string_cleaner 0.2.0 → 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 8451c9bc58c373d7b4a768cb3ed1ff355e5116f24b02c6a5bfeb69aa0549c589
+  data.tar.gz: b226d948238bd18cdacb01402c0576203da724b895c6745d3b713fae5d21f9ee
+SHA512:
+  metadata.gz: 3a83693387d088db6f0b89ea73ecffbdf0b034885a0b2418d222c1197c48794b05cc8fb28f477bcfc4d345ee561d0ea3e1a543c34309ddb77ecc79a6adffe4fb
+  data.tar.gz: 3a35bab3513612149b345bf96d536d741ed3d4dfa757a353d3bc955782173139e8dac4c92b0bef025534706ca13e0ba17b14a30da0b10029d2653eeded5224f2

data/.gitignore

@@ -3,4 +3,5 @@
 coverage
 rdoc
 pkg
-*.gem
+*.gem
+Gemfile.lock

data/README.rdoc

@@ -6,21 +6,15 @@ Just add a method .clean to String which does:
 * replace \r\n and \r with \n normalizing end of lines
 * replace control characters and other invisible chars by spaces
 
-== Install
-
-  sudo gem install JosephHalter-string_cleaner
-
-== Ruby 1.9+
+Supports only Ruby 2.6+
 
-Ruby 1.9+ has native support for unicode and specs are 100% passing.
-
-== Ruby 1.8.x
+== Install
 
-Because Ruby 1.8.x has no native support for Unicode, you must install oniguruma and the jasherai-oniguruma gem.
+  sudo gem install string_cleaner
 
 == Example usage
 
-  "\210\004".clean # => " "
+    "\210\004".clean # => " "
 
 == Copyright
 

data/Rakefile

@@ -1,4 +1,11 @@
-require 'rubygems'
+if RUBY_VERSION.to_f<1.9
+  require 'rake/tasklib'
+  require 'rake/rdoctask'
+  require 'rubygems'
+else
+  require 'rdoc/task'
+end
+
 begin
   require 'bundler/setup'
 rescue LoadError
@@ -17,7 +24,6 @@ end
 
 task :default => :spec
 
-require 'rake/rdoctask'
 Rake::RDocTask.new do |rdoc|
   rdoc.rdoc_dir = 'rdoc'
   rdoc.title = "string_cleaner"

data/lib/string_cleaner.rb

@@ -9,14 +9,13 @@ module String::Cleaner
 
   def fix_encoding
     utf8 = dup
-    if utf8.respond_to?(:force_encoding) 
+    if utf8.respond_to?(:force_encoding)
       utf8.force_encoding("UTF-8") # for Ruby 1.9+
       unless utf8.valid_encoding? # if invalid UTF-8
-        utf8 = utf8.force_encoding("ISO8859-15")
+        utf8 = utf8.force_encoding("ISO8859-1")
         utf8.encode!("UTF-8", :invalid => :replace, :undef => :replace, :replace => "")
-        utf8.gsub!("\xC2\x80", "€") # special case for euro sign from Windows-1252
-        utf8.force_encoding("UTF-8")
       end
+      utf8.gsub!(/\u0080|¤/, "€") # special case for euro sign from Windows-1252
       utf8
     else
       require "iconv"
@@ -25,7 +24,7 @@ module String::Cleaner
         Iconv.new("UTF-8", "UTF-8").iconv(utf8)
       rescue
         utf8.gsub!(/\x80/n, "\xA4")
-        Iconv.new("UTF-8//IGNORE", "ISO8859-15").iconv(utf8)
+        Iconv.new("UTF-8//IGNORE", "ISO8859-1").iconv(utf8).gsub("¤", "€")
       end
     end
   end
@@ -35,31 +34,40 @@ module String::Cleaner
   end
   
