twitter_ebooks 3.1.2 → 3.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8d63241151084c8291adc98bb9304834e9b2ed2a
-  data.tar.gz: 97db6f8b0a722e1b9b911a938f19edd70eb45f9e
+  metadata.gz: b8c70b5760bf1a3545b08b1899585ce08e0e10c5
+  data.tar.gz: 3d98fe56163d2682c516690ab14564c3d6b573dd
 SHA512:
-  metadata.gz: be8cd6c17a3682627c3087d2712f97343f773fb630423ca020be484adb25de279d62b3dbe5cae313b48f5d030a2c3ac43adba9ac88672072156274e3f2b6c476
-  data.tar.gz: cd7b2a04a13b8b34a5b07aeecdbc9ca1ad7f1f9756cb28c5b252a0c18ed9e89a93410ff6f54849963346fe7633d5584bc511ef63eed8a4c5a792283652d687f3
+  metadata.gz: 8dddfdc46f98ef0184cf8929ae310d9ce1527fad7a22d75301a33d18bc0389542ab05ac802723d47c3455e2141f07c882163c409de7a56d15651fc3e01dd4ddd
+  data.tar.gz: 97e4d64f43cdb32d4dcecb63fc85634c6c114557faa22cb4f6919c3918feeee9979987fb05c23b4660c60f3862d10724db82f8c0d34ac91ca20e30b7ae2a80d3

data/bin/ebooks

@@ -93,7 +93,9 @@ STR
       filename = File.basename(path)
       shortname = filename.split('.')[0..-2].join('.')
 
+      FileUtils.mkdir_p(File.join(APP_PATH, 'model'))
       outpath = File.join(APP_PATH, 'model', "#{shortname}.model")
+
       Ebooks::Model.consume(path).save(outpath)
       log "Corpus consumed to #{outpath}"
     end
@@ -120,7 +122,7 @@ STR
   HELP.append = <<-STR
     Usage: ebooks append <model_name> <corpus_path>
 
-    Process then append the provided corpus to the model 
+    Process then append the provided corpus to the model
     instead of overwriting.
   STR
 
@@ -133,7 +135,7 @@ STR
     Ebooks::Model.consume(path).append(File.join(APP_PATH,'model',"#{name}.model"))
     log "Corpus appended to #{name}.model"
   end
- 
+
 
   HELP.jsonify = <<-STR
     Usage: ebooks jsonify <tweets.csv> [tweets.csv2] [...]
@@ -209,6 +211,11 @@ STR
     Output defaults to corpus/<username>.json
     Due to API limitations, this can only receive up to ~3000 tweets
     into the past.
+
+    The first time you run archive, you will need to enter the auth
+    details of some account to use for accessing the API. This info
+    will then be stored in ~/.ebooksrc for later use, and can be
+    modified there if needed.
   STR
 
   def self.archive(username, outpath=nil)
@@ -300,7 +307,7 @@ STR
 
     Shows you twitter_ebooks' version number.
   STR
-  
+
   def self.version
     require File.expand_path('../../lib/twitter_ebooks/version', __FILE__)
     log Ebooks::VERSION

data/lib/twitter_ebooks/bot.rb

@@ -2,6 +2,14 @@
 require 'twitter'
 require 'rufus/scheduler'
 
+# Monkeypatch hack to fix upstream dependency issue
+# https://github.com/sferik/twitter/issues/709
+class HTTP::URI
+  def port
+    443 if self.https?
+  end
+end
+
 module Ebooks
   class ConfigurationError < Exception
   end

data/lib/twitter_ebooks/model.rb

@@ -96,7 +96,7 @@ module Ebooks
       end
       self
     end
-     
+
 
     def initialize
       @tokens = []
@@ -113,7 +113,7 @@ module Ebooks
         return @tikis[token]
       else
         (@tokens.length+1)%1000 == 0 and puts "#{@tokens.length+1} tokens"
-        @tokens << token 
+        @tokens << token
         return @tikis[token] = @tokens.length-1
       end
     end
@@ -255,8 +255,7 @@ module Ebooks
 
