rbscmlex 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 2ac1672aabaa3f5da45e737b0a662488a9a3fdddfc543b2c5b5835576bbbcb9d
+  data.tar.gz: aadf9ea25326c7b0b45335b99f6d31d7a7540f0b812d8b39434c40977a48f053
+SHA512:
+  metadata.gz: 2dd3a53f7bc19f8b56aed51383cdeff7dff1e351822a3971558933690918d66147a599bba5f28c68782a6511bda7d811780fdaef11fe0226716b16204ca3edec
+  data.tar.gz: 27a1df5414a12c1db2d074e39ab81a11c0c89aeee913b9644b611ac45d099164a67b50113b713e9a63f88eb0617633f0074a29a08b64c39b5cedabf77c00bfb1

data/.github/workflows/main.yml

@@ -0,0 +1,18 @@
+name: Build
+
+on: [push,pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: 3.0.1
+    - name: Run the default task
+      run: |
+        gem install bundler -v 2.2.15
+        bundle install
+        bundle exec rake

data/.gitignore

@@ -0,0 +1,57 @@
+Gemfile.lock
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
+/tmp/
+
+# Used by dotenv library to load environment variables.
+# .env
+
+# Ignore Byebug command history file.
+.byebug_history
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+*.bridgesupport
+build-iPhoneOS/
+build-iPhoneSimulator/
+
+## Specific to RubyMotion (use of CocoaPods):
+#
+# We recommend against adding the Pods directory to your .gitignore. However
+# you should judge for yourself, the pros and cons are mentioned at:
+# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
+#
+# vendor/Pods/
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalization:
+/.bundle/
+/vendor/bundle
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# Gemfile.lock
+# .ruby-version
+# .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+
+# Used by RuboCop. Remote config files pulled in from inherit_from directive.
+# .rubocop-https?--*

data/CHANGELOG.md

@@ -0,0 +1,11 @@
+# Change Log
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/)
+and this project adheres to [Semantic Versioning](https://semver.org/).
+
+## [Unreleased]
+- (nothing to record here)
+
+## [0.1.0] - 2021-05-06
+- Initial release

data/Gemfile

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in rbscmlex.gemspec
+gemspec
+
+gem "rake", "~> 13.0"
+
+gem "minitest", "~> 5.0"

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2021 mnbi
+
+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.

data/README.md

@@ -0,0 +1,36 @@
+# rbscmlex
+
+[![Build Status](https://github.com/mnbi/rbscmlex/workflows/Build/badge.svg)](https://github.com/mnbi/rbscmlex/actions?query=workflow%3A"Build")
+
+A simple lexical analyzer for Scheme.
+
+It is intended to be used as a part of a Scheme implementation written
+in Ruby.
+
+## Installation
+
+Execute as:
+
+    > gem install rbscmlex
+
+## Usage
+
+See `examples/sample_parser.rb` to know about how to use as a lexical
+analyzer for Scheme.
+
+Or, run `rbscmlex` to see the output of the lexer.
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+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/mnbi/rus3](https://github.com/mnbi/rus3).
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+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

data/bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require "bundler/setup"
+require "rbscmlex"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/examples/simaple_parser.rb

@@ -0,0 +1,41 @@
+#!/usr/bin/env ruby
+
+require "rbscmlex"
+
+def parse_program(lex)
+  program = []
+  loop {
+    program << parse_expression(lex)
+  }
+  program
+end
+
+def parse_expression(lex)
+  if lex.peek_token.type == :lparen
+    parse_list(lex)
+  else
+    parse_simple(lex)
+  end
+end
+
+def parse_list(lex)
+  lex.next_token                # skip :lparen
+  list = []
+  loop {
+    break if lex.peek_token.type == :rparen
+    list << parse_expression(lex)
+  }
+  lex.next_token                # skip :rparen
+  list
+end
+
+def parse_simple(lex)
+  lex.next_token.literal
+end
+
+source = ARGF.entries.join(" ")
+lex = Rbscmlex::Lexer.new(source)
+
+result = parse_program(lex)
+
+pp result

