Ascii85 0.9.0 → 1.0.0

data/History.txt

@@ -1,3 +1,10 @@
+=== 1.0.0 / 2009-12-25
+
+* 2 major enhancements
+
+  * Ruby 1.9 compatibility
+  * Added command-line en- and decoder
+
 === 0.9.0 / 2009-02-17
 
 * 1 major enhancement

data/Manifest.txt

@@ -2,5 +2,6 @@ History.txt
 Manifest.txt
 README.txt
 Rakefile
+bin/ascii85
 lib/ascii85.rb
 spec/ascii85_spec.rb

data/README.txt

@@ -2,6 +2,7 @@
 
 * http://ascii85.rubyforge.org
 
+
 == DESCRIPTION:
 
 Ascii85 is a simple gem that provides methods for encoding/decoding Adobe's
@@ -25,13 +26,29 @@ http://en.wikipedia.org/wiki/Ascii85 for more information about the format.
 In addition, Ascii85::encode can take a second parameter that specifies the
 length of the returned lines. The default is 80; use +false+ for unlimited.
 
-Ascii85::decode expects the input to be enclosed in <~ and ~>. It ignores
-everything outside of these.
+Ascii85::decode expects the input to be enclosed in <~ and ~> — it
+ignores everything outside of these. The output of Ascii85::decode
+will have the ASCII-8BIT encoding, so in Ruby 1.9 you may have to use
+<tt>String#force_encoding</tt> to correct the encoding.
+
+
+== Command-line utility
+
+This gem includes +ascii85+, a command-line utility modeled after +base64+ from
+the GNU coreutils. It can be used to encode/decode Ascii85 directly from the
+command-line:
+
+    Usage: ascii85 [OPTIONS] [FILE]
+    Encodes or decodes FILE or STDIN using Ascii85 and write to STDOUT.
+        -w, --wrap COLUMN                Wrap lines at COLUMN. Default is 80, use 0 for no wrapping
+        -d, --decode                     Decode the input
+        -h, --help                       Display this help and exit
+            --version                    Output version information
 
 
 == INSTALL:
 
-* sudo gem install ascii85
+* sudo gem install Ascii85
 
 
 == LICENSE:
@@ -40,20 +57,20 @@ everything outside of these.
 
 Copyright (c) 2009 Johannes Holzfuß
 
-Permission is hereby granted, free of charge, to any person obtaining a
-copy of this software and associated documentation files (the "Software"),
-to deal in the Software without restriction, including without limitation the
-rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
-sell copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+of the Software, and to permit persons to whom the Software is furnished to do
+so, subject to the following conditions:
 
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
 
 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/Rakefile

@@ -1,43 +1,23 @@
+# encoding: utf-8
 
 require 'rubygems'
-
 require 'hoe'
-require 'rake'
-require 'rake/clean'
-require 'rake/rdoctask'
-require 'spec/rake/spectask'
-
-require 'lib/ascii85.rb'
-
-
-# rspec
-
-desc "Run specs"
-Spec::Rake::SpecTask.new do |t|
-  t.spec_opts = ["--color"]
-end
-
-desc "Show specdoc"
-Spec::Rake::SpecTask.new('specdoc') do |t|
-  t.spec_opts = ["--color", "--format=specdoc"]
-end
 
+Hoe.spec 'Ascii85' do
 
-# Hoe
+  developer \
+    "Johannes Holzfuß",
+    "Drangon@gmx.de"
 
-Hoe.new('Ascii85', Ascii85::VERSION) do |p|
-  p.author  = "Johannes Holzfuß"
-  p.email   = "Drangon@gmx.de"
-  p.summary = "Ascii85 encoder/decoder"
+  summary
+    "Ascii85 encoder/decoder"
 
-  p.description = "Ascii85 provides methods to encode/decode Adobe's binary-to-text encoding of the same name."
+  description
+    "Ascii85 provides methods to encode/decode Adobe's binary-to-text encoding"
+    "of the same name."
 
