string_master 0.3.19 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: d5a075abc613363e9a4ff6a34fb2e090f904ad2e
-  data.tar.gz: cf180f4ff24e411cb4dc101be650c85de93fa3f1
+SHA256:
+  metadata.gz: db109c39955fd4d1cff51273ffebc3cbc3408e8e1bec70e78f6708c7502edcda
+  data.tar.gz: e76a26c8d32c689e71ee384f855c80a439b127e4e485c352b40725fbde3da9c2
 SHA512:
-  metadata.gz: 5f94f5a00b02b0a9f2e5652816f69406ab1fc61c27f8ffc769299cc12827e6a30993f2c5fb9b88d3b991c8e4df9ef1c08b0c0ca788b51edbcde0f1763a56f4fe
-  data.tar.gz: ca02e659e224132ba171ac05fee58d0f4f97276e5236c03c1abf0062ee1a05dd33d9fce2567471724173e8af6fce210682c1e19227ec81f3f47c45e196b876ad
+  metadata.gz: 3190989568bd6d9488480127b16b37c4aff378a4e418e88674e7e0a743d3cc37738f809f90b12382b364a58d7d4da442397543a51752d336341fc4ffee3fec87
+  data.tar.gz: 1a6cb57073486eac0aeb9d38451f2b74f483014cdb22907c6a7ee142419c521746c0273ea45ddfdd4bfade91a2ae1597b0517bb5d701f4195a7113824edfb200

