ipynbdiff 0.3.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: c0839dd5e5fbcdf19b5525d859fa7d224ec1bb647d7131f9cc20487190ccea80
+  data.tar.gz: ca32de2c784712f66f2f1c8b5642b32fca0078eae0279c8b30f975216101d143
+SHA512:
+  metadata.gz: 45353d2e38a4378cb5f785edb6b38d250bf38ce4934f8943dcbe08973e4c187942449d185d4a3af59649d9459c74071475b33f23033c192b4345b24f95a2fd78
+  data.tar.gz: 7d8df2c34356018dfe098c0f36e8fb8f3c189c8121411826b9923b406ead730856a9e46ca57124b4e4e23e0409e1fdf83c5785686ab6aa0254bcedca07b95246

data/.gitignore

@@ -0,0 +1,6 @@
+.tool-versions
+.bundle
+
+
+*.gem
+

data/Gemfile

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+gem 'diffy', '3.3.0'
+gem 'json', '2.5.1'
+gem 'rspec', '3.10.0'

data/Gemfile.lock

@@ -0,0 +1,29 @@
+GEM
+  specs:
+    diff-lcs (1.4.4)
+    diffy (3.3.0)
+    json (2.5.1)
+    rspec (3.10.0)
+      rspec-core (~> 3.10.0)
+      rspec-expectations (~> 3.10.0)
+      rspec-mocks (~> 3.10.0)
+    rspec-core (3.10.1)
+      rspec-support (~> 3.10.0)
+    rspec-expectations (3.10.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.10.0)
+    rspec-mocks (3.10.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.10.0)
+    rspec-support (3.10.2)
+
+PLATFORMS
+  x86_64-darwin-20
+
+DEPENDENCIES
+  diffy (= 3.3.0)
+  json (= 2.5.1)
+  rspec (= 3.10.0)
+
+BUNDLED WITH
+   2.2.28

data/README.md

@@ -0,0 +1,3 @@
+# rb-ipynbdiff: Better Jupyter Notebook diffs, in Ruby
+
+This is a port of [ipynbdiff](https://gitlab.com/gitlab-org/incubation-engineering/mlops/ipynbdiff)

data/ipynbdiff.gemspec

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+Gem::Specification.new do |s|
+  s.name        = 'ipynbdiff'
+  s.version     = '0.3.1'
+  s.summary     = 'Human Readble diffs for Jupyter Notebooks'
+  s.description = 'A simple hello world gem'
+  s.authors     = ['Eduardo Bonet']
+  s.email       = 'ebonet@gitlab.com'
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  s.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(spec|example)/}) }
+  end
+  s.homepage    =
+    'https://gitlab.com/gitlab-org/incubation-engineering/mlops/rb-ipynbdiff'
+  s.license       = 'MIT'
+
+  s.require_paths = ['lib']
+
+  s.add_runtime_dependency 'diffy', '3.3.0'
+  s.add_runtime_dependency 'json', '2.5.1'
+
+  s.add_development_dependency 'bundler', '~> 2.2'
+  s.add_development_dependency 'guard-rspec'
+  s.add_development_dependency 'pry'
+  s.add_development_dependency 'rake'
+  s.add_development_dependency 'rspec'
+end

data/lib/ipynbdiff.rb

@@ -0,0 +1,42 @@
+# frozen_string_literal: true
+
+# Human Readable Jupyter Diffs
+module IpynbDiff
+  require 'transformer.rb'
+  require 'diffy'
+
+  @default_options = {
+    preprocess_input: TRUE,
+    write_output_to: nil,
+    format: :text,
+    sources_are_files: FALSE,
+    diff_opts: {
+      include_diff_info: FALSE
+    }
+  }.freeze
+
+  def self.prepare_input(to_prepare, load_from_file, preprocess)
+    prepared = to_prepare
+    prepared = File.read(prepared) if load_from_file
+    prepared = Transformer.transform(prepared) if preprocess
+
+    prepared
+  end
+
+  def self.diff(
+    from_notebook,
+    to_notebook,
+    options = {}
+  )
+    options = @default_options.merge(options)
+
+    from = prepare_input(from_notebook, options[:sources_are_files], options[:preprocess_input])
+    to = prepare_input(to_notebook, options[:sources_are_files], options[:preprocess_input])
+
+    d = Diffy::Diff.new(from, to, **options[:diff_opts]).to_s(options[:format])
+
+    File.write(options[:write_output_to], d) if options[:write_output_to]
+
+    d
+  end
+end

