spout 0.6.0.beta1 → 0.6.0.beta2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7a6e21bcb87ee2582bbe4e201dbcb42b65e11259
-  data.tar.gz: 86edbf1fff97458cb2eb30d06b7d0b96f4e4226d
+  metadata.gz: f4ae8ef2362ef67fc7cb4cb86560fabee408ef7b
+  data.tar.gz: aa825b0f03d9def1e26e784c09eb205424896258
 SHA512:
-  metadata.gz: 74e71e9826b2b38a4090be8e8dba01ce504f8674f993a0403c858ddce35bfec8449989ff701503d19e3c8e882e4728ffe9f80fc59e3cbdbffa02016ee38672cc
-  data.tar.gz: 6664b2fa054288630ec72d6ee4def325ef0bce008cec0d7a235fc8e80af047b532494d9370a418d70a682e83bb6fa341355f63eee9e6970649f984a288b8f4b0
+  metadata.gz: 815ae970ecfdf3ba9db2aa6f2095eff92608df08312e7903fdaf23e15243aca4a842147ada5031faa7fee594646b6f9632b0bfa1be87de408f7e41fe32d45562
+  data.tar.gz: 1b55348b328af02eee3e2ee189f88778584f09cc1a82eff5160d4258c8bdf78646facb23c3dd2baa515897260ed223cb2a6d4ec9dce49c1ba23af178051210c3

data/lib/spout/actions.rb

@@ -19,7 +19,7 @@ module Spout
         new_data_dictionary_export(argv)
       when 'hybrid', '-hybrid', '--hybrid', 'y', 'hy', '-y', '-hy'
         new_data_dictionary_export(argv, 'hybrid')
-      when 'dataset', '-dataset', '--dataset', 'd', '-d', 'match', '-match', '--match', 'm', '-m'
+      when 'dataset', '-dataset', '--dataset', 'd', '-d', 'match', '-match', '--match', 'm', '-m', 'coverage', '-coverage', '--coverage', 'c', '-c'
         match_dataset_report(argv)
       else
         help

data/lib/spout/tasks/engine.rake

@@ -46,41 +46,56 @@ namespace :dd do
 
   desc 'Match CSV dataset with JSON repository'
   task :coverage do
-    puts 'MDR'
-    puts Dir.pwd
     puts csvs = Dir.glob("dd/csvs/*.csv")
 
-    @all_column_headers = []
+    all_column_headers = []
 
-    @variable_json_ids = []
-    @variable_file_names = []
+    variable_json_ids = []
+    variable_file_names = []
 
     Dir.glob("variables/**/*.json").each do |file|
       if json = JSON.parse(File.read(file)) rescue false
-        @variable_json_ids << json['id']
+        variable_json_ids << json['id']
       end
-      @variable_file_names << file.split('/').last.to_s.split('.json').first.to_s
+      variable_file_names << file.split('/').last.to_s.split('.json').first.to_s
     end
 
     csvs.each do |csv_file|
+      csv_name = csv_file.split('/').last.to_s
       column_headers = []
 
       CSV.parse( File.open(csv_file, 'r:iso-8859-1:utf-8'){|f| f.read} ) do |line|
-        column_headers = line
+        column_headers = line.collect{|l| [csv_name, l.to_s.downcase]}
         break # Only read first line
       end
 
-      column_headers.each do |column_header|
+      all_column_headers += column_headers
+    end
 
-      end
 
-      @all_column_headers += column_headers
+    all_column_headers
+
+    @matching_results = []
+
+    all_column_headers.each do |csv, column|
+      file_name_test = variable_file_names.include?(column)
+      json_id_test = variable_json_ids.include?(column)
+      # SpoutCoverageResult
+      @matching_results << [ csv, column, file_name_test, json_id_test ]
     end
 
+    @matching_results.sort!{|a,b| [(a[2] && a[3] ? 1 : 0), a[0].to_s, a[1].to_s] <=> [(b[2] && b[3] ? 1 : 0), b[0].to_s, b[1].to_s]}
+
+    @coverage_results = []
+
+    csvs.each do |csv_file|
+      csv_name = csv_file.split('/').last.to_s
 
