utterson 0.2.0 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: b284cf9e9272e1093bd7c4172ef0036750de59e8
-  data.tar.gz: 512987cf376f785eb0621c7e374a002c3385cdb8
+SHA256:
+  metadata.gz: f068f678f7ad3eace6ba4083e1fab800e571165483fd366b80807620776063ed
+  data.tar.gz: d20d1495a36de95ae1212e11b18f06b926da37351ef72cf06fa6ccabb7ebf20f
 SHA512:
-  metadata.gz: e1aec6ceb0f9748d1f5e378592159e322335214a6f96987bd253e38f2c4c42b6fe9a6c52791a0b9402228e71b5653bd9dfa0760360f3bab733e3a439eeb520c3
-  data.tar.gz: 64d65499f25e4c614995eced88b5a052c4623dbd8bbba7024abdfd512b696ecbe4d124b919eca19775e78ffaf2961e8281b2d17147732b5dbfaa9793e84131e4
+  metadata.gz: 424f2cdbdfa9f56bbb92b64baff326b3722ca1ec8d6c97db0f176c70ad5066918696595364544f6cf283a616f38eabdb2d4a69d68beb5235eced8ed703727234
+  data.tar.gz: a5ee5b1682da10e1953f5de0addc9231179d3d00fc4fd5f9877b0352d2cd1615fcf91d73b87afa74081d47f4ee76e0a9866a66450c618de990f15603ad471ba1

data/README.md

@@ -1,6 +1,8 @@
 Simple utility to traverse directory of html files and check links in them.
 
-[![Build Status](https://travis-ci.org/iiska/utterson.png)](https://travis-ci.org/iiska/utterson) [![Dependency Status](https://gemnasium.com/iiska/utterson.png)](https://gemnasium.com/iiska/utterson)
+[![Gem Version](https://badge.fury.io/rb/utterson.png)](http://badge.fury.io/rb/utterson)
+[![Tests](https://github.com/iiska/utterson/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/iiska/utterson/actions/workflows/ci.yml)
+
 
 ## Getting started
 
@@ -27,4 +29,4 @@ Hyde](https://en.wikipedia.org/wiki/Strange_Case_of_Dr_Jekyll_and_Mr_Hyde).
 
 ## License
 
-Released under the [MIT License](http://www.opensource.org/licenses/MIT)
+Released under the [MIT License](http://www.opensource.org/licenses/MIT)

data/bin/utterson

@@ -2,10 +2,10 @@
 
 $:.unshift File.join(File.dirname(__FILE__), *%w{ .. lib })
 
-require 'trollop'
+require 'optimist'
 require 'utterson'
 
-opts = Trollop::options do
+opts = Optimist::options do
   opt :root, "Root directory for the site if it differs from target dir", type: :string
 end
 

data/lib/utterson/base.rb

@@ -1,6 +1,10 @@
+require 'ruby-progressbar'
+
 require 'utterson/html_check'
 
 module Utterson
+  # Base implements initialization of the checking process and handles
+  # outputting final results.
   class Base
     attr_reader :errors
 
@@ -13,15 +17,16 @@ module Utterson
     end
 
     def check
+      bar = ProgressBar.create
       threads = []
       Dir.glob(File.join(@dir, '**/*.{html,htm}')) do |f|
         @stats[:files] += 1
-        puts "Checking file #{f}"
+        bar.total = @stats[:files]
         c = HtmlCheck.new(file: f, root: @root)
         c.when_done do |r|
+          bar.increment
           @stats[:urls] = r[:urls]
           @errors.merge! r[:errors]
-          puts "Check done with #{f}"
         end
         threads << c.run
       end
@@ -42,7 +47,8 @@ module Utterson
       if count == 0
         puts "#{@stats[:files]} files with #{@stats[:urls]} urls checked."
       else
-        puts "#{@stats[:files]} files with #{@stats[:urls]} urls checked and #{count} errors found."
+        puts "Q{#{@stats[:files]} files with #{@stats[:urls]} urls checked "+
+          "and #{count} errors found."
       end
     end
   end

data/lib/utterson/html_check.rb

@@ -5,6 +5,8 @@ require 'timeout'
 require 'thread'
 
 module Utterson
+  # Handle collecting URIs from HTML documents and both remote and
+  # local checking of them.
   class HtmlCheck
     attr_reader :errors
 
