src_lexer 0.0.1

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    YWNmNzQ2N2JjN2UyNTVhM2UwZTE3ZmVkMWVlZjE4OTJiZGRkNGUwNg==
+  data.tar.gz: !binary |-
+    ZWFmYTU0NmVjYTkxZWI5NjNkNTQ3Zjc4ZjNlMTkzNjQwMTFkOWI2Mg==
+SHA512:
+  metadata.gz: !binary |-
+    MGY0M2JlNWZkNjY3ZTEzNjk5M2E4OTZlMjBhYmU4Mzg5OGI3ZGZjNWQyNTZm
+    NzliYjU2OGFmNDk2OWJkZDY5ZGJlMmYzMTViMjhkYmMwMDk2NmUyYzBhYjdl
+    ZDFmNmExOGZkNTA2YTY2NDVjOGI3YzVkZjlhYzI4ZDU1YzViMzI=
+  data.tar.gz: !binary |-
+    ZmE5YWQ3YTViY2FmZWE0YTRlMWQxODhlZThkMDA0ZWExMDNiODQwNGI0ZTQ1
+    ZDRkYzAyZTczZDhiNGJiZjVjYWNhMDI5M2Y5NDBlNmI3ZjBkZTUxODlkMzM4
+    MDNiNGI3ZjBiZjFlM2ZmMmY4MWYxZTVjM2ZhMjEzNDIwNGM1ZGM=

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - 1.9.3

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in src_lexer.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 kkikzk
+
+MIT License
+
+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 +1,29 @@
+# SrcLexer
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'src_lexer'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install src_lexer
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it ( http://github.com/<my-github-username>/src_lexer/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/src_lexer

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+
+require 'src_lexer'

