words_counted 0.1.1 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c2d80aa2eb60a01c71a85f3b28b02231496c79ab
-  data.tar.gz: 93cd0029317b142161f4cb3170207fb507b82a50
+  metadata.gz: 07c1e76ee27525e7aa28de6a61dedde8ba6eae39
+  data.tar.gz: e8062169aaf99c19947a246ff33385e1fca928a7
 SHA512:
-  metadata.gz: 2fa36912b371084ddb87af00a26db538bcd8836abc34e51a76f5560d5bbb2e133a3dd4b980fe96cc7da07f251ce188b9ca183fda5a08c731e0450572bdf816f0
-  data.tar.gz: b91c95329ad60db96adfda332a9a933de013122660c47b5da85c290ae5dc25cbb98763afae20ee19b595aa4e8e526ee5648db461199e20dbc9df275ea23dc496
+  metadata.gz: 680cc6c8048a809941f4e23c53c99a2ee7fed5e3d0fe7943d9842b29967c7d19f8430143d56ed510042a493e166c99c4ae70c9b82e4b21fb4aeb3dbe9280f52e
+  data.tar.gz: ec317b1d90f3f14ba399996c8061835393d4aac6dd55f8ebc342b95a315c710bd62d3c9981e37cff6397863b8b5e10744748b1cede99e610dbf5cdd59aafcb90

data/README.md

@@ -50,7 +50,7 @@ counter = WordsCounted.count(
 )
 
 # Using a file
-counter = WordsCounted.from_file("path/to/my/file.txt")
+counter = WordsCounted.from_file("path/or/url/to/my/file.txt")
 ```
 
 ### API
@@ -172,9 +172,9 @@ counter.words
 #=> ["We", "are", "all", "in", "the", "gutter", "but", "some", "of", "us", "are", "looking", "at", "the", "stars"]
 ```
 
-#### `.word_density`
+#### `.word_density([ precision = 2 ])`
 
-Returns a two-dimentional array of words and their density.
+Returns a two-dimentional array of words and their density to a precision of two. It accepts a precision argument which defaults to two.
 
 ```ruby
 counter.word_density
@@ -182,17 +182,17 @@ counter.word_density
 [
   ["are",     13.33],
   ["the",     13.33],
-  ["but",     6.67],
-  ["us",      6.67],
-  ["of",      6.67],
-  ["some",    6.67],
-  ["looking", 6.67],
-  ["gutter",  6.67],
-  ["at",      6.67],
-  ["in",      6.67],
-  ["all",     6.67],
-  ["stars",   6.67],
-  ["we",      6.67]
+  ["but",     6.67 ],
+  ["us",      6.67 ],
+  ["of",      6.67 ],
+  ["some",    6.67 ],
+  ["looking", 6.67 ],
+  ["gutter",  6.67 ],
+  ["at",      6.67 ],
+  ["in",      6.67 ],
+  ["all",     6.67 ],
+  ["stars",   6.67 ],
+  ["we",      6.67 ]
 ]
 ```
 
@@ -204,9 +204,9 @@ Returns the string's character count.
 counter.char_count              #=> 76
 ```
 
-#### `.average_chars_per_word`
+#### `.average_chars_per_word([ precision = 2 ])`
 
-Returns the average character count per word.
+Returns the average character count per word. Accepts a precision argument which defaults to two.
 
 ```ruby
 counter.average_chars_per_word  #=> 4

data/lib/words_counted/counter.rb

@@ -4,14 +4,18 @@ module WordsCounted
 
     WORD_REGEXP = /[\p{Alpha}\-']+/
 
+    def self.from_file(path, options = {})
+      File.open(path) do |file|
+        new file.read, options
+      end
+    end
+
     def initialize(string, options = {})
       @options = options
       exclude = filter_proc(options[:exclude])
       @words = string.scan(regexp).reject { |word| exclude.call(word) }
       @char_count = @words.join.size
-      @word_occurrences = words.each_with_object(Hash.new(0)) do |word, hash|
-        hash[word.downcase] += 1
-      end
+      @word_occurrences = words.each_with_object(Hash.new(0)) { |word, hash| hash[word.downcase] += 1 }
       @word_lengths = words.each_with_object({}) { |word, hash| hash[word] ||= word.length }
     end
 
@@ -23,8 +27,8 @@ module WordsCounted
       words.uniq.size
     end
 
-    def average_chars_per_word
-      (char_count / word_count).round(2)
+    def average_chars_per_word(precision = 2)
+      (char_count.to_f / word_count.to_f).round(precision)
     end
 
     def most_occurring_words
@@ -35,28 +39,29 @@ module WordsCounted
       highest_ranking word_lengths
     end
 
