markovite 0.2.1 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 59954d2685196332c680dcad7b09ac470e25fc284035da71fbb9b40898bac750
-  data.tar.gz: abd736b797da4d2b6c25a1d64226e4d0ea402cb861b539d8edbfd0eee2c015cf
+  metadata.gz: b6fee92d46759244fd174b5292ae9d7f5b418f25f9268922b9e1c9bc0d4d08fc
+  data.tar.gz: 12601a0899b487e1fae3415ad3cb12b7107d5961cf06f9d32dda38bd6968cb13
 SHA512:
-  metadata.gz: 589de5784a1afe9e2cf25b5cb41c71eafb962646b77c62b4f5bdb358f573cf4891ba933252ee065fadd50ae3cc7ba1a29d06f4f8a47a0cc833b0b5aa16d63746
-  data.tar.gz: a2434e3dd6e04f9946ba5800daf2fdb0826decb23504cc901bd9d73ef88bc389bfc135de74c47b62b8b47656000831026b2a3ede7144ba095cd7768f7e1b4d23
+  metadata.gz: 15f2a32d7a25bae0bcb2b085ab548bc156fdc49cb50d9b196e731bd9d9b214e216f9ffd2f0c6570516e966907f1eb06172879b5d718661ab9b7605c25354803f
+  data.tar.gz: 6f39d34312712dbc3dee5070be285adfef7f98bc181def7ffc6d46b408864077d69e159cef2cd54638de61de3419193e6487d88c4d5bb9abbf0ed5e61406ecfb

data/Gemfile

@@ -2,5 +2,7 @@ source "https://rubygems.org"
 
 git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
 
+
+
 # Specify your gem's dependencies in markovite.gemspec
 gemspec

data/Gemfile.lock

@@ -1,12 +1,17 @@
 PATH
   remote: .
   specs:
-    markovite (0.2.1)
+    markovite (0.2.2)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    coderay (1.1.2)
     diff-lcs (1.3)
+    method_source (0.9.0)
+    pry (0.11.3)
+      coderay (~> 1.1.0)
+      method_source (~> 0.9.0)
     rake (10.4.2)
     rspec (3.7.0)
       rspec-core (~> 3.7.0)
@@ -28,8 +33,9 @@ PLATFORMS
 DEPENDENCIES
   bundler (~> 1.16)
   markovite!
+  pry
   rake (~> 10.0)
   rspec (~> 3.0)
 
 BUNDLED WITH
-   1.16.0
+   1.16.1

data/README.md

@@ -1,8 +1,6 @@
 # Markovite
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/markovite`. To experiment with that code, run `bin/console` for an interactive prompt.
-
-TODO: Delete this and the text above, and describe your gem
+Markovite, a markov chain generator that is simple to use and easy to hack. You can use this gem to generate random text using a corpus. 
 
 ## Installation
 
@@ -22,7 +20,51 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+To hit the ground running, you can do the following:
+
+```ruby
+require "markovite"
+
+chain = Markovite::Chain.new
+chain << "tiny-shakespeare.txt"
+
+chain.make_sentence_of_length(140)
+
+```
+This will train the chain model on a file named `tiny-shakespear.txt` and return a sentence that is no longer than 140 characters, which does not appear in the training corpus.
+
+You can push multiple files or strings into one chain instance. By default, chains will be initialized with a depth of 2. 
+
+### Expanding Chain
+A new chain instance can optionally be initialized with
+a filename as the first argument, and the desired depth size as the second argument.
+
+`chain = Markovite::Chain.new("tiny-shakespeare.txt", 3)`
+
+Instances of chains can be modified by using the more specific 
+`chain.parse_file("sherlock.txt", 3)`
+or
+`chain.parse_string("I am a giant hamster person")`
+The second argument, the chain depth, will default to 2.
+
+### Creating Sentences
+
+`chain.make_sentence`
+
+Returns one sentence that does not appear in the corpus, or nil if the model is unable to generate a unique sentence.
+
+`chain.make_sentences(5)`
+
+Returns five sentences that do not appear in the corpus, or nil if the model is unable to generate a unique sentence.
+
+`chain.make_sentence_starts_with("Hello listeners")`
+
+Returns a sentence that begins with the argument, or nil if the model is unable to generate a unique sentence.
+
+`chain.make_sentence_of_length(280)`
+
+Returns a sentence with the length of 280 characters, or nil if the model is unable to generate a unique sentence.
+
 
