csv-diff 0.3.0 → 0.3.1

data/lib/csv-diff/algorithm.rb

@@ -41,8 +41,31 @@ class CSVDiff
             include_deletes = !options[:ignore_deletes]
 
             diffs = Hash.new{ |h, k| h[k] = {} }
+
+            # First identify deletions
+            if include_deletes
+                (left_keys - right_keys).each do |key|
+                    # Delete
+                    key_vals = key.split('~', -1)
+                    parent = key_vals[0...parent_fields].join('~')
+                    left_parent = left_index[parent]
+                    left_value = left_values[key]
+                    left_idx = left_parent.index(key)
+                    next unless left_idx
+                    id = {}
+                    id[:row] = left_keys.index(key) + 1
+                    id[:sibling_position] = left_idx + 1
+                    key_fields.each do |field_name|
+                        id[field_name] = left_value[field_name]
+                    end
+                    diffs[key].merge!(id.merge(left_values[key].merge(:action => 'Delete')))
+                    #puts "Delete: #{key}"
+                end
+            end
+
+            # Now identify adds/updates
             right_keys.each_with_index do |key, right_row_id|
-                key_vals = key.split('~')
+                key_vals = key.split('~', -1)
                 parent = key_vals[0...parent_fields].join('~')
                 left_parent = left_index[parent]
                 right_parent = right_index[parent]
@@ -81,26 +104,6 @@ class CSVDiff
                 end
             end
 
-            # Now identify deletions
-            if include_deletes
-                (left_keys - right_keys).each do |key|
-                    # Delete
-                    key_vals = key.split('~')
-                    parent = key_vals[0...parent_fields].join('~')
-                    left_parent = left_index[parent]
-                    left_value = left_values[key]
-                    left_idx = left_parent.index(key)
-                    next unless left_idx
-                    id = {}
-                    id[:row] = left_keys.index(key) + 1
-                    id[:sibling_position] = left_idx + 1
-                    key_fields.each do |field_name|
-                        id[field_name] = left_value[field_name]
-                    end
-                    diffs[key].merge!(id.merge(left_values[key].merge(:action => 'Delete')))
-                    #puts "Delete: #{key}"
-                end
-            end
             diffs
         end
 

data/lib/csv-diff/csv_diff.rb

@@ -95,8 +95,8 @@ class CSVDiff
     # Performs a diff with the specified +options+.
     def diff(options = {})
         @summary = nil
-        @diffs = diff_sources(@left, @right, @key_fields, @diff_fields, options)
         @options = options
+        @diffs = diff_sources(@left, @right, @key_fields, @diff_fields, options)
     end
 
 
@@ -138,20 +138,22 @@ class CSVDiff
     # Given two sets of field names, determines the common set of fields present
     # in both, on which members can be diffed.
     def get_diff_fields(left_fields, right_fields, options)
-        ignore_fields = (options[:ignore_fields] || []).map do |f|
-            f.is_a?(Fixnum) ? right_fields[f] : f
+        ignore_fields = options.fetch(:ignore_fields, [])
+        ignore_fields = [ignore_fields] unless ignore_fields.is_a?(Array)
+        ignore_fields.map! do |f|
+            (f.is_a?(Fixnum) ? right_fields[f] : f).upcase
         end
         diff_fields = []
         if options[:diff_common_fields_only]
             right_fields.each_with_index do |fld, i|
                 if left_fields.include?(fld)
-                    diff_fields << fld unless ignore_fields.include?(fld)
+                    diff_fields << fld unless ignore_fields.include?(fld.upcase)
                 else
                     @warnings << "Field '#{fld}' is missing from the left (from) file, and won't be diffed"
                 end
             end
         else
-            diff_fields = (right_fields + left_fields).uniq.reject{ |fld| ignore_fields.include?(fld) }
+            diff_fields = (right_fields + left_fields).uniq.reject{ |fld| ignore_fields.include?(fld.upcase) }
         end
         diff_fields
     end

