csv-diff 0.1 → 0.2

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    ZGY3NTBiZGFiNTQxMmZiZmMwOTE2MDIzYmEwNWQ3NTY0MzZmNjRkMg==
+  data.tar.gz: !binary |-
+    NzAyNTY1OTk3MTA3Y2ZhNjk2YWRmNTJkYTljNGZhZDY2YjQ1OTg2ZQ==
+SHA512:
+  metadata.gz: !binary |-
+    ZDRmODg2NDlhYTY4NDM1MWYxNjgyZGQ0MGRiZDNkYmI3MDkwYjFkZWVhOWYw
+    YmVkNDVhMjk1M2EyNjFkZGIxOGE0Y2MwOWQwMWRhNzhjZDk2N2RhZmEyZGRm
+    MjliNmM4Y2ZmNzY4ZTJkY2EzZWY4Mjg3NmU3ZjQxM2RkYTBjODE=
+  data.tar.gz: !binary |-
+    YTljOGZhNDY0YzdjZGYzMTA2NTM3MzIwNDg4MTcwYWEyM2IyZTc1YWYxMjFm
+    YjMwYWU1NWMzNGVkZGRkYWYyZjUwMTQ2MWZlMjdkNjQwMjIwYWUwNmNlYjM3
+    NDlmZDk5MGNlMTk4ZDhlMzFiOGUyZTIwY2EyZTY3MjUwYjc2NWY=

data/lib/csv-diff/algorithm.rb

@@ -31,7 +31,6 @@ class CSVDiff
             right_keys.each_with_index do |key, right_row_id|
                 key_vals = key.split('~')
                 parent = key_vals[0...parent_fields].join('~')
-                child = key_vals[parent_fields..-1].join('~')
                 left_parent = left_index[parent]
                 right_parent = right_index[parent]
                 left_value = left_values[key]
@@ -58,7 +57,7 @@ class CSVDiff
                             #puts "Move #{left_idx} -> #{right_idx}: #{key}"
                         end
                     end
-                    if include_updates && (changes = diff_row(left_values[key], right_values[key], diff_fields))
+                    if include_updates && (changes = diff_row(left_value, right_value, diff_fields))
                         diffs[key].merge!(id.merge(changes.merge(:action => 'Update')))
                         #puts "Change: #{key}"
                     end
@@ -75,7 +74,6 @@ class CSVDiff
                     # Delete
                     key_vals = key.split('~')
                     parent = key_vals[0...parent_fields].join('~')
-                    child = key_vals[parent_fields..-1].join('~')
                     left_parent = left_index[parent]
                     left_value = left_values[key]
                     left_idx = left_parent.index(key)

data/lib/csv-diff/csv_diff.rb

@@ -45,11 +45,15 @@ class CSVDiff
     # child id, and the remaining fields (if any) are the parent field(s) that
     # uniquely qualify the child instance.
     #
-    # @param left [Array<Array<String>>] An Array of lines, each of which is in
-    #   turn an Array containing fields.
-    # @param right [Array<Array<String>>] An Array of lines, each of which is in
-    #   turn an Array containing fields.
+    # @param left [Array|String|CSVSource] An Array of lines, each of which is in
+    #   an Array of fields, or a String specifying a path to a CSV file, or a
+    #   CSVSource object.
+    # @param right [Array|String|CSVSource] An Array of lines, each of which is
+    #   an Array of fields, or a String specifying a path to a CSV file, or a
+    #   CSVSource object.
     # @param options [Hash] A hash containing options.
+    # @option options [String] :encoding The encoding to use when opening the
+    #   CSV files.
     # @option options [Array<String>] :field_names An Array of field names for
     #   each field in +left+ and +right+. If not provided, the first row is
     #   assumed to contain field names.
@@ -75,12 +79,12 @@ class CSVDiff
     # @option options [Boolean] :ignore_deletes If true, records that appear
     #   in the left/from file but not in the right/to file are not reported.
     def initialize(left, right, options = {})
-        @left = CSVSource.new(left, options)
+        @left = left.is_a?(CSVSource) ? left : CSVSource.new(left, options)
         raise "No field names found in left (from) source" unless @left.field_names && @left.field_names.size > 0
-        @right = CSVSource.new(right, options)
+        @right = right.is_a?(CSVSource) ? right : CSVSource.new(right, options)
         raise "No field names found in right (to) source" unless @right.field_names && @right.field_names.size > 0
         @warnings = []
-        @diff_fields = get_diff_fields(@left.field_names, @right.field_names, options.fetch(:ignore_fields, []))
+        @diff_fields = get_diff_fields(@left.field_names, @right.field_names, options[:ignore_fields])
         @key_fields = @left.key_fields.map{ |kf| @diff_fields[kf] }
         diff(options)
     end
@@ -98,7 +102,7 @@ class CSVDiff
         unless @summary
             @summary = Hash.new{ |h, k| h[k] = 0 }
             @diffs.each{ |k, v| @summary[v[:action]] += 1 }
-            @summary['Warnings'] = warnings.size if warnings.size > 0
+            @summary['Warning'] = warnings.size if warnings.size > 0
         end
         @summary
     end
@@ -112,13 +116,19 @@ class CSVDiff
     end
 
