words_counted 0.0.9 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f3043d1270f35c595ab088f6278749274daf60d3
-  data.tar.gz: 46e566b6a0fc584393ed066d4827cf7b18a4dc0a
+  metadata.gz: 5e3073a0ef54dff27a5d4314dc6d59625467538c
+  data.tar.gz: aaf703178dd69595bfd9c7023329dc68e5de4daa
 SHA512:
-  metadata.gz: 05b360658c8cf57b1c117afde1a36623b5172a0ef2c53bfb39a8a4d1a7a3cf634896b5176ebf8f68aa0fb1e4afb84350a27805d5906a7524c84404240c54d097
-  data.tar.gz: 6bd402a6df332407b2b333d4c859980986bf61df46a9a7f5dac484c65fcddc49a6d60f0f0e54c51d0f70b1ecfc6c1b58a61d095887a766ad0dcf97e9a9876dc3
+  metadata.gz: ec4445ddab09b7deaad64fefb41e7e56539ebd64910e5f0cac6529ff39f7674714720d6b942176f6615d4c5ba176002c3c6291f65d4dbd25029345baa7580eab
+  data.tar.gz: 6300d20538fd36f00921b2e9f1f2fc665bfb14e6fa092f1ba6a623c15c2c1b60b30fd4ebcf9301f0ebf6ae7502b3f05c554512e17b47b855dec59f00317a6305

data/README.md

@@ -1,14 +1,14 @@
 # Words Counted
 
-Words Counted is a highly customisable Ruby string analyser. It includes some handy utility methods that go beyond word counting. You can use this gem to get word density, words and their number of occurrences, the highest occurring words, and few more things.
+Words Counted is a highly customisable Ruby string analyser. It includes many handy utility methods that go beyond word counting. You can use this gem to get word density, words and the number of times they occur, the highest occurring words, and few more things.
 
-I use the word *word* loosely here, since you can pass the program any string you want: words, numbers, characters, etc...
+I use *word* loosely here, since you can pass the program any string you want: words, numbers, characters, etc...
 
-You can pass in your custom criteria for splitting strings in the form of a custom regular expression. This affords you a great deal of flexibility, whether you want to count words, numbers, or special characters.
+Pass in your own regular expression to customise the criteria for splitting strings. This makes Words Counted very flexible, whether you want to count words, numbers, or special characters.
 
 ### Features
 
-* Get the following data from any string:
+* Get the following data from any string or readable file:
     * Word count
     * Unique word count
     * Word density
@@ -19,9 +19,10 @@ You can pass in your custom criteria for splitting strings in the form of a cust
     * The longest word(s) and its length
     * The most occurring word(s) and its number of occurrences.
 * A flexible way to exclude words (or anything) from the count. You can pass in a **string**, a **regexp**, an **array**, or a **lambda**.
-* Filters special characters but respects hyphens and apostrophes.
-* Plays nicely with diacritics (UTF and unicode characters): "São Paulo" is treated as `["São", "Paulo"]` and not `["S", "", "o", "Paulo"]`.
-* Customisable criteria. Pass in your own regexp rules to split strings if you prefer.
+* Customisable criteria. Pass in your own regexp rules to split strings if you prefer. The default regexp has two features:
+  * Filters special characters but respects hyphens and apostrophes.
+  * Plays nicely with diacritics (UTF and unicode characters): "São Paulo" is treated as `["São", "Paulo"]` and not `["S", "", "o", "Paulo"]`.
+* Pass in a file path instead of a string. WordsCounted opens and reads files.
 
 See usage instructions for details on each feature.
 
@@ -41,12 +42,13 @@ Or install it yourself as:
 
 ## Usage
 
-Create an instance of `Counter` and pass in a string and an optional filter and/or regexp.
+Pass in a string or a file path, and an optional filter and/or regexp.
 
 ```ruby
-counter = WordsCounted::Counter.new(
-	"We are all in the gutter, but some of us are looking at the stars."
-)
+counter = WordsCounted.count("We are all in the gutter, but some of us are looking at the stars.")
+
+# Using a file
+counter = WordsCounted.from_file("path/to/my/file.txt")
 ```
 
 ### API
@@ -67,19 +69,19 @@ Returns a hash map of words and their number of occurrences. Uppercase and lower
 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
+  "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
  }
 ```
 
@@ -144,19 +146,19 @@ Returns a two-dimentional array of words and their density.
 counter.word_density
 
 [
-  ["are", 13.33],
-  ["the", 13.33],
-  ["but", 6.67],
-  ["us", 6.67],
-  ["of", 6.67],
-  ["some", 6.67],
+  ["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]
+  ["gutter",  6.67],
+  ["at",      6.67],
+  ["in",      6.67],
+  ["all",     6.67],
+  ["stars",   6.67],
+  ["we",      6.67]
 ]
 ```
 
