xenon-http 0.0.4

data/xenon-http/lib/xenon/parsers/basic_rules.rb

@@ -0,0 +1,86 @@
+require 'parslet'
+
+module Xenon
+  module Parsers
+
+    # Parslet doesn't match sequence of sequences (i.e. [['foo', 'bar']]) as a sequence(:v) in transform
+    # rules so this is a little wrapper class that allows smuggling an array through the matcher rules,
+    # for example above would be [Tuple.new('foo', 'bar')], when no 'proper' class is required.
+    class Tuple
+      def initialize(*values)
+        @values = values
+      end
+
+      def to_a
+        @values
+      end
+    end
+
+    module BasicRules
+      include Parslet
+
+      # http://tools.ietf.org/html/rfc5234#appendix-B.1
+      rule(:alpha) { match(/[a-z]/i) }
+      rule(:bit) { match(/[01]/) }
+      rule(:char) { match(/[\u0001-\u007f]/) }
+      rule(:digit) { match(/[0-9]/) }
+      rule(:hexdig) { match(/[a-f0-9]/i)}
+      rule(:vchar) { match(/[\u0021-\u007e]/) }
+      rule(:alphanum) { alpha | digit }
+
+      rule(:sp) { str(' ') }
+      rule(:sp?) { sp.repeat }
+      rule(:htab) { str("\t") }
+      rule(:wsp) { sp | htab }
+      rule(:lwsp) { (crlf.maybe >> wsp).repeat }
+
+      rule(:cr) { str("\r") }
+      rule(:lf) { str("\n") }
+      rule(:crlf) { cr >> lf }
+      rule(:dquote) { str('"') }
+
+      # http://tools.ietf.org/html/rfc7230#section-3.2.3
+      rule(:ows) { wsp.repeat }
+      rule(:rws) { wsp.repeat(1) }
+      rule(:bws) { wsp.repeat }
+
+      # http://tools.ietf.org/html/rfc7230#section-3.2.6
+      rule(:tchar) { alpha | digit | match(/[!#\$%&'\*\+\-\.\^_`\|~]/) }
+      rule(:token) { tchar.repeat(1) }
+
+      # http://tools.ietf.org/html/rfc7231#section-7.1.1.1
+      rule(:day_name) { str('Mon') | str('Tue') | str('Wed') | str('Thu') | str('Fri') | str('Sat') | str('Sun') }
+      rule(:day) { digit.repeat(2) }
+      rule(:month) { (str('Jan') | str('Feb') | str('Mar') | str('Apr') | str('May') | str('Jun') | str('Jul') | str('Aug') | str('Sep') | str('Oct') | str('Nov') | str('Dec')) }
+      rule(:year) { digit.repeat(4) }
+      rule(:date1) { day >> sp >> month >> sp >> year }
+      rule(:gmt) { str('GMT') }
+      rule(:hour) { digit.repeat(2) }
+      rule(:minute) { digit.repeat(2) }
+      rule(:second) { digit.repeat(2) }
+      rule(:time_of_day) { hour >> str(':') >> minute >> str(':') >> second }
+      rule(:imf_fixdate) { day_name >> str(',') >> sp >> date1 >> sp >> time_of_day >> sp >> gmt }
+      rule(:day_name_l) { str('Monday') | str('Tuesday') | str('Wednesday') | str('Thursday') | str('Friday') | str('Saturday') | str('Sunday') }
+      rule(:year2) { digit.repeat(2) }
+      rule(:date2) { day >> str('-') >> month >> str('-') >> year2 }
+      rule(:rfc850_date) { day_name_l >> str(',') >> sp >> date2 >> sp >> time_of_day >> sp >> gmt }
+      rule(:day1) { sp >> digit }
+      rule(:date3) { month >> sp >> (day | day1) }
+      rule(:asctime_date) { day_name >> sp >> date3 >> sp >> time_of_day >> sp >> year }
+      rule(:obs_date) { rfc850_date | asctime_date }
+      rule(:http_date) { (imf_fixdate | obs_date).as(:http_date) }
+
+      # extras -- TODO: move these into header rules?
+      rule(:comma) { str(',') >> sp? }
+      rule(:semicolon) { str(';') >> sp? }
+    end
+
+    class BasicTransform < Parslet::Transform
+      rule(simple(:v)) { v.respond_to?(:str) ? v.str : v }
+
+      rule(quoted_string: simple(:qs)) { qs[1..-2].gsub(/\\(.)/, '\1') }
+      rule(http_date: simple(:str)) { Time.httpdate(str) }
+    end
+
+  end
+end

