linkey 1.4.0 → 1.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: aecb337d1fc6a5912ddbfdb8d5ab85571680eb19
-  data.tar.gz: 7f3e4c32377465f87300ef4324e3fa9612c4b836
+  metadata.gz: 86d840ae1eee23f4d83fb1fac2ab24412283e2ff
+  data.tar.gz: eb990de7ca319e5842e0b86928031d73123ac6e1
 SHA512:
-  metadata.gz: 749aa652254f43d038ca1199d8b8a4107612a0381847b38c0b33e451185d355cd30f0b2f66ff95fc6924687b3f836ae69c47874d1a872ac3e4834b1dc92a48b0
-  data.tar.gz: 36b71fc3fa9d8e7c3f83d796a511da1a21884b8f42495804e9a5cff80c1c11ad6dd4d456c782392b99e79c1e663634ce473ceff2ccc6b400960b70aa548b7508
+  metadata.gz: b77a591f2eef8bf76e5b1ecb519b97792b78d482b6811328603a89b1bba61a1179f3fe767f597d80e432c75434c07cb3072beb35b9494122f7fe4bb1925c2dd1
+  data.tar.gz: 86acdb19a4e504cd65d3fd8f901e2e7f76fbb80658c41b3242b9602cb10dd7b99443721641bf2512e97519201a143f58a66c5416a3a4738deaa1b372edd58b6d

data/README.md

@@ -1,49 +1,45 @@
-[![Build Status](https://travis-ci.org/DaveBlooman/linkey.png?branch=master)](https://travis-ci.org/DaveBlooman/linkey)  [![Code Climate](https://codeclimate.com/github/DaveBlooman/linkey/badges/gpa.svg)](https://codeclimate.com/github/DaveBlooman/linkey)  [![Gem Version](https://badge.fury.io/rb/linkey.svg)](http://badge.fury.io/rb/linkey)
-Linkey
-=====
+# Linkey
 
-Link checker for BBC News/WS Sites
+[![gem_version.png](https://img.shields.io/gem/v/linkey.svg)](https://rubygems.org/gems/linkey) [![gem_downloads.png](https://img.shields.io/gem/dt/linkey.svg)](https://rubygems.org/gems/linkey) [![travis.png](https://img.shields.io/travis/DaveBlooman/linkey/master.svg)](https://travis-ci.org/DaveBlooman/linkey) [![code_climate.png](https://img.shields.io/codeclimate/github/DaveBlooman/linkey.svg)](https://codeclimate.com/github/DaveBlooman/linkey)
+
+**Link checker for BBC News & World Services sites.**
 
 The idea is to quickly check a page for broken links by doing a status check on all the relative URL's on the page.
 
 There are 4 parts to this tool, the URL, the base URL, the regex and the filename.  
 
-The URL is the page that you want to check for broken links, e.g www.bbc.co.uk/news/uk-29928282
-The Base URL is used with the relative URL from the regex to create a full URL, e.g www.bbc.co.uk  
-The regex is the point of the URL that you want to keep from the regex, e.g bbc.co.uk/news/uk, specifying /news would create /news/uk.  
-The filename is .md file where all the page links are stored, this can be useful for manual checks, e.g file.md
+* **URL** is the page that you want to check for broken links, e.g `www.bbc.co.uk/news/uk-29928282`
+* **Base URL** is used with the relative URL from the regex to create a full URL, e.g `www.bbc.co.uk`
+* **Regex** is the point of the URL that you want to keep from the regex, e.g `bbc.co.uk/news/uk`, specifying `/news` would create `/news/uk`.  
+* **Filename** is markdown (.md) file where all the page links are stored, this can be useful for manual checks, e.g `file.md`
 
-## Install
+## Installation
 
-```
-gem install linkey
-```
+    gem install linkey
 
-## Command line usage
+## Usage
 
-To use run
+### Command Line
 
 ```
-linkey check URL BASEURL /regex Filename
+linkey check <url> <base_url> <regex> <filename>
 ```
-Example
+
+**Examples**
 
 ```
 linkey check http://www.bbc.co.uk/arabic http://www.bbc.co.uk /arabic arabic.md
 ```
-Another
 
 ```
 linkey check http://www.theguardian.com/technology/2014/feb/15/year-of-code-needs-reboot-teachers http://theguardian.com /technology news.md
 ```
-Output
+**Output**
 
