hashdiff 0.3.4 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 284b7371148ba31499e35fdfb3783faced5a8498
-  data.tar.gz: 3d902c91f2d00eb00df4cb96d27f5d6c242e9ee8
+  metadata.gz: 204c04301ec7d5b755863a0ec7b9001930a569c1
+  data.tar.gz: c0bf2c27e34271b637da82792549104a5b0ca2cb
 SHA512:
-  metadata.gz: e80104dc13c931f44352337d0027fd774f8a54a67c2ae15b2870e05723c41aafbe00be06d5073078ccfcf44b320e3ae03693623f0d61cab95fa040671e708599
-  data.tar.gz: 8efef12e5b3ff1c9a78dfc7655f121211d91e6b7d62521d33a5376b202e31913da440e2754f5ae0a3f1cba7189e2006db033027786c7402410ecf5dac58d44f2
+  metadata.gz: 68f07faf7b58132dae314317cf90e1dae5549218d93c19be33df0460659d2e74a861f458c9f6401909ce78ca1b0cb649cc843e0a804a4dad70e3c824568bfd7c
+  data.tar.gz: ba2ff10babe7886c263cbac1c761a38e205880dc323199746ed6845762b462a08b7664f9f1159b5765751b020dfd38ac365fcec04e350d894f97df6b519f3c71

data/.rubocop.yml

@@ -0,0 +1,24 @@
+require: rubocop-rspec
+Metrics/PerceivedComplexity:
+  Enabled: false
+Metrics/CyclomaticComplexity:
+  Enabled: false
+Metrics/MethodLength:
+  Enabled: false
+Metrics/AbcSize:
+  Enabled: false
+Metrics/LineLength:
+  Enabled: false
+Metrics/ClassLength:
+  Enabled: false
+Metrics/BlockLength:
+  Enabled: false
+Metrics/ModuleLength:
+  Enabled: false
+Style/Documentation:
+  Enabled: false
+Style/FrozenStringLiteralComment:
+  Enabled: true
+  EnforcedStyle: always
+RSpec/ExampleLength:
+  Enabled: false

data/.travis.yml

@@ -1,10 +1,11 @@
 sudo: false
 language: ruby
+cache: bundler
 rvm:
-  - 1.9.3
   - 2.0.0
   - 2.1.10
-  - 2.2.6
-  - 2.3.3
-  - 2.4.0
-script: "bundle exec rake spec"
+  - 2.2.8
+  - 2.3.4
+  - 2.4.2
+  - 2.5.3
+  - 2.6.0

data/Gemfile

@@ -1,4 +1,6 @@
-source "http://rubygems.org"
+# frozen_string_literal: true
+
+source 'http://rubygems.org'
 gemspec
 
 group :test do

data/README.md

@@ -1,14 +1,17 @@
-# HashDiff [![Build Status](https://secure.travis-ci.org/liufengyun/hashdiff.png)](http://travis-ci.org/liufengyun/hashdiff) [![Gem Version](https://badge.fury.io/rb/hashdiff.png)](http://badge.fury.io/rb/hashdiff)
+# Hashdiff [![Build Status](https://secure.travis-ci.org/liufengyun/hashdiff.svg)](http://travis-ci.org/liufengyun/hashdiff) [![Gem Version](https://badge.fury.io/rb/hashdiff.svg)](http://badge.fury.io/rb/hashdiff)
 
-HashDiff is a ruby library to compute the smallest difference between two hashes.
+Hashdiff is a ruby library to compute the smallest difference between two hashes.
 
 It also supports comparing two arrays.
 
-HashDiff does not monkey-patch any existing class. All features are contained inside the `HashDiff` module.
+Hashdiff does not monkey-patch any existing class. All features are contained inside the `Hashdiff` module.
 
 **Docs**: [Documentation](http://rubydoc.info/gems/hashdiff)
 
-## Why HashDiff?
+
+__WARNING__: Don't use the library for comparing large arrays, say ~10K (see #49).
+
+## Why Hashdiff?
 
 Given two Hashes A and B, sometimes you face the question: what's the smallest modification that can be made to change A into B?
 
@@ -18,7 +21,7 @@ An algorithm that responds to this question has to do following:
 * Compute recursively -- Arrays and Hashes may be nested arbitrarily in A or B.
 * Compute the smallest change -- it should recognize similar child Hashes or child Arrays between A and B.
 
