truncator 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: f2291c4c5706173cac9a8d622c702e15fa3d0b17
+  data.tar.gz: 193f48279bd97d6a4c298417c796ff42f7c78e95
+SHA512:
+  metadata.gz: 9e58e7ce29d2996fc93868c89d94d86351827a8b9a396724bb21514dd844d91b4e1bd8613cb1e996adc23f72c079d80b4cc5d6579857d57e8ff98ae06fb3b38a
+  data.tar.gz: e403967ea6e475503f3050939ae5e9b0e780f941e4c3c0d15fa1b34c12e422a638e18a0e539b43df70c364bf9d1f56029079eef883e5970eabfa57adf0e3c10e

data/.gitignore

@@ -0,0 +1,20 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.rspec
+.ruby-version
+Gemfile.lock

data/Gemfile

@@ -0,0 +1,8 @@
+source 'https://rubygems.org'
+
+gemspec
+
+ruby '2.0.0'
+
+gem 'rspec', '~> 2.13'
+gem 'byebug'

data/LICENSE.txt

@@ -0,0 +1,20 @@
+The MIT License (MIT)
+
+Copyright (c) 2013 freemanoid
+
+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/README.md

@@ -0,0 +1,29 @@
+# Truncator [![Code Climate](https://codeclimate.com/github/freemanoid/truncator.png)](https://codeclimate.com/github/freemanoid/truncator)
+
+Truncate you urls as much as possible
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'truncator'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install truncator
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,4 @@
+require "bundler/gem_tasks"
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new

data/lib/truncator.rb

@@ -0,0 +1,2 @@
+require 'truncator/version'
+require 'truncator/url_parser'

data/lib/truncator/url_parser.rb

@@ -0,0 +1,155 @@
+class UrlParser
+  class << self
+    URL_VALID_SYMBOLS = %Q{[#{Regexp.escape('!#$&-;=?-[]_~')}a-zA-Z0-9]}
+    SEPARATOR = '...'
+
+    def shorten_url(url, truncation_length = 42)
+      url = url.dup
+      unless ordinary_hostname?(url)
+        if url[-1] != '/'
+          # truncate all parameter except the first
+          url[url.index('&')..-1] = '...'
+        end
+        return url
+      end
+
+      url.sub!(/\Ahttp:\/\//, '') # remove http protocol
+      url.gsub(/\/{2,}/, '/') # replace multiple slashes by one
+      url.chomp!('/') # remove slash from the end
+      return url if valid_length?(url.length, truncation_length)
+
+      if !has_path?(url)
+        url = truncate(url, truncation_length)
+        return url
+      end
+
+      if params_exists?(url)
+        if invalid_length?(hostname(url).length, truncation_length) and last_directory(url).length > truncation_length
+          url = truncate_last_directory(url, truncation_length)
+        elsif valid_length?(url.length - last_directory(url).length, truncation_length) or !has_dirs?(url)
+          url = truncate(url, truncation_length)
+        end
+      else
+        if valid_length?(hostname(url).length, truncation_length)
+          url = truncate_by_shortest(url, truncation_length)
+        else
+          url = truncate_all_directories(url)
+          url = truncate_last_directory(url, truncation_length)
+        end
+      end
+
+      url
+    end
+
+    private
+      ## FIXME: add to String#truncate
+      def truncate(str, length)
+        str = str.dup
+        if str.length > length
+          str[(length - SEPARATOR.length)..-1] = SEPARATOR
+        end
+        str
+      end
+
+      def ordinary_hostname?(url)
+        if url.start_with?('https://')