-    def word_density
-      word_occurrences.each_with_object({}) do |(word, occ), hash|
-        hash[word] = percent_of(occ)
-      end.sort_by { |_, value| value }.reverse
+    def word_density(precision = 2)
+      word_densities = word_occurrences.each_with_object({}) do |(word, occ), hash|
+        hash[word] = (occ.to_f / word_count.to_f * 100).round(precision)
+      end
+      sort_by_descending_value word_densities
     end
 
     def sorted_word_occurrences
-      word_occurrences.sort_by { |_, v| v }.reverse
+      sort_by_descending_value word_occurrences
     end
 
     def sorted_word_lengths
-      word_lengths.sort_by { |_, v| v }.reverse
+      sort_by_descending_value word_lengths
     end
 
   private
 
     def highest_ranking(entries)
-      entries.group_by { |word, value| value }.sort.last.last
+      entries.group_by { |_, value| value }.sort.last.last
     end
 
-    def percent_of(n)
-      (n.to_f / word_count.to_f * 100).round(2)
+    def sort_by_descending_value(entries)
+      entries.sort_by { |_, value| value }.reverse
     end
 
     def regexp
@@ -74,13 +79,12 @@ module WordsCounted
         ->(word) {
           exclusion_list.include?(word.downcase)
         }
-      elsif Regexp.try_convert(filter)
-        filter = Regexp.try_convert(filter)
-        Proc.new { |word| word =~ filter }
+      elsif regexp_filter = Regexp.try_convert(filter)
+        Proc.new { |word| word =~ regexp_filter }
       elsif filter.respond_to?(:to_proc)
         filter.to_proc
       else
-        raise ArgumentError, "Filter must String, Array, Proc, or Regexp"
+        raise ArgumentError, "Filter must String, Array, Lambda, or Regexp"
       end
     end
   end

data/lib/words_counted/version.rb

@@ -1,3 +1,3 @@
 module WordsCounted
-  VERSION = "0.1.1"
+  VERSION = "0.1.3"
 end

data/lib/words_counted.rb

@@ -12,9 +12,6 @@ module WordsCounted
   end
 
   def self.from_file(path, options = {})
-    file = File.open(path)
-    data = file.read
-    file.close
-    count(data, options)
+    Counter.from_file(path, options)
   end
 end

data/spec/words_counted/counter_spec.rb

@@ -175,32 +175,42 @@ module WordsCounted
       end
 
       it "returns words and their density in percent" do
-        counter = Counter.new("His name was major, I mean, Major Major Major Major.")
-        expect(counter.word_density).to eq([["major", 50.0], ["mean", 10.0], ["i", 10.0], ["was", 10.0], ["name", 10.0], ["his", 10.0]])
+        counter = Counter.new("His name was Major, major Major Major.")
+        expect(counter.word_density).to eq([["major", 57.14], ["was", 14.29], ["name", 14.29], ["his", 14.29]])
+      end
+
+      it "accepts a precision" do
+        counter = Counter.new("His name was Major, major Major Major.")
+        expect(counter.word_density(4)).to eq([["major", 57.1429], ["was", 14.2857], ["name", 14.2857], ["his", 14.2857]])
       end
     end
 
     describe "char_count" do
       it "returns the number of chars in the passed in string" do
-        counter = Counter.new("His name was major, Major Major Major Major.")
-        expect(counter.char_count).to eq(35)
+        counter = Counter.new("His name was Major, major Major Major.")
+        expect(counter.char_count).to eq(30)
       end
 
       it "returns the number of chars in the passed in string after the filter is applied" do
-        counter = Counter.new("His name was major, Major Major Major Major.", exclude: "Major")
+        counter = Counter.new("His name was Major, major Major Major.", exclude: "Major")
         expect(counter.char_count).to eq(10)
       end
     end
 
     describe "average_chars_per_word" do
       it "returns the average number of chars per word" do
-        counter = Counter.new("His name was major, Major Major Major Major.")
-        expect(counter.average_chars_per_word).to eq(4)
+        counter = Counter.new("His name was major, Major Major Major.")
+        expect(counter.average_chars_per_word).to eq(4.29)
       end
 
       it "returns the average number of chars per word after the filter is applied" do
-        counter = Counter.new("His name was major, Major Major Major Major.", exclude: "Major")
-        expect(counter.average_chars_per_word).to eq(3)
+        counter = Counter.new("His name was Major, Major Major Major.", exclude: "Major")
+        expect(counter.average_chars_per_word).to eq(3.33)
+      end
+
+      it "accepts precision" do
+        counter = Counter.new("This line should have 39 characters minus spaces.")
+        expect(counter.average_chars_per_word(4)).to eq(5.5714)
       end
     end
 

data/words_counted.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
   spec.version       = WordsCounted::VERSION
   spec.authors       = ["Mohamad El-Husseini"]
   spec.email         = ["husseini.mel@gmail.com"]
-  spec.description   = %q{A Ruby word counter with helpful utility methods.}
+  spec.description   = %q{A Ruby word counter and string analyser with helpful utility methods.}
   spec.summary       = %q{See README.}
   spec.homepage      = "https://github.com/abitdodgy/words_counted"
   spec.license       = "MIT"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: words_counted
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.3
 platform: ruby
 authors:
 - Mohamad El-Husseini
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-23 00:00:00.000000000 Z
+date: 2014-10-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -66,7 +66,7 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: A Ruby word counter with helpful utility methods.
+description: A Ruby word counter and string analyser with helpful utility methods.
 email:
 - husseini.mel@gmail.com
 executables: []