   SPECIAL_SPACES = [
-            0x00A0,                # White_Space # Zs       NO-BREAK SPACE
-            0x1680,                # White_Space # Zs       OGHAM SPACE MARK
-            0x180E,                # White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
-            (0x2000..0x200A).to_a, # White_Space # Zs  [11] EN QUAD..HAIR SPACE
-            0x2028,                # White_Space # Zl       LINE SEPARATOR
-            0x2029,                # White_Space # Zp       PARAGRAPH SEPARATOR
-            0x202F,                # White_Space # Zs       NARROW NO-BREAK SPACE
-            0x205F,                # White_Space # Zs       MEDIUM MATHEMATICAL SPACE
-            0x3000,                # White_Space # Zs       IDEOGRAPHIC SPACE
-          ].flatten.collect{|e| [e].pack 'U*'}
+    0x00A0,                # NO-BREAK SPACE
+    0x1680,                # OGHAM SPACE MARK
+    0x180E,                # MONGOLIAN VOWEL SEPARATOR
+    (0x2000..0x200A).to_a, # EN QUAD..HAIR SPACE
+    0x2028,                # LINE SEPARATOR
+    0x2029,                # PARAGRAPH SEPARATOR
+    0x202F,                # NARROW NO-BREAK SPACE
+    0x205F,                # MEDIUM MATHEMATICAL SPACE
+    0x3000,                # IDEOGRAPHIC SPACE
+  ].flatten.collect{|e| [e].pack 'U*'}
+
+  ZERO_WIDTH = [
+    0x200B,                # ZERO WIDTH SPACE
+    0x200C,                # ZERO WIDTH NON-JOINER
+    0x200D,                # ZERO WIDTH JOINER
+    0x2060,                # WORD JOINER
+    0xFEFF,                # ZERO WIDTH NO-BREAK SPACE
+  ].flatten.collect{|e| [e].pack 'U*'}
 
   def fix_invisible_chars
     utf8 = self.dup
-    if utf8.respond_to?(:force_encoding)
+    utf8.gsub!(Regexp.new(ZERO_WIDTH.join("|")), "")
+    utf8 = if utf8.respond_to?(:force_encoding)
       utf8 = (utf8 << " ").split(/\n/u).each{|line|
         line.gsub!(/[\s\p{C}]/u, " ")
       }.join("\n").chop!
-      utf8.gsub!(Regexp.new(SPECIAL_SPACES.join("|")), " ")
-      utf8.force_encoding("UTF-8")
     else
       require "oniguruma"
       utf8.split(/\n/n).collect{|line|
-        Oniguruma::ORegexp.new("[\\s\\p{C}]", {:encoding => Oniguruma::ENCODING_UTF8}).gsub(line, " ")
+        Oniguruma::ORegexp.new("[\\p{C}]", {:encoding => Oniguruma::ENCODING_UTF8}).gsub(line, " ")
       }.join("\n").chop!
     end
+    utf8.gsub!(Regexp.new(SPECIAL_SPACES.join("|") + "|\s"), " ")
+    utf8
   end
 
   def trim(chars = "")
@@ -67,7 +75,7 @@ module String::Cleaner
   end
 
   def to_permalink(separator="-")
-    fix_endlines.to_ascii(chartable).downcase.gsub(/[^a-z0-9]+/, separator).trim(separator)
+    clean.to_ascii(chartable).downcase.gsub(/[^a-z0-9]+/, separator).trim(separator)
   end
 
   def nl2br

data/spec/string_cleaner_spec.rb

@@ -1,147 +1,72 @@
-# encoding: UTF-8
-require File.dirname(__FILE__) + "/spec_helper"
+require "spec_helper"
 
