Module: FatCore::String

Included in:
String
Defined in:
lib/fat_core/string.rb

Defined Under Namespace

Modules: ClassMethods

Transforming collapse

UPPERS = 
('A'..'Z').to_a

Matching collapse

REGEXP_META_CHARACTERS = 
"\\$()*+.<>?[]^{|}".chars

Transforming collapse

Matching collapse

Numbers collapse

Instance Method Details

#as_date ⇒ Date

Convert a string representing a date with only digits, hyphens, or slashes to a Date.

Examples:

"20090923".as_date.iso -> "2009-09-23"
"2009/09/23".as_date.iso -> "2009-09-23"
"2009-09-23".as_date.iso -> "2009-09-23"
"2009-9-23".as_date.iso -> "2009-09-23"

Returns:

  • (Date) —

    the translated Date

[View source]

110
111
112
 
# File 'lib/fat_core/string.rb', line 110

def as_date
  ::Date.new($1.to_i, $2.to_i, $3.to_i) if self =~ %r{(\d\d\d\d)[-/]?(\d\d?)[-/]?(\d\d?)}
end

#as_string ⇒ String

Return self unmodified. This method is here so to comply with the API of Symbol#as_string so that it can be applied to a variable that is either a String or a Symbol.

Returns:

  • (String) —

    self unmodified

[View source]

43
44
45
 
# File 'lib/fat_core/string.rb', line 43

def as_string
  self
end

#as_sym ⇒ Symbol

Convert to a lower-case symbol with all white space converted to a single '_' and all non-alphanumerics deleted, such that the string will work as an unquoted Symbol.

Examples:

"Hello World" -> :hello_world
"Hello*+World" -> :helloworld

Returns:

  • (Symbol) —

    self converted to a Symbol

[View source]

31
32
33
34
35
36
 
# File 'lib/fat_core/string.rb', line 31

def as_sym
  clean
    .gsub(/\s+/, '_')
    .gsub(/[^_A-Za-z0-9]/, '')
    .downcase.to_sym
end

#clean ⇒ String

Remove leading and trailing white space and compress internal runs of white space to a single space.

Examples:

'  hello   world\n  '.clean #=> 'hello world'

Returns:

[View source]

18
19
20
 
# File 'lib/fat_core/string.rb', line 18

def clean
  strip.squeeze(' ')
end

#commas(places = nil) ⇒ String

If the string is a valid number, return a string that adds grouping commas to the whole number part; otherwise, return self. Round the number to the given number places after the decimal if places is positive; round to the left of the decimal if places is negative. Pad with zeroes on the right for positive places, on the left for negative places.

Examples:

'hello'.commas             #=> 'hello'
'+4654656.33e66'.commas    #=> '+4,654,656.33e66'
'6789345612.14'.commas(-5) #=> '6,789,350,000'
'6543.14'.commas(5)        #=> '6,543.14000'

Returns:

  • (String) —

    self if not a valid number

  • (String) —

    commified number as a String

[View source]

347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
 
# File 'lib/fat_core/string.rb', line 347

def commas(places = nil)
  numeric_re = /\A([-+])?([\d_]*)((\.)?([\d_]*))?([eE][+-]?[\d_]+)?\z/
  return self unless clean =~ numeric_re
  sig = $1 || ''
  whole = $2 ? $2.delete('_') : ''
  frac = $5 || ''
  exp = $6 || ''

  # Round frac or whole if places given.  For positve places, round fraction
  # to that many places; for negative, round the whole-number part to the
  # absolute value of places left of the decimal.
  if places
    new_frac = frac.dup
    new_whole = whole.dup
    if places.zero?
      new_frac = ''
    elsif places.positive? && places < frac.length
      new_frac = frac[0...places - 1]
      new_frac[places - 1] =
        if frac[places].to_i >= 5
          (frac[places - 1].to_i + 1).to_s
        else
          frac[places - 1]
        end
    elsif places >= frac.length
      new_frac = frac + '0' * (places - frac.length)
    else
      # Negative places, round whole to places.abs from decimal
      places = places.abs
      if places > whole.length
        lead = whole[0].to_i >= 5 ? '1' : '0'
        new_whole[0] = places == whole.length + 1 ? lead : '0'
        new_whole[1..-1] = '0' * (places - 1)
        new_frac = ''
      elsif places > 1
        target = whole.length - places
        new_whole[target] =
          if whole[target + 1].to_i >= 5
            (whole[target].to_i + 1).to_s
          else
            whole[target]
          end
        new_whole[target + 1..whole.length - 1] =
          '0' * (whole.length - target - 1)
        new_frac = ''
      else
        # Rounding to 1 place, therefore, no rounding
        new_frac = ''
        new_whole = whole
      end
    end
    frac = new_frac
    whole = new_whole
  end

  # Place the commas in the whole part only
  whole = whole.reverse
  whole.gsub!(/([0-9]{3})/, '\\1,')
  whole.gsub!(/,$/, '')
  whole.reverse!

