json_csv 0.0.7 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: '0043834553b3243296e8b2b55c6806721b82673c'
-  data.tar.gz: 857ab74bc2b9f95ffb0f5d9d47ba520f8ba0a17f
+SHA256:
+  metadata.gz: fca9d1007e87cc6543be68112f80a858d7cadc7bdc409b9643b300167c26a9a7
+  data.tar.gz: 6205ee5d616c4c5dd3cd456a5806b9705bf3356723310c1284a2a41eb3131381
 SHA512:
-  metadata.gz: 427f4714f7b6999c798bef38b8e80bef3f0fe5033b31909e4a3aa064aee79e407e5f5957a207dfaa55d9d389b7da763d813c053ce184f3dd8bc97c0b38ead32a
-  data.tar.gz: cdf0311ca31c8c830f22daf426f18e2a36f77cb5ebc47ebdc97ceaf8eeecea1bf1b88f2dec60dd2155e4f6d94c17ccfa5aded6cb64efe9b399d1aaf27beb5738
+  metadata.gz: ec26fe5b50b337de6e7de99a2698c311fbe606343605bfa7a296c5b4f2f39be2b9a21969af107758b99d3e2332b346c06dc3f7b007b7f1c8e435d03609c128fc
+  data.tar.gz: fb0f10c4b581af63325bd69cec48158fca497e0a29c5a416c4df415c53249d7b01f1668b3b55660382c87dc378ff2697c942a01a8b15eda8ebae039d309c23b0

data/README.md

@@ -13,9 +13,26 @@ gem install json_csv
 ```ruby
 require 'json_csv'
 
-TODO: Provide usage examples
+path_to_output_csv_file = '/path/to/file.csv'
+
+# Write json-like hash objects to a csv file
+
+JsonCsv.create_csv_for_json_records(path_to_output_csv_file) do |csv_builder|
+  digital_objects_for_batch_export(batch_export) do |digital_object|
+    csv_builder.add({...json-like hash...})
+  end
+end
+
+# Read csv back into json-like hash objects
+
+JsonCsv.csv_file_to_hierarchical_json_hash(csv_file.path) do |json_hash_for_row, csv_row_number|
+  puts "Row: #{csv_row_number}" # prints out 2 the first time, then 3, etc.
+  puts "Object: #{json_hash_for_row}" # prints out a hierarchical json object, created from the csv row
+end
 ```
 
+See specs for advanced usage.
+
 ### Running Tests (for developers):
 
 Tests are great and we should run them.  Here's how:

data/lib/json_csv/csv_builder.rb

@@ -1,10 +1,15 @@
+# frozen_string_literal: true
+
 require 'csv'
 require 'json_csv/json_to_csv'
 
 module JsonCsv
   class CsvBuilder
-    private_class_method :new # private constructor. we don't want users to initialize this class.
-    attr_reader :known_headers_to_indexes # map of all headers seen by this CsvBuilder, mapped to their column order indexes
+    # private constructor. we don't want users to initialize this class.
+    private_class_method :new
+
+    # map of all headers seen by this CsvBuilder, mapped to their column order indexes
+    attr_reader :known_headers_to_indexes
 
     def initialize(open_csv_handle)
       @known_headers_to_indexes = {}
@@ -15,7 +20,10 @@ module JsonCsv
     def add(json_hash)
       row_to_write = []
       JsonCsv.json_hash_to_flat_csv_row_hash(json_hash).each do |column_header, cell_value|
-        known_headers_to_indexes[column_header] = known_headers_to_indexes.length unless known_headers_to_indexes.key?(column_header)
+        unless known_headers_to_indexes.key?(column_header)
+          known_headers_to_indexes[column_header] =
+            known_headers_to_indexes.length
+        end
         row_to_write[known_headers_to_indexes[column_header]] = cell_value
       end
       @open_csv_handle << row_to_write
@@ -41,13 +49,14 @@ module JsonCsv
 
     def self.original_header_indexes_to_sorted_indexes(csv_headers, column_header_comparator)
       original_headers_to_indexes = Hash[csv_headers.map.with_index { |header, index| [header, index] }]
-      headers_to_sorted_indexes = Hash[csv_headers.sort(&column_header_comparator).map.with_index { |header, index| [header, index] }]
+      headers_to_sorted_indexes = Hash[csv_headers.sort(&column_header_comparator).map.with_index do |header, index|
+                                         [header, index]
+                                       end ]
       original_to_sorted_index_map = {}
       original_headers_to_indexes.each do |header, original_index|
         original_to_sorted_index_map[original_index] = headers_to_sorted_indexes[header]
       end
       original_to_sorted_index_map
     end
-
   end
 end

data/lib/json_csv/csv_to_json.rb

@@ -1,13 +1,14 @@
+# frozen_string_literal: true
+
 require 'json_csv/utils'
 require 'csv'
 
 module JsonCsv
   module CsvToJson
-
-    TYPE_STRING = 'string'.freeze
-    TYPE_INTEGER = 'integer'.freeze
-    TYPE_FLOAT = 'float'.freeze
-    TYPE_BOOLEAN = 'boolean'.freeze
+    TYPE_STRING = 'string'
+    TYPE_INTEGER = 'integer'
+    TYPE_FLOAT = 'float'
+    TYPE_BOOLEAN = 'boolean'
     FIELD_CASTING_TYPES = [TYPE_STRING, TYPE_INTEGER, TYPE_FLOAT, TYPE_BOOLEAN].freeze
 
     def self.included(base)
@@ -19,9 +20,14 @@ module JsonCsv
       # presenting that row as un-flattened json.
       # This method works for large CSVs and uses very little memory
       # because it only keeps one row in memory at a time.
-      # Sample usage: csv_file_to_hierarchical_json_hash(path_to_csv, field_casting_rules = {}, strip_value_whitespace = true) do |row_json_hash, row_number|
+      # Sample usage:
+      # csv_file_to_hierarchical_json_hash(
+      #  path_to_csv, field_casting_rules = {}, strip_value_whitespace = true
+      # ) { |row_json_hash, row_number| ...your block logic here... }
       def csv_file_to_hierarchical_json_hash(path_to_csv, field_casting_rules = {}, strip_value_whitespace = true)
-        i = 1 # start with row 1 because this corresponds to the first row of 0-indexed CSV data
+        # Start with row 2 because this corresponds to the SECOND row of
+        # 1-indexed CSV data (where headers are row 1)
+        i = 2
         CSV.foreach(path_to_csv, headers: true, header_converters: lambda { |header|
           header.strip # remove leading and trailