aboutsummaryrefslogtreecommitdiffstats
path: root/actionpack/lib/action_view/helpers/text_helper.rb
blob: 5e1a2e66cebd30daee02b8aa6a74dae6bd70a9dd (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
require File.dirname(__FILE__) + '/tag_helper'

module ActionView
  module Helpers #:nodoc:
    # Provides a set of methods for working with text strings that can help unburden the level of inline Ruby code in the
    # templates. In the example below we iterate over a collection of posts provided to the template and prints each title
    # after making sure it doesn't run longer than 20 characters:
    #   <% for post in @posts %>
    #     Title: <%= truncate(post.title, 20) %>
    #   <% end %>
    module TextHelper
      # The regular puts and print are outlawed in eRuby. It's recommended to use the <%= "hello" %> form instead of print "hello".
      # If you absolutely must use a method-based output, you can use concat. It's use like this <% concat "hello", binding %>. Notice that
      # it doesn't have an equal sign in front. Using <%= concat "hello" %> would result in a double hello.
      def concat(string, binding)
        eval("_erbout", binding).concat(string)
      end

      # Truncates +text+ to the length of +length+ and replaces the last three characters with the +truncate_string+
      # if the +text+ is longer than +length+.
      def truncate(text, length = 30, truncate_string = "...")
        if text.nil? then return end
        if text.length > length then text[0..(length - 3)] + truncate_string else text end
      end

      # Highlights the +phrase+ where it is found in the +text+ by surrounding it like
      # <strong class="highlight">I'm a highlight phrase</strong>. The highlighter can be specialized by
      # passing +highlighter+ as single-quoted string with \1 where the phrase is supposed to be inserted.
      # N.B.: The +phrase+ is sanitized to include only letters, digits, and spaces before use.
      def highlight(text, phrase, highlighter = '<strong class="highlight">\1</strong>')
        if phrase.blank? then return text end
        text.gsub(/(#{escape_regexp(phrase)})/i, highlighter) unless text.nil?
      end

      # Extracts an excerpt from the +text+ surrounding the +phrase+ with a number of characters on each side determined
      # by +radius+. If the phrase isn't found, nil is returned. Ex:
      #   excerpt("hello my world", "my", 3) => "...lo my wo..."
      def excerpt(text, phrase, radius = 100, excerpt_string = "...")
        if text.nil? || phrase.nil? then return end
        phrase = escape_regexp(phrase)

        if found_pos = text =~ /(#{phrase})/i
          start_pos = [ found_pos - radius, 0 ].max
          end_pos   = [ found_pos + phrase.length + radius, text.length ].min

          prefix  = start_pos > 0 ? excerpt_string : ""
          postfix = end_pos < text.length ? excerpt_string : ""

          prefix + text[start_pos..end_pos].strip + postfix
        else
          nil
        end
      end

      # Attempts to pluralize the +singular+ word unless +count+ is 1. See source for pluralization rules.
      def pluralize(count, singular, plural = nil)
         "#{count} " + if count == 1
          singular
        elsif plural
          plural
        elsif Object.const_defined?("Inflector")
          Inflector.pluralize(singular)
        else
          singular + "s"
        end
      end

      # Word wrap long lines to line_width.
      def word_wrap(text, line_width = 80)
        text.gsub(/\n/, "\n\n").gsub(/(.{1,#{line_width}})(\s+|$)/, "\\1\n").strip
      end

      begin
        require "redcloth"

        # Returns the text with all the Textile codes turned into HTML-tags.
        # <i>This method is only available if RedCloth can be required</i>.
        def textilize(text)
          text.blank? ? "" : RedCloth.new(text, [ :hard_breaks ]).to_html
        end

        # Returns the text with all the Textile codes turned into HTML-tags, but without the regular bounding <p> tag.
        # <i>This method is only available if RedCloth can be required</i>.
        def textilize_without_paragraph(text)
          textiled = textilize(text)
          if textiled[0..2] == "<p>" then textiled = textiled[3..-1] end
          if textiled[-4..-1] == "</p>" then textiled = textiled[0..-5] end
          return textiled
        end
      rescue LoadError
        # We can't really help what's not there
      end

      begin
        require "bluecloth"

        # Returns the text with all the Markdown codes turned into HTML-tags.
        # <i>This method is only available if BlueCloth can be required</i>.
        def markdown(text)
          text.blank? ? "" : BlueCloth.new(text).to_html
        end
      rescue LoadError
        # We can't really help what's not there
      end
      
