nadoka 0.8.0

data/plugins/timestampbot.nb

@@ -0,0 +1,62 @@
+# -*-ruby-*-
+#
+# Copyright (c) 2004-2005 SASADA Koichi <ko1 at atdot.net>
+#
+# This program is free software with ABSOLUTELY NO WARRANTY.
+# You can re-distribute and/or modify this program under
+# the same terms of the Ruby's license.
+#
+#
+# $Id$
+#
+
+=begin
+
+== Abstract
+
+Add time stamp to each log.
+
+
+== Configuration
+BotConfig = [
+{
+  :name        => :TimeStampBot,
+  :interval    => 60 * 60,       # sec
+  :stampformat => '== %y/%m/%d-%H:%M:%S ==========================================',
+  :client      => false,
+}
+]
+
+=end
+
+class TimeStampBot < Nadoka::NDK_Bot
+  def bot_initialize
+    @interval    = @bot_config.fetch(:interval, 60 * 60) # default: 1 hour
+    @stampformat = @bot_config.fetch(:stampformat,
+      '== %y/%m/%d-%H:%M:%S ==========================================')
+    @client      = @bot_config.fetch(:client, false)
+    @nexttime    = nexttime
+  end
+
+  def nexttime
+    t = (Time.now.to_i + @interval)
+    Time.at(t - (t % @interval))
+  end
+  
+  def on_timer tm
+    if tm >= @nexttime
+      stamp_log
+      @nexttime = nexttime
+    end
+  end
+  
+  def stamp_log
+    msg = @nexttime.strftime(@stampformat)
+    @state.channels.each{|ch|
+      @logger.clog(ch, msg, true)
+    }
+    @logger.slog(msg, true) if @client
+  end
+end
+
+

data/plugins/titlebot.nb

@@ -0,0 +1,226 @@
+# -*-ruby-*-
+#
+# Copyright (c) 2009, 2011 Kazuhiro NISHIYAMA
+#
+# This program is free software with ABSOLUTELY NO WARRANTY.
+# You can re-distribute and/or modify this program under
+# the same terms of the Ruby's license.
+#
+
+=begin
+
+== Abstract
+
+Reply title of URL.
+
+== Configuration
+
+  BotConfig << {
+    :name => :TitleBot,
+    :ch => //,
+    :timeout => 10,
+  }
+
+=end
+
+require 'nkf'
+require 'open-uri'
+require 'timeout'
+require 'tmpdir'
+
+begin
+  require 'rubygems'
+  require 'nokogiri'
+rescue LoadError
+end
+
+module URL2Title
+  module_function
+
+  def get_title(url)
+    uri = URI(url)
+    info = { :uri => uri }
+    info[:errors] = []
+    case uri.host
+    when /localhost/, /\A127\./, /\A192\.168\./, /\A10\./
+      info[:title] = "(ignored)"
+      return info
+    end
+    uri.open(:content_length_proc => proc{|x| raise Errno::EFBIG if x && x > 1048576}) do |f|
+      info[:uri] = f.base_uri
+      body = f.read
+
+      if /\.blog\d+\.fc2\.com\z/ =~ uri.host
+        # set last content-type only
+        f.meta_add_field("content-type", f.meta["content-type"].split(/, /)[-1])
+      end
+
+      case f.content_type
+      when /\Atext\//
+        charset = f.charset{} # without block, returns "iso-8859-1"
+
+        # Content-Encoding
+        case
+        when f.content_encoding.empty?