data/xenon-http/lib/xenon/parsers/header_rules.rb

@@ -0,0 +1,60 @@
+require 'xenon/quoted_string'
+require 'xenon/parsers/basic_rules'
+
+module Xenon
+  module Parsers
+
+    module HeaderRules
+      include Parslet, BasicRules
+
+      # http://tools.ietf.org/html/rfc7230#section-3.2.6
+      rule(:list_sep) { str(',') >> sp? }
+      rule(:param_sep) { str(';') >> sp? }
+      rule(:obs_text) { match(/[\u0080-\u00ff]/)}
+      rule(:qdtext) { htab | sp | match(/[\u0021\u0023-\u005b\u005d-\u007e]/) | obs_text }
+      rule(:quoted_pair) { str('\\') >> (htab | sp | vchar | obs_text) }
+      rule(:quoted_string) { (dquote >> (qdtext | quoted_pair).repeat >> dquote).as(:quoted_string) }
+      rule(:ctext) { htab | sp | match(/[\u0021-\u0027\u002a-\u005b\u005d-\u007e]/) | obs_text }
+      rule(:comment) { (str('(') >> (ctext | quoted_pair | comment).repeat >> str(')')).as(:comment) }
+
+      # http://tools.ietf.org/html/rfc7231#section-5.3.1
+      rule(:weight_value) { (digit >> (str('.') >> digit.repeat(0, 3)).maybe).as(:q) }
+      rule(:weight) { param_sep >> str('q') >> sp? >> str('=') >> sp? >> weight_value >> sp? }
+    end
+
+    module AuthHeaderRules
+      include Parslet, HeaderRules
+
+      rule(:token68) { ((alpha | digit | match(/[\-\._~\+\/]/)) >> str('=').repeat).repeat(1).as(:token) }
+      rule(:auth_scheme) { token.as(:auth_scheme) }
+      rule(:name) { token.as(:name) }
+      rule(:value) { token.as(:value) }
+      rule(:auth_param) { (name >> bws >> str('=') >> bws >> (token | quoted_string).as(:value)).as(:auth_param) }
+      rule(:auth_params) { (auth_param.maybe >> (ows >> comma >> ows >> auth_param).repeat).as(:auth_params) }
+    end
+
+    module ETagHeaderRules
+      include Parslet, HeaderRules
+
+      # http://tools.ietf.org/html/rfc7232#section-2.3
+      rule(:wildcard) { str('*').as(:wildcard) }
+      rule(:weak) { str('W/').as(:weak) }
+      rule(:etagc) { str('!') | match(/[\u0023-\u007e#-~]/) | obs_text }
+      rule(:opaque_tag) { dquote >> etagc.repeat.as(:opaque_tag) >> dquote }
+      rule(:etag) { (weak.maybe >> opaque_tag).as(:etag) }
+    end
+
+    class HeaderTransform < BasicTransform
+      using QuotedString
+
+      rule(quoted_string: simple(:qs)) { qs.unquote }
+      rule(comment: simple(:c)) { c.uncomment }
+    end
+
+    class ETagHeaderTransform < HeaderTransform
+      rule(etag: { opaque_tag: simple(:t), weak: simple(:w) }) { Xenon::ETag.new(t, weak: true) }
+      rule(etag: { opaque_tag: simple(:t) }) { Xenon::ETag.new(t) }
+    end
+
+  end
+end

