uri 0.12.1 → 0.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7d86620a487d2769ad2d77ec2d040b38ce8d97c49c7e58228083cd41cae23e94
-  data.tar.gz: 5bc762b3a032fedea0ecd0640fd3d580296171ce12231e6cd6c766ff51622675
+  metadata.gz: 8f4eaea3d45b9a860a4a1765dfa211d195929e01ea90e2ff25405fea90948098
+  data.tar.gz: 5f962ae3a2b0c56f589df823edf89560420d8c2dced50ac7332e5a6322a772bc
 SHA512:
-  metadata.gz: 026e3ef8b7e0cb8b5d243169a8eab6b8be7ca820328456b737fc21862ec8e09f1390e9010891607ed6a4689a8bc075384d51ae6c79aaaf872b5f1f5f50473f42
-  data.tar.gz: c7817221a6ee496344c4d62e91da663ff2eaf4f7d93a05818460225ce75c069b414eb24248bff1d0979cc57f9c559381053768845ffcfdad7997a9e968aa7d8e
+  metadata.gz: 8fb0be9745374a552f34d58d834e206adabc9a81bfc15bc7179c4143b639f0f62dd73ab46637023147e10be72b61ffdb2b18ac32a697d185244026a51560dc54
+  data.tar.gz: 6961a3339bfa178cd339a14828cbb4be6d79249fc1d262da0ea7d68095435efe801ef71642866ab0de2e7a5edc759a168e8b54a006f038e446d755c9781dbf49

data/.github/workflows/gh-pages.yml

@@ -0,0 +1,46 @@
+name: Deploy RDoc site to Pages
+
+on:
+  push:
+    branches: [ 'master' ]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup Ruby
+        uses: ruby/setup-ruby@250fcd6a742febb1123a77a841497ccaa8b9e939 # v1.152.0
+        with:
+          ruby-version: '3.2'
+          bundler-cache: true
+      - name: Setup Pages
+        id: pages
+        uses: actions/configure-pages@v3
+      - name: Build with RDoc
+        # Outputs to the './_site' directory by default
+        run: bundle exec rake rdoc
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v2
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v2

data/.github/workflows/test.yml

@@ -3,19 +3,25 @@ name: CI
 on: [push, pull_request]
 
 jobs:
+  ruby-versions:
+    uses: ruby/actions/.github/workflows/ruby_versions.yml@master
+    with:
+      min_version: 2.5
+
   build:
+    needs: ruby-versions
     name: build (${{ matrix.ruby }} / ${{ matrix.os }})
     strategy:
       matrix:
-        ruby: [ 3.1, '3.0', 2.7, 2.6, 2.5, 2.4, head, truffleruby ]
+        ruby: ${{ fromJson(needs.ruby-versions.outputs.versions) }}
         os: [ ubuntu-latest, macos-latest ]
     runs-on: ${{ matrix.os }}
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Ruby
       uses: ruby/setup-ruby@v1
       with:
         ruby-version: ${{ matrix.ruby }}
-        bundler-cache: true
+    - run: bundle install --jobs 4 --retry 3
     - name: Run test
       run: rake test

data/.gitignore

@@ -7,3 +7,4 @@
 /spec/reports/
 /tmp/
 Gemfile.lock
+/_site

data/Gemfile

@@ -6,4 +6,5 @@ group :development do
   gem "bundler"
   gem "rake"
   gem "test-unit"
+  gem "test-unit-ruby-core"
 end

data/README.md

@@ -1,6 +1,7 @@
 # URI
 
 [![CI](https://github.com/ruby/uri/actions/workflows/test.yml/badge.svg)](https://github.com/ruby/uri/actions/workflows/test.yml)
+[![Yard Docs](https://img.shields.io/badge/docs-exist-blue.svg)](https://ruby.github.io/uri/)
 
 URI is a module providing classes to handle Uniform Resource Identifiers [RFC2396](http://tools.ietf.org/html/rfc2396).
 

data/Rakefile

@@ -7,11 +7,12 @@ Rake::TestTask.new(:test) do |t|
   t.test_files = FileList["test/**/test_*.rb"]
 end
 
-task :sync_tool do
-  require 'fileutils'
-  FileUtils.cp "../ruby/tool/lib/test/unit/core_assertions.rb", "./test/lib"
-  FileUtils.cp "../ruby/tool/lib/envutil.rb", "./test/lib"
-  FileUtils.cp "../ruby/tool/lib/find_executable.rb", "./test/lib"
+require "rdoc/task"
+RDoc::Task.new do |doc|
+  doc.main   = "README.md"
+  doc.title  = "URI - handle Uniform Resource Identifiers"
+  doc.rdoc_files = FileList.new %w[lib README.md LICENSE.txt]
+  doc.rdoc_dir = "_site" # for github pages
 end
 
