mecab with rails on Docker

readme.md

mecab with rails on Docker

infomation

name	version
ruby	2.5.1
rails	latest
mecab	latest

mecab rapper class

mecab_client.rb

puts MecabClient.new("すもももももももものうち").parse
=>
すもも	名詞,一般,*,*,*,*,すもも,スモモ,スモモ
も	助詞,係助詞,*,*,*,*,も,モ,モ
もも	名詞,一般,*,*,*,*,もも,モモ,モモ
も	助詞,係助詞,*,*,*,*,も,モ,モ
もも	名詞,一般,*,*,*,*,もも,モモ,モモ
の	助詞,連体化,*,*,*,*,の,ノ,ノ
うち	名詞,非自立,副詞可能,*,*,*,うち,ウチ,ウチ

pp MecabClient.new("すもももももももものうち").words
=>
[#<MecabClient::Word:0x00005576e2965948
  @category1="名詞",
  @category2="一般",
  @category3="*",
  @text="すもも">,
 #<MecabClient::Word:0x00005576e29655b0
  @category1="助詞",
  @category2="係助詞",
  @category3="*",
  @text="も">,
 #<MecabClient::Word:0x00005576e2965218
  @category1="名詞",
  @category2="一般",
  @category3="*",
  @text="もも">,
 #<MecabClient::Word:0x00005576e2964e80
  @category1="助詞",
  @category2="係助詞",
  @category3="*",
  @text="も">,
 #<MecabClient::Word:0x00005576e2964ae8
  @category1="名詞",
  @category2="一般",
  @category3="*",
  @text="もも">,
 #<MecabClient::Word:0x00005576e2964750
  @category1="助詞",
  @category2="連体化",
  @category3="*",
  @text="の">,
 #<MecabClient::Word:0x00005576e29643b8
  @category1="名詞",
  @category2="非自立",
  @category3="副詞可能",
  @text="うち">]

build for mac

$ docker build -t mecab-with-rails .
$ docker run -v mount_from_path:mount_to_path -p 3000:3000 -d -it --name mecab-with-rails mecab-with-rails
$ docker exec -it mecab-with-rails bash

remove

 $ docker stop mecab-with-rails
 $ docker rm mecab-with-rails
 $ docker rmi mecab-with-rails

Dockerfile

FROM ruby:2.5.1
ENV LANG=C.UTF-8
ENV WORK_SPACE=/work

RUN mkdir ${WORK_SPACE}
WORKDIR ${WORK_SPACE}

RUN apt-get update
RUN apt-get install libmecab2 libmecab-dev mecab mecab-ipadic mecab-ipadic-utf8 mecab-utils
RUN apt-get install -y nodejs build-essential libpq-dev mysql-server
ADD Gemfile ${WORK_SPACE}/Gemfile

RUN gem install bundler
RUN bundle install
EXPOSE 3000

Gemfile

source "https://rubygems.org"

gem "rails"

mecab_client.rb

class MecabClient
  attr_reader :text, :parsed_text, :words

  def initialize(text)
    @text = text
    parse
  end

  def parse
    @parsed_text = MeCab::Tagger.new.parse @text
    @words = parsed_text_rows.map { |row| build_word(row) }
    @parsed_text
  end

  private

  def parsed_text_rows
    rows = @parsed_text.split("\n")
    rows[0...(rows.length - 1)]
  end

  def build_word(row)
    text = row.split("\t")[0]
    properties = row.split("\t")[1].split(',')
    Word.new(
      text: text,
      category1: properties[0],
      category2: properties[1],
      category3: properties[2]
    )
  end

  class Word
    attr_reader :text, :category1, :category2, :category3

    def initialize(text: nil, category1: nil, category2: nil, category3: nil)
      @text = text
      @category1 = category1
      @category2 = category2
      @category3 = category3
    end

    def noun?
      @category1 == "名詞"
    end

    def number?
      @category2 == '数'
    end
  end
end