fk_str 0.0.1

data/LICENSE

@@ -0,0 +1,20 @@
+ Copyright (c) 2012 Guilherme Baptista
+ https://github.com/gbaptista/fk_str
+
+ Permission is hereby granted, free of charge, to any person obtaining a copy
+ of this software and associated documentation files (the "Software"), to deal
+ in the Software without restriction, including without limitation the rights
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ copies of the Software, and to permit persons to whom the Software is
+ furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ THE SOFTWARE.

data/Rakefile

@@ -0,0 +1,8 @@
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+	t.libs << 'test'
+end
+
+desc 'Run tests'
+task :default => :test

data/lib/fk_str.rb

@@ -0,0 +1,497 @@
+# encoding: utf-8
+
+require 'date'
+require 'fk_str/dictionary'
+
+module FkStr
+
+	def self.treat_encoding str, debug=false
+		str_r = ''
+		str.lines.each_with_index { |l, i| str_r += ' ' + self.treat_encoding_s(l, debug) if !debug or (i > -1 and i < 1) }
+		return str_r.strip
+	end
+
+	def self.is_eq str, str_b, pct=1
+		
+		str = self.to_term str, true
+		str_b = self.to_term str_b, true
+
+		str_c = str.concat str_b
+
+		return true if (100-(100*str_c.uniq.size/str_c.size)) >= pct
+
+		return false
+
+	end
+
+	def self.to_slug str
+		
+		return str if str.to_s == ''
+
+		return self.remove_accents(str).gsub(/\s{1,}| {1,}/, ' ').gsub(/[\+\/_\-|:@#\\,]/, ' ').gsub('&', 'e').gsub(/[^a-zA-Z0-9 ]/, '').downcase.gsub(/\s{1,}| {1,}/, ' ').strip.gsub(' ', '-')
+
+	end
+
+	def self.to_term str, ar=false
+		
+		return str if str.to_s == ''
+		
+		str_ar = []
+		
+		self.to_slug(str).split('-').each do |s|
+			s.split('').uniq.each { |r| s = s.gsub /#{r}{2,}/, r }
+			@@simple_downcase_consonants.each { |c| s = s.gsub /#{c}(h|r|l|u)/, c }
+			if !s.empty? and !@@countries_acronyms.include? s and !@@articles_and_others.include? s
+				s = s.gsub /m/, 'n'
+				s = s.gsub /l/, 'r'
+				s = s.gsub /z/, 's'
+				s = s.gsub /g/, 'j'
+				s = s.gsub /e|y/, 'i'
+				s = s.gsub /o|w/, 'u'
+				s = s.gsub /c|q/, 'k'
+				s.split('').uniq.each { |r| s = s.gsub /#{r}{2,}/, r }
+				s = s.gsub /(r|s|n)$/, ''
+				str_ar << s if !s.empty?
+			end
+		end
+		
+		return str_ar.uniq if ar
+		
+		return str_ar.uniq.join
+		
+	end
+
+	def self.remove_accents str
+
+		return '' if str.to_s == ''
+		str = str.gsub(/[ÁÃÂÀÄĂĀÅÆ]/, 'A').gsub(/[áãâàäăāåæ]/, 'a')
+		str = str.gsub(/[ÉẼÊÈËĔĒ]/, 'E').gsub(/[éẽêèëĕē]/, 'e')
+		str = str.gsub(/[ÍĨÎÌÏĬĪ]/, 'I').gsub(/[íĩîìïĭī]/, 'i')
+		str = str.gsub(/[ÓÕÔÒÖŎŌŐÐ]/, 'O').gsub(/[óõôòöŏōőð]/, 'o')
+		str = str.gsub(/[ÚŨÛÙÜŬŪǕ]/, 'U').gsub(/[úũûùüŭūǖ]/, 'u')
+		str = str.gsub(/[ÇČ]/, 'C').gsub(/[çč]/, 'c').gsub(/Ğ/, 'G').gsub(/ğ/, 'g').gsub(/Ñ/, 'N').gsub(/ñ/, 'n').gsub(/Š/, 'S').gsub(/š/, 's')
+		str = str.gsub(/[ȲŸÝỲ]/, 'Y').gsub(/[ȳÿýỳ]/, 'y').gsub(/Ž/, 'Z').gsub(/ž/, 'z')
+
+		return str
+		
+	end
+
+	# 35 seconds
+	# 18 seconds
+	# 16 seconds
+	def self.upcasewords str
+
+		return str if str.to_s == ''
+
+		# Trata espaçamentos duplicados ou inválidos.