 task :default => :test

data/lib/uri/common.rb

@@ -68,16 +68,32 @@ module URI
   end
   private_constant :Schemes
 
+  # Registers the given +klass+ as the class to be instantiated
+  # when parsing a \URI with the given +scheme+:
   #
-  # Register the given +klass+ to be instantiated when parsing URLs with the given +scheme+.
-  # Note that currently only schemes which after .upcase are valid constant names
-  # can be registered (no -/+/. allowed).
+  #   URI.register_scheme('MS_SEARCH', URI::Generic) # => URI::Generic
+  #   URI.scheme_list['MS_SEARCH']                   # => URI::Generic
   #
+  # Note that after calling String#upcase on +scheme+, it must be a valid
+  # constant name.
   def self.register_scheme(scheme, klass)
     Schemes.const_set(scheme.to_s.upcase, klass)
   end
 
-  # Returns a Hash of the defined schemes.
+  # Returns a hash of the defined schemes:
+  #
+  #   URI.scheme_list
+  #   # =>
+  #   {"MAILTO"=>URI::MailTo,
+  #    "LDAPS"=>URI::LDAPS,
+  #    "WS"=>URI::WS,
+  #    "HTTP"=>URI::HTTP,
+  #    "HTTPS"=>URI::HTTPS,
+  #    "LDAP"=>URI::LDAP,
+  #    "FILE"=>URI::File,
+  #    "FTP"=>URI::FTP}
+  #
+  # Related: URI.register_scheme.
   def self.scheme_list
     Schemes.constants.map { |name|
       [name.to_s.upcase, Schemes.const_get(name)]
@@ -88,9 +104,21 @@ module URI
   private_constant :INITIAL_SCHEMES
   Ractor.make_shareable(INITIAL_SCHEMES) if defined?(Ractor)
 
+  # Returns a new object constructed from the given +scheme+, +arguments+,
+  # and +default+:
+  #
+  # - The new object is an instance of <tt>URI.scheme_list[scheme.upcase]</tt>.
+  # - The object is initialized by calling the class initializer
+  #   using +scheme+ and +arguments+.
+  #   See URI::Generic.new.
+  #
+  # Examples:
   #
-  # Construct a URI instance, using the scheme to detect the appropriate class
-  # from +URI.scheme_list+.
+  #   values = ['john.doe', 'www.example.com', '123', nil, '/forum/questions/', nil, 'tag=networking&order=newest', 'top']
+  #   URI.for('https', *values)
+  #   # => #<URI::HTTPS https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
+  #   URI.for('foo', *values, default: URI::HTTP)
+  #   # => #<URI::HTTP foo://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
   #
   def self.for(scheme, *arguments, default: Generic)
     const_name = scheme.to_s.upcase
@@ -121,95 +149,49 @@ module URI
   #
   class BadURIError < Error; end
 
-  #
-  # == Synopsis
-  #
-  #   URI::split(uri)
-  #
-  # == Args
-  #
-  # +uri+::
-  #   String with URI.
-  #
-  # == Description
-  #
-  # Splits the string on following parts and returns array with result:
-  #
-  # * Scheme
-  # * Userinfo
-  # * Host
-  # * Port
-  # * Registry
-  # * Path
-  # * Opaque
-  # * Query
-  # * Fragment
-  #
-  # == Usage
-  #
-  #   require 'uri'
-  #
-  #   URI.split("http://www.ruby-lang.org/")
-  #   # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil]
+  # Returns a 9-element array representing the parts of the \URI
+  # formed from the string +uri+;
+  # each array element is a string or +nil+:
+  #
+  #   names = %w[scheme userinfo host port registry path opaque query fragment]
+  #   values = URI.split('https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top')
+  #   names.zip(values)
+  #   # =>
+  #   [["scheme", "https"],
+  #    ["userinfo", "john.doe"],
+  #    ["host", "www.example.com"],
+  #    ["port", "123"],
+  #    ["registry", nil],
+  #    ["path", "/forum/questions/"],
+  #    ["opaque", nil],
+  #    ["query", "tag=networking&order=newest"],
+  #    ["fragment", "top"]]
   #
   def self.split(uri)
     RFC3986_PARSER.split(uri)
   end
 
+  # Returns a new \URI object constructed from the given string +uri+:
   #
-  # == Synopsis
-  #
-  #   URI::parse(uri_str)
-  #
-  # == Args
-  #
-  # +uri_str+::
-  #   String with URI.
-  #
-  # == Description
-  #
-  # Creates one of the URI's subclasses instance from the string.
-  #
-  # == Raises
-  #
-  # URI::InvalidURIError::
-  #   Raised if URI given is not a correct one.
+  #   URI.parse('https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top')
+  #   # => #<URI::HTTPS https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
+  #   URI.parse('http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top')
+  #   # => #<URI::HTTP http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
   #
-  # == Usage
-  #
-  #   require 'uri'
-  #
-  #   uri = URI.parse("http://www.ruby-lang.org/")
-  #   # => #<URI::HTTP http://www.ruby-lang.org/>
-  #   uri.scheme
-  #   # => "http"
-  #   uri.host
-  #   # => "www.ruby-lang.org"
-  #
-  # It's recommended to first ::escape the provided +uri_str+ if there are any
-  # invalid URI characters.
+  # It's recommended to first ::escape string +uri+
+  # if it may contain invalid URI characters.
   #
   def self.parse(uri)
     RFC3986_PARSER.parse(uri)
   end
 