data/lib/src_lexer/version.rb

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

data/lib/src_lexer.rb

@@ -0,0 +1,170 @@
+# -*- encoding: utf-8 -*-
+require "src_lexer/version"
+
+module SrcLexer
+  class Token
+    attr_reader :str, :line_no, :char_no
+
+    def initialize(str, line_no, char_no)
+      @str = str
+      @line_no = line_no
+      @char_no = char_no
+    end
+
+    def ==(other_object)
+      @str == other_object.str && @line_no == other_object.line_no && @char_no == other_object.char_no
+    end
+  end
+
+  class Lexer
+    END_TOKEN = [false, nil]
+    attr_reader :keywords, :symbols, :line_comment_marker, :comment_markers, :tokens, :str
+
+    def initialize(keywords, symbols, line_comment_marker, comment_marker)
+      @keywords = ((keywords.nil?) ? [] : keywords.uniq.compact)
+      @symbols = ((symbols.nil?) ? [] : symbols.uniq.compact)
+      @line_comment_marker = ((line_comment_marker.nil?) ? '' : line_comment_marker)
+      @comment_markers = ((comment_marker.nil?) ? ['', ''] : comment_marker)
+    end
+
+    def analyze(str)
+      @str = str
+      tokenize
+    end
+
+    def pop_token
+      token = @tokens.shift
+      if token.nil? then
+        return END_TOKEN
+      end
+      case token[0]
+      when /^[\d]+[\.]?[\d]*\z/
+        [:NUMBER, Token.new(token[0], token[1], token[2])]
+      when /^\"(.*)\"\z/m
+        [:STRING, Token.new(token[0], token[1], token[2])]
+      else
+        id = is_reserved?(token[0]) ? token[0] : :IDENT
+        [id, Token.new(token[0], token[1], token[2])]
+      end
+    end
+
+    private
+
+    class StringIterator
+      attr_reader :index
+
+      def initialize(str)
+        @str = str
+        @index = 0
+        @marked_pos = -1
+      end
+
+      def mark_set
+        @marked_pos = @index
+      end
+
+      def is(target_string)
+        return false if target_string.length.zero?
+        end_pos = (@index + target_string.length - 1)
+        @str[@index..end_pos] == target_string
+      end
+
+      def is_in(target_list)
+        target_list.find { |target| is(target) } != nil
+      end
+
+      def move_next
+        @index += 1
+      end
+
+      def move_to_the_end_of_the_line
+        @index += (@str[@index..-1] =~ /$/) - 1
+      end
+
+      def move_to(target)
+        esceped_target = Regexp.escape(target)
+        @index += (@str[@index..-1] =~ /#{esceped_target}/m) + target.length - 1
+      end
+
+      def [](range)
+        @str[range]
+      end
+
+      def <(pos)
+        @index < pos
+      end
+
+      def char
+        @str[@index]
+      end
+
+      def is_white_space
+        /[\s]/.match(char)
+      end
+
+      def info(pos)
+        [0, 0] if pos == 0
+        line_no, char_no = 1, 0
+        @str[0..pos].each_char do |char|
+          if /\n/.match(char)
+            line_no += 1
+            char_no = 0
+          else
+            char_no += 1
+          end
+        end
+        [line_no, char_no]
+      end
+
+      def marked?
+        @marked_pos != -1
+      end
+
+      def shift
+        result = @str[@marked_pos..(@index - 1)]
+        line_no_and_char_no = info(@marked_pos) 
+        @marked_pos = -1
+        return result, *line_no_and_char_no
+      end
+    end
+
+    def tokenize()
+      @tokens = []
+      iterator = StringIterator.new(@str)
+
+      while iterator < @str.length do
+        if iterator.is_white_space then
+          @tokens.push iterator.shift if iterator.marked?
+        elsif iterator.is(@line_comment_marker) then
+          @tokens.push iterator.shift if iterator.marked?
+          iterator.move_to_the_end_of_the_line
+        elsif iterator.is(@comment_markers[0]) then
+          @tokens.push iterator.shift if iterator.marked?
+          iterator.move_to(@comment_markers[1])
+        elsif iterator.is('"') then
+          @tokens.push iterator.shift if iterator.marked?
+          iterator.mark_set
+          iterator.move_next
+          iterator.move_to('"')
+          iterator.move_next
+          @tokens.push iterator.shift
+          next
+        elsif iterator.is_in(@symbols) then
+          @tokens.push iterator.shift if iterator.marked?
+          symbol = @symbols.find { |symbol| iterator.is(symbol) }
+          @tokens.push [iterator[iterator.index..(iterator.index + symbol.length - 1)], *iterator.info(iterator.index)]
+          (symbol.length - 1).times { iterator.move_next }
+        elsif !iterator.marked? then
+          iterator.mark_set
+        end
+        iterator.move_next
+      end
+
+      @tokens.push iterator.shift if iterator.marked?
+    end
+
+    def is_reserved?(token)
+      @keywords.include?(token) || @symbols.include?(token)
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,3 @@
+# -*- encoding: utf-8 -*-
+$LOAD_PATH.unshift File.expand_path('../../lib', __FILE__)
+require 'src_lexer'