-HashDiff answers the question above using an opinionated approach:
+Hashdiff answers the question above using an opinionated approach:
 
 * Hash can be represented as a list of (dot-syntax-path, value) pairs. For example, `{a:[{c:2}]}` can be represented as `["a[0].c", 2]`.
 * The change set can be represented using the dot-syntax representation. For example, `[['-', 'b.x', 3], ['~', 'b.z', 45, 30], ['+', 'b.y', 3]]`.
@@ -43,7 +46,7 @@ Two simple hashes:
 a = {a:3, b:2}
 b = {}
 
-diff = HashDiff.diff(a, b)
+diff = Hashdiff.diff(a, b)
 diff.should == [['-', 'a', 3], ['-', 'b', 2]]
 ```
 
@@ -53,7 +56,7 @@ More complex hashes:
 a = {a:{x:2, y:3, z:4}, b:{x:3, z:45}}
 b = {a:{y:3}, b:{y:3, z:30}}
 
-diff = HashDiff.diff(a, b)
+diff = Hashdiff.diff(a, b)
 diff.should == [['-', 'a.x', 2], ['-', 'a.z', 4], ['-', 'b.x', 3], ['~', 'b.z', 45, 30], ['+', 'b.y', 3]]
 ```
 
@@ -63,7 +66,7 @@ Arrays in hashes:
 a = {a:[{x:2, y:3, z:4}, {x:11, y:22, z:33}], b:{x:3, z:45}}
 b = {a:[{y:3}, {x:11, z:33}], b:{y:22}}
 
-diff = HashDiff.best_diff(a, b)
+diff = Hashdiff.best_diff(a, b)
 diff.should == [['-', 'a[0].x', 2], ['-', 'a[0].z', 4], ['-', 'a[1].y', 22], ['-', 'b.x', 3], ['-', 'b.z', 45], ['+', 'b.y', 22]]
 ```
 
@@ -72,27 +75,28 @@ diff.should == [['-', 'a[0].x', 2], ['-', 'a[0].z', 4], ['-', 'a[1].y', 22], ['-
 patch example:
 
 ```ruby
-a = {a: 3}
-b = {a: {a1: 1, a2: 2}}
+a = {'a' => 3}
+b = {'a' => {'a1' => 1, 'a2' => 2}}
 
-diff = HashDiff.diff(a, b)
-HashDiff.patch!(a, diff).should == b
+diff = Hashdiff.diff(a, b)
+Hashdiff.patch!(a, diff).should == b
 ```
 
 unpatch example:
 
 ```ruby
-a = [{a: 1, b: 2, c: 3, d: 4, e: 5}, {x: 5, y: 6, z: 3}, 1]
-b = [1, {a: 1, b: 2, c: 3, e: 5}]
+a = [{'a' => 1, 'b' => 2, 'c' => 3, 'd' => 4, 'e' => 5}, {'x' => 5, 'y' => 6, 'z' => 3}, 1]
+b = [1, {'a' => 1, 'b' => 2, 'c' => 3, 'e' => 5}]
 
-diff = HashDiff.diff(a, b) # diff two array is OK
-HashDiff.unpatch!(b, diff).should == a
+diff = Hashdiff.diff(a, b) # diff two array is OK
+Hashdiff.unpatch!(b, diff).should == a
 ```
 
 ### Options
 
-There are six options available: `:delimiter`, `:similarity`,
-`:strict`, `:numeric_tolerance`, `:strip` and `:case_insensitive`.
+There are eight options available: `:delimiter`, `:similarity`,
+`:strict`, `:numeric_tolerance`, `:strip`, `:case_insensitive`, `:array_path`
+and `:use_lcs`
 
 #### `:delimiter`
 
@@ -102,7 +106,7 @@ You can specify `:delimiter` to be something other than the default dot. For exa
 a = {a:{x:2, y:3, z:4}, b:{x:3, z:45}}
 b = {a:{y:3}, b:{y:3, z:30}}
 
-diff = HashDiff.diff(a, b, :delimiter => '\t')
+diff = Hashdiff.diff(a, b, :delimiter => '\t')
 diff.should == [['-', 'a\tx', 2], ['-', 'a\tz', 4], ['-', 'b\tx', 3], ['~', 'b\tz', 45, 30], ['+', 'b\ty', 3]]
 ```
 
