data_model 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: d6f87b58a7e7706f284041ccc8479520af309c3e632ef89311be431a11112273
+  data.tar.gz: e945d11a1ac73459be8b1c067eb8bc40cafe7f43a665cb069fecf880d413d91d
+SHA512:
+  metadata.gz: f6470deed88de3b60a5aad2e5926724f4d3255567d0668016ff6c13e1a82608ea71dc8b82ae82a4b0993771c222ad3a9353236243e6c0e8f8c4c0423614e8c71
+  data.tar.gz: 82434cccbdb292e7e416e46eb1eb353193ff39329008a107b2837d97b2c907228c79c62f3be16a2f5966c437c777372f2c08708e0acf5b688fb2f22232565dae

data/.editorconfig

@@ -0,0 +1,10 @@
+root = true
+
+[*]
+indent_style = tab
+indent_size = 2
+
+[*.yml]
+indent_style = space
+indent_size = 2
+

data/.rubocop.yml

@@ -0,0 +1,4 @@
+inherit_from: "https://raw.githubusercontent.com/mbriggs/configs/main/dotfiles/rubocop.yml"
+
+Style/SymbolArray:
+  EnforcedStyle: brackets

data/Gemfile

@@ -0,0 +1,2 @@
+source "https://rubygems.org"
+gemspec

data/Gemfile.lock

@@ -0,0 +1,80 @@
+PATH
+  remote: .
+  specs:
+    data_model (0.0.1)
+      zeitwerk (~> 2.6)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.2)
+    backport (1.2.0)
+    benchmark (0.2.0)
+    diff-lcs (1.5.0)
+    e2mmap (0.1.0)
+    jaro_winkler (1.5.4)
+    json (2.6.2)
+    kramdown (2.4.0)
+      rexml
+    kramdown-parser-gfm (1.1.0)
+      kramdown (~> 2.0)
+    mini_portile2 (2.8.0)
+    nokogiri (1.13.8)
+      mini_portile2 (~> 2.8.0)
+      racc (~> 1.4)
+    parallel (1.22.1)
+    parser (3.1.2.1)
+      ast (~> 2.4.1)
+    racc (1.6.0)
+    rainbow (3.1.1)
+    regexp_parser (2.6.0)
+    reverse_markdown (2.1.1)
+      nokogiri
+    rexml (3.2.5)
+    rubocop (1.36.0)
+      json (~> 2.3)
+      parallel (~> 1.10)
+      parser (>= 3.1.2.1)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.20.1, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 3.0)
+    rubocop-ast (1.21.0)
+      parser (>= 3.1.1.0)
+    ruby-progressbar (1.11.0)
+    solargraph (0.47.2)
+      backport (~> 1.2)
+      benchmark
+      bundler (>= 1.17.2)
+      diff-lcs (~> 1.4)
+      e2mmap
+      jaro_winkler (~> 1.5)
+      kramdown (~> 2.3)
+      kramdown-parser-gfm (~> 1.1)
+      parser (~> 3.0)
+      reverse_markdown (>= 1.0.5, < 3)
+      rubocop (>= 0.52)
+      thor (~> 1.0)
+      tilt (~> 2.0)
+      yard (~> 0.9, >= 0.9.24)
+    sus (0.14.0)
+    thor (1.2.1)
+    tilt (2.0.11)
+    unicode-display_width (2.3.0)
+    webrick (1.7.0)
+    yard (0.9.28)
+      webrick (~> 1.7.0)
+    zeitwerk (2.6.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  data_model!
+  solargraph
+  sus (~> 0.14)
+
+BUNDLED WITH
+   2.3.7

data/config/sus.rb

@@ -0,0 +1,2 @@
+require "pp"
+require_relative "../lib/data_model"

data/fixtures/schema.rb

@@ -0,0 +1,14 @@
+module Schema
+	extend self
+
+	def string
+		[:string]
+	end
+
+	def contact
+		[:hash, { open?: false },
+			[[:first_name, :string],
+				[:last_name, :string],
+				[:email, :string]]]
+	end
+end

data/lib/data_model/model.rb

@@ -0,0 +1,54 @@
+module DataModel
+	module Model
+		extend self
+
+		def defaults
+			{
+				# name of validator if a child, and validating a named property
+				property: nil,
+
+				# context passed to read and write
+				config: {},
+				types: nil,
+				children: [],
+
+				# default writer
+				write: ->(val) { val }
+			}
+		end
+
+		def validate!(model)
+			model => {
+				property:, config:, types:,
+				read: Proc, write: Proc,
+				children: Array,
+			}
+		end
+
+		def read(model, data)
+			validate! model
+			invoke(model, :read, data)
+		end
+
+		def write(model, data)
+			validate! model
+			invoke(model, :write, data)
+		end
+
+		private
+
+		def invoke(model, action, data)
+			fn = model.fetch(action)
+
+			case fn.arity
+			when 1
+				fn.call(data)
+			when 2
+				ctx = model.slice(:config, :types, :children)
+				fn.call(data, ctx)
+			else
+				raise "expected an arity of 1 or 2, got: #{fn.arity}"
+			end
+		end
+	end
+end

data/lib/data_model/registry.rb

@@ -0,0 +1,44 @@
+module DataModel
+	class Registry
+		def self.instance
+			@instance ||= new(defaults)
+		end
+
+		def self.register(name, type)
+			instance.register(name, type)
+		end
+
+		def self.defaults
+			{
+				string: Type.string,
+				hash: Type.hash
+			}
+		end
+
+		def initialize(*defaults)
+			@types = {}
+
+			defaults.each do |d|
+				d.each do |k, s|
+					register(k, s)
+				end
+			end
+		end
+
+		def register(name, type)
+			@types[name] = Model.defaults.merge(type)
+		end
+
+		def type?(name)
+			@types.key?(name)
+		end
+
+		def type(name, property = nil)
+			unless @types.key?(name)
+				raise "#{name} is not registered as a type"
+			end
+
+			@types.fetch(name).merge(property:)
+		end
+	end
+end

