pseudo_date 0.1.5 → 0.3.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 194f7ad213e4723e13dadd0bb7e4808b0e7d078d96302f27e67c926a471740a7
+  data.tar.gz: 5924349cb3530554acc4778d3983351afecb4f22a413906555259b3a70a008b8
+SHA512:
+  metadata.gz: 6af99fbd3a7e1a14c4e0966e145e60abd25242b9bc127e24304134eee90a35c66224878da002fb8f7e168d61065cdf22b7ed99c4ab56d3e134d13e7ef56e9a1f
+  data.tar.gz: f18fde6cdade727c95c9768a713a664dc4842a80afc8e4d464c2c44d02d78d30b4cf83930a0359b22f03772f2f9a464ed79227844995412ee8ee27024277161c

data/Gemfile.lock

@@ -1,20 +1,24 @@
 PATH
   remote: .
   specs:
-    pseudo_date (0.1.5)
+    pseudo_date (0.2.0)
 
 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)
+    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
@@ -22,3 +26,6 @@ PLATFORMS
 DEPENDENCIES
   pseudo_date!
   rspec
+
+BUNDLED WITH
+   2.1.4

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/core_extensions/string.rb

@@ -1,11 +1,11 @@
 class String
   
   def to_date_hash
-    Parser.parse(self)
+    PseudoDate::Parser.parse(self)
   end
     
   def to_pseudo_date
     PseudoDate.new(self)
   end
   
-end
+end

data/lib/pseudo_date/parser.rb

@@ -1,90 +1,115 @@
 require 'date'
-class Parser
+require_relative 'pseudo_date'
+
+class PseudoDate
+  class Parser
   
-  def self.parse(input)
-    date_hash = {}
-    # Minor Pre Cleanup
-    input.strip!; input.gsub!('~','')
+    AMERICAN_DATE_FORMAT = '%m/%d/%Y'
+    EUROPEAN_DATE_FORMAT = '%Y-%m-%d'
     
-    date = input.split(/\/|-/).length < 3 ? nil : Date.parse(input) rescue nil
-    if date
-      date_hash = { :year => date.year.to_s, :month => date.month.to_s, :day => date.day.to_s }
-    else
-      year, month, day = parse_string(input)
-      date_hash = { :year => year, :month => month, :day => day }
-    end
-    
-    # Post parsing cleanup
-    date_hash.each do |key, value|
-      date_hash[key] = if value.nil?
-        key.to_s == 'year' ? '0000' : '00'
+    def self.parse(input)
+      date_hash = {}
+      # Minor Pre Cleanup
+      input.strip!; input.gsub!('~','')
+      
+      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
-        date_hash[key] = value.to_s.strip
+        year, month, day = parse_string(input)
+        date_hash = { :year => year, :month => month, :day => day }
       end
-    end
-    
-    # Cleanup the single digit values
-    unless date_hash.empty?
-      date_hash.each do |key,value|
-        date_hash[key] = "0#{value}" if value.to_s.length == 1
+      
+      # Post parsing cleanup
+      date_hash.each do |key, value|
+        date_hash[key] = if value.nil?
+          key.to_s == 'year' ? '0000' : '00'
+        else
+          date_hash[key] = value.to_s.strip
+        end
       end
+      
+      # Cleanup the single digit values
+      unless date_hash.empty?
+        date_hash.each do |key,value|
+          date_hash[key] = "0#{value}" if value.to_s.length == 1
+        end
+      end
+      
+      # Two character years
+      if date_hash[:year].length == 2
+        date_hash[:year] = date_hash[:year].to_i > Date.today.year.to_s.slice(2..4).to_i ? "19#{date_hash[:year]}" : "20#{date_hash[:year]}"
+      end
+      
+      # Attempt to correct some known OCR issues
+      if date_hash[:year].to_s.match('00') && date_hash[:year] != '0000'
+        date_hash[:year] = "2#{date_hash[:year].slice(1..3)}"
+      end
+      
+      return date_hash.empty? ? nil : date_hash
     end
     