+		str = str.gsub(/\s{1,}| {1,}/, ' ').strip
+
+		rstr = []
+		str.split(' ').each { |w| rstr << upcaseword(w) }
+		str = rstr.join(' ')
+
+		# Trata espaçamentos duplicados ou inválidos.
+		str = str.gsub(/\s{1,}| {1,}/, ' ')
+
+		# Maiúsculo na primeira letra
+		fl = @@letters_by_letter[remove_accents(str[0]).downcase]
+		fl.each { |l| str[0] = str[0].gsub(l[0], l[1]) } if fl
+
+		return str
+
+	end
+
+	def self.remove_if_ends_with str, texts, not_change_if_returns_with=nil, if_not_change_returns_with_last_removed=0
+
+		return str if str.split(' ').size == 1
+
+		texts.each_with_index { |t, i| texts.delete_at i if t == '' }
+
+		str_o = str
+
+		str = str.strip
+
+		str_t = self.remove_accents(str).downcase
+
+		texts = texts.uniq
+
+		texts.each_with_index { |v, i| texts[i] = self.remove_accents(v).downcase }
+
+		not_change_if_returns_with.each_with_index { |v, i| not_change_if_returns_with[i] = self.remove_accents(v).downcase } if !not_change_if_returns_with.nil?
+
+		removed = []
+
+		continue = true
+		while continue
+			continue = false
+			texts.each do |t|
+
+				# Se o final da string for igual ao termo...
+				if t == str_t[str_t.size-t.size..str_t.size].to_s
+
+					# Se antes do termo final na string não for igual à ' de ' ou ' da '...
+					if ![' de ', ' da '].include? str_t[str_t.size-t.size-4].to_s + str_t[str_t.size-t.size-3..str_t.size-t.size-2].to_s + str_t[str_t.size-t.size-1].to_s
+
+						# Se o primeiro char do termo não for uma letra ou se o char anterior ao termo não for uma letra...
+						if (!@@simple_downcase_letters.include? t[0] or !@@simple_downcase_letters.include? str_t[str_t.size-t.size-1]) and str_t.size > 1
+							
+							str_l = str
+							
+							str = str[0..str.size-t.size-1].strip
+							str_t = self.remove_accents(str).downcase
+
+							removed << str_l[str.size..str_l.size]
+
+							continue = true
+
+						end
+
+					end
+
+				end
+
+			end
+		end
+
+		# Se o retorno for igual à alguma condição que não deve ser retornada...
+		if !not_change_if_returns_with.nil?
+			if not_change_if_returns_with.include?(self.remove_accents(str).downcase)
+				# Se for solicitado que retorne apenas com x termos que foram removidos...
+				if if_not_change_returns_with_last_removed > 0
+					removed = removed.reverse
+					(1..if_not_change_returns_with_last_removed).each { |n| str += removed[n-1].to_s }
+					return str.strip
+				end
+				return str_o
+			end
+		end
+
+		return str
+
+	end
+
+	def self.extract_dates str, reference_date=Time.now, reverse_month_day=false
+		
+		return [] if str.nil?