-describe String::Cleaner do
-  if "".respond_to?(:force_encoding)
-    # specs for Ruby 1.9+
+RSpec.describe String::Cleaner do
+  describe "#clean" do
     describe "with all 8-bit characters" do
       before :all do
-        @input = "".force_encoding("ISO8859-15")
+        @input = ""
+        @input.force_encoding("ISO8859-15") if @input.respond_to?(:force_encoding)
         (0..255).each{|i| @input << i.chr}
-        @input.force_encoding("UTF-8")
+        @input.force_encoding("UTF-8") if @input.respond_to?(:force_encoding)
         @output = @input.clean
       end
-      it "should output a valid UTF-8 string" do
-        @output.encoding.name.should == "UTF-8"
-        @output.should be_valid_encoding
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
       end
       it "should wipe out the control characters" do
-        @output.should == "          \n  \n                   !\"\#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ €                                ¡¢£€¥Š§š©ª«¬ ®¯°±²³Žµ¶·ž¹º»ŒœŸ¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ"
-      end
-    end
-    it "should convert all type of spaces to normal spaces" do
-      input = [
-                (0x0009..0x000D).to_a, # White_Space # Cc   [5] <control-0009>..<control-000D>
-                0x0020,                # White_Space # Zs       SPACE
-                0x0085,                # White_Space # Cc       <control-0085>
-                0x00A0,                # White_Space # Zs       NO-BREAK SPACE
-                0x1680,                # White_Space # Zs       OGHAM SPACE MARK
-                0x180E,                # White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
-                (0x2000..0x200A).to_a, # White_Space # Zs  [11] EN QUAD..HAIR SPACE
-                0x2028,                # White_Space # Zl       LINE SEPARATOR
-                0x2029,                # White_Space # Zp       PARAGRAPH SEPARATOR
-                0x202F,                # White_Space # Zs       NARROW NO-BREAK SPACE
-                0x205F,                # White_Space # Zs       MEDIUM MATHEMATICAL SPACE
-                0x3000,                # White_Space # Zs       IDEOGRAPHIC SPACE
-              ].flatten.collect{ |e| [e].pack 'U*' }
-      input.join.clean.should == " \n  \n                     "
-    end
-    describe "with invalid UTF-8 sequence" do
-      before :all do
-        @input = "\210\004"
-        @output = @input.clean
-      end
-      it "should output a valid UTF-8 string" do
-        @output.encoding.name.should == "UTF-8"
-        @output.should be_valid_encoding
-      end
-      it "should replace invisible chars by space" do
-        @output.should == "  "
-      end
-    end
-    describe "with mixed valid and invalid characters" do
-      before :all do
-        @input = "a?^?\xddf"
-        @output = @input.clean
-      end
-      it "should output a valid UTF-8 string" do
-        @output.encoding.name.should == "UTF-8"
-        @output.should be_valid_encoding
-      end
-      it "should keep the valid characters" do
-        @output.should == "a?^?Ýf"
-      end
-    end
-    describe "with already valid characters" do
-      before :all do
-        @input = "\n\t\r\r\n\v\n"
-        @output = @input.clean
-      end
-      it "should output a valid UTF-8 string" do
-        @output.encoding.name.should == "UTF-8"
-        @output.should be_valid_encoding
-      end
-      it "should replace invisible chars by space" do
-        @output.should == "\n \n\n \n"
-      end
-    end
-    describe "with watermarked text" do
-      before :all do
-        @input = "Here is \357\273\277a block \357\273\277of text \357\273\277inside of which a number will be hidden!"
-        @output = @input.clean
-      end
-      it "should output a valid UTF-8 string" do
-        @output.encoding.name.should == "UTF-8"
-        @output.should be_valid_encoding
-      end
-      it "should replace invisible chars by space" do
-        @output.should == "Here is  a block  of text  inside of which a number will be hidden!"
-      end
-    end
-    describe "with unusual valid spaces" do
-      before :all do
-        @input = []
-        @input << "\u0020" # SPACE
-        @input << "\u00A0" # NO-BREAK SPACE
-        @input << "\u2000" # EN QUAD
-        @input << "\u2001" # EM QUAD
-        @input << "\u2002" # EN SPACE
-        @input << "\u2003" # EM SPACE
-        @input << "\u2004" # THREE-PER-EM SPACE
-        @input << "\u2005" # FOUR-PER-EM SPACE
-        @input << "\u2006" # SIX-PER-EM SPACE
-        @input << "\u2007" # FIGURE SPACE
-        @input << "\u2008" # PUNCTUATION SPACE
-        @input << "\u2009" # THIN SPACE
-        @input << "\u200A" # HAIR SPACE
-        @input << "\u200B" # ZERO WIDTH SPACE
-        @input << "\u202F" # NARROW NO-BREAK SPACE
-        @input << "\u205F" # MEDIUM MATHEMATICAL SPACE
-        @input << "\u3000" # IDEOGRAPHIC SPACE
-        @input << "\uFEFF" # ZERO WIDTH NO-BREAK SPACE