-  p.remote_rdoc_dir = ''
+  self.url =
+    ["http://ascii85.rubyforge.org", "http://github.com/drangon/ascii85gem"]
 
-  p.testlib    = "spec"
-  p.test_globs = "spec/ascii85_spec.rb"
+  self.testlib = "spec"
 end
-
-
-# default task is spec
-task :default => :spec

data/bin/ascii85

@@ -0,0 +1,82 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+#
+# A simple command-line tool to de- and encode Ascii85, modeled after `base64`
+# from the GNU Coreutils.
+#
+
+
+require "optparse"
+require File.join(File.dirname(__FILE__), '..', 'lib', 'ascii85')
+
+@options = {
+  :wrap   => 80,
+  :decode => false
+}
+
+ARGV.options do |opts|
+  opts.banner = "Usage: #{File.basename($PROGRAM_NAME)} [OPTIONS] [FILE]\n" +
+                "Encodes or decodes FILE or STDIN using Ascii85 and write to STDOUT."
+
+
+  opts.on( "-w", "--wrap COLUMN", Integer,
+          "Wrap lines at COLUMN. Default is 80, use 0 for no wrapping") do |opt|
+
+    @options[:wrap] = opt.abs
+    @options[:wrap] = false if opt.zero?
+  end
+
+  opts.on( "-d", "--decode", "Decode the input") do
+    @options[:decode] = true
+  end
+
+  opts.on( "-h", "--help", "Display this help and exit") do
+    puts opts
+    exit
+  end
+
+  opts.on( "--version", "Output version information") do |opt|
+    puts "Ascii85 v#{Ascii85::VERSION},\nwritten by Johannes Holzfuß"
+    exit
+  end
+
+  remaining_args = opts.parse!
+
+  case remaining_args.size
+  when 0
+    @options[:file] = '-'
+  when 1
+    @options[:file] = remaining_args.first
+  else
+    abort "Superfluous operand(s): \"#{remaining_args.join('", "')}\""
+  end
+
+end
+
+if @options[:file] == '-'
+  $stdin.binmode
+  @input = $stdin.read
+else
+  unless File.exists?(@options[:file])
+    abort "File not found: \"#{@options[:file]}\""
+  end
+
+  unless File.readable_real?(@options[:file])
+    abort "File is not readable: \"#{@options[:file]}\""
+  end
+
+  File.open(@options[:file], 'rb') do |f|
+    @input = f.read
+  end
+end
+
+if @options[:decode]
+  begin
+    print Ascii85::decode(@input)
+  rescue Ascii85::DecodingError => error
+    abort "Decoding Error: #{error.message.to_s}"
+  end
+else
+  print Ascii85::encode(@input, @options[:wrap])
+end

data/lib/ascii85.rb

@@ -1,3 +1,6 @@
+# encoding: utf-8
+
+
 #
 # Ascii85 is an implementation of Adobe's binary-to-text encoding of the same
 # name in pure Ruby.
@@ -12,13 +15,13 @@
 
 module Ascii85
   # The gem version number
-  VERSION = '0.9.0' # :nodoc:
+  VERSION = '1.0.0' # :nodoc:
 
   #
-  # Encodes the given String as Ascii85.
+  # Encodes the bytes of the given String as Ascii85.
   #
-  # If +wrap_lines+ evaluates to +false+, the output will be returned as a
-  # single long line. Otherwise #encode formats the output into lines of
+  # If +wrap_lines+ evaluates to +false+, the output will be returned as
+  # a single long line. Otherwise #encode formats the output into lines of
   # length +wrap_lines+ (minimum is 2).
   #
   #     Ascii85::encode("Ruby")
@@ -36,13 +39,21 @@ module Ascii85
   #
   def self.encode(str, wrap_lines = 80)
 
-    return '' if str.to_s.empty?
+    to_encode = str.to_s
+    return '' if to_encode.empty?
+
+    # Deal with multi-byte encodings
+    if to_encode.methods.include?(:bytesize)
+      input_size = to_encode.bytesize
+    else
+      input_size = to_encode.size
+    end
 
     # Compute number of \0s to pad the message with (0..3)
-    padding_length = (-str.to_s.length) % 4
+    padding_length = (-input_size) % 4
 
     # Extract big-endian integers
-    tuples = (str.to_s + ("\0" * padding_length)).unpack('N*')
+    tuples = (to_encode + ("\0" * padding_length)).unpack('N*')
 
     # Encode
     tuples.map! do |tuple|
@@ -51,7 +62,7 @@ module Ascii85
       else
         tmp = ""
         5.times do
-          tmp += ((tuple % 85) + 33).chr
+          tmp << ((tuple % 85) + 33).chr
           tuple /= 85
         end
         tmp.reverse
@@ -66,12 +77,9 @@ module Ascii85
     # Cut off the padding
     tuples[-1] = tuples[-1][0..(4 - padding_length)]
 
