pseudo_date 0.1.6 → 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 62d190d71ddd979da81fbea52eb5e2df961dcb4c
+  data.tar.gz: ec4fe5b5c8739ad59631bce20bb5bfd320a57b2e
+SHA512:
+  metadata.gz: 7fb8dd8c6bc227e74d89190d8870071235823db1b6810acc8596eed61b5ae4745e7960ad57b6f76fec45f76375858d0f8385c2361d8a78de9cde91c8a7cdf5a3
+  data.tar.gz: 2298c31062c1295cca27a575e977a82b7e1b881eddf2f0dfb2858dffbbcd6d09eea2cb358b3f48a3348ec140336d70236702a3f9fda96ed88fbbaa30c6c1119e

data/Gemfile.lock

@@ -1,24 +1,34 @@
 PATH
   remote: .
   specs:
-    pseudo_date (0.1.5)
+    pseudo_date (0.1.6)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    diff-lcs (1.2.4)
-    rspec (2.13.0)
-      rspec-core (~> 2.13.0)
-      rspec-expectations (~> 2.13.0)
-      rspec-mocks (~> 2.13.0)
-    rspec-core (2.13.1)
-    rspec-expectations (2.13.0)
-      diff-lcs (>= 1.1.3, < 2.0)
-    rspec-mocks (2.13.1)
+    byebug (3.1.2)
+      columnize (~> 0.8)
+      debugger-linecache (~> 1.2)
+    columnize (0.8.9)
+    debugger-linecache (1.2.0)
+    diff-lcs (1.2.5)
+    rspec (3.0.0)
+      rspec-core (~> 3.0.0)
+      rspec-expectations (~> 3.0.0)
+      rspec-mocks (~> 3.0.0)
+    rspec-core (3.0.1)
+      rspec-support (~> 3.0.0)
+    rspec-expectations (3.0.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.0.0)
+    rspec-mocks (3.0.1)
+      rspec-support (~> 3.0.0)
+    rspec-support (3.0.0)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
+  byebug
   pseudo_date!
   rspec

data/README.mdown

@@ -6,15 +6,17 @@ It's a date but not really.  A PseudoDate object has a day, month, and year but
 
 ## What Is This For?
 
-PseudoDate was created to parse odd dates in odd formats and attempt to extract as much information from them as possible.  It's especially handy when you're trying to convert a date string that has come from an OCR'd source.
+PseudoDate was created to parse odd dates in odd formats and attempt to extract as much information from them as possible.  It's especially handy when you're trying to convert a date string that has come from an OCR'd source.  It was primarily written to parse dates in American public record data in an effort to have a common date format when doing record matching.
 
 ## Assumptions
 
-As with all parsing, one needs to make assumptions.  The main assumption made here is that all dates will be in the past.
+As with all parsing, one needs to make assumptions.  The main assumption made here is that all dates will be in the past.  Dates that appear to be far-future are generally labeled as "invalid."
+
+Since this gem was built for trying to wrangle OCR'd dates we have to make some assumptions when it comes to date formats.  As of `0.2.0` the gem now assumes that dates separated by a "/" are American dates and those that are separated by a "-" are European dates.  Future versions may allow some configuration for this depending on your usage but in my experience there has not been a need for that.  This mimics the behavior from Ruby 1.8.7 which was changed in Ruby 1.9+.
 
 ## Other Notes
 
-PseudoDate stores date attributes in strings instead of integers to avoid losing the preceding '0' on various attributes.  This was a decision made when first creating the class because of the way things were being output in the project it was created for.
+PseudoDate stores date attributes in strings instead of integers to avoid losing the preceding '0' on various attributes.  This was a decision made when first creating the class because of the way things were being output in the project it was created for.  There has been some discussion about switching these to integers in order to help save on memory but no decision has been made here either way.
 
 ## Compatability
 

data/lib/pseudo_date/parser.rb

@@ -1,12 +1,16 @@
 require 'date'
 class Parser
   
+  AMERICAN_DATE_FORMAT = '%m/%d/%Y'
+  EUROPEAN_DATE_FORMAT = '%Y-%m-%d'
+  
   def self.parse(input)
     date_hash = {}
     # Minor Pre Cleanup
     input.strip!; input.gsub!('~','')
     
-    date = input.split(/\/|-/).length < 3 ? nil : Date.parse(input) rescue nil
+    date = parse_with_poro_date(input)
+    
     if date
       date_hash = { :year => date.year.to_s, :month => date.month.to_s, :day => date.day.to_s }
     else
@@ -45,6 +49,22 @@ class Parser
   
   private
   
+  def self.parse_with_poro_date(string)
+    # If our date has 3 parts then let's try to parse it with Date::strptime
+    if string.split(/\/|-/).length < 3
+      case string
+      when /-/ # Europeans generally use hyphens to separate date pieces
+        Date.strptime(string, EUROPEAN_DATE_FORMAT)
+      when /\// # Americans usually use a / to separate date pieces
+        Date.strptime(string, AMERICAN_DATE_FORMAT)
+      end
+    else
+      nil # Not enough parts so just return nil
+    end
+  rescue
+    nil # We don't actually care why Date is complaining. We'll fall back to slower parsing later.
+  end
+  
   def self.parse_string(input)
     day, month, year = "00", "00", "0000"
     if input.match('/') # 02/25/2008