+        expect(@output).to eq "          \n  \n                   !\"\#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ €                                ¡¢£€¥¦§¨©ª«¬ ®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ"
+      end
+    end
+    describe "with various type of spaces" do
+      before do
+        @input = [
+          (0x0009..0x000D).to_a, # <control-0009>..<control-000D>
+          0x0020,                # SPACE
+          0x0085,                # <control-0085>
+          0x00A0,                # NO-BREAK SPACE
+          0x1680,                # OGHAM SPACE MARK
+          0x180E,                # MONGOLIAN VOWEL SEPARATOR
+          (0x2000..0x200A).to_a, # EN QUAD..HAIR SPACE
+          0x2028,                # LINE SEPARATOR
+          0x2029,                # PARAGRAPH SEPARATOR
+          0x202F,                # NARROW NO-BREAK SPACE
+          0x205F,                # MEDIUM MATHEMATICAL SPACE
+          0x3000,                # IDEOGRAPHIC SPACE
+        ].flatten.collect{ |e| [e].pack 'U*' }
         @output = @input.join.clean
       end
-      it "should output a valid UTF-8 string" do
-        @output.encoding.name.should == "UTF-8"
-        @output.should be_valid_encoding
-      end
-      it "should replace invisible chars by space" do
-        @output.should == " "*@input.size
-      end
-    end
-    describe "with euro sign from both ISO 8859-15 or Windows-1252" do
-      before :all do
-        @input = "\x80\xA4"
-        @output = @input.clean
-      end
-      it "should output a valid UTF-8 string" do
-        @output.encoding.name.should == "UTF-8"
-        @output.should be_valid_encoding
-      end
-      it "should replace invisible chars by space" do
-        @output.should == "€€"
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
+      end
+      it "should replace all spaces to normal spaces" do
+        expect(@output.clean).to eq " \n  \n                     "
+      end
+    end
+    describe "with various no-width characters" do
+      before do
+        @input = [
+          0x200B,                # ZERO WIDTH SPACE
+          0x200C,                # ZERO WIDTH NON-JOINER
+          0x200D,                # ZERO WIDTH JOINER
+          0x2060,                # WORD JOINER
+          0xFEFF,                # ZERO WIDTH NO-BREAK SPACE
+        ].flatten.collect{ |e| [e].pack 'U*' }
+        @output = @input.join.clean
       end
-    end
-  else
-    # specs for Ruby 1.8.6
-    describe "with all 8-bit characters" do
-      before :all do
-        @input = ""
-        (0..255).each{|i| @input << i.chr}
-        @output = @input.clean
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
       end
-      it "should wipe out the control characters" do
-        @output.should == "          \n  \n                   !\"\#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ €                                ¡¢£€¥Š§š©ª«¬ ®¯°±²³Žµ¶·ž¹º»ŒœŸ¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ"
+      it "should remove no-width characters" do
+        expect(@output).to eq ""
       end
     end
     describe "with invalid UTF-8 sequence" do
@@ -149,8 +74,14 @@ describe String::Cleaner do
         @input = "\210\004"
         @output = @input.clean
       end
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
+      end
       it "should replace invisible chars by space" do
-        @output.should == "  "
+        expect(@output).to eq "  "
       end
     end
     describe "with mixed valid and invalid characters" do
@@ -158,8 +89,14 @@ describe String::Cleaner do
         @input = "a?^?\xddf"
         @output = @input.clean
       end
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
+      end
       it "should keep the valid characters" do
-        @output.should == "a?^?Ýf"
+        expect(@output).to eq "a?^?Ýf"
       end
     end
     describe "with already valid characters" do
@@ -167,8 +104,14 @@ describe String::Cleaner do
         @input = "\n\t\r\r\n\v\n"
         @output = @input.clean
       end
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
+      end
       it "should replace invisible chars by space" do
-        @output.should == "\n \n\n \n"
+        expect(@output).to eq "\n \n\n \n"
       end
     end
     describe "with watermarked text" do
@@ -176,36 +119,14 @@ describe String::Cleaner do
         @input = "Here is \357\273\277a block \357\273\277of text \357\273\277inside of which a number will be hidden!"
         @output = @input.clean
       end
-      it "should replace invisible chars by space" do
-        @output.should == "Here is  a block  of text  inside of which a number will be hidden!"
-      end
-    end
-    describe "with unusual valid spaces" do
-      before :all do
-        @input = []
-        # "\uXXXX" doesn't exists yet on Ruby 1.8.6
-        @input << " "            # SPACE
-        @input << "\xC2\xA0"     # NO-BREAK SPACE
-        @input << "\xE2\x80\x80" # EN QUAD
-        @input << "\xE2\x80\x81" # EM QUAD
-        @input << "\xE2\x80\x82" # EN SPACE
-        @input << "\xE2\x80\x83" # EM SPACE