data/xenon-http/lib/xenon/parsers/media_type.rb

@@ -0,0 +1,53 @@
+require 'xenon/parsers/basic_rules'
+
+module Xenon
+  module Parsers
+
+    # note this uses the rules from https://tools.ietf.org/html/rfc6838 not http://tools.ietf.org/html/rfc7231
+    # because the latter is slightly ambiguous, e.g. a token can include * so */json would parse correctly
+    module MediaTypeRules
+      include Parslet, BasicRules
+
+      rule(:restricted_name_first) { match(/[a-zA-Z0-9]/) }
+      rule(:restricted_name_chars) { match(/[a-zA-Z0-9!#\$&\-\^_\.\+]/).repeat(0, 126) }
+      rule(:restricted_name) { restricted_name_first >> restricted_name_chars }
+
+      rule(:type) { restricted_name.as(:type) }
+      rule(:slash) { str('/') }
+      rule(:subtype) { restricted_name.as(:subtype) >> sp? }
+
+      rule(:param_sep) { str(';') >> sp? }
+      rule(:param_name) { restricted_name.as(:param_name) >> sp? }
+      rule(:equals) { str('=') >> sp? }
+      rule(:param_value) { token.as(:param_value) >> sp? } # not quite correct but probably correct enough
+      rule(:param) { param_sep >> param_name >> (equals >> param_value).maybe >> sp? }
+      rule(:params) { param.repeat.as(:params) }
+
+      rule(:media_type) { (type >> slash >> subtype >> params).as(:media_type) >> sp? }
+
+      rule(:wildcard) { str('*') }
+      rule(:wild_media_range) { wildcard.as(:type) >> slash >> wildcard.as(:subtype) >> params }
+      rule(:root_media_range) { type >> slash >> (wildcard.as(:subtype) | subtype) >> params }
+      rule(:media_range) { (wild_media_range | root_media_range).as(:media_range) >> sp? }
+    end
+
+    class MediaType < Parslet::Parser
+      include MediaTypeRules
+      root(:media_type)
+    end
+
+    class MediaRange < Parslet::Parser
+      include MediaTypeRules
+      root(:media_range)
+    end
+
+    class MediaTypeTransform < Parslet::Transform
+      rule(param_name: simple(:n), param_value: simple(:v)) { [n.str, v.str] }
+      rule(param_name: simple(:n)) { [n.str, nil] }
+      rule(type: simple(:t), subtype: simple(:s), params: subtree(:p)) { { type: t.str, subtype: s.str, params: Hash[p] } }
+      rule(media_type: subtree(:mt)) { Xenon::MediaType.new(mt[:type], mt[:subtype], mt[:params])}
+      rule(media_range: subtree(:mr)) { Xenon::MediaRange.new(mr[:type], mr[:subtype], mr[:params])}
+    end
+
+  end
+end

data/xenon-http/lib/xenon/quoted_string.rb

@@ -0,0 +1,20 @@
+module Xenon
+  module QuotedString
+    refine String do
+      def quote
+        qs = gsub(/([\\"])/, '\\\\\1')
+        self == qs ? self : %{"#{qs}"}
+      end
+
+      def unquote
+      	qs = start_with?('"') && end_with?('"') ? self[1..-2] : self
+      	qs.gsub(/\\(.)/, '\1')
+      end
+
+      def uncomment
+      	qs = start_with?('(') && end_with?(')') ? self[1..-2] : self
+      	qs.gsub(/\\(.)/, '\1')
+      end
+    end
+  end
+end

data/xenon-http/spec/spec_helper.rb

@@ -0,0 +1,94 @@
+require "codeclimate-test-reporter"
+CodeClimate::TestReporter.start
+
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause
+# this file to always be loaded, without a need to explicitly require it in any
+# files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need
+# it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
+  #   - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end

data/xenon-http/spec/xenon/etag_spec.rb

@@ -0,0 +1,19 @@
+require 'xenon/etag'
+
+describe Xenon::ETag do
+
+  describe '::parse' do
+    it 'can parse a strong etag' do
+      etag = Xenon::ETag.parse('"xyzzy"')
+      expect(etag.opaque_tag).to eq 'xyzzy'
+      expect(etag).to be_strong
+    end
+
+    it 'can parse a weak etag' do
+      etag = Xenon::ETag.parse('W/"xyzzy"')
+      expect(etag.opaque_tag).to eq 'xyzzy'
+      expect(etag).to be_weak
+    end
+  end
+
+end

data/xenon-http/spec/xenon/headers/accept_charset_spec.rb

@@ -0,0 +1,31 @@
+require 'xenon/headers/accept_charset'
+
+describe Xenon::Headers::AcceptCharset do
+
+  context '::parse' do
+    it 'can parse a basic charset range' do
+      header = Xenon::Headers::AcceptCharset.parse('unicode-1-1;q=0.8')
+      expect(header.charset_ranges.size).to eq(1)
+      expect(header.charset_ranges[0].to_s).to eq('unicode-1-1; q=0.8')
+    end
+
+    it 'can parse the example from RFC 7231 § 5.3.3 with the right precedence' do
+      header = Xenon::Headers::AcceptCharset.parse('iso-8859-5, unicode-1-1;q=0.8')
+      expect(header.charset_ranges.size).to eq(2)
+      expect(header.charset_ranges[0].to_s).to eq('iso-8859-5')
+      expect(header.charset_ranges[1].to_s).to eq('unicode-1-1; q=0.8')
+    end
+  end
+
+  context '#merge' do
+    it 'can merge two headers with the right precedence' do
+      h1 = Xenon::Headers::AcceptCharset.parse('unicode-1-1;q=0.8')
+      h2 = Xenon::Headers::AcceptCharset.parse('iso-8859-5')
+      header = h1.merge(h2)
+      expect(header.charset_ranges.size).to eq(2)
+      expect(header.charset_ranges[0].to_s).to eq('iso-8859-5')
+      expect(header.charset_ranges[1].to_s).to eq('unicode-1-1; q=0.8')
+    end
+  end
+
+end