 ## Development
 

data/lib/markovite.rb

@@ -36,9 +36,7 @@ module Markovite
 
     ####Future Self: Make this a module####
 
-    def split_words(str)
-      str.split(" ")
-    end
+
 
     def make_sentence
       chainer.make_sentence
@@ -60,6 +58,10 @@ module Markovite
 
     private
 
+    def split_words(str)
+      str.split(" ")
+    end
+
     def new_from_text(text, dict_depth)
       #look into refactoring this
       @depth = dict_depth

data/lib/markovite/chainer.rb

@@ -17,18 +17,26 @@ class Chainer
 
   def make_sentence_starts_with(phrase)
     chunk = get_chunk(phrase)
-    partial = generate_text(chunk)
+    begin
+      partial = generate_text(chunk)
+    rescue ArgumentError
+      return nil
+    end
     "#{phrase} #{partial}"
   end
 
   def make_sentence_of_length(how_long)
-    make_sentence_with_block {|sentence| sentence.length <= how_long}
+    begin
+      make_sentence_with_block {|sentence| sentence.length <= how_long}
+    rescue NoMethodError
+      return nil
+    end
   end
 
   def make_sentences(amount, condition=true)
     sentences = []
     amount.times do
-      sentences << make_sentence(condition)
+      sentences << make_sentence
     end
     sentences.join(' ')
   end
@@ -76,7 +84,7 @@ class Chainer
 
   def pick_next(words)
     word_list = dictionary.chain[words]
-    raise "No matching state found" if word_list.empty?
+    raise ArgumentError, "No matching state" if word_list.empty?
     word_list.sample
   end
 

data/lib/markovite/dict.rb

@@ -29,8 +29,8 @@ class Dictionary
   end
 
   def expand_chain(text)
-    new_sentences = sentence_split.expand_corpus(text)
-    sentences = sentence_split.sentences
+    new_sentences = sentence_split.split_text(text)
+    self.sentences += sentence_split.sentences
     construct_chain(new_sentences)
   end
 

data/lib/markovite/splitter.rb

@@ -3,7 +3,19 @@
 
 class SplitSentence
 
-  SPLITTERS = ['\n', '?', '.', '!']
+  ENDERS = ['?', '.', '!']
+  ABBREVIATIONS = [
+    'ave.','blvd.','ln','rd.','st.', #directional
+    'tsp.','t.', 'tbs.', 'tbsp.','gal.','lb.','pt.','qt.', #cooking
+    "ak.", "al.", "ar.", "az.", "ca.", "co.", "ct.", "dc.", "de.", "fl.",
+    "ga.", "gu.", "hi.", "ia.", "id.", "il.", "in.", "ks.", "ky.", "la.",
+    "ma.", "md.", "me.", "mh.", "mi.", "mn.", "mo.", "ms.", "mt.", "nc.",
+    "nd.", "ne.", "nh.", "nj.", "nm.", "nv.", "ny.", "oh.", "ok.", "or.",
+    "pa.", "pr.", "pw.", "ri.", "sc.", "sd.", "tn.", "tx.", "ut.", "va.",
+    "vi.", "vt.", "wa.", "wi.", "wv.", "wy.",  "u.s.", "u.s.a,", #us locations
+    "dr.", "esq.", "jr.", "mr.", "mrs.", "ms.", "mx.",
+    "prof.", "rev.", "rt. hon.", "sr.", "st." #personal
+  ]
 
   #look into detecting abbreviations!
 
