broken_link_finder 0.9.3 → 0.9.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0e03d27fce04a04ff97aa40ea895b01272926915367712a865787cda0efc3a0a
-  data.tar.gz: 487abab06c5664fb4024e58c7e1ba43209d076100d5d7da275db2f534aee4c4b
+  metadata.gz: cb0cc981acce272911be9d8a3ed36dd49e0f621eee3e9fd71893020da1600945
+  data.tar.gz: 3b368404cf3b2da83445212c44e43f32ad7d1fc5119c8980aeaa04540ebce2c9
 SHA512:
-  metadata.gz: 2b90b76061107fcde9b79e6b737710ee067be255182bdd7726ba2343aa64f0357b9901217f78cd0e3928244610cb9ad37007db8d316bbbef2a50355213d5764b
-  data.tar.gz: 5d727113d883f94e263933c726ea0eb0a41da343844c044d8220e042b877ac84b5c806e2f2d5570dd0dd9eb09a56f4603676b9194bc62201a01cb9fba7b14e23
+  metadata.gz: 92ffd946b60411dba032ac30b8a96820dea262520ab92e1f2d64c48477d4c4ca6e22fe41d221fb421423565f9d61883b48017c1c5af651c1bb71ba96eacf490c
+  data.tar.gz: 17455ab4cf7cb3ab0df9763b98cc844b1c1c07ed702c600cc623e263119a8f071b8a9f55519a021662db64e6bffda91d1c5d439ed8594ae87d830da19acf3529

data/CHANGELOG.md

@@ -9,6 +9,15 @@
 - ...
 ---
 
+## v0.9.4
+### Added
+- ...
+### Changed/Removed
+- Updated `wgit` gem to version 0.5.0 which contains improvements and bugs fixes.
+### Fixed
+- ...
+---
+
 ## v0.9.3
 ### Added
 - ...

data/Gemfile.lock

@@ -1,17 +1,17 @@
 PATH
   remote: .
   specs:
-    broken_link_finder (0.9.3)
+    broken_link_finder (0.9.4)
       thor (~> 0.20.3)
       thread (~> 0.2.0)
-      wgit (~> 0.4.1)
+      wgit (~> 0.5.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
     addressable (2.6.0)
       public_suffix (>= 2.0.2, < 4.0)
-    bson (4.5.0)
+    bson (4.6.0)
     byebug (11.0.1)
     coderay (1.1.2)
     crack (0.4.3)
@@ -27,7 +27,7 @@ GEM
     minitest (5.12.2)
     mongo (2.9.2)
       bson (>= 4.4.2, < 5.0.0)
-    nokogiri (1.10.4)
+    nokogiri (1.10.5)
       mini_portile2 (~> 2.4.0)
     pry (0.12.2)
       coderay (~> 1.1.0)
@@ -43,7 +43,7 @@ GEM
       addressable (>= 2.3.6)
       crack (>= 0.3.2)
       hashdiff (>= 0.4.0, < 2.0.0)
-    wgit (0.4.1)
+    wgit (0.5.0)
       addressable (~> 2.6.0)
       mongo (~> 2.9.0)
       nokogiri (~> 1.10.3)

data/README.md

@@ -2,7 +2,9 @@
 
 Does what it says on the tin; Finds a website's broken links.
 
-Simply point it at a website and it will crawl all of its webpages searching for and identifing any broken links. You will then be presented with a nice concise summary of the broken links found.
+Simply point it at a website and it will crawl all of its webpages searching for and identifing any broken links. You will then be presented with a concise summary of the broken links found.
+
+Because `libcurl` is used under the hood, Broken Link Finder is fast!
 
 ## How It Works
 
@@ -10,7 +12,7 @@ Any HTML page element with a `href` or `src` attribute is considered a link. For
 
 - An empty HTML response body is returned.
 - A response status code of `404 Not Found` is returned.
-- The HTML response body doesn't contain an element ID matching that of the link's anchor e.g. `http://server.com#about` must contain an element with `id="about"` or the link is considered broken.
+- The HTML response body doesn't contain an element ID matching that of the link's fragment e.g. `http://server.com#about` must contain an element with `id="about"` or the link is considered broken.
 - The link redirects more than 5 times consecutively.
 