+  # Merges the given URI strings +str+
+  # per {RFC 2396}[https://www.rfc-editor.org/rfc/rfc2396.html].
   #
-  # == Synopsis
-  #
-  #   URI::join(str[, str, ...])
+  # Each string in +str+ is converted to an
+  # {RFC3986 URI}[https://www.rfc-editor.org/rfc/rfc3986.html] before being merged.
   #
-  # == Args
-  #
-  # +str+::
-  #   String(s) to work with, will be converted to RFC3986 URIs before merging.
-  #
-  # == Description
-  #
-  # Joins URIs.
-  #
-  # == Usage
-  #
-  #   require 'uri'
+  # Examples:
   #
   #   URI.join("http://example.com/","main.rbx")
   #   # => #<URI::HTTP http://example.com/main.rbx>
@@ -254,7 +236,7 @@ module URI
   #   URI.extract("text here http://foo.example.org/bla and here mailto:test@example.com and here also.")
   #   # => ["http://foo.example.com/bla", "mailto:test@example.com"]
   #
-  def self.extract(str, schemes = nil, &block)
+  def self.extract(str, schemes = nil, &block) # :nodoc:
     warn "URI.extract is obsolete", uplevel: 1 if $VERBOSE
     DEFAULT_PARSER.extract(str, schemes, &block)
   end
@@ -291,7 +273,7 @@ module URI
   #     p $&
   #   end
   #
-  def self.regexp(schemes = nil)
+  def self.regexp(schemes = nil)# :nodoc:
     warn "URI.regexp is obsolete", uplevel: 1 if $VERBOSE
     DEFAULT_PARSER.make_regexp(schemes)
   end
@@ -314,40 +296,86 @@ module URI
   TBLDECWWWCOMP_['+'] = ' '
   TBLDECWWWCOMP_.freeze
 
-  # Encodes given +str+ to URL-encoded form data.
+  # Returns a URL-encoded string derived from the given string +str+.
+  #
+  # The returned string:
+  #
+  # - Preserves:
+  #
+  #   - Characters <tt>'*'</tt>, <tt>'.'</tt>, <tt>'-'</tt>, and <tt>'_'</tt>.
+  #   - Character in ranges <tt>'a'..'z'</tt>, <tt>'A'..'Z'</tt>,
+  #     and <tt>'0'..'9'</tt>.
+  #
+  #   Example:
   #
-  # This method doesn't convert *, -, ., 0-9, A-Z, _, a-z, but does convert SP
-  # (ASCII space) to + and converts others to %XX.
+  #     URI.encode_www_form_component('*.-_azAZ09')
+  #     # => "*.-_azAZ09"
   #
-  # If +enc+ is given, convert +str+ to the encoding before percent encoding.
+  # - Converts:
   #
-  # This is an implementation of
-  # https://www.w3.org/TR/2013/CR-html5-20130806/forms.html#url-encoded-form-data.
+  #   - Character <tt>' '</tt> to character <tt>'+'</tt>.
+  #   - Any other character to "percent notation";
+  #     the percent notation for character <i>c</i> is <tt>'%%%X' % c.ord</tt>.
   #
-  # See URI.decode_www_form_component, URI.encode_www_form.
+  #   Example:
+  #
+  #     URI.encode_www_form_component('Here are some punctuation characters: ,;?:')
+  #     # => "Here+are+some+punctuation+characters%3A+%2C%3B%3F%3A"
+  #
+  # Encoding:
+  #
+  # - If +str+ has encoding Encoding::ASCII_8BIT, argument +enc+ is ignored.
+  # - Otherwise +str+ is converted first to Encoding::UTF_8
+  #   (with suitable character replacements),
+  #   and then to encoding +enc+.
+  #
+  # In either case, the returned string has forced encoding Encoding::US_ASCII.
+  #
+  # Related: URI.encode_uri_component (encodes <tt>' '</tt> as <tt>'%20'</tt>).
   def self.encode_www_form_component(str, enc=nil)
     _encode_uri_component(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_, str, enc)
   end
 
