wgit 0.5.1 → 0.6.0

data/lib/wgit/document_extensions.rb

@@ -55,7 +55,7 @@ end
 # Text.
 Wgit::Document.define_extension(
   :text,
-  proc { Wgit::Document.text_elements_xpath },
+  Wgit::Document::TEXT_ELEMENTS_XPATH,
   singleton: false,
   text_content_only: true
 )

data/lib/wgit/response.rb

@@ -56,11 +56,11 @@ module Wgit
       @body.empty? ? nil : @body
     end
 
-    # Returns true if the response isn't a #success? or a #redirect?
+    # Returns whether or not a server response is absent.
     #
-    # @return [Boolean] True if failed, false otherwise.
+    # @return [Boolean] True if the status is nil or < 1, false otherwise.
     def failure?
-      !success? && !redirect?
+      !success?
     end
 
     # Sets the headers Hash to the given value. The header keys are mapped
@@ -122,13 +122,13 @@ module Wgit
       @status = int.positive? ? int : nil
     end
 
-    # Returns whether or not the response is a 2xx Success.
+    # Returns whether or not a server response is present.
     #
-    # @return [Boolean] True if 2xx Success, false otherwise.
+    # @return [Boolean] True if the status is > 0, false otherwise.
     def success?
       return false unless @status
 
-      @status.between?(200, 299)
+      @status.positive?
     end
 
     alias code       status

data/lib/wgit/url.rb

@@ -19,7 +19,7 @@ module Wgit
     include Assertable
 
     # Whether or not the Url has been crawled or not. A custom crawled= method
-    # is provided by this class, overridding the default one.
+    # is provided by this class.
     attr_reader :crawled
 
     # The Time stamp of when this Url was crawled.
@@ -31,7 +31,7 @@ module Wgit
     # Initializes a new instance of Wgit::Url which represents a web based
     # HTTP URL.
     #
-    # @param url_or_obj [String, Wgit::Url, Object#fetch#[]] Is either a String
+    # @param url_or_obj [String, Wgit::Url, #fetch#[]] Is either a String
     #   based URL or an object representing a Database record e.g. a MongoDB
     #   document/object.
     # @param crawled [Boolean] Whether or not the HTML of the URL's web page
@@ -114,16 +114,22 @@ module Wgit
 
     # Returns true if self is a relative Url; false if absolute.
     #
-    # All external links in a page are expected to have a scheme prefix e.g.
-    # 'http://', otherwise the link is treated as an internal link (regardless
+    # An absolute URL must have a scheme prefix e.g.
+    # 'http://', otherwise the URL is regarded as being relative (regardless
     # of whether it's valid or not). The only exception is if an opts arg is
     # provided and self is a page belonging to that arg type e.g. host; then
     # the link is relative.
     #
+    # @example
+    #   url = Wgit::Url.new('http://example.com/about')
+    #
+    #   url.relative? # => false
+    #   url.relative?(host: 'http://example.com') # => true
+    #
     # @param opts [Hash] The options with which to check relativity. Only one
     #   opts param should be provided. The provided opts param Url must be
     #   absolute and be prefixed with a scheme. Consider using the output of
-    #   Wgit::Url#to_base which should work unless it's nil.
+    #   Wgit::Url#to_base which should work (unless it's nil).
     # @option opts [Wgit::Url, String] :base The Url base e.g.
     #   http://www.google.com/how which gives a base of
     #   'http://www.google.com'.
@@ -133,7 +139,7 @@ module Wgit
     #   http://www.google.com/how which gives a domain of 'google.com'.
     # @option opts [Wgit::Url, String] :brand The Url brand e.g.
     #   http://www.google.com/how which gives a domain of 'google'.
-    # @raise [StandardError] If self is invalid e.g. empty or an invalid opts
+    # @raise [StandardError] If self is invalid (e.g. empty) or an invalid opts
     #   param has been provided.
     # @return [Boolean] True if relative, false if absolute.
     def relative?(opts = {})
@@ -151,9 +157,9 @@ module Wgit
 
       type, url = opts.first
       url = Wgit::Url.new(url)
-      unless url.to_base
-        raise "Invalid opts param value, Url must be absolute and contain \
-protocol scheme: #{url}"
+      if url.invalid?
+        raise "Invalid opts param value, it must be absolute, containing a \
+protocol scheme and domain (e.g. http://example.com): #{url}"
       end
 
       case type
@@ -177,18 +183,20 @@ protocol scheme: #{url}"
       @uri.absolute?
     end
 