@@ -61,23 +63,18 @@ module Utterson
     end
 
     def check_remote_uri(url, file)
-      begin
-        uri = URI(url.gsub(/^\/\//, 'http://'))
-      rescue URI::InvalidURIError => e
-        return add_error(file, uri.to_s, e.message)
+      uri = URI(url.gsub(/^\/\//, 'http://'))
+
+      response = Net::HTTP.start(uri.host, uri.port,
+                                 :use_ssl => uri.scheme == 'https') do |http|
+        http.head uri.path.empty? ? "/" : uri.path
       end
-      begin
-        response = Net::HTTP.start(uri.host, uri.port,
-                                   :use_ssl => uri.scheme == 'https') do |http|
-          p = uri.path.empty? ? "/" : uri.path
-          http.head(p)
-        end
-        if response.code =~ /^[^23]/
-          add_error(file, uri.to_s, response)
-        end
-      rescue => e
-        add_error(file, uri.to_s, e.message)
+      if response.code =~ /^[^23]/
+        add_error(file, uri.to_s, response)
       end
+
+    rescue => e
+      add_error(file, uri.to_s, e.message)
     end
 
     def check_local_uri(url, file)
@@ -87,7 +84,7 @@ module Utterson
       else
         path = File.expand_path(url, File.dirname(file))
       end
-      add_error(file, url, "File not found") unless File.exists? path
+      add_error(file, url, "File not found") unless File.exist? path
     end
 
     def add_error(file, url, response)

data/lib/utterson/version.rb

@@ -1,3 +1,3 @@
 module Utterson
-  VERSION = '0.2.0'
+  VERSION = '0.3.2'
 end

data/spec/spec_helper.rb

@@ -3,6 +3,7 @@
 require 'webmock/rspec'
 
 require 'simplecov'
+SimpleCov.formatter = SimpleCov::Formatter::HTMLFormatter
 SimpleCov.start
 
 require 'utterson'

data/spec/utterson/base_spec.rb

@@ -11,7 +11,7 @@ module Utterson
        "spec/fixtures/dir-structure/2.html",
        "spec/fixtures/dir-structure/a/3.htm",
        "spec/fixtures/dir-structure/a/b/4.html"].each do |file|
-        HtmlCheck.should_receive(:new).with(file: file, root: dir)
+        expect(HtmlCheck).to receive(:new).with(file: file, root: dir)
       end
 
       u.check
@@ -23,7 +23,7 @@ module Utterson
         output = capture_stdout do
           u.check
         end
-        output.should match(/4 files with 0 urls checked/)
+        expect(output).to match(/4 files with 0 urls checked/)
       end
 
       it "should output error information" do
@@ -34,11 +34,12 @@ module Utterson
         output = capture_stdout do
           u.check
         end
-        output.should match("spec/fixtures/sample.html\n\tstyle.css\n\t\tFile not found")
-        output.should match("script.js\n\t\tFile not found")
-        output.should match("image.jpg\n\t\tFile not found")
-        output.should match("http://example.com\n\t\tHTTP 404")
-        output.should match("5 files with 4 urls checked and 4 errors found")
+        expect(output).to match("spec/fixtures/sample.html\n\tstyle.css\n"+
+                            "\t\tFile not found")
+        expect(output).to match("script.js\n\t\tFile not found")
+        expect(output).to match("image.jpg\n\t\tFile not found")
+        expect(output).to match("http://example.com\n\t\tHTTP 404")
+        expect(output).to match("5 files with 4 urls checked and 4 errors found")
       end
     end
   end

data/spec/utterson/html_check_spec.rb

@@ -18,10 +18,10 @@ module Utterson
     it "should find all uris from sample document" do
       h = HtmlCheck.new(file: sample_file)
       uris = h.collect_uris_from(sample_file)
-      uris.should include("script.js")
-      uris.should include("style.css")
-      uris.should include("http://example.com")
-      uris.should include("image.jpg")
+      expect(uris).to include("script.js")
+      expect(uris).to include("style.css")
+      expect(uris).to include("http://example.com")
+      expect(uris).to include("image.jpg")
     end
 
     describe "#check_uri" do
@@ -65,36 +65,36 @@ module Utterson
       end
     end
 
-    describe "#check_local_uri" do
+    describe "#check_relative_uri" do
       let(:h) {HtmlCheck.new(root: "spec/fixtures/dir-structure")}
       let(:html_file) {"spec/fixtures/dir-structure/1.htm"}
 
       it "should not assign error info if file exists" do
         h.check_local_uri("../sample.html", html_file)
-        h.errors.should be_empty
+        expect(h.errors).to be_empty
       end
 
       it "should assign error info if file doesn't exist" do
         url = "../sample_not_found.html"
         h.check_local_uri(url, html_file)
-        h.errors[html_file].should == {url => "File not found"}
+        expect(h.errors[html_file]).to eq({url => "File not found"})
       end
 
       it "should use root directory when urls start with /" do
         h2 = HtmlCheck.new(file: html_file,
                            root: "spec/fixtures")
         h2.check_local_uri("/sample.html", html_file)
-        h2.errors.should be_empty
+        expect(h2.errors).to be_empty
       end
 
-      it "should handle target directory as root for urls starting with / if root is no available" do
+      it "uses target directory as root if undefined when url starts with /" do
         h.check_local_uri("/2.html", html_file)
-        h.errors.should be_empty
+        expect(h.errors).to be_empty
       end
 
       it "should ignore query string when checking local files" do
         h.check_local_uri("2.html?queryparam=value", html_file)
-        h.errors.should be_empty
+        expect(h.errors).to be_empty
       end
     end
 
