hrx 1.0.0

data/spec/parse_spec.rb

@@ -0,0 +1,346 @@
+# coding: utf-8
+# Copyright 2018 Google Inc
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+require 'hrx'
+
+require_relative 'validates_path'
+
+RSpec.describe HRX, ".parse" do
+  it "parses an empty file" do
+    expect(HRX::Archive.parse("").entries).to be_empty
+  end
+
+  it "converts the file to UTF-8" do
+    hrx = HRX::Archive.parse("<===> いか\n".encode("SJIS"))
+    expect(hrx.entries.first.path).to be == "いか"
+  end
+
+  it "requires the file to be convetible to UTF-8" do
+    expect do
+      HRX::Archive.parse("<===> \xc3\x28\n".b)
+    end.to raise_error(EncodingError)
+  end
+
+  context "with a single file" do
+    subject {HRX::Archive.parse(<<END)}
+<===> file
+contents
+END
+
+    it "parses one entry" do
+      expect(subject.entries.length).to be == 1
+    end
+
+    it "parses the filename" do
+      expect(subject.entries.first.path).to be == "file"
+    end
+
+    it "parses the contents" do
+      expect(subject.entries.first.content).to be == "contents\n"
+    end
+
+    it "parses contents without a newline" do
+      hrx = HRX::Archive.parse("<===> file\ncontents")
+      expect(hrx.entries.first.content).to be == "contents"
+    end
+
+    it "parses contents with boundary-like sequences" do
+      hrx = HRX::Archive.parse(<<END)
+<===> file
+<==>
+inline <===>
+<====>
+END
+      expect(hrx.entries.first.content).to be == <<END
+<==>
+inline <===>
+<====>
+END
+    end
+
+    context "with a comment" do
+      subject {HRX::Archive.parse(<<END)}
+<===>
+comment
+<===> file
+contents
+END
+
+      it "parses one entry" do
+        expect(subject.entries.length).to be == 1
+      end
+
+      it "parses the filename" do
+        expect(subject.entries.first.path).to be == "file"
+      end
+
+      it "parses the contents" do
+        expect(subject.entries.first.content).to be == "contents\n"
+      end
+
+      it "parses the comment" do
+        expect(subject.entries.first.comment).to be == "comment"
+      end
+    end
+  end
+
+  context "with multiple files" do
+    subject {HRX::Archive.parse(<<END)}
+<===> file 1
+contents 1
+
+<===> file 2
+contents 2
+END
+
+    it "parses two entries" do
+      expect(subject.entries.length).to be == 2
+    end
+
+    it "parses the first filename" do
+      expect(subject.entries.first.path).to be == "file 1"
+    end
+
+    it "parses the first contents" do
+      expect(subject.entries.first.content).to be == "contents 1\n"
+    end
+
+    it "parses the second filename" do
+      expect(subject.entries.last.path).to be == "file 2"
+    end
+
+    it "parses the second contents" do
+      expect(subject.entries.last.content).to be == "contents 2\n"
+    end
+
+    it "allows an explicit parent directory" do
+      hrx = HRX::Archive.parse(<<END)
+<===> dir/
+<===> dir/file
+contents
+END
+
+      expect(hrx.entries.last.content).to be == "contents\n"
+    end
+
+    it "parses contents without a newline" do
+      hrx = HRX::Archive.parse(<<END)
+<===> file 1
+contents 1
+<===> file 2
+contents 2
+END
+      expect(hrx.entries.first.content).to be == "contents 1"
+    end
+
+    it "parses contents with boundary-like sequences" do
+      hrx = HRX::Archive.parse(<<END)
+<===> file 1
+<==>
+inline <===>
+<====>
+
+<===> file 2
+contents
+END
+      expect(hrx.entries.first.content).to be == <<END
+<==>
+inline <===>
+<====>
+END
+    end
+
+    context "with a comment" do
+      subject {HRX::Archive.parse(<<END)}
+<===> file 1
+contents 1
+
+<===>
+comment
+<===> file 2
+contents 2
+END
+
+      it "parses two entries" do
+        expect(subject.entries.length).to be == 2
+      end
+
+      it "parses the first filename" do
+        expect(subject.entries.first.path).to be == "file 1"
+      end
+
+      it "parses the first contents" do
+        expect(subject.entries.first.content).to be == "contents 1\n"
+      end
+
+      it "parses the second filename" do
+        expect(subject.entries.last.path).to be == "file 2"
+      end
+
+      it "parses the second contents" do
+        expect(subject.entries.last.content).to be == "contents 2\n"
+      end
+
+      it "parses the comment" do
+        expect(subject.entries.last.comment).to be == "comment"
