twexicon 0.1.7.1 → 0.1.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8628e88177bf13abeb0aabcdf40f85829cf3234b
-  data.tar.gz: 0dfa52e2ed29c01ec14b575587f5b9ee038a81fa
+  metadata.gz: 166ba87d5e9f7c5039ffc03a8a9b74aaf25d6599
+  data.tar.gz: c3f0f992b626d751057db8850589fec2c5fdb47f
 SHA512:
-  metadata.gz: dffb2fbd8eaa81c1550aef0ccac4d745a3595ae43cd5cff2729cc1ffa9f5a21cc61b5488865af8e0184166ceb2fb58d5ca6359bd63164eb2425eea070de22799
-  data.tar.gz: 60c9217cf1fe43793c4d474d56d00bd668dd60d2e4f57bc72d7473392f57291484e1c0d4cb27bcc710d93906f751ea19f731bcf91cbfbfa7281f2eb3d0f81cdb
+  metadata.gz: a575dc49c0ee39ee40b0501cc65d1d47d7567ea035cac6a2c02ebeb26712be09edeeaffc893c2f13c009bed0bfbf2960ccb38df66d0923e1b6fa1944a9d57bd0
+  data.tar.gz: 521809c9442611e804c9b36d4affa9534f7c002a8089011eb5c200757914f456e8a50e64c4b7450380b1850ffb4fc5fbe12836275c67df6b1ef267ad16b88624

data/lib/twexicon/analyzer.rb

@@ -13,7 +13,7 @@ class Twexicon::Analyzer
     until quit
       @input = nil
       @int = ""
-      puts "What would you like to do next? For options, type 'help'."
+      puts "\nWhat would you like to do next? For options, type 'help'."
       until is_valid?
         @input = gets.strip.gsub(/\W/, "").downcase
       end
@@ -69,14 +69,16 @@ class Twexicon::Analyzer
     end
   end
 
-  # 38 words from https://en.wikipedia.org/wiki/Most_common_words_in_English –– Left out some common yet still interesting ones (People, Good, Think, Work, First, One, Two, Want, New, Give, Know)
+  # Words from https://en.wikipedia.org/wiki/Most_common_words_in_English –– Left out some common yet still interesting ones (People, Good, Think, Work, First, One, Two, Want, New, Give, Know)
   COMMON_WORDS = ["A", "About", "An", "And", "Are", "As", "At", "Be", "Been", "But", "By", "For", "From", "Get", "Had", "Has", "Have", "In", "Into", "Is", "It", "It's", "Its", "Just", "Not", "Of", "On", "Or", "Say", "So", "Some", "That", "The", "There", "These", "This", "Those", "To", "Up", "With", "I", "My", "Your", "They", "He", "You", "Do", "His", "We", "Her", "She", "Will", "All", "Would", "Their", "What", "Out", "If", "Who", "Which", "Go", "Me", "When", "Make", "Can", "Time", "No", "Him", "Take", "Year", "Could", "Them", "See", "Other", "Than", "Then", "Now", "Look", "Only", "Come", "Over", "Also", "Back", "After", "Use", "How", "Our", "Well", "Way", "Even", "Because", "Any", "Day", "Most", "Us",
     # other additions
-    "Wouldn't", "Couldn't", "Shouldn't", "Mustn't", "Would've", "Could've", "Should've", "Must've", "Hadn't", "Wasn't", "Weren't", "Ain't", "Aint", "Here", "Seem", "Seems", "That's", "Took", "Much", "More", "You're", "We're", "We've", "I've", "I'm",
+    "Wouldn't", "Couldn't", "Shouldn't", "Mustn't", "Would've", "Could've", "Should've", "Must've", "Hadn't", "Wasn't", "Weren't", "Ain't", "Aint", "Here", "Seem", "Seems", "That's", "Took", "Much", "More", "You're", "We're", "We've", "I've", "I'm", "Don't", "Got", "Soon",
     # contraction endings until I fix the parsing error
     "Re", "Ll", "Ve",
     # Letters until I fix the contraction parsing error
-    "B", "C", "D", "E", "F", "G", "H", "J", "K", "L", "M", "N", "O", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z"]
+    "B", "C", "D", "E", "F", "G", "H", "J", "K", "L", "M", "N", "O", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z",
+    # Common words in other languages that *aren't* uncommon English words (so, "Con" doesn't count)
+    "En"]
 