-Once running, you'll see either a 200 with
-`Status is 200 for URL`
-or
-`Status is NOT GOOD for URL`
+Once running, you'll see either a 200 with `Status is 200 for <URL>` or `Status is NOT GOOD for <URL>`.
+
+### Script It
 
-## Script it
 ```ruby
 require 'linkey'
 
@@ -58,7 +54,8 @@ status = Linkey::CheckResponse.new(url, base, reg, filename)
 page.capture_links
 status.check_links
 ```
-## From a file
+
+### From a File
 
 If you have a lot of URLs that you want to check all the time using from a file is an alternative option.  This will utilise the smoke option, then point to a YAML file with the extension.  In some situations, we are deploying applications that we don't want public facing, so ensuring they 404 is essential.  There is a status code option to allow a specific status code to be set against a group of URL's, ensuring builds fail if the right code conditions are met.
 
@@ -66,10 +63,13 @@ If you have a lot of URLs that you want to check all the time using from a file
 linkey smoke test.yaml
 ```
 
-Example yaml file
+Example YAML Config:
+
 ```yaml
 base: 'http://www.bbc.co.uk'
 
+concurrency: 100
+
 headers:
  -
    X-content-override: 'https://example.com'
@@ -81,7 +81,7 @@ paths:
   - /news/uk
 ```
 
-Smoke test
+Via a Ruby script:
 
 ```ruby
 require 'linkey'

data/lib/linkey.rb

@@ -28,7 +28,7 @@ module Linkey
 
     def scan(page_links)
       urls = page_links.scan(/^#{Regexp.quote(reg)}(?:|.+)?$/)
-      Getter.new(urls, base).check
+      Getter.new(urls, base, 100, 200, {}).check
     end
   end
 
@@ -50,29 +50,40 @@ module Linkey
   end
 
   class Checker
+    attr_accessor :config
+
     def initialize(config)
-      @smoke_urls = YAML.load(File.open("#{config}"))
+      @config = YAML.load(File.open("#{config}"))
     end
 
     def base
-      @smoke_urls["base"]
+      config["base"]
+    end
+
+    def concurrency
+      config["concurrency"] ? config["concurrency"] : 100
+    end
+
+    def status_code
+      config["status_code"] ? config["status_code"] : 200
     end
 
     def smoke
-      urls = @smoke_urls["paths"]
-      options = @smoke_urls["headers"]
+      urls = config["paths"]
+      options = config["headers"]
       headers = Hash[*options]
-      @smoke_urls["status_code"] ? status_code = @smoke_urls["status_code"] : status_code = 200
-      Getter.new(urls, base, { :headers => headers }, status_code).check
+      Getter.new(urls, base, concurrency, status_code, { :headers => headers }).check
     end
   end
 
   class Getter
-    def initialize(paths, base, headers = {}, status = 200)
-      @paths   = paths
-      @base    = base
-      @headers = headers
-      @status  = status
+    def initialize(paths, base, concurrency, status, headers)
+      @paths       = paths
+      @base        = base
+      @headers     = headers
+      @status      = status
+
+      @hydra = Typhoeus::Hydra.new(:max_concurrency => concurrency)
     end
 
     def check
@@ -82,22 +93,20 @@ module Linkey
         begin
           Typhoeus::Request.new(url(path), options).tap do |req|
             req.on_complete { |r| parse_response(r, status) }
-            HYDRA.queue req
+            hydra.queue req
           end
-        rescue
-          puts "Error with URL #{path}, please check config"
+        rescue URI::InvalidURIError
+          puts "Error with URL #{path}, please check config."
         end
       end
 
-      HYDRA.run
+      hydra.run
       check_for_broken
     end
 
     private
 
-    attr_reader :base, :headers, :paths, :status
-
-    HYDRA = Typhoeus::Hydra.new(:max_concurrency => 100)
+    attr_reader :base, :headers, :paths, :status, :concurrency, :hydra
 
     def check_for_broken
       puts "Checking"

data/lib/linkey/version.rb

@@ -1,3 +1,3 @@
 module Linkey
-  VERSION = "1.4.0"
+  VERSION = "1.5.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: linkey
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.5.0
 platform: ruby
 authors:
 - Dave Blooman
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-02-20 00:00:00.000000000 Z
+date: 2015-04-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: thor