data/spec/src_lexer_spec.rb

@@ -0,0 +1,105 @@
+# -*- encoding: utf-8 -*-
+require_relative './spec_helper'
+
+describe SrcLexer do
+  it 'should have a version number' do
+    SrcLexer::VERSION.should_not be_nil
+  end
+end
+
+describe SrcLexer::Lexer, 'with empty string' do  
+  it 'should return Lexer::END_TOKEN' do
+    sut = SrcLexer::Lexer.new(nil, nil, nil, nil)
+    sut.analyze('')
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+end
+
+describe SrcLexer::Lexer, 'with keyword definitions' do
+  it 'should recognize keywords' do
+    sut = SrcLexer::Lexer.new(['struct', 'enum'], nil, nil, nil)
+    sut.analyze('struct structenum enum')
+    sut.pop_token.should == ['struct', SrcLexer::Token.new('struct', 1, 1)]
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('structenum', 1, 8)]
+    sut.pop_token.should == ['enum', SrcLexer::Token.new('enum', 1, 19)]
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+  it 'should reduce keyword duplication' do
+    sut = SrcLexer::Lexer.new(['struct', 'struct'], nil, nil, nil)
+    sut.keywords.should == ['struct']
+  end
+  it 'should ignore nil keyword' do
+    sut = SrcLexer::Lexer.new(['struct', nil, 'enum'], nil, nil, nil)
+    sut.keywords.should == ['struct', 'enum']
+  end
+end
+
+describe SrcLexer::Lexer, 'with symbol definitions' do
+  it 'should recognize symbols' do
+    sut = SrcLexer::Lexer.new(nil, ['..', ','], nil, nil)
+    sut.analyze('.. A ,')
+    sut.pop_token.should == ['..', SrcLexer::Token.new('..', 1, 1)]
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('A', 1, 4)]
+    sut.pop_token.should == [',', SrcLexer::Token.new(',', 1, 6)]
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+  it 'should recognize symbols(,) if continues like "A,B"' do
+    sut = SrcLexer::Lexer.new(nil, [','], nil, nil)
+    sut.analyze('A,B')
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('A', 1, 1)]
+    sut.pop_token.should == [',', SrcLexer::Token.new(',', 1, 2)]
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('B', 1, 3)]
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+  it 'should reduce symbol duplication' do
+    sut = SrcLexer::Lexer.new(nil, [',', ','], nil, nil)
+    sut.symbols.should == [',']
+  end
+  it 'should ignore nil keyword' do
+    sut = SrcLexer::Lexer.new(nil, ['{', nil, '}'], nil, nil)
+    sut.symbols.should == ['{', '}']
+  end
+end
+
+describe SrcLexer::Lexer, 'with line comment marker' do
+  it 'should recognize line comment' do
+    sut = SrcLexer::Lexer.new(nil, nil, '//', nil)
+    sut.analyze(<<-'EOS')
+      A//comment
+      B
+    EOS
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('A', 1, 7)]
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('B', 2, 7)]
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+  it 'should recognize multi line comment' do
+    sut = SrcLexer::Lexer.new(nil, nil, '//', ['/*', '*/'])
+    sut.analyze(<<-'EOS')
+      A/*comment
+      B//still in comment*/C
+    EOS
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('A', 1, 7)]
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('C', 2, 28)]
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+end
+
+describe SrcLexer::Lexer do
+  it 'should analyze number string' do
+    sut = SrcLexer::Lexer.new(nil, nil, nil, nil)
+    sut.analyze('9 1.5')
+    sut.pop_token.should == [:NUMBER, SrcLexer::Token.new("9", 1, 1,)]
+    sut.pop_token.should == [:NUMBER, SrcLexer::Token.new("1.5", 1, 3)]
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+  it 'should analyze string literal' do
+    sut = SrcLexer::Lexer.new(nil, nil, '//', ['/*', '*/'])
+    sut.analyze('A"//"B"/**/"C')
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('A', 1, 1)]
+    sut.pop_token.should == [:STRING, SrcLexer::Token.new('"//"', 1, 2)]
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('B', 1, 6)]
+    sut.pop_token.should == [:STRING, SrcLexer::Token.new('"/**/"', 1, 7)]
+    sut.pop_token.should == [:IDENT, SrcLexer::Token.new('C', 1, 13)]
+    sut.pop_token.should == SrcLexer::Lexer::END_TOKEN
+  end
+end

data/src_lexer.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'src_lexer/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "src_lexer"
+  spec.version       = SrcLexer::VERSION
+  spec.authors       = ["kkikzk"]
+  spec.email         = ["kkikzk@gmail.com"]
+  spec.summary       = %q{A simple source file lexer}
+  spec.description   = ""
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.5"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
+end

metadata

@@ -0,0 +1,102 @@
+--- !ruby/object:Gem::Specification
+name: src_lexer
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- kkikzk
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-04-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+- !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: ''
+email:
+- kkikzk@gmail.com
+executables:
+- src_lexer
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- .travis.yml
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/src_lexer
+- lib/src_lexer.rb
+- lib/src_lexer/version.rb
+- spec/spec_helper.rb
+- spec/src_lexer_spec.rb
+- src_lexer.gemspec
+homepage: ''
+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: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: A simple source file lexer
+test_files:
+- spec/spec_helper.rb
+- spec/src_lexer_spec.rb