postrank-uri 1.0.23 → 1.0.24

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 45096e106f5528a2cee2b9b61856889699b1319c
-  data.tar.gz: d487c8d4ea2e19a78f8a191de9cf5e2bc1946060
+  metadata.gz: 8ea2cc7f1dc58cb559b9168ff0f83150f1ec6119
+  data.tar.gz: 73d97d1f7c56b4b0644eb9a8ad54490ca1561fbf
 SHA512:
-  metadata.gz: 34b61b475882e456ae4d68a2e440c9006a619c849b0dea0fad4f1ec15728aea9e2efeb04a9fea24a39ceb874e5a9eb1fae75db87180676da123ae99dfb319bd4
-  data.tar.gz: dd6a80d445bcd08ac8cde60ebb44f66836e8612e4313b52ae7187829722fec9b5d1d96e3f7bf6ba6201cea0d41432007c483fbd3da91970c559d515e70c27477
+  metadata.gz: 1fa2d5475a617ab8181554f4d15f4d72a1c67f40bb60c16502a575e16de6d721edcbe0c6ca1e5c331588510e0dd1cced56ea9dd4704dc7e9ab59b71c6a6385a5
+  data.tar.gz: 6ab0bf3e698d99127db88528a8fefba1b4d4c7667a6c42cc256a71dadb2dd78dd1f080e206312cc395b9a9c3c68b1fb62335c2f6a48346871cd85466ac86660b

data/.travis.yml

@@ -1,10 +1,10 @@
 language: ruby
 cache: bundler
 rvm:
-  - 2.1
-  - 2.2
-  - 2.3
-  - 2.4.0
+  - 2.3.8
+  - 2.4.5
+  - 2.5.3
+  - 2.6.1
 before_install:
   - gem install bundler
 install:

data/Appraisals

@@ -1,19 +1,15 @@
-appraise "nokogiri-1.7" do
-  gem "nokogiri", "~> 1.7.0"
-end
-
-appraise "nokogiri-1.6" do
-  gem "nokogiri", "~> 1.6.1"
-end
+nokogiri_versions = ["1.8", "1.9", "1.10"]
 
-appraise "addressable-2.3" do
-  gem "addressable", "~> 2.3.0"
+nokogiri_versions.each do |version|
+  appraise "nokogiri-#{version}" do
+    gem "nokogiri", "~> #{version}.0"
+  end
 end
 
-appraise "addressable-2.4" do
-  gem "addressable", "~> 2.4.0"
-end
+addressable_versions = ["2.4", "2.5", "2.6"]
 
-appraise "addressable-2.5" do
-  gem "addressable", "~> 2.5.0"
+addressable_versions.each do |version|
+  appraise "addressable-#{version}" do
+    gem "addressable", "~> #{version}.0"
+  end
 end

data/README.md

@@ -2,7 +2,7 @@
 
 [![Gem Version](https://badge.fury.io/rb/postrank-uri.svg)](https://rubygems.org/gems/postrank-uri) [![Build Status](https://travis-ci.org/postrank-labs/postrank-uri.svg?branch=master)](https://travis-ci.org/postrank-labs/postrank-uri)
 
-A collection of convenience methods (Ruby 2.0+) for dealing with extracting, (un)escaping, normalization, and canonicalization of URIs. At PostRank we process over 20M URI associated activities each day, and we need to make sure that we can reliably extract the URIs from a variety of text formats, deal with all the numerous and creative ways users like to escape and unescape their URIs, normalize the resulting URIs, and finally apply a set of custom canonicalization rules to make sure that we can cross-reference when the users are talking about the same URL.
+A collection of convenience methods (Ruby 2.3+) for dealing with extracting, (un)escaping, normalization, and canonicalization of URIs. At PostRank we process over 20M URI associated activities each day, and we need to make sure that we can reliably extract the URIs from a variety of text formats, deal with all the numerous and creative ways users like to escape and unescape their URIs, normalize the resulting URIs, and finally apply a set of custom canonicalization rules to make sure that we can cross-reference when the users are talking about the same URL.
 
 In a nutshell, we need to make sure that creative cases like the ones below all resolve to same URI:
 

data/lib/postrank-uri.rb

@@ -89,6 +89,7 @@ module PostRank
     URIREGEX[:reserved_characters] = /%3F|%26/i
     URIREGEX[:escape]   = /([^ a-zA-Z0-9_.-]+)/x
     URIREGEX[:unescape] = /(%[0-9a-fA-F]{2})/x
+    URIREGEX[:double_slash_outside_scheme] = /(?<!http:|https:)\/{2}/x
     URIREGEX.each_pair{|k,v| v.freeze }
 
     module_function
@@ -152,7 +153,7 @@ module PostRank
 
     def normalize(uri, opts = {})
       u = parse(uri, opts)
-      u.path = u.path.squeeze('/')
+      u.path = u.path.gsub(URIREGEX[:double_slash_outside_scheme], '/')
       u.path = u.path.chomp('/') if u.path.size != 1
       u.query = nil if u.query && u.query.empty?
       u.fragment = nil

data/lib/postrank-uri/version.rb

@@ -1,5 +1,5 @@
 module PostRank
   module URI
-    VERSION = "1.0.23"
+    VERSION = "1.0.24"
   end
 end

data/postrank-uri.gemspec

@@ -12,13 +12,13 @@ Gem::Specification.new do |s|
   s.summary     = "URI normalization, c14n, escaping, and extraction"
   s.description = s.summary
   s.license     = 'MIT'
-  s.required_ruby_version  = ">= 2.0.0"
+  s.required_ruby_version  = ">= 2.3.0"
 
   s.rubyforge_project = "postrank-uri"
 
-  s.add_dependency "addressable",   ">= 2.3.0", "< 2.6"
+  s.add_dependency "addressable",   ">= 2.4.0"
   s.add_dependency "public_suffix", ">= 2.0.0", "< 2.1"
-  s.add_dependency "nokogiri",      ">= 1.6.1", "< 1.9"
+  s.add_dependency "nokogiri",      ">= 1.8.0"
 
   s.add_development_dependency "rake"
   s.add_development_dependency "rspec"

data/spec/postrank-uri_spec.rb

@@ -98,6 +98,10 @@ describe PostRank::URI do
       expect(n('http://igvita.com/a/b')).to eq('http://igvita.com/a/b')
       expect(n('http://igvita.com/a/b/')).to eq('http://igvita.com/a/b')
     end
+    it 'preserves nested urls' do
+      expect(n('http://igvita.com/a/b/http://hello.com')).to eq('http://igvita.com/a/b/http://hello.com')
+      expect(n('http://igvita.com/a//b/https://hello.com')).to eq('http://igvita.com/a/b/https://hello.com')
+    end
   end
 
   context "canonicalization" do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: postrank-uri
 version: !ruby/object:Gem::Version
-  version: 1.0.23
+  version: 1.0.24
 platform: ruby
 authors:
 - Ilya Grigorik
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-12-16 00:00:00.000000000 Z
+date: 2019-04-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -16,20 +16,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.0
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '2.6'
+        version: 2.4.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.0
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '2.6'
+        version: 2.4.0
 - !ruby/object:Gem::Dependency
   name: public_suffix
   requirement: !ruby/object:Gem::Requirement
@@ -56,20 +50,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.1
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '1.9'
+        version: 1.8.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.1
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '1.9'
+        version: 1.8.0
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -152,7 +140,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.0.0
+      version: 2.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="