bunpa 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: b68a4b60aa085901f9797f5beea784f11ac322ac
+  data.tar.gz: 08ab437798631a5f11b0a8d6b4311345152d31c7
+SHA512:
+  metadata.gz: 1ae1d695acfb725315d2973409f2f0cb8d9c4d4951258a779c90d1e960c42bfb4f67eb4a78c719cf90ad00f3146fde10edac7fc63402ac52fa7b07e22472096e
+  data.tar.gz: 6c2715bfba32f2c9eac30f07de1f03d868ed1a1d45158f8b46b40161a31fcc00d6e66e1149bcdc84a028e69c60af8dc14d1e592aedf1bd36a08d6204d46119a8

data/README.md

@@ -0,0 +1,57 @@
+Bunpa
+==========================
+
+Bunpa is an extremely simple wrapper around the MeCab Japanese grammar parser. It was designed with two key features in mind:
+
+1. Simplicity - only returns the text and major part of speech for each component
+2. Completeness - ensure that whitespace and any unknown characters are preserved
+
+## Background
+
+Bunpa parses Japanese text into a set of ordered components. Each component represents either a part of speech (noun, verb, etc.) or formatting (whitespace, etc.) All components have a text value (exactly as they appear in the text provided) and kind (usually part of speech).
+
+All grammatical information is provided by the excellent [MeCab](http://mecab.googlecode.com/svn/trunk/mecab/doc/index.html) Japanese part of speech and morphological analyser. Formatting information is inserted into the set of components in a post processing step (it is not done by MeCab). These components have a fake 'kind' assigned to them. Currently the following kinds of formatting components are handled by Bunpa:
+* spaces (スペース)
+* tabs (タブ)
+* newlines (改行)
+
+Any components that cannot be identified by either MeCab or Bunpa are marked as unknown (未知).
+
+## Installation
+
+From within your Rails application's base directory:
+
+1. Edit your Gemfile and add:
+
+        gem 'bunpa'
+
+2. Install the gem:
+
+        bundle
+
+## Usage
+
+Bunpa operates as a very simple parser. It returns the components it identifies in an Enumerator in the same order as they appear in the document.
+
+Basic usage is as follows:
+
+```
+require 'bunpa'
+
+# Create the parser
+parser = Bunpa::JapaneseTextParser.new
+
+# Get an enumerable of Bunpa::Text::Components
+components = parser.parse("こんにちは！お元気ですか。")
+
+components.each do |component|
+  puts "#{component.text}\t(#{component.kind}"
+end
+
+```
+
+For a slightly more detailed example, see the `usage_example.rb` script in the `bin` directory.
+
+## Notes
+
+This is very much a work in progress - it only has minimal testing at the moment, so use at your own risk :)

data/spec/parser_spec.rb

@@ -0,0 +1,31 @@
+require 'spec_helper'
+
+describe Bunpa::JapaneseTextParser do
+  describe "#parse" do
+    before(:each) do
+      @content = <<TEST
+ほんと、悲し過ぎるわよね。 でも、しかたないな。
+そうだよ！「Very sad」	だもん。
+TEST
+      @parser = Bunpa::JapaneseTextParser.new
+    end
+ 
+    it "converts a Japanese text string into a list of components of different types (grammar, formatting, etc.) in the same order as they appear in the string" do
+      expect(@parser.parse(@content).map { |c| c.text }.join).to eq(@content)
+    end
+
+    context "component categories" do
+      it "marks spaces as component kind スペース" do
+        expect(@parser.parse(" ").first.kind).to eq("スペース")
+      end
+
+      it "marks newlines as component kind 改行" do
+        expect(@parser.parse("\n").first.kind).to eq("改行")
+      end
+
+      it "marks tabs as component kind タブ" do
+        expect(@parser.parse("\t").first.kind).to eq("タブ")
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,20 @@
+require 'bundler/setup'
+Bundler.setup
+
+require 'bunpa'
+
+RSpec.configure do |config|
+  # ## Mock Framework
+  #
+  # If you prefer to use mocha, flexmock or RR, uncomment the appropriate line:
+  #
+  # config.mock_with :mocha
+  # config.mock_with :flexmock
+  # config.mock_with :rr
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = "random"
+end

metadata

@@ -0,0 +1,78 @@
+--- !ruby/object:Gem::Specification
+name: bunpa
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Daniel Carter
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-06-28 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mecab
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.996'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.996'
+- !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 wrapper around the MeCab Japanese grammar parser than maintains
+  formatting.
+email: clownba0t@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- spec/parser_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/clownba0t/bunpa
+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: 2.3.0
+signing_key: 
+specification_version: 4
+summary: bunpa v0.2.0
+test_files:
+- spec/spec_helper.rb
+- spec/parser_spec.rb
+has_rdoc: