Basic parser for DBML.

.gitignore

@@ -0,0 +1,8 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in dbml.gemspec
+gemspec

LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2020 Simon Worthington
+
+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 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.

README.md

@@ -0,0 +1,47 @@
+# DBML
+
+Ruby library for [Database Markup Language (DBML)](https://www.dbml.org/).
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'dbml'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install dbml
+
+## Usage
+
+```ruby
+require 'dbml'
+project = DBML::Parser.parse """
+  Table users {
+    id int64 [pk, unique]
+    name varchar [unique]
+    Note: 'add some more things in here!'
+  }"""
+puts project.tables.first.name
+# => "users"
+```
+
+## Development
+
+After checking out the repo, run `bundle install` to install dependencies. Then, run `rake test` to run the tests.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/simonwo/dbml-ruby.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+task :default => :test

dbml.gemspec

@@ -0,0 +1,29 @@
+
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'dbml/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'dbml'
+  spec.version       = DBML::VERSION
+  spec.authors       = ['Simon Worthington']
+  spec.email         = ['[email protected]']
+
+  spec.summary       = %q{Parser for Database Markup Language (DBML).}
+  spec.homepage      = 'https://github.com/simonwo/dbml-ruby'
+  spec.license       = 'MIT'
+
+  # 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.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'rsec', '~> 1.0'
+  spec.add_development_dependency 'bundler'
+  spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'minitest', '~> 5.0'
+end