@@ -122,7 +126,7 @@ The :numeric_tolerance option allows for a small numeric tolerance.
 a = {x:5, y:3.75, z:7}
 b = {x:6, y:3.76, z:7}
 
-diff = HashDiff.diff(a, b, :numeric_tolerance => 0.1)
+diff = Hashdiff.diff(a, b, :numeric_tolerance => 0.1)
 diff.should == [["~", "x", 5, 6]]
 ```
 
@@ -134,22 +138,77 @@ The :strip option strips all strings before comparing.
 a = {x:5, s:'foo '}
 b = {x:6, s:'foo'}
 
-diff = HashDiff.diff(a, b, :comparison => { :numeric_tolerance => 0.1, :strip => true })
+diff = Hashdiff.diff(a, b, :comparison => { :numeric_tolerance => 0.1, :strip => true })
 diff.should == [["~", "x", 5, 6]]
 ```
 
 #### `:case_insensitive`
 
-The :case_insensitive option makes string comparisions ignore case.
+The :case_insensitive option makes string comparisons ignore case.
 
 ```ruby
 a = {x:5, s:'FooBar'}
 b = {x:6, s:'foobar'}
 
-diff = HashDiff.diff(a, b, :comparison => { :numeric_tolerance => 0.1, :case_insensitive => true })
+diff = Hashdiff.diff(a, b, :comparison => { :numeric_tolerance => 0.1, :case_insensitive => true })
 diff.should == [["~", "x", 5, 6]]
 ```
 
+#### `:array_path`
+
+The :array_path option represents the path of the diff in an array rather than
+a string. This can be used to show differences in between hash key types and
+is useful for `patch!` when used on hashes without string keys.
+
+```ruby
+a = {x:5}
+b = {'x'=>6}
+
+diff = Hashdiff.diff(a, b, :array_path => true)
+diff.should == [['-', [:x], 5], ['+', ['x'], 6]]
+```
+
+For cases where there are arrays in paths their index will be added to the path.
+```ruby
+a = {x:[0,1]}
+b = {x:[0,2]}
+
+diff = Hashdiff.diff(a, b, :array_path => true)
+diff.should == [["-", [:x, 1], 1], ["+", [:x, 1], 2]]
+```
+
+This shouldn't cause problems if you are comparing an array with a hash:
+
+```ruby
+a = {x:{0=>1}}
+b = {x:[1]}
+
+diff = Hashdiff.diff(a, b, :array_path => true)
+diff.should == [["~", [:x], {0=>1}, [1]]]
+```
+
+#### `:use_lcs`
+
+The :use_lcs option is used to specify whether a
+[Longest common subsequence](https://en.wikipedia.org/wiki/Longest_common_subsequence_problem)
+(LCS) algorithm is used to determine differences in arrays. This defaults to
+`true` but can be changed to `false` for significantly faster array comparisons
+(O(n) complexity rather than O(n<sup>2</sup>) for LCS).
+
+When :use_lcs is false the results of array comparisons have a tendency to
+show changes at indexes rather than additions and subtractions when :use_lcs is
+true.
+
+Note, currently the :similarity option has no effect when :use_lcs is false.
+
+```ruby
+a = {x: [0, 1, 2]}
+b = {x: [0, 2, 2, 3]}
+
+diff = Hashdiff.diff(a, b, :use_lcs => false)
+diff.should == [["~", "x[1]", 1, 2], ["+", "x[3]", 3]]
+```
+
 #### Specifying a custom comparison method
 
 It's possible to specify how the values of a key should be compared.
@@ -158,7 +217,7 @@ It's possible to specify how the values of a key should be compared.
 a = {a:'car', b:'boat', c:'plane'}
 b = {a:'bus', b:'truck', c:' plan'}
 
-diff = HashDiff.diff(a, b) do |path, obj1, obj2|
+diff = Hashdiff.diff(a, b) do |path, obj1, obj2|
   case path
   when  /a|b|c/
     obj1.length == obj2.length
@@ -174,7 +233,7 @@ The yielded params of the comparison block is `|path, obj1, obj2|`, in which pat
 a = {a:'car', b:['boat', 'plane'] }
 b = {a:'bus', b:['truck', ' plan'] }
 
-diff = HashDiff.diff(a, b) do |path, obj1, obj2|
+diff = Hashdiff.diff(a, b) do |path, obj1, obj2|
   case path
   when 'b[*]'
     obj1.length == obj2.length
@@ -186,6 +245,8 @@ diff.should == [["~", "a", "car", "bus"], ["~", "b[1]", "plane", " plan"], ["-",
 
 When a comparison block is given, it'll be given priority over other specified options. If the block returns value other than `true` or `false`, then the two values will be compared with other specified options.
 