+      end
+    end
+  end
+
+  it "parses a file that only contains a comment" do
+    expect(HRX::Archive.parse(<<END).last_comment).to be == "contents\n"
+<===>
+contents
+END
+  end
+
+  it "parses a file that only contains a comment with boundary-like sequences" do
+    expect(HRX::Archive.parse(<<HRX).last_comment).to be == <<CONTENTS
+<===>
+<==>
+inline <===>
+<====>
+HRX
+<==>
+inline <===>
+<====>
+CONTENTS
+  end
+
+  context "with a file and a trailing comment" do
+    subject {HRX::Archive.parse(<<END)}
+<===> file
+contents
+
+<===>
+comment
+END
+
+    it "parses one entry" do
+      expect(subject.entries.length).to be == 1
+    end
+
+    it "parses the filename" do
+      expect(subject.entries.first.path).to be == "file"
+    end
+
+    it "parses the contents" do
+      expect(subject.entries.first.content).to be == "contents\n"
+    end
+
+    it "parses the trailing comment" do
+      expect(subject.last_comment).to be == "comment\n"
+    end
+  end
+
+  context "with a single directory" do
+    subject {HRX::Archive.parse("<===> dir/\n")}
+
+    it "parses one entry" do
+      expect(subject.entries.length).to be == 1
+    end
+
+    it "parses a directory" do
+      expect(subject.entries.first).to be_a(HRX::Directory)
+    end
+
+    it "parses the filename" do
+      expect(subject.entries.first.path).to be == "dir/"
+    end
+  end
+
+  it "serializes in source order" do
+    hrx = HRX::Archive.parse(<<END)
+<===> foo
+<===> dir/bar
+<===> baz
+<===> dir/qux
+END
+
+    expect(hrx.to_hrx).to be == <<END
+<===> foo
+<===> dir/bar
+<===> baz
+<===> dir/qux
+END
+  end
+
+  it "serializes with the source boundary" do
+    hrx = HRX::Archive.parse("<=> file\n")
+    expect(hrx.to_hrx).to be == "<=> file\n"
+  end
+
+  let(:constructor) {lambda {|path| HRX::Archive.parse("<===> #{path}\n")}}
+  include_examples "validates paths"
+
+  context "forbids an HRX file that" do
+    # Specifies that the given HRX archive, with the given human-readable
+    # description, can't be parsed.
+    def self.that(description, text, message)
+      it description do
+        expect {HRX::Archive.parse(text)}.to raise_error(HRX::ParseError, message)
+      end
+    end
+
+    that "doesn't start with a boundary", "file\n", /Expected boundary/
+    that "starts with an unclosed boundary", "<== file\n", /Expected boundary/
+    that "starts with an unopened boundary", "==> file\n", /Expected boundary/
+    that "starts with a malformed boundary", "<> file\n", /Expected boundary/
+    that "has a directory with contents", "<===> dir/\ncontents", /Expected boundary/
+
+    that "has duplicate files", "<=> file\n<=> file\n", /"file" defined twice/
+    that "has duplicate directories", "<=> dir/\n<=> dir/\n", %r{"dir/" defined twice}
+    that "has file with the same name as a directory", "<=> foo/\n<=> foo\n", /"foo" defined twice/
+    that "has file with the same name as an earlier implicit directory", "<=> foo/bar\n<=> foo\n", /"foo" defined twice/
+    that "has file with the same name as a later implicit directory", "<=> foo\n<=> foo/bar\n", /"foo" defined twice/
+
+    context "has a boundary that" do
+      that "isn't followed by a space", "<=>file\n", /Expected space/
+      that "isn't followed by a path", "<=> \n", /Expected a path/
+      that "has a file without a newline", "<=> file", /Expected newline/
+    end
+
+    context "has a middle boundary that" do
+      that "isn't followed by a space", "<=> file 1\n<=>file 2\n", /Expected space/
+      that "isn't followed by a path", "<=> file 1\n<=> \n", /Expected a path/
+      that "has a file without a newline", "<=> file 1\n<=> file", /Expected newline/
+    end
+
+    context "has multiple comments that" do
+      that "come before a file", <<END, /Expected space/
+<=>
+comment 1
+<=>
+comment 2
+<=> file
+END
+
+      that "come after a file", <<END, /Expected space/
+<=> file
+<=>
+comment 1
+<=>
+comment 2
+END
+
+      that "appear on their own", <<END, /Expected space/
+<=>
+comment 1
+<=>
+comment 2
+END
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,95 @@
+# Copyright 2018 Google Inc
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+require 'stringio'
+
+module Helpers
+  # Runs a block with warnings disabled.