data/lib/pseudo_date/pseudo_date.rb

@@ -86,22 +86,22 @@ class PseudoDate
     when 'exact'
       self.to_date < other.to_date
     when 'year_month'
-      self.year == other.year ? (self.month < other.month) : (self.year < other.year)
+      self.year == other.year ? (self.month.to_i < other.month.to_i) : (self.year.to_i < other.year.to_i)
     when 'year'
-      self.year < other.year
+      self.year.to_i < other.year.to_i
     when 'mixed'
       if self.precision == 'invalid'
         true
       elsif other.precision == 'invalid'
         false
-      elsif self.year == other.year
-        if self.month == other.month
+      elsif self.year.to_i == other.year.to_i
+        if self.month.to_i == other.month.to_i
           self.day.to_i < other.day.to_i
         else
-          self.month < other.month
+          self.month.to_i < other.month.to_i
         end
       else
-        self.year < other.year
+        self.year.to_i < other.year.to_i
       end
     else
       false

data/lib/pseudo_date/version.rb

@@ -1,3 +1,3 @@
 class PseudoDate
-  VERSION = "0.1.6"
+  VERSION = "0.2.0"
 end

data/pseudo_date.gemspec

@@ -16,6 +16,8 @@ Gem::Specification.new do |gem|
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
   gem.require_paths = ["lib"]
+  gem.license       = 'MIT'
   
-  gem.add_development_dependency("rspec")
+  gem.add_development_dependency("rspec", "~> 0")
+  gem.add_development_dependency("byebug", "~> 0")
 end

data/spec/parser_spec.rb

@@ -95,6 +95,20 @@ describe "PseudoDate Parsing" do
     end
   end
   
+  # 06/7/1985
+  context "month/day/year" do
+    it 'should be exact precision' do
+      PseudoDate.new("#{@month}/7/#{@year}").precision.should == 'exact'
+    end
+  
+    it 'should match original input' do
+      pd = PseudoDate.new("#{@month}/7/#{@year}")
+      pd.day.should == "07"
+      pd.month.should == @month
+      pd.year.should == @year
+    end
+  end
+  
   # 06/1985
   context "month/year" do
     it 'should be partial precision' do

data/spec/pseudo_date_spec.rb

@@ -22,7 +22,7 @@ describe "PseudoDate" do
     it "should demonstrate later dates as greater than older dates" do
       old_date = PseudoDate.new(:year => @year, :month => @month)
       new_date = PseudoDate.new(:year => 1996, :month => @month)
-      (old_date < new_date).should be_true
+      (old_date < new_date).should == true
     end
     it "should respond properly with the spaceship operator" do
       old_date = PseudoDate.new(:year => @year, :month => @month)
@@ -37,7 +37,7 @@ describe "PseudoDate" do
     it "should demonstrate later dates as greater than older dates" do
       old_date = PseudoDate.new(:year => @year, :month => @month, :day => @day)
       new_date = PseudoDate.new(:year => 1996, :month => @month, :day => @day)
-      (old_date < new_date).should be_true
+      (old_date < new_date).should == true
     end
     it "should respond properly with the spaceship operator" do
       old_date = PseudoDate.new(:year => @year, :month => @month, :day => @day)
@@ -52,12 +52,12 @@ describe "PseudoDate" do
     it "should demonstrate later dates as greater than older dates" do
       old_date = PseudoDate.new(:year => @year, :month => @month)
       new_date = PseudoDate.new(:year => 1996, :month => @month, :day => @day)
-      (old_date < new_date).should be_true
+      (old_date < new_date).should == true
     end
     it "should demonstrate invalid dates as less than complete dates" do
       complete = PseudoDate.new(:year => @year, :month => @month)
       invalid = PseudoDate.new("")
-      (complete > invalid).should be_true
+      (complete > invalid).should == true
     end
     it "should respond properly with the spaceship operator" do
       old_date = PseudoDate.new(:year => @year, :month => @month)

data/spec/spec_helper.rb

@@ -1,3 +1,10 @@
 require 'rubygems'
 require 'rspec'
 require File.dirname(__FILE__) + '/../lib/pseudo_date'
+require 'byebug'
+
+RSpec.configure do |config|
+  config.expect_with :rspec do |c|
+    c.syntax = :should
+  end
+end

metadata

@@ -1,30 +1,41 @@
 --- !ruby/object:Gem::Specification
 name: pseudo_date
 version: !ruby/object:Gem::Version
-  version: 0.1.6
-  prerelease: 
+  version: 0.2.0
 platform: ruby
 authors:
 - Patrick Tulskie
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-04 00:00:00.000000000 Z
+date: 2014-06-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  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: Date parser and container for partial or incomplete dates.
@@ -34,7 +45,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - Gemfile.lock
 - Manifest
@@ -52,28 +63,28 @@ files:
 - spec/pseudo_date_spec.rb
 - spec/spec_helper.rb
 homepage: http://github.com/PatrickTulskie/pseudo_date
-licenses: []
+licenses:
+- MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Date parser and container for partial or incomplete dates.
 test_files:
 - spec/parser_spec.rb