revs-utils 1.0.21 → 2.0.0

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    ZTI2NDBhNTNmMzBhYzdiY2M5MjM2Y2QzNjVkYzEwNWFjZGRlNWRlMw==
+    ZDhhZDFiZDllZWY5MjhhMjE1NTBlN2YxYzNjYTM1YjdlMjk1NTU4ZA==
   data.tar.gz: !binary |-
-    N2Q0Y2MzNmM0MWFjNmMyMWViOTU0NGY4NjMyM2Y4MDlkMTUzZWYxOA==
+    NjJiY2E0MGRjZTllZGE1YTRlNGJiZjg1NDcyNmM5YzcwOWNmNDQwYg==
 SHA512:
   metadata.gz: !binary |-
-    ODVmMGMwNjVmZTlmOGZiMDlkZjg3Y2YyODFkODBlNzVhZmZmNzAxZTg3NTlj
-    YzhmODE2NTc4ZmIyYTNlNTMwMjIwYmRhODgzNDYxMzY4MTZmZTA5NjQwOGQw
-    NjljZjc3Yzg1NTRhZTUxZjlhNjYzOTIyYjMyZTFlNzg2NTIwODE=
+    NjE0YmY4NWViN2U3ZDE5ZjRhMWM2ZWQxYWM3ZTkyNDQ5MTRkYjE4YjUyZDUx
+    OWFkZGNjOGFjN2JjNTZlZWQzMDVlZWMzMDM2YjEzN2Y4MmVkODgyMDUxM2E3
+    NzkyOTdhYWQ0OTRjNGNlMDA0YzYyNGUwOWY4NTcwNTI1ZGUyZmM=
   data.tar.gz: !binary |-
-    Mjc1MjMwMjAwN2JiYjNiYzQzZmY1YWRkZGYwOTllZjNhYmE2OWRkYmE5OTZl
-    M2YxNmE5MTk1MGM4Mzg5YzZjMGY3ZjQ5NmE3MTI0YzI2YTkyZWNkYzgzYWY3
-    MzQ5NWUwZjk5NGQ1Y2VlMThjYmJjZTdlZGYzMTI4MGQ4ZDQyNDE=
+    NDEwNGY0NDg5MjdiYWIxMDZhZDhmMGRlZGMzYmE4NzM5OGYzZjhmZjBiOWE0
+    NDY1Mzg2NjU0MWQ1M2JkY2Q3NjE4ZTIxNDZkOWU0YWE4N2Q1OTQ0ZjlkN2Qz
+    MTc1NjgzMTQ1NjJjNWFmMDUyMmQ3YzNmNzQ5MjY2MWFmMGY2ZjE=

data/Gemfile.lock

@@ -1,9 +1,8 @@
 PATH
   remote: .
   specs:
-    revs-utils (1.0.21)
-      actionpack (~> 3)
-      chronic
+    revs-utils (2.0.0)
+      actionpack (~> 4.1.6)
       countries (= 0.9.2)
       rdf
 
