bitarray 1.0.0 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: c79a60a3580af853940651ca520abd24f359fc97
-  data.tar.gz: 96cb2ffe5551ac793e33f3eb06563aadcc6cfd1d
+SHA256:
+  metadata.gz: 5a056ce9816063f7e51c6fce69fb88c4644336236545613d4224977a01c50df8
+  data.tar.gz: f9f05b2a142f7cea4f529f9ebfbf9e053f635bb75d4ba44a10bdb6a2864c3f0d
 SHA512:
-  metadata.gz: bcd93a192a22cf477b45cd582028a3cd60c090dd9cdfbfd5b507a86f4c996a1dede387926d34f0495441cb90b0d899c96d5bb9a34dc8b16b5e933794f0e89bf1
-  data.tar.gz: cb2b120ce2abe9242bfc07ac9f1dff0bff7aab271daabaaafca53f39a06be8ce690946575bc6c423e8258fbf99c284ab783301327c0495bb37477798a0def376
+  metadata.gz: 7373fc1fc97187412eee8e854839961b7647f880afbffa8d4f0e261830d214edc4626763a100dcd71a8ce4dd05c2892522594d63c6d21f95be7bc413afc26c87
+  data.tar.gz: f884ad42cba8ce15fa2c3810427f510028db459f14080ca9bda02f823b35d27e00769e941cb5232fb6e0220ddc494d55e00843e5186d4d96a41e5b250754cfc5

data/README.md

@@ -1,13 +1,13 @@
-# BitArray: A simple bit-array/bitfield library in pure Ruby
+# BitArray: Pure Ruby bit-array/bitfield library
 
-Basic, pure Ruby bit field. Works well for Bloom filters (the use case for which I originally wrote it).
+A simple, pure-Ruby 'bit field' object. Works well for Bloom filters (the use case for which I originally wrote it, although there are numerous good libraries for that task now).
 
-Originally written in 2007 and left without significant update until 2017, it has now been updated to work within a typical, modern Ruby environment while maintaining the same API.
+Despite its age, BitArray has been updated to work within a typical, modern Ruby environment, but is only 'mildly' maintained.
 