-  # Decodes given +str+ of URL-encoded form data.
+  # Returns a string decoded from the given \URL-encoded string +str+.
+  #
+  # The given string is first encoded as Encoding::ASCII-8BIT (using String#b),
+  # then decoded (as below), and finally force-encoded to the given encoding +enc+.
+  #
+  # The returned string:
+  #
+  # - Preserves:
+  #
+  #   - Characters <tt>'*'</tt>, <tt>'.'</tt>, <tt>'-'</tt>, and <tt>'_'</tt>.
+  #   - Character in ranges <tt>'a'..'z'</tt>, <tt>'A'..'Z'</tt>,
+  #     and <tt>'0'..'9'</tt>.
+  #
+  #   Example:
+  #
+  #     URI.decode_www_form_component('*.-_azAZ09')
+  #     # => "*.-_azAZ09"
+  #
+  # - Converts:
+  #
+  #   - Character <tt>'+'</tt> to character <tt>' '</tt>.
+  #   - Each "percent notation" to an ASCII character.
   #
-  # This decodes + to SP.
+  #   Example:
   #
-  # See URI.encode_www_form_component, URI.decode_www_form.
+  #     URI.decode_www_form_component('Here+are+some+punctuation+characters%3A+%2C%3B%3F%3A')
+  #     # => "Here are some punctuation characters: ,;?:"
+  #
+  # Related: URI.decode_uri_component (preserves <tt>'+'</tt>).
   def self.decode_www_form_component(str, enc=Encoding::UTF_8)
     _decode_uri_component(/\+|%\h\h/, str, enc)
   end
 
-  # Encodes +str+ using URL encoding
-  #
-  # This encodes SP to %20 instead of +.
+  # Like URI.encode_www_form_component, except that <tt>' '</tt> (space)
+  # is encoded as <tt>'%20'</tt> (instead of <tt>'+'</tt>).
   def self.encode_uri_component(str, enc=nil)
     _encode_uri_component(/[^*\-.0-9A-Z_a-z]/, TBLENCURICOMP_, str, enc)
   end
 
-  # Decodes given +str+ of URL-encoded data.
-  #
-  # This does not decode + to SP.
+  # Like URI.decode_www_form_component, except that <tt>'+'</tt> is preserved.
   def self.decode_uri_component(str, enc=Encoding::UTF_8)
     _decode_uri_component(/%\h\h/, str, enc)
   end
@@ -372,33 +400,104 @@ module URI
   end
   private_class_method :_decode_uri_component
 