data/Gemfile.lock

@@ -1,15 +1,15 @@
 GIT
   remote: git@github.com:technicalpickles/jeweler.git
-  revision: 20ae6a869ac588d479774cb60df896cd6138a6bb
+  revision: f1a62a72ca08a0f707a83541414ff9d36c875c90
   specs:
-    jeweler (2.3.4)
+    jeweler (2.3.9)
       builder
-      bundler (>= 1.0)
+      bundler
       git (>= 1.2.5)
-      github_api (~> 0.11.0)
+      github_api (~> 0.16.0)
       highline (>= 1.6.15)
       nokogiri (>= 1.5.10)
-      psych (~> 2.2)
+      psych
       rake
       rdoc
       semver2
@@ -17,94 +17,91 @@ GIT
 GEM
   remote: http://rubygems.org/
   specs:
-    actionpack (4.2.3)
-      actionview (= 4.2.3)
-      activesupport (= 4.2.3)
-      rack (~> 1.6)
-      rack-test (~> 0.6.2)
-      rails-dom-testing (~> 1.0, >= 1.0.5)
+    actionpack (5.2.2)
+      actionview (= 5.2.2)
+      activesupport (= 5.2.2)
+      rack (~> 2.0)
+      rack-test (>= 0.6.3)
+      rails-dom-testing (~> 2.0)
       rails-html-sanitizer (~> 1.0, >= 1.0.2)
-    actionview (4.2.3)
-      activesupport (= 4.2.3)
+    actionview (5.2.2)
+      activesupport (= 5.2.2)
       builder (~> 3.1)
-      erubis (~> 2.7.0)
-      rails-dom-testing (~> 1.0, >= 1.0.5)
-      rails-html-sanitizer (~> 1.0, >= 1.0.2)
-    activesupport (4.2.3)
-      i18n (~> 0.7)
-      json (~> 1.7, >= 1.7.7)
+      erubi (~> 1.4)
+      rails-dom-testing (~> 2.0)
+      rails-html-sanitizer (~> 1.0, >= 1.0.3)
+    activesupport (5.2.2)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 0.7, < 2)
       minitest (~> 5.1)
-      thread_safe (~> 0.3, >= 0.3.4)
       tzinfo (~> 1.1)
-    addressable (2.5.0)
-      public_suffix (~> 2.0, >= 2.0.2)
-    builder (3.2.2)
+    addressable (2.4.0)
+    builder (3.2.3)
+    concurrent-ruby (1.1.4)
+    crass (1.0.4)
     descendants_tracker (0.0.4)
       thread_safe (~> 0.3, >= 0.3.1)
-    diff-lcs (1.2.5)
-    erubis (2.7.0)
+    diff-lcs (1.3)
+    erubi (1.8.0)
     faraday (0.9.2)
       multipart-post (>= 1.2, < 3)
-    git (1.3.0)
-    github_api (0.11.3)
-      addressable (~> 2.3)
-      descendants_tracker (~> 0.0.1)
+    git (1.5.0)
+    github_api (0.16.0)
+      addressable (~> 2.4.0)
+      descendants_tracker (~> 0.0.4)
       faraday (~> 0.8, < 0.10)
-      hashie (>= 1.2)
-      multi_json (>= 1.7.5, < 2.0)
-      nokogiri (~> 1.6.0)
-      oauth2
-    hashie (3.5.5)
-    highline (1.7.8)
-    i18n (0.7.0)
-    json (1.8.3)
-    jwt (1.5.6)
-    loofah (2.0.2)
+      hashie (>= 3.4)
+      mime-types (>= 1.16, < 3.0)
+      oauth2 (~> 1.0)
+    hashie (3.6.0)
+    highline (2.0.0)
+    i18n (1.3.0)
+      concurrent-ruby (~> 1.0)
+    jwt (2.1.0)
+    loofah (2.2.3)
+      crass (~> 1.0.2)
       nokogiri (>= 1.5.9)
-    mini_portile (0.6.2)
-    minitest (5.8.0)
-    multi_json (1.12.1)
+    mime-types (2.99.3)
+    mini_portile2 (2.4.0)
+    minitest (5.11.3)
+    multi_json (1.13.1)
     multi_xml (0.6.0)
     multipart-post (2.0.0)
-    nokogiri (1.6.6.2)
-      mini_portile (~> 0.6.0)
-    oauth2 (1.3.1)
-      faraday (>= 0.8, < 0.12)
-      jwt (~> 1.0)
+    nokogiri (1.9.1)
+      mini_portile2 (~> 2.4.0)
+    oauth2 (1.4.1)
+      faraday (>= 0.8, < 0.16.0)
+      jwt (>= 1.0, < 3.0)
       multi_json (~> 1.3)
       multi_xml (~> 0.5)
       rack (>= 1.2, < 3)
-    psych (2.2.4)
-    public_suffix (2.0.5)
-    rack (1.6.4)
-    rack-test (0.6.3)
-      rack (>= 1.0)
-    rails-deprecated_sanitizer (1.0.3)
-      activesupport (>= 4.2.0.alpha)
-    rails-dom-testing (1.0.6)
-      activesupport (>= 4.2.0.beta, < 5.0)
-      nokogiri (~> 1.6.0)
-      rails-deprecated_sanitizer (>= 1.0.1)
-    rails-html-sanitizer (1.0.2)
-      loofah (~> 2.0)
-    rake (12.0.0)
-    rdoc (5.1.0)
-    rspec (3.3.0)
-      rspec-core (~> 3.3.0)
-      rspec-expectations (~> 3.3.0)
-      rspec-mocks (~> 3.3.0)
-    rspec-core (3.3.2)
-      rspec-support (~> 3.3.0)
-    rspec-expectations (3.3.1)
+    psych (3.1.0)
+    rack (2.0.6)
+    rack-test (1.1.0)
+      rack (>= 1.0, < 3)
+    rails-dom-testing (2.0.3)
+      activesupport (>= 4.2.0)
+      nokogiri (>= 1.6)
+    rails-html-sanitizer (1.0.4)
+      loofah (~> 2.2, >= 2.2.2)
+    rake (12.3.2)
+    rdoc (6.1.0)
+    rspec (3.8.0)
+      rspec-core (~> 3.8.0)
+      rspec-expectations (~> 3.8.0)
+      rspec-mocks (~> 3.8.0)
+    rspec-core (3.8.0)
+      rspec-support (~> 3.8.0)
+    rspec-expectations (3.8.2)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.3.0)
-    rspec-mocks (3.3.2)
+      rspec-support (~> 3.8.0)
+    rspec-mocks (3.8.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.3.0)
-    rspec-support (3.3.0)
+      rspec-support (~> 3.8.0)
+    rspec-support (3.8.0)
     semver2 (3.4.2)
-    thread_safe (0.3.5)
-    tzinfo (1.2.2)
+    thread_safe (0.3.6)
+    tzinfo (1.2.5)
       thread_safe (~> 0.1)
 