data/exe/rbscmlex

@@ -0,0 +1,85 @@
+#!/usr/bin/env ruby
+
+require "readline"
+require "rbscmlex"
+
+def version
+  "rbscmlex version #{Rbscmlex::VERSION} #{Rbscmlex::RELEASE}"
+end
+
+def usage
+  <<HELP
+usage:
+    rbscmlex [option] [FILE ...]
+option:
+    -o, --output-file OUTPUT_FILE : specify the output file
+    -t, --format-type TYPE : specify the output format
+    -d, --debug   : specify to run verbose mode
+    -v, --version : print version
+    -h, --help    : show this message
+
+OUTPUT_FORMAT:
+    Use one of the following name to specify the output format.
+        token, hash, json
+HELP
+end
+
+def opt_parse(args, opts = {})
+  files = []
+  while args.size > 0
+    arg = args.shift
+    case arg
+    when "-o", "--output-file"
+      opts[:output_file] = args.shift
+    when "-t", "--format-type"
+      format_type = args.shift
+      raise ArgumentError, "not specified as format type" if format_type.nil?
+      opts[:format_type] = format_type.intern
+    when "-d", "--debug"
+      opts[:verbose] = true
+    when "-v", "--version"
+      puts version
+      exit 0
+    when "-h", "--help"
+      puts usage
+      exit 0
+    else                        # must be a filename
+      files << arg if arg
+    end
+  end
+  args.concat(files)
+  opts
+end
+
+opts = opt_parse(ARGV)
+if opts[:verbose]
+  puts version
+  format = opts[:format_type] || "default"
+  puts "Output format: #{format}"
+  ofname = opts[:output_file] || "STDOUT"
+  puts "Output file: #{ofname}"
+end
+
+of = STDOUT
+of = File.open(opts[:output_file], "w") if opts[:output_file]
+form = opts[:format_type] || :token
+
+if ARGV.size > 0
+  puts "reading... #{ARGV.join(", ")}" if opts[:verbose]
+
+  source = ARGF.entries.join(" ")
+  lex = Rbscmlex::Lexer.new(source, form: form)
+
+  Kernel.loop {
+    of.puts lex.next_token
+  }
+else
+  puts "reading...STDIN" if opts[:verbose]
+
+  Kernel.loop {
+    src_line = Readline::readline("Rbscmlex> ")
+    break if src_line.nil?
+    lex = Rbscmlex::Lexer.new(src_line, type: type)
+    Kernel.loop { of.puts lex.next_token }
+  }
+end

data/lib/rbscmlex.rb

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+module Rbscmlex
+  require_relative "rbscmlex/error"
+  require_relative "rbscmlex/token"
+  require_relative "rbscmlex/lexer"
+  require_relative "rbscmlex/version"
+end

data/lib/rbscmlex/error.rb

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+module Rbscmlex
+  class Error < StandardError; end
+
+  class UnknownTokenTypeError < Error
+  end
+
+  class InvalidConversionTypeError < Error
+  end
+
+  class InvalidHashError < Error
+  end
+
+  class InvalidJsonError < Error
+  end
+
+end