   def get_words
     words = {}
@@ -93,15 +95,17 @@ class Twexicon::Analyzer
     end
     words.each do |w, n| # Create strings for the words that occur >1 times
       case n
-      when 1..9 then word_array << "0#{n}x #{w}"
-      when 10..99 then word_array << "#{n}x #{w}"
+      when 1..9 then word_array << "000#{n}x #{w}"
+      when 10..99 then word_array << "00#{n}x #{w}"
+      when 100..999 then word_array << "0#{n}x #{w}"
+      when 1000..9999 then word_array << "#{n}x #{w}"
       end
     end
     if word_array.empty?
       puts "\nIt appears that @#{username} is not much of a talker."
     else
       puts "\n@#{username}'s current favorite word(s):"
-      puts word_array.sort.reverse.take(10)
+      puts word_array.sort.reverse.each{|w| w.sub!(/^0+/, "")}.take(10)
     end
   end
 

data/lib/twexicon/scraper.rb

@@ -14,12 +14,12 @@ class Twexicon::Scraper
     tweets.each do |num, tweet|
       t = tweet.keys[0].dup
       t.scan(/pic.twitter.com\/\w{10}/){|p| tweet.values[0][:pix] << p.strip}.gsub!(/pic.twitter.com\/\w{10}/, " ")
-      t.scan(/https?:\/\/[\w\.\?\=\&\-\/\#]+/){|w| tweet.values[0][:links] << w.strip}.gsub!(/https?:\/\/[\w\.\?\=\&\-\/\#]+/, " ")
+      t.scan(/https?:\/\/[\w\.\?\=\&\-\/\#\:]+/){|w| tweet.values[0][:links] << w.strip}.gsub!(/https?:\/\/[\w\.\?\=\&\-\/\#\:]+/, " ")
       t.scan(/#\w+/){|h| tweet.values[0][:hashtags] << h.gsub(/\W/, "").prepend("#")}.gsub!(/#\w+/, " ")
       t.scan(/@\w+/){|u| tweet.values[0][:usernames] << u.gsub(/\W/, "").prepend("@")}.gsub!(/@\w+/, " ")
-      t.scan(/(\d+[:\.\b]?\d*)+/){|n| tweet.values[0][:numbers] << n.first.gsub(/(^\W+|\W+$)/, "")}.gsub!(/(\d+[:\.\b]?\d*)+/, " ")
-      t.scan(/(\b[A-Z][\.\b][A-Z][\.\b][A-Z][\.\b]|\b[A-Z][\.\b][A-Z][\.\b])/){|a| tweet.values[0][:acronyms] << a.first.strip}.gsub!(/(\b[A-Z][\.\b][A-Z][\.\b][A-Z][\.\b]|\b[A-Z][\.\b][A-Z][\.\b])/, " ")
-      t.scan(/(([A-Z]+\W){2,}|[A-Z]{4,}\W)/){|s| tweet.values[0][:shouts] << s.first.gsub(/\W/, " ").strip}.gsub!(/(([A-Z]+\W){2,}|[A-Z]{4,}\W)/, " ")
+      t.scan(/(\d+[:\.\ ]?\d*)+/){|n| tweet.values[0][:numbers] << n.first.gsub(/(^\W+|\W+$)/, "")}.gsub!(/(\d+[:\.\ ]?\d*)+/, " ")
+      t.scan(/(\b[A-Z][\.\ ][A-Z][\.\ ][A-Z][\.\ ]|\b[A-Z][\.\ ][A-Z][\.\ ])/){|a| tweet.values[0][:acronyms] << a.first.strip}.gsub!(/(\b[A-Z][\.\ ][A-Z][\.\ ][A-Z][\.\ ]|\b[A-Z][\.\ ][A-Z][\.\ ])/, " ")
+      t.scan(/(([A-Z]+[\s\,\&\:\-]+){2,}|[A-Z]{4,}\W)/){|s| tweet.values[0][:shouts] << s.first.gsub(/\W/, " ").strip}.gsub!(/(([A-Z]+[\s\,\&\:\-]+){2,}|[A-Z]{4,}\W)/, " ")
       t.scan(/\b[A-Z]{2,3}\b/){|a| tweet.values[0][:acronyms] << a.strip}.gsub!(/\b[A-Z]{2,3}\b/, " ")
       t.scan(/\w+['\/]?\w*/){|w| tweet.values[0][:words] << w.strip}.gsub!(/\w+['\/]?\w*/, " ")
     end

data/lib/twexicon/version.rb

@@ -1,3 +1,3 @@
 module Twexicon
-  VERSION = "0.1.7.1"
+  VERSION = "0.1.8"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: twexicon
 version: !ruby/object:Gem::Version
-  version: 0.1.7.1
+  version: 0.1.8
 platform: ruby
 authors:
 - Gabe Jackson