+		
+		return [Time.new(str.year, str.month, str.day)] if str.kind_of?(Time) or str.kind_of?(Date) or str.kind_of?(DateTime)
+		
+		o_str = str
+		
+		years = []
+		(-30..20).each { |y| years << reference_date.year+y }
+
+		begin
+			
+			str = str.gsub /[0-9]{1,}(º|ª)/, ' '
+
+			str = self.remove_accents str
+
+			str = str.downcase
+
+			str = str.gsub /[0-9]{1,}+[a-z]{1,}+[0-9]{1,}/, ''
+			str = str.gsub /[0-9]{1,}+[a-z]{1,}/, ' '
+			str = str.gsub /[a-z]{1,}+[0-9]{1,}/, ' '
+
+			str = str.gsub(/[^a-z|^0-9|^\/|^\-|^\.|^:]/i, ' ')
+
+			str = str.gsub(/[0-9]{1,}:[0-9]{1,}|:[0-9]{1,}|[0-9]{1,}h[0-9]{1,}|[0-9]{1,}%|[0-9]{1,}h |[0-9]{1,}h$|palco [0-9]{1,}/i, '')
+
+			str.scan(/[0-9]{1,}+.+[0-9]{1,}/).each { |d| str = str.gsub(d, d.gsub('.', '/')) }
+			
+			if reverse_month_day
+				str.scan(/[0-9]{1,}\/[0-9]{1,}/).each do |d|
+					str = str.gsub(d, d.split('/')[1] + '/' + d.split('/')[0])
+				end
+			end
+			
+			@@months_strs.each do |mc|
+				str.scan(/#{mc.first}.*[0-9]{1,2}+[1-9]{2,4}/).each do |md|
+					if md.scan(/[0-9]{1,2}/).size < 4 and md.scan(/[0-9]{4,}/).size < (md.scan(/[0-9]{2,2}/).size-1)
+						
+						continue = true
+
+						@@months_strs.each do |smc|
+							md.scan(/[0-9].*#{smc.first}/).each do |d|
+								continue = false
+							end
+						end
+						if continue
+							m = md.scan(/[0-9]{1,2}/).first
+							str = str.gsub(/#{mc.first}.+#{m}/, "#{m} #{mc.first}").gsub(',', '')
+						end
+					end
+				end
+			end
+
+			str.scan(/[0-9]{4,4}-[0-9]{1,2}-[0-9]{1,2}/).each do |y|
+				str = str.gsub(y, y.split('-')[2] + '/' + y.split('-')[1] + '/' + y.split('-')[0])
+			end
+
+			str.scan(/[0-9]{4,4}\/[0-9]{1,2}\/[0-9]{1,2}/).each do |y|
+				str = str.gsub(y, y.split('/')[2] + '/' + y.split('/')[1] + '/' + y.split('/')[0])
+			end
+
+			str.scan(/[0-9]{1,2}-[0-9]{1,2}-[0-9]{2,4}/).each do |y|
+				str = str.gsub(y, y.split('-')[0] + '/' + y.split('-')[1] + '/' + y.split('-')[2])
+			end
+
+			str.scan(/[0-9]{1,2}\/[0-9]{1,2}\/[0-9]{1,}/).each do |y|
+				if y.split('/')[2].size < 4
+					sr = y.split('/').first + '/' + y.split('/')[1]
+					sy = y.split('/')[2]
+					if sy.size < 3
+						sy = '0' + sy if sy.size == 1
+						if years.include? (reference_date.year.to_s[0..1]+sy).to_i
+							sr += '/' + reference_date.year.to_s[0..1]+sy
+						elsif years.include? ((reference_date.year-100).to_s[0..1]+sy).to_i
+							sr += '/' + (reference_date.year-100).to_s[0..1]+sy
+						end
+					end
+					str = str.gsub(y, sr)
+				end
+			end
+
+			str = str.gsub(/[0-9]{5,}/, '')
+
+			dates = []
+			continue = true
+			while continue
+
+				@@months_strs.each do |m|
+
+					str.scan(/([0-9].*#{m.first})+([^0-9]|$)/).each do |d|
+						days = d.first.split(/(#{m.first})+([^0-9]|$)/).first
+						jump=false
+						@@months_strs.each do |mc|
+							if days.scan(/([0-9].*#{mc.first})+([^0-9]|$)/).size > 0
+								jump = true
+							end
+						end
+						if !jump
+
+							year = nil
+							str.scan(/#{days}#{m.first}.*[0-9]{4,4}/).each do |sc|
+								sy = sc.gsub(/(#{days}#{m.first})+([^0-9]|$)/, '')
+
+								# [lorem 9/jan/2012] = false
+								# [2012 e 07/05/2012] = true
+								# [2012] = true
+
+								if sy.scan(/[0-9]{4,4}/).size > 1 or (sy.scan(/[0-9]{4,4}/).size == 1 and !sy.gsub(/[0-9]{4,4}/, '').match(/[0,9]/))
+									sy.scan(/[0-9]{4,4}/).each { |y| year=y.to_i if years.include? y.to_i; break; }
+								end
+							end
+
+							#puts '[' + str + '] => ' + year.inspect
+							str = str.gsub(/(#{days}#{m.first})+([^0-9]|$)/, '')
+							#puts '[' + str + "\n\n"
+
+							days.gsub(/[0-9]{4,4}/, '').scan(/[0-9]{1,2}/).each do |day|
+								day = day.to_i
+								if day > 0 and day < 32
+									if year
+										dates<<Time.new(year, m[1], day)
+									elsif m[1]<(reference_date.month-3)
+										dates<<Time.new(reference_date.year+1, m[1], day)
+									else
+										dates<<Time.new(reference_date.year, m[1], day)
+									end
+								end
+							end
+						end
+					end
+				end
+				continue = false
+				@@months_strs.each do |mt|
+						if str.scan(/([0-9].*#{mt.first})+([^0-9]|$)/).size > 0
+						continue = true
+					end
+				end
+			end
+					
+			return dates.uniq.sort
+
+		rescue => exc
+			return []
+		end
+		
+	end
+
+	def self.extract_time str, date=nil, reference_time=Time.now
+
+		return nil if date.nil?