+  def silence_warnings
+    old_stderr = $stderr
+    $stderr = StringIO.new
+    yield
+  ensure
+    $stderr = old_stderr if old_stderr
+  end
+
+  # Runs a block with `encoding` as Encoding.default_external.
+  def with_external_encoding(encoding)
+    old_encoding = Encoding.default_external
+    silence_warnings {Encoding.default_external = "iso-8859-1"}
+  ensure
+    silence_warnings {Encoding.default_external = old_encoding if old_encoding}
+  end
+end
+
+RSpec.configure do |config|
+  config.include Helpers
+
+  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
+
+  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
+
+  # This option will default to `:apply_to_host_groups` in RSpec 4 (and will
+  # have no way to turn it off -- the option exists only for backwards
+  # compatibility in RSpec 3). It causes shared context metadata to be
+  # inherited by the metadata hash of host groups and examples, rather than
+  # triggering implicit auto-inclusion in groups with matching metadata.
+  config.shared_context_metadata_behavior = :apply_to_host_groups
+
+  # Allows RSpec to persist some state between runs in order to support
+  # the `--only-failures` and `--next-failure` CLI options. We recommend
+  # you configure your source control system to ignore this file.
+  config.example_status_persistence_file_path = "spec/examples.txt"
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  #   - http://rspec.info/blog/2012/06/rspecs-new-expectation-syntax/
+  #   - http://www.teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://rspec.info/blog/2014/05/notable-changes-in-rspec-3/#zero-monkey-patching-mode
+  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
+
+  # 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

data/spec/validates_path.rb

@@ -0,0 +1,49 @@
+# coding: utf-8
+# Copyright 2018 Google Inc
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+RSpec.shared_examples "validates paths" do
+  # Specifies that the given `path`, described by `description`, is allowed.
+  def self.allows_a_path_that(description, path)
+    it "allows a path that #{description}" do
+      expect { constructor[path] }.not_to raise_error
+    end
+  end
+
+  # Specifies that the given `path`, described by `description`, is not allowed.
+  def self.forbids_a_path_that(description, path)
+    it "forbids a path that #{description}" do
+      expect { constructor[path] }.to raise_error(HRX::ParseError)
+    end
+  end
+
+  allows_a_path_that "contains one component", "foo"
+  allows_a_path_that "contains multiple components", "foo/bar/baz"
+  allows_a_path_that "contains three dots", "..."
+  allows_a_path_that "starts with a dot", ".foo"
+  allows_a_path_that "contains non-alphanumeric characters", '~`!@#$%^&*()_-+= {}[]|;"\'<,>.?'
+  allows_a_path_that "contains non-ASCII characters", "☃"
+
+  forbids_a_path_that "is empty", ""
+  forbids_a_path_that 'is "."', "."
+  forbids_a_path_that 'is ".."', ".."
+  forbids_a_path_that "is only a separator", "/"
+  forbids_a_path_that "begins with a separator", "/foo"
+  forbids_a_path_that "contains multiple separators in a row", "foo//bar"
+  forbids_a_path_that "contains an invalid component", "foo/../bar"
+
+  [*0x00..0x09, *0x0B..0x1F, 0x3A, 0x5C, 0x7F].each do |c|
+    forbids_a_path_that "contains U+00#{c.to_s(16).rjust(2, "0")}", "fo#{c.chr}o"
+  end
+end