-        @input << "\xE2\x80\x84" # THREE-PER-EM SPACE
-        @input << "\xE2\x80\x85" # FOUR-PER-EM SPACE
-        @input << "\xE2\x80\x86" # SIX-PER-EM SPACE
-        @input << "\xE2\x80\x87" # FIGURE SPACE
-        @input << "\xE2\x80\x88" # PUNCTUATION SPACE
-        @input << "\xE2\x80\x89" # THIN SPACE
-        @input << "\xE2\x80\x8A" # HAIR SPACE
-        @input << "\xE2\x80\x8B" # ZERO WIDTH SPACE
-        @input << "\xE2\x80\xAF" # NARROW NO-BREAK SPACE
-        @input << "\xE2\x81\x9F" # MEDIUM MATHEMATICAL SPACE
-        @input << "\xE3\x80\x80" # IDEOGRAPHIC SPACE
-        @input << "\xEF\xBB\xBF" # ZERO WIDTH NO-BREAK SPACE
-        @output = @input.join.clean
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
       end
       it "should replace invisible chars by space" do
-        @output.should == " "*@input.size
+        expect(@output).to eq "Here is a block of text inside of which a number will be hidden!"
       end
     end
     describe "with euro sign from both ISO 8859-15 or Windows-1252" do
@@ -213,59 +134,65 @@ describe String::Cleaner do
         @input = "\x80\xA4"
         @output = @input.clean
       end
+      if RUBY_VERSION.to_f>1.9
+        it "should output a valid UTF-8 string" do
+          expect(@output.encoding.name).to eq "UTF-8"
+          expect(@output).to be_valid_encoding
+        end
+      end
       it "should replace invisible chars by space" do
-        @output.should == "€€"
+        expect(@output).to eq "€€"
       end
     end
   end
   describe "#trim(chars = \"\")" do
     it "should use #strip when used without params" do
-      string, expected = "", mock
-      string.stub(:strip).and_return expected
-      string.trim.should be expected
+      string, expected = "", double
+      expect(string).to receive(:strip).and_return expected
+      expect(string.trim).to be expected
     end
     it "should remove multiple characters at once from beginning and end" do
       prefix, suffix = " rhuif dww f f", "dqz  qafdédsj iowe fcms. qpo asttt t dtt"
       to_remove = "acdeéfhijmopqrstuwz "
-      "#{prefix}d#{suffix}".trim(to_remove).should eql "."
-      "#{prefix}D#{suffix}".trim(to_remove).should eql "Ddqz  qafdédsj iowe fcms."
+      expect("#{prefix}d#{suffix}".trim(to_remove)).to eq "."
+      expect("#{prefix}D#{suffix}".trim(to_remove)).to eq "Ddqz  qafdédsj iowe fcms."
     end
   end
   describe "#fix_endlines" do
     it "should convert windows endlines" do
-      "this is a\r\ntest\r\n".fix_endlines.should eql "this is a\ntest\n"
+      expect("this is a\r\ntest\r\n".fix_endlines).to eql "this is a\ntest\n"
     end
     it "should convert old mac endlines" do
-      "this is a\rtest\r".fix_endlines.should eql "this is a\ntest\n"
+      expect("this is a\rtest\r".fix_endlines).to eql "this is a\ntest\n"
     end
     it "should not modify proper linux endlines" do
-      "this is a\ntest\n".fix_endlines.should eql "this is a\ntest\n"
+      expect("this is a\ntest\n".fix_endlines).to eql "this is a\ntest\n"
     end
     it "should convert mixed endlines" do
-      "this is a\n\rtest\r\n".fix_endlines.should eql "this is a\n\ntest\n"
+      expect("this is a\n\rtest\r\n".fix_endlines).to eql "this is a\n\ntest\n"
     end
   end
   describe "#to_permalink(separator=\"-\")" do
     it "should create nice permalink for string with many accents" do
       crazy = "  ÀÁÂÃÄÅÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝàáâãäåçèéêëìíîïñòóôõöøùúûüý - Hello world, I'm a crazy string!! "
-      crazy.to_permalink.should == "aaaaaaceeeeiiiidnoooooxouuuuyaaaaaaceeeeiiiinoooooouuuuy-hello-world-i-m-a-crazy-string"
+      expect(crazy.to_permalink).to eq "aaaaaaceeeeiiiidnoooooxouuuuyaaaaaaceeeeiiiinoooooouuuuy-hello-world-i-m-a-crazy-string"
     end
     it "should create nice permalink even for evil string" do
       evil = (128..255).inject(""){ |acc, b| acc += ("%c" % b) }
-      evil.to_permalink.should == "euros-cents-pounds-euros-yens-section-copyright-registered-trademark-degrees-approx-23-micro-paragraph-10-1-4-1-2-3-4-aaaaaaaeceeeeiiiidnoooooxouuuuythssaaaaaaaeceeeeiiiidnooooo-ouuuuythy"
+      expect(evil.to_permalink).to eq "euros-cents-pounds-euros-yens-section-copyright-registered-trademark-degrees-approx-23-micro-paragraph-10-1-4-1-2-3-4-aaaaaaaeceeeeiiiidnoooooxouuuuythssaaaaaaaeceeeeiiiidnooooo-ouuuuythy"
     end
     it "should remove endlines too" do
-      "this\nis\ta\ntest".to_permalink("_").should eql "this_is_a_test"
+      expect("this\nis\ta\ntest".to_permalink("_")).to eq "this_is_a_test"
     end
   end
   describe "#nl2br" do
     it "should convert \n to <br/>\n" do
-      "this\nis\ta\ntest\r".nl2br.should eql "this<br/>\nis\ta<br/>\ntest\r"
+      expect("this\nis\ta\ntest\r".nl2br).to eq "this<br/>\nis\ta<br/>\ntest\r"
     end
   end
   describe "#to_nicer_sym" do
     it "should convert \"Select or Other\" to :select_or_other" do
-      "Select or Other".to_nicer_sym.should be :select_or_other
+      expect("Select or Other".to_nicer_sym).to be :select_or_other
     end
   end
-end
+end