 PLATFORMS
@@ -117,4 +114,4 @@ DEPENDENCIES
   rspec
 
 BUNDLED WITH
-   1.12.4
+   1.16.1

data/VERSION

@@ -1 +1 @@
-0.3.19
+0.4.0

data/lib/string_master/string_master.rb

@@ -2,7 +2,7 @@ class StringMaster
 
   require "erb"
   require "action_view"
- 
+
   include ERB::Util
   include ActionView::Helpers
 
@@ -23,7 +23,7 @@ class StringMaster
     text.scan(/<([a-zA-Z0-9]+?)(\s[^>]*)?>/).each { |t| open_tags.unshift(t[0]) }
     text.scan(/<\/\s*?([a-zA-Z0-9]+)\s*?>/).each  { |t| open_tags.slice!(open_tags.index(t[0])) unless open_tags.index(t[0]).nil? }
     open_tags.each { |t| text += "</#{t}>" unless %w(img br hr).include?(t.to_s) }
-    
+
     @modified_string = text
     return self
   end
@@ -45,7 +45,7 @@ class StringMaster
     end
     # Convert all unclosed left tag brackets (<) into &lt;
     @modified_string.gsub!(/<+([^>]*)\Z/, '&lt;\1')
-    # Convert all unopened right tag brackets (<) into &lt;
+    # Convert all unopened right tag brackets (>) into &gt;
     @modified_string.gsub!(/\A([^<]*)>+/, '\1&gt;')
     self
   end
@@ -67,16 +67,22 @@ class StringMaster
   def urls_to_links(options = {})
     wrap_with = options[:wrap_with] || ['','']
     html_options = options[:html_options] || ''
-    @modified_string.gsub!(
-      /(\s|^|\A|\n|\t|\r)((http|https):\/\/.*?)([,.])?(\s|$|\n|\Z|\t|\r|<)/,
-      '\1<a href="\2" ' + html_options + '>\2</a>\4\5'
-    )
+
+    # ascii_only option - show URLs with warning about contain non-latin characters
+    if options[:ascii_only]
+      validate_url_contains_ascii(@modified_string, html_options, wrap_with)
+    else
+      @modified_string.gsub!(
+          /(\s|^|\A|\n|\t|\r)((http|https):\/\/.*?)([,.])?(\s|$|\n|\Z|\t|\r|<)/,
+          '\1<a href="\2" ' + html_options + '>\2</a>\4\5'
+      )
+    end
     self
   end
 
   # Breaks words that are longer than 'length'
   def break_long_words(length=75, break_char=" ", &block)
-    @modified_string.gsub!(/<a [^>]+>|<img [^>]+>|([^\s^\n^\^^\A^\t^\r<]{#{length},}?)|<\/a>/) do |s|
+    @modified_string.gsub!(/https?:\/\/\S+|<a [^>]+>|<img [^>]+>|([^\s^\n^\^^\A^\t^\r<]{#{length},}?)|<\/a>/) do |s|
       if $1
         ns = block_given? ? yield($1) : $1
         last_pos, result_string = 0, ''
@@ -118,7 +124,7 @@ class StringMaster
       if line =~ regexp
         unless code_tag == :opened
           result.chomp! if options[:remove_newlines]
-          result += "<#{tag}>" 
+          result += "<#{tag}>"
           code_tag = :opened
         end
         result += line.sub(regexp, '')
@@ -134,11 +140,11 @@ class StringMaster
         result += line
       end
     end
-    
+
     # Make sure there's always a closing tag
     if code_tag == :opened
       result.chomp!
-      result += "</#{tag}>\n" 
+      result += "</#{tag}>\n"
     end
 
