or tags.
in_pre = false
# Here is the result stored in.
result = +""
# 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.
prev_token_last_char = nil
tokens.each do |token|
if token.first == :tag
result << token[1]
if token[1] =~ %r{<(/?)(?:pre|code|kbd|script|math)[\s>]}
in_pre = ($1 != "/") # Opening or closing tag?
end
else
t = token[1]
# Remember last char of this token before processing.
last_char = t[-1].chr
unless in_pre
t.gsub!("'", "'")
t.gsub!(""", '"')
if do_dashes
t = educate_dashes t if do_dashes == :normal
t = educate_dashes_oldschool t if do_dashes == :oldschool
t = educate_dashes_inverted t if do_dashes == :inverted
end
t = educate_ellipses t if do_ellipses
t = educate_fractions t
# Note: backticks need to be processed before quotes.
if do_backticks
t = educate_backticks t
t = educate_single_backticks t if do_backticks == :both
end
if do_quotes
if t == "'"
# Special case: single-character ' token
if prev_token_last_char =~ /\S/
t = entity(:single_right_quote)
else
t = entity(:single_left_quote)
end
elsif t == '"'
# Special case: single-character " token
if prev_token_last_char =~ /\S/
t = entity(:double_right_quote)
else
t = entity(:double_left_quote)
end
else
# Normal case:
t = educate_quotes t
end
end
t = stupefy_entities t if do_stupefy
end
prev_token_last_char = last_char
result << t
end
end
# Done
result
end
protected
# The string, with each instance of "--" translated to an
# em-dash HTML entity.
#
def educate_dashes(str)
str.gsub(/--/, entity(:em_dash))
end
# The string, with each instance of "--" translated to an
# en-dash HTML entity, and each "---" translated to an
# em-dash HTML entity.
#
def educate_dashes_oldschool(str)
str.gsub(/---/, entity(:em_dash)).gsub(/--/, entity(:en_dash))
end
# Return 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 +educate_dashes_oldschool+, 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.)
#
def educate_dashes_inverted(str)
str.gsub(/---/, entity(:en_dash)).gsub(/--/, entity(:em_dash))
end
# Return the string, with each instance of "..." translated
# to an ellipsis HTML entity. Also converts the case where there are
# spaces between the dots.
#
def educate_ellipses(str)
str.gsub("...", entity(:ellipsis)).gsub(". . .", entity(:ellipsis))
end
# Return the string, with "``backticks''"-style single quotes
# translated into HTML curly quote entities.
#
def educate_backticks(str)
str.gsub("``", entity(:double_left_quote)).gsub("''", entity(:double_right_quote))
end
# Return the string, with "`backticks'"-style single quotes
# translated into HTML curly quote entities.
#
def educate_single_backticks(str)
str.gsub("`", entity(:single_left_quote)).gsub("'", entity(:single_right_quote))
end
def educate_fractions(str)
str.gsub(%r{(\s+|^)(1/4|1/2|3/4)([,.;\s]|$)}) do
frac =
if $2 == "1/2"
entity(:frac12)
elsif $2 == "1/4"
entity(:frac14)
elsif $2 == "3/4"
entity(:frac34)
end
"#{$1}#{frac}#{$3}"
end
end
# Return the string, with "educated" curly quote HTML entities.
#
def educate_quotes(str)
punct_class = '[!"#\$\%\'()*+,\-.\/:;<=>?\@\[\\\\\]\^_`{|}~]'
# normalize html
str = str.dup
# Special case if the very first character is a quote followed by
# punctuation at a non-word-break. Close the quotes by brute
# force:
str.gsub!(/^'(?=#{punct_class}\B)/, entity(:single_right_quote))
str.gsub!(/^"(?=#{punct_class}\B)/, entity(:double_right_quote))
# Special case for double sets of quotes, e.g.:
# He said, "'Quoted' words in a larger quote."
str.gsub!(/"'(?=\w)/, "#{entity(:double_left_quote)}#{entity(:single_left_quote)}")
str.gsub!(/'"(?=\w)/, "#{entity(:single_left_quote)}#{entity(:double_left_quote)}")
# Special case for decade abbreviations (the '80s):
str.gsub!(/'(?=\d\ds)/, entity(:single_right_quote))
close_class = %![^\ \t\r\n\\[\{\(\-]!
dec_dashes = "#{entity(:en_dash)}|#{entity(:em_dash)}"
# Get most opening single quotes:
str.gsub!(
/(\s| |=|--|&[mn]dash;|#{dec_dashes}|ȁ[34];)'(?=\w)/,
'\1' + entity(:single_left_quote),
)
# Single closing quotes:
str.gsub!(/(#{close_class})'/, '\1' + entity(:single_right_quote))
str.gsub!(/'(\s|s\b|$)/, entity(:single_right_quote) + '\1')
# Any remaining single quotes should be opening ones:
str.gsub!(/'/, entity(:single_left_quote))
# Get most opening double quotes:
str.gsub!(
/(\s| |=|--|&[mn]dash;|#{dec_dashes}|ȁ[34];)"(?=\w)/,
'\1' + entity(:double_left_quote),
)
# Double closing quotes:
str.gsub!(/(#{close_class})"/, '\1' + entity(:double_right_quote))
str.gsub!(/"(\s|s\b|$)/, entity(:double_right_quote) + '\1')
# Any remaining quotes should be opening ones:
str.gsub!(/"/, entity(:double_left_quote))
str
end
# Return the string, with each RubyPants HTML entity translated to
# its ASCII counterpart.
#
# Note: This is not reversible (but exactly the same as in SmartyPants)
#
def stupefy_entities(str)
new_str = str.dup
{
en_dash: "-",
em_dash: "--",
single_left_quote: "'",
single_right_quote: "'",
double_left_quote: '"',
double_right_quote: '"',
ellipsis: "...",
}.each { |k, v| new_str.gsub!(/#{entity(k)}/, v) }
new_str
end
# Return an array of the tokens comprising the 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.
#
# Based on the _tokenize() subroutine from Brad Choate's
# MTRegex plugin.
#
# This is actually the easier variant using tag_soup, as used by
# Chad Miller in the Python port of SmartyPants.
#
def tokenize
tag_soup = /([^<]*)(<[^>]*>)/
tokens = []
prev_end = 0
scan(tag_soup) do
tokens << [:text, $1] if $1 != ""
tokens << [:tag, $2]
prev_end = $~.end(0)
end
tokens << [:text, self[prev_end..-1]] if prev_end < size
tokens
end
def default_entities
{
single_left_quote: "‘",
double_left_quote: "“",
single_right_quote: "’",
double_right_quote: "”",
em_dash: "—",
en_dash: "–",
ellipsis: "…",
html_quote: """,
frac12: "½",
frac14: "¼",
frac34: "¾",
}
end
def entity(key)
@entities[key]
end
end