@@ -28,42 +40,55 @@ class SplitSentence
   # This way, we can impose grammatical rules by making the first word of the sentence
   # capitalized, and the end of the sentence will end with some sort of punctuation.
 
-
-
   def split_text(new_text = nil)
-    #not sure how elegant clear_sentence is here
-    clear_sentences unless new_text
+    clear_sentences
+    current_sentence = []
     new_text = new_text || corpus
-    current_sentence = ""
-    new_sentences = []
-    new_text.each_char do |char|
-      if SPLITTERS.include?(char)
-        current_sentence << char
-        new_sentences << current_sentence
-        self.sentences << current_sentence
-        current_sentence = ""
+    all_words = split_words(new_text)
+    all_words.each do |word|
+      if is_end_of_sentence?(word)
+        current_sentence = add_sentence(current_sentence, word)
+      elsif has_newline?(word)
+        newline_words = split_newline(word)
+        current_sentence = add_sentence(current_sentence, newline_words[0])
+        current_sentence << newline_words[1]
       else
-        next if current_sentence == "" && char == " "
-        current_sentence << char
+        current_sentence << word
       end
     end
-    new_sentences
+    add_sentence(current_sentence, nil) if !current_sentence.empty?
+    sentences
+  end
+
+  private
+
+  def add_sentence(sentence, word)
+    sentence << word if word
+    sentences << sentence.compact.join(" ")
+    []
   end
 
-  def expand_corpus(new_text)
-    corpus << "\n" + new_text
-    split_text(new_text)
+  def split_words(text)
+    text.split(/ /)
   end
 
-  private
+  def is_abbreviation(word)
+    ABBREVIATIONS.include?(word.downcase)
+  end
 
-  def is_abbreviation
+  def has_newline?(word)
+    word.include?("\n")
   end
 
-  def is_url
+  def split_newline(word)
+    word.split("\n").map{|str| str.empty? ? nil:str}
   end
 
-  def is_sentence_end
+  def is_end_of_sentence?(word)
+    #check punctuation before delving into abbreviations to save time
+    return false if !ENDERS.include?(word[-1])
+    return false if is_abbreviation(word)
+    return true
   end
 
 end

data/lib/markovite/version.rb

@@ -1,3 +1,3 @@
 module Markovite
-  VERSION = "0.2.1"
+  VERSION = "0.2.2"
 end

data/markovite.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
   spec.email         = ["superbiscuit@gmail.com"]
 
   spec.summary       = "A markov chain generator that is simple to use and easy to hack."
-  spec.description   = "Doctors hate this one weird trick that generates really good looking gibberish!"
+  spec.description   = "Doctors hate this one weird trick that generates really good looking gibberish! \n Markovite is simple, but powerful markov chain generator that is designed to be hackable to your heart's delight"
   spec.homepage      = "https://github.com/f3mshep/ruby_markovify"
   spec.license       = "MIT"
 
@@ -32,4 +32,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "bundler", "~> 1.16"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "pry"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: markovite
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors:
 - Alexandra Wright
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-03-30 00:00:00.000000000 Z
+date: 2018-03-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -52,8 +52,23 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
-description: Doctors hate this one weird trick that generates really good looking
-  gibberish!
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: "Doctors hate this one weird trick that generates really good looking
+  gibberish! \n Markovite is simple, but powerful markov chain generator that is designed
+  to be hackable to your heart's delight"
 email:
 - superbiscuit@gmail.com
 executables: []
@@ -77,8 +92,6 @@ files:
 - lib/markovite/splitter.rb
 - lib/markovite/version.rb
 - markovite.gemspec
-- pkg/markovite-0.1.0.gem
-- pkg/markovite-0.2.0.gem
 homepage: https://github.com/f3mshep/ruby_markovify
 licenses:
 - MIT
@@ -101,7 +114,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.4
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: A markov chain generator that is simple to use and easy to hack.