@@ -11,63 +10,55 @@ GEM
   remote: http://rubygems.org/
   remote: http://sul-gems.stanford.edu/
   specs:
-    actionpack (3.2.22)
-      activemodel (= 3.2.22)
-      activesupport (= 3.2.22)
-      builder (~> 3.0.0)
+    actionpack (4.1.6)
+      actionview (= 4.1.6)
+      activesupport (= 4.1.6)
+      rack (~> 1.5.2)
+      rack-test (~> 0.6.2)
+    actionview (4.1.6)
+      activesupport (= 4.1.6)
+      builder (~> 3.1)
       erubis (~> 2.7.0)
-      journey (~> 1.0.4)
-      rack (~> 1.4.5)
-      rack-cache (~> 1.2)
-      rack-test (~> 0.6.1)
-      sprockets (~> 2.2.1)
-    activemodel (3.2.22)
-      activesupport (= 3.2.22)
-      builder (~> 3.0.0)
-    activesupport (3.2.22)
-      i18n (~> 0.6, >= 0.6.4)
-      multi_json (~> 1.0)
-    builder (3.0.4)
-    chronic (0.10.2)
+    activesupport (4.1.6)
+      i18n (~> 0.6, >= 0.6.9)
+      json (~> 1.7, >= 1.7.7)
+      minitest (~> 5.1)
+      thread_safe (~> 0.1)
+      tzinfo (~> 1.1)
+    builder (3.2.2)
     countries (0.9.2)
       currencies (>= 0.4.0)
     currencies (0.4.2)
-    diff-lcs (1.2.4)
+    diff-lcs (1.2.5)
     erubis (2.7.0)
-    hike (1.2.3)
-    i18n (0.7.0)
-    journey (1.0.4)
-    link_header (0.0.8)
+    i18n (0.6.11)
+    json (1.8.1)
     lyberteam-gems-devel (1.0.1)
       rake (>= 0.8.7)
       rest-client
-    mime-types (2.0)
-    multi_json (1.11.2)
-    rack (1.4.7)
-    rack-cache (1.2)
-      rack (>= 0.4)
-    rack-test (0.6.3)
+    mime-types (2.3)
+    minitest (5.4.1)
+    netrc (0.7.7)
+    rack (1.5.2)
+    rack-test (0.6.2)
       rack (>= 1.0)
-    rake (10.1.0)
-    rdf (1.1.15)
-      link_header (~> 0.0, >= 0.0.8)
-    rest-client (1.6.7)
-      mime-types (>= 1.16)
-    rspec (2.14.1)
-      rspec-core (~> 2.14.0)
-      rspec-expectations (~> 2.14.0)
-      rspec-mocks (~> 2.14.0)
-    rspec-core (2.14.7)
-    rspec-expectations (2.14.3)
+    rake (10.3.2)
+    rdf (1.1.6)
+    rest-client (1.7.2)
+      mime-types (>= 1.16, < 3.0)
+      netrc (~> 0.7)
+    rspec (2.99.0)
+      rspec-core (~> 2.99.0)
+      rspec-expectations (~> 2.99.0)
+      rspec-mocks (~> 2.99.0)
+    rspec-core (2.99.2)
+    rspec-expectations (2.99.2)
       diff-lcs (>= 1.1.3, < 2.0)
-    rspec-mocks (2.14.4)
-    sprockets (2.2.3)
-      hike (~> 1.2)
-      multi_json (~> 1.0)
-      rack (~> 1.0)
-      tilt (~> 1.1, != 1.3.0)
-    tilt (1.4.1)
-    yard (0.8.7.3)
+    rspec-mocks (2.99.2)
+    thread_safe (0.3.4)
+    tzinfo (1.2.2)
+      thread_safe (~> 0.1)
+    yard (0.8.7.4)
 
 PLATFORMS
   ruby

data/README.rdoc

@@ -18,17 +18,11 @@ Shared methods and functions used by revs-indexer, pre-assembly and bulk metadat
 - <b>1.0.6</b> Add some more conditions to CSV header checks
 - <b>1.0.7</b> Label column needs to be there but does not need to have a value to register
 - <b>1.0.8</b> Update clean_collection_name method to deal with other possible names
-- <b>1.0.9</b> Add more common format corrections
-- <b>1.0.10</b> Update valid for metadata method so it is not sensitive to blank or uppercase columns
-- <b>1.0.11</b> Fix issues with year parsing
-- <b>1.0.12</b> Allow two digit years in year formatting
-- <b>1.0.19</b> Display output showing reasons for validation failures when checking manifests
-- <b>1.0.20</b> Allow for optional metadata columns in the manifest
-- <b>1.0.21</b> Add more information when sourceIDs are not unique
+- <b>2.0.0</b> Updating to use ActionPack 4 for Rails 4 applications.  For Rails 3, continue to use 1.x.y releases.  
 
