Module: LuckySneaks::StringExtensions

Defined in:
lib/lucky_sneaks/string_extensions.rb,
lib/lucky_sneaks/unidecoder.rb

Overview

These methods are all added on String class.

Defined Under Namespace

Modules: ClassMethods

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.included(base) ⇒ Object

:nodoc:



4
5
6
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 4

def self.included(base) # :nodoc:
  base.extend(ClassMethods)
end

Instance Method Details

#collapse(character = " ") ⇒ Object

Removes specified character from the beginning and/or end of the string and then performs String#squeeze(character), condensing runs of the character within the string.

Note: This method has been superceded by ActiveSupport’s squish method.



160
161
162
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 160

def collapse(character = " ")
  sub(/^#{character}*/, "").sub(/#{character}*$/, "").squeeze(character)
end

#convert_accented_entities ⇒ Object

Converts HTML entities into the respective non-accented letters. Examples:

"á".convert_accented_entities # => "a"
"ç".convert_accented_entities # => "c"
"è".convert_accented_entities # => "e"
"î".convert_accented_entities # => "i"
"ø".convert_accented_entities # => "o"
"ü".convert_accented_entities # => "u"

Note: This does not do any conversion of Unicode/Ascii accented-characters. For that functionality please use to_ascii.



67
68
69
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 67

def convert_accented_entities
  gsub(/&([A-Za-z])(grave|acute|circ|tilde|uml|ring|cedil|slash);/, '\1')
end

#convert_misc_characters ⇒ Object

Converts various common plaintext characters to a more URI-friendly representation. Examples:

"foo & bar".convert_misc_characters # => "foo and bar"
"Chanel #9".convert_misc_characters # => "Chanel number nine"
"user@host".convert_misc_characters # => "user at host"
"google.com".convert_misc_characters # => "google dot com"
"$10".convert_misc_characters # => "10 dollars"
"*69".convert_misc_characters # => "star 69"
"100%".convert_misc_characters # => "100 percent"
"windows/mac/linux".convert_misc_characters # => "windows slash mac slash linux"

Note: Because this method will convert any & symbols to the string “and”, you should run any methods which convert HTML entities (convert_html_entities and convert_misc_entities) before running this method.



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
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 118

def convert_misc_characters
  dummy = dup.gsub(/\.{3,}/, " dot dot dot ") # Catch ellipses before single dot rule!
  # Special rules for money
  {
    /(\s|^)\$(\d+)\.(\d+)(\s|$)/ => '\2 dollars \3 cents',
    /(\s|^)£(\d+)\.(\d+)(\s|$)/u => '\2 pounds \3 pence',
  }.each do |found, replaced|
    replaced = " #{replaced} " unless replaced =~ /\\1/
    dummy.gsub!(found, replaced)
  end
  # Back to normal rules
  {
    /\s*&\s*/ => "and",
    /\s*#/ => "number",
    /\s*@\s*/ => "at",
    /(\S|^)\.(\S)/ => '\1 dot \2',
    /(\s|^)\$(\d*)(\s|$)/ => '\2 dollars',
    /(\s|^)£(\d*)(\s|$)/u => '\2 pounds',
    /(\s|^)¥(\d*)(\s|$)/u => '\2 yen',
    /\s*\*\s*/ => "star",
    /\s*%\s*/ => "percent",
    /\s*(\\|\/)\s*/ => "slash",
  }.each do |found, replaced|
    replaced = " #{replaced} " unless replaced =~ /\\1/
    dummy.gsub!(found, replaced)
  end
  dummy = dummy.gsub(/(^|\w)'(\w|$)/, '\1\2').gsub(/[\.,:;()\[\]\/\?!\^'"_]/, " ")
end

#convert_misc_entities ⇒ Object

Converts HTML entities (taken from common Textile/RedCloth formattings) into plain text formats.

Note: This isn’t an attempt at complete conversion of HTML entities, just those most likely to be generated by Textile.