+          # https
+          false
+        elsif url =~ /^http[s]?:\/\/[a-zA-Z\d.]+:\d{1,5}\//
+          # has port
+          false
+        elsif url.start_with?('ftp://')
+          # ftp
+          false
+        elsif url =~ /^http:\/\/[a-zA-Z\d]+:[a-zA-Z\d]+@[a-zA-Z\d.]+\//
+          # with credentials
+          false
+        else
+          true
+        end
+      end
+
+      def hostname(url)
+        url[0..(url.index('/') - 1)]
+      end
+
+      def valid_length?(url_length, truncation_length)
+        url_length <= truncation_length
+      end
+
+      def invalid_length?(url_length, truncation_length)
+        !valid_length?(url_length, truncation_length)
+      end
+
+      # Check if url has query parameters
+      def params_exists?(url)
+        valid_symbols_before_params = URL_VALID_SYMBOLS.dup.tap { |r| r[-1] = '.\/]' }
+        !!(url =~ /^#{valid_symbols_before_params}+\?(#{URL_VALID_SYMBOLS}+)/)
+      end
+
+      def params(url)
+        valid_symbols_before_params = URL_VALID_SYMBOLS.dup.tap { |r| r[-1] = '.\/]' }
+        url.match(/^#{valid_symbols_before_params}+\?(#{URL_VALID_SYMBOLS}+)/)[1]
+      end
+
+      # Get the 'directories' of the link
+      def directories(url)
+        url.to_enum(:scan, /(?<=\/)(#{URL_VALID_SYMBOLS}+)(?=\/)/).map { Regexp.last_match }
+      end
+
+      def truncate_all_directories(url)
+        first_slash = url.index('/')
+        last_slash = url.rindex('/')
+        url = url.dup
+        url[first_slash..last_slash] = "/#{SEPARATOR}/"
+        url
+      end
+
+      def last_directory(url)
+        url[(url.rindex('/') + 1)..-1]
+      end
+
+      def truncate_last_directory(url, truncation_length)
+        last_dir_begin = url.rindex('/') + 1
+        last_dir = last_directory(url)
+        url = url.dup
+        url[last_dir_begin..-1] = truncate(last_dir, truncation_length)
+        url
+      end
+
+      # If url has any 'dirs' this is suburls between '/'
+      def has_dirs?(url)
+        url.count('/') > 1
+      end
+
+      def has_path?(url)
+        url.count('/') > 0
+      end
+
+      def truncate_by_shortest(url, target_length)
+        url = url.dup
+        dirs = directories(url)
+        dirs_sorted = dirs.sort_by { |d| d.to_s.length }
+
+        # Get the shortest dir and try to truncate the url by this dir and nexts
+        dirs_sorted.each do |next_min_dir|
+          current_dirs_length = 0
+          current_dirs_count = 0
+          dirs[dirs.index(next_min_dir)..-1].each do |dir|
+            current_dirs_length += dir.to_s.length
+            current_dirs_count += 1
+            current_dirs_length_with_slashes = current_dirs_length + (current_dirs_count - 1) - SEPARATOR.length
+            break if url.length - current_dirs_length_with_slashes <= target_length
+          end
+          current_dirs_length_with_slashes = current_dirs_length + (current_dirs_count - 1) - SEPARATOR.length
+
+          if url.length - current_dirs_length_with_slashes <= target_length
+            url[next_min_dir.begin(0)..
+              (dirs[dirs.index(next_min_dir) + (current_dirs_count - 1)].end(0) - 1)] = SEPARATOR
+            break
+          end
+        end
+        url
+      end
+  end
+end

