pairtree 0.1.0 → 0.3.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: bfe1638a3d904fd9b8d4f7ae4e6f3f09ff2cc421a66977e8b82a142e00c55daa
+  data.tar.gz: 581951758cc1e541080ddec8ec977caaffe54a2d4420a454c5bc0d4d9aff26bf
+SHA512:
+  metadata.gz: 4f6ed2b44ac4c133072e1589932bfa0dd2465ead35ede03fe6f487f319ca1a8517b4c0bbeeda521b3a313842a18aaf12c217dd9e00d735800ce832d6a33dc00c
+  data.tar.gz: 4b1c7550ce53c1161963e8a7d99663df9cd93c108fa4c7bb0be16b5edb8d8ef6a10852d6c4445ddee1b2da9ac2e72a9acde525d01d677a9cfd9328e9f4c17cee

data/.github/workflows/tests.yml

@@ -0,0 +1,22 @@
+name: Run Tests
+
+on: push
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    name: Ruby ${{ matrix.ruby }}
+    strategy:
+      matrix:
+        ruby: [2.7, 3.0, 3.1, 3.2]
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+        bundler-cache: true
+    - name: Run linter for Ruby
+      run: bundle exec standardrb
+    - name: Run tests
+      run: bundle exec rspec

data/.gitignore

@@ -10,6 +10,7 @@ doc
 
 # bundler
 .bundle
+vendor/
 
 # jeweler generated
 pkg
@@ -42,3 +43,5 @@ pkg
 #*.swp
 #
 Gemfile.lock
+
+.idea/

data/Gemfile

@@ -1,4 +1,10 @@
-source "http://rubygems.org"
+source "https://rubygems.org"
 
+# Specify your gem's dependencies in test.gemspec
 gemspec
-gem 'rcov', :platform => :mri_18
+
+group :development, :test do
+  gem "simplecov"
+  gem "standardrb"
+  gem "simplecov-lcov"
+end

data/README.md

@@ -0,0 +1,56 @@
+[![Tests](https://github.com/ruby-microservices/pairtree/actions/workflows/tests.yml/badge.svg)](https://github.com/ruby-microservices/pairtree/actions/workflows/tests.yml)
+[![Ruby Style Guide](https://img.shields.io/badge/code_style-standard-brightgreen.svg)](https://github.com/testdouble/standard)
+
+# pairtree
+
+Ruby implementation of the [Pairtree](https://www.ietf.org/archive/id/draft-kunze-pairtree-01.txt) specification from the California Digital Library.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'pairtree'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install pairtree
+
+## Usage
+
+```ruby
+  require 'pairtree'
+
+  # Initiate a tree
+  pairtree = Pairtree.at('./data', :prefix => 'pfx:', :create => true)
+  
+  # Create a ppath
+  obj = pairtree.mk('pfx:abc123def')
+  
+  # Access an existing ppath
+  obj = pairtree['pfx:abc123def']
+  obj = pairtree.get('pfx:abc123def')
+  
+  # ppaths are Dir instances with some File and Dir class methods mixed in
+  obj.read('content.xml')
+  => "<content/>"
+  obj.open('my_file.txt','w') { |io| io.write("Write text to file") }
+  obj.entries
+  => ["content.xml","my_file.txt"]
+  obj['*.xml']
+  => ["content.xml"]
+  obj.each { |file| ... }
+  obj.unlink('my_file.txt')
+  
+  # Delete a ppath and all its contents
+  pairtree.purge!('pfx:abc123def')
+```
+
+##  Copyright
+
+Copyright (c) 2010 Chris Beer. See LICENSE.txt for further details.