      # Returns +text+ transformed into html using very simple formatting rules
      # Surrounds paragraphs with <tt>&lt;p&gt;</tt> tags, and converts line breaks into <tt>&lt;br /&gt;</tt>
      # Two consecutive newlines(<tt>\n\n</tt>) are considered as a paragraph, one newline (<tt>\n</tt>) is
      # considered a linebreak, three or more consecutive newlines are turned into two newlines 
      def simple_format(text)
        text.gsub!(/(\r\n|\n|\r)/, "\n") # lets make them newlines crossplatform
        text.gsub!(/\n\n+/, "\n\n") # zap dupes
        text.gsub!(/\n\n/, '</p>\0<p>') # turn two newlines into paragraph
        text.gsub!(/([^\n])(\n)([^\n])/, '\1\2<br />\3') # turn single newline into <br />
        
        return '<p>' + text + '</p>' # wrap the first and last line in paragraphs before we're done
      end

      # Turns all urls and email addresses into clickable links. The +link+ parameter can limit what should be linked.
      # Options are :all (default), :email_addresses, and :urls.
      #
      # Example:
      #   auto_link("Go to http://www.rubyonrails.com and say hello to david@loudthinking.com") =>
      #     Go to <a href="http://www.rubyonrails.com">http://www.rubyonrails.com</a> and
      #     say hello to <a href="mailto:david@loudthinking.com">david@loudthinking.com</a>
      def auto_link(text, link = :all, href_options = {})
        case link
          when :all             then auto_link_urls(auto_link_email_addresses(text), href_options)
          when :email_addresses then auto_link_email_addresses(text)
          when :urls            then auto_link_urls(text, href_options)
        end
      end

      # Turns all links into words, like "<a href="something">else</a>" to "else".
      def strip_links(text)
        text.gsub(/<a.*>(.*)<\/a>/m, '\1')
      end

      # Try to require the html-scanner library
      begin
        require 'html/tokenizer'
        require 'html/node'
      rescue LoadError
        # if there isn't a copy installed, use the vendor version in
        # action controller
        $:.unshift File.join(File.dirname(__FILE__), "..", "..",
                      "action_controller", "vendor", "html-scanner")
        require 'html/tokenizer'
        require 'html/node'
      end

      VERBOTEN_TAGS = %w(form script) unless defined?(VERBOTEN_TAGS)
      VERBOTEN_ATTRS = /^on/i unless defined?(VERBOTEN_ATTRS)

      # Sanitizes the given HTML by making form and script tags into regular
      # text, and removing all "onxxx" attributes (so that arbitrary Javascript
      # cannot be executed). Also removes href attributes that start with
      # "javascript:".
      #
      # Returns the sanitized text.
      def sanitize(html)
        # only do this if absolutely necessary
        if html.index("<")
          tokenizer = HTML::Tokenizer.new(html)
          new_text = ""

          while token = tokenizer.next
            node = HTML::Node.parse(nil, 0, 0, token, false)
            new_text << case node
              when HTML::Tag
                if VERBOTEN_TAGS.include?(node.name)
                  node.to_s.gsub(/</, "&lt;")
                else
                  if node.closing != :close
                    node.attributes.delete_if { |attr,v| attr =~ VERBOTEN_ATTRS }
                    if node.attributes["href"] =~ /^javascript:/i
                      node.attributes.delete "href"
                    end
                  end
                  node.to_s
                end
              else
                node.to_s.gsub(/</, "&lt;")
            end
          end

          html = new_text
        end

        html
      end

      
      private
        # Returns a version of the text that's safe to use in a regular expression without triggering engine features.
        def escape_regexp(text)
          text.gsub(/([\\|?+*\/\)\(])/) { |m| "\\#{$1}" }
        end

        # Turns all urls into clickable links.
        def auto_link_urls(text, href_options = {})
          text.gsub(/(<\w+.*?>|[^=!:'"\/]|^)((?:http[s]?:\/\/)|(?:www\.))([^\s<]+\/?)([[:punct:]]|\s|<|$)/) do
            all, a, b, c, d = $&, $1, $2, $3, $4
            if a =~ /<a\s/i # don't replace URL's that are already linked
              all
            else
              extra_options = tag_options(href_options.stringify_keys) || ""
              %(#{a}<a href="#{b=="www."?"http://www.":b}#{c}"#{extra_options}>#{b}#{c}</a>#{d})
            end
          end
        end

        # Turns all email addresses into clickable links.
        def auto_link_email_addresses(text)
          text.gsub(/([\w\.!#\$%\-+.]+@[A-Za-z0-9\-]+(\.[A-Za-z0-9\-]+)+)/, '<a href="mailto:\1">\1</a>')
        end
    end
  end
end