data/lib/rbscmlex/lexer.rb

@@ -0,0 +1,155 @@
+# frozen_string_literal: true
+
+require "json"
+
+module Rbscmlex
+
+  # A lexical analyzer for Scheme program.  It returns an Array
+  # instance of tokens.  The representation of each token is depends
+  # on the specification of type, which is specified to the `new`
+  # method.
+  #
+  # Currently, 3 types of the representation are available.
+  #
+  #   1. a struct Token,
+  #   2. a Hash object,
+  #   3. a JSON string.
+
+  class Lexer
+
+    class << self
+
+      def version               # :nodoc:
+        "(scheme-lexer :version #{VERSION})"
+      end
+
+    end
+
+    # :stopdoc:
+
+    BOOLEAN    = /\A#(f(alse)?|t(rue)?)\Z/
+    STRING     = /\A\"[^\"]*\"\Z/
+
+    # idents
+    EXTENDED_CHARS = "!\\$%&\\*\\+\\-\\./:<=>\\?@\\^_~"
+    IDENT_PAT  = "[a-zA-Z_][a-zA-Z0-9#{EXTENDED_CHARS}]*"
+    IDENTIFIER = Regexp.new("\\A#{IDENT_PAT}\\Z")
+
+    # operators
+    ARITHMETIC_OPS = /\A[+\-*\/%]\Z/
+    COMPARISON_OPS = /\A([<>]=?|=)\Z/
+
+    # numbers
+    REAL_PAT   = "(([1-9][0-9]*)|0)(\.[0-9]+)?"
+    RAT_PAT    = "#{REAL_PAT}\\/#{REAL_PAT}"
+    C_REAL_PAT = "(#{REAL_PAT}|#{RAT_PAT})"
+    C_IMAG_PAT = "#{C_REAL_PAT}"
+    COMP_PAT   = "#{C_REAL_PAT}(\\+|\\-)#{C_IMAG_PAT}i"
+
+    REAL_NUM   = Regexp.new("\\A[+-]?#{REAL_PAT}\\Z")
+    RATIONAL   = Regexp.new("\\A[+-]?#{RAT_PAT}\\Z")
+    COMPLEX    = Regexp.new("\\A[+-]?#{COMP_PAT}\\Z")
+    PURE_IMAG  = Regexp.new("\\A[+-](#{C_IMAG_PAT})?i\\Z")
+
+    # char
+    SINGLE_CHAR_PAT = "."
+    SPACE_PAT       = "space"
+    NEWLINE_PAT     = "newline"
+
+    CHAR_PREFIX = "\#\\\\"
+    CHAR_PAT    = "(#{SINGLE_CHAR_PAT}|#{SPACE_PAT}|#{NEWLINE_PAT})"
+    CHAR        = Regexp.new("\\A#{CHAR_PREFIX}#{CHAR_PAT}\\Z")
+
+    # :startdoc:
+
+    include Enumerable
+
+    def initialize(src, form: TOKEN_DEFAULT_FORM)
+      @form = form
+      @tokens = tokenize(src)
+      @size = @tokens.size
+
+      @current_pos = @next_pos = 0
+    end
+
+    def each(&blk)
+      if block_given?
+        @tokens.each(&blk)
+        self
+      else
+        @tokens.each
+      end
+    end
+
+    def to_a
+      @tokens
+    end
+
+    def size
+      @size
+    end
+
+    def current_token
+      @tokens[@current_pos]
+    end
+
+    def next_token
+      check_pos
+      @current_pos = @next_pos
+      @next_pos += 1
+      @tokens[@current_pos]
+    end
+
+    def peek_token(num = 0)
+      check_pos
+      @tokens[@next_pos + num]
+    end
+
+    def rewind
+      @current_pos = @next_pos = 0
+      self
+    end
+
+    private
+
+    def check_pos
+      raise StopIteration if @next_pos >= @size
+    end
+
+    S2R_MAP = { "(" => "( ", ")" => " ) ", "'" => " ' " } # :nodoc:
+
+    def tokenize(src)
+      cooked = src.gsub(/[()']/, S2R_MAP)
+
+      cooked.split(" ").map { |literal|
+        case literal
+        when "("
+          Rbscmlex.new_token(:lparen, literal, @form)
+        when ")"
+          Rbscmlex.new_token(:rparen, literal, @form)
+        when "."
+          Rbscmlex.new_token(:dot, literal, @form)
+        when "'"
+          Rbscmlex.new_token(:quotation, literal, @form)
+        when "#("
+          Rbscmlex.new_token(:vec_lparen, literal, @form)
+        when BOOLEAN
+          Rbscmlex.new_token(:boolean, literal, @form)
+        when IDENTIFIER
+          Rbscmlex.new_token(:identifier, literal, @form)
+        when CHAR
+          Rbscmlex.new_token(:character, literal, @form)
+        when STRING
+          Rbscmlex.new_token(:string, literal, @form)
+        when ARITHMETIC_OPS, COMPARISON_OPS
+          Rbscmlex.new_token(:op_proc, literal, @form)
+        when REAL_NUM, RATIONAL, COMPLEX, PURE_IMAG
+          Rbscmlex.new_token(:number, literal, @form)
+        else
+          Rbscmlex.new_token(:illegal, literal, @form)
+        end
+      }
+    end
+
+  end
+end

