twitter_ebooks 2.2.6 → 2.2.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b50e63b5ee0a1fd5149d7ecd0157c10831433ecc
-  data.tar.gz: e77e9ac3f6605dac9effe22f856a02b7e9f1df8a
+  metadata.gz: 69ac58617389d783dde49b9295bc12f00380ee2f
+  data.tar.gz: 6afd456d5eae6d74a8330240c40e427640255dda
 SHA512:
-  metadata.gz: 1cf7e279e5f1c35b151f4af5296ea65de049bce7718502828381d9bbd9008898954b1093764eb7046f9e48a029d70629cea052e2747926a827ecd48b31b874e5
-  data.tar.gz: 88ebd09ae226e30954fa287617c09775488536f897a9d025cdde1511da660df42d8c63fd760503a2766c680266c656a9f32c96488016951b4d79ceac0d48c096
+  metadata.gz: 4990cbbe8e4fa74bbf8b935598474d245de148464679b85a1908abe9612653849981f38343fb7f1706b241cc85ba166d45a89a8ee030d43878c91361f5d2dff4
+  data.tar.gz: 67bdec6974c5aea4bebf299045653b3f71cb3a69becd49b926c956bd22da546d01fc276334034c39175a9f329bf325535344a9e77f2036ab76085b95073c49a1

data/.rspec

@@ -0,0 +1 @@
+--color

data/Gemfile

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

data/README.md

@@ -1,4 +1,4 @@
-# twitter\_ebooks 2.2.6
+# twitter\_ebooks 2.2.7
 
 Rewrite of my twitter\_ebooks code. While the original was solely a tweeting Markov generator, this framework helps you build any kind of interactive twitterbot which responds to mentions/DMs. See [ebooks\_example](https://github.com/mispy/ebooks_example) for an example of a full bot.
 