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
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 75

def convert_misc_entities
  dummy = dup
  {
    "#822[01]" => "\"",
    "#821[67]" => "'",
    "#8230" => "...",
    "#8211" => "-",
    "#8212" => "--",
    "#215" => "x",
    "gt" => ">",
    "lt" => "<",
    "(#8482|trade)" => "(tm)",
    "(#174|reg)" => "(r)",
    "(#169|copy)" => "(c)",
    "(#38|amp)" => "and",
    "nbsp" => " ",
    "(#162|cent)" => " cent",
    "(#163|pound)" => " pound",
    "(#188|frac14)" => "one fourth",
    "(#189|frac12)" => "half",
    "(#190|frac34)" => "three fourths",
    "(#176|deg)" => " degrees"
  }.each do |textiled, normal|
    dummy.gsub!(/&#{textiled};/, normal)
  end
  dummy.gsub(/&[^;]+;/, "")
end

#remove_formatting ⇒ Object

Performs multiple text manipulations. Essentially a shortcut for typing them all. View source below to see which methods are run.



42
43
44
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 42

def remove_formatting
  strip_html_tags.convert_accented_entities.convert_misc_entities.convert_misc_characters.to_ascii.collapse
end

#replace_whitespace(replace = " ") ⇒ Object

Replace runs of whitespace in string. Defaults to a single space but any replacement string may be specified as an argument. Examples:

"Foo       bar".replace_whitespace # => "Foo bar"
"Foo       bar".replace_whitespace("-") # => "Foo-bar"



152
153
154
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 152

def replace_whitespace(replace = " ")
  gsub(/\s+/, replace)
end

#strip_html_tags(leave_whitespace = false) ⇒ Object

Removes HTML tags from text. This code is simplified from Tobias Luettke’s regular expression in Typo.



48
49
50
51
52
53
54
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 48

def strip_html_tags(leave_whitespace = false)
  name = /[\w:_-]+/
  value = /([A-Za-z0-9]+|('[^']*?'|"[^"]*?"))/
  attr = /(#{name}(\s*=\s*#{value})?)/
  rx = /<[!\/?\[]?(#{name}|--)(\s+(#{attr}(\s+#{attr})*))?\s*([!\/?\]]+|--)?>/
  (leave_whitespace) ?  gsub(rx, "").strip : gsub(rx, "").gsub(/\s+/, " ").strip
end

#to_ascii ⇒ Object

Returns string with its UTF-8 characters transliterated to ASCII ones. Example:

"⠋⠗⠁⠝⠉⠑".to_ascii #=> "braille"



57
58
59
 
# File 'lib/lucky_sneaks/unidecoder.rb', line 57

def to_ascii
  LuckySneaks::Unidecoder.decode(self)
end

#to_html(lite_mode = false) ⇒ Object

Returns the string converted (via Textile/RedCloth) to HTML format or self [with a friendly warning] if Redcloth is not available.

Using :lite argument will cause RedCloth to not wrap the HTML in a container P element, which is useful behavior for generating header element text, etc. This is roughly equivalent to ActionView’s textilize_without_paragraph except that it makes RedCloth do all the work instead of just gsubbing the return from RedCloth.



16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 16

def to_html(lite_mode = false)
  if defined?(RedCloth)
    if lite_mode
      RedCloth.new(self, [:lite_mode]).to_html
    else
      if self =~ /<pre>/
        RedCloth.new(self).to_html.tr("\t", "")
      else
        RedCloth.new(self).to_html.tr("\t", "").gsub(/\n\n/, "")
      end
    end
  else
    warn "String#to_html was called without RedCloth being successfully required"
    self
  end
end

#to_url ⇒ Object

Create a URI-friendly representation of the string. This is used internally by acts_as_url but can be called manually in order to generate an URI-friendly version of any string.



36
37
38
 
# File 'lib/lucky_sneaks/string_extensions.rb', line 36

def to_url
  remove_formatting.downcase.replace_whitespace("-").collapse("-")
end