url_extractor 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 12e9a39d947f5860ec829d6f3a0c2a2c8829b0b3
+  data.tar.gz: a37afb38367c298689aa194d0945f8c0f82e1318
+SHA512:
+  metadata.gz: cc38c7af36334af7f4a23b5f63c0af6bf6f658c070f21a35b370d0c5e5a25942861344c61a74fe85dd02d6cbd78636ff45e9ce488752509ea56d38782243f08f
+  data.tar.gz: f8abdf7eae0aa71e35880af91db019970faf3081a3f8363c70a835b9996fb34cef95cfdaef4d0c71852f0c2c0d2e58f3ce3352f90dff8d0abe55aecfe7d6bb0a

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rvmrc

@@ -0,0 +1 @@
+rvm use 2.1.0@url_extractor --create

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in url_extractor.gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Michael Guterl
+
+MIT License
+
+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 @@
+# UrlExtractor
+
+A tool for extracting and replacing URLs from inside a block of text or HTML.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'url_extractor'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install url_extractor
+
+## 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 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/lib/url_extractor.rb

@@ -0,0 +1,6 @@
+module UrlExtractor
+  autoload :VERSION, 'url_extractor/version'
+  autoload :Util, 'url_extractor/util'
+  autoload :PlainText, 'url_extractor/plain_text'
+  autoload :HTML, 'url_extractor/html'
+end

data/lib/url_extractor/html.rb

@@ -0,0 +1,33 @@
+require 'nokogiri'
+
+module UrlExtractor
+  class HTML
+
+    InvalidURL = Class.new(StandardError)
+
+    def initialize(ignore_patterns = [])
+      @ignore_patterns = ignore_patterns
+    end
+
+    def replace_urls(template)
+      document = Nokogiri::HTML(template)
+
+      document.search("a").each do |link|
+        url = link['href']
+        raise InvalidURL, "cannot be blank" if UrlExtractor::Util.blank_string?(url)
+        next if ignored_url?(url)
+
+        link['href'] = yield(url)
+      end
+
+      document.to_s
+    end
+
+    private
+
+    def ignored_url?(url)
+      url !~ /https?:\/\// || @ignore_patterns.any? { |pattern| url =~ pattern }
+    end
+
+  end
+end

data/lib/url_extractor/plain_text.rb

@@ -0,0 +1,29 @@
+require 'uri'
+
+module UrlExtractor
+  class PlainText
+
+    def initialize(ignore_patterns = [])
+      @ignore_patterns = ignore_patterns
+    end
+
+    def replace_urls(text)
+      urls = URI.extract text
+
+      urls.each do |url|
+        next if ignogred_url?(url)
+
+        text = text.gsub url, yield(url)
+      end
+
+      text
+    end
+
+    private
+
+    def ignogred_url?(url)
+      url !~ /https?:\/\// || @ignore_patterns.any? { |pattern| url =~ pattern }
+    end
+
+  end
+end

data/lib/url_extractor/util.rb

@@ -0,0 +1,13 @@
+module UrlExtractor
+  module Util
+
+    extend self
+
+    NON_WHITESPACE_REGEXP = %r![^\s#{[0x3000].pack("U")}]!
+
+    def blank_string?(string)
+      string !~ NON_WHITESPACE_REGEXP
+    end
+
+  end
+end