-  # Generates URL-encoded form data from given +enum+.
+  # Returns a URL-encoded string derived from the given
+  # {Enumerable}[https://docs.ruby-lang.org/en/master/Enumerable.html#module-Enumerable-label-Enumerable+in+Ruby+Classes]
+  # +enum+.
+  #
+  # The result is suitable for use as form data
+  # for an \HTTP request whose <tt>Content-Type</tt> is
+  # <tt>'application/x-www-form-urlencoded'</tt>.
+  #
+  # The returned string consists of the elements of +enum+,
+  # each converted to one or more URL-encoded strings,
+  # and all joined with character <tt>'&'</tt>.
+  #
+  # Simple examples:
+  #
+  #   URI.encode_www_form([['foo', 0], ['bar', 1], ['baz', 2]])
+  #   # => "foo=0&bar=1&baz=2"
+  #   URI.encode_www_form({foo: 0, bar: 1, baz: 2})
+  #   # => "foo=0&bar=1&baz=2"
+  #
+  # The returned string is formed using method URI.encode_www_form_component,
+  # which converts certain characters:
+  #
+  #   URI.encode_www_form('f#o': '/', 'b-r': '$', 'b z': '@')
+  #   # => "f%23o=%2F&b-r=%24&b+z=%40"
+  #
+  # When +enum+ is Array-like, each element +ele+ is converted to a field:
+  #
+  # - If +ele+ is an array of two or more elements,
+  #   the field is formed from its first two elements
+  #   (and any additional elements are ignored):
+  #
+  #     name = URI.encode_www_form_component(ele[0], enc)
+  #     value = URI.encode_www_form_component(ele[1], enc)
+  #     "#{name}=#{value}"
   #
-  # This generates application/x-www-form-urlencoded data defined in HTML5
-  # from given an Enumerable object.
+  #   Examples:
   #
-  # This internally uses URI.encode_www_form_component(str).
+  #     URI.encode_www_form([%w[foo bar], %w[baz bat bah]])
+  #     # => "foo=bar&baz=bat"
+  #     URI.encode_www_form([['foo', 0], ['bar', :baz, 'bat']])
+  #     # => "foo=0&bar=baz"
   #
-  # This method doesn't convert the encoding of given items, so convert them
-  # before calling this method if you want to send data as other than original
-  # encoding or mixed encoding data. (Strings which are encoded in an HTML5
-  # ASCII incompatible encoding are converted to UTF-8.)
+  # - If +ele+ is an array of one element,
+  #   the field is formed from <tt>ele[0]</tt>:
   #
-  # This method doesn't handle files.  When you send a file, use
-  # multipart/form-data.
+  #     URI.encode_www_form_component(ele[0])
   #
-  # This refers https://url.spec.whatwg.org/#concept-urlencoded-serializer
+  #   Example:
   #
-  #    URI.encode_www_form([["q", "ruby"], ["lang", "en"]])
-  #    #=> "q=ruby&lang=en"
-  #    URI.encode_www_form("q" => "ruby", "lang" => "en")
-  #    #=> "q=ruby&lang=en"
-  #    URI.encode_www_form("q" => ["ruby", "perl"], "lang" => "en")
-  #    #=> "q=ruby&q=perl&lang=en"
-  #    URI.encode_www_form([["q", "ruby"], ["q", "perl"], ["lang", "en"]])
-  #    #=> "q=ruby&q=perl&lang=en"
+  #     URI.encode_www_form([['foo'], [:bar], [0]])
+  #     # => "foo&bar&0"
+  #
+  # - Otherwise the field is formed from +ele+:
+  #
+  #     URI.encode_www_form_component(ele)
+  #
+  #   Example:
+  #
+  #     URI.encode_www_form(['foo', :bar, 0])
+  #     # => "foo&bar&0"
+  #
+  # The elements of an Array-like +enum+ may be mixture:
+  #
+  #   URI.encode_www_form([['foo', 0], ['bar', 1, 2], ['baz'], :bat])
+  #   # => "foo=0&bar=1&baz&bat"
+  #
+  # When +enum+ is Hash-like,
+  # each +key+/+value+ pair is converted to one or more fields:
+  #
+  # - If +value+ is
+  #   {Array-convertible}[https://docs.ruby-lang.org/en/master/implicit_conversion_rdoc.html#label-Array-Convertible+Objects],
+  #   each element +ele+ in +value+ is paired with +key+ to form a field:
+  #
+  #     name = URI.encode_www_form_component(key, enc)
+  #     value = URI.encode_www_form_component(ele, enc)
+  #     "#{name}=#{value}"
+  #
+  #   Example:
+  #
+  #     URI.encode_www_form({foo: [:bar, 1], baz: [:bat, :bam, 2]})
+  #     # => "foo=bar&foo=1&baz=bat&baz=bam&baz=2"
+  #
+  # - Otherwise, +key+ and +value+ are paired to form a field:
+  #
+  #     name = URI.encode_www_form_component(key, enc)
+  #     value = URI.encode_www_form_component(value, enc)
+  #     "#{name}=#{value}"
+  #
+  #   Example:
+  #
+  #     URI.encode_www_form({foo: 0, bar: 1, baz: 2})
+  #     # => "foo=0&bar=1&baz=2"
+  #
+  # The elements of a Hash-like +enum+ may be mixture:
+  #
+  #   URI.encode_www_form({foo: [0, 1], bar: 2})
+  #   # => "foo=0&foo=1&bar=2"
   #
-  # See URI.encode_www_form_component, URI.decode_www_form.
   def self.encode_www_form(enum, enc=nil)
     enum.map do |k,v|
       if v.nil?
@@ -419,22 +518,39 @@ module URI
     end.join('&')
   end
 
-  # Decodes URL-encoded form data from given +str+.
+  # Returns name/value pairs derived from the given string +str+,
+  # which must be an ASCII string.
+  #
+  # The method may be used to decode the body of Net::HTTPResponse object +res+
+  # for which <tt>res['Content-Type']</tt> is <tt>'application/x-www-form-urlencoded'</tt>.
+  #
+  # The returned data is an array of 2-element subarrays;
+  # each subarray is a name/value pair (both are strings).
+  # Each returned string has encoding +enc+,
+  # and has had invalid characters removed via
+  # {String#scrub}[https://docs.ruby-lang.org/en/master/String.html#method-i-scrub].
   #
-  # This decodes application/x-www-form-urlencoded data
-  # and returns an array of key-value arrays.
+  # A simple example:
   #
-  # This refers http://url.spec.whatwg.org/#concept-urlencoded-parser,
-  # so this supports only &-separator, and doesn't support ;-separator.
+  #   URI.decode_www_form('foo=0&bar=1&baz')
+  #   # => [["foo", "0"], ["bar", "1"], ["baz", ""]]
   #
-  #    ary = URI.decode_www_form("a=1&a=2&b=3")
-  #    ary                   #=> [['a', '1'], ['a', '2'], ['b', '3']]
-  #    ary.assoc('a').last   #=> '1'
-  #    ary.assoc('b').last   #=> '3'
-  #    ary.rassoc('a').last  #=> '2'
-  #    Hash[ary]             #=> {"a"=>"2", "b"=>"3"}
+  # The returned strings have certain conversions,
+  # similar to those performed in URI.decode_www_form_component:
+  #
+  #   URI.decode_www_form('f%23o=%2F&b-r=%24&b+z=%40')
+  #   # => [["f#o", "/"], ["b-r", "$"], ["b z", "@"]]
+  #
+  # The given string may contain consecutive separators:
+  #
+  #   URI.decode_www_form('foo=0&&bar=1&&baz=2')
+  #   # => [["foo", "0"], ["", ""], ["bar", "1"], ["", ""], ["baz", "2"]]
+  #
+  # A different separator may be specified:
+  #
+  #   URI.decode_www_form('foo=0--bar=1--baz', separator: '--')
+  #   # => [["foo", "0"], ["bar", "1"], ["baz", ""]]
   #
-  # See URI.decode_www_form_component, URI.encode_www_form.
   def self.decode_www_form(str, enc=Encoding::UTF_8, separator: '&', use__charset_: false, isindex: false)
     raise ArgumentError, "the input of #{self.name}.#{__method__} must be ASCII only string" unless str.ascii_only?
     ary = []
@@ -713,7 +829,15 @@ end # module URI
 module Kernel
 