@@ -108,7 +108,7 @@ module Utterson
           with(:headers => {'Accept'=>'*/*', 'User-Agent'=>'Ruby'}).
           to_return(:status => 200, :body => "", :headers => {})
         h.check_remote_uri(url, html_file)
-        h.errors.should be_empty
+        expect(h.errors).to be_empty
       end
 
       it "should assign error info if there is error response" do
@@ -116,40 +116,38 @@ module Utterson
           with(:headers => {'Accept'=>'*/*', 'User-Agent'=>'Ruby'}).
           to_return(:status => 404, :body => "", :headers => {})
         h.check_remote_uri(url, html_file)
-        puts h.errors.inspect
-        h.errors[html_file].should_not be_empty
-        h.errors[html_file][url].instance_of?(Net::HTTPNotFound).should be_true
+        expect(h.errors[html_file]).not_to be_empty
+        expect(h.errors[html_file][url].instance_of?(Net::HTTPNotFound)).to be_truthy
       end
 
       it "should add error status from buffer timeouts" do
         stub_request(:head, url).to_timeout
         h.check_remote_uri(url, html_file)
-        h.errors.should_not be_empty
+        expect(h.errors).not_to be_empty
       end
 
       it "should add error status from connection timeouts" do
         stub_request(:head, url).to_raise(Errno::ETIMEDOUT)
         h.check_remote_uri(url, html_file)
-        h.errors.should_not be_empty
+        expect(h.errors).not_to be_empty
       end
 
       it "should add error status from 'No route to host' errors" do
         stub_request(:head, url).to_raise(Errno::EHOSTUNREACH)
         h.check_remote_uri(url, html_file)
-        h.errors.should_not be_empty
+        expect(h.errors).not_to be_empty
       end
 
       it "shoud add error status from name resolution errors" do
         stub_request(:head, url).
           to_raise(SocketError.new('getaddrinfo: Name or service not known'))
         h.check_remote_uri(url, html_file)
-        h.errors.should_not be_empty
+        expect(h.errors).not_to be_empty
       end
 
       it "shoud add error status when invalid URI" do
-        URI.stub(:new).and_raise(URI::InvalidURIError)
-        h.check_remote_uri("http://invalid_uri", html_file)
-        h.errors.should_not be_empty
+        h.check_remote_uri(":", html_file)
+        expect(h.errors).not_to be_empty
       end
     end
   end

metadata

@@ -1,99 +1,127 @@
 --- !ruby/object:Gem::Specification
 name: utterson
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.2
 platform: ruby
 authors:
 - Juhamatti Niemelä
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-07 00:00:00.000000000 Z
+date: 2023-04-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: trollop
+  name: optimist
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.14.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.14.0
+- !ruby/object:Gem::Dependency
+  name: ruby-progressbar
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.13.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.13.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.12'
 - !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
   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: simplecov
   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: 1.15.2
+        version: 3.18.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.15.2
+        version: 3.18.0
 description: Traverses all HTML files from given directory and checks links found
   in them.
 email: iiska@iki.fi
@@ -102,20 +130,20 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- README.md
 - bin/utterson
+- lib/utterson.rb
+- lib/utterson/base.rb
 - lib/utterson/html_check.rb
 - lib/utterson/version.rb
-- lib/utterson/base.rb
-- lib/utterson.rb
-- README.md
-- spec/utterson/base_spec.rb
-- spec/utterson/html_check_spec.rb
-- spec/spec_helper.rb
+- spec/fixtures/dir-structure/1.htm
+- spec/fixtures/dir-structure/2.html
 - spec/fixtures/dir-structure/a/3.htm
 - spec/fixtures/dir-structure/a/b/4.html
-- spec/fixtures/dir-structure/2.html
-- spec/fixtures/dir-structure/1.htm
 - spec/fixtures/sample.html
+- spec/spec_helper.rb
+- spec/utterson/base_spec.rb
+- spec/utterson/html_check_spec.rb
 homepage: https://github.com/iiska/utterson
 licenses:
 - MIT
@@ -126,27 +154,25 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.3
+      version: 2.7.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.0.3
+rubygems_version: 3.4.10
 signing_key: 
 specification_version: 4
 summary: Friendly HTML crawler and url checker
 test_files:
-- spec/utterson/base_spec.rb
-- spec/utterson/html_check_spec.rb
-- spec/spec_helper.rb
+- spec/fixtures/dir-structure/1.htm
+- spec/fixtures/dir-structure/2.html
 - spec/fixtures/dir-structure/a/3.htm
 - spec/fixtures/dir-structure/a/b/4.html
-- spec/fixtures/dir-structure/2.html
-- spec/fixtures/dir-structure/1.htm
 - spec/fixtures/sample.html
-has_rdoc: 
+- spec/spec_helper.rb
+- spec/utterson/base_spec.rb
+- spec/utterson/html_check_spec.rb