lib/dbml.rb

@@ -0,0 +1,206 @@
+require 'rsec'
+include Rsec::Helpers
+
+module DBML
+  Column     = Struct.new :name, :type, :settings
+  Table      = Struct.new :name, :alias, :notes, :columns, :indexes
+  Index      = Struct.new :fields, :settings
+  Expression = Struct.new :text
+  Enum       = Struct.new :name, :choices
+  EnumChoice = Struct.new :name, :settings
+  TableGroup = Struct.new :name, :tables
+  Project    = Struct.new :name, :notes, :settings, :tables, :enums, :table_groups
+  ProjectDef = Struct.new :name, :notes, :settings
+
+  module Parser
+    def self.long_or_short p
+      (':'.r >> p) | ('{'.r >> p << '}'.r)
+    end
+
+    def self.unwrap p, *_
+      if p.empty? then nil else p.first end
+    end
+
+    def self.comma_separated p
+      p.join(/, */.r.map {|_| nil}).star.map {|v| v.first.reject(&:nil?) }
+    end
+
+    def self.space_surrounded p
+      /\s*/.r >> p << /\s*/.r
+    end
+
+    def self.block type, name_parser, content_parser, &block
+      seq_(type.r >> name_parser, '{'.r >> space_surrounded(content_parser).star.map {|a| a.flatten(1) } << '}'.r, &block)
+    end
+
+    BOOLEAN            = 'true'.r | 'false'.r
+    NULL               = 'null'.r
+    NUMBER             = prim(:double)
+    EXPRESSION         = seq('`'.r, /[^`]+/.r, '`'.r)[1].map {|str| Expression.new str}
+    SINGLE_LING_STRING = seq("'".r, /[^']+/.r, "'".r)[1]
+    MULTI_LINE_STRING  = seq("'''".r, /([^']|'[^']|''[^'])+/m.r, "'''".r)[1].map do |string|
+      # Remove the indentation on the first line from all other lines.
+      indent = string.match(/^\s*/m)[0].size
+      string.lines.map do |line|
+        raise "Indentation does not match" unless line =~ /\s{#{indent}}/
+        line[indent..]
+      end.join
+    end
+    STRING = SINGLE_LING_STRING | MULTI_LINE_STRING
+    ATOM = BOOLEAN | NULL | NUMBER | EXPRESSION | STRING
+
+    # Each setting item can take in 2 forms: Key: Value or keyword, similar to that of Python function parameters.
+    SETTING = seq_(/[^,:\[\]\{\}\s]+/.r, (':'.r >> ATOM).maybe(&method(:unwrap))) {|(key, value)| {key => value} }
+    # Settings are all defined within square brackets: [setting1: value1, setting2: value2, setting3, setting4]
+    SETTINGS = ('['.r >> comma_separated(SETTING) << ']'.r).map {|values| values.reduce({}, &:update) }
+
+    NOTE = 'Note'.r >> (long_or_short STRING)
+
+    # Index Definition
+    #
+    # Indexes allow users to quickly locate and access the data. Users can define single or multi-column indexes.
+    #
+    #     Table bookings {
+    #       id integer
+    #       country varchar
+    #       booking_date date
+    #       created_at timestamp
+    #
+    #       indexes {
+    #           (id, country) [pk] // composite primary key
+    #           created_at [note: 'Date']
+    #           booking_date
+    #           (country, booking_date) [unique]
+    #           booking_date [type: hash]
+    #           (`id*2`)
+    #           (`id*3`,`getdate()`)
+    #           (`id*3`,id)
+    #       }
+    #     }
+    #
+    # There are 3 types of index definitions:
+    #
+    #     Index with single field (with index name): CREATE INDEX on users (created_at)
+    #     Index with multiple fields (composite index): CREATE INDEX on users (created_at, country)
+    #     Index with an expression: CREATE INDEX ON films ( first_name + last_name )
+    #     (bonus) Composite index with expression: CREATE INDEX ON users ( country, (lower(name)) )
+
+    INDEX_SINGLE = /[^\(\)\,\{\}\s]+/.r
+    INDEX_COMPOSITE = seq_('('.r, comma_separated(EXPRESSION | INDEX_SINGLE), ')'.r).inner.map {|v| unwrap(v) }
+    INDEX = seq_(INDEX_SINGLE | INDEX_COMPOSITE, SETTINGS.maybe).map do |(fields, settings)|
+      Index.new fields, unwrap(settings)
+    end
+    INDEXES = ('indexes {'.r >> INDEX.star << '}'.r).map{|v| p v; v }
+
+    # Enum Definition
+    # ---------------
+    #
+    # Enum allows users to define different values of a particular column.
+    #
+    #     enum job_status {
+    #         created [note: 'Waiting to be processed']
+    #         running
+    #         done
+    #         failure
+    #     }
+
+    ENUM_CHOICE = seq_(/\S+/.r, SETTINGS.maybe).map {|(name, settings)| EnumChoice.new name, unwrap(settings) }
+    ENUM = seq_('enum'.r >> /\S+/.r, '{'.r >> ENUM_CHOICE.star << '}'.r).map {|(name, choices)| Enum.new name, choices }
+