   #
-  # Returns +uri+ converted to an URI object.
+  # Returns a \URI object derived from the given +uri+,
+  # which may be a \URI string or an existing \URI object:
+  #
+  #   # Returns a new URI.
+  #   uri = URI('http://github.com/ruby/ruby')
+  #   # => #<URI::HTTP http://github.com/ruby/ruby>
+  #   # Returns the given URI.
+  #   URI(uri)
+  #   # => #<URI::HTTP http://github.com/ruby/ruby>
   #
   def URI(uri)
     if uri.is_a?(URI::Generic)

data/lib/uri/generic.rb

@@ -1376,6 +1376,7 @@ module URI
       end
       str
     end
+    alias to_str to_s
 
     #
     # Compares two URIs.

data/lib/uri/rfc2396_parser.rb

@@ -497,8 +497,8 @@ module URI
       ret = {}
 
       # for URI::split
-      ret[:ABS_URI] = Regexp.new('\A\s*' + pattern[:X_ABS_URI] + '\s*\z', Regexp::EXTENDED)
-      ret[:REL_URI] = Regexp.new('\A\s*' + pattern[:X_REL_URI] + '\s*\z', Regexp::EXTENDED)
+      ret[:ABS_URI] = Regexp.new('\A\s*+' + pattern[:X_ABS_URI] + '\s*\z', Regexp::EXTENDED)
+      ret[:REL_URI] = Regexp.new('\A\s*+' + pattern[:X_REL_URI] + '\s*\z', Regexp::EXTENDED)
 
