url_scrubber 0.7.10 → 0.7.11

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: dc1cea704c5440cf1114fe0ab1a013963bb0184f
+  data.tar.gz: 15e202c908bc49f2dd65aa1ab8bdb482bdc0fa71
+SHA512:
+  metadata.gz: e12356b808e46f5e2bb292105eb69b001b9a7ef42c65908351bfac100fd5bcbc29cffe8740ad75e0e55ea1b2fd0a8981f101333ad3198718ce743a3fb2721f7f
+  data.tar.gz: 4b0961d123a5962dc027e82e11b43ac6135bebf94ac92e6462af1634e4734fb90d63dea6edd146ec09f76903416522d535a2f8f3845500b71b1bc213c0d21e0c

data/lib/url_scrubber.rb

@@ -112,6 +112,18 @@ module UrlScrubber
     end
   end
 
+  # Requirements:
+  # 1.  must have http/https scheme
+  # 2.  no "@" in any of the passed in url string
+  # 3.  valid uri as determined by Addressable::URI
+  def self.valid_url?(url)
+    schemes = %w(http https)
+    parsed = URI.parse(url) or return false
+    schemes.include?(parsed.scheme) && !url.include?("@")
+    rescue URI::InvalidURIError
+    false
+  end
+  
   private
 
   def self.downcase_domain(url)
@@ -238,68 +250,66 @@ module UrlScrubber
     url
   end
   
-  private
-  
-    def self.check_for_redirection(uri_str, limit = 5)
-      login_patterns = [
-        # pages that require user logins
-        %r{^.*/login[^/]*$}
-      ]
-
-      failure_patterns = [
-        # pages that give 200 codes but actually indicate a not found
-        %r{linkedin\.com/home\?report%2Efailure}i
-      ]
-
-      raise 'Too many HTTP redirects' if limit == 0
-      
-      begin
-        url = URI.parse(uri_str)        
-      rescue URI::InvalidURIError => e
-        return [uri_str, CustomError.new(786, "Invalid URI #{uri_str} : #{e.message}") ]
-      end
+  def self.check_for_redirection(uri_str, limit = 5)
+    login_patterns = [
+      # pages that require user logins
+      %r{^.*/login[^/]*$}
+    ]
+
+    failure_patterns = [
+      # pages that give 200 codes but actually indicate a not found
+      %r{linkedin\.com/home\?report%2Efailure}i
+    ]
+
+    raise 'Too many HTTP redirects' if limit == 0
+    
+    begin
+      url = URI.parse(uri_str)        
+    rescue URI::InvalidURIError => e
+      return [uri_str, CustomError.new(786, "Invalid URI #{uri_str} : #{e.message}") ]
+    end
 
-      http = Net::HTTP.new(url.host, url.port)
-      if url.port == 443
-        http.use_ssl = true
-        http.verify_mode = OpenSSL::SSL::VERIFY_NONE
-      else
-        http.use_ssl = false
+    http = Net::HTTP.new(url.host, url.port)
+    if url.port == 443
+      http.use_ssl = true
+      http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+    else
+      http.use_ssl = false
+    end
+    request = Net::HTTP::Get.new(url.request_uri, { 'User-Agent' => USER_AGENT })
+
+    begin
+      response = http.request(request)    
+    rescue Exception => e
+      failure_response = Net::HTTPClientError.new('1.1', '404', 'Not Found')
+      return [uri_str, failure_response]
       end
-      request = Net::HTTP::Get.new(url.request_uri, { 'User-Agent' => USER_AGENT })
 
-      begin
-        response = http.request(request)    
-      rescue Exception => e
-        failure_response = Net::HTTPClientError.new('1.1', '404', 'Not Found')
-        return [uri_str, failure_response]
+    if response.is_a? Net::HTTPRedirection
+      if response['location'][0,4] == "http"
+        if failure_patterns.any? { |pattern| response['location'].match(pattern) }
+          # got redirected to a page indicating failure, so act like it's a 404
+          failure_response = Net::HTTPClientError.new('1.1', '404', 'Not Found')
+          return [uri_str, failure_response]
         end
 