data/string_cleaner.gemspec

@@ -2,12 +2,12 @@
 
 Gem::Specification.new do |s|
   s.name = %q{string_cleaner}
-  s.version = "0.2.0"
-
-  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.version = "1.0.0"
   s.authors = ["Joseph Halter"]
   s.date = %q{2010-10-18}
   s.email = %q{joseph@openhood.com}
+  s.required_ruby_version = ">= 2.6"
+  s.license = "MIT"
   s.extra_rdoc_files = [
     "LICENSE",
      "README.rdoc"
@@ -22,26 +22,14 @@ Gem::Specification.new do |s|
      "spec/string_cleaner_spec.rb",
      "string_cleaner.gemspec"
   ]
-  s.has_rdoc = true
   s.homepage = %q{http://github.com/JosephHalter/string_cleaner}
-  s.rdoc_options = ["--charset=UTF-8"]
   s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.3.1}
-  s.summary = %q{Fix invalid UTF-8 and wipe invisible chars, fully compatible with Ruby 1.8 & 1.9 with extensive specs}
+  s.summary = %q{Fix invalid UTF-8 and wipe invisible chars, compatible with Ruby 2.6+ with extensive specs}
   s.test_files = [
     "spec/spec_helper.rb",
      "spec/string_cleaner_spec.rb"
   ]
-  s.add_runtime_dependency "unidecoder"
+  s.add_runtime_dependency "talentbox-unidecoder", "2.0.0"
+  s.add_development_dependency "rake"
   s.add_development_dependency "rspec"
-
-  if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
-    s.specification_version = 2
-
-    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
-    else
-    end
-  else
-  end
 end

metadata

@@ -1,59 +1,66 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: string_cleaner
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 2
-  - 0
-  version: 0.2.0
+version: !ruby/object:Gem::Version
+  version: 1.0.0
 platform: ruby
-authors: 
+authors:
 - Joseph Halter
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2010-10-18 00:00:00 +02:00
-default_executable: 
-dependencies: 
-- !ruby/object:Gem::Dependency 
-  name: unidecoder
+date: 2010-10-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: talentbox-unidecoder
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  type: :runtime
   prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
     - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        version: "0"
-  type: :runtime
-  version_requirements: *id001
-- !ruby/object:Gem::Dependency 
-  name: rspec
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
     - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        version: "0"
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :development
-  version_requirements: *id002
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: 
 email: joseph@openhood.com
 executables: []
-
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files:
 - LICENSE
 - README.rdoc
-files: 
-- .gitignore
+files:
+- ".gitignore"
 - LICENSE
 - README.rdoc
 - Rakefile
@@ -61,38 +68,30 @@ files:
 - spec/spec_helper.rb
 - spec/string_cleaner_spec.rb
 - string_cleaner.gemspec
-has_rdoc: true
 homepage: http://github.com/JosephHalter/string_cleaner
-licenses: []
-
+licenses:
+- MIT
+metadata: {}
 post_install_message: 
-rdoc_options: 
-- --charset=UTF-8
-require_paths: 
+rdoc_options: []
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+    - !ruby/object:Gem::Version
+      version: '2.6'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
-rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 3.1.6
 signing_key: 
-specification_version: 2
-summary: Fix invalid UTF-8 and wipe invisible chars, fully compatible with Ruby 1.8 & 1.9 with extensive specs
-test_files: 
+specification_version: 4
+summary: Fix invalid UTF-8 and wipe invisible chars, compatible with Ruby 2.6+ with
+  extensive specs
+test_files:
 - spec/spec_helper.rb
 - spec/string_cleaner_spec.rb