bad_link_finder 0.2.3 → 0.3.0

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    YTkzYzA3MDcwZjBkODJiN2VmZWM0OGRlODllMzFiZGJiMGQxNjc1Yg==
-  data.tar.gz: !binary |-
-    ZDNmNDg2NjYwODNmN2IwNGQyNTllZGQ3Yjc2ZTY0MjU4Y2JkMTBkMA==
+SHA1:
+  metadata.gz: 1958650ee80f6111928153181b576b6e2964450b
+  data.tar.gz: 74cf1cdd49ee638a65d5759dd051ad32709a5693
 SHA512:
-  metadata.gz: !binary |-
-    NWI0NGU1MTBiMzIyZDE2MTU0YmUxNTM5MWQyZTE3YTUwZjMyZThiYTcxNzA3
-    MjEzYWYxOWE0NTBmZjg2ZGJiYmQxZmYwMWEzNzA1NWJjNjEwM2RhMGJmZmNi
-    MzQ2NGU3NGMxNWI0MmFlYjdlNjYxODY5N2ExZjQ3OGQ3YThiZDk=
-  data.tar.gz: !binary |-
-    NWEzMmE1NGRlNmUwOGVkNmY3ZDNmMTNkZjc3MzVkMTZlOTY1ZGRjY2M2YWM5
-    NDI0ZTYxNTg0MzVlYTcwZjUyNDMwNGE5OTcxYmFkMjJiMGUxOTUzZGIxODQ1
-    NmEzNjM5OTBhZWE1ZTk4OTgzZTBjYTU5ZmViM2Y5N2M3Y2ZlZDI=
+  metadata.gz: 0dbf259bf6364c615f222ec5698bf3816212373ce12dc056a5edd9ac51ec2a4daedfbd37759d7a655f7320a041f0772a80f193f1fda9e4751cedaf58a659e06a
+  data.tar.gz: f3049d9b48675bdbf2eddfc35cda601fdb67b75321bb96ee78299a2cbccdeb840f865b97ee8488e82cb610c1df94c70ebaa5fa2adfd14eb5d1715a655ab4748c

data/README.md

@@ -6,8 +6,10 @@ Crawls a mirrored site and checks that all links either return a successful resp
 
 Set environment variables:
 
-- `MIRROR_DIR`, to the location of your mirrored site.
+- `MIRROR_DIR`, to the location of your mirrored site.  Local files will be read in alphabetical order.
 - `REPORT_OUTPUT_FILE`, to the location you'd like the CSV saved to.
 - `SITE_HOST`, to the full host of the live site you'd like to test against, including protocol.  For example, `https://www.example.com`
+- `START_FROM`, optional, specify a file on disk from which to start, e.g. `example-folder/example.html`.
+  Will check this file and all following files.  Useful for restarting aborted runs.
 
 Then execute `bad_link_finder`.

data/lib/bad_link_finder.rb

@@ -16,7 +16,7 @@ module BadLinkFinder
     csv_file = report_path.open('w')
     csv_builder = BadLinkFinder::CSVBuilder.new(csv_file)
 
-    BadLinkFinder::SiteChecker.new(ENV['MIRROR_DIR'], ENV['SITE_HOST'], csv_builder).run
+    BadLinkFinder::SiteChecker.new(ENV['MIRROR_DIR'], ENV['SITE_HOST'], csv_builder, ENV['START_FROM']).run
 
     csv_file.close
 

data/lib/bad_link_finder/site.rb

@@ -5,13 +5,17 @@ module BadLinkFinder
   class Site
     include Enumerable
 
-    def initialize(mirror_dir)
+    def initialize(mirror_dir, start_from = nil)
       @mirror_dir = mirror_dir.is_a?(String) ? Pathname.new(mirror_dir) : mirror_dir
+      @start_from = start_from
     end
 
     def each
       Dir.chdir(@mirror_dir) do
-        Dir.glob('**/*').each do |path|
+        paths = Dir.glob('**/*').sort
+        paths = paths[paths.index(@start_from)..-1] if @start_from
+
+        paths.each do |path|
           next if File.directory?(path)
           yield BadLinkFinder::Page.new(@mirror_dir, path)
         end

data/lib/bad_link_finder/site_checker.rb

@@ -4,15 +4,16 @@ require 'bad_link_finder/page_checker'
 
 module BadLinkFinder
   class SiteChecker
-    def initialize(mirror_dir, host, csv_builder)
+    def initialize(mirror_dir, host, csv_builder, start_from = nil)
       @mirror_dir = File.expand_path(mirror_dir)
       @host = host
       @csv_builder = csv_builder
+      @start_from = start_from
       @result_cache = BadLinkFinder::ResultCache.new
     end
 