+          # ignore
+        when f.content_encoding.any?{|c_e| /deflate/ =~ c_e }
+          require "zlib"
+          body = Zlib::Inflate.inflate(body)
+        when f.content_encoding.any?{|c_e| /gzip/ =~ c_e }
+          require "zlib"
+          body = Zlib::GzipReader.new(StringIO.new(body)).read || ''
+        end
+
+        # encoding
+        if NKF.guess(body) == NKF::BINARY
+          info[:title] = "(binary)"
+          return info
+        end
+        body = NKF.nkf("-wm0x --numchar-input", body)
+
+        title = nil
+        case uri.host
+        when /\A(?:www\.so-net\.ne\.jp)\z/
+          if %r"<title\b(?>[^<>]*)>(.*?)</title(?>[^<>]*)>"miu =~ body
+            title = $1
+          end
+          if %r!<dt id="ttl">(.*?)</dt>!miu =~ body
+            title = $1
+          end
+        else
+          if %r"<title\b(?>[^<>]*)>(.*?)</title(?>[^<>]*)>"miu =~ body
+            title = $1
+          end
+          if uri.fragment && defined?(::Nokogiri)
+            begin
+              doc = Nokogiri::HTML(body, uri.to_s, 'utf-8')
+              xpath = "//*[@id='#{uri.fragment}' or @name='#{uri.fragment}']"
+              fragment_element = doc.xpath(xpath)
+              # tDiary style
+              unless fragment_element.xpath("span[@class='sanchor']").empty?
+                fragment_element = fragment_element.xpath("..")
+              end
+              info[:fragment_text] = truncate(fragment_element.text)
+            rescue Exception => e
+              info[:errors] << e
+            end
+          end
+        end
+        info[:title] = title || body
+        return info
+      when /\Aimage\//
+        if f.respond_to?(:path) && f.path
+          info[:title] = `identify '#{f.path}'`.sub(/\A#{Regexp.quote(f.path)}/, '').strip
+          return info
+        else
+          info[:title] = "(unknown image format)"
+          return info
+        end
+      else
+        info[:title] = "#{f.content_type} #{f.size} bytes"
+        return info
+      end
+    end
+  rescue Errno::EFBIG
+    info[:title] = "(too big)"
+    return info
+  end
+
+  def truncate s
+    if /\A(?>(.{197})....)/mu =~ s
+      return $1+'...'
+    else
+      return s
+    end
+  end
+
+  def prepare_url(url)
+    url.sub(/\/\#!\//, '/')
+  end
+
+  def url2title(url)
+    url = prepare_url(url)
+    info = get_title(url)
+    info[:title] = truncate(info[:title])
+    info
+  end
+end
+
+if __FILE__ == $0
+  def u2t(url)
+    URL2Title.url2title(url)
+  rescue
+    $!.inspect
+  end
+  if ARGV.empty?
+    # TODO: test
+  else
+    ARGV.each do |url|
+      info = u2t(url)
+      p info
+      puts url
+      puts info[:title]
+    end
+  end
+  exit
+end
+
+class TitleBot < Nadoka::NDK_Bot
+  include URL2Title
+
+  def bot_initialize
+    if @bot_config.key?(:channels)
+      channels = '\A(?:' + @bot_config[:channels].collect{|ch|
+        Regexp.quote(ch)
+      }.join('|') + ')\z'
+      @available_channel = Regexp.compile(channels)
+    else
+      @available_channel = @bot_config.fetch(:ch, //)
+    end
+
+    @same_bot = @bot_config.fetch(:same_bot, /(?!)/)
+    @nkf_options = @bot_config.fetch(:nkf, "--oc=CP50221 --numchar-input --fb-xml")
+    @timeout = @bot_config.fetch(:timeout, 10)
+    @too_long_threshold = @bot_config.fetch(:too_long_threshold, 250)
+  end
+
+  def send_notice(ch, msg)
+    msg = msg.tr("\r\n", "  ")
+    if @nkf_options
+      msg = NKF.nkf(@nkf_options, msg)
+    end
+    super(ch, msg)
+  end
+
+  def on_privmsg prefix, ch, msg
+    return unless @available_channel === ch
+
+    if /https?:/ === msg
+      return if @state.channel_users(ccn(ch)).find{|x| @same_bot =~ x }
+
+      url, = URI.extract(msg, ["http", "https"])
+      info = Timeout.timeout(@timeout) do
+        url2title(url)
+      end
+      return unless info[:title]
+      if url != info[:uri].to_s
+        send_notice(ch, "title bot: #{info[:title]} - #{info[:uri]}")
+      else
+        send_notice(ch, "title bot: #{info[:title]}")
+      end
+      if info[:fragment_text]
+        # ignore when fragment_text is too long
+        if info[:fragment_text].size < @too_long_threshold
+          send_notice(ch, "title bot:: #{info[:fragment_text]}")
+        end
+      end
+      info[:errors].each do |e|
+        @manager.ndk_error e
+        send_notice(ch, "title bot error: #{e}")
+      end
+    end
+  rescue Exception => e
+    send_notice(ch, "title bot error! #{e}")
+    @manager.ndk_error e
+  end
+end

data/plugins/translatebot.nb

@@ -0,0 +1,301 @@
+# -*-ruby-*-
+#
+# Copyright (c) 2010 SASADA Koichi <ko1 at atdot.net>
+#
+# This program is free software with ABSOLUTELY NO WARRANTY.
