tsub/.env.template

## .env.template
ESA_ACCESS_TOKEN=
ESA_TEAM=

## .gitignore
.env
Gemfile.lock
author_mappings.json
author_mappings_modified.json
vendor/bundle

## README.md

      
    Raw
  

              README.md
            
          
    esa の記事のカテゴリを整理するための雑スクリプト群。
一回切りの整理用で記事タイトルのフォーマットがバラバラ過ぎてトライアンドエラーでやるため、かなり雑に作っている。
各スクリプト説明


daily_report.rb

「日報」記事のカテゴリを整理するためのスクリプト


daily_report_for_no_title.rb

「日報」記事のカテゴリを整理するためのスクリプト。タイトルがない記事用
author_mappings_modified.json を参照して、記事内の Created by:  に書かれた Qiita:Team のユーザー名を元にタイトルに入れる名前を決定する


daily_report_for_no_year.rb

「日報」記事のカテゴリを整理するためのスクリプト。「年」がない記事用
記事内の Original created at:  に書かれた Qiita:Team に記事を作成した日付を元にタイトルに入れる日付を決定する
author_mappings_modified.json を参照して、記事内の Created by:  に書かれた Qiita:Team のユーザー名を元にタイトルに入れる名前を決定する


daily_report_for_multiple_days.rb

「日報」記事のカテゴリを整理するためのスクリプト。複数の日付についての記事用
author_mappings_modified.json を参照して、記事内の Created by:  に書かれた Qiita:Team のユーザー名を元にタイトルに入れる名前を決定する


create_author_mappings.rb

Qiita:Team のユーザー名とタイトルに入れたい名前のマッピング表を作るためのスクリプト
author_mappings.json が生成されるので、それをコピーして author_mappings_modified.json を作り、値の部分を手動で編集して他のスクリプトから使う
手動編集を楽にするため、esa にユーザーが存在する場合は esa のユーザー名をデフォルト値として入れている


## create_author_mappings.rb
# frozen_string_literal: true

require 'bundler/setup'
require 'esa'
require 'json'
require 'time'

search_query = 'in:"(unsorted)/all" title:日報'
daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)[\s　]*([(（].+[)）])*[\s　]*日報([\s　][(（)]\d+[)）])*\Z}
created_by_regexp = /Created by: (?<author>.+)\n/

client = Esa::Client.new(access_token: ENV.fetch('ESA_ACCESS_TOKEN'), current_team: ENV.fetch('ESA_TEAM'))

author_mappings = {}
page = 1

loop do
  posts_response = client.posts(q: search_query, page: page, per_page: 100)

  posts_response.body['posts'].each do |post|
    full_name = post['full_name']

    matches = daily_report_regexp.match(full_name)&.named_captures
    next unless matches

    body_matches = created_by_regexp.match(post['body_md'])&.named_captures
    next unless body_matches

    key = body_matches['author']
    value = post['created_by']['name'] == 'esa_bot' ? nil : post['created_by']['name']

    author_mappings.merge!(key => value)
  end

  page = posts_response.body['next_page']
  puts "page: #{page}"
  break if page.nil?
  break if page > 100 # 10000 アイテム以上はページネーションで取得できないため
end

File.open('author_mappings.json', 'w') do |f|
  f.write(JSON.pretty_generate(author_mappings))
end

## daily_report.rb
# frozen_string_literal: true

require 'bundler/setup'
require 'esa'
require 'time'

# pattern 1: "日報" が名前より先
search_query = 'in:"(unsorted)/all" title:日報'
daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})(&#47;|-)(?<month>[0-9]+)(&#47;|-)(?<day>[0-9]+)[\s　]*([(（].+[)）])*[\s　]*日報[\s　]*(?<name>.+)}

# pattern 2: "日報" が名前より先で (1) などの数字入り
# search_query = 'in:"(unsorted)/all" title:日報 title:"(1)"'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)[\s　]*([(（].+[)）])*[\s　]*日報[\s　]*(?<name>.+)[\s　]([(（)]\d+[)）])*\Z}

