Module: TextUtils::HypertextHelper

Defined in:
lib/textutils/helper/hypertext_helper.rb

Instance Method Summary collapse

Instance Method Details

#content_tag(tag, content, opts = {}) ⇒ Object

content tag (e.g. <p>hello</p> - w/ opening and closing tag)



150
151
152
153
154
155
156
157
158
159
160
161
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 150

def content_tag( tag, content, opts={} ) # content tag (e.g. <p>hello</p> - w/ opening and closing tag)
  attribs = []
  opts.each do |key,value|
    attribs << "#{key}='#{value}'"
  end
  
  if attribs.size > 0
    "<#{tag} #{attribs.join(' ')}>#{content}</#{tag}>"
  else
    "<#{tag}>#{content}</#{tag}>"
  end
end

#image_tag(src, opts = {}) ⇒ Object 



173
174
175
176
177
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 173

def image_tag( src, opts={} )
  attribs = { src: src }
  attribs = attribs.merge( opts )  ### fix/todo: use reverse merge e.g. overwrite only if not present
  tag( :img, attribs )   ### "<img src='#{src}' #{attributes}>"
end

#link_to(content, href, opts = {}) ⇒ Object 



179
180
181
182
183
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 179

def link_to( content, href, opts={} )
  attribs = { href: href }
  attribs = attribs.merge( opts )  ### fix/todo: use reverse merge e.g. overwrite only if not present
  content_tag( :a, content, attribs )  ### "<a href='#{href}' #{attributes}>#{text}</a>"
end

#sanitize(ht, opts = {}) ⇒ Object

change to simple_hypertext or

hypertext_simple or
sanitize ???



92
93
94
95
96
97
98
99
100
101
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 92

def sanitize( ht, opts={} )  # ht -> hypertext
  # todo: add options for
  #   keep links, images, lists (?too), code, codeblocks

  ht = whitelist( ht, [:br, :p, :ul, :ol, :li, :pre, :code, :blockquote, :q, :cite], opts )

# clean (prettify) literal urls (strip protocoll) 
  ht = ht.gsub( /(http|https):\/\//, '' )
  ht
end

#strip_tags(ht) ⇒ Object 



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
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 7

def strip_tags( ht )
  ### to be done
  ## strip markup tags; return plain text; use brute force for now
  # check at least for presence of required a-z+ tag names
  #
  #  note: make sure we cover h1/h2/h3/h4/h5/h6  tag w/ number!!

  ### ht.gsub( /<[^>]+>/, '' ) - old simple

  ## todo: add strip comments e.g. <!-- xxxx --> ???
  ##  or use new strip_comments( ht )


  ## note: follow offical xml spec
  ##  - allows for first char:  (Letter | '_' | ':')
  ##  - allows for followup chars: (Letter | Digit | '_' | ':' | '.' | '-')

  tag_name_pattern = "[a-z_:][a-z0-9_:.\\-]*"

  empty_tag_pattern   =  "<#{tag_name_pattern}\\s*/>"
  opening_tag_pattern =  "<#{tag_name_pattern}(\\s+[^>]*)?>"
  closing_tag_pattern =  "</#{tag_name_pattern}\\s*>"

  ht = ht.gsub( /#{empty_tag_pattern}/i, '' )    # remove xml-style empty tags eg. <br /> or <br/>
  ht = ht.gsub( /#{opening_tag_pattern}/i, '' )  # opening tag <p>
  ht = ht.gsub( /#{closing_tag_pattern}/i, '' )  # closing tag e.g. </p>
  ht
end

#stylesheet_link_tag(href, opts = {}) ⇒ Object 



164
165
166
167
168
169
170
171
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 164

def stylesheet_link_tag( href, opts={} )
  href = "#{href}.css"  unless href.end_with?( '.css' )   # auto-add .css if not present
  attribs = { rel:  'stylesheet',
              type: 'text/css',
              href: href }
  attribs = attribs.merge( opts )  ### fix/todo: use reverse merge e.g. overwrite only if not present
  tag( :link, attribs )
end

#tag(tag, opts = {}) ⇒ Object

rails-style asset, url tag helpers and friends

todo:  move into different helper module/modules?? why? why not?