data/lib/transformer.rb

@@ -0,0 +1,101 @@
+# frozen_string_literal: true
+
+module IpynbDiff
+  # Returns a markdown version of the Jupyter Notebook
+  class Transformer
+    require 'json'
+    require 'yaml'
+
+    def self.transform(notebook, include_metadata: TRUE)
+      notebook_json = JSON.parse(notebook)
+      transformed_blocks = notebook_json['cells'].map { |cell| transform_cell(cell, notebook_json) }
+      transformed_blocks.prepend(transform_metadata(notebook_json)) if include_metadata
+      transformed_blocks.join("\n")
+    end
+
+    def self.transform_cell(cell, notebook)
+      cell['cell_type'] == 'code' ? transform_code_cell(cell, notebook) : transform_text_cell(cell)
+    end
+
+    def self.transform_code_cell(cell, notebook)
+      tags = cell['metadata'].fetch('tags', []).join(' ')
+
+      [
+        %(<div class="cell code" data-id="#{cell['id']}" data-tags="#{tags}">\n\n),
+        %(``` #{notebook['metadata']['kernelspec']['language']}\n),
+        *cell['source'],
+        "\n```\n",
+        *cell['outputs'].map { |output| transform_output(output) },
+        "\n</div>\n"
+      ].join('')
+    end
+
+    def self.format_traceback(traceback)
+      traceback.map do |t|
+        t.split("\n").map do |line|
+          line.gsub(/\[[0-9][0-9;]*m/, '').sub("\u001B", '    ').gsub(/\u001B/, '').rstrip
+        end
+      end.join("\n")
+    end
+
+    def self.transform_execute_result(output)
+      [
+        %(\n<div class="output execute_result">\n\n),
+        *output['data']['text/plain'].map { |line| "    #{line}" },
+        "\n\n</div>\n"
+      ].join('')
+    end
+
+    def self.transform_image_result(output)
+      if output['data'].key?('image/png')
+        [
+          %(\n<div class="output display_data">\n\n),
+          "![](data:image/png;base64,#{output['data']['image/png'].gsub("\n", '')})",
+          "\n\n</div>\n"
+        ].join('')
+      end
+    end
+
+    def self.transform_error_result(output)
+      [
+        %(\n<div class="output error">\n\n),
+        format_traceback(output['traceback']),
+        "\n\n</div>\n"
+      ].join('')
+    end
+
+    def self.transform_output(output)
+      case output['output_type']
+      when 'execute_result'
+        transform_execute_result(output)
+      when 'display_data'
+        transform_image_result(output)
+      when 'error'
+        transform_error_result(output)
+      end
+    end
+
+    def self.transform_text_cell(cell)
+      tags = cell['metadata'].fetch('tags', []).join(' ')
+      id = cell['id']
+      cell_type = cell['cell_type']
+
+      [
+        %(<div class="cell #{cell_type}" data-id="#{id}" data-tags="#{tags}">\n\n),
+        *cell['source'],
+        "\n\n</div>\n"
+      ].join('')
+    end
+
+    def self.transform_metadata(notebook_json)
+      {
+        'jupyter' => {
+          'kernelspec' => notebook_json['metadata']['kernelspec'],
+          'language_info' => notebook_json['metadata']['language_info'],
+          'nbformat' => notebook_json['nbformat'],
+          'nbformat_minor' => notebook_json['nbformat_minor']
+        }
+      }.to_yaml + "---\n"
+    end
+  end
+end

metadata

@@ -0,0 +1,147 @@
+--- !ruby/object:Gem::Specification
+name: ipynbdiff
+version: !ruby/object:Gem::Version
+  version: 0.3.1
+platform: ruby
+authors:
+- Eduardo Bonet
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2021-10-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: diffy
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.5.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.5.1
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.2'
+- !ruby/object:Gem::Dependency
+  name: guard-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A simple hello world gem
+email: ebonet@gitlab.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- Gemfile.lock
+- README.md
+- ipynbdiff.gemspec
+- lib/ipynbdiff.rb
+- lib/transformer.rb
+homepage: https://gitlab.com/gitlab-org/incubation-engineering/mlops/rb-ipynbdiff
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.6
+signing_key: 
+specification_version: 4
+summary: Human Readble diffs for Jupyter Notebooks
+test_files: []