# pattern 3: 週報
# search_query = 'in:"(unsorted)/all" title:週報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})(&#47;|-)(?<month>[0-9]+)(&#47;|-)(?<day>[0-9]+)[\s　]*(Mon|Tue|Wed|Thu|Fri|Sat|Sun)*[\s　](?<name>(ほぼ|隔)*週報.+)}

# pattern 4: 週報その２
# search_query = 'in:"(unsorted)/all" title:週報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})(&#47;|-)(?<month>[0-9]+)(&#47;|-)(?<day>[0-9]+)(?<name>(ほぼ|隔)*週報.+)}

# 特殊フォーマットその１
# search_query = 'in:"(unsorted)/all" title:"日報 201"'
# daily_report_regexp = %r{\A\(unsorted\)/all/日報[\s　](?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)[\s　]*([(（].+[)）])[\s　]*-[\s　]*(?<name>.+)}

# 特殊フォーマットその２
# search_query = 'in:"(unsorted)/all" title:"日報 201"'
# daily_report_regexp = %r{\A\(unsorted\)/all/日報[\s　](?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)[\s　]*([(（].+[)）])[\s　]*(?<name>.+)}

# 特殊フォーマットその３
# search_query = 'in:"(unsorted)/all" title:"日報 201"'
# daily_report_regexp = %r{\A\(unsorted\)/all/日報[\s　](?<year>[0-9]{4})(&#47;|\s|　)(?<month>[0-9]+)(&#47;|\s|　)(?<day>[0-9]+)[\s　](?<name>.+)}

# 特殊フォーマットその４
# search_query = 'in:"(unsorted)/all" title:"日報 201"'
# daily_report_regexp = %r{\A\(unsorted\)/all/日報[\s　](?<year>[0-9]{4})(?<month>[0-9]{2})(?<day>[0-9]{2})[\s　](?<name>.+)}

# 特殊フォーマットその５
# search_query = 'in:"(unsorted)/all" title:日報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]{2})&#47;(?<day>[0-9]{2})([(（].+[)）])[\s　](?<name>.+)[\s　]日報(?<additional_title>[\s　].+)*}

# 特殊フォーマットその６
# search_query = 'in:"(unsorted)/all" title:日報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]{2})&#47;(?<day>[0-9]{2})[\s　](Mon|Tue|Wed|Thu|Fri|Sat|Sun)[\s　]日報[\s　](?<name>.+)}

# 特殊フォーマットその７
# search_query = 'in:"(unsorted)/all" title:"\'s 日報"'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]{2})&#47;(?<day>[0-9]{2})[\s　](?<name>.+)}

# 特殊フォーマットその８
# search_query = 'in:"(unsorted)/all" title:日報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]{2})&#47;(?<day>[0-9]{2})[\s　](?<name>.+)[\s　]日報\Z}

# 特殊フォーマットその９
# search_query = 'in:"(unsorted)/all" title:日報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]{2})&#47;(?<day>[0-9]{2})[\s　]*[<＜][\s　]*日報[\s　]*[>＞][\s　]*(?<name>.+)}

# 後から修正用
# search_query = 'in:"(unsorted)/日報" title:"(1)"'
# daily_report_regexp = %r{\A\(unsorted\)/日報/(?<year>[0-9]{4})/(?<month>[0-9]+)/(?<day>[0-9]+)(\s\(.\))/(?<name>.+)[\s　]([(（)]\d+[)）])*\Z}

client = Esa::Client.new(access_token: ENV.fetch('ESA_ACCESS_TOKEN'), current_team: ENV.fetch('ESA_TEAM'))

update_posts = []
page = 1

loop do
  posts_response = client.posts(q: search_query, page: page, per_page: 100)

  posts_response.body['posts'].each do |post|
    number = post['number']
    full_name = post['full_name']

    matches = daily_report_regexp.match(full_name)&.named_captures
    next unless matches

    begin
      date = Date.parse("#{matches['year']}/#{matches['month']}/#{matches['day']}")
    rescue ArgumentError
      puts matches
      next
    end

    wday = %w[日 月 火 水 木 金 土][date.wday]
    renamed_category = "(unsorted)/日報/#{date.strftime('%Y/%2m/%2d')} (#{wday})"
    name = matches['additional_title'] ? "#{matches['name']}#{matches['additional_title']}" : matches['name']