     @modified_string = result
@@ -147,9 +153,9 @@ class StringMaster
 
   # Finds all lines that start with 4 spaces and wraps them into <code> tags.
   # It also transforms each occurence of 2 or more spaces into an &nbsp; entity,
-  # which is available as a standalone method #preserve_whitespace 
+  # which is available as a standalone method #preserve_whitespace
   def wrap_code
-    wrap_lines("code", /\A\s{4}/, remove_newlines: true) 
+    wrap_lines("code", /\A\s{4}/, remove_newlines: true)
     preserve_whitespace_within("code") # already returns `self`
   end
 
@@ -166,7 +172,7 @@ class StringMaster
     @modified_string.gsub!(/`(.+?)`/m, opening_tag + '\1' + closing_tag)
     self
   end
-  
+
   # Same as wrap_inline_code, but spans across multiplelines
   def wrap_backticks_code(opening_tag="<code>", closing_tag="</code>")
     @modified_string.gsub!(/`(.+?)`/m, opening_tag + '\1' + closing_tag)
@@ -177,5 +183,18 @@ class StringMaster
     modified_string.html_safe
   end
 
-end
+  private
 
+  # Checking references for the presence of non-latin characters. If such
+  # characters are found, the link will not be displayed like html link.
+  # Instead of it, will be returned a warning message.
+  def validate_url_contains_ascii(string, html_options, wrap_with)
+    string.gsub!(/((http|https)[^<\s,]{7,}\b)/im) do |link|
+      if link.ascii_only?
+        "<a href='#{link}'#{html_options}>#{link}</a>"
+      else
+        "[WARNING, URL CONTAINS NON-LATIN LETTERS: #{link}]"
+      end
+    end
+  end
+end

data/spec/lib/string_master/string_master_spec.rb

@@ -1,7 +1,7 @@
 require "spec_helper"
 
 describe StringMaster do
-  
+
   it "closes unclosed tags" do
     parser = StringMaster.new("<b>Hello,<i>world</b>")
     parser.close_tags.string.should == '<b>Hello,<i>world</b></i>'
@@ -50,33 +50,121 @@ describe StringMaster do
 
   it "makes images of urls that end with .jpg and other image extensions" do
     parser = StringMaster.new('Hello, this is my photo http://image.com/image.jpg, yeah baby')
-    parser.urls_to_images(:wrap_with => ['<p>', '</p>'], :html_options => 'class="ico"').string.should == 
+    parser.urls_to_images(:wrap_with => ['<p>', '</p>'], :html_options => 'class="ico"').string.should ==
       'Hello, this is my photo<p><img src="http://image.com/image.jpg" alt="" class="ico"/> </p>yeah baby'
 
     # use https
     parser = StringMaster.new('Hello, this is my photo https://image.com/image.jpg, yeah baby')
-    parser.urls_to_images(:wrap_with => ['<p>', '</p>'], :html_options => 'class="ico"').string.should == 
+    parser.urls_to_images(:wrap_with => ['<p>', '</p>'], :html_options => 'class="ico"').string.should ==
       'Hello, this is my photo<p><img src="https://image.com/image.jpg" alt="" class="ico"/> </p>yeah baby'
   end
 