-    # Returns if self is a valid and absolute HTTP Url or not.
+    # Returns if self is a valid and absolute HTTP URL or not. Self should
+    # always be crawlable if this method returns true.
     #
-    # @return [Boolean] True if valid and absolute, otherwise false.
+    # @return [Boolean] True if valid, absolute and crawable, otherwise false.
     def valid?
       return false if relative?
-      return false unless start_with?('http://') || start_with?('https://')
+      return false unless to_base && to_domain
       return false if URI::DEFAULT_PARSER.make_regexp.match(normalize).nil?
 
       true
     end
 
-    # Returns if self is an invalid (relative) HTTP Url or not.
+    # Returns if self is an invalid (e.g. relative) HTTP URL. See
+    # Wgit::Url#valid? for the inverse (and more information).
     #
     # @return [Boolean] True if invalid, otherwise false.
     def invalid?
@@ -227,8 +235,9 @@ protocol scheme: #{url}"
     # idempotent. The doc's <base> element is used if present, otherwise
     # doc.url is used as the base; which is concatted with self.
     #
-    # Typically used to build an absolute link obtained from a document e.g.
+    # Typically used to build an absolute link obtained from a document.
     #
+    # @example
     #   link = Wgit::Url.new('/favicon.png')
     #   doc  = Wgit::Document.new('http://example.com')
     #

data/lib/wgit/utils.rb

@@ -188,9 +188,9 @@ module Wgit
     #
     # @param arr [Enumerable] The Array to process. arr is modified.
     # @return [Enumerable] The processed arr is both modified and then returned.
-    def self.process_arr(arr)
+    def self.process_arr(arr, encode: true)
       if arr.is_a?(Array)
-        arr.map! { |str| process_str(str) }
+        arr.map! { |str| process_str(str, encode: encode) }
         arr.reject! { |str| str.is_a?(String) ? str.empty? : false }
         arr.compact!
         arr.uniq!

data/lib/wgit/version.rb

@@ -5,7 +5,7 @@
 # @author Michael Telford
 module Wgit
   # The current gem version of Wgit.
-  VERSION = '0.5.1'
+  VERSION = '0.6.0'
 
   # Returns the current gem version of Wgit as a String.
   def self.version

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: wgit
 version: !ruby/object:Gem::Version
-  version: 0.5.1
+  version: 0.6.0
 platform: ruby
 authors:
 - Michael Telford
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-11-22 00:00:00.000000000 Z
+date: 2019-12-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -213,6 +213,12 @@ files:
 - "./lib/wgit/url.rb"
 - "./lib/wgit/utils.rb"
 - "./lib/wgit/version.rb"
+- ".yardopts"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- CONTRIBUTING.md
+- LICENSE.txt
+- README.md
 homepage: https://github.com/michaeltelford/wgit
 licenses:
 - MIT
@@ -221,7 +227,7 @@ metadata:
   source_code_uri: https://github.com/michaeltelford/wgit
   changelog_uri: https://github.com/michaeltelford/wgit/blob/master/CHANGELOG.md
   bug_tracker_uri: https://github.com/michaeltelford/wgit/issues
-  documentation_uri: https://www.rubydoc.info/gems/wgit
+  documentation_uri: https://www.rubydoc.info/github/michaeltelford/wgit/master
   allowed_push_host: https://rubygems.org
 post_install_message: 
 rdoc_options: []
@@ -238,8 +244,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Wgit is a Ruby gem similar in nature to GNU's `wget` tool. It provides an