    update_post = { number: number, name: name, category: renamed_category }
    puts "before: '#{full_name}', after: '#{update_post[:category]}/#{update_post[:name]}'"
    update_posts << update_post
  end

  page = posts_response.body['next_page']
  puts "page: #{page}"
  break if page.nil?
  break if page > 100 # 10000 アイテム以上はページネーションで取得できないため
end

puts "update_posts: #{update_posts.count}"

if ARGV[0] == 'run'
  update_posts.each do |update_post|
    client.update_post(update_post[:number], name: update_post[:name], category: update_post[:category])
  end
end

## daily_report_for_multiple.rb
# frozen_string_literal: true

require 'bundler/setup'
require 'esa'
require 'json'
require 'time'

# pattern 1
search_query = 'in:"(unsorted)/all" title:日報'
daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]{1,2})&#47;(?<multiple_days>[0-9]{1,2}[\,、\-~〜～・ &＆+＋]+[0-9]{1,2})[\s　]*日報[\s　](?<name>.+)}

# pattern 2
# search_query = 'in:"(unsorted)/all" title:日報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<multiple_days>[0-9]+[\,、\-~〜][0-9]+)[\s　]([(（].+[)）])[\s　]日報(?<name>[\s　].+)*}

# pattern 3: 週報
# search_query = 'in:"(unsorted)/all" title:週報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})(&#47;|-)(?<month>[0-9]+)(&#47;|-)(?<multiple_days>[0-9]{1,2}[\,、\-~〜～・ &＆+＋]+[0-9]{1,2})[\s　]*(?<name>週報.+)}

created_by_regexp = /Created by: (?<author>.+)\n/
created_at_regexp = /Original created at: (?<created_at>.+)\n/

author_mappings = {}
File.open('author_mappings_modified.json') do |f|
  author_mappings = JSON.parse(f.read)
end

client = Esa::Client.new(access_token: ENV.fetch('ESA_ACCESS_TOKEN'), current_team: ENV.fetch('ESA_TEAM'))

update_posts = []
page = 1

loop do
  posts_response = client.posts(q: search_query, page: page, per_page: 100)

  posts_response.body['posts'].each do |post|
    number = post['number']
    full_name = post['full_name']

    matches = daily_report_regexp.match(full_name)&.named_captures
    next unless matches

    created_at_matches = created_at_regexp.match(post['body_md'])&.named_captures
    next unless created_at_matches

    created_at = Time.parse(created_at_matches['created_at'])

    wday = %w[日 月 火 水 木 金 土][created_at.wday]
    renamed_category = "(unsorted)/日報/#{created_at.strftime('%Y/%2m/%2d')} (#{wday})"

    body_matches = created_by_regexp.match(post['body_md'])&.named_captures
    next unless body_matches

    qiita_team_author = body_matches['author'].delete("\r")
    name = matches['name'] || author_mappings[qiita_team_author]

    if name.nil?
      p "unmapped name: '#{qiita_team_author}'"
      next
    end

    update_post = { number: number, name: "#{matches['month']}&#47;#{matches['multiple_days']} #{name}", category: renamed_category }
    puts "before: '#{full_name}', after: '#{update_post[:category]}/#{update_post[:name]}'"
    update_posts << update_post
  end

  page = posts_response.body['next_page']
  puts "page: #{page}"
  break if page.nil?
  break if page > 100 # 10000 アイテム以上はページネーションで取得できないため
end

puts "update_posts: #{update_posts.count}"

if ARGV[0] == 'run'
  update_posts.each do |update_post|
    client.update_post(update_post[:number], name: update_post[:name], category: update_post[:category])
  end
end

## daily_report_for_no_title.rb
# frozen_string_literal: true

require 'bundler/setup'
require 'esa'
require 'json'
require 'time'

# pattern 1: タイトルなし
search_query = 'in:"(unsorted)/all" title:日報'
daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})(&#47;|-)(?<month>[0-9]+)(&#47;|-)(?<day>[0-9]+)[\s　]*([(（].+[)）])*[\s　]*日報([\s　][(（)]\d+[)）])*\Z}

