Get most opening double quotes:
+		$_ = preg_replace("{
+			(
+				\\s          |   # a whitespace char, or
+				       |   # a non-breaking space entity, or
+				--          |   # dashes, or
+				&[mn]dash;  |   # named dash entities
+				$dec_dashes |   # or decimal entities
+				&\\#x201[34];    # or hex
+			)
+			\"                   # the quote
+			(?=\\w)              # followed by a word character
+			}x", '\1“', $_);
+
+		# Double closing quotes:
+		$_ = preg_replace("{
+			($close_class)?
+			\"
+			(?(1)|(?=\\s))   # If $1 captured, then do nothing;
+							   # if not, then make sure the next char is whitespace.
+			}x", '\1”', $_);
+
+		# Any remaining quotes should be opening ones.
+		$_ = str_replace('"', '“', $_);
+
+		return $_;
+	}
+
+
+	function educateBackticks($_) {
+	#
+	#   Parameter:  String.
+	#   Returns:    The string, with ``backticks'' -style double quotes
+	#               translated into HTML curly quote entities.
+	#
+	#   Example input:  ``Isn't this fun?''
+	#   Example output: “Isn't this fun?”
+	#
+
+		$_ = str_replace(array("``",       "''",),
+						 array('“', '”'), $_);
+		return $_;
+	}
+
+
+	function educateSingleBackticks($_) {
+	#
+	#   Parameter:  String.
+	#   Returns:    The string, with `backticks' -style single quotes
+	#               translated into HTML curly quote entities.
+	#
+	#   Example input:  `Isn't this fun?'
+	#   Example output: ‘Isn’t this fun?’
+	#
+
+		$_ = str_replace(array("`",       "'",),
+						 array('‘', '’'), $_);
+		return $_;
+	}
+
+
+	function educateDashes($_) {
+	#
+	#   Parameter:  String.
+	#
+	#   Returns:    The string, with each instance of "--" translated to
+	#               an em-dash HTML entity.
+	#
+
+		$_ = str_replace('--', '—', $_);
+		return $_;
+	}
+
+
+	function educateDashesOldSchool($_) {
+	#
+	#   Parameter:  String.
+	#
+	#   Returns:    The string, with each instance of "--" translated to
+	#               an en-dash HTML entity, and each "---" translated to
+	#               an em-dash HTML entity.
+	#
+
+		#                      em         en
+		$_ = str_replace(array("---",     "--",),
+						 array('—', '–'), $_);
+		return $_;
+	}
+
+
+	function educateDashesOldSchoolInverted($_) {
+	#
+	#   Parameter:  String.
+	#
+	#   Returns:    The string, with each instance of "--" translated to
+	#               an em-dash HTML entity, and each "---" translated to
+	#               an en-dash HTML entity. Two reasons why: First, unlike the
+	#               en- and em-dash syntax supported by
+	#               EducateDashesOldSchool(), it's compatible with existing
+	#               entries written before SmartyPants 1.1, back when "--" was
+	#               only used for em-dashes.  Second, em-dashes are more
+	#               common than en-dashes, and so it sort of makes sense that
+	#               the shortcut should be shorter to type. (Thanks to Aaron
+	#               Swartz for the idea.)
+	#
+
+		#                      en         em
+		$_ = str_replace(array("---",     "--",),
+						 array('–', '—'), $_);
+		return $_;
+	}
+
+
+	function educateEllipses($_) {
+	#
+	#   Parameter:  String.
+	#   Returns:    The string, with each instance of "..." translated to
+	#               an ellipsis HTML entity. Also converts the case where
+	#               there are spaces between the dots.
+	#
+	#   Example input:  Huh...?
+	#   Example output: Huh…?
+	#
+
+		$_ = str_replace(array("...",     ". . .",), '…', $_);
+		return $_;
+	}
+
+
+	function stupefyEntities($_) {
+	#
+	#   Parameter:  String.
+	#   Returns:    The string, with each SmartyPants HTML entity translated to
+	#               its ASCII counterpart.
+	#
+	#   Example input:  “Hello — world.”
+	#   Example output: "Hello -- world."
+	#
+
+							#  en-dash    em-dash
+		$_ = str_replace(array('–', '—'),
+						 array('-',       '--'), $_);
+
+		# single quote         open       close
+		$_ = str_replace(array('‘', '’'), "'", $_);
+
+		# double quote         open       close
+		$_ = str_replace(array('“', '”'), '"', $_);
+
+		$_ = str_replace('…', '...', $_); # ellipsis
+
+		return $_;
+	}
+
+
+	function processEscapes($_) {
+	#
+	#   Parameter:  String.
+	#   Returns:    The string, with after processing the following backslash
+	#               escape sequences. This is useful if you want to force a "dumb"
+	#               quote or other character to appear.
+	#
+	#               Escape  Value
+	#               ------  -----
+	#               \\      \
+	#               \"      "
+	#               \'      '
+	#               \.      .
+	#               \-      -
+	#               \`      `
+	#
+		$_ = str_replace(
+			array('\\\\',  '\"',    "\'",    '\.',    '\-',    '\`'),
+			array('\', '"', ''', '.', '-', '`'), $_);
+
+		return $_;
+	}
+
+
+	function tokenizeHTML($str) {
+	#
+	#   Parameter:  String containing HTML markup.
+	#   Returns:    An array of the tokens comprising the input
+	#               string. Each token is either a tag (possibly with nested,
+	#               tags contained therein, such as , or a
+	#               run of text between tags. Each element of the array is a
+	#               two-element array; the first is either 'tag' or 'text';
+	#               the second is the actual value.
+	#
+	#
+	#   Regular expression derived from the _tokenize() subroutine in 
+	#   Brad Choate's MTRegex plugin.
+	#   
+	#
+		$index = 0;
+		$tokens = array();
+
+		$match = '(?s:)|'.	# comment
+				 '(?s:<\?.*?\?>)|'.				# processing instruction
+												# regular tags
+				 '(?:<[/!$]?[-a-zA-Z0-9:]+\b(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*>)'; 
+
+		$parts = preg_split("{($match)}", $str, -1, PREG_SPLIT_DELIM_CAPTURE);
+
+		foreach ($parts as $part) {
+			if (++$index % 2 && $part != '') 
+				$tokens[] = array('text', $part);
+			else
+				$tokens[] = array('tag', $part);
+		}
+		return $tokens;
+	}
+
+}
+
+
+/*
+
+PHP SmartyPants
+===============
+
+Description
+-----------
+
+This is a PHP translation of the original SmartyPants quote educator written in
+Perl by John Gruber.
+
+SmartyPants is a web publishing utility that translates plain ASCII
+punctuation characters into "smart" typographic punctuation HTML
+entities. SmartyPants can perform the following transformations:
+
+*	Straight quotes (`"` and `'`) into "curly" quote HTML entities
+*	Backticks-style quotes (` ``like this'' `) into "curly" quote HTML 
+	entities
+*	Dashes (`--` and `---`) into en- and em-dash entities
+*	Three consecutive dots (`...`) into an ellipsis entity
+
+SmartyPants does not modify characters within `
`, ``, ``, 
+`