Module: Typogruby

154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176

# File 'lib/typogruby.rb', line 154

def caps(text)
  exclude_sensitive_tags(text) do |t|
    # $1 and $2 are excluded HTML tags, $3 is the part before the caps and $4 is the caps match
    t.gsub(%r{
        (<[^/][^>]+?>)|                     # Ignore any opening tag, so we don't mess up attribute values
        (\s|&nbsp;|^|'|"|>)                 # Make sure our capture is preceded by whitespace or quotes
        ([A-Z\d]([\.']?[A-Z\d][\.']?){1,})  # Capture capital words, with optional dots or numbers in between
        (?!\w)                              # ...which must not be followed by a word character.
      }x) do |str|
      tag, before, caps = $1, $2, $3

      # Do nothing with the contents if ignored tags, the inside of an opening HTML element
      # so we don't mess up attribute values, or if our capture is only digits.
      if tag || caps =~ /^\d+\.?$/
        str
      elsif $3 =~ /^[\d\.]+$/
        before + caps
      else
        before + '<span class="caps">' + caps + '</span>'
      end
    end
  end
end

213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231

# File 'lib/typogruby.rb', line 213

def entities(text)
  o = ''
  text.scan(/(?x)

      ( <\?(?:[^?]*|\?(?!>))*\?>
      | <!-- (?m:.*?) -->
      | <\/? (?i:a|abbr|acronym|address|applet|area|b|base|basefont|bdo|big|blockquote|body|br|button|caption|center|cite|code|col|colgroup|dd|del|dfn|dir|div|dl|dt|em|fieldset|font|form|frame|frameset|h1|h2|h3|h4|h5|h6|head|hr|html|i|iframe|img|input|ins|isindex|kbd|label|legend|li|link|map|menu|meta|noframes|noscript|object|ol|optgroup|option|p|param|pre|q|s|samp|script|select|small|span|strike|strong|style|sub|sup|table|tbody|td|textarea|tfoot|th|thead|title|tr|tt|u|ul|var)\b
          (?:[^>"']|"[^"]*"|'[^']*')*
        >
      | &(?:[a-zA-Z0-9]+|\#[0-9]+|\#x[0-9a-fA-F]+);
      )
      |([^<&]+|[<&])

    /x) do |tag, text|
    o << tag.to_s
    o << encode(text.to_s)
  end
  o
end

237
238
239

# File 'lib/typogruby.rb', line 237

def improve(text)
  initial_quotes(caps(smartypants(widont(amp(text)))))
end

198
199
200
201
202
203

# File 'lib/typogruby.rb', line 198

def initial_quotes(text)
  # $1 is the initial part of the string, $2 is the quote or entitity, and $3 is the double quote
  exclude_sensitive_tags(text) do |t|
    t.gsub(/((?:<(?:h[1-6]|p|li|dt|dd)[^>]*>|^)\s*(?:<(?:a|em|strong|span)[^>]*>)?)('|&#8216;|&lsquo;|("|&#8220;|&ldquo;))/) {$1 + "<span class=\"#{'d' if $3}quo\">#{$2}</span>"}
  end
end

31
32
33

# File 'lib/typogruby.rb', line 31

def smartypants(text)
  ::RubyPants.new(text).to_html
end

112
113
114
115
116
117
118
119
120
121
122
123

# File 'lib/typogruby.rb', line 112

def widont(text)
  exclude_sensitive_tags(text) do |t|
    t.gsub(%r{
      ((?:</?(?:a|em|span|strong|i|b)[^>]*>)|[^<>\s]) # must be proceeded by an approved inline opening or closing tag or a nontag/nonspace
      \s+                                             # the space to replace
      (([^<>\s]+)                                     # must be flollowed by non-tag non-space characters
      \s*                                             # optional white space!
      (</(a|em|span|strong|i|b)>\s*)*                 # optional closing inline tags with optional white space after each
      ((</(p|h[1-6]|li|dt|dd)>)|$))                   # end with a closing p, h1-6, li or the end of the string
    }x) { |match| $1 + (match.include?('&nbsp;') ? ' ' : '&nbsp;') + $2 } # Make sure to not add another nbsp before one already there
  end
end