-    # Add start-marker and join into a String
-    result = '<~' + tuples.join
-
-    # If we don't need to wrap the lines to a certain length, add ~> and return
+    # If we don't need to wrap the lines, add delimiters and return
     if (!wrap_lines)
-      return result + '~>'
+      return '<~' + tuples.join + '~>'
     end
 
     # Otherwise we wrap the lines
@@ -79,15 +87,17 @@ module Ascii85
     line_length = [2, wrap_lines.to_i].max
 
     wrapped = []
-    0.step(result.length, line_length) do |index|
-      wrapped << result.slice(index, line_length)
+    to_wrap = '<~' + tuples.join
+
+    0.step(to_wrap.length, line_length) do |index|
+      wrapped << to_wrap.slice(index, line_length)
     end
 
-    # Add end-marker -- on a new line if necessary
+    # Add end-marker – on a new line if necessary
     if (wrapped.last.length + 2) > line_length
       wrapped << '~>'
     else
-      wrapped[-1] += '~>'
+      wrapped[-1] << '~>'
     end
 
     return wrapped.join("\n")
@@ -96,8 +106,9 @@ module Ascii85
   #
   # Searches through +str+ and decodes the _first_ Ascii85-String found.
   #
-  # #decode expects an Ascii85-encoded String enclosed in <~ and ~>. It will
-  # ignore all characters outside these markers.
+  # #decode expects an Ascii85-encoded String enclosed in <~ and ~> — it
+  # will ignore all characters outside these markers. The returned strings are
+  # always encoded as ASCII-8BIT.
   #
   #     Ascii85::decode("<~;KZGo~>")
   #     => "Ruby"
@@ -113,15 +124,32 @@ module Ascii85
   #
   def self.decode(str)
 
-    # Find the Ascii85 encoded data between <~ and ~>
-    input = str.to_s.match(/<~.*?~>/mn)
+    input = str.to_s
 
-    return '' if input.nil?
+    # Try to compile the regular expression for finding the input between
+    # the <~ and ~> delimiters. In order to work properly with different
+    # input encodings, the RegExp itself is re-encoded to the input encoding
+    # if possible. Thanks to Myrddin Emrys for suggesting this approach
+    # (http://is.gd/5x18O)
+    begin
+      regex = "<~(.*?)?~>"
+
+      if regex.methods.include?(:encode)
+        regex = regex.encode(input.encoding)
+      end
+      regex = Regexp.compile(regex, Regexp::MULTILINE)
+
+      # Find the actual data to be decoded
+      input = input.match(regex)
 
-    # Remove the delimiters
-    input = input.to_s[2..-3]
+    rescue EncodingError
+      raise ArgumentError, "Incompatible input encoding: #{str.encoding.inspect}"
+    end
+
+    return '' if input.nil?
 
-    return '' if input.empty?
+    # Get the matched data as String
+    input = input.captures.first
 
     # Decode
     result = []
@@ -182,9 +210,9 @@ module Ascii85
       count -= 1
       word += 85**(4 - count)
 
-      result += ((word >> 24) & 255).chr if count >= 1
-      result += ((word >> 16) & 255).chr if count >= 2
-      result += ((word >>  8) & 255).chr if count == 3
+      result << ((word >> 24) & 255).chr if count >= 1
+      result << ((word >> 16) & 255).chr if count >= 2
+      result << ((word >>  8) & 255).chr if count == 3
     end
 
     return result

data/spec/ascii85_spec.rb

@@ -6,6 +6,10 @@ require 'ascii85'
 
 describe Ascii85 do
 
+  before( :all ) do
+    @string_has_encoding = "String".methods.include?(:encoding)
+  end
+
   TEST_CASES = {
 
     ""          => "",
@@ -61,6 +65,15 @@ describe Ascii85 do
       end
     end
 
+    it "[Ruby 1.9] should encode Strings in different encodings correctly" do
+      if @string_has_encoding
+        input_EUC_JP  = 'どうもありがとうミスターロボット'.encode('EUC-JP')
+        input_Ascii85 = input_EUC_JP.force_encoding('ASCII-8BIT')
+
+        Ascii85::encode(input_EUC_JP).should == Ascii85::encode(input_Ascii85)
+      end
+    end
+
     it "should produce output lines no longer than specified" do
       test_str = '0123456789' * 30
 