data/Rakefile

@@ -1,27 +1,37 @@
-Dir.glob('lib/tasks/*.rake').each { |r| import r }
-
-require 'bundler/gem_tasks'
-require 'rake'
-require 'rspec/core/rake_task'
-
+require "rubygems"
+require "bundler"
 begin
-  if RUBY_VERSION < "1.9"
-require 'rcov/rcovtask'
-desc "Generate code coverage"
-RSpec::Core::RakeTask.new(:rcov) do |t|
-  t.pattern = "./spec/**/*_spec.rb" # don't need this, it's default.
-  t.rcov = true
-  t.rcov_opts = ['--exclude', 'spec', '--exclude', 'gems']
-end
-  end
-rescue
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  warn e.message
+  warn "Run `bundle install` to install missing gems"
+  exit e.status_code
 end
 
-RSpec::Core::RakeTask.new(:spec)
+Bundler::GemHelper.install_tasks
 
-task :clean do
-  puts 'Cleaning old coverage.data'
-  FileUtils.rm('coverage.data') if(File.exists? 'coverage.data')
-end
+require "rake"
+require "rspec"
+require "rspec/core/rake_task"
+
+desc "Default: run specs."
+task default: :spec
 
-task :default => [:rcov, :doc]
+# Use yard to build docs
+begin
+  require "yard"
+  require "yard/rake/yardoc_task"
+  project_root = __dir__
+  doc_destination = File.join(project_root, "doc")
+
+  YARD::Rake::YardocTask.new(:doc) do |yt|
+    yt.files = Dir.glob(File.join(project_root, "lib", "**", "*.rb")) +
+      [File.join(project_root, "README.md")]
+    yt.options = ["--output-dir", doc_destination, "--readme", "README.md"]
+  end
+rescue LoadError
+  desc "Generate YARD Documentation"
+  task :doc do
+    abort "Please install the YARD gem to generate rdoc."
+  end
+end

data/lib/pairtree/identifier.rb

@@ -1,34 +1,51 @@
 module Pairtree
   class Identifier
-    ENCODE_REGEX = Regexp.compile("[\"*+,<=>?\\\\^|]|[^\x21-\x7e]", nil, 'u')
-    DECODE_REGEX = Regexp.compile("\\^(..)", nil, 'u')
+    ENCODE_REGEX = Regexp.compile("[\"*+,<=>?\\\\^|]|[^\x21-\x7e]", nil)
+    DECODE_REGEX = Regexp.compile("\\^(..)", nil)
 
     ##
     # Encode special characters within an identifier
     # @param [String] id The identifier
     def self.encode id
-      id.gsub(ENCODE_REGEX) { |c| char2hex(c) }.tr('/:.', '=+,')
+      id.gsub(ENCODE_REGEX) { |c| char2hex(c) }.tr("/:.", "=+,")
     end
 
     ##
     # Decode special characters within an identifier
     # @param [String] id The identifier
     def self.decode id
-      id.tr('=+,', '/:.').gsub(DECODE_REGEX) { |h| hex2char(h) } 
+      input = id.tr("=+,", "/:.").bytes.to_a
+      intermediate = []
+      while input.first
+        if input.first == 94
+          h = []
+          input.shift
+          h << input.shift
+          h << input.shift
+          intermediate << h.pack("c*").hex
+        else
+          intermediate << input.shift
+        end
+      end
+      result = intermediate.pack("c*")
+      if result.respond_to? :force_encoding
+        result.force_encoding("UTF-8")
+      end
+      result
     end
 
     ##
     # Convert a character to its pairtree hexidecimal representation
     # @param [Char] c The character to convert
     def self.char2hex c
-      c.unpack('H*')[0].scan(/../).map { |x| "^#{x}"}
+      c.unpack1("H*").scan(/../).map { |x| "^#{x}" }.join("")
     end
 