       while (tikis = generator.generate(3, :bigrams)) do
         log "Attempting to produce tweet try #{retries+1}/#{retry_limit}"
-        next if tikis.length <= 3 && !responding
-        break if valid_tweet?(tikis, limit)
+        break if (tikis.length > 3 || responding) && valid_tweet?(tikis, limit)
 
         retries += 1
         break if retries >= retry_limit

data/lib/twitter_ebooks/nlp.rb

@@ -14,10 +14,10 @@ module Ebooks
     # to be using it all of the time
 
     # Lazily loads an array of stopwords
-    # Stopwords are common English words that should often be ignored
+    # Stopwords are common words that should often be ignored
     # @return [Array<String>]
     def self.stopwords
-      @stopwords ||= File.read(File.join(DATA_PATH, 'stopwords.txt')).split
+      @stopwords ||= File.exists?('stopwords.txt') ? File.read('stopwords.txt').split : []
     end
 
     # Lazily loads an array of known English nouns
@@ -99,7 +99,7 @@ module Ebooks
         #set :vowels, 1                     # => default: 0 = not considered
         #set :consonants, 5                 # => default: 0 = not considered
         #set :ignore_case, true             # => default: false
-        set :word_pattern, /(?<!@)(?<=\s)[\w']+/           # => default: /\w+/
+        set :word_pattern, /(?<!@)(?<=\s)[\p{Word}']+/           # => default: /\w+/
         #set :stemming, true                # => default: false
       end
 

data/lib/twitter_ebooks/version.rb

@@ -1,3 +1,3 @@
 module Ebooks
-  VERSION = "3.1.2"
+  VERSION = "3.1.3"
 end

data/spec/model_spec.rb

@@ -36,7 +36,7 @@ describe Ebooks::Model do
     report2 = MemoryUsage.report do
       model = Ebooks::Model.load(file.path)
     end
-    expect(report2.total_memsize).to be < 3000000
+    expect(report2.total_memsize).to be < 4000000
 
     expect(model.tokens[0]).to be_a String
     expect(model.sentences[0][0]).to be_a Fixnum

data/twitter_ebooks.gemspec

@@ -22,7 +22,7 @@ Gem::Specification.new do |gem|
   gem.add_development_dependency 'pry-byebug'
   gem.add_development_dependency 'yard'
 
-  gem.add_runtime_dependency 'twitter', '= 5.14'
+  gem.add_runtime_dependency 'twitter', '~> 5.15'
   gem.add_runtime_dependency 'rufus-scheduler'
   gem.add_runtime_dependency 'gingerice'
   gem.add_runtime_dependency 'htmlentities'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: twitter_ebooks
 version: !ruby/object:Gem::Version
-  version: 3.1.2
+  version: 3.1.3
 platform: ruby
 authors:
 - Jaiden Mispy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-09-25 00:00:00.000000000 Z
+date: 2016-01-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -98,16 +98,16 @@ dependencies:
   name: twitter
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.14'
+        version: '5.15'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.14'
+        version: '5.15'
 - !ruby/object:Gem::Dependency
   name: rufus-scheduler
   requirement: !ruby/object:Gem::Requirement
@@ -238,7 +238,6 @@ files:
 - bin/ebooks
 - data/adjectives.txt
 - data/nouns.txt
-- data/stopwords.txt
 - lib/twitter_ebooks.rb
 - lib/twitter_ebooks/archive.rb
 - lib/twitter_ebooks/bot.rb
@@ -252,6 +251,7 @@ files:
 - skeleton/corpus/.gitignore
 - skeleton/gitignore
 - skeleton/model/.gitignore
+- skeleton/stopwords.txt
 - spec/bot_spec.rb
 - spec/data/0xabad1dea.json
 - spec/data/0xabad1dea.model