# pattern 2: (1) などの数字のみ
# search_query = 'in:"(unsorted)/all" title:日報 title:"(1)"'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)[\s　]*([(（].+[)）])*[\s　]*日報([\s　][(（)]\d+[)）])*\Z}

# pattern 3: 週報
# search_query = 'in:"(unsorted)/all" title:週報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})(&#47;|-)(?<month>[0-9]+)(&#47;|-)(?<day>[0-9]+)[\s　]*週報[\s　]*\Z}

# 特殊フォーマットその１
# search_query = 'in:"(unsorted)/all" title:"日報:"'
# daily_report_regexp = %r{\A\(unsorted\)/all/日報[:：][\s　]*(?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)}

# 特殊フォーマットその２
# search_query = 'in:"(unsorted)/all" title:"日報 201"'
# daily_report_regexp = %r{\A\(unsorted\)/all/日報[\s　:：]+(?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)[\s　]*([(（].+[)）])}

# 特殊フォーマットその３
# search_query = 'in:"(unsorted)/all" title:"日報 201"'
# daily_report_regexp = %r{\A\(unsorted\)/all/日報[\s　:：]+(?<year>[0-9]{4})&#47;(?<month>[0-9]+)&#47;(?<day>[0-9]+)\Z}

# 後から修正用
# search_query = 'in:"(unsorted)/日報" title:"(1)"'
# daily_report_regexp = %r{\A\(unsorted\)/日報/(?<year>[0-9]{4})/(?<month>[0-9]+)/(?<day>[0-9]+)(\s\(.\))/([(（)]\d+[)）])*\Z}

created_by_regexp = /Created by: (?<author>.+)\n/

author_mappings = {}
File.open('author_mappings_modified.json') do |f|
  author_mappings = JSON.parse(f.read)
end

client = Esa::Client.new(access_token: ENV.fetch('ESA_ACCESS_TOKEN'), current_team: ENV.fetch('ESA_TEAM'))

update_posts = []
page = 1

loop do
  posts_response = client.posts(q: search_query, page: page, per_page: 100)

  posts_response.body['posts'].each do |post|
    number = post['number']
    full_name = post['full_name']

    matches = daily_report_regexp.match(full_name)&.named_captures
    next unless matches

    begin
      date = Date.parse("#{matches['year']}/#{matches['month']}/#{matches['day']}")
    rescue ArgumentError
      puts matches
      next
    end

    wday = %w[日 月 火 水 木 金 土][date.wday]

    renamed_category = "(unsorted)/日報/#{date.strftime('%Y/%2m/%2d')} (#{wday})"

    body_matches = created_by_regexp.match(post['body_md'])&.named_captures
    next unless body_matches

    qiita_team_author = body_matches['author'].delete("\r")
    name = author_mappings[qiita_team_author]

    if name.nil?
      p "unmapped name: '#{qiita_team_author}'"
      next
    end

    update_post = { number: number, name: name, category: renamed_category }
    puts "before: '#{full_name}', after: '#{update_post[:category]}/#{update_post[:name]}'"
    update_posts << update_post
  end

  page = posts_response.body['next_page']
  puts "page: #{page}"
  break if page.nil?
  break if page > 100 # 10000 アイテム以上はページネーションで取得できないため
end

puts "update_posts: #{update_posts.count}"

if ARGV[0] == 'run'
  update_posts.each do |update_post|
    client.update_post(update_post[:number], name: update_post[:name], category: update_post[:category])
  end
end

## daily_report_for_no_year.rb
# frozen_string_literal: true

require 'bundler/setup'
require 'esa'
require 'json'
require 'time'

# pattern 1
search_query = 'in:"(unsorted)/all" title:日報'
daily_report_regexp = %r{\A\(unsorted\)/all/(?<month>[0-9]{1,2})&#47;(?<day>[0-9]{1,2})[\s　]日報[\s　](?<name>.+)}