     ##
     # Convert a pairtree hexidecimal string to its character representation
     # @param [String] h The hexidecimal string to convert
     def self.hex2char h
-       '' << h.delete('^').hex
+      "" << h.delete("^").hex
     end
   end
 end

data/lib/pairtree/obj.rb

@@ -1,52 +1,51 @@
-module Pairtree  
+module Pairtree
   class Obj < ::Dir
-    
-    FILE_METHODS = [:atime, :open, :read, :file?, :directory?, :exist?, :exists?, :file?, :ftype, :lstat, 
+    FILE_METHODS = [:atime, :open, :read, :file?, :directory?, :exist?, :exists?, :file?, :ftype, :lstat,
       :mtime, :readable?, :size, :stat, :truncate, :writable?, :zero?]
     FILE_METHODS.each do |file_method|
-      define_method file_method do |fname,*args,&block|
-        File.send(file_method, File.join(self.path, fname), *args, &block)
+      define_method file_method do |fname, *args, &block|
+        File.send(file_method, File.join(path, fname), *args, &block)
       end
     end
 
     def delete *args
-      File.delete(*(prepend_filenames(args)))
+      File.delete(*prepend_filenames(args))
     end
     alias_method :unlink, :delete
 
     def link *args
-      File.link(*(prepend_filenames(args)))
+      File.link(*prepend_filenames(args))
     end
 
     def rename *args
-      File.rename(*(prepend_filenames(args)))
+      File.rename(*prepend_filenames(args))
     end
-    
+
     def utime atime, mtime, *args
-      File.utime(atime, mtime, *(prepend_filenames(args)))
+      File.utime(atime, mtime, *prepend_filenames(args))
     end
-    
+
     def entries
-      super - ['.','..']
+      super - [".", ".."]
     end
-    
+
     def each &block
-      super { |entry| yield(entry) unless entry =~ /^\.{1,2}$/ }
+      super { |entry| yield(entry) unless /^\.{1,2}$/.match?(entry) }
     end
-    
+
     def glob(string, flags = 0)
-      result = Dir.glob(File.join(self.path, string), flags) - ['.','..']
-      result.collect { |f| f.sub(%r{^#{self.path}/},'') }
+      result = Dir.glob(File.join(path, string), flags) - [".", ".."]
+      result.collect { |f| f.sub(%r{^#{path}/}, "") }
     end
-    
+
     def [](string)
       glob(string, 0)
     end
-    
+
     private
+
     def prepend_filenames(files)
-      files.collect { |fname| File.join(self.path, fname) }
+      files.collect { |fname| File.join(path, fname) }
     end
-    
   end
 end

data/lib/pairtree/path.rb

@@ -1,43 +1,41 @@
 module Pairtree
   class Path
     @@leaf_proc = lambda { |id| id }
-    
+
     def self.set_leaf value = nil, &block
-      if value.nil?
-        @@leaf_proc = block
+      @@leaf_proc = if value.nil?
+        block
+      elsif value.is_a?(Proc)
+        value
       else
-        if value.is_a?(Proc)
-          @@leaf_proc = value
-        else
-          @@leaf_proc = lambda { |id| value }
-        end
+        lambda { |id| value }
       end
     end
-    
+
     def self.leaf id
       if @@leaf_proc
         Pairtree::Identifier.encode(@@leaf_proc.call(id))
       else
-        ''
+        ""
       end
     end
-    
+
     def self.id_to_path id
-      path = File.join(Pairtree::Identifier.encode(id).scan(/..?/),self.leaf(id))
-      path.sub(%r{#{File::SEPARATOR}+$},'')
+      path = File.join(Pairtree::Identifier.encode(id).scan(/..?/), leaf(id))
+      path.sub(%r{#{File::SEPARATOR}+$}o, "")
     end
 
     def self.path_to_id ppath
       parts = ppath.split(File::SEPARATOR)
-      parts.pop if @@leaf_proc and parts.last.length > Root::SHORTY_LENGTH
+      parts.pop if @@leaf_proc && (parts.last.length > Root::SHORTY_LENGTH)
       Pairtree::Identifier.decode(parts.join)
     end
-    
+
     def self.remove! path
       FileUtils.remove_dir(path, true)
       parts = path.split(File::SEPARATOR)
       parts.pop
-      while parts.length > 0 and parts.last != 'pairtree_root'
+      while (parts.length > 0) && (parts.last != "pairtree_root")
         begin
           FileUtils.rmdir(parts.join(File::SEPARATOR))
           parts.pop