  # Reassemble
  if frac.blank?
    sig + whole + exp
  else
    sig + whole + '.' + frac + exp
  end
end

#distance(other) ⇒ Integer

Return the Damerau-Levenshtein distance between self an another string using a transposition block size of 1 and quitting if a max distance of 10 is reached.

Parameters:

  • other (#to_s) —

    string to compute self's distance from

Returns:

  • (Integer) —

    the distance between self and other

[View source]

216
217
218
 
# File 'lib/fat_core/string.rb', line 216

def distance(other)
  DamerauLevenshtein.distance(self, other.to_s, 1, 10)
end

#entitle ⇒ String

Return self capitalized according to the conventions for capitalizing titles of books or articles. Tries to follow the rules of the University of Chicago's A Manual of Style, Section 7.123, except to the extent that doing so requires knowing the parts of speech of words in the title. Also tries to use sensible capitalization for things such as postal address abbreviations, like P.O Box, Ave., Cir., etc. Considers all-consonant words of 3 or more characters as acronyms to be kept all uppercase, e.g., ddt => DDT, and words that are all uppercase in the input are kept that way, e.g. IBM stays IBM. Thus, if the source string is all uppercase, you should lowercase the whole string before using #entitle, otherwise is will not have the intended effect.

Examples:

'now is the time for all good men' #=> 'Now Is the Time for All

Good Men' 'how in the world does IBM do it?'.entitle #=> "How in the
World Does IBM Do It?" 'how in the world does ibm do it?'.entitle #=>
"How in the World Does Ibm Do It?" 'ne by nw'.entitle #=> 'NE by NW' 'my
life: a narcissistic tale' => 'My Life: A Narcissistic Tale'

Returns:

[View source]

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
 
# File 'lib/fat_core/string.rb', line 148

def entitle
  little_words = %w[a an the at for up and but
                    or nor in on under of from as by to]
  preserve_acronyms = !all_upper?
  newwords = []
  capitalize_next = false
  words = split(/\s+/)
  last_k = words.size - 1
  words.each_with_index do |w, k|
    first = (k == 0)
    last = (k == last_k)
    if w =~ %r{c/o}i
      # Care of
      newwords.push('c/o')
    elsif w =~ /^p\.?o\.?$/i
      # Post office
      newwords.push('P.O.')
    elsif w =~ /^[0-9]+(st|nd|rd|th)$/i
      # Ordinals
      newwords.push(w.downcase)
    elsif w =~ /^(cr|dr|st|rd|ave|pk|cir)$/i
      # Common abbrs to capitalize
      newwords.push(w.capitalize)
    elsif w =~ /^(us|ne|se|rr)$/i
      # Common 2-letter abbrs to upcase
      newwords.push(w.upcase)
    elsif w =~ /^[0-9].*$/i
      # Other runs starting with numbers,
      # like 3-A
      newwords.push(w.upcase)
    elsif w =~ /^(N|S|E|W|NE|NW|SE|SW)$/i
      # Compass directions all caps
      newwords.push(w.upcase)
    elsif w =~ /^[^aeiouy]*$/i && w.size > 2
      # All consonants and at least 3 chars, probably abbr
      newwords.push(w.upcase)
    elsif w =~ /^[A-Z0-9]+\z/ && preserve_acronyms
      # All uppercase and numbers, keep as is
      newwords.push(w)
    elsif w =~ /^(\w+)-(\w+)$/i
      # Hyphenated double word
      newwords.push($1.capitalize + '-' + $2.capitalize)
    elsif capitalize_next
      # Last word ended with a ':'
      newwords.push(w.capitalize)
      capitalize_next = false
    elsif little_words.include?(w.downcase)
      # Only capitalize at beginning or end
      newwords.push(first || last ? w.capitalize : w.downcase)
    else
      # All else
      newwords.push(w.capitalize)
    end
    # Capitalize following a ':'
    capitalize_next = true if newwords.last =~ /:\s*\z/
  end
  newwords.join(' ')
end

#fuzzy_match(matcher) ⇒ String?

Return the matched portion of self, minus punctuation characters, if self matches the string matcher using the following notion of matching:

  1. Remove all periods, commas, apostrophes, and asterisks (the punctuation characters) from both self and matcher,
  2. Treat ':' in the matcher as the equivalent of '.*' in a regular expression, that is, match anything in self,
  3. Ignore case in the match
  4. Match if any part of self matches matcher

Examples:

"St. Luke's Hospital".fuzzy_match('st lukes') #=> 'St Lukes'
"St. Luke's Hospital".fuzzy_match('luk:hosp') #=> 'Lukes Hosp'
"St. Luke's Hospital".fuzzy_match('st:spital') #=> 'St Lukes Hospital'
"St. Luke's Hospital".fuzzy_match('st:laks') #=> nil

Parameters:

  • matcher (String) —

    pattern to test against where ':' is wildcard

Returns:

  • (String) —

    the unpunctuated part of self that matched

  • (nil) —

    if self did not match matcher

[View source]

260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
 
# File 'lib/fat_core/string.rb', line 260

def fuzzy_match(matcher)
  # Remove periods, asterisks, commas, and apostrophes
  matcher = matcher.gsub(/[\*.,']/, '')
  target = gsub(/[\*.,']/, '')
  matchers = matcher.split(/[: ]+/)
  regexp_string = matchers.map { |m| ".*?#{Regexp.escape(m)}.*?" }.join('[: ]')
  regexp_string.sub!(/^\.\*\?/, '')
  regexp_string.sub!(/\.\*\?$/, '')
  regexp = /#{regexp_string}/i
  matched_text =
    if (match = regexp.match(target))
      match[0]
    end
  matched_text
end

#matches_with(matcher) ⇒ nil, String

Test whether self matches the matcher treating matcher as a case-insensitive regular expression if it is of the form '/.../' or as a string to #fuzzy_match against otherwise.