data/lib/url_extractor/version.rb

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

data/spec/url_extractor/html_spec.rb

@@ -0,0 +1,41 @@
+require 'url_extractor'
+
+describe UrlExtractor::HTML do
+  def html_wrapped_string(string)
+    "<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML 4.0 Transitional//EN\" \"http://www.w3.org/TR/REC-html40/loose.dtd\">\n<html><body>#{string}\n</body></html>\n"
+  end
+
+  it 'returns a string with the modified URLs that were returned in the block' do
+    extractor = UrlExtractor::HTML.new
+    text = html_wrapped_string('foo bar <a href="http://google.com">Google</a>')
+
+    actual = extractor.replace_urls(text) do |extracted|
+      'http://foo.bar'
+    end
+
+    actual.should == html_wrapped_string("foo bar <a href=\"http://foo.bar\">Google</a>")
+  end
+
+  it 'ignores urls that match patterns provided' do
+    extractor = UrlExtractor::HTML.new([/google/])
+    text = html_wrapped_string('foo bar <a href="http://google.com">Stuff</a> <a href="http://bar.baz">Google</a>')
+
+    actual = extractor.replace_urls(text) do |extracted|
+      'http://foo.bar'
+    end
+
+    actual.should == html_wrapped_string("foo bar <a href=\"http://google.com\">Stuff</a> <a href=\"http://foo.bar\">Google</a>")
+  end
+
+  it "ignores URLs that don't match http or https" do
+    extractor = UrlExtractor::HTML.new
+    text = html_wrapped_string("foo bar <a href=\"Reminder:foobar\">Hi</a>")
+
+    actual = extractor.replace_urls(text) do |extracted|
+      'http://foo.bar'
+    end
+
+    actual.should == text
+  end
+
+end

data/spec/url_extractor/plain_text_spec.rb

@@ -0,0 +1,38 @@
+require 'url_extractor'
+
+describe UrlExtractor::PlainText do
+
+  it 'returns a string with the modified URLs that were returned in the block' do
+    extractor = UrlExtractor::PlainText.new
+    text = 'foo bar http://google.com'
+
+    actual = extractor.replace_urls(text) do |extracted|
+      'http://foo.bar'
+    end
+
+    actual.should == 'foo bar http://foo.bar'
+  end
+
+  it 'ignores urls that match patterns provided' do
+    extractor = UrlExtractor::PlainText.new([/google/])
+    text = 'http://google.com http://foobar.com'
+
+    actual = extractor.replace_urls(text) do |extracted|
+      'http://foo.bar'
+    end
+
+    actual.should == 'http://google.com http://foo.bar'
+  end
+
+  it "ignores URLs that don't match http or https" do
+    extractor = UrlExtractor::PlainText.new
+    text = "Reminder: Blah"
+
+    actual = extractor.replace_urls(text) do |extracted|
+      'http://foo.bar'
+    end
+
+    actual.should == 'Reminder: Blah'
+  end
+
+end

data/url_extractor.gemspec

@@ -0,0 +1,20 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/url_extractor/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Michael Guterl"]
+  gem.email         = ["michael@diminishing.org"]
+  gem.description   = %q{A tool for extracting and replacing URLs from inside a block of text or HTML.}
+  gem.summary       = %q{A tool for extracting and replacing URLs from inside a block of text or HTML.}
+  gem.homepage      = ""
+
+  gem.files         = `git ls-files`.split($\)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "url_extractor"
+  gem.require_paths = ["lib"]
+  gem.version       = UrlExtractor::VERSION
+
+  gem.add_development_dependency 'rspec'
+  gem.add_dependency 'nokogiri'
+end

metadata

@@ -0,0 +1,88 @@
+--- !ruby/object:Gem::Specification
+name: url_extractor
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Michael Guterl
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-04-21 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  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: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A tool for extracting and replacing URLs from inside a block of text
+  or HTML.
+email:
+- michael@diminishing.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rvmrc"
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- lib/url_extractor.rb
+- lib/url_extractor/html.rb
+- lib/url_extractor/plain_text.rb
+- lib/url_extractor/util.rb
+- lib/url_extractor/version.rb
+- spec/url_extractor/html_spec.rb
+- spec/url_extractor/plain_text_spec.rb
+- url_extractor.gemspec
+homepage: ''
+licenses: []
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: A tool for extracting and replacing URLs from inside a block of text or HTML.
+test_files:
+- spec/url_extractor/html_spec.rb
+- spec/url_extractor/plain_text_spec.rb