-    @all_column_headers
+      total_column_count = @matching_results.select{|mr| mr[0] == csv_name}.count
+      mapped_column_count = @matching_results.select{|mr| mr[0] == csv_name and mr[2] and mr[3]}.count
 
-    # puts File.join(File.dirname(__FILE__), '../views/', "")
+      @coverage_results << [ csv_name, total_column_count, mapped_column_count ]
+    end
 
     coverage_file = File.join(Dir.pwd, 'dd', 'index.html')
 
@@ -93,7 +108,6 @@ namespace :dd do
     open_command = 'open'  if RUBY_PLATFORM.match(/darwin/) != nil
     open_command = 'start' if RUBY_PLATFORM.match(/mingw/) != nil
 
-
     system "#{open_command} #{coverage_file}" if ['start', 'open'].include?(open_command)
     puts coverage_file
   end
@@ -235,3 +249,12 @@ end
 def additional_csv_info
   "\n\nFor additional information on specifying CSV column headers before import see:\n\n    " + "https://github.com/sleepepi/spout#generate-a-new-repository-from-an-existing-csv-file".colorize( :light_cyan ) + "\n\n"
 end
+
+
+# class SpoutCoverageResult
+#   attr_accessor :error, :error_message
+
+#   def errored?
+#     error == true
+#   end
+# end

data/lib/spout/version.rb

@@ -3,7 +3,7 @@ module Spout
     MAJOR = 0
     MINOR = 6
     TINY = 0
-    BUILD = "beta1" # nil, "pre", "rc", "rc2"
+    BUILD = "beta2" # nil, "pre", "rc", "rc2"
 
     STRING = [MAJOR, MINOR, TINY, BUILD].compact.join('.')
   end

data/lib/spout/views/index.html.erb

@@ -38,27 +38,56 @@ body {
 
     <div class="container" style="padding-top:50px">
 
+      <table class="table">
+        <thead>
+          <tr>
+            <th>CSV</th>
+            <th>Coverage</th>
+            <th>Columns</th>
+            <th>Columns Missed</th>
+          </tr>
+        </thead>
+        <tbody>
+          <% @coverage_results.each do |csv, total_column_count, mapped_column_count| %>
+            <tr>
+              <td><%= csv %></td>
+              <td>
+                <% if total_column_count.to_i > 0 %>
+                  <%= "%0.02f %" % (mapped_column_count * 100.0 / total_column_count) %>
+                <% else %>
+                  <span class="text-muted">---</span>
+                <% end %>
+              </td>
+              <td><%= total_column_count %></td>
+              <td><%= total_column_count - mapped_column_count %> </td>
+            </tr>
+          <% end %>
+        </tbody>
+      </table>
+
       <table class="table table-bordered table-hover">
         <thead>
           <tr>
+            <th>CSV</th>
             <th>Dataset Column Header</th>
             <th>JSON File</th>
             <th>Found in Data Dictionary</th>
           </tr>
         </thead>
         <tbody>
-          <% @all_column_headers.each do |column| %>
+          <% @matching_results.each do |csv, column, file_name_test, json_id_test| %>
             <tr>
+              <td><code><%= csv %></code></td>
               <td><%= column %></td>
               <td>
-                <% if @variable_file_names.include?(column) %>
+                <% if file_name_test %>
                   <span class="text-success">File Found</span>
                 <% else %>
                   <span class="text-danger">No JSON File Found, expecting: <code><%= column %>.json</code></span>
                 <% end %>
               </td>
               <td>
-                <% if @variable_json_ids.include?(column) %>
+                <% if json_id_test %>
                   <span class="text-success">JSON ID Found</span>
                 <% else %>
                   <span class="text-danger">No Matching JSON ID</span>

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: spout
 version: !ruby/object:Gem::Version
-  version: 0.6.0.beta1
+  version: 0.6.0.beta2
 platform: ruby
 authors:
 - Remo Mueller