data/lib/pairtree/root.rb

@@ -1,10 +1,10 @@
-require 'fileutils'
+require "fileutils"
 module Pairtree
   class Root
     SHORTY_LENGTH = 2
 
     attr_reader :root, :prefix
-    
+
     ##
     # @param [String] root The pairtree_root directory within the pairtree home
     # @param [Hash] args Pairtree options
@@ -12,9 +12,9 @@ module Pairtree
     # @option args [String] :version (Pairtree::SPEC_VERSION) the version of the pairtree spec that this tree conforms to
     def initialize root, args = {}
       @root = root
-      
+
       @shorty_length = args.delete(:shorty_length) || SHORTY_LENGTH
-      @prefix = args.delete(:prefix) || ''
+      @prefix = args.delete(:prefix) || ""
 
       @options = args
     end
@@ -22,15 +22,15 @@ module Pairtree
     ##
     # Get a list of valid existing identifiers within the pairtree
     # @return [Array]
-    def list          
+    def list
       objects = []
       return [] unless File.directory? @root
 
       Dir.chdir(@root) do
-        possibles = Dir['**/?'] + Dir['**/??']
+        possibles = Dir["**/?"] + Dir["**/??"]
         possibles.each { |path|
           contents = Dir.entries(path).reject { |x| x =~ /^\./ }
-          objects << path unless contents.all? { |f| f.length <= @shorty_length and File.directory?(File.join(path, f)) }
+          objects << path unless contents.all? { |f| (f.length <= @shorty_length) && File.directory?(File.join(path, f)) }
         }
       end
       objects.map { |x| @prefix + Pairtree::Path.path_to_id(x) }
@@ -42,7 +42,7 @@ module Pairtree
     def path
       File.dirname(root)
     end
-    
+
     ##
     # Get the full path for a given identifier (whether it exists or not)
     # @param [String] id The full, prefixed identifier
@@ -51,7 +51,7 @@ module Pairtree
       unless id.start_with? @prefix
         raise IdentifierError, "Identifier must start with #{@prefix}"
       end
-      path_id = id[@prefix.length..-1]
+      path_id = id[@prefix.length..]
       File.join(@root, Pairtree::Path.id_to_path(path_id))
     end
 
@@ -62,7 +62,7 @@ module Pairtree
     def exists? id
       File.directory?(path_for(id))
     end
-    
+
     ##
     # Get an existing ppath
     # @param [String] id The full, prefixed identifier
@@ -71,7 +71,7 @@ module Pairtree
       Pairtree::Obj.new path_for(id)
     end
     alias_method :[], :get
-    
+
     ##
     # Create a new ppath
     # @param [String] id The full, prefixed identifier
@@ -80,7 +80,7 @@ module Pairtree
       FileUtils.mkdir_p path_for(id)
       get(id)
     end
-    
+
     ##
     # Delete a ppath
     # @param [String] id The full, prefixed identifier
@@ -89,7 +89,7 @@ module Pairtree
       if exists?(id)
         Pairtree::Path.remove!(path_for(id))
       end
-      not exists?(id)
+      !exists?(id)
     end
 
     ##
@@ -98,6 +98,5 @@ module Pairtree
     def pairtree_version
       @options[:version]
     end
-    
   end
 end

data/lib/pairtree.rb

@@ -1,17 +1,19 @@
-require 'pairtree/identifier'
-require 'pairtree/path'
-require 'pairtree/obj'
-require 'pairtree/root'
+require "pairtree/identifier"
+require "pairtree/path"
+require "pairtree/obj"
+require "pairtree/root"
 
-require 'fileutils'
+require "fileutils"
 
 module Pairtree
-  class IdentifierError < Exception; end
-  class PathError < Exception; end
-  class VersionMismatch < Exception; end
+  class IdentifierError < RuntimeError; end
+
+  class PathError < RuntimeError; end
+
+  class VersionMismatch < RuntimeError; end
 