@@ -50,6 +50,7 @@ Ebooks::Bot.new("abby_ebooks") do |bot|
     # Tweet something every 24 hours
     # See https://github.com/jmettraux/rufus-scheduler
     # bot.tweet("hi")
+	# bot.pictweet("hi", "cuteselfie.jpg", ":possibly_sensitive => true")
   end
 end
 ```

data/lib/twitter_ebooks/bot.rb

@@ -43,16 +43,15 @@ module Ebooks
         config.oauth_token_secret = @oauth_token_secret
       end
 
-      Twitter.configure do |config|
+      @twitter = Twitter::REST::Client.new do |config|
         config.consumer_key = @consumer_key
         config.consumer_secret = @consumer_secret
-        config.oauth_token = @oauth_token
-        config.oauth_token_secret = @oauth_token_secret
+        config.access_token = @access_token
+        config.access_token_secret = @access_token_secret
       end
 
       needs_stream = [@on_follow, @on_message, @on_mention, @on_timeline].any? {|e| !e.nil?}
 
-      @twitter = Twitter::Client.new
       @stream = TweetStream::Client.new if needs_stream
     end
 
@@ -89,19 +88,19 @@ module Ebooks
       end
 
       @stream.userstream do |ev|
-        next unless ev[:text] # If it's not a text-containing tweet, ignore it
-        next if ev[:user][:screen_name] == @username # Ignore our own tweets
+        next unless ev.text # If it's not a text-containing tweet, ignore it
+        next if ev.user.screen_name == @username # Ignore our own tweets
 
         meta = {}
         mentions = ev.attrs[:entities][:user_mentions].map { |x| x[:screen_name] }
 
         reply_mentions = mentions.reject { |m| m.downcase == @username.downcase }
-        reply_mentions = [ev[:user][:screen_name]] + reply_mentions
+        reply_mentions = [ev.user.screen_name] + reply_mentions
 
         meta[:reply_prefix] = reply_mentions.uniq.map { |m| '@'+m }.join(' ') + ' '
         meta[:limit] = 140 - meta[:reply_prefix].length
 
-        mless = ev[:text]
+        mless = ev.text
         begin
           ev.attrs[:entities][:user_mentions].reverse.each do |entity|
             last = mless[entity[:indices][1]..-1]||''
@@ -109,7 +108,7 @@ module Ebooks
           end
         rescue Exception
           p ev.attrs[:entities][:user_mentions]
-          p ev[:text]
+          p ev.text
           raise
         end
         meta[:mentionless] = mless
@@ -118,8 +117,8 @@ module Ebooks
         # - The tweet mentions list contains our username
         # - The tweet is not being retweeted by somebody else
         # - Or soft-retweeted by somebody else
-        if mentions.map(&:downcase).include?(@username.downcase) && !ev[:retweeted_status] && !ev[:text].start_with?('RT ')
-          log "Mention from @#{ev[:user][:screen_name]}: #{ev[:text]}"
+        if mentions.map(&:downcase).include?(@username.downcase) && !ev.retweeted_status && !ev.text.start_with?('RT ')
+          log "Mention from @#{ev.user.screen_name}: #{ev.text}"
           @on_mention.call(ev, meta) if @on_mention
         else
           @on_timeline.call(ev, meta) if @on_timeline
@@ -140,11 +139,11 @@ module Ebooks
       opts = opts.clone
 
       if ev.is_a? Twitter::DirectMessage
-        log "Sending DM to @#{ev[:sender][:screen_name]}: #{text}"
-        @twitter.direct_message_create(ev[:sender][:screen_name], text, opts)
+        log "Sending DM to @#{ev.sender.screen_name}: #{text}"
+        @twitter.direct_message_create(ev.sender.screen_name, text, opts)
       elsif ev.is_a? Twitter::Tweet
-        log "Replying to @#{ev[:user][:screen_name]} with: #{text}"
-        @twitter.update(text, in_reply_to_status_id: ev[:id])
+        log "Replying to @#{ev.user.screen_name} with: #{text}"
+        @twitter.update(text, in_reply_to_status_id: ev.id)
       else
         raise Exception("Don't know how to reply to a #{ev.class}")
       end
@@ -164,6 +163,12 @@ module Ebooks
       @twitter.update(*args)
     end
 
+    # could easily just be *args however the separation keeps it clean.
+    def pictweet(txt, pic, *args)
+      log "Tweeting #{txt.inspect} - #{pic} #{args}"
+      @twitter.update_with_media(txt, File.new(pic), *args)
+    end
+
     def on_startup(&b); @on_startup = b; end
     def on_follow(&b); @on_follow = b; end
     def on_mention(&b); @on_mention = b; end

data/lib/twitter_ebooks/model.rb

@@ -18,14 +18,28 @@ module Ebooks
       Marshal.load(File.open(path, 'rb') { |f| f.read })
     end
 
+    def mass_tokenize(text)
+      sentences = NLP.sentences(text)
+      tokens = []
+
+      sentences.each do |s|
+        tokens << NLP.tokenize(s).reject do |t|
+          # Don't include usernames/urls as tokens
+          t.include?('@') || t.include?('http')
+        end
+      end
+
+      tokens
+    end
+
     def consume(path)
       content = File.read(path, :encoding => 'utf-8')
       @hash = Digest::MD5.hexdigest(content)
 
       if path.split('.')[-1] == "json"
         log "Reading json corpus from #{path}"
-        lines = JSON.parse(content, symbolize_names: true).map do |tweet|
-          tweet[:text]
+        lines = JSON.parse(content).map do |tweet|
+          tweet['text']
         end
       elsif path.split('.')[-1] == "csv"
         log "Reading CSV corpus from #{path}"
@@ -42,41 +56,28 @@ module Ebooks
 
       log "Removing commented lines and sorting mentions"
 
-      keeping = []
+      statements = []
       mentions = []
       lines.each do |l|
         next if l.start_with?('#') # Remove commented lines
         next if l.include?('RT') || l.include?('MT') # Remove soft retweets
-        
+
         if l.include?('@')
-          mentions << l
+          statements << NLP.normalize(l)
         else
-          keeping << l
+          mentions << NLP.normalize(l)
         end
       end
-      text = NLP.normalize(keeping.join("\n")) # Normalize weird characters
-      mention_text = NLP.normalize(mentions.join("\n"))
 
-      log "Segmenting text into sentences"
+      text = statements.join("\n")
+      mention_text = mentions.join("\n")
 
-      statements = NLP.sentences(text)
-      mentions = NLP.sentences(mention_text)
+      lines = nil; statements = nil; mentions = nil # Allow garbage collection
 
-      log "Tokenizing #{statements.length} statements and #{mentions.length} mentions"
-      @sentences = []
-      @mentions = []
+      log "Tokenizing #{text.count('\n')} statements and #{mention_text.count('\n')} mentions"
 
-      statements.each do |s|
-        @sentences << NLP.tokenize(s).reject do |t|
-          t.include?('@') || t.include?('http')
-        end
-      end
-
-      mentions.each do |s|
-        @mentions << NLP.tokenize(s).reject do |t|
-          t.include?('@') || t.include?('http')
-        end
-      end
+      @sentences = mass_tokenize(text)
+      @mentions = mass_tokenize(mention_text)
 
       log "Ranking keywords"
       @keywords = NLP.keywords(@sentences)

data/lib/twitter_ebooks/nlp.rb

@@ -43,7 +43,7 @@ module Ebooks
     end
 
     ### Utility functions
-    
+
     # We don't really want to deal with all this weird unicode punctuation
     def self.normalize(text)
       htmlentities.decode text.gsub('“', '"').gsub('”', '"').gsub('’', "'").gsub('…', '...')

data/lib/twitter_ebooks/version.rb

@@ -1,3 +1,3 @@
 module Ebooks
-  VERSION = "2.2.6"
+  VERSION = "2.2.7"
 end

data/lib/twitter_ebooks.rb

@@ -1,5 +1,3 @@
-gem 'minitest'
-
 $debug = false
 
 def log(*args)

data/skeleton/bots.rb

@@ -37,5 +37,6 @@ Ebooks::Bot.new("{{BOT_NAME}}") do |bot|
     # Tweet something every 24 hours
     # See https://github.com/jmettraux/rufus-scheduler
     # bot.tweet("hi")
+    # bot.pictweet("hi", "cuteselfie.jpg", ":possibly_sensitive => true")
   end
 end