 == Running tests
 
-bundle exec rspec spec
+./bin/run_all_tests
 
 == Release the gem to the gemserver
 
@@ -42,7 +36,7 @@ gem build revs-utils.gemspec
 
 6. Release the gem to RubyGems:
 
-gem push revs-utils-1.0.9.gem  # substitute actual version number
+gem push revs-utils-1.0.8.gem  # substitute actual version number
 
 == Installation
 

data/config/manifest_headers.yml

@@ -30,18 +30,5 @@ metadata:
   hide: hide
   format: format
   collection_name: collection_name
-metadata_optional:
-  format_authority: format_authority
-known_formats: 
-  - black-and-white film
-  - color film
-  - slides
-  - foldouts
-  - pamphlets
-  - oversize items
-  - photographic prints
-  - black-and-white negatives
-  - color negatives
-  - black-and-white transparencies
-  - color transparencies
-  - Glass negatives
+  
+  

data/lib/revs-utils/version.rb

@@ -1,5 +1,5 @@
 module Revs
   module Utils
-    VERSION = "1.0.21"
+    VERSION = "2.0.0"
   end
 end

data/lib/revs-utils.rb

@@ -5,7 +5,6 @@ require "countries"
 require 'active_support/core_ext/string'
 require 'active_support/core_ext/hash'
 require 'csv'
-require 'chronic'
 
 PROJECT_ROOT = File.expand_path(File.dirname(__FILE__) + '/..')
 
@@ -14,8 +13,7 @@ REVS_LC_TERMS_FILENAME=File.join(PROJECT_ROOT,'files','revs-lc-marque-terms.obj'
 REVS_MANIFEST_HEADERS_FILEPATH = File.join(PROJECT_ROOT,'config',"manifest_headers.yml")
 REGISTER = "register"
 METADATA = "metadata"
-OPTIONAL = "metadata_optional"
-FORMATS = "known_formats"
+
 
 module Revs
   module Utils
@@ -24,14 +22,11 @@ module Revs
       # a hash of LC Subject Heading terms and their IDs for linking for "Automobiles" http://id.loc.gov/authorities/subjects/sh85010201.html
       # this is cached and loaded from disk and deserialized back into a hash for performance reasons, then stored as a module
       # level constant so it can be reused throughout the pre-assembly run as a constant
-      #  This cached set of terms can be re-generated with "ruby bin/revs_lc_automobile_terms.rb"
+      #  This cached set of terms can be re-generated with "ruby devel/revs_lc_automobile_terms.rb"
       AUTOMOBILE_LC_TERMS= File.open(REVS_LC_TERMS_FILENAME,'rb'){|io| Marshal.load(io)} if File.exists?(REVS_LC_TERMS_FILENAME)
       REVS_MANIFEST_HEADERS_FILE = File.open(REVS_MANIFEST_HEADERS_FILEPATH)
       REVS_MANIFEST_HEADERS = YAML.load( REVS_MANIFEST_HEADERS_FILE)
       
-      def revs_known_formats
-        get_manifest_section(FORMATS)
-      end
       
       def get_manifest_section(section)
         return REVS_MANIFEST_HEADERS[section]
@@ -71,98 +66,50 @@ module Revs
         sources = Array.new
         files.each do |file|
           file.each do |row|
-            #Make sure the sourceid and filename are the same
+            #Make sure the sourcid and filename are the same
             fname = row[get_manifest_section(REGISTER)['filename']].chomp(File.extname(row[get_manifest_section(REGISTER)['filename']]))
-            return false if ((row[get_manifest_section(REGISTER)['sourceid']] != fname) || ((/\s/ =~ row[get_manifest_section(REGISTER)['sourceid']].strip) != nil))  
+            return false if row[get_manifest_section(REGISTER)['sourceid']] != fname
             sources << row[get_manifest_section(REGISTER)['sourceid']]
-          end         
+          end
+          
+          
+         
         end
         return sources.uniq.size == sources.size
       