data/lib/truncator/version.rb

@@ -0,0 +1,3 @@
+module Truncator
+  VERSION = "0.0.1"
+end

data/spec/spec_helper.rb

@@ -0,0 +1,17 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  # config.order = 'random'
+end

data/spec/url_parser_spec.rb

@@ -0,0 +1,177 @@
+require 'spec_helper'
+require 'truncator'
+
+describe UrlParser do
+
+  describe ".shorten_url" do
+
+    context "when no truncation length is specified, the URL is too long, has sublevels, but no query params" do
+      let(:shortened) { UrlParser.shorten_url "http://www.foo.com/this/is/a/b/c/d/e/f/string.html" }
+
+      it "should default to truncate at 42 characters" do
+        # shortened.should == "www.foo.com/this/is/a/.../e/f/string.html"
+        shortened.length.should <= 42
+      end
+    end
+
+    context 'when URL has a large last folder level' do
+      let(:shortened) { UrlParser.shorten_url "http://m.whitehouse.gov/blog/2013/08/23/check-out-secretary-education-arne-duncans-google-hangout-sal-khan?utm_source=email&utm_medium=email&utm_content=email232-graphic2&utm_campaign=education" }
+
+      it "should should default to truncate at 42 characters" do
+        shortened.should == "m.whitehouse.gov/blog/2013/08/23/check-..."
+      end
+    end
+
+    context "when URL is too long, has sublevels, but no query params" do
+      it "should ellipse the directories and just show the file" do
+        UrlParser.shorten_url("http://www.foo.com/this/is/a/really/long/url/that/has/no/query/string.html", 30).should == "www.foo.com/.../string.html"
+      end
+
+      it "should replace path segments with ellipses to shorten the path as much as necessary" do
+        url_prefix = "http://www.foo.com/this/goes/on/"
+        url_middle = ""
+        url_suffix = "with/XXX.html"
+        0.upto(20) do |n|
+          url = url_prefix + url_middle + url_suffix
+          url_middle += "and/on/"
+          shorter_url = UrlParser.shorten_url(url, 30)
+          #TODO: rewrite this
+          shorter_url.should == if url[7..-1].length <= 30
+                                  url[7..-1]
+                                else
+                                  "www.foo.com/.../with/XXX.html"
+                                end
+        end
+      end
+
+      it "should replace path segments with ellipses to shorten the path as much as necessary (different path pattern)" do
+        url_prefix = "http://www.foo.com/on/"
+        url_middle = ""
+        url_suffix = "X.html"
+        0.upto(20) do |n|
+          url = url_prefix + url_middle + url_suffix
+          url_middle += "nd/on/"
+          shorter_url = UrlParser.shorten_url(url, 30)
+          #TODO: rewrite this
+          shorter_url.should == if url[7..-1].length <= 30
+                                  url[7..-1]
+                                else
+                                  "www.foo.com/.../nd/on/X.html"
+                                end
+        end
+      end
+
+      # it "should replace path segments with ellipses to shorten the path as much as necessary for various lengths", focus: true do
+      #   url = "http://www.foo.com/this/goes/on/and/on/and/on/with/XXX.html"
+      #   UrlParser.shorten_url(url, 24).should == "www.foo.com/.../XXX.html"
+      #   32.upto(33) { |n| UrlParser.shorten_url(url, n).should == "www.foo.com/.../on/with/XXX.html" }
+      #   35.upto(39) { |n| UrlParser.shorten_url(url, n).should == "www.foo.com/this/.../with/XXX.html" }
+      #   40.upto(42) { |n| UrlParser.shorten_url(url, n).should == "www.foo.com/this/goes/.../with/XXX.html" }
+      #   43.upto(45) { |n| UrlParser.shorten_url(url, n).should == "www.foo.com/this/goes/.../on/with/XXX.html" }
+      # end
+    end
+
+    # context "when URL is too long and has at least one sublevel specified as well as a query parameter" do
+    #   let(:shortened) { UrlParser.shorten_url("http://www.foo.com/this/goes/on/and/on/and/on/and/on/and/ends/with/XXXX.html?q=1&a=2&b=3", 50) }
+
+    #   it "should replace path segments with ellipses to shorten the path as much as necessary, and show only the first param, followed by ellipses" do
+    #     shortened.should == "www.foo.com/this/goes/.../with/XXXX.html?q=1..."
+    #   end
+    # end
+
+    context "when URL is more than 30 chars long and does not have at least one sublevel specified" do
+      let(:shortened) { UrlParser.shorten_url("http://www.mass.gov/?pageID=trepressrelease&L=4&L0=Home&L1=Media+%26+Publications&L2=Treasury+Press+Releases&L3=2006&sid=Ctre&b=pressrelease&f=2006_032706&csid=Ctre", 30) }
+
+      it "should truncate to 30 chars with ellipses" do
+        shortened.should == "www.mass.gov/?pageID=trepre..."
+      end
+    end
+
+    context "when the URL contains a really long host name and a long trailing filename" do
+      let(:shortened) { UrlParser.shorten_url("http://www128376218.skjdhfskdjfhs.lqdkwjqlkwjdqlqwkjd.com/some/path/1234567890123456789012345678901234test_of_the_mergency_broadcastingnet_work.html", 30) }
+
+      it "should not truncate the host name and truncated the last part of the path to truncation length and all dirs" do