data/xenon-http/spec/xenon/headers/accept_encoding_spec.rb

@@ -0,0 +1,40 @@
+require 'xenon/headers/accept_encoding'
+
+describe Xenon::Headers::AcceptEncoding do
+
+  context '::parse' do
+    %w(identity compress x-compress deflate gzip x-gzip *).each do |cc|
+      it "can parse the #{cc} content coding" do
+        header = Xenon::Headers::AcceptEncoding.parse(cc)
+        expect(header.coding_ranges.size).to eq(1)
+        expect(header.coding_ranges[0].to_s).to eq(cc)
+      end
+    end
+
+    it 'can parse the fifth example from RFC 7231 § 5.3.4 with the right precedence' do
+      header = Xenon::Headers::AcceptEncoding.parse('gzip;q=1.0, identity; q=0.5, *;q=0')
+      expect(header.coding_ranges.size).to eq(3)
+      expect(header.coding_ranges[0].to_s).to eq('gzip')
+      expect(header.coding_ranges[1].to_s).to eq('identity; q=0.5')
+      expect(header.coding_ranges[2].to_s).to eq('*; q=0.0')
+    end
+
+    it 'parses an empty header as containing no codings' do
+      header = Xenon::Headers::AcceptEncoding.parse('')
+      expect(header.coding_ranges.size).to eq(0) 
+    end
+  end
+
+  context '#merge' do
+    it 'can merge two headers with the right precedence' do
+      h1 = Xenon::Headers::AcceptEncoding.parse('identity; q=0.5')
+      h2 = Xenon::Headers::AcceptEncoding.parse('gzip;q=1.0, *;q=0')
+      header = h1.merge(h2)
+      expect(header.coding_ranges.size).to eq(3)
+      expect(header.coding_ranges[0].to_s).to eq('gzip')
+      expect(header.coding_ranges[1].to_s).to eq('identity; q=0.5')
+      expect(header.coding_ranges[2].to_s).to eq('*; q=0.0')
+    end
+  end
+
+end

data/xenon-http/spec/xenon/headers/accept_language_spec.rb

@@ -0,0 +1,33 @@
+require 'xenon/headers/accept_language'
+
+describe Xenon::Headers::AcceptLanguage do
+
+  context '::parse' do
+    it 'can parse a basic language range' do
+      header = Xenon::Headers::AcceptLanguage.parse('en-gb;q=0.8')
+      expect(header.language_ranges.size).to eq(1)
+      expect(header.language_ranges[0].to_s).to eq('en-gb; q=0.8')
+    end
+
+    it 'can parse the example from RFC 7231 § 5.3.5 with the right precedence' do
+      header = Xenon::Headers::AcceptLanguage.parse('da, en-gb;q=0.8, en;q=0.7')
+      expect(header.language_ranges.size).to eq(3)
+      expect(header.language_ranges[0].to_s).to eq('da')
+      expect(header.language_ranges[1].to_s).to eq('en-gb; q=0.8')
+      expect(header.language_ranges[2].to_s).to eq('en; q=0.7')
+    end
+  end
+
+  context '#merge' do
+    it 'can merge two headers with the right precedence' do
+      h1 = Xenon::Headers::AcceptLanguage.parse('da, en;q=0.7')
+      h2 = Xenon::Headers::AcceptLanguage.parse('en-gb;q=0.8')
+      header = h1.merge(h2)
+      expect(header.language_ranges.size).to eq(3)
+      expect(header.language_ranges[0].to_s).to eq('da')
+      expect(header.language_ranges[1].to_s).to eq('en-gb; q=0.8')
+      expect(header.language_ranges[2].to_s).to eq('en; q=0.7')
+    end
+  end
+
+end