+# You can re-distribute and/or modify this program under
+# the same terms of the Ruby's license.
+#
+
+=begin
+
+== Usage with irc client
+
+  trans> hello
+    -> translate hello as a English to Japanese.
+
+  trans:ja> hello
+    -> ditto.
+
+  trans:en,ja> hello
+    -> ditto.
+
+  trans:(([lang_from],)[lang_to])> [phrase]
+    -> translate [phrase] as lang_from to lang_to.
+
+  transj> [phrase]
+    -> translate to Japanese
+
+  transe> [phrase]
+    -> translate to English
+
+== Configuration:
+
+BotConfig = [
+{
+  :name                => :TranslateBot,
+  :ch                  => /.*/,
+  :referer             => 'http://rubyforge.org/projects/nadoka/',
+  # Register URL at http://code.google.com/intl/ja/apis/ajaxsearch/signup.html
+  # and set your URL to :referer and your API key to :api_key if you want.
+  :to_lang             => 'ja',
+  :to_lang2            => 'en',
+  :ch_kcode            => :tojis,
+},
+]
+
+=end
+
+require 'iconv'
+require 'kconv'
+require 'shellwords'
+require 'cgi'
+require 'open-uri'
+begin
+  require 'json'
+rescue LoadError
+  require 'rubygems'
+  require 'json'
+end
+
+class TranslateBot < Nadoka::NDK_Bot
+  def bot_initialize
+    @available_channel   = @bot_config[:ch] || /.*/
+    @search_default_lang = (@bot_config[:search_default_lang] || 'ja').sub(/^lang_/, '')
+    @referer = @bot_config[:referer] || 'http://rubyforge.org/projects/nadoka/'
+    @ch_kcode = @bot_config.fetch(:ch_kcode, :tojis)
+    @to_lang = @bot_config.fetch(:to_lang, 'ja')
+    @to_lang2 = @bot_config.fetch(:to_lang2, 'en')
+    @bing_appid = @bot_config.fetch(:bing_appid, nil)
+  end
+
+  def on_privmsg prefix, ch, msg
+    if @available_channel === ch and /^tr/ =~ msg
+      if response = dispatch_command(msg)
+        response.each{|r|
+          send_notice(ch, r) if r
+        }
+      end
+    end
+  end
+
+  SHORT_LANG = {'e' => 'en', 'j' => 'ja'}
+
+  def dispatch_command msg
+    begin
+      case msg
+      when /^trans(?:late)?(:(.*?))?>\s*(.+)/o
+        translate($3, *parse_trans_option($2, $3))
+      when /^trans([ej])>\s*(.+)/o
+        translate($2, nil, SHORT_LANG[$1])
+      when /^trans(?:late)?r(:(.*?))?>\s*(.+)/o
+        translate_r($3, *parse_trans_option($2, $3))
+      when /^translang>(.+)/
+        lang = $1.strip
+        desc = 'Unknown.  See http://code.google.com/intl/ja/apis/ajaxlanguage/documentation/reference.html#LangNameArray'
+        r = LANGUAGE_MAP_S2L.fetch(lang.downcase,
+                                   LANGUAGE_MAP.fetch(lang.upcase, desc))
+        "translang> #{lang} = #{r}"
+      end