data/lib/data_model/scanner.rb

@@ -0,0 +1,67 @@
+module DataModel
+	module Scanner
+		extend self
+
+		def scan(schema, registry = Registry.instance)
+			start = { validator: nil, property: nil, state: :start }
+			result = schema.each_with_index.reduce(start) do |context, (token, pos)|
+				context => {state:, validator:, property:}
+				peek = schema[pos + 1]
+
+				# detect named validators, a name could be any type so cannot be detected
+				# by ruby type and state. detect name by ensuring we are at the start
+				# of scanning, and the next element is a valid type.
+				if state == :start && registry.type?(peek)
+					context.merge(
+						property: token,
+						state: :named,
+					)
+				else
+					# with the special case of a name aside, we can detect the meaning
+					# of further tokens by their type and scanner state
+					case token
+					when Symbol
+						unless [:start, :named].include?(state)
+							raise "got a symbol at pos #{pos}, but validator already defined"
+						end
+
+						unless registry.type?(token)
+							raise "expected a type in pos #{pos}, but found #{token.inspect} which is not a registered type"
+						end
+
+						context.merge(
+							validator: registry.type(token, property),
+							state: :defined,
+						)
+
+					when Hash
+						unless state == :defined
+							raise "got a hash at pos #{pos}, but state is not :defined (#{state.inspect})"
+						end
+
+						context.merge(
+							validator: validator.merge(config: token),
+							state: :configured,
+						)
+
+					when Array
+						unless [:defined, :configured].include?(state)
+							raise "#{schema.inspect} at pos #{pos}: expected (String | Hash | Symbol | Array), got #{token.class.name}"
+						end
+
+						children = token.map { |s| scan(s, registry) }
+
+						context.merge(
+							validator: validator.merge(children:),
+							state: :complete,
+						)
+					else
+						raise "got token #{token.inspect} at position #{pos} which was unexpected given the scanner was in a state of #{state}"
+					end
+				end
+			end
+
+			result.fetch(:validator)
+		end
+	end
+end

data/lib/data_model/type.rb

@@ -0,0 +1,48 @@
+module DataModel
+	module Type
+		extend self
+
+		def string
+			{
+				read: lambda do |val|
+					err = {}
+
+					unless val.is_a? String
+						err[:root] = "#{val} is not a string, it is a #{val.class.name}"
+					end
+
+					[val, err]
+				end
+			}
+		end
+
+		def hash
+			{
+				read: lambda do |val, ctx|
+					err = {}
+					ctx => {config:, children:}
+
+					unless val.is_a? Hash
+						err[:root] = "#{val} is not a hash, it is a #{val.class.name}"
+						return [val, err]
+					end
+
+					# TODO: this needs to be wayyyy better
+					if !config[:open?] && (val.length > children.length)
+						err[:root] = "more elements found in closed hash then specified children"
+					end
+
+					children.each do |child|
+						child => {property:}
+						v, e = Model.read(child, val.fetch(property))
+
+						val = val.merge({ property => v })
+						err[property] = e
+					end
+
+					[val, err]
+				end
+			}
+		end
+	end
+end

data/lib/data_model/version.rb

@@ -0,0 +1,3 @@
+module DataModel
+  VERSION = "0.0.1"
+end

data/lib/data_model.rb

@@ -0,0 +1,28 @@
+require "zeitwerk"
+
+loader = Zeitwerk::Loader.for_gem
+loader.setup
+
+module DataModel
+	extend self
+
+	def validate(schema, data, registry: Registry.instance)
+		_, err = read(schema, data, registry:)
+		err.empty? || err.values.all?(&:empty?)
+	end
+
+	def read(schema, data, registry: Registry.instance)
+		Model.read(compiled(schema, registry:), data)
+	end
+
+	def write(schema, data, registry: Registry.instance)
+		Model.write(compiled(schema, registry:), data)
+	end
+
+	def compiled(model, registry: Registry.instance)
+		if model in Array
+			model = Scanner.scan(model, registry)
+		end
+		model
+	end
+end

metadata

@@ -0,0 +1,102 @@
+--- !ruby/object:Gem::Specification
+name: data_model
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Matt Briggs
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2022-10-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: zeitwerk
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+- !ruby/object:Gem::Dependency
+  name: sus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.14'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.14'
+- !ruby/object:Gem::Dependency
+  name: solargraph
+  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 framework for describing and validating data.
+email:
+- matt@mattbriggs.net
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".editorconfig"
+- ".rubocop.yml"
+- Gemfile
+- Gemfile.lock
+- config/sus.rb
+- fixtures/schema.rb
+- lib/data_model.rb
+- lib/data_model/model.rb
+- lib/data_model/registry.rb
+- lib/data_model/scanner.rb
+- lib/data_model/type.rb
+- lib/data_model/version.rb
+homepage: https://github.com/mbriggs/data_model
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/mbriggs/data_model
+  source_code_uri: https://github.com/mbriggs/data_model
+  changelog_uri: https://github.com/mbriggs/data_model/releases
+  funding_uri: https://github.com/sponsors/mbriggs
+  rubygems_mfa_required: 'true'
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.7'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.7
+signing_key:
+specification_version: 4
+summary: Define a model for your data
+test_files: []