@@ -198,7 +200,7 @@ You can exclude anything you want from the string you want to analyse by passing
 
 #### Using a string
 ```ruby
-WordsCounted::Counter.new(
+WordsCounted.count(
   "Magnificent! That was magnificent, Trevor.", exclude: "was magnificent"
 )
 counter.words
@@ -207,21 +209,21 @@ counter.words
 
 #### Using an array
 ```ruby
-WordsCounted::Counter.new("1 2 3 4 5 6", regexp: /[0-9]/, exclude: ['1', '2', '3'])
+WordsCounted.count("1 2 3 4 5 6", regexp: /[0-9]/, exclude: ['1', '2', '3'])
 counter.words
 #=> ["4", "5", "6"]
 ```
 
 #### Using a regular expression
 ```ruby
-WordsCounted::Counter.new("Hello Beirut", exclude: /Beirut/)
+WordsCounted.count("Hello Beirut", exclude: /Beirut/)
 counter.words
 #=> ["Hello"]
 ```
 
 #### Using a lambda
 ```ruby
-WordsCounted::Counter.new(
+WordsCounted.count(
   "1 2 3 4 5 6", regexp: /[0-9]/, exclude: ->(w) { w.to_i.even? }
 )
 counter.words
@@ -241,17 +243,25 @@ But maybe you don't want to count words? Well, count anything you want. What you
 For example, if you wanted to include numbers in your analysis, you can override the regular expression:
 
 ```ruby
-counter = WordsCounted::Counter.new("Numbers 1, 2, and 3", regexp: /[\p{Alnum}\-']+/)
+counter = WordsCounted.count("Numbers 1, 2, and 3", regexp: /[\p{Alnum}\-']+/)
 counter.words
 #=> ["Numbers", "1", "2", "and", "3"]
 ```
 
+## Opening and Reading Files
+
+Use the `from_file` method to open files. Opening files accepts the same options as reading from a string. The file path can be a URL.
+
+```ruby
+counter = WordsCounted.from_file("url/or/path/to/file.text")
+```
+
 ## Gotchas
 