-  it "makes links of urls" do
-    # example 1
-    parser = StringMaster.new('Hello, this is my homepage http://url.com, yeah baby')
-    parser.urls_to_links.string.should ==
-      'Hello, this is my homepage <a href="http://url.com" >http://url.com</a>, yeah baby'
-    
-    # example 2
-    parser = StringMaster.new("http://localhost:3000/\nhttp://localhost:3000/")
-    parser.urls_to_links.string.should ==
-      "<a href=\"http://localhost:3000/\" >http://localhost:3000/</a>\n<a href=\"http://localhost:3000/\" >http://localhost:3000/</a>"
+  describe 'makes links of urls' do
+    # ascii_only option - show URLs with warning about contain non-latin characters
+    describe 'without ascii_only validate' do
+      # example 1
+      it 'when text include url' do
+        parser = StringMaster.new('Hello, this is my homepage http://url.com, yeah baby')
+        parser.urls_to_links(ascii_only: false).string.should ==
+          'Hello, this is my homepage <a href="http://url.com" >http://url.com</a>, yeah baby'
+      end
+
+      # example 2
+      it 'when text have several urls' do
+        parser = StringMaster.new("http://localhost:3000/\nhttp://localhost:3000/")
+        parser.urls_to_links(ascii_only: false).string.should ==
+          "<a href=\"http://localhost:3000/\" >http://localhost:3000/</a>\n<a href=\"http://localhost:3000/\" >http://localhost:3000/</a>"
+      end
+
+      # example 3
+      it 'when text have html tag and url' do
+        parser = StringMaster.new('http://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png<br>')
+        parser.urls_to_links(ascii_only: false).string.should == '<a href="http://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png" >http://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png</a><br>'
+      end
+
+      # example 4, with https
+      it 'when text include https and url' do
+        parser = StringMaster.new('https://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png<br>')
+        parser.urls_to_links(ascii_only: false).string.should == '<a href="https://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png" >https://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png</a><br>'
+      end
+
+      describe 'when url contain non-latin characters and' do
+
+        it "warning message doesn't shows" do
+          parser = StringMaster.new('http://url.cоm')
+          parser.urls_to_links(ascii_only: false).string.should_not ==
+            '[WARNING, URL CONTAINS NON-LATIN LETTERS: http://url.cоm]'
+        end
+
+        it "non-latin url shows like a url with latin only characters" do
+          parser = StringMaster.new('http://url.cоm')
+          parser.urls_to_links(ascii_only: false).string.should ==
+            '<a href="http://url.cоm" >http://url.cоm</a>'
+        end
+      end
+    end
+
+    describe 'with ascii_only validate' do
+      # example 1
+      it 'show warning when text include non-latin url' do
+        parser = StringMaster.new('Hello, this is my homepage http://url.cоm, yeah baby')
+        parser.urls_to_links(ascii_only: true).string.should ==
+          'Hello, this is my homepage [WARNING, URL CONTAINS NON-LATIN LETTERS: http://url.cоm], yeah baby'
+      end
+
+      # example 2
+      it 'show warning when text have several non-latin urls' do
+        parser = StringMaster.new("http://lоcalhost:3000\nhttp://lоcalhost:3000")
+        parser.urls_to_links(ascii_only: true).string.should ==
+          "[WARNING, URL CONTAINS NON-LATIN LETTERS: http://lоcalhost:3000]\n[WARNING, URL CONTAINS NON-LATIN LETTERS: http://lоcalhost:3000]"
+      end
 
-    # example 3
-    parser = StringMaster.new('http://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png<br>')
-    parser.urls_to_links.string.should == '<a href="http://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png" >http://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png</a><br>'
+      # example 3
+      it 'show warning when text have html tag and non-latin url' do
+        parser = StringMaster.new('http://gyаzo.com/a4c16e7a6009f40f29248ad4fed41bd3.png<br>')
+        parser.urls_to_links(ascii_only: true).string.should == '[WARNING, URL CONTAINS NON-LATIN LETTERS: http://gyаzo.com/a4c16e7a6009f40f29248ad4fed41bd3.png]<br>'
+      end
 