+    rescue Exception => e
+      "translate bot: #{e.message}"
+    end
+  end
+
+  def detect_lang str
+    uri = "http://ajax.googleapis.com/ajax/services/language/detect?v=1.0&q="
+    uri << CGI.escape(str.toutf8)
+
+    result = open(uri, "Referer" => @referer) do |f|
+      JSON.parse(f.read)
+    end
+
+    if result["responseData"]
+      result["responseData"]["language"]
+    end
+  end
+
+  def parse_trans_option opt, str
+    case opt
+    when nil
+      from_lang = detect_lang(str)
+      to_lang = @to_lang
+      if to_lang == from_lang
+        to_lang = @to_lang2
+      end 
+      [from_lang, to_lang]
+    when /\A([\w\-]+)[, \>]([\w\-]+)\z/
+      [$1, $2]
+    when /\A([\w\-]+)\z/
+      [nil, $1]
+    else
+      raise "can't parse translation option: #{opt}"
+    end
+  end
+
+  def translate phrase, from_lang, to_lang
+    r = []
+
+    gr = translate_ggl(phrase, from_lang, to_lang)
+    r << "g:translate bot (#{gr[1]}): #{gr[0]}"
+
+    if @bing_appid
+      mr = translate_ms(phrase, from_lang, to_lang) if @bing_appid
+      r <<  "m:translate bot (#{mr[1]}): #{mr[0]}"
+    end
+    r
+  end
+
+  def translate_r phrase, from_lang, to_lang
+    rs = []
+    %w(ggl ms).each{|system|
+      r = send("translate_#{system}", phrase, from_lang, to_lang)
+      from_lang = r[2]
+      first = r[0]
+      if from_lang
+        r = send("translate_#{system}", r[0], to_lang, from_lang)
+        rs << "#{system.split(//)[0]}:trans_r (#{from_lang}>#{to_lang}>#{from_lang}): #{r[0]} (#{first})"
+      end
+    }
+    rs
+  end
+
+
+  def translate_ggl(phrase, from_lang, to_lang)
+    uri = 'http://ajax.googleapis.com/ajax/services/language/translate?v=1.0&q='
+    uri << CGI.escape(phrase.toutf8)
+    uri << "&langpair=#{from_lang}%7C#{to_lang}"
+
+    result = open(uri, "Referer" => @referer) do |f|
+      JSON.parse(f.read)
+    end
+
+    if result["responseData"]
+      text = CGI.unescapeHTML(result["responseData"]["translatedText"])
+      text = text.send(@ch_kcode) if @ch_kcode
+      from_lang ||= result["responseData"]["detectedSourceLanguage"]
+      opts = "#{from_lang}>#{to_lang}"
+      [text, opts, from_lang]
+    else
+      opts = "#{from_lang ? "from #{from_lang} to " : ''}#{to_lang}"
+      ["#{result["responseDetails"]} (#{uri})", opts]
+    end
+  end
+
+  ## ms translate
+
+  def get_result_ms result
+    # puts result
+    doc = REXML::Document.new(result)
+    doc.elements.map{|e| e.text}[0]
+  end
+
+  def translate_ms phrase, from_lang, to_lang
+    api_url = 'http://api.microsofttranslator.com/V2/Http.svc/Translate'