       # for URI::extract
       ret[:URI_REF]     = Regexp.new(pattern[:URI_REF])

data/lib/uri/rfc3986_parser.rb

@@ -1,9 +1,73 @@
-# frozen_string_literal: false
+# frozen_string_literal: true
 module URI
   class RFC3986_Parser # :nodoc:
     # URI defined in RFC3986
-    RFC3986_URI = /\A(?<URI>(?<scheme>[A-Za-z][+\-.0-9A-Za-z]*+):(?<hier-part>\/\/(?<authority>(?:(?<userinfo>(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*+)@)?(?<host>(?<IP-literal>\[(?:(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{1,4}?::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h++\.[!$&-.0-;=A-Z_a-z~]++))\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])*+))(?::(?<port>\d*+))?)(?<path-abempty>(?:\/(?<segment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*+))*+)|(?<path-absolute>\/(?:(?<segment-nz>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])++)(?:\/\g<segment>)*+)?)|(?<path-rootless>\g<segment-nz>(?:\/\g<segment>)*+)|(?<path-empty>))(?:\?(?<query>[^#]*+))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*+))?)\z/
-    RFC3986_relative_ref = /\A(?<relative-ref>(?<relative-part>\/\/(?<authority>(?:(?<userinfo>(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*+)@)?(?<host>(?<IP-literal>\[(?:(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{1,4}?::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:){,1}\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h++\.[!$&-.0-;=A-Z_a-z~]++))\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])++))?(?::(?<port>\d*+))?)(?<path-abempty>(?:\/(?<segment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*+))*+)|(?<path-absolute>\/(?:(?<segment-nz>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])++)(?:\/\g<segment>)*+)?)|(?<path-noscheme>(?<segment-nz-nc>(?:%\h\h|[!$&-.0-9;=@-Z_a-z~])++)(?:\/\g<segment>)*+)|(?<path-empty>))(?:\?(?<query>[^#]*+))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*+))?)\z/
+    HOST = %r[
+      (?<IP-literal>\[(?:
+          (?<IPv6address>
+            (?:\h{1,4}:){6}
+            (?<ls32>\h{1,4}:\h{1,4}
+            | (?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)
+                \.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>)
+            )
+          | ::(?:\h{1,4}:){5}\g<ls32>
+          | \h{1,4}?::(?:\h{1,4}:){4}\g<ls32>
+          | (?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>
+          | (?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>
+          | (?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>
+          | (?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>
+          | (?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}
+          | (?:(?:\h{1,4}:){,6}\h{1,4})?::
+          )
+        | (?<IPvFuture>v\h++\.[!$&-.0-9:;=A-Z_a-z~]++)
+        )\])
+    | \g<IPv4address>
+    | (?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])*+)
+    ]x
+
+    USERINFO = /(?:%\h\h|[!$&-.0-9:;=A-Z_a-z~])*+/
+
+    SCHEME = %r[[A-Za-z][+\-.0-9A-Za-z]*+].source
+    SEG = %r[(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/])].source
+    SEG_NC = %r[(?:%\h\h|[!$&-.0-9;=@A-Z_a-z~])].source
+    FRAGMENT = %r[(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/?])*+].source
+
+    RFC3986_URI = %r[\A
+    (?<seg>#{SEG}){0}
+    (?<URI>
+      (?<scheme>#{SCHEME}):
+      (?<hier-part>//
+        (?<authority>
+          (?:(?<userinfo>#{USERINFO.source})@)?
+          (?<host>#{HOST.source.delete(" \n")})
+          (?::(?<port>\d*+))?
+        )
+        (?<path-abempty>(?:/\g<seg>*+)?)
+      | (?<path-absolute>/((?!/)\g<seg>++)?)
+      | (?<path-rootless>(?!/)\g<seg>++)
+      | (?<path-empty>)
+      )
+      (?:\?(?<query>[^\#]*+))?
+      (?:\#(?<fragment>#{FRAGMENT}))?
+    )\z]x
+
+    RFC3986_relative_ref = %r[\A
+    (?<seg>#{SEG}){0}
+    (?<relative-ref>
+      (?<relative-part>//
+        (?<authority>
+          (?:(?<userinfo>#{USERINFO.source})@)?
+          (?<host>#{HOST.source.delete(" \n")}(?<!/))?
+          (?::(?<port>\d*+))?
+        )
+        (?<path-abempty>(?:/\g<seg>*+)?)
+      | (?<path-absolute>/\g<seg>*+)
+      | (?<path-noscheme>#{SEG_NC}++(?:/\g<seg>*+)?)
+      | (?<path-empty>)
+      )
+      (?:\?(?<query>[^#]*+))?
+      (?:\#(?<fragment>#{FRAGMENT}))?
+    )\z]x
     attr_reader :regexp
 
     def initialize
@@ -19,9 +83,9 @@ module URI
       uri.ascii_only? or
         raise InvalidURIError, "URI must be ascii only #{uri.dump}"
       if m = RFC3986_URI.match(uri)
-        query = m["query".freeze]
-        scheme = m["scheme".freeze]
-        opaque = m["path-rootless".freeze]
+        query = m["query"]
+        scheme = m["scheme"]
+        opaque = m["path-rootless"]
         if opaque
           opaque << "?#{query}" if query
           [ scheme,
@@ -32,35 +96,35 @@ module URI
             nil, # path
             opaque,
             nil, # query
-            m["fragment".freeze]
+            m["fragment"]
           ]
         else # normal
           [ scheme,
-            m["userinfo".freeze],
-            m["host".freeze],
-            m["port".freeze],
+            m["userinfo"],
+            m["host"],
+            m["port"],
             nil, # registry
-            (m["path-abempty".freeze] ||
-             m["path-absolute".freeze] ||
-             m["path-empty".freeze]),
+            (m["path-abempty"] ||
+             m["path-absolute"] ||
+             m["path-empty"]),
             nil, # opaque
             query,
-            m["fragment".freeze]
+            m["fragment"]
           ]
         end
       elsif m = RFC3986_relative_ref.match(uri)
         [ nil, # scheme
-          m["userinfo".freeze],
-          m["host".freeze],
-          m["port".freeze],
+          m["userinfo"],
+          m["host"],
+          m["port"],
           nil, # registry,
-          (m["path-abempty".freeze] ||
-           m["path-absolute".freeze] ||
-           m["path-noscheme".freeze] ||
-           m["path-empty".freeze]),
+          (m["path-abempty"] ||
+           m["path-absolute"] ||
+           m["path-noscheme"] ||
+           m["path-empty"]),
           nil, # opaque
-          m["query".freeze],
-          m["fragment".freeze]
+          m["query"],
+          m["fragment"]
         ]
       else
         raise InvalidURIError, "bad URI(is not URI?): #{uri.inspect}"
@@ -92,15 +156,15 @@ module URI
 
