words_counted 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 190a90d67fb727203b2956402d95b3d830947ba9
-  data.tar.gz: 3af82b30917c67c6d8e0460461a87eccd311080d
+  metadata.gz: 5d127f1d7ea83482f4efa3b8d25ff2154d6d8006
+  data.tar.gz: 4e537850f5749aadf25f7ac435fbc141601b3425
 SHA512:
-  metadata.gz: 9becd4e96f51c2cd5b4e2b2aff9a0a08c6807ef9d3d7556d1017ce74540b9fe918de7b2ba01fe460546f214d3994467d9e91d60d6e183a0fbff3c4c23e525ed7
-  data.tar.gz: 8265fdb5cb49b37d1f2adaa8490ad0cba31497a93addd2f1aefa6ac1742b130877e95ad96b247f49f9d47991e873ee604aac44119105b2071a38eb8a707f6e5c
+  metadata.gz: 95adf80c2551fb0dd92fa260aad8b0b0eb62ddb11ced4b4a3afb70493782810c24919c84ce1b89b646c07ea34db7f94e3cd0515d10709d956139b87bd441c2be
+  data.tar.gz: 2494524dc28161f2ca8d7ada896c7522ddb7266b9aac5ca50288b67298f8a0b1eb1460e027d60478c23c2fd220078ce02c98e2f0f977496723ae59d5aac4cf30

data/.yardopts

@@ -0,0 +1,2 @@
+--title 'Word Counter for Ruby'
+--private

data/README.md

@@ -1,15 +1,15 @@
 # Words Counted
 
-This Ruby gem is a word counter that includes some handy utility methods.
+This Ruby gem is a word counter that includes some handy utility methods. It lets you send in a string of text and count the number of words, get the words sorted by number occurrences, get the highest occurring words, and few more things.
 
 ### Features
 
 1. Count the number of words in a string.
-2. Get a hash of each word and the number of times it occurres.
-3. Get a hash of each word and its length.
+2. Get a hash map of words and the number of times they occur.
+3. Get a hash map of words and their lengthes.
 4. Get the most occurring word(s) and its number of occurrences.
 5. Get the longest word(s) and its length.
-6. Ability to filter words.
+6. Ability to filter out words from the count. Useful if you don't want to count `a`, `the`, etc...
 7. Filters special characters but respects hyphens and apostrophes.
 
 See usage instructions for details on each feature.
@@ -30,7 +30,7 @@ Or install it yourself as:
 
 ## Usage
 
-Create an instance of `Counter` and pass in a string and an optional filter.
+Create an instance of `Counter` and pass in a string and an optional filter string.
 
 ```ruby
 counter = WordsCounted::Counter.new(
@@ -38,50 +38,117 @@ counter = WordsCounted::Counter.new(
 )
 ```
 
-### `.word_count`
+#### `.word_count`
 
 Returns the word count of a given string. The word count includes only alpha characters. Hyphenated and words with apostrophes are considered a single word.
 
 ```ruby
 counter.word_count #=> 15
 ```
-### `.word_occurrences`
 
-Returns a hash of words and their number of occurrences. Uppercase and lowercase words are counted as the same word.
+#### `.word_occurrences`
+
+Returns a hash map of words and their number of occurrences. Uppercase and lowercase words are counted as the same word.
 
 ```ruby
-counter.word_occurrences #=> { "we"=>1, "are"=>2, "all"=>1, "in"=>1, "the"=>2, "gutter"=>1, "but"=>1, "some"=>1, "of"=>1, "us"=>1, "looking"=>1, "at"=>1, "stars"=>1}
+counter.word_occurrences
+#=> {
+  "we"=>1,
+  "are"=>2,
+  "all"=>1,
+  "in"=>1,
+  "the"=>2,
+  "gutter"=>1,
+  "but"=>1,
+  "some"=>1,
+  "of"=>1,
+  "us"=>1,
+  "looking"=>1,
+  "at"=>1,
+  "stars"=>1
+}
 ```
 
