Module: Stringex::StringExtensions

Defined in:
lib/stringex/string_extensions.rb,
lib/stringex/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:



6
7
8
 
# File 'lib/stringex/string_extensions.rb', line 6

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Note: This method has been superceded by ActiveSupport’s squish method.



229
230
231
 
# File 'lib/stringex/string_extensions.rb', line 229

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.



84
85
86
 
# File 'lib/stringex/string_extensions.rb', line 84

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

#convert_misc_characters(options = {}) ⇒ 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.



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
 
# File 'lib/stringex/string_extensions.rb', line 177

def convert_misc_characters(options = {})
  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
  # Special rules for abbreviations
  dummy.gsub!(/(\s|^)([[:alpha:]](\.[[:alpha:]])+(\.?)[[:alpha:]]*(\s|$))/) do |x|
    x.gsub(".", "")
  end
  # Back to normal rules
  misc_characters =
  {
    /\s*&\s*/ => "and",
    /\s*#/ => "number",
    /\s*@\s*/ => "at",
    /(\S|^)\.(\S)/ => '\1 dot \2',
    /(\s|^)\$(\d*)(\s|$)/ => '\2 dollars',
    /(\s|^)£(\d*)(\s|$)/u => '\2 pounds',
    /(\s|^)¥(\d*)(\s|$)/u => '\2 yen',
    /\s*\*\s*/ => "star",
    /\s*%\s*/ => "percent",
    /(\s*=\s*)/ => " equals ",
    /\s*\+\s*/ => "plus",
    /\s*÷\s*/ => "divide",
    /\s*°\s*/ => "degrees"
  }
  misc_characters[/\s*(\\|\/|／)\s*/] = 'slash' unless options[:allow_slash]
  misc_characters.each do |found, replaced|
    replaced = " #{replaced} " unless replaced =~ /\\1/
    dummy.gsub!(found, replaced)
  end
  dummy = dummy.gsub(/(^|[[:alpha:]])'|`([[:alpha:]]|$)/, '\1\2').gsub(/[\.,:;()\[\]\/\?!\^'ʼ"_\|]/, " ").strip
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.



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
 
# File 'lib/stringex/string_extensions.rb', line 92

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",
    "(#247|divide)" => "divide",
    "(#176|deg)" => " degrees "
  }.each do |textiled, normal|
    dummy.gsub!(/&#{textiled};/, normal)
  end
  dummy.gsub(/&[^;]+;/, "").strip
end

#convert_smart_punctuation ⇒ Object

Converts MS Word ‘smart punctuation’ to ASCII



149
150
151
152
153
154
155
156
157
158
159
160
 
# File 'lib/stringex/string_extensions.rb', line 149

def convert_smart_punctuation
  dummy = dup
  {

    "(“|”|\302\223|\302\224|\303\222|\303\223)" => '"',
    "(‘|’|\302\221|\302\222|\303\225)" => "'",
    "…" => "...",
  }.each do |smart, normal|
    dummy.gsub!(/#{smart}/, normal)
  end
  dummy.strip
end

#convert_vulgar_fractions ⇒ Object

Converts vulgar fractions from supported html entities and unicode to plain text formats.



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/stringex/string_extensions.rb', line 123

def convert_vulgar_fractions
  dummy = dup
  {
    "(&#188;|&frac14;|¼)" => "one fourth",
    "(&#189;|&frac12;|½)" => "half",
    "(&#190;|&frac34;|¾)" => "three fourths",
    "(&#8531;|⅓)" => "one third",
    "(&#8532;|⅔)" => "two thirds",
    "(&#8533;|⅕)" => "one fifth",
    "(&#8534;|⅖)" => "two fifths",
    "(&#8535;|⅗)" => "three fifths",
    "(&#8536;|⅘)" => "four fifths",
    "(&#8537;|⅙)" => "one sixth",
    "(&#8538;|⅚)" => "five sixths",
    "(&#8539;|⅛)" => "one eighth",
    "(&#8540;|⅜)" => "three eighths",
    "(&#8541;|⅝)" => "five eighths",
    "(&#8542;|⅞)" => "seven eighths"
  }.each do |textiled, normal|
    dummy.gsub!(/#{textiled}/, normal)
  end
  dummy
end

#limit(limit = nil) ⇒ Object

Returns the string limited in size to the value of limit.



44
45
46
 
# File 'lib/stringex/string_extensions.rb', line 44

def limit(limit = nil)
  limit.nil? ? self : self[0...limit]
end

#remove_formatting(options = {}) ⇒ Object

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



50
51
52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/stringex/string_extensions.rb', line 50

def remove_formatting(options = {})
  strip_html_tags.
    convert_smart_punctuation.
    convert_accented_entities.
    convert_vulgar_fractions.
    convert_misc_entities.
    convert_misc_characters(options).
    to_ascii.
    # NOTE: String#to_ascii may convert some Unicode characters to ascii we'd already transliterated
    # so we need to do it again just to be safe
    convert_misc_characters(options).
    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"



221
222
223
 
# File 'lib/stringex/string_extensions.rb', line 221

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.



66
67
68
69
70
71
72
 
# File 'lib/stringex/string_extensions.rb', line 66

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 #=> "france"



167
168
169
 
# File 'lib/stringex/unidecoder.rb', line 167

def to_ascii
  Stringex::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.



18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
 
# File 'lib/stringex/string_extensions.rb', line 18

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(options = {}) ⇒ 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.



38
39
40
41
 
# File 'lib/stringex/string_extensions.rb', line 38

def to_url(options = {})
  return self if options[:exclude] && options[:exclude].include?(self)
  remove_formatting(options).downcase.replace_whitespace("-").collapse("-").limit(options[:limit])
end