 ## Installation
 
 ```ruby
-gem install bitarray
+bundle add bitarray
 ```
 
 ## Examples
@@ -47,7 +47,25 @@ ba.total_set
 #=> 7
 ```
 
+Initializing `BitArray` with a custom field value:
+
+```ruby
+ba = BitArray.new(16, ["0000111111110000"].pack('B*'))
+ba.to_s # "1111000000001111"
+```
+
+`BitArray` by default stores the bits in reverse order for each byte. If for example, you are initializing `BitArray` with Redis raw value manipulated with `setbit` / `getbit` operations, you will need to tell `BitArray` to not reverse the bits in each byte using the `reverse_byte: false` option:
+
+```ruby
+ba = BitArray.new(16, ["0000111111110000"].pack('B*'), reverse_byte: false)
+ba.to_s # "0000111111110000"
+```
+
+
 ## History
+- 1.3 in 2022 (cleanups and a minor perf tweak)
+- 1.2 in 2018 (Added option to skip reverse the bits for each byte by @dalibor)
+- 1.1 in 2018 (fixed a significant bug)
 - 1.0 in 2017 (updated for modern Ruby, more efficient storage, and 10th birthday)
 - 0.0.1 in 2012 (original v5 released on GitHub)
 - v5 (added support for flags being on by default, instead of off)
@@ -60,6 +78,8 @@ ba.total_set
 
 Thanks to Michael Slade for encouraging me to update this library on its 10th birthday and for suggesting finally using String's getbyte and setbyte methods now that we're all on 1.9+ compatible implementations.
 
+Further thanks to @tdeo, @JoshuaSP, @dalibor, @yegct and @m1lt0n for pull requests.
+
 ## License
 
-MIT licensed. Copyright 2007-2017 Peter Cooper.
+MIT licensed. Copyright 2007-2022 Peter Cooper.

data/Rakefile

@@ -2,4 +2,10 @@ require "bundler/gem_tasks"
 require "rake/testtask"
 
 Rake::TestTask.new
+
 task :default => :test
+
+desc "Open an irb session to work with bitarray"
+task :console do
+  sh "irb -rubygems -I lib -r bitarray"
+end

data/lib/bitarray-array.rb

@@ -3,7 +3,7 @@ class BitArray
   attr_reader :field
   include Enumerable
 
-  VERSION = "1.0.0"
+  VERSION = "1.3.0"
   ELEMENT_WIDTH = 32
 
   def initialize(size, field = nil)
@@ -26,7 +26,8 @@ class BitArray
   end
 
   # Iterate over each bit
-  def each(&block)
+  def each
+    return to_enum unless block_given?
     @size.times { |position| yield self[position] }
   end
 
@@ -34,10 +35,17 @@ class BitArray
   def to_s
     @field.collect{|ea| ("%0#{ELEMENT_WIDTH}b" % ea).reverse}.join[0..@size-1]
   end
+  
+  # Iterate over each byte
+  def each_byte
+    return to_enum(:each_byte) unless block_given?
+    @field.each { |byte| yield byte }
+  end
 
   # Returns the total number of bits that are set
-  # (The technique used here is about 6 times faster than using each or inject direct on the bitfield)
+  # Use Brian Kernighan's way, see
+  # https://graphics.stanford.edu/~seander/bithacks.html#CountBitsSetKernighan
   def total_set
-    @field.inject(0) { |a, byte| a += byte & 1 and byte >>= 1 until byte == 0; a }
+    @field.each_byte.inject(0) { |a, byte| (a += 1; byte &= byte - 1) while byte > 0 ; a }
   end
 end

data/lib/bitarray.rb

@@ -3,40 +3,57 @@ class BitArray
   attr_reader :field
   include Enumerable
 
-  VERSION = "1.0.0"
+  VERSION = "1.3.0"
 
-  def initialize(size, field = nil)
+  def initialize(size, field = nil, reverse_byte: true)
     @size = size
-    @field = "\0" * (size / 8 + 1)
+    @field = field || "\0" * (size / 8 + 1)
+    @reverse_byte = reverse_byte
   end
 
   # Set a bit (1/0)
   def []=(position, value)
     if value == 1
-      @field.setbyte(position >> 3, @field.getbyte(position >> 3) | (1 << (position % 8)))
+      @field.setbyte(position >> 3, @field.getbyte(position >> 3) | (1 << (byte_position(position) % 8)))
     else
-      @field.setbyte(position >> 3, @field.getbyte(position >> 3) ^ (1 << (position % 8)))
+      @field.setbyte(position >> 3, @field.getbyte(position >> 3) & ~(1 << (byte_position(position) % 8)))
     end
   end
 
   # Read a bit (1/0)
   def [](position)
-    (@field.getbyte(position >> 3) & (1 << (position % 8))) > 0 ? 1 : 0
+    (@field.getbyte(position >> 3) & (1 << (byte_position(position) % 8))) > 0 ? 1 : 0
   end
 
   # Iterate over each bit
-  def each(&block)
+  def each
+    return to_enum(:each) unless block_given?
     @size.times { |position| yield self[position] }
   end
 
   # Returns the field as a string like "0101010100111100," etc.
   def to_s
-    @field.bytes.collect{|ea| ("%08b" % ea).reverse}.join[0, @size]
+    if @reverse_byte