   SPEC_VERSION = 0.1
-  
+
   ##
   # Instantiate a pairtree at a given path location
   # @param [String] path The path in which the pairtree resides
@@ -20,34 +22,34 @@ module Pairtree
   # @option args [String] :version (Pairtree::SPEC_VERSION) the version of the pairtree spec that this tree conforms to
   # @option args [Boolean] :create (false) if true, create the pairtree and its directory structure if it doesn't already exist
   def self.at path, args = {}
-    args = { :prefix => nil, :version => nil, :create => false }.merge(args)
+    args = {prefix: nil, version: nil, create: false}.merge(args)
     args[:version] ||= SPEC_VERSION
     args[:version] = args[:version].to_f
-    
-    root_path = File.join(path, 'pairtree_root')
-    prefix_file = File.join(path, 'pairtree_prefix')
+
+    root_path = File.join(path, "pairtree_root")
+    prefix_file = File.join(path, "pairtree_prefix")
     version_file = File.join(path, pairtree_version_filename(args[:version]))
-    existing_version_file = Dir[File.join(path, "pairtree_version*")].sort.last
-    
+    existing_version_file = Dir[File.join(path, "pairtree_version*")].max
+
     if args.delete(:create)
-      if File.exists?(path) and not File.directory?(path)
+      if File.exist?(path) && !File.directory?(path)
         raise PathError, "#{path} exists, but is not a valid pairtree root"
       end
       FileUtils.mkdir_p(root_path)
 
-      unless File.exists? prefix_file
-        File.open(prefix_file, 'w') { |f| f.write(args[:prefix].to_s) }
+      unless File.exist? prefix_file
+        File.write(prefix_file, args[:prefix].to_s)
       end
-      
+
       if existing_version_file
         if existing_version_file != version_file
-          stored_version = existing_version_file.scan(/([0-9]+)_([0-9]+)/).flatten.join('.').to_f
+          stored_version = existing_version_file.scan(/([0-9]+)_([0-9]+)/).flatten.join(".").to_f
           raise VersionMismatch, "Version #{args[:version]} specified, but #{stored_version} found."
         end
       else
         args[:version] ||= SPEC_VERSION
         version_file = File.join(path, pairtree_version_filename(args[:version]))
-        File.open(version_file, 'w') { |f| f.write %{This directory conforms to Pairtree Version #{args[:version]}. Updated spec: http://www.cdlib.org/inside/diglib/pairtree/pairtreespec.html} }
+        File.write(version_file, %(This directory conforms to Pairtree Version #{args[:version]}. Updated spec: http://www.cdlib.org/inside/diglib/pairtree/pairtreespec.html))
         existing_version_file = version_file
       end
     else
@@ -57,22 +59,25 @@ module Pairtree
     end
 
     stored_prefix = File.read(prefix_file)
-    unless args[:prefix].nil? or args[:prefix].to_s == stored_prefix
+    unless args[:prefix].nil? || (args[:prefix].to_s == stored_prefix)
       raise IdentifierError, "Specified prefix #{args[:prefix].inspect} does not match stored prefix #{stored_prefix.inspect}"
     end
     args[:prefix] = stored_prefix
 
-    stored_version = existing_version_file.scan(/([0-9]+)_([0-9]+)/).flatten.join('.').to_f
+    stored_version = existing_version_file.scan(/([0-9]+)_([0-9]+)/).flatten.join(".").to_f
     args[:version] ||= stored_version
     unless args[:version] == stored_version
       raise VersionMismatch, "Version #{args[:version]} specified, but #{stored_version} found."
     end
-        
-    Pairtree::Root.new(File.join(path, 'pairtree_root'), args)
+
+    Pairtree::Root.new(File.join(path, "pairtree_root"), args)
   end
 
