text_analysis 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2197f3109b941d4e689529a18d361dec6a8645f0
-  data.tar.gz: b5e8a30a0007b3b3f07cc48e29a21675c2d29611
+  metadata.gz: 8bf0a077bb90faf47c6a8dbb4a390099b6128b4f
+  data.tar.gz: 080a37894e3d3118ebca46617eb3a75216a68490
 SHA512:
-  metadata.gz: a8530ae5b4449823464ca4055f99ae0dba0803f13a5c0b13f114dd3d088df4bb5c658c68ee26a2a755a0a912e5f2fcae388c67caa3d4c759cb89a787057478f6
-  data.tar.gz: 4d60333852d771621c0610f7370e9c8f4d4e7ae955ca231a64f4630962ad74e8c2e9fdd5ee25c6e7427febfae76e8d60a40104d3d8367623aec4abf4640d850f
+  metadata.gz: eed1848f7929c86359066a959a777cfac269e97f87aada48a8d1956c47d7cd985e5b3359e4508843610f4cfacd5b2b3aeedf6ffee0a06af601c831caafdb9652
+  data.tar.gz: c56d71c7d7c6cd2c949761bd1afa275c3a790e8a57defd0fc8048414bf36b65e0fae8d80898a4ddd68dd3cd7933912ed110d9c1d106b1c3ccceedef103bd3e5f

data/CHANGELOG.md

@@ -0,0 +1,11 @@
+## 0.2.0 (2016-07-22)
+
+New features
+* Move out of hash response into proper model and attributes
+* Added stop_words_found
+* Added most_common_words
+* Added most_common_non_stop_words
+
+## 0.1.0 (2016-07-19)
+
+* Initial commit

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    text_analysis (0.1.0)
+    text_analysis (0.2.0)
 
 GEM
   remote: https://rubygems.org/
@@ -17,6 +17,9 @@ GEM
     rspec-expectations (3.4.0)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.4.0)
+    rspec-its (1.2.0)
+      rspec-core (>= 3.0.0)
+      rspec-expectations (>= 3.0.0)
     rspec-mocks (3.4.0)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.4.0)
@@ -29,6 +32,7 @@ DEPENDENCIES
   bundler (~> 1.10)
   rake (~> 10.0)
   rspec
+  rspec-its
   text_analysis!
 
 BUNDLED WITH

data/data/stop_words/en.txt

@@ -0,0 +1,182 @@
+i
+me
+my
+myself
+we
+our
+ours
+ourselves
+you
+your
+yours
+yourself
+yourselves
+he
+him
+his
+himself
+she
+her
+hers
+herself
+it
+its
+itself
+they
+them
+their
+theirs
+themselves
+what
+which
+who
+whom
+this
+that
+these
+those
+am
+is
+are
+was
+were
+be
+been
+being
+have
+has
+had
+having
+do
+does
+did
+doing
+would
+should
+could
+ought
+i'm
+you're
+he's
+she's
+it's
+we're
+they're
+i've
+you've
+we've
+they've
+i'd
+you'd
+he'd
+she'd
+we'd
+they'd
+i'll
+you'll
+he'll
+she'll
+we'll
+they'll
+isn't
+aren't
+wasn't
+weren't
+hasn't
+haven't
+hadn't
+doesn't
+don't
+didn't
+won't
+wouldn't
+shan't
+shouldn't
+can't
+cannot
+couldn't
+mustn't
+let's
+that's
+who's
+what's
+here's
+there's
+when's
+where's
+why's
+how's
+a
+an
+the
+and
+but
+if
+or
+because
+as
+until
+while
+of
+at
+by
+for
+with
+about
+against
+between
+into
+through
+during
+before
+after
+above
+below
+to
+from
+up
+down
+in
+out
+on
+off
+over
+under
+again
+further
+then
+once
+here
+there
+when
+where
+why
+how
+all
+any
+both
+each
+few
+more
+most
+other
+some
+such
+no
+nor
+not
+only
+same
+so
+than
+too
+very
+still
+much
+many
+per
+yet
+sure
+ok
+now
+might

data/lib/text_analysis/version.rb

@@ -1,3 +1,3 @@
 module TextAnalysis
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/lib/text_analysis.rb

@@ -2,12 +2,39 @@ require "text_analysis/version"
 
 module TextAnalysis
   def self.analyze_text(text_input)
-    hash = {}
+    result = Result.new
 
-    hash[:total_characters] = text_input.length
-    hash[:total_characters_without_whitespaces] = text_input.gsub(/\s+/, "").length
-    hash[:total_words] = text_input.split(/[\w-]+/).size
+    stop_words = File.readlines('data/stop_words/en.txt').map { |word| word.gsub("\n", '') }.inspect
+    input_words = text_input.split(/[\s]+/)
 
-    hash
+    result.total_characters = text_input.length
+    result.total_characters_without_whitespaces = text_input.gsub(/\s+/, "").length
+    result.total_words = input_words.size
+    result.stop_words_found = input_words.select { |word| stop_words.include? word.downcase }.uniq
+    result.most_common_words =
+        input_words.
+            group_by { |word| word.downcase }.
+            map { |k,v| { :word => k, :occurences => v.size } }.
+            sort_by { |hash| hash[:occurences] }.
+            reverse
+
+    result.most_common_non_stop_words =
+        input_words.
+            reject { |word| stop_words.include? word.downcase }.
+            group_by { |word| word.downcase }.
+            map { |k,v| { :word => k, :occurences => v.size } }.
+            sort_by { |hash| hash[:occurences] }.
+            reverse
+
+    result
+  end
+
+  class Result
+    attr_accessor :total_characters,
+                  :total_characters_without_whitespaces,
+                  :total_words,
+                  :stop_words_found,
+                  :most_common_words,
+                  :most_common_non_stop_words
   end
 end

data/text_analysis.gemspec

@@ -22,4 +22,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "bundler", "~> 1.10"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec"
+  spec.add_development_dependency "rspec-its"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_analysis
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Vasilis Kalligas
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-07-18 00:00:00.000000000 Z
+date: 2016-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -52,6 +52,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec-its
+  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: TextAnalysis is a gem that given a text input, can produce a list of
   text analysis information such as word and character count.
 email:
@@ -63,6 +77,7 @@ files:
 - ".gitignore"
 - ".rspec"
 - ".travis.yml"
+- CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - Gemfile
 - Gemfile.lock
@@ -72,6 +87,7 @@ files:
 - Rakefile
 - bin/console
 - bin/setup
+- data/stop_words/en.txt
 - lib/text_analysis.rb
 - lib/text_analysis/version.rb
 - text_analysis.gemspec