 
-    # @return [Array<String>] an array of warning messages generated during the
-    #    diff process.
+    # @return [Array<String>] an array of warning messages generated from the
+    #    sources and the diff process.
     def warnings
         @left.warnings + @right.warnings + @warnings
     end
 
 
+    # @return [Array<String>] an array of warning messages from the diff process.
+    def diff_warnings
+        @warnings
+    end
+
+
     private
 
 
@@ -126,9 +136,10 @@ class CSVDiff
     # in both, on which members can be diffed.
     def get_diff_fields(left_fields, right_fields, ignore_fields)
         diff_fields = []
-        right_fields.each do |fld|
+        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 && (ignore_fields.include?(fld) ||
+                                                            ignore_fields.include?(i))
             else
                 @warnings << "Field '#{fld}' is missing from the left (from) file, and won't be diffed"
             end

data/lib/csv-diff/csv_source.rb

@@ -47,8 +47,8 @@ class CSVDiff
         #   Array of Arrays containing CSV data. If the :field_names option is
         #   not specified, the first line must contain the names of the fields.
         # @param options [Hash] An options hash.
-        # @option options [String] :mode_string The mode to use when opening the
-        #   CSV file. Defaults to 'r'.
+        # @option options [String] :encoding The encoding to use when opening the
+        #   CSV file.
         # @option options [Hash] :csv_options Any options you wish to pass to
         #   CSV.open, e.g. :col_sep.
         # @option options [Array<String>] :field_names The names of each of the
@@ -66,7 +66,7 @@ class CSVDiff
         def initialize(source, options = {})
             if source.is_a?(String)
                 require 'csv'
-                mode_string = options.fetch(:mode_string, 'r')
+                mode_string = options[:encoding] ? "r:#{options[:encoding]}" : 'r'
                 csv_options = options.fetch(:csv_options, {})
                 @path = source
                 source = CSV.open(@path, mode_string, csv_options).readlines
@@ -76,8 +76,8 @@ class CSVDiff
                 @parent_fields = @key_fields[0...-1]
                 @child_fields = @key_fields[-1..-1]
             else
-                @parent_fields = [options.fetch(:parent_field, options.fetch(:parent_fields, []))].flatten
-                @child_fields = [options.fetch(:child_field, options.fetch(:child_fields, [0]))].flatten
+                @parent_fields = [options.fetch(:parent_field, options[:parent_fields]) || []].flatten
+                @child_fields = [options.fetch(:child_field, options[:child_fields]) || [0]].flatten
                 @key_fields = @parent_fields + @child_fields
             end
             @field_names = options[:field_names]

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csv-diff
 version: !ruby/object:Gem::Version
-  version: '0.1'
-  prerelease: 
+  version: '0.2'
 platform: ruby
 authors:
 - Adam Gardiner
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-30 00:00:00.000000000 Z
+date: 2014-08-11 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
@@ -28,35 +27,34 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- README.md
 - LICENSE
+- README.md
+- lib/csv-diff.rb
 - 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: []
-post_install_message: 
+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: 1.8.23
+rubygems_version: 2.4.1
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: CSV Diff is a library for generating diffs from data in CSV format
 test_files: []