data/lib/csv-diff/csv_source.rb

@@ -22,6 +22,9 @@ class CSVDiff
         #   values.
         attr_reader :case_sensitive
         alias_method :case_sensitive?, :case_sensitive
+        # @return [Boolean] True if leading/trailing whitespace should be stripped
+        #   from fields
+        attr_reader :trim_whitespace
         # @return [Hash<String,Hash>] A hash containing each line of the source,
         #   keyed on the values of the +key_fields+.
         attr_reader :lines
@@ -113,6 +116,7 @@ class CSVDiff
             @index = Hash.new{ |h, k| h[k] = [] }
             @key_fields = find_field_indexes(@key_fields, @field_names) if @field_names
             @case_sensitive = options.fetch(:case_sensitive, true)
+            @trim_whitespace = options.fetch(:trim_whitespace, false)
             line_num = 0
             lines.each do |row|
                 line_num += 1
@@ -126,6 +130,7 @@ class CSVDiff
                 line = {}
                 @field_names.each_with_index do |field, i|
                     line[field] = field_vals[i]
+                    line[field].strip! if @trim_whitespace && line[field]
                 end
                 key_values = @key_fields.map{ |kf| field_vals[kf].to_s.upcase }
                 key = key_values.join('~')

metadata

@@ -1,14 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: csv-diff
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
+  prerelease: 
 platform: ruby
 authors:
 - Adam Gardiner
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-08-14 00:00:00.000000000 Z
+date: 2016-01-26 00:00:00.000000000 Z
 dependencies: []
 description: ! "        This library performs diffs of CSV files.\n\n        Unlike
   a standard diff that compares line by line, and is sensitive to the\n        ordering
@@ -34,34 +35,35 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- LICENSE
 - README.md
-- lib/csv-diff.rb
+- LICENSE
 - lib/csv-diff/algorithm.rb
 - lib/csv-diff/csv_diff.rb
 - lib/csv-diff/csv_source.rb
+- lib/csv-diff.rb
 - lib/csv_diff.rb
 homepage: https://github.com/agardiner/csv-diff
 licenses: []
-metadata: {}
 post_install_message: For command-line tools and diff reports, 'gem install csv-diff-report'
 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: 2.4.1
+rubygems_version: 1.8.21
 signing_key: 
-specification_version: 4
+specification_version: 3
 summary: CSV Diff is a library for generating diffs from data in CSV format
 test_files: []

checksums.yaml

@@ -1,15 +0,0 @@
----
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    MzM3MmMzNzU5ZDE5ZTA5MGI4OGQxNTBkMTE0NWM1MzYzNDVkYTFjYQ==
-  data.tar.gz: !binary |-
-    MDQ3Yzk3ZDc4ZTZiNTMwMzc1NGMxMTU5ZTBkMzdjMTMyNzE5OTYwMg==
-SHA512:
-  metadata.gz: !binary |-
-    YTYxMDM1MjUxNDk3ZjE3YWUxZWJjNGFmMzQzMDUyNGJlOGUzMmI2MDVlNjg4
-    OWJiYmQxNTI2MjBlMmQzNGFkZTk0ZGY1Y2I0ZDBkODljYjc4NDQ1ZDY1ODky
-    ZDU4MDUwZjVjYWU0MTE5NTExMmExYTM0NTY1ZGMzYzc5NDkxYmE=
-  data.tar.gz: !binary |-
-    YzU4YWM2MmZjMjE4MjlhZDgxN2IxNmI1NmU2YjFiZTcwN2ZlNTZlYzE5MzZm
-    NGJkZDNkODUzNGNlNjA2NGZlZWIyMWFmMjljOTQyNjE3OGU4YWFmY2UyZWE2
-    YzhlZmI0YTcxMGY3N2Y2ODQ5NTM3ODcyMTUzOTJkODhjNjY0YWM=