-  private
-  def self.pairtree_version_filename(version)
-    "pairtree_version#{version.to_s.gsub(/\./,'_')}"
+  class << self
+    private
+
+    def pairtree_version_filename(version)
+      "pairtree_version#{version.to_s.tr(".", "_")}"
+    end
   end
 end

data/lib/tasks/rdoc.rake

@@ -1,21 +1,21 @@
 desc "Generate RDoc"
-task :doc => ['doc:generate']
+task doc: ["doc:generate"]
 
 namespace :doc do
-  project_root = File.expand_path(File.join(File.dirname(__FILE__), '..', '..'))
-  doc_destination = File.join(project_root, 'rdoc')
+  project_root = File.expand_path(File.join(File.dirname(__FILE__), "..", ".."))
+  doc_destination = File.join(project_root, "rdoc")
 
   begin
-    require 'yard'
-    require 'yard/rake/yardoc_task'
+    require "yard"
+    require "yard/rake/yardoc_task"
 
     YARD::Rake::YardocTask.new(:generate) do |yt|
-      yt.files   =  Dir.glob(File.join(project_root, 'lib', '*.rb')) + 
-                    Dir.glob(File.join(project_root, 'lib', '**', '*.rb')) +
-                   [ File.join(project_root, 'README.rdoc') ] +
-                   [ File.join(project_root, 'LICENSE') ]
-                   
-      yt.options = ['--output-dir', doc_destination, '--readme', 'README.rdoc']
+      yt.files = Dir.glob(File.join(project_root, "lib", "*.rb")) +
+        Dir.glob(File.join(project_root, "lib", "**", "*.rb")) +
+        [File.join(project_root, "README.rdoc")] +
+        [File.join(project_root, "LICENSE")]
+
+      yt.options = ["--output-dir", doc_destination, "--readme", "README.rdoc"]
     end
   rescue LoadError
     desc "Generate YARD Documentation"
@@ -26,7 +26,6 @@ namespace :doc do
 
   desc "Remove generated documenation"
   task :clean do
-    rm_r doc_destination if File.exists?(doc_destination)
+    rm_r doc_destination if File.exist?(doc_destination)
   end
-
-end
+end

data/pairtree.gemspec

@@ -1,24 +1,17 @@
 Gem::Specification.new do |s|
-  s.name             = %q{pairtree}
-  s.summary          = %q{Ruby Pairtree implementation}
-  s.version          = "0.1.0"
-  s.homepage         = %q{http://github.com/microservices/pairtree}
-  s.licenses         = ["Apache2"]
-  s.rubygems_version = %q{1.3.7}
+  s.name = "pairtree"
+  s.summary = "Ruby Pairtree implementation"
+  s.version = "0.3.0"
+  s.homepage = "http://github.com/ruby-microservices/pairtree"
+  s.licenses = ["Apache2"]
+  s.authors = ["Chris Beer, Bryan Hockey, Michael Slone, Aaron Elkiss"]
+  s.files = `git ls-files`.split("\n")
+  s.extra_rdoc_files = ["LICENSE.txt", "README.md"]
+  s.executables = `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) }
+  s.require_paths = ["lib"]
 
-  s.authors          = ["Chris Beer"]
-  s.date             = %q{2010-12-23}
-  s.email            = %q{chris@cbeer.info}
-  s.files            = `git ls-files`.split("\n")
-  s.test_files       = `git ls-files -- {test,spec,features}/*`.split("\n")
-  s.extra_rdoc_files = ["LICENSE.txt", "README.textile"]
-  s.executables      = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
-  s.require_paths    = ["lib"]
-
-
-  s.add_development_dependency "bundler", "~> 1.0.0"
-  s.add_development_dependency "rspec", ">= 2.0"
+  s.add_development_dependency "bundler"
+  s.add_development_dependency "rspec", ">= 3.12"
   s.add_development_dependency "yard"
-  s.add_development_dependency "RedCloth"
+  s.add_development_dependency "rake"
 end
-