-      if response.is_a? Net::HTTPRedirection
-        if response['location'][0,4] == "http"
-          if failure_patterns.any? { |pattern| response['location'].match(pattern) }
-            # got redirected to a page indicating failure, so act like it's a 404
-            failure_response = Net::HTTPClientError.new('1.1', '404', 'Not Found')
-            return [uri_str, failure_response]
-          end
-
-          redirected_url, base_response = check_for_redirection(response['location'], limit - 1)
-
-          if login_patterns.any? { |pattern| redirected_url.match(pattern) }
-            # got redirected to a login page. return the ultimate response, but the previous url
-            return [uri_str, base_response]
-          else
-            return [redirected_url, base_response]
-          end
+        redirected_url, base_response = check_for_redirection(response['location'], limit - 1)
 
+        if login_patterns.any? { |pattern| redirected_url.match(pattern) }
+          # got redirected to a login page. return the ultimate response, but the previous url
+          return [uri_str, base_response]
         else
-          redir_url = "http://#{url.host}#{response['location']}"
-          redirected_url, base_response = check_for_redirection(redir_url, limit - 1)
           return [redirected_url, base_response]
         end
+
       else
-        return [uri_str, response]
+        redir_url = "http://#{url.host}#{response['location']}"
+        redirected_url, base_response = check_for_redirection(redir_url, limit - 1)
+        return [redirected_url, base_response]
       end
+    else
+      return [uri_str, response]
     end
+  end
   
 end

data/lib/url_scrubber/version.rb

@@ -1,3 +1,3 @@
 module UrlScrubber
-  VERSION = "0.7.10"
+  VERSION = "0.7.11"
 end

data/url_scrubber.gemspec

@@ -2,8 +2,8 @@
 require File.expand_path('../lib/url_scrubber/version', __FILE__)
 
 Gem::Specification.new do |gem|
-  gem.authors       = ["Colin Langton", "Christopher Maujean", "David Hillard"]
-  gem.email         = ["colin@hoteldelta.net", "cmaujean@brandle.net", "dhillard@brandle.net"]
+  gem.authors       = ["Colin Langton", "Christopher Maujean", "David Hillard", "Edgar Abadines"]
+  gem.email         = ["colin@hoteldelta.net", "cmaujean@brandle.net", "dhillard@brandle.net", "ed@brandle.net"]
   gem.description   = %q{Remove extraneous bits from URLs, follow redirects, identify social media urls, etc.}
   gem.summary       = %q{Clean up URLs.}
   gem.homepage      = "http://brandle.net"

metadata

@@ -1,22 +1,21 @@
 --- !ruby/object:Gem::Specification
 name: url_scrubber
 version: !ruby/object:Gem::Version
-  version: 0.7.10
-  prerelease: 
+  version: 0.7.11
 platform: ruby
 authors:
 - Colin Langton
 - Christopher Maujean
 - David Hillard
+- Edgar Abadines
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-09-27 00:00:00.000000000 Z
+date: 2014-02-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -24,7 +23,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -32,7 +30,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: guard-bundler
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -40,7 +37,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -48,7 +44,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: guard-rspec
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -56,7 +51,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -64,7 +58,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: terminal-notifier-guard
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -72,7 +65,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -80,7 +72,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: rb-fsevent
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -88,7 +79,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -99,6 +89,7 @@ email:
 - colin@hoteldelta.net
 - cmaujean@brandle.net
 - dhillard@brandle.net
+- ed@brandle.net
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -116,27 +107,26 @@ files:
 - url_scrubber.gemspec
 homepage: http://brandle.net
 licenses: []
+metadata: {}
 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: 1.8.21
+rubygems_version: 2.1.10
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Clean up URLs.
 test_files:
 - spec/spec_helper.rb