# pattern 2: 週報
# search_query = 'in:"(unsorted)/all" title:週報'
# daily_report_regexp = %r{\A\(unsorted\)/all/(?<month>[0-9]{1,2})(&#47;|-)(?<day>[0-9]{1,2})[\s　]*(Mon|Tue|Wed|Thu|Fri|Sat|Sun)*[\s　](?<name>(ほぼ)*週報.+)}

created_by_regexp = /Created by: (?<author>.+)\n/
created_at_regexp = /Original created at: (?<created_at>.+)\n/

author_mappings = {}
File.open('author_mappings_modified.json') do |f|
  author_mappings = JSON.parse(f.read)
end

client = Esa::Client.new(access_token: ENV.fetch('ESA_ACCESS_TOKEN'), current_team: ENV.fetch('ESA_TEAM'))

update_posts = []
page = 1

loop do
  posts_response = client.posts(q: search_query, page: page, per_page: 100)

  posts_response.body['posts'].each do |post|
    number = post['number']
    full_name = post['full_name']

    matches = daily_report_regexp.match(full_name)&.named_captures
    next unless matches

    created_at_matches = created_at_regexp.match(post['body_md'])&.named_captures
    next unless created_at_matches

    created_at = Time.parse(created_at_matches['created_at'])

    wday = %w[日 月 火 水 木 金 土][created_at.wday]
    renamed_category = "(unsorted)/日報/#{created_at.strftime('%Y/%2m/%2d')} (#{wday})"

    body_matches = created_by_regexp.match(post['body_md'])&.named_captures
    next unless body_matches

    qiita_team_author = body_matches['author'].delete("\r")
    name = matches['name'] || author_mappings[qiita_team_author]

    if name.nil?
      p "unmapped name: '#{qiita_team_author}'"
      next
    end

    update_post = { number: number, name: name, category: renamed_category }
    puts "before: '#{full_name}', after: '#{update_post[:category]}/#{update_post[:name]}'"
    update_posts << update_post
  end

  page = posts_response.body['next_page']
  puts "page: #{page}"
  break if page.nil?
  break if page > 100 # 10000 アイテム以上はページネーションで取得できないため
end

puts "update_posts: #{update_posts.count}"

if ARGV[0] == 'run'
  update_posts.each do |update_post|
    client.update_post(update_post[:number], name: update_post[:name], category: update_post[:category])
  end
end

## Gemfile
# frozen_string_literal: true

source "https://rubygems.org"

git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }

gem "esa", "~> 1.14"
	.env
	Gemfile.lock
	author_mappings.json
	author_mappings_modified.json
	vendor/bundle
	# frozen_string_literal: true

	require 'bundler/setup'
	require 'esa'
	require 'json'
	require 'time'

	search_query = 'in:"(unsorted)/all" title:日報'
	daily_report_regexp = %r{\A\(unsorted\)/all/(?<year>[0-9]{4})/(?<month>[0-9]+)/(?<day>[0-9]+)[\s　]([(（].+[)）])[\s　]日報([\s　][(（)]\d+[)）])\Z}
	created_by_regexp = /Created by: (?<author>.+)\n/

	client = Esa::Client.new(access_token: ENV.fetch('ESA_ACCESS_TOKEN'), current_team: ENV.fetch('ESA_TEAM'))

	author_mappings = {}
	page = 1

	loop do
	posts_response = client.posts(q: search_query, page: page, per_page: 100)

	posts_response.body['posts'].each do \|post\|
	full_name = post['full_name']

	matches = daily_report_regexp.match(full_name)&.named_captures
	next unless matches

	body_matches = created_by_regexp.match(post['body_md'])&.named_captures
	next unless body_matches

	key = body_matches['author']
	value = post['created_by']['name'] == 'esa_bot' ? nil : post['created_by']['name']

	author_mappings.merge!(key => value)
	end

	page = posts_response.body['next_page']
	puts "page: #{page}"
	break if page.nil?
	break if page > 100 # 10000 アイテム以上はページネーションで取得できないため
	end

	File.open('author_mappings.json', 'w') do \|f\|
	f.write(JSON.pretty_generate(author_mappings))
	end
	# frozen_string_literal: true

	source "https://rubygems.org"

	git_source(:github) {\|repo_name\| "https://github.com/#{repo_name}" }

	gem "esa", "~> 1.14"