     def default_regexp # :nodoc:
       {
-        SCHEME: /\A[A-Za-z][A-Za-z0-9+\-.]*\z/,
-        USERINFO: /\A(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*\z/,
-        HOST: /\A(?:(?<IP-literal>\[(?:(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{,4}::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h+\.[!$&-.0-;=A-Z_a-z~]+))\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])*))\z/,
-        ABS_PATH: /\A\/(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*(?:\/(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*)*\z/,
-        REL_PATH: /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+(?:\/(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*)*\z/,
-        QUERY: /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*\z/,
-        FRAGMENT: /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*\z/,
-        OPAQUE: /\A(?:[^\/].*)?\z/,
-        PORT: /\A[\x09\x0a\x0c\x0d ]*\d*[\x09\x0a\x0c\x0d ]*\z/,
+        SCHEME: %r[\A#{SCHEME}\z]o,
+        USERINFO: %r[\A#{USERINFO}\z]o,
+        HOST: %r[\A#{HOST}\z]o,
+        ABS_PATH: %r[\A/#{SEG}*+\z]o,
+        REL_PATH: %r[\A(?!/)#{SEG}++\z]o,
+        QUERY: %r[\A(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/?])*+\z],
+        FRAGMENT: %r[\A#{FRAGMENT}\z]o,
+        OPAQUE: %r[\A(?:[^/].*)?\z],
+        PORT: /\A[\x09\x0a\x0c\x0d ]*+\d*[\x09\x0a\x0c\x0d ]*\z/,
       }
     end
 

data/lib/uri/version.rb

@@ -1,6 +1,6 @@
 module URI
   # :stopdoc:
-  VERSION_CODE = '001201'.freeze
+  VERSION_CODE = '001300'.freeze
   VERSION = VERSION_CODE.scan(/../).collect{|n| n.to_i}.join('.').freeze
   # :startdoc:
 end

data/rakelib/sync_tool.rake

@@ -0,0 +1,17 @@
+task :sync_tool, [:from] do |t, from: nil|
+  from ||= (File.identical?(__dir__, "rakelib") ? "../ruby/tool" : File.dirname(__dir__))
+
+  require 'fileutils'
+
+  {
+    "rakelib/sync_tool.rake" => "rakelib",
+    "lib/core_assertions.rb" => "test/lib",
+    "lib/envutil.rb" => "test/lib",
+    "lib/find_executable.rb" => "test/lib",
+    "lib/helper.rb" => "test/lib",
+  }.each do |src, dest|
+    FileUtils.mkpath(dest)
+    FileUtils.cp "#{from}/#{src}", dest
+  rescue Errno::ENOENT
+  end
+end

data/uri.gemspec

@@ -12,18 +12,26 @@ Gem::Specification.new do |spec|
 
   spec.summary       = %q{URI is a module providing classes to handle Uniform Resource Identifiers}
   spec.description   = spec.summary
-  spec.homepage      = "https://github.com/ruby/uri"
+
+  github_link        = "https://github.com/ruby/uri"
+
+  spec.homepage      = github_link
   spec.licenses      = ["Ruby", "BSD-2-Clause"]
 
-  spec.required_ruby_version = '>= 2.4'
+  spec.required_ruby_version = '>= 2.5'
 
-  spec.metadata["homepage_uri"] = spec.homepage
-  spec.metadata["source_code_uri"] = spec.homepage
+  spec.metadata = {
+    "bug_tracker_uri" => "#{github_link}/issues",
+    "changelog_uri" => "#{github_link}/releases",
+    "documentation_uri" => "https://ruby.github.io/uri/",
+    "homepage_uri" => spec.homepage,
+    "source_code_uri" => github_link
+  }
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
   spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
-    `git ls-files -z 2>/dev/null`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+    `git ls-files -z 2>#{IO::NULL}`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   end
   spec.bindir        = "exe"
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: uri
 version: !ruby/object:Gem::Version
-  version: 0.12.1
+  version: 0.13.0
 platform: ruby
 authors:
 - Akira Yamada
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-03-28 00:00:00.000000000 Z
+date: 2023-11-06 00:00:00.000000000 Z
 dependencies: []
 description: URI is a module providing classes to handle Uniform Resource Identifiers
 email:
@@ -18,6 +18,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".github/dependabot.yml"
+- ".github/workflows/gh-pages.yml"
 - ".github/workflows/test.yml"
 - ".gitignore"
 - Gemfile
@@ -41,12 +42,16 @@ files:
 - lib/uri/version.rb
 - lib/uri/ws.rb
 - lib/uri/wss.rb
+- rakelib/sync_tool.rake
 - uri.gemspec
 homepage: https://github.com/ruby/uri
 licenses:
 - Ruby
 - BSD-2-Clause
 metadata:
+  bug_tracker_uri: https://github.com/ruby/uri/issues
+  changelog_uri: https://github.com/ruby/uri/releases
+  documentation_uri: https://ruby.github.io/uri/
   homepage_uri: https://github.com/ruby/uri
   source_code_uri: https://github.com/ruby/uri
 post_install_message:
@@ -57,7 +62,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.4'
+      version: '2.5'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="