+When used in conjunction with the `array_path` option, the path passed in as an argument will be an array. When determining the ordering of an array a key of `"*"` will be used in place of the `key[*]` field. It is possible, if you have hashes with integer or `"*"` keys, to have problems distinguishing between arrays and hashes - although this shouldn't be an issue unless your data is very difficult to predict and/or your custom rules are very specific.
+
 #### Sorting arrays before comparison
 
 An order difference alone between two arrays can create too many diffs to be useful. Consider sorting them prior to diffing.
@@ -194,14 +255,18 @@ An order difference alone between two arrays can create too many diffs to be use
 a = {a:'car', b:['boat', 'plane'] }
 b = {a:'car', b:['plane', 'boat'] }
 
-HashDiff.diff(a, b) => [["+", "b[0]", "plane"], ["-", "b[2]", "plane"]]
+Hashdiff.diff(a, b) => [["+", "b[0]", "plane"], ["-", "b[2]", "plane"]]
 
 b[:b].sort!
 
-HashDiff.diff(a, b) => []
+Hashdiff.diff(a, b) => []
 ```
 
-## License
+## Maintainers
+
+- Krzysztof Rybka ([@krzysiek1507](https://github.com/krzysiek1507))
+- Fengyun Liu ([@liufengyun](https://github.com/liufengyun))
 
-HashDiff is distributed under the MIT-LICENSE.
+## License
 
+Hashdiff is distributed under the MIT-LICENSE.

data/Rakefile

@@ -1,13 +1,18 @@
-$:.push File.expand_path("../lib", __FILE__)
+# frozen_string_literal: true
+
+$LOAD_PATH.push File.expand_path('lib', __dir__)
+
+require 'rubocop/rake_task'
 
 require 'bundler'
 Bundler::GemHelper.install_tasks
 
 require 'rspec/core/rake_task'
 
-task :default => :spec
+RuboCop::RakeTask.new
+
+task default: %w[spec rubocop]
 
 RSpec::Core::RakeTask.new(:spec) do |spec|
-  spec.pattern = "./spec/**/*_spec.rb"
+  spec.pattern = './spec/**/*_spec.rb'
 end
-

data/changelog.md

@@ -1,8 +1,34 @@
 # Change Log
 
+## v0.4.0 2019-05-28
+
+* refactoring (#56 #57 #59 #61 krzysiek1507)
+* fix typo in README (#64 @pboling)
+* change HashDiff to Hashdiff (#65 @jfelchner)
+
+## v0.3.9 2019-04-22
+
+* Performance tweak (thanks @krzysiek1507: #51 #52 #53)
+
+## v0.3.8 2018-12-30
+
+* Add Rubocop and drops Ruby 1.9 support #47
+
+## v0.3.7 2017-10-08
+
+* remove 1.8.7 support from gemspec #39
+
+## v0.3.6 2017-08-22
+
+* add option `use_lcs` #35
+
+## v0.3.5 2017-08-06
+
+* add option `array_path` #34
+
 ## v0.3.4 2017-05-01
 
-* performance improvement of HashDiff#similar? #31
+* performance improvement of `#similar?` #31
 
 ## v0.3.2 2016-12-27
 
@@ -44,7 +70,7 @@
 ## v0.0.5 2012-7-1
 
 * fix a bug in judging whehter two objects are similiar.
-* add more spec test for HashDiff.best_diff
+* add more spec test for `.best_diff`
 
 ## v0.0.4 2012-6-24
 
@@ -57,4 +83,3 @@ For example, `diff({a:2, c:[4, 5]}, {a:2}) will generate following output:
 instead of following:
 
     [['-', 'c[0]', 4], ['-', 'c[1]', 5], ['-', 'c', []]]
-

data/hashdiff.gemspec

@@ -1,25 +1,40 @@
-$LOAD_PATH << File.expand_path("../lib", __FILE__)
+# frozen_string_literal: true
+
+$LOAD_PATH << File.expand_path('lib', __dir__)
 require 'hashdiff/version'
 
 Gem::Specification.new do |s|
-  s.name        = %q{hashdiff}
-  s.version     = HashDiff::VERSION
+  s.name        = 'hashdiff'
+  s.version     = Hashdiff::VERSION
   s.license     = 'MIT'
-  s.summary     = %q{ HashDiff is a diff lib to compute the smallest difference between two hashes. }
-  s.description = %q{ HashDiff is a diff lib to compute the smallest difference between two hashes. }