+
+		return Time.new(date.year, date.month, date.day, reference_time.hour, reference_time.min) if str.nil? or !str.match /[0-9]{1,2}:[0-9]{1,2}/
+
+		begin
+			time = str.scan(/[0-9]{1,2}:[0-9]{1,2}/).first.split(':')
+			return Time.new(date.year, date.month, date.day, time[0], time[1])
+		rescue => exp
+			return Time.new(date.year, date.month, date.day, reference_time.hour, reference_time.min) 
+		end
+
+	end
+	
+	private
+
+	def self.treat_encoding_s str, debug=false
+		begin
+			str_r = ''
+			ws = str.split(' ').each_slice(20)
+			ws.each_with_index do |w, i|
+				if i == 0
+					str_r += self.treat_encoding_i w.join(' '), 0, debug
+				else
+					str_r += ' ' + self.treat_encoding_i(w.join(' '), 0, debug)
+				end
+			end
+		rescue => exp
+			str_r = ''
+			str.chars.each_slice(200).each { |w| str_r += self.treat_encoding_i w.join, 0, debug }
+		end
+
+		return str_r
+
+	end
+
+	def self.valid_encoding str, tolerance=0, debug=false
+		str_v = str
+		begin
+			str_v.match 'á'
+			str_v = str_v.gsub /\s{1,}|\n{1,}|\r{1,}/, ''
+			@@legal_chars.each { |lc| str_v = str_v.gsub lc, '' }
+			@@invalid_sequences.each { |is| raise 'invalid sequence: ' + is if str.match is }
+			puts '[' + str_v + ']' if debug and str_v.size > 0
+			return false if str_v.size > tolerance
+			str_v.split('').each { |c| str = str.gsub c, '' } if str_v.size > 0
+			return str
+		rescue => exp
+			#puts '[error] ' + exp.message if debug or !exp.message.match /incompatible encoding|invalid byte sequence|invalid sequence/i
+			return false
+		end
+	end
+
+	def self.treat_encoding_i str, tolerance=0, debug=false
+		
+		str_t = str
+		
+		str_v = self.valid_encoding str_t, tolerance, debug
+		if !str_v
+			puts '[try force_encoding UTF-8]' if debug
+			begin
+				str_t = str.force_encoding 'UTF-8'
+			rescue  => exp
+			end
+		else
+			return str_v
+		end
+		
+		str_v = self.valid_encoding str_t, tolerance, debug
+		if !str_v
+			puts '[try WINDOWS-1252]' if debug
+			begin
+				str_t = str.encode 'UTF-8', 'WINDOWS-1252'
+			rescue  => exp
+			end
+		else
+			return str_v
+		end
+		
+		str_v = self.valid_encoding str_t, tolerance, debug
+		if !str_v
+			puts '[try UTF-8]' if debug
+			begin
+				str_t = str.encode 'UTF-8', 'UTF-8'
+			rescue  => exp
+			end
+		else
+			return str_v
+		end
+
+		str_v = self.valid_encoding str_t, tolerance, debug
+		if !str_v
+			puts '[try ISO-8859-2]' if debug
+			begin
+				str_t = str.encode 'UTF-8', 'ISO-8859-2'
+			rescue  => exp
+			end
+		else
+			return str_v
+		end
+		
+		str_v = self.valid_encoding str_t, tolerance, debug
+		if !str_v
+			puts '[try ISO-8859-3]' if debug
+			begin
+				str_t = str.encode 'UTF-8', 'ISO-8859-3'
+			rescue  => exp
+			end
+		else
+			return str_v
+		end
+		
+		str_v = self.valid_encoding str_t, tolerance, debug
+		if tolerance == 0 and !str_v
+			str_t = self.treat_encoding_i str, 1, debug
+		end
+		
+		return str_t
+		
+	end
+
+	def self.upcaseword w
+
+		return w if w.to_s == ''
+
+		if w.scan(/#{@@separators_regex.join('|')}/).size == 0
+
+			# Cria uma Array apenas com os caracteres necessários por questões de performance.