-    # Two character years
-    if date_hash[:year].length == 2
-      date_hash[:year] = date_hash[:year].to_i > Date.today.year.to_s.slice(2..4).to_i ? "19#{date_hash[:year]}" : "20#{date_hash[:year]}"
-    end
+    private
     
-    # Attempt to correct some known OCR issues
-    if date_hash[:year].to_s.match('00') && date_hash[:year] != '0000'
-      date_hash[:year] = "2#{date_hash[:year].slice(1..3)}"
+    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
     
-    return date_hash.empty? ? nil : date_hash
-  end
-  
-  private
-  
-  def self.parse_string(input)
-    day, month, year = "00", "00", "0000"
-    if input.match('/') # 02/25/2008
-      date_array = input.split('/')
-      if date_array.length == 3
-        begin
-          parsed_date = Date.parse(self)
-          month, day, year = parsed_date.month, parsed_date.day, parsed_date.year
-        rescue
-          month, day, year = date_array
+    def self.parse_string(input)
+      day, month, year = "00", "00", "0000"
+      if input.match('/') # 02/25/2008
+        date_array = input.split('/')
+        if date_array.length == 3
+          begin
+            parsed_date = Date.parse(self)
+            month, day, year = parsed_date.month, parsed_date.day, parsed_date.year
+          rescue
+            month, day, year = date_array
+          end
+        elsif date_array.length == 2
+          month, year = date_array
         end
-      elsif date_array.length == 2
-        month, year = date_array
-      end
-    elsif input.length == 8 && is_numeric?(input) # 20080225
-      year, month, day = input.slice(0..3), input.slice(4..5), input.slice(6..7)
-    elsif input.match('-') # 1985-09-25 or 02-25-2008
-      date_array = input.split('-')
-      year = date_array.select{ |part| part.length == 4 }.first
-      unless year.nil? || date_array.length != 3
-        if date_array.first == year
-          month = date_array.last
-          day = date_array[1]
-        else
-          month = date_array.first
-          day = date_array[1]
+      elsif input.length == 8 && is_numeric?(input) # 20080225
+        year, month, day = input.slice(0..3), input.slice(4..5), input.slice(6..7)
+      elsif input.match('-') # 1985-09-25 or 02-25-2008
+        date_array = input.split('-')
+        year = date_array.select{ |part| part.length == 4 }.first
+        unless year.nil? || date_array.length != 3
+          if date_array.first == year
+            month = date_array.last
+            day = date_array[1]
+          else
+            month = date_array.first
+            day = date_array[1]
+          end
+          month, day = [day, month] if month.to_i > 12 && month.to_i > day.to_i
         end
-        month, day = [day, month] if month.to_i > 12 && month.to_i > day.to_i
+      elsif input.length == 4 # 2004
+        year = input.to_s
+      elsif input.length == 2 # 85
+        year = (input.to_i > Date.today.year.to_s.slice(2..4).to_i) ? "19#{input}" : "20#{input}"
+      elsif input.match(/\w/) # Jun 23, 2004
+        begin
+          d = Date.parse(input)
+          year, month, day = d.year.to_s, d.month.to_s, d.day.to_s
+        rescue; end
       end
-    elsif input.length == 4 # 2004
-      year = input.to_s if (input.slice(0..1) == '19' || input.slice(0..1) == '20')
-    elsif input.length == 2 # 85
-      year = (input.to_i > Date.today.year.to_s.slice(2..4).to_i) ? "19#{input}" : "20#{input}"
-    elsif input.match(/\w/) # Jun 23, 2004
-      begin
-        d = Date.parse(input)
-        year, month, day = d.year.to_s, d.month.to_s, d.day.to_s
-      rescue; end
+      return [year, month, day]
     end
-    return [year, month, day]
+    
   end
-  
-end
+
+end