+  s.summary     = ' Hashdiff is a diff lib to compute the smallest difference between two hashes. '
+  s.description = ' Hashdiff is a diff lib to compute the smallest difference between two hashes. '
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- Appraisals {spec}/*`.split("\n")
 
   s.require_paths = ['lib']
-  s.required_ruby_version = Gem::Requirement.new(">= 1.8.7")
+  s.required_ruby_version = Gem::Requirement.new('>= 2.0.0')
+  s.post_install_message = 'The HashDiff constant used by this gem conflicts with another gem of a similar name.  As of version 1.0 the HashDiff constant will be completely removed and replaced by Hashdiff.  For more information see https://github.com/liufengyun/hashdiff/issues/45.'
+
+  s.authors = ['Liu Fengyun']
+  s.email   = ['liufengyunchina@gmail.com']
 
-  s.authors = ["Liu Fengyun"]
-  s.email   = ["liufengyunchina@gmail.com"]
+  s.homepage = 'https://github.com/liufengyun/hashdiff'
 
-  s.homepage = "https://github.com/liufengyun/hashdiff"
+  s.add_development_dependency('bluecloth')
+  s.add_development_dependency('rspec', '~> 2.0')
+  s.add_development_dependency('rubocop')
+  s.add_development_dependency('rubocop-rspec')
+  s.add_development_dependency('yard')
 
-  s.add_development_dependency("rspec",    "~> 2.0")
-  s.add_development_dependency("yard")
-  s.add_development_dependency("bluecloth")
+  if s.respond_to?(:metadata)
+    s.metadata = {
+      'bug_tracker_uri' => 'https://github.com/liufengyun/hashdiff/issues',
+      'changelog_uri' => 'https://github.com/liufengyun/hashdiff/blob/master/changelog.md',
+      'documentation_uri' => 'https://www.rubydoc.info/gems/hashdiff',
+      'homepage_uri' => 'https://github.com/liufengyun/hashdiff',
+      'source_code_uri' => 'https://github.com/liufengyun/hashdiff'
+    }
+  end
 end

data/lib/hashdiff/compare_hashes.rb

@@ -0,0 +1,56 @@
+# frozen_string_literal: true
+
+module Hashdiff
+  # @private
+  # Used to compare hashes
+  class CompareHashes
+    class << self
+      def call(obj1, obj2, opts = {})
+        return [] if obj1.empty? && obj2.empty?
+
+        obj1_keys = obj1.keys
+        obj2_keys = obj2.keys
+
+        added_keys = (obj2_keys - obj1_keys).sort_by(&:to_s)
+        common_keys = (obj1_keys & obj2_keys).sort_by(&:to_s)
+        deleted_keys = (obj1_keys - obj2_keys).sort_by(&:to_s)
+
+        result = []
+
+        # add deleted properties
+        deleted_keys.each do |k|
+          change_key = Hashdiff.prefix_append_key(opts[:prefix], k, opts)
+          custom_result = Hashdiff.custom_compare(opts[:comparison], change_key, obj1[k], nil)
+
+          if custom_result
+            result.concat(custom_result)
+          else
+            result << ['-', change_key, obj1[k]]
+          end
+        end
+
+        # recursive comparison for common keys
+        common_keys.each do |k|
+          prefix = Hashdiff.prefix_append_key(opts[:prefix], k, opts)
+
+          result.concat(Hashdiff.diff(obj1[k], obj2[k], opts.merge(prefix: prefix)))
+        end
+
+        # added properties
+        added_keys.each do |k|
+          change_key = Hashdiff.prefix_append_key(opts[:prefix], k, opts)
+
+          custom_result = Hashdiff.custom_compare(opts[:comparison], change_key, nil, obj2[k])
+
+          if custom_result
+            result.concat(custom_result)
+          else
+            result << ['+', change_key, obj2[k]]
+          end
+        end
+
+        result
+      end
+    end
+  end
+end