     def run
-      BadLinkFinder::Site.new(@mirror_dir).each do |page|
+      BadLinkFinder::Site.new(@mirror_dir, @start_from).each do |page|
         page_checker = BadLinkFinder::PageChecker.new(@host, page, @result_cache)
         puts "Checking page #{page.path} as #{page_checker.page_url}"
 

data/lib/bad_link_finder/version.rb

@@ -1,3 +1,3 @@
 module BadLinkFinder
-  VERSION = "0.2.3"
+  VERSION = "0.3.0"
 end

data/test/integration/bad_link_finder_test.rb

@@ -1,6 +1,7 @@
 require 'test_helper'
 require 'webmock/minitest'
 require 'bad_link_finder'
+require 'tempfile'
 
 describe BadLinkFinder do
 
@@ -11,17 +12,27 @@ describe BadLinkFinder do
     stub_request(:any, 'http://www.example.com/example/?test=true&redirect=http://www.example.com/in-param-url/index.html').to_return(status: 404)
 
     ENV['MIRROR_DIR'] = (FIXTURES_ROOT+'www.example.com').to_s
-    ENV['REPORT_OUTPUT_FILE'] = (TMP_ROOT+'bad_links.csv').to_s
     ENV['SITE_HOST'] = 'http://www.example.com/'
+
+    @tempfile = Tempfile.new('bad_links.csv')
+    ENV['REPORT_OUTPUT_FILE'] = @tempfile.path
+  end
+
+  after do
+    @tempfile.close
+    @tempfile.unlink
+
+    ['MIRROR_DIR', 'REPORT_OUTPUT_FILE', 'SITE_HOST', 'START_FROM'].each { |k| ENV.delete(k) }
   end
 
   it "finds all broken links and exports to a CSV" do
     BadLinkFinder.run
 
-    csv_string = File.read(ENV['REPORT_OUTPUT_FILE'])
+    csv_string = @tempfile.read
 
     assert_match 'http://www.example.com/example/relative-example', csv_string
     assert_match 'correct-article-id', csv_string
+    assert_match 'https://www.example.net/external-example.html', csv_string
   end
 
   it "complains if key variables are missing" do
@@ -42,4 +53,16 @@ describe BadLinkFinder do
     end
   end
 
+  it "starts from a specific page if requested" do
+    ENV['START_FROM'] = 'example/relative-example.html'
+
+    BadLinkFinder.run
+
+    csv_string = @tempfile.read
+
+    assert_match 'http://www.example.com/example/relative-example', csv_string
+    assert_match 'correct-article-id', csv_string
+    refute_match 'https://www.example.net/external-example.html', csv_string
+  end
+
 end

data/test/unit/site_test.rb

@@ -17,6 +17,16 @@ describe BadLinkFinder::Site do
 
       assert_same_elements site_map, BadLinkFinder::Site.new(@site_mirror).map { |page| page.path.to_s }
     end
+
+    it "starts from a specific path if given" do
+      site_map = [
+        'example/relative-example',
+        ''
+      ]
+
+      site = BadLinkFinder::Site.new(@site_mirror, 'example/relative-example.html')
+      assert_equal site_map, site.map { |page| page.path.to_s }
+    end
   end
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bad_link_finder
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.3.0
 platform: ruby
 authors:
 - Elliot Crosby-McCullough
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-04 00:00:00.000000000 Z
+date: 2014-02-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
@@ -30,40 +30,54 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.5'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.5'
 - !ruby/object:Gem::Dependency
   name: minitest
   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: webmock
   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: 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
@@ -103,7 +117,10 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- LICENCE.txt
+- README.md
 - bin/bad_link_finder
+- lib/bad_link_finder.rb
 - lib/bad_link_finder/csv_builder.rb
 - lib/bad_link_finder/link.rb
 - lib/bad_link_finder/page.rb
@@ -112,9 +129,6 @@ files:
 - lib/bad_link_finder/site.rb
 - lib/bad_link_finder/site_checker.rb
 - lib/bad_link_finder/version.rb
-- lib/bad_link_finder.rb
-- README.md
-- LICENCE.txt
 - test/fixtures/www.example.com/example/index.html
 - test/fixtures/www.example.com/example/relative-example.html
 - test/fixtures/www.example.com/index.html
@@ -137,17 +151,17 @@ 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: 2.1.11
+rubygems_version: 2.2.0
 signing_key: 
 specification_version: 4
 summary: Tests links in static site mirrors