137
138
139
140
141
142
143
144
145
146
147
148
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 137

def tag( tag, opts={} )  # empty tag (no content e.g. <br>, <img src=''> etc.)
  attribs  = []
  opts.each do |key,value|
    attribs << "#{key}='#{value}'"
  end
  
  if attribs.size > 0
    "<#{tag} #{attribs.join(' ')}>"
  else
    "<#{tag}>"
  end
end

#textify(ht, opts = {}) ⇒ Object

ht -> hypertext



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
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 104

def textify( ht, opts={} )   # ht -> hypertext
  ## turn into plain (or markdown/wiki-style) text - to be done

  sanitize( ht, opts )   # step 1 - sanitize html
  # to be done

# strip bold
#    ht = ht.gsub( /<b[^>]*>/, '**' )  # fix: will also swallow bxxx tags - add b space
#    ht = ht.gsub( /<\/b>/, '**' )

# strip em
#   ht = ht.gsub( /<em[^>]*>/, '__' )
#   ht = ht.gsub( /<\/em>/, '__' )

#    ht = ht.gsub( /&nbsp;/, ' ' )

#    # try to cleanup whitespaces
#    # -- keep no more than two spaces
#    ht = ht.gsub( /[ \t]{3,}/, '  ' )
#    # -- keep no more than two new lines
#    ht = ht.gsub( /\n{2,}/m, "\n\n" ) 
#    # -- remove all trailing spaces
#    ht = ht.gsub( /[ \t\n]+$/m, '' )
#    # -- remove all leading spaces
#    ht = ht.gsub( /^[ \t\n]+/m, '' )
end

#whitelist(ht, tags, opts = {}) ⇒ Object 



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
 
# File 'lib/textutils/helper/hypertext_helper.rb', line 37

def whitelist( ht, tags, opts={} )

  # note: assumes properly escaped <> in ht/hypertext

  ###############################################
  # step one - save whitelisted tags use ‹tag›
  tags.each do |tag|
    # note: we strip all attribues
    # note: match all tags case insensitive e.g. allow a,A or br,BR,bR etc.
    #   downcase all tags

    # convert xml-style empty tags to simple html emtpty tags
    #  e.g. <br/> or <br /> becomses <br>
    ht = ht.gsub( /<(#{tag})\s*\/>/i )       { |_| "‹#{$1.downcase}›" }   # eg. <br /> or <br/> becomes ‹br›

    # make sure we won't swall <br> for <b> for example, thus use \s+ before [^>]
    ht = ht.gsub( /<(#{tag})(\s+[^>]*)?>/i ) { |_| "‹#{$1.downcase}›" }   # opening tag <p>
    ht = ht.gsub( /<\/(#{tag})\s*>/i )       { |_| "‹/#{$1.downcase}›" }  # closing tag e.g. </p>
  end

  ############################
  # step two - clean tags

  #   strip images - special treatment for debugging
  ht = ht.gsub( /<img[^>]*>/i, '♦' )   # for debugging use black diamond e.g. ♦
  ht = ht.gsub( /<\/img>/i, '' )   # should not exists

  # strip all remaining tags
  #  -- note: will NOT strip comments for now e.g. <!-- -->
  ht = strip_tags( ht )

  ## pp ht  # fix: debugging indo - remove

  ############################################
  # step three - restore whitelisted tags

  return ht   if opts[:skip_restore]   # skip step 3 for debugging

  tags.each do |tag|
#      ht = ht.gsub( /‹(#{tag})›/, "<\1>" )  # opening tag e.g. <p>
#      ht = ht.gsub( /‹\/(#{tag})›/, "<\/\1>" )  # closing tag e.g. </p>
    ht = ht.gsub( /‹(#{tag})›/ )   { |_| "<#{$1}>" }
    ht = ht.gsub( /‹\/(#{tag})›/ ) { |_| "<\/#{$1}>" }  # closing tag e.g. </p>
  end

  ht
end