       end
-            
+      
+      
       #Pass this function a CSV file and it will return true if the proper headers are there and each entry has the required fields filled in
       def valid_to_register(file_path)
+        
         file = read_csv_with_headers(file_path)
-        return check_valid_to_register(file)
-      end
-      
-      #Pass this function a CSV file and it will return true if the proper headers are there and each entry has the required fields filled in.  
-      def valid_for_metadata(file_path)
-        file = read_csv_with_headers(file_path)
-        return check_headers(file)
-      end
-      
-      # pass in csv data and it will tell if you everything is safe to register based on having labels, unique sourceIDs and filenames matching sourceIDs
-      def check_valid_to_register(csv_data)
         #Make sure all the required headers are there
-        result1=result2=result3=result4=true
-        if not get_manifest_section(REGISTER).values-csv_data[0].keys == []
-          puts "missing headers required for registration"
-          result1=false
-        end
-        sources=Array.new
+        return false if not get_manifest_section(REGISTER).values-file[0].keys == []
+        
         #Make sure all files have entries for those required headers
-        csv_data.each do |row|
+        file.each do |row|
           get_manifest_section(REGISTER).keys.each do |header| # label should be there as a column but does not always need a value
-             if header.downcase !='label' && row[header].blank? 
-               puts "#{row[get_manifest_section(REGISTER)['sourceid']]} does not have a value for a required registration field"
-               result2=false
-             end
-          end
-          fname = row[get_manifest_section(REGISTER)['filename']].chomp(File.extname(row[get_manifest_section(REGISTER)['filename']]))
-          if ((row[get_manifest_section(REGISTER)['sourceid']] != fname) || ((/\s/ =~ row[get_manifest_section(REGISTER)['sourceid']].strip) != nil))  
-            puts "#{row[get_manifest_section(REGISTER)['sourceid']]} does not match the filename or has a space in it"            
-            result3=false
+            return false if header.downcase !='label' && row[header].blank? #Alternatively consider row[header].class != String or row[header].size <= 0
           end
-          sources << row[get_manifest_section(REGISTER)['sourceid']]
-        end
-        result4 = (sources.uniq.size == sources.size)
-        unless result4
-          puts "sourceIDs are not all unique" 
-          puts sources.uniq.map { | e | [sources.count(e), e] }.select { | c, _ | c > 1 }.sort.reverse.map { | c, e | "#{e}: #{c}" } # show all non-unique sourceIDs and their frequency
         end
-        return (result1 && result2 && result3 && result4)
-        
+       return true
       end
       
-      # looks at certain metadata fields in manifest to confirm validity (such as dates and formats)
-      def check_metadata(csv_data)
-        bad_rows=0
-        csv_data.each do |row|
-          valid_date=revs_is_valid_datestring?(row[get_manifest_section(METADATA)['year']] || row[get_manifest_section(METADATA)['date']])
-          valid_format=revs_is_valid_format?(row[get_manifest_section(METADATA)['format']])
-          unless (valid_date && valid_format)
-            bad_rows+=1 
-            puts "#{row[get_manifest_section(REGISTER)['sourceid']]} has a bad year/date or format"
-          end
-        end
-        return bad_rows
-      end
-      
-      # pass in csv data from a file read in and it will tell you if the headers are valid
-      def check_headers(csv_data)
-        
-        result1=result2=true
-        file_headers=csv_data[0].keys.reject(&:blank?).collect(&:downcase)
+      #Pass this function a CSV file and it will return true if the proper headers are there and each entry has the required fields filled in.  
+      def valid_for_metadata(file_path)
+        file = read_csv_with_headers(file_path)
+        file_headers=file[0].keys
         #The file doesn't need to have all the metadata values, it just can't have headers that aren't used for metadata or registration
         if file_headers.include?('date') && file_headers.include?('year') # can't have both date and year 
-          puts "has both year and date columns"
-          result1=false
-        end
-        if file_headers.include?('location') && file_headers.include?('state') && file_headers.include?('city') && file_headers.include?('country') # can't have both location and the specific fields
-          puts "has location column as well as specific state,city,country columns"
-          result2=false
+          return false
+        elsif file_headers.include?('location') && file_headers.include?('state') && file_headers.include?('city') && file_headers.include?('country') # can't have both location and the specific fields
+          return false
+        else
+          return file_headers-get_manifest_section(METADATA).values-get_manifest_section(REGISTER).values == []
         end
-        extra_columns = file_headers-get_manifest_section(METADATA).values-get_manifest_section(REGISTER).values-get_manifest_section(OPTIONAL).values
-        has_extra_columns = (extra_columns == [])
-        puts "has unknown columns: #{extra_columns.join(', ')}" unless has_extra_columns
-        result3 = has_extra_columns
-        
-        return (result1 && result2 && result3)
-        
       end
-      
+
       def clean_collection_name(name)
         return "" if name.blank? || name.nil?
         name=name.to_s
@@ -199,32 +146,19 @@ module Revs
         return row
       end
 