+			letters = []
+			clean_word = self.remove_accents(w).downcase.gsub(/[^a-z]/, '')
+			clean_word.split('').uniq.each { |lt| @@letters_by_letter[lt].each { |l| letters << l } }
+
+			trf = 'tm'
+			trf = 'tfu'	if w.size > 5 or !@@articles_and_others.include? clean_word
+			trf = 'tau'	if !w.match(/^mr$|^jr$|^mr.$|^jr.$|^sr$|^sr.$/i) and ((w.size < 6 and clean_word.match(/[^aeiouwy]{4,}|[aeiouwy]{4,}|^[^aeiouwy]{2,3}$/)) or w.scan('.').size > 2)
+			
+			letters.each do |l|
+				
+				# Transforma tudo em minúsculo.
+				w = w.gsub l[1], l[0] if trf == 'tm' || trf == 'tfu'
+
+				# Maiúsculo na primeira letra caso não seja um artigo ou algo do gênero.
+				w = w.gsub /^#{l[0]}/, l[1] if trf == 'tfu'
+
+				# Transforma em maiúsculo:
+				# * Sequência de 4 ou mais consoantes.
+				# * Sequência de 4 ou mais vogais.
+				# * Sequência exata de 2 ou 3 vogais.
+
+				w = w.gsub l[0], l[1] if trf == 'tau'
+
+			end
+
+		else
+
+			# Quebra termos entre caracteres separadores como "'", "(", etc.
+			@@separators.each do |l|
+				sw = w.split(l)
+				if sw.size > 1
+					# Trata o termo isoladamente se não for uma letra única antes de "'"
+					sw.each_with_index { |v, i| sw[i] = upcaseword v if !(["'"].include? l and v.size == 1 and i == 0) }
+					if w[w.size-1] == l
+						w = sw.join(l) + l
+					else
+						w = sw.join(l)
+					end
+				end
+			end
+
+		end
+
+		return w
+
+	end
+	
+end

data/lib/fk_str/dictionary.rb

@@ -0,0 +1,106 @@
+# encoding: utf-8
+
+module FkStr
+
+	@@months_strs = {
+		'jan' => 1, 'fev' => 2, 'mar' => 3, 'abr' => 4, 'mai' => 5, 'jun' => 6,
+		'jul' => 7, 'ago' => 8, 'set' => 9, 'out' => 10, 'nov' => 11, 'dez' => 12,
+		'/1' => 1, '/2' => 2, '/3' => 3, '/4' => 4,
+		'/5' => 5, '/6' => 6, '/7' => 7, '/8' => 8, '/9' => 9,
+		'/01' => 1, '/02' => 2, '/03' => 3, '/04' => 4, '/05' => 5, '/06' => 6,
+		'/07' => 7, '/08' => 8, '/09' => 9, '/10' => 10, '/11' => 11, '/12' => 12,
+		'feb' => 2, 'apr' => 4, 'may' => 5, 'aug' => 8, 'sep' => 9, 'oct' => 10, 'dec' => 12
+	}
+
+	@@letters_by_letter = {
+		'a' => { 'a' => 'A', 'á' => 'Á', 'ã' => 'Ã', 'â' => 'Â', 'à' => 'À', 'ä' => 'Ä', 'ă' => 'Ă', 'ā' => 'Ā', 'å' => 'Å', 'æ' => 'Æ' },
+		'b' => { 'b' => 'B' },
+		'c' => { 'c' => 'C', 'ç' => 'Ç', 'č' => 'Č' },
+		'd' => { 'd' => 'D' },
+		'e' => { 'e' => 'E', 'é' => 'É', 'ẽ' => 'Ẽ', 'ê' => 'Ê', 'è' => 'È', 'ë' => 'Ë', 'ĕ' => 'Ĕ', 'ē' => 'Ē' },
+		'f' => { 'f' => 'F' },
+		'g' => { 'g' => 'G', 'ğ' => 'Ğ' },
+		'h' => { 'h' => 'H' },
+		'i' => { 'i' => 'I', 'í' => 'Í', 'ĩ' => 'Ĩ', 'î' => 'Î', 'ì' => 'Ì', 'ï' => 'Ï', 'ĭ' => 'Ĭ', 'ī' => 'Ī' },