+      @field.bytes.collect { |ea| ("%08b" % ea).reverse }.join[0, @size]
+    else
+      @field.bytes.collect { |ea| ("%08b" % ea) }.join[0, @size]
+    end
+  end
+  
+  # Iterates over each byte
+  def each_byte
+    return to_enum(:each_byte) unless block_given?
+    @field.bytes.each{ |byte| yield byte }
   end
 
   # Returns the total number of bits that are set
-  # (The technique used here is about 6 times faster than using each or inject direct on the bitfield)
+  # Use Brian Kernighan's way, see
+  # https://graphics.stanford.edu/~seander/bithacks.html#CountBitsSetKernighan
   def total_set
-    @field.bytes.inject(0) { |a, byte| a += byte & 1 and byte >>= 1 until byte == 0; a }
+    @field.each_byte.inject(0) { |a, byte| (a += 1; byte &= byte - 1) while byte > 0 ; a }
+  end
+
+  def byte_position(position)
+    @reverse_byte ? position : 7 - position
   end
 end

data/test/test_bitarray.rb

@@ -1,5 +1,5 @@
 require "minitest/autorun"
-require "bitarray"
+require_relative "../lib/bitarray"
 
 class TestBitArray < Minitest::Test
   def setup
@@ -30,15 +30,19 @@ class TestBitArray < Minitest::Test
 
   def test_multiple_setting
     1.upto(999) do |pos|
-      2.times { @public_ba[pos] = 1 }
-      assert_equal 1, @public_ba[pos]
+      2.times do
+        @public_ba[pos] = 1
+        assert_equal 1, @public_ba[pos]
+      end
     end
   end
 
   def test_multiple_unsetting
     1.upto(999) do |pos|
-      2.times { @public_ba[pos] = 0 }
-      assert_equal 0, @public_ba[pos]
+      2.times do
+        @public_ba[pos] = 0
+        assert_equal 0, @public_ba[pos]
+      end
     end
   end
 
@@ -48,10 +52,26 @@ class TestBitArray < Minitest::Test
 
   def test_to_s
     ba = BitArray.new(35)
-    [1, 5, 6, 7, 10, 16, 33].each{|i|ba[i] = 1}
+    [1, 5, 6, 7, 10, 16, 33].each { |i| ba[i] = 1}
     assert_equal "01000111001000001000000000000000010", ba.to_s
   end
 
+  def test_field
+    ba = BitArray.new(35)
+    [1, 5, 6, 7, 10, 16, 33].each { |i| ba[i] = 1}
+    assert_equal "1110001000000100000000010000000000000010", ba.field.unpack('B*')[0]
+  end
+
+  def test_initialize_with_field
+    ba = BitArray.new(15, ["0100011100100001"].pack('B*'))
+
+    assert_equal [0, 1, 2, 6, 8, 13], 0.upto(15).select { |i| ba[i] == 1 }
+
+    ba[2] = 1
+    ba[12] = 1
+    assert_equal [0, 1, 2, 6, 8, 12, 13], 0.upto(15).select { |i| ba[i] == 1 }
+  end
+
   def test_total_set
     ba = BitArray.new(10)
     ba[1] = 1
@@ -60,3 +80,27 @@ class TestBitArray < Minitest::Test
     assert_equal 3, ba.total_set
   end
 end
+
+class TestBitArrayWhenNonReversedByte < Minitest::Test
+  def test_to_s
+    ba = BitArray.new(35, nil, reverse_byte: true)
+    [1, 5, 6, 7, 10, 16, 33].each { |i| ba[i] = 1}
+    assert_equal "01000111001000001000000000000000010", ba.to_s
+  end
+
+  def test_field
+    ba = BitArray.new(35, nil, reverse_byte: false)
+    [1, 5, 6, 7, 10, 16, 33].each { |i| ba[i] = 1}
+    assert_equal "0100011100100000100000000000000001000000", ba.field.unpack('B*')[0]
+  end
+
+  def test_initialize_with_field
+    ba = BitArray.new(15, ["0100011100100001"].pack('B*'), reverse_byte: false)
+
+    assert_equal [1, 5, 6, 7, 10, 15], 0.upto(15).select { |i| ba[i] == 1 }
+
+    ba[2] = 1
+    ba[12] = 1
+    assert_equal [1, 2, 5, 6, 7, 10, 12, 15], 0.upto(15).select { |i| ba[i] == 1 }
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bitarray
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.3.0
 platform: ruby
 authors:
 - Peter Cooper
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2017-01-07 00:00:00.000000000 Z
+date: 2022-04-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -47,7 +47,6 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - Gemfile
-- Gemfile.lock
 - README.md
 - Rakefile
 - bitarray.gemspec
@@ -58,7 +57,7 @@ files:
 homepage: https://github.com/peterc/bitarray
 licenses: []
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -73,9 +72,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.8
-signing_key: 
+rubygems_version: 3.2.22
+signing_key:
 specification_version: 4
 summary: A simple, pure Ruby bit-array / bitfield implementation.
 test_files:

data/Gemfile.lock

@@ -1,21 +0,0 @@
-PATH
-  remote: .
-  specs:
-    bitarray (1.0.0)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    minitest (5.10.1)
-    rake (12.0.0)
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  bitarray!
-  minitest
-  rake
-
-BUNDLED WITH
-   1.13.7