+    # Column Definition
+    # =================
+    # * name of the column is listed as column_name
+    # * type of the data in the column listed as column_type
+    # * supports all data types, as long as it is a single word (remove all spaces in the data type). Example, JSON, JSONB, decimal(1,2), etc.
+    # * column_name can be stated in just plain text, or wrapped in a double quote as "column name"
+    #
+    # Column Settings
+    # ---------------
+    # Each column can take have optional settings, defined in square brackets like:
+    #
+    #     Table buildings {
+    #         ...
+    #         address varchar(255) [unique, not null, note: 'to include unit number']
+    #         id integer [ pk, unique, default: 123, note: 'Number' ]
+    #     }
+
+    QUOTED_COLUMN_NAME = '"'.r >> /[^"]+/.r << '"'.r
+    UNQUOTED_COLUMN_NAME = /\S+/.r
+    COLUMN_TYPE = /\S+/.r
+    COLUMN = seq_(
+      QUOTED_COLUMN_NAME | UNQUOTED_COLUMN_NAME,
+      COLUMN_TYPE,
+      SETTINGS.maybe
+    ) {|(name, type, settings)| Column.new name, type, unwrap(settings) }
+
+    # Table Definition
+    #
+    #     Table table_name {
+    #       column_name column_type [column_settings]
+    #     }
+    #
+    # * title of database table is listed as table_name
+    # * list is wrapped in curly brackets {}, for indexes, constraints and table definitions.
+    # * string value is be wrapped in a single quote as 'string'
+
+    TABLE_NAME = seq_ /\S+/.r, ('as'.r >> /\S+/.r).maybe(&method(:unwrap))
+    TABLE = seq_('Table'.r >> TABLE_NAME, (long_or_short (/\s*/.r >> (INDEXES | NOTE | COLUMN) << /\s*/.r).star)) do |((name, aliaz), objects)|
+      Table.new name, aliaz,
+        objects.select {|o| o.is_a? String },
+        objects.select {|o| o.is_a? Column },
+        objects.select {|o| (o.is_a? Array) && (o.all? {|e| e.is_a? Index })}.flatten
+    end
+
+    # TableGroup
+    # ==========
+    #
+    # TableGroup allows users to group the related or associated tables together.
+    #
+    #     TableGroup tablegroup_name { // tablegroup is case-insensitive.
+    #         table1
+    #         table2
+    #         table3
+    #     }
+    TABLE_GROUP = seq_('TableGroup'.r >> /\S+/.r, '{'.r >> /\S+/.r.star << '}'.r) do |(name, tables)|
+      TableGroup.new name, tables
+    end
+
+    # Project Definition
+    # ==================
+    # You can give overall description of the project.
+    #
+    #     Project project_name {
+    #       database_type: 'PostgreSQL'
+    #       Note: 'Description of the project'
+    #     }
+
+    PROJECT_DEFINITION = block 'Project', /\S+/.r, (NOTE | SETTING).star do |(name, objects)|
+      ProjectDef.new name,
+        objects.select {|o| o.is_a? String },
+        objects.select {|o| o.is_a? Hash }.reduce({}, &:update)
+    end
+    PROJECT = space_surrounded(PROJECT_DEFINITION | TABLE | TABLE_GROUP | ENUM).star do |objects|
+      definition = objects.find {|o| o.is_a? ProjectDef }
+      Project.new definition.nil? ? nil : definition.name,
+        definition.nil? ? [] : definition.notes,
+        definition.nil? ? [] : definition.settings,
+        objects.select {|o| o.is_a? Table },
+        objects.select {|o| o.is_a? Enum },
+        objects.select {|o| o.is_a? TableGroup }
+    end
+
+    def self.parse str
+      PROJECT.eof.parse! str.gsub(/\/{2}.*$/, '')
+    end
+  end
+end
+
+if $0 == __FILE__
+  p DBML::Parser::PROJECT_DEFINITION.parse! "Project geoff {\n  database_table: 'PostgreSQL'\n}"
+  p DBML::Parser::NOTE.parse! "Note { \n'''  Simon is\n  very wicked'''\n}"
+  p DBML::Parser::SETTINGS.parse! "[long: 'short', unique, not null, default: 123.45678]"
+  p DBML::Parser::INDEX.eof.parse! '(id, `id*3`) [pk]'
+  x = DBML::Parser.parse "Project geoff {\n  database_type: 'postgres'\n}\nTable banter {\n  id string [pk]// the id \n// TODO: rest of schema\nNote: 'this is a great table'\nindexes { id\n(id, `id*2`)\n}  }"
+  p x.tables
+  p x.name
+end

lib/dbml/version.rb

@@ -0,0 +1,3 @@
+module DBML
+  VERSION = "0.1.0"
+end

test/dbml_test.rb

@@ -0,0 +1,11 @@
+require "test_helper"
+
+class DbmlTest < Minitest::Test
+  def test_that_it_has_a_version_number
+    refute_nil ::Dbml::VERSION
+  end
+
+  def test_it_does_something_useful
+    assert false
+  end
+end

test/test_helper.rb

@@ -0,0 +1,4 @@
+$LOAD_PATH.unshift File.expand_path("../../lib", __FILE__)
+require "dbml"
+
+require "minitest/autorun"