+		'j' => { 'j' => 'J' },
+		'k' => { 'k' => 'K' },
+		'l' => { 'l' => 'L' },
+		'm' => { 'm' => 'M' },
+		'n' => { 'n' => 'N', 'ñ' => 'Ñ' },
+		'o' => { 'o' => 'O', 'ó' => 'Ó', 'õ' => 'Õ', 'ô' => 'Ô', 'ò' => 'Ò', 'ö' => 'Ö', 'ŏ' => 'Ŏ', 'ō' => 'Ō', 'ő' => 'Ő', 'ð' => 'Ð' },
+		'p' => { 'p' => 'P' },
+		'q' => { 'q' => 'Q' },
+		'r' => { 'r' => 'R' },
+		's' => { 's' => 'S', 'š' => 'Š' },
+		't' => { 't' => 'T' },
+		'u' => { 'u' => 'U', 'ú' => 'Ú', 'ũ' => 'Ũ', 'û' => 'Û', 'ù' => 'Ù', 'ü' => 'Ü', 'ŭ' => 'Ŭ', 'ū' => 'Ū', 'ǖ' => 'Ǖ' },
+		'v' => { 'v' => 'V' },
+		'w' => { 'w' => 'W' },
+		'x' => { 'x' => 'X' },
+		'y' => { 'y' => 'Y', 'ȳ' => 'Ȳ', 'ÿ' => 'Ÿ', 'ý' => 'Ý', 'ỳ' => 'Ỳ' },
+		'z' => { 'z' => 'Z', 'ž' => 'Ž' }
+	}
+
+	@@articles_and_others = [
+		# Português
+		'a', 'ao', 'aos', 'as',
+		'co', 'coa', 'coas', 'com', 'cos',
+		'da', 'das', 'de', 'do', 'dos', 'dum', 'duma', 'dumas', 'duns',
+		'e', 'em',
+		'na', 'nas', 'no', 'nos', 'num', 'numa', 'numas', 'nuns',
+		'o', 'os', 'ou',
+		'pela', 'pelas', 'pelo', 'pelos', 'per', 'por',
+		'um', 'uma', 'umas', 'uns',
+		# English
+		'an', 'and', 'at', 'by', 'in', 'of', 'or', 'on', 's', 'the'
+	]
+	def FkStr.articles_and_others
+		return @@articles_and_others
+	end
+
+	@@countries_acronyms = [
+		# Brasil
+		'br',
+		'ac', 'al', 'ap', 'am', 'ba', 'ce', 'df', 'es', 'go', 'ma', 'mt','ms', 'mg', 'pa', 'pb',
+		'pr', 'pe', 'pi', 'rj', 'rn', 'rs', 'ro', 'rr', 'sc', 'sp', 'se', 'to',
+		# USA
+		'us',
+		'ak', 'al', 'ar', 'az', 'ca', 'co', 'ct', 'dc', 'de', 'fl', 'ga', 'hi', 'ia', 'id', 'il',
+		'in', 'ks', 'ky', 'la', 'ma', 'md', 'me', 'mi', 'mn', 'mo', 'ms', 'mt', 'nc', 'nd', 'ne',
+		'nh', 'nj', 'nm', 'nv', 'ny', 'oh', 'ok', 'or', 'pa', 'ri', 'sc', 'sd', 'tn', 'tx', 'ut',
+		'va', 'vt', 'wa', 'wi', 'wv', 'wy'
+	]
+	def FkStr.countries_acronyms
+		return @@countries_acronyms
+	end
+
+	@@simple_downcase_letters = [
+		'a', 'b', 'c', 'd', 'e',
+		'f', 'g', 'h', 'i', 'j',
+		'k', 'l', 'm', 'n', 'o',
+		'p', 'q', 'r', 's', 't',
+		'u', 'v', 'w', 'x', 'y',
+		'z'
+	]
+	
+	@@simple_downcase_consonants = [
+		'b', 'c', 'd',
+		'f', 'g', 'h', 'j',
+		'k', 'l', 'm', 'n',
+		'p', 'q', 'r', 's', 't',
+		'v', 'w', 'x', 'y',
+		'z'
+	]
+
+	@@separators = ['/', '-', '_', ',', '.', "'", '"', '(', ')', '[', ']', '{', '}', '|', '\\', ';']
+	def FkStr.separators
+		return @@separators
+	end
+	
+	@@separators_regex = ['\/', '\-', "\'", '\"', '\(', '\)', '\[', '\]', '\{', '\}']
+	