 **Note**: Not all link types are supported.
@@ -73,9 +75,9 @@ Below is a simple script which crawls a website and outputs its broken links to
 require 'broken_link_finder'
 
 finder = BrokenLinkFinder.new
-finder.crawl_site 'http://txti.es'    # Or use Finder#crawl_page for a single webpage.
-finder.pretty_print_link_report       # Or use Finder#broken_links and Finder#ignored_links
-                                      # for direct access to the link Hashes.
+finder.crawl_site 'http://txti.es' # Or use Finder#crawl_page for a single webpage.
+finder.pretty_print_link_report    # Or use Finder#broken_links and Finder#ignored_links
+                                   # for direct access to the link Hashes.
 ```
 
 Then execute the script with:
@@ -126,9 +128,11 @@ After checking out the repo, run `bin/setup` to install dependencies. Then, run
 To install this gem onto your local machine, run `bundle exec rake install`.
 
 To release a new gem version:
+- Update the deps in the `*.gemspec` if necessary
 - Update the version number in `version.rb` and add the new version to the `CHANGELOG`
 - Run `bundle install`
 - Run `bundle exec rake test` ensuring all tests pass
 - Run `bundle exec rake compile` ensuring no warnings
-- Run `bundle exec rake install && rbenv rehash` and manually test the executable
+- Run `bundle exec rake install && rbenv rehash`
+- Manually test the executable
 - Run `bundle exec rake release[origin]`

data/broken_link_finder.gemspec

@@ -46,5 +46,5 @@ Gem::Specification.new do |spec|
 
   spec.add_runtime_dependency 'thor', '~> 0.20.3'
   spec.add_runtime_dependency 'thread', '~> 0.2.0'
-  spec.add_runtime_dependency 'wgit', '~> 0.4.1'
+  spec.add_runtime_dependency 'wgit', '~> 0.5.0'
 end

data/lib/broken_link_finder/finder.rb

@@ -112,8 +112,8 @@ module BrokenLinkFinder
     private
 
     # Finds which links are unsupported or broken and records the details.
-    def find_broken_links(doc)
-      links = get_supported_links(doc)
+    def find_broken_links(page)
+      links = get_supported_links(page)
 
       # Iterate over the supported links checking if they're broken or not.
       links.each do |link|
@@ -121,18 +121,18 @@ module BrokenLinkFinder
         next if @all_intact_links.include?(link)
 
         if @all_broken_links.include?(link)
-          append_broken_link(doc.url, link)
+          append_broken_link(page.url, link)
           next
         end
 
         # The link hasn't been processed before so we crawl it.
-        link_doc = crawl_link(doc, link)
+        link_doc = crawl_link(page, link)
 
         # Determine if the crawled link is broken or not.
         if  link_doc.nil? ||
-            @crawler.last_response.code == 404 ||
+            @crawler.last_response.not_found? ||
             has_broken_anchor(link_doc)
-          append_broken_link(doc.url, link)
+          append_broken_link(page.url, link)
         else
           @lock.synchronize { @all_intact_links << link }
         end
@@ -155,24 +155,18 @@ module BrokenLinkFinder
 
     # Makes the link absolute and crawls it, returning its Wgit::Document.
     def crawl_link(doc, link)
-      link = get_absolute_link(doc, link)
+      link = link.prefix_base(doc)
       @crawler.crawl(link)
     end
 
-    # Returns the link in absolute form so it can be crawled.
-    def get_absolute_link(doc, link)
-      link.is_relative? ? doc.base_url(link: link).concat(link) : link
-    end
-
-    # Returns true if the link is/contains a broken anchor.
+    # Returns true if the link is/contains a broken anchor/fragment.
     def has_broken_anchor(doc)
       raise 'link document is nil' unless doc
 
-      anchor = doc.url.anchor
-      return false if anchor.nil? || (anchor == '#')
+      fragment = doc.url.fragment
+      return false if fragment.nil? || fragment.empty?
 
-      anchor = anchor[1..-1] if anchor.start_with?('#')
-      doc.xpath("//*[@id='#{anchor}']").empty?
+      doc.xpath("//*[@id='#{fragment}']").empty?
     end
 
     # Append key => [value] to @broken_links.

data/lib/broken_link_finder/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module BrokenLinkFinder
-  VERSION = '0.9.3'
+  VERSION = '0.9.4'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: broken_link_finder
 version: !ruby/object:Gem::Version
-  version: 0.9.3
+  version: 0.9.4
 platform: ruby
 authors:
 - Michael Telford
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-10-20 00:00:00.000000000 Z
+date: 2019-11-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -128,14 +128,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.1
+        version: 0.5.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.1
+        version: 0.5.0
 description: Finds a website's broken links using the 'wgit' gem and reports back
   to you with a summary.
 email: michael.telford@live.com