-      # checks to see if we have a valid format
-      def revs_is_valid_format?(format)
-        return true if format.nil? || format.blank?
-        formats=format.split("|").collect{|f| f.strip}
-        !formats.collect {|f| revs_known_formats.include?(f)}.uniq.include?(false)
-      end
-      
-      # check a single format and fix some common issues
       def revs_check_format(format)
         return revs_check_formats([format]).first
       end
       
-      # check the incoming array of formats and fix some common issues
+      # check the incoming format and fix some common issues
       def revs_check_formats(format)
         known_fixes = {"black-and-white negative"=>"black-and-white negatives",
                        "color negative"=>"color negatives",
                        "slides/color transparency"=>"color transparencies",
                        "color negatives/slides"=>"color negatives",
                        "black-and-white negative strips"=>"black-and-white negatives",
-                       "black and white"=>"black-and-white negatives",
-                       "black-and-white"=>"black-and-white negatives",                       
-                       "black and white negative"=>"black-and-white negatives",
-                       "black and white negatives"=>"black-and-white negatives",
                        "color transparency"=>"color transparencies",
-                       "slide"=>"slides",
-                       "color transparancies"=>"color transparencies"
+                       "slide"=>"slides"
                      }
         count = 0 
         format.each do |f|
@@ -297,21 +231,11 @@ module Revs
         date_string.to_s.strip.scan(/\D/).empty? and (starting_year..Date.today.year).include?(date_string.to_i)
       end
 
-      # tell us if the incoming datestring supplied in the manifest column is a valid date, year or list of years
-      def revs_is_valid_datestring?(date_string)
-        return true if date_string.nil? || date_string.empty?
-        is_full_date=(get_full_date(date_string) != false)
-        is_year=!parse_years(date_string).empty?
-        return is_year || is_full_date
-      end
-      
-      # tell us if the string passed is in is a full date of the format M/D/YYYY or m-d-yyyy or m-d-yy or M/D/YY, and returns the date object if it is valid
+      # tell us if the string passed is in is a full date of the format M/D/YYYY, and returns the date object if it is valid
       def get_full_date(date_string)
         begin
-          return false if date_string.scan(/(-|\/)/).count < 2 # we need at least two / or - characters to count as a full date
-          date_obj=Chronic.parse(date_string).to_date
-          date_obj=date_obj.prev_year(100) if date_obj > Date.today # if the parsing yields a date in the future, this is a problem, so adjust back a century (due to this issue: http://stackoverflow.com/questions/27058068/ruby-incorrectly-parses-2-digit-year)
-          is_valid_year?(date_obj.year.to_s) ? date_obj : false
+          date_obj=Date.strptime(date_string.gsub('-','/').delete(' '), '%m/%d/%Y')
+          return (is_valid_year?(date_obj.year.to_s) ? date_obj : false)
         rescue
           false
         end
@@ -329,14 +253,14 @@ module Revs
         years_to_add=[]
         result.each do |year|
 