+	@@legal_chars = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz _-!@#$%&*+=?^~´`,.:;\'"()[]{}|/\\<>ÁÃÂÀÄĂĀÅÆáãâàäăāåæÉẼÊÈËĔĒéẽêèëĕēÍĨÎÌÏĬĪíĩîìïĭīÓÕÔÒÖŎŌŐÐóõôòöŏōőðšŠÚŨÛÙÜŬŪǕúũûùüŭūǖÇçČčĞğÑñȲȳŸÿÝýỲỳŽž¹²³ºª	– ’©®℗¿¡±“”•«»‘°'.split('')
+
+	@@invalid_sequences = ['é']
+	
+end

data/test/test_fk_str.rb

@@ -0,0 +1,255 @@
+# encoding: utf-8
+
+require 'test/unit'
+require 'fk_str'
+
+class FkStrTest < Test::Unit::TestCase
+
+	def test_treat_encoding
+
+		assert_equal(
+			'çUTF-8',
+			FkStr.treat_encoding("\xE7")+FkStr.treat_encoding("\xE7").encoding.to_s.upcase
+		)
+
+		assert_equal(
+			'©UTF-8',
+			FkStr.treat_encoding("\xC2\xA9")+FkStr.treat_encoding("\xC2\xA9").encoding.to_s.upcase
+		)
+
+		assert_equal(
+			'caçaUTF-8',
+			FkStr.treat_encoding("ca\xE7a")+FkStr.treat_encoding("ca\xE7a").encoding.to_s.upcase
+		)
+
+		assert_equal(
+			'casaUTF-8',
+			FkStr.treat_encoding('casa')+FkStr.treat_encoding('casa').encoding.to_s.upcase
+		)
+
+	end
+
+	def test_is_eq
+
+		assert_equal(
+			true,
+			FkStr.is_eq('Hangar 110', 'Hangar 110', 40)
+		)
+
+		assert_equal(
+			true,
+			FkStr.is_eq('Armagedon + Atos de Vingança', 'Armagedom')
+		)
+
+		assert_equal(
+			false,
+			FkStr.is_eq('Gato Cat', 'Cachorro Dog')
+		)
+
+		assert_equal(
+			true,
+			FkStr.is_eq('Creedence Clearwater Revisited', 'Creedence Clearwater')
+		)
+
+	end
+
+	def test_to_slug
+
+		assert_equal(
+			'teste-dog',
+			FkStr.to_slug('teste:dog')
+		)
+
+		assert_equal(
+			'centro-rio-de-janeiro-rj',
+			FkStr.to_slug('Centro - Rio de Janeiro [RJ]')
+		)
+
+		assert_equal(
+			'sao-paulo-sp',
+			FkStr.to_slug('São Paulo/SP')
+		)
+
+		assert_equal(
+			'sao-paulo-sp',
+			FkStr.to_slug('São Paulo_SP')
+		)
+
+	end
+
+	def test_to_term
+
+		assert_equal(
+			'kasadujkakurururi',
+			FkStr.to_term('casa & dog and cachorro e lorem')
+		)
+
+		assert_equal(
+			'tistiduj',
+			FkStr.to_term('teste:de\dog')
+		)
+
+		assert_equal(
+			'saupauru',
+			FkStr.to_term('São Paulo-SP')
+		)
+
+		assert_equal(
+			'tistiduj',
+			FkStr.to_term('teste:de:dog')
+		)
+
+	end
+
+	def test_remove_accents
+
+		assert_equal(
+			'Sao Jose do Rio Preto - SP',
+			FkStr.remove_accents('São José do Rio Preto - SP')
+		)
+
+		assert_equal(
+			'Sao Paulo',
+			FkStr.remove_accents('São Paulo')
+		)
+
+		assert_equal(
+			'Acougue',
+			FkStr.remove_accents('Açougue')
+		)
+
+		assert_equal(
+			'Lorem Ipsum',
+			FkStr.remove_accents('Lôrém Ipsum')
+		)
+
+	end
+
+	def test_upcasewords
+
+		assert_equal(
+			'Charlie Brown Jr.',
+			FkStr.upcasewords('CHARLIE BROWN JR.')