@@ -105,13 +118,40 @@ describe Ascii85 do
 
     it "should decode all specified test-cases correctly" do
       TEST_CASES.each_pair do |decoded, input|
-        Ascii85::decode(input).should == decoded
+        if @string_has_encoding
+          Ascii85::decode(input).should == decoded.dup.force_encoding('ASCII-8BIT')
+        else
+          Ascii85::decode(input).should == decoded
+        end
+      end
+    end
+
+    it "[Ruby 1.9] should accept valid input in encodings other than the default" do
+      if @string_has_encoding
+        input = "Ragnarök  τέχνη  русский язык  I ♥ Ruby"
+        input_ascii85 = Ascii85::encode(input)
+
+        # Try to encode input_ascii85 in all possible encodings and see if we
+        # do the right thing in #decode.
+        Encoding.list.each do |encoding|
+          next if encoding.dummy?
+
+          to_test = input_ascii85.encode(encoding)
+
+          lambda {
+            Ascii85::decode(to_test).force_encoding('UTF-8').should == input
+          }.should_not raise_error
+        end
+
       end
     end
 
-    it "should ignore everything before/after the delimiter-pairs" do
+    it "should only process data within delimiters" do
       Ascii85::decode("Doesn't contain delimiters").should == ''
+      Ascii85::decode("<~~>").should == ''
       Ascii85::decode("FooBar<~z~>BazQux").should == ("\0" * 4)
+      Ascii85::decode("<~;KZGo~><~z~>").should == "Ruby"
+      Ascii85::decode("foo~>bar<~baz").should == ''
     end
 
     it "should ignore whitespace" do
@@ -119,6 +159,12 @@ describe Ascii85 do
       decoded.should == 'Antidisestablishmentarianism'
     end
 
+    it "[Ruby 1.9] should return ASCII-8BIT encoded strings" do
+      if @string_has_encoding
+        Ascii85::decode("<~;KZGo~>").encoding.name.should == "ASCII-8BIT"
+      end
+    end
+
     describe "Error conditions" do
 
       it "should raise DecodingError if it encounters a word >= 2**32" do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: Ascii85
 version: !ruby/object:Gem::Version 
-  version: 0.9.0
+  version: 1.0.0
 platform: ruby
 authors: 
 - "Johannes Holzfu\xC3\x9F"
@@ -29,7 +29,7 @@ cert_chain:
   5FGhYN16QZS8VKLApBtxxP9XmwFASMyJLNizTN2q6hCCy/MjoTzHWzodPaWm0Q==
   -----END CERTIFICATE-----
 
-date: 2009-02-17 00:00:00 +01:00
+date: 2009-12-25 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -40,12 +40,18 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 1.8.3
+        version: 2.4.0
     version: 
-description: Ascii85 provides methods to encode/decode Adobe's binary-to-text encoding of the same name.
-email: Drangon@gmx.de
-executables: []
-
+description: |-
+  Ascii85 is a simple gem that provides methods for encoding/decoding Adobe's
+  binary-to-text encoding of the same name.
+  
+  See http://www.adobe.com/products/postscript/pdfs/PLRM.pdf page 131 and
+  http://en.wikipedia.org/wiki/Ascii85 for more information about the format.
+email: 
+- Drangon@gmx.de
+executables: 
+- ascii85
 extensions: []
 
 extra_rdoc_files: 
@@ -57,10 +63,13 @@ files:
 - Manifest.txt
 - README.txt
 - Rakefile
+- bin/ascii85
 - lib/ascii85.rb
 - spec/ascii85_spec.rb
 has_rdoc: true
 homepage: http://ascii85.rubyforge.org
+licenses: []
+
 post_install_message: 
 rdoc_options: 
 - --main
@@ -82,9 +91,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: ascii85
-rubygems_version: 1.3.1
+rubygems_version: 1.3.5
 signing_key: 
-specification_version: 2
-summary: Ascii85 encoder/decoder
-test_files: 
-- spec/ascii85_spec.rb
+specification_version: 3
+summary: Ascii85 is a simple gem that provides methods for encoding/decoding Adobe's binary-to-text encoding of the same name
+test_files: []
+