+    uri = "#{api_url}?appId=#{@bing_appid}&text=#{CGI.escape(phrase.toutf8)}&to=#{CGI.escape(to_lang)}"
+    begin
+      text = get_result_ms open(uri, "Referer" => @referer).read
+      text = text.send(@ch_kcode) if @ch_kcode
+      opts = "#{from_lang}>#{to_lang}"
+      [text, opts, from_lang]
+    rescue OpenURI::HTTPError => e
+      opts = "#{from_lang ? "from #{from_lang} to " : ''}#{to_lang}"
+      ["#{e.message} (uri)", opts]
+    end
+  end
+
+# copy from http://code.google.com/intl/ja/apis/ajaxlanguage/documentation/reference.html
+LANGUAGE_MAP = {
+  'AFRIKAANS' => 'af',
+  'ALBANIAN' => 'sq',
+  'AMHARIC' => 'am',
+  'ARABIC' => 'ar',
+  'ARMENIAN' => 'hy',
+  'AZERBAIJANI' => 'az',
+  'BASQUE' => 'eu',
+  'BELARUSIAN' => 'be',
+  'BENGALI' => 'bn',
+  'BIHARI' => 'bh',
+  'BULGARIAN' => 'bg',
+  'BURMESE' => 'my',
+  'CATALAN' => 'ca',
+  'CHEROKEE' => 'chr',
+  'CHINESE' => 'zh',
+  'CHINESE_SIMPLIFIED' => 'zh-CN',
+  'CHINESE_TRADITIONAL' => 'zh-TW',
+  'CROATIAN' => 'hr',
+  'CZECH' => 'cs',
+  'DANISH' => 'da',
+  'DHIVEHI' => 'dv',
+  'DUTCH'=> 'nl',  
+  'ENGLISH' => 'en',
+  'ESPERANTO' => 'eo',
+  'ESTONIAN' => 'et',
+  'FILIPINO' => 'tl',
+  'FINNISH' => 'fi',
+  'FRENCH' => 'fr',
+  'GALICIAN' => 'gl',
+  'GEORGIAN' => 'ka',
+  'GERMAN' => 'de',
+  'GREEK' => 'el',
+  'GUARANI' => 'gn',
+  'GUJARATI' => 'gu',
+  'HEBREW' => 'iw',
+  'HINDI' => 'hi',
+  'HUNGARIAN' => 'hu',
+  'ICELANDIC' => 'is',
+  'INDONESIAN' => 'id',
+  'INUKTITUT' => 'iu',
+  'ITALIAN' => 'it',
+  'JAPANESE' => 'ja',
+  'KANNADA' => 'kn',
+  'KAZAKH' => 'kk',
+  'KHMER' => 'km',
+  'KOREAN' => 'ko',
+  'KURDISH'=> 'ku',
+  'KYRGYZ'=> 'ky',
+  'LAOTHIAN'=> 'lo',
+  'LATVIAN' => 'lv',
+  'LITHUANIAN' => 'lt',
+  'MACEDONIAN' => 'mk',
+  'MALAY' => 'ms',
+  'MALAYALAM' => 'ml',
+  'MALTESE' => 'mt',
+  'MARATHI' => 'mr',
+  'MONGOLIAN' => 'mn',
+  'NEPALI' => 'ne',
+  'NORWEGIAN' => 'no',
+  'ORIYA' => 'or',
+  'PASHTO' => 'ps',
+  'PERSIAN' => 'fa',
+  'POLISH' => 'pl',
+  'PORTUGUESE' => 'pt-PT',
+  'PUNJABI' => 'pa',
+  'ROMANIAN' => 'ro',
+  'RUSSIAN' => 'ru',
+  'SANSKRIT' => 'sa',
+  'SERBIAN' => 'sr',
+  'SINDHI' => 'sd',
+  'SINHALESE' => 'si',
+  'SLOVAK' => 'sk',
+  'SLOVENIAN' => 'sl',
+  'SPANISH' => 'es',
+  'SWAHILI' => 'sw',
+  'SWEDISH' => 'sv',
+  'TAJIK' => 'tg',
+  'TAMIL' => 'ta',
+  'TAGALOG' => 'tl',
+  'TELUGU' => 'te',
+  'THAI' => 'th',
+  'TIBETAN' => 'bo',
+  'TURKISH' => 'tr',
+  'UKRAINIAN' => 'uk',
+  'URDU' => 'ur',
+  'UZBEK' => 'uz',
+  'UIGHUR' => 'ug',
+  'VIETNAMESE' => 'vi',
+  'UNKNOWN' => ''
+}
+
+LANGUAGE_MAP_S2L = LANGUAGE_MAP.invert
+end