-          if year.scan(/[1-2][0-9][0-9][0-9][-][0-9][0-9]/).size > 0 && year.size == 7 # if we have a year that looks like "1961-62" or "1961-73", lets deal with it turning it into [1961,1962] or [1961,1962,1963,1964,1965,1966,1967...etc]
+          if year.scan(/[1-2][0-9][0-9][0-9][-][0-9][0-9]/).size > 0 # if we have a year that looks like "1961-62" or "1961-73", lets deal with it turning it into [1961,1962] or [1961,1962,1963,1964,1965,1966,1967...etc]
             start_year=year[2..3]
             end_year=year[5..6]
             stem=year[0..1] 
             for n in start_year..end_year
               years_to_add << "#{stem}#{n}"
             end
-          elsif year.scan(/[1-2][0-9][0-9][0-9][-][1-9]/).size > 0 && year.size == 6 # if we have a year that lloks like "1961-2" or "1961-3", lets deal with it turning it into [1961,1962] or [1961,1962,1963]
+          elsif year.scan(/[1-2][0-9][0-9][0-9][-][1-9]/).size > 0 # if we have a year that lloks like "1961-2" or "1961-3", lets deal with it turning it into [1961,1962] or [1961,1962,1963]
             start_year=year[3..3]
             end_year=year[5..5]
             stem=year[0..2]
@@ -351,7 +275,7 @@ module Revs
             %w{0 1 2 3 4 5 6 7 8 9}.each {|n| years_to_add << "#{stem}#{n}"} # add each year in that decade to the output array
           end
 
-          if year.scan(/[1-2][0-9][0-9][0-9][-][1-2][0-9][0-9][0-9]/).size > 0 && year.size == 9 # if we have a year that lloks like "1961-1962" or "1930-1955", lets deal with it turning it into [1961,1962] or [1961,1962,1963]
+          if year.scan(/[1-2][0-9][0-9][0-9][-][1-2][0-9][0-9][0-9]/).size > 0 # if we have a year that lloks like "1961-1962" or "1930-1955", lets deal with it turning it into [1961,1962] or [1961,1962,1963]
             start_year=year[0..3]
             end_year=year[5..8]
             if end_year.to_i - start_year.to_i < 10 # let's only do the expansion if we don't have some really large date range, like "1930-1985" .. only ranges less than 9 years will be split into separate years

data/revs-utils.gemspec

@@ -11,8 +11,7 @@ Gem::Specification.new do |gem|
   gem.description   = "Shared methods and functions used by revs-indexer, pre-assembly and bulk metadata loading code."
   gem.summary       = "Shared methods and functions used by revs-indexer, pre-assembly and bulk metadata loading code."
   gem.homepage      = ""
-  gem.license       = "All rights reserved, Stanford University."
-  
+
   gem.files         = `git ls-files`.split($/)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
@@ -20,8 +19,7 @@ Gem::Specification.new do |gem|
   
   gem.add_dependency "countries", "0.9.2"
   gem.add_dependency "rdf"
-  gem.add_dependency "actionpack", '~> 3'
-  gem.add_dependency "chronic"
+  gem.add_dependency "actionpack", '~> 4.1.6'
   
   gem.add_development_dependency "rspec", "~> 2.6"
   gem.add_development_dependency "lyberteam-gems-devel", "> 1.0.0"

data/spec/revs-utils_spec.rb

@@ -62,7 +62,6 @@ describe "Revs-Utils" do
    
    it "should clean up some common format errors from an array" do 
      @revs.revs_check_formats(['black-and-white negative','color negative','leave alone']).should == ['black-and-white negatives','color negatives','leave alone']
-     @revs.revs_check_formats(['black and white','color negative','black-and-white negative']).should == ['black-and-white negatives','color negatives','black-and-white negatives']
    end
 
    it "should clean up some common format errors from a string" do 
@@ -76,30 +75,10 @@ describe "Revs-Utils" do
    end
       