 A hyphen used in leu of an *em* or *en* dash will form part of the word and throw off the `word_occurences` algorithm.
 
 ```ruby
-counter = WordsCounted::Counter.new("How do you do?-you are well, I see.")
+counter = WordsCounted.count("How do you do?-you are well, I see.")
 counter.word_occurrences
 
 {
@@ -273,10 +283,10 @@ Another gotcha is that the default criteria does not include numbers in its anal
 
 ## Road Map
 
-1. Add ability to open files or URLs.
+1. Add ability to open URLs.
 2. Add paragraph, sentence, average words per sentence, and average sentence chars counters.
 
-#### Ability to open files and URLs
+#### Ability to open URLs
 
 Maybe I can some class methods to open the file and init the counter class.
 

data/lib/words_counted/counter.rb

@@ -48,7 +48,7 @@ module WordsCounted
     end
 
     def percent_of(n)
-      (n.to_f / word_count.to_f * 100.0).round(2)
+      (n.to_f / word_count.to_f * 100).round(2)
     end
 
     def regexp
@@ -63,16 +63,16 @@ module WordsCounted
         }
       elsif filter.respond_to?(:to_str)
         exclusion_list = filter.split.collect(&:downcase)
-        ->(w) {
-          exclusion_list.include?(w.downcase)
+        ->(word) {
+          exclusion_list.include?(word.downcase)
         }
       elsif Regexp.try_convert(filter)
         filter = Regexp.try_convert(filter)
-        Proc.new { |w| w =~ filter }
+        Proc.new { |word| word =~ filter }
       elsif filter.respond_to?(:to_proc)
         filter.to_proc
       else
-        raise ArgumentError, "Incorrect filter type"
+        raise ArgumentError, "Filter must String, Array, Proc, or Regexp"
       end
     end
   end

data/lib/words_counted/version.rb

@@ -1,3 +1,3 @@
 module WordsCounted
-  VERSION = "0.0.9"
+  VERSION = "0.1.0"
 end

data/lib/words_counted.rb

@@ -7,4 +7,14 @@ rescue LoadError
 end
 
 module WordsCounted
+  def self.count(string, options = {})
+    Counter.new(string, options)
+  end
+
+  def self.from_file(path, options = {})
+    file = File.open(path)
+    data = file.read
+    file.close
+    count(data, options)
+  end
 end

data/spec/support/the_hart_and_the_hunter.txt

@@ -0,0 +1,16 @@
+The Hart and the Hunter
+
+	The Hart was once drinking from a pool and admiring the noble
+figure he made there.  "Ah," said he, "where can you see such
+noble horns as these, with such antlers!  I wish I had legs more
+worthy to bear such a noble crown; it is a pity they are so slim
+and slight."  At that moment a Hunter approached and sent an arrow
+whistling after him.  Away bounded the Hart, and soon, by the aid
+of his nimble legs, was nearly out of sight of the Hunter; but not
+noticing where he was going, he passed under some trees with
+branches growing low down in which his antlers were caught, so
+that the Hunter had time to come up.  "Alas! alas!" cried the
+Hart:
+
+
+"We often despise what is most useful to us."

data/spec/words_counted/counter_spec.rb

@@ -5,7 +5,7 @@ module WordsCounted
   describe Counter do
     let(:counter) { Counter.new("We are all in the gutter, but some of us are looking at the stars.") }
 
-    describe "#initialize" do
+    describe "initialize" do
       it "sets @options" do
         expect(counter.instance_variables).to include(:@options)
       end
@@ -27,7 +27,7 @@ module WordsCounted
       end
     end
 
-    describe ".words" do
+    describe "words" do
       it "returns an array" do
         expect(counter.words).to be_a(Array)
       end
@@ -97,13 +97,13 @@ module WordsCounted
       end
     end
 
-    describe ".word_count" do
+    describe "word_count" do
       it "returns the correct word count" do
         expect(counter.word_count).to eq(15)
       end
     end
 
-    describe ".word_occurrences" do
+    describe "word_occurrences" do
       it "returns a hash" do
         expect(counter.word_occurrences).to be_a(Hash)
       end
@@ -114,7 +114,7 @@ module WordsCounted
       end
     end
 
-    describe ".most_occurring_words" do
+    describe "most_occurring_words" do
       it "returns an array" do
         expect(counter.most_occurring_words).to be_a(Array)
       end
@@ -125,7 +125,7 @@ module WordsCounted
       end
     end
 
-    describe '.word_lengths' do
+    describe 'word_lengths' do
       it "returns a hash" do
         expect(counter.word_lengths).to be_a(Hash)
       end
@@ -136,7 +136,7 @@ module WordsCounted
       end
     end
 
-    describe ".longest_words" do
+    describe "longest_words" do
       it "returns an array" do
         expect(counter.longest_words).to be_a(Array)
       end
@@ -147,8 +147,8 @@ module WordsCounted
       end
     end
 
-    describe ".word_density" do
-      it "returns a hash" do
+    describe "word_density" do
+      it "returns an array" do
         expect(counter.word_density).to be_a(Array)
       end
 
@@ -158,7 +158,7 @@ module WordsCounted
       end
     end
 
-    describe ".char_count" do
+    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)
@@ -170,7 +170,7 @@ module WordsCounted
       end
     end
 
-    describe ".average_chars_per_word" do
+    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)
@@ -182,10 +182,17 @@ module WordsCounted
       end
     end
 
-    describe ".unique_word_count" do
+    describe "unique_word_count" do
       it "returns the number of unique words" do
         expect(counter.unique_word_count).to eq(13)
       end
     end
   end
+
+  describe "from_file" do
+    it "opens and reads a text file" do
+      counter = WordsCounted.from_file('spec/support/the_hart_and_the_hunter.txt')
+      expect(counter.word_count).to eq(139)
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: words_counted
 version: !ruby/object:Gem::Version
-  version: 0.0.9
+  version: 0.1.0
 platform: ruby
 authors:
 - Mohamad El-Husseini
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-22 00:00:00.000000000 Z
+date: 2014-10-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -84,6 +84,7 @@ files:
 - lib/words_counted/counter.rb
 - lib/words_counted/version.rb
 - spec/spec_helper.rb
+- spec/support/the_hart_and_the_hunter.txt
 - spec/words_counted/counter_spec.rb
 - words_counted.gemspec
 homepage: https://github.com/abitdodgy/words_counted
@@ -112,4 +113,5 @@ specification_version: 4
 summary: See README.
 test_files:
 - spec/spec_helper.rb
+- spec/support/the_hart_and_the_hunter.txt
 - spec/words_counted/counter_spec.rb