data/lib/rbscmlex/token.rb

@@ -0,0 +1,96 @@
+# frozen_string_literal: true
+
+require "json"
+
+module Rbscmlex
+
+  TOKEN_FORMS = [ :token, :hash, :json, ] # :nodoc:
+  TOKEN_DEFAULT_FORM = :token             # :nodoc:
+
+  TOKEN_TYPES = [             # :nodoc:
+    # delimiters
+    :lparen,                  # `(`
+    :rparen,                  # `)`
+    :vec_lparen,              # `#(`
+    :bytevec_lparen,          # `#u8(`
+    :quotation,               # `'`
+    :backquote,               # "`" (aka quasiquote)
+    :comma,                   # `,`
+    :comma_at,                # `,@`
+    :dot,                     # `.`
+    :semicolon,               # `;`
+    :comment_lparen,          # `#|`
+    :comment_rparen,          # `|#`
+    # value types
+    :identifier,              # `foo`
+    :boolean,                 # `#f` or `#t` (`#false` or `#true`)
+    :number,                  # `123`, `456.789`, `1/2`, `3+4i`
+    :character,               # `#\a`
+    :string,                  # `"hoge"`
+    # operators
+    :op_proc,                 # `+`, `-`, ...
+    # control
+    :illegal,
+  ]
+
+  # a structure to store properties of a token of Scheme program.
+
+  Token = Struct.new(:type, :literal) {
+    alias :to_s :literal
+  }
+
+  class << self
+
+    # Instantiates a new token object form type and literal.  The 3rd
+    # argument specifies the form of the object.  It must be one of
+    # :token, :hash, and :json.
+
+    def new_token(type, literal = nil, form = :token)
+      case form
+      when :token
+        Token.new(type, literal)
+      when :hash
+        {type: type, literal: literal}
+      when :json
+        JSON.generate(to_hash)
+      else
+        raise InvalidConversionTypeError, "cannot generate #{type} as token"
+      end
+    end
+
+    # Returns true when the argument is valid token type.
+
+    def token_type?(type)
+      TOKEN_TYPES.include?(type)
+    end
+
+    # Converts a Hash object, which has type and literal as its key,
+    # to a new token object.  The value associated to type of the Hash
+    # must be valid token type.  Otherwise, raises UnknownTokenTypeError.
+
+    def hash2token(hash)
+      if h.key?("type") and h.key?("literal")
+        type = h["type"].intern
+        raise UnknownTokenTypeError, ("got=%s" % type) unless token_type?(type)
+        literal = h["literal"]
+        Token.new(type.intern, literal)
+      else
+        raise InvalidHashError, ("got=%s" % hash)
+      end
+    end
+
+    # Converts a JSON notation, which hash type and literal, to a new
+    # token object.  The value associated to type of the Hash must be
+    # valid token type.  Otherwise, raises UnknownTokenTypeError.
+
+    def json2token(json)
+      h = JSON.parse(json)
+      begin
+        hash2token(h)
+      rescue InvalidHashError => _
+        raise InvalidJsonError, ("got=%s" % json)
+      end
+    end
+  end
+
+end

data/lib/rbscmlex/version.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+module Rbscmlex
+  VERSION = "0.1.0"
+  RELEASE = "2021-05-06"
+end

data/rbscmlex.gemspec

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+require_relative "lib/rbscmlex/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "rbscmlex"
+  spec.version       = Rbscmlex::VERSION
+  spec.authors       = ["mnbi"]
+  spec.email         = ["mnbi@users.noreply.github.com"]
+
+  spec.summary       = "A simple lexical analyzer for Scheme"
+  spec.description   = "A simple lexical analyzer for Scheme"
+  spec.homepage      = "https://github.com/mnbi/rbscmlex"
+  spec.license       = "MIT"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.7.0")
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/mnbi/rbscmlex"
+  spec.metadata["changelog_uri"] = "https://github.com/mnbi/rbscmlex/blob/main/CHANGELOG.md"
+
+  # 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(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  # Uncomment to register a new dependency of your gem
+  # spec.add_dependency "example-gem", "~> 1.0"
+
+  # For more information and examples about making a new gem, checkout our
+  # guide at: https://bundler.io/guides/creating_gem.html
+end

metadata

@@ -0,0 +1,64 @@
+--- !ruby/object:Gem::Specification
+name: rbscmlex
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- mnbi
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2021-05-06 00:00:00.000000000 Z
+dependencies: []
+description: A simple lexical analyzer for Scheme
+email:
+- mnbi@users.noreply.github.com
+executables:
+- rbscmlex
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/main.yml"
+- ".gitignore"
+- CHANGELOG.md
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- examples/simaple_parser.rb
+- exe/rbscmlex
+- lib/rbscmlex.rb
+- lib/rbscmlex/error.rb
+- lib/rbscmlex/lexer.rb
+- lib/rbscmlex/token.rb
+- lib/rbscmlex/version.rb
+- rbscmlex.gemspec
+homepage: https://github.com/mnbi/rbscmlex
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/mnbi/rbscmlex
+  source_code_uri: https://github.com/mnbi/rbscmlex
+  changelog_uri: https://github.com/mnbi/rbscmlex/blob/main/CHANGELOG.md
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.7.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.15
+signing_key:
+specification_version: 4
+summary: A simple lexical analyzer for Scheme
+test_files: []