+		)
+
+		assert_equal(
+			'Coldplay',
+			FkStr.upcasewords('COLDPLAY')
+		)
+
+		assert_equal(
+			'Queensrÿche',
+			FkStr.upcasewords('QUEENSRŸCHE')
+		)
+
+		assert_equal(
+			'Mindflow',
+			FkStr.upcasewords('MINDFLOW')
+		)
+
+	end
+
+	def test_remove_if_ends_with
+
+		assert_equal(
+			'Natal La Barra',
+			FkStr.remove_if_ends_with(
+				'Natal La Barra - Caxias do Sul / RS',
+				['La Barra', 'Caxias do Sul', 'RS', '/', '-'],
+				['Natal'],
+				1
+			)
+		)
+
+		assert_equal(
+			'Natal La Barra -',
+			FkStr.remove_if_ends_with(
+				'Natal La Barra - Caxias do Sul / RS',
+				['La Barra', 'Caxias do Sul', 'RS', '/', '-'],
+				['Natal'],
+				2
+			)
+		)
+
+		assert_equal(
+			'Natal La Barra - Caxias do Sul',
+			FkStr.remove_if_ends_with(
+				'Natal La Barra - Caxias do Sul / RS',
+				['La Barra', 'Caxias do Sul', 'RS', '/', '-'],
+				['Natal'],
+				3
+			)
+		)
+
+		assert_equal(
+			'Masp',
+			FkStr.remove_if_ends_with('Masp São Paulo/SP', ['São Paulo', 'SP', '/'])
+		)
+
+	end
+
+	def test_extract_dates
+
+		assert_equal(
+			[Time.new(2012, 12, 6)].uniq.sort,
+			FkStr.extract_dates('December 06, 2012', Time.new(2012, 9, 12))
+		)
+
+		assert_equal(
+			[Time.new(2012, 9, 14)].uniq.sort,
+			FkStr.extract_dates('FRI 09.14.2012', Time.new(2012, 9, 12), true)
+		)
+
+		assert_equal(
+			[Time.new(2011, 12, 8), Time.new(2012, 1, 9)].uniq.sort,
+			FkStr.extract_dates('8/dez lorem 9/jan/2012', Time.new(2011, 10, 8))
+		)
+
+		assert_equal(
+			[Time.new(2012, 1, 2)].uniq.sort,
+			FkStr.extract_dates('2 de janeiro', Time.new(2011, 10, 8))
+		)
+
+	end
+
+	def test_extract_time
+
+		assert_equal(
+			Time.new(2011, 07, 14, 22, 18, 0),
+			FkStr.extract_time(
+				'Thu, 14 Jul 2011 22:18:49 +0000',
+				FkStr.extract_dates('Thu, 14 Jul 2011 22:18:49 +0000',Time.new(2012, 5, 28)).first,
+				Time.new(2012, 5, 28)
+			)
+		)
+
+		assert_equal(
+			Time.new(2011, 07, 14, 16, 15, 0),
+			FkStr.extract_time(
+				'14 Jul 2011 16:15',
+				FkStr.extract_dates('14 Jul 2011 16:15',Time.new(2012, 5, 28)).first,
+				Time.new(2012, 5, 28)
+			)
+		)
+
+		assert_equal(
+			Time.new(2011, 07, 14, 9, 0, 0),
+			FkStr.extract_time(
+				'14 Jul 2011 9:00',
+				FkStr.extract_dates('14 Jul 2011 9:00',Time.new(2012, 5, 28)).first,
+				Time.new(2012, 5, 28)
+			)
+		)
+
+		assert_equal(
+			Time.new(2011, 07, 14, 7, 35, 0),
+			FkStr.extract_time(
+				'14 Jul 2011 07:35',
+				FkStr.extract_dates('14 Jul 2011 07:35',Time.new(2012, 5, 28)).first,
+				Time.new(2012, 5, 28)
+			)
+		)
+
+	end
+
+end

metadata

@@ -0,0 +1,49 @@
+--- !ruby/object:Gem::Specification
+name: fk_str
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Guilherme Baptista
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-03-13 00:00:00.000000000 Z
+dependencies: []
+description: String manipulation.
+email: guilhermebaptistasilva@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE
+- Rakefile
+- lib/fk_str.rb
+- lib/fk_str/dictionary.rb
+- test/test_fk_str.rb
+homepage: https://github.com/gbaptista/fk_str
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: FkStr
+test_files: []