    it "should indicate if a date is valid" do
-     
-     # formats that are ok
+     @revs.get_full_date('bogus').should be_false
      @revs.get_full_date('5/1/1959').should == Date.strptime("5/1/1959", '%m/%d/%Y')
      @revs.get_full_date('5-1-1959').should == Date.strptime("5/1/1959", '%m/%d/%Y')
-     @revs.get_full_date('5-1-2014').should == Date.strptime("5/1/2014", '%m/%d/%Y')
-     @revs.get_full_date('5-1-59').should == Date.strptime("5/1/1959", '%m/%d/%Y') 
-     @revs.get_full_date('1/1/71').should == Date.strptime("1/1/1971", '%m/%d/%Y') 
-     @revs.get_full_date('5-1-14').should == Date.strptime("5/1/2014", '%m/%d/%Y')     
-     @revs.get_full_date('5-1-21').should == Date.strptime("5/1/1921", '%m/%d/%Y')     
-     @revs.get_full_date('1966-02-27').should == Date.strptime("2/27/1966", '%m/%d/%Y')  
-     @revs.get_full_date('1966-2-5').should == Date.strptime("2/5/1966", '%m/%d/%Y')  
-     
-     # bad full dates
-     @revs.get_full_date('1966-14-11').should be_false # bad month
-     @revs.get_full_date('1966\4\11').should be_false # slashes are the wrong way
-     @revs.get_full_date('bogus').should be_false # crap string
-     @revs.get_full_date('').should be_false # blank
-     @revs.get_full_date('1965').should be_false # only the year
-     @revs.get_full_date('1965-68').should be_false # range of years
-     @revs.get_full_date('1965,1968').should be_false # multiple years
-     @revs.get_full_date('1965|1968').should be_false # multiple years
-     @revs.get_full_date('1965-1968').should be_false # multiple years
-     @revs.get_full_date('1965-8').should be_false # multiple years
-
+     @revs.get_full_date('5-1-59').should be_false # two digit year is not allowed
    end
 
    it "should indicate if we have a valid year" do
@@ -108,29 +87,7 @@ describe "Revs-Utils" do
      @revs.is_valid_year?('1700').should be_false # too old! no cars even existed yet
      @revs.is_valid_year?('1700',1600).should be_true # unless we allow it to be ok
   end
-
-  it "should indicate if we have unknown formats" do
-    @revs.revs_is_valid_format?(nil).should be_true
-    @revs.revs_is_valid_format?('').should be_true    
-    @revs.revs_is_valid_format?('slides').should be_true
-    @revs.revs_is_valid_format?('slide').should be_false
-    @revs.revs_is_valid_format?('slides | slide').should be_false
-    @revs.revs_is_valid_format?('slides | black-and-white negatives').should be_true
-    @revs.revs_is_valid_format?('black-and-white-negatives').should be_false
-    @revs.revs_is_valid_format?('black-and-white negatives').should be_true   
-  end
-  
-  it "should indicate if we have a valid datestring" do
-    @revs.revs_is_valid_datestring?('1959').should be_true
-    @revs.revs_is_valid_datestring?('bogus').should be_false
-    @revs.revs_is_valid_datestring?('').should be_true
-    @revs.revs_is_valid_datestring?(nil).should be_true
-    @revs.revs_is_valid_datestring?([]).should be_true
-    @revs.revs_is_valid_datestring?('2/2/1950').should be_true
-    @revs.revs_is_valid_datestring?('2/31/1950').should be_false
-    @revs.revs_is_valid_datestring?('2/2/50').should be_true
-    @revs.revs_is_valid_datestring?('195x').should be_true
- end   
+   
    
    it "should lookup the country correctly" do
      @revs.revs_get_country('USA').should == "United States"
@@ -159,7 +116,6 @@ describe "Revs-Utils" do
   it "should parse 1950s correctly" do
     
     @revs.parse_years('1950s').should == ['1950','1951','1952','1953','1954','1955','1956','1957','1958','1959']    
-    @revs.parse_years("1950's").should == ['1950','1951','1952','1953','1954','1955','1956','1957','1958','1959']    
     
   end
 
@@ -181,12 +137,6 @@ describe "Revs-Utils" do
     
   end
 
-  it "should parse 1800-1802" do
-    
-    @revs.parse_years('1800-1802').should == ['1800','1801','1802']    
-    
-  end
-  
   it "should parse 1955-1957 | 1955 | 1955 and not produce duplicate years" do
     