Parameters:

  • matcher (String) —

    regexp if looks like /.../; #fuzzy_match pattern otherwise

Returns:

  • (nil) —

    if no match

  • (String) —

    the matched portion of self, with punctuation stripped in case of #fuzzy_match

See Also:

[View source]

230
231
232
233
234
235
236
237
238
239
 
# File 'lib/fat_core/string.rb', line 230

def matches_with(matcher)
  if matcher.nil?
    nil
  elsif matcher =~ %r{^\s*/}
    re = matcher.to_regexp
    $& if to_s =~ re
  else
    to_s.fuzzy_match(matcher)
  end
end

#number? ⇒ Boolean

Return whether self is convertible into a valid number.

Examples:

'6465321'.number?        #=> true
'6465321.271828'.number? #=> true
'76 trombones'           #=> false
'2.77e7'                 #=> true
'+12_534'                #=> true

Returns:

  • (Boolean) —

    does self represent a valid number

[View source]

326
327
328
329
330
331
 
# File 'lib/fat_core/string.rb', line 326

def number?
  Float(self)
  true
rescue ArgumentError
  return false
end

#tex_quote ⇒ String

Return self with special TeX characters replaced with control-sequences that output the literal value of the special characters instead. It handles _, $, &, %, #, {, }, \, ^, ~, <, and >.

Examples:

'$100 & 20#'.tex_quote #=> '\\$100 \\& 20\\#'

Returns:

[View source]

85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/fat_core/string.rb', line 85

def tex_quote
  r = dup
  r = r.gsub(/[{]/, 'XzXzXobXzXzX')
  r = r.gsub(/[}]/, 'XzXzXcbXzXzX')
  r = r.gsub(/\\/, '\textbackslash{}')
  r = r.gsub(/\^/, '\textasciicircum{}')
  r = r.gsub(/~/, '\textasciitilde{}')
  r = r.gsub(/\|/, '\textbar{}')
  r = r.gsub(/\</, '\textless{}')
  r = r.gsub(/\>/, '\textgreater{}')
  r = r.gsub(/([_$&%#])/) { |m| '\\' + m }
  r = r.gsub('XzXzXobXzXzX', '\\{')
  r.gsub('XzXzXcbXzXzX', '\\}')
end

#to_regexp ⇒ Regexp

Convert a string of the form '/.../Iixm' to a regular expression. However, make the regular expression case-insensitive by default and extend the modifier syntax to allow '/I' to indicate case-sensitive. Without the surrounding '/', do not make the Regexp case insensitive, just translate it to a Regexp with Regexp.new.

Examples:

'/Hello/'.to_regexp #=> /Hello/i
'/Hello/I'.to_regexp #=> /Hello/
'Hello'.to_regexp #=> /Hello/

Returns:

  • (Regexp)
[View source]

290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
 
# File 'lib/fat_core/string.rb', line 290

def to_regexp
  if self =~ %r{^\s*/([^/]*)/([Iixm]*)\s*$}
    body = $1
    opts = $2
    flags = Regexp::IGNORECASE
    unless opts.blank?
      flags = 0 if opts.include?('I')
      flags |= Regexp::IGNORECASE if opts.include?('i')
      flags |= Regexp::EXTENDED if opts.include?('x')
      flags |= Regexp::MULTILINE if opts.include?('m')
    end
    flags = nil if flags.zero?
    body = Regexp.quote(body) if REGEXP_META_CHARACTERS.include?(body)
    Regexp.new(body, flags)
  else
    if REGEXP_META_CHARACTERS.include?(self)
      Regexp.new(Regexp.quote(self))
    else
      Regexp.new(self)
    end
  end
end

#wrap(width = 70, hang = 0) ⇒ String

Return a string wrapped to width characters with lines following the first indented by hang characters.

Returns:

[View source]

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
 
# File 'lib/fat_core/string.rb', line 51

def wrap(width = 70, hang = 0)
  result = ''
  first_line = true
  first_word_on_line = true
  line_width_so_far = 0
  words = split(' ')
  words.each do |w|
    if !first_line && first_word_on_line
      w = ' ' * hang + w
    end
    unless first_word_on_line
      w = ' ' + w
    end
    result << w
    first_word_on_line = false
    line_width_so_far += 1 + w.length
    if line_width_so_far >= width
      result << "\n"
      line_width_so_far = 0
      first_line = false
      first_word_on_line = true
    end
  end
  result.strip
end