+        shortened.should == "www128376218.skjdhfskdjfhs.lqdkwjqlkwjdqlqwkjd.com/.../123456789012345678901234567..."
+      end
+    end
+
+    #TODO: this and the next spec can be merged
+    context "when the URL contains a really long host name and is an http url and has an empty path" do
+      let(:shortened) { UrlParser.shorten_url("http://www128376218.skjdhfskdj.lqdkwjqlkwjdqlqwkjd.com/", 30) }
+
+      it "should truncate the host name and have no trailing /" do
+        shortened.should == "www128376218.skjdhfskdj.lqd..."
+      end
+    end
+
+    context "when the URL contains a really long host name and is an http url and has an empty path and no trailing /" do
+      let(:shortened) { UrlParser.shorten_url("http://www128376218.skjdhfskdj.lqdkwjqlkwjdqlqwkjd.com", 30) }
+
+      it "should truncate the URL and have no trailing /" do
+        shortened.should == "www128376218.skjdhfskdj.lqd..."
+      end
+    end
+
+    context "when the URL contains a really long host name and has a really long query parameter" do
+      let(:shortened) { UrlParser.shorten_url("http://www128376218.skjdhfskdjfhs.lqdkwjqlkwjdqlqwkjd.com/?cmd=1234567890123456789012345678901234&api_key=1234567890123456789012345678901234", 30) }
+
+      it "should not truncate the host name but truncate the query parameter" do
+        shortened.should == "www128376218.skjdhfskdjfhs.lqdkwjqlkwjdqlqwkjd.com/?cmd=1234567890123456789012..."
+      end
+    end
+
+    context "when URL is really short and contains only the protocol http and hostname" do
+      let(:shortened) { UrlParser.shorten_url("http://bit.ly/") }
+
+      it "should omit the protocol as well as trailing slash" do
+        shortened.should == "bit.ly"
+      end
+    end
+
+    context "when URL is really short and contains only the protocol http and hostname and a long query parameter" do
+      let(:shortened) { UrlParser.shorten_url("http://api.bit.ly/?cmd=boom&t=now&auth_token=f886c1c02896492577e92b550cd22b3c83b062") }
+
+      it "should omit the protocol as well as trailing slash" do
+        shortened.should == "api.bit.ly/?cmd=boom&t=now&auth_token=f..."
+      end
+    end
+
+    context "when URL is really short and contains only the protocol http and hostname and a short query parameter" do
+      let(:shortened) { UrlParser.shorten_url("http://api.bit.ly/?cmd=boom&t=now") }
+
+      it "should omit the protocol as well as trailing slash" do
+        shortened.should == "api.bit.ly/?cmd=boom&t=now"
+      end
+    end
+
+    context "when the URL starts with something other than http://hostname/" do
+      before do
+        @long_urls = [
+            "https://www.mass.gov/",
+            "http://www.mass.gov:80/",
+            "http://user:secret@www.mass.gov/",
+            "https://www.mass.gov/?pageID=trepressrelease&L=4&L0=Home&L1=Media+%26+Publications&L2=Treasury+Press+Releases&L3=2006&sid=Ctre&b=pressrelease&f=2006_032706&csid=Ctre",
+            "http://www.mass.gov:80/?pageID=trepressrelease&L=4&L0=Home&L1=Media+%26+Publications&L2=Treasury+Press+Releases&L3=2006&sid=Ctre&b=pressrelease&f=2006_032706&csid=Ctre",
+            "http://user:secret@www.mass.gov/?pageID=trepressrelease&L=4&L0=Home&L1=Media+%26+Publications&L2=Treasury+Press+Releases&L3=2006&sid=Ctre&b=pressrelease&f=2006_032706&csid=Ctre",
+            "ftp://www.mass.gov/"
+        ]
+        @short_urls = [
+            "https://www.mass.gov/",
+            "http://www.mass.gov:80/",
+            "http://user:secret@www.mass.gov/",
+            "https://www.mass.gov/?pageID=trepressrelease...",
+            "http://www.mass.gov:80/?pageID=trepressrelease...",
+            "http://user:secret@www.mass.gov/?pageID=trepressrelease...",
+            "ftp://www.mass.gov/"
+        ]
+      end
+
+      it "should truncate to 30 chars with ellipses" do
+        @long_urls.each_with_index do |url, x|
+          UrlParser.shorten_url(url, 30).should == @short_urls[x]
+        end
+      end
+    end
+  end
+
+end

data/truncator.gemspec

@@ -0,0 +1,21 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'truncator/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "truncator"
+  spec.version       = Truncator::VERSION
+  spec.authors       = ["freemanoid"]
+  spec.email         = ["freemanoid321@gmail.com"]
+  spec.description   = %q{url truncator}
+  spec.summary       = %q{Truncate urls as much as possible}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec", "~> 2.13"
+end

metadata

@@ -0,0 +1,97 @@
+--- !ruby/object:Gem::Specification
+name: truncator
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- freemanoid
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-11-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.13'
+description: url truncator
+email:
+- freemanoid321@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/truncator.rb
+- lib/truncator/url_parser.rb
+- lib/truncator/version.rb
+- spec/spec_helper.rb
+- spec/url_parser_spec.rb
+- truncator.gemspec
+homepage: ''
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Truncate urls as much as possible
+test_files: []