-    # example 4, with https
-    parser = StringMaster.new('https://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png<br>')
-    parser.urls_to_links.string.should == '<a href="https://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png" >https://gyazo.com/a4c16e7a6009f40f29248ad4fed41bd3.png</a><br>'
+      # example 4, with https
+      it 'show warning when text include https and non-latin url' do
+        parser = StringMaster.new('https://gyаzo.com/a4c16e7a6009f40f29248ad4fed41bd3.png<br>')
+        parser.urls_to_links(ascii_only: true).string.should == '[WARNING, URL CONTAINS NON-LATIN LETTERS: https://gyаzo.com/a4c16e7a6009f40f29248ad4fed41bd3.png]<br>'
+      end
+
+      describe 'when url contain latin characters and' do
+        it "warning message doesn't shows" do
+          parser = StringMaster.new('http://url.com')
+          parser.urls_to_links(ascii_only: true).string.should_not ==
+            '[WARNING, URL CONTAINS NON-LATIN LETTERS: http://url.cоm]'
+        end
+
+        it "latin url shows correct" do
+          parser = StringMaster.new('http://url.com')
+          parser.urls_to_links(ascii_only: true).string.should ==
+            "<a href='http://url.com'>http://url.com</a>"
+        end
+      end
+
+      describe 'when text contain' do
+        it 'non-latin symbols and latin url' do
+          parser = StringMaster.new('тест http://url.com')
+          parser.urls_to_links(ascii_only: true).string.should ==
+            "тест <a href='http://url.com'>http://url.com</a>"
+        end
+
+        it 'both symbol types and non-latin url' do
+          parser = StringMaster.new('тест non-latin url http://url.cоm')
+          parser.urls_to_links(ascii_only: true).string.should ==
+            "тест non-latin url [WARNING, URL CONTAINS NON-LATIN LETTERS: http://url.cоm]"
+        end
+
+        it 'both symbol types both url types' do
+          parser = StringMaster.new('тест non-latin url http://url.cоm и тест only-latin url https://url.com')
+          parser.urls_to_links(ascii_only: true).string.should ==
+            "тест non-latin url [WARNING, URL CONTAINS NON-LATIN LETTERS: http://url.cоm] и тест only-latin url <a href='https://url.com'>https://url.com</a>"
+        end
+      end
+    end
   end
 
   it "wraps code in <code> tags" do
@@ -143,6 +231,18 @@ WRAPPED_CODE
     parser.break_long_words(5).string.should == '<img src="image.gif" alt="looooooooooooongalt"/>'
   end
 
+  it "handles http links when attempt to break long words" do
+    string_with_long_link = 'some text http://verylonglink.com other text'
+    parser = StringMaster.new(string_with_long_link)
+    parser.break_long_words(6).string.should == string_with_long_link
+  end
+
+  it "handles http links when attempt to break long words" do
+    string_with_long_link = 'some text https://verylonglink.com other text'
+    parser = StringMaster.new(string_with_long_link)
+    parser.break_long_words(6).string.should == string_with_long_link
+  end
+
   it "cuts too long string and appends (if specified) characters to its end" do
     parser = StringMaster.new("This is quite a long text")
     parser.cut(11, 7, :append => '...').string.should == "This is..."

data/spec/spec_helper.rb

@@ -5,4 +5,5 @@ Dir[File.dirname(__FILE__) + "/../lib/string_master/*.rb"].each {|f| require f }
 
 RSpec.configure do |config|
   config.expect_with(:rspec) { |c| c.syntax = :should }
+  config.default_formatter = "doc"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: string_master
 version: !ruby/object:Gem::Version
-  version: 0.3.19
+  version: 0.4.0
 platform: ruby
 authors:
 - Roman Snitko
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-04-20 00:00:00.000000000 Z
+date: 2018-12-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: actionpack
@@ -113,7 +113,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: Most common string manipulations for a webapp