-### `.most_occurring_words`
+#### `.most_occurring_words`
 
-Returns a two dimensional array of the highest occurring word and its number of occurrences. In case there is a tie all tied words are returned.
+Returns a two dimensional array of the most occurring word and its number of occurrences. In case there is a tie all tied words are returned.
 
 ```ruby
-counter.most_occurring_words #=> [["are", 2], ["the", 2]]
+counter.most_occurring_words
+#=>
+  [
+    ["are", 2],
+    ["the", 2]
+  ]
 ```
 
-### `.word_lengths`
+#### `.word_lengths`
 
 Returns a hash of words and their lengths.
 
 ```ruby
-counter.word_lengths #=> {"We"=>2, "are"=>3, "all"=>3, "in"=>2, "the"=>3, "gutter"=>6, "but"=>3, "some"=>4, "of"=>2, "us"=>2, "looking"=>7, "at"=>2, "stars"=>5}
+counter.word_lengths
+#=> {
+  "We"=>2,
+  "are"=>3,
+  "all"=>3,
+  "in"=>2,
+  "the"=>3,
+  "gutter"=>6,
+  "but"=>3,
+  "some"=>4,
+  "of"=>2,
+  "us"=>2,
+  "looking"=>7,
+  "at"=>2,
+  "stars"=>5
+}
 ```
 
-### `.longest_word`
+#### `.longest_word`
 
 Returns a two dimensional array of the longest word and its length. In case there is a tie all tied words are returned.
 
+```ruby
+counter.longest_words
+#=> [
+      ["looking", 7]
+    ]
+```
+
 ## Filtering
 
-You can pass in a space-delimited word list to filter words that you don't want to count. Filter words should be lowercase. The filter will remove both uppercase and lowercase variants of the word.
+You can pass in a space-delimited word list to filter words that you don't want to count. Filter words should be *lowercase*. The filter will remove both uppercase and lowercase variants of the word.
+
+```ruby
+WordsCounted::Counter.new("Magnificent! That was magnificent, Trevor.", "was magnificent")
+#<WordsCounted::Counter:0x007fd4949f99d8 @words=["That", "Trevor"]>
+```
+
+## Gotchas
+
+A hyphen use in leu of an *em* or *en* dash will form part of the word and throw off the `word_occurences` algorithm.
 
 ```ruby
-WordsCounted::Counter.new("That was magnificent, Trevor.", "that was")
-#=> <WordsCounted::Counter:0x007fd494312520 @words=["magnificent", "Trevor"]>
+counter = WordsCounted::Counter.new("How do you do?-you are well, I see.")
+#<WordsCounted::Counter:0x007fd494252518 @words=["How", "do", "you", "do", "-you", "are", "well", "I", "see"]>
+
+counter.word_occurrences
+#=> {
+  "how"=>1,
+  "do"=>2,
+  "you"=>1,
+  "-you"=>1, # WTF, mate!
+  "are"=>1,
+  "very"=>1,
+  "well"=>1,
+  "i"=>1,
+  "see"=>1
+}
 ```
 
+In this example, `-you` and `you` are counted as separate words. Writers should use the correct dash element, but this is not always the case.
+
 ## About
 
 Originally I wrote this program for a code challenge. My initial implementation was decent, but it could have been better. Thanks to [Dave Yarwood](http://codereview.stackexchange.com/a/47515/1563) for helping me improve my code. Some of this code is based on his recommendations. You can find the original implementation as well as the code review on [Code Review](http://codereview.stackexchange.com/questions/46105/a-ruby-string-analyser).

data/lib/words_counted/counter.rb

@@ -1,6 +1,6 @@
 module WordsCounted
   class Counter
-    # @!attribute [Array] an array of words resulting for the string to act on.
+    # @!words [Array] an array of words resulting from the string passed to the initializer.
     attr_reader :words
 
     # This is the criteria for defining words.

data/lib/words_counted/version.rb

@@ -1,3 +1,3 @@
 module WordsCounted
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: words_counted
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Mohamad El-Husseini
@@ -75,6 +75,7 @@ extra_rdoc_files: []
 files:
 - .gitignore
 - .rspec
+- .yardopts
 - Gemfile
 - LICENSE.txt
 - README.md