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 = "0.1.5"
+  VERSION = "0.3.0"
 end

data/pseudo_date.gemspec

@@ -16,6 +16,7 @@ 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")
 end

data/spec/parser_spec.rb

@@ -8,7 +8,7 @@ describe "PseudoDate Parsing" do
     @year        = '1985'
     @string_date = 'Jun 25, 1985'
   end
-
+  
   context "date hash" do
     it "should parse an exact hash" do
       pd = PseudoDate.new(:year => @year, :day => @day, :month => @month)
@@ -24,7 +24,7 @@ describe "PseudoDate Parsing" do
       pd.year.should == @year
     end
   end
-
+  
   # 19850625
   context "yearmonthday" do
     it 'should be exact precision' do
@@ -38,7 +38,7 @@ describe "PseudoDate Parsing" do
       pd.year.should == @year
     end
   end
-
+  
   # 1985-25-06
   context "year-day-month" do
     it 'should be exact precision' do
@@ -52,7 +52,7 @@ describe "PseudoDate Parsing" do
       pd.year.should == @year
     end
   end
-
+  
   # 06-25-1985
   context "month-day-year" do
     it 'should be exact precision' do
@@ -66,7 +66,7 @@ describe "PseudoDate Parsing" do
       pd.year.should == @year
     end
   end
-
+  
   # 25-06-1985
   context "day-month-year" do
     it 'should be exact precision' do
@@ -80,7 +80,7 @@ describe "PseudoDate Parsing" do
       pd.year.should == @year
     end
   end
-
+  
   # 06/25/1985
   context "month/day/year" do
     it 'should be exact precision' do
@@ -94,7 +94,21 @@ describe "PseudoDate Parsing" do
       pd.year.should == @year
     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
@@ -107,7 +121,7 @@ describe "PseudoDate Parsing" do
       pd.year.should == @year
     end
   end
-
+  
   # 85
   context "two digit year" do
     it 'should be year precision' do
@@ -120,16 +134,36 @@ describe "PseudoDate Parsing" do
     end
   end
 
-  # 1985
   context "four digit year" do
+    
     it 'should be year precision' do
       PseudoDate.new(@year).precision.should == 'year'
     end
-  
-    it 'should match original input' do
-      pd = PseudoDate.new(@year)
-      pd.year.should == @year
-    end
+    
+    # 1885
+    context "in the 19th century" do
+      it 'should match original input' do
+        pd = PseudoDate.new('1885')
+        pd.year.should == '1885'
+      end
+    end
+    
+    # 1985
+    context "in the 20th century" do
+      it 'should match original input' do
+        pd = PseudoDate.new('1985')
+        pd.year.should == '1985'
+      end
+    end
+    
+    # 2085
+    context "in the 21st century" do
+      it 'should match original input' do
+        pd = PseudoDate.new('2085')
+        pd.year.should == '2085'
+      end
+    end
+    
   end
 
   # Jun 25, 1985

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 +1,9 @@
 require 'rubygems'
 require 'rspec'
 require File.dirname(__FILE__) + '/../lib/pseudo_date'
+
+RSpec.configure do |config|
+  config.expect_with :rspec do |c|
+    c.syntax = :should
+  end
+end

metadata

@@ -1,30 +1,27 @@
 --- !ruby/object:Gem::Specification
 name: pseudo_date
 version: !ruby/object:Gem::Version
-  version: 0.1.5
-  prerelease: 
+  version: 0.3.0
 platform: ruby
 authors:
 - Patrick Tulskie
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-05-01 00:00:00.000000000 Z
+date: 2022-06-09 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'
 description: Date parser and container for partial or incomplete dates.
@@ -34,7 +31,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - Gemfile.lock
 - Manifest
@@ -52,28 +49,27 @@ files:
 - spec/pseudo_date_spec.rb
 - spec/spec_helper.rb
 homepage: http://github.com/PatrickTulskie/pseudo_date
-licenses: []
-post_install_message: 
+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
-signing_key: 
-specification_version: 3
+rubygems_version: 3.2.3
+signing_key:
+specification_version: 4
 summary: Date parser and container for partial or incomplete dates.
 test_files:
 - spec/parser_spec.rb