     @revs.parse_years('1955-1957 | 1955 | 1955').should == ['1955','1956','1957']    
@@ -297,11 +247,7 @@ describe "Revs-Utils" do
     sheets = [Dir.pwd + "/spec/sample-csv-files/malformed-sourceid.csv"]
     @revs.unique_source_ids(sheets).should == false
   end
-
-  it "should return false when a sourceid has a space in it" do
-    sheets = [Dir.pwd + "/spec/sample-csv-files/space-sourceid.csv"]
-    @revs.unique_source_ids(sheets).should == false
-  end    
+    
   
  
 end

data/spec/sample-csv-files/clean-sheet.csv

@@ -1,4 +1,4 @@
-format,sourceid,collection_name,filename,year,photographer,label,marque,model,model_year,people,city,state,country,event,description,inst_notes,prod_notes,has_more_metadata,format_authority
+format,sourceid,collection_name,filename,year,photographer,label,marque,model,model_year,people,city,state,country,event,description,inst_notes,prod_notes,has_more_metadata
 black-and-white negatives,2004-100CRAI-b1_1.0_0001,Bruce R Craig Photograph Collection,2004-100CRAI-b1_1.0_0001.tif,,Bruce R Craig,Rutherford Special,Rutherford Special,,,"Rutherford, Slim",,,"full car (rear), #62",,,
 black-and-white negatives,2004-100CRAI-b1_1.0_0002,Bruce R Craig Photograph Collection,2004-100CRAI-b1_1.0_0002.tif,,Bruce R Craig,City of Roses,City of Roses,,,"Sezekendy, Charley",,,"full car, #2",,,
 black-and-white negatives,2004-100CRAI-b1_1.0_0003,Bruce R Craig Photograph Collection,2004-100CRAI-b1_1.0_0003.tif,,Ed Hitzwe,Wilburn | Morgan,,,,Wilburn | Morgan,,,"install tire on wheel, posed photo",,,

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: revs-utils
 version: !ruby/object:Gem::Version
-  version: 1.0.21
+  version: 2.0.0
 platform: ruby
 authors:
 - Peter Mangiafico
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-09-21 00:00:00.000000000 Z
+date: 2014-10-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: countries
@@ -44,28 +44,14 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '3'
+        version: 4.1.6
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '3'
-- !ruby/object:Gem::Dependency
-  name: chronic
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
+        version: 4.1.6
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -147,11 +133,9 @@ files:
 - spec/sample-csv-files/no-blank-label.csv
 - spec/sample-csv-files/no-label-column.csv
 - spec/sample-csv-files/no-sourceid.csv
-- spec/sample-csv-files/space-sourceid.csv
 - spec/spec_helper.rb
 homepage: ''
-licenses:
-- All rights reserved, Stanford University.
+licenses: []
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -169,7 +153,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.2
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Shared methods and functions used by revs-indexer, pre-assembly and bulk
@@ -187,6 +171,5 @@ test_files:
 - spec/sample-csv-files/no-blank-label.csv
 - spec/sample-csv-files/no-label-column.csv
 - spec/sample-csv-files/no-sourceid.csv
-- spec/sample-csv-files/space-sourceid.csv
 - spec/spec_helper.rb
 has_rdoc: 

data/spec/sample-csv-files/space-sourceid.csv

@@ -1,3 +0,0 @@
-format,sourceid,collection_name,filename,year,photographer,label,marque,model,model_year,people,location,event,description,inst_notes,prod_notes,has_more_metadata
-black-and-white negatives,2004-100CRAI-b1_1.0 _0001,Bruce R Craig Photograph Collection,2004-100CRAI-b1_1.0 _0001.tif,,Bruce R Craig,Rutherford Special,Rutherford Special,,,"Rutherford, Slim",,,"full car (rear), #62",,,
-black-and-white negatives,2004-100CRAI-b1_1.0_0002,Bruce R Craig Photograph Collection,2004-100CRAI-b1_1.0_0002.tif,,Bruce R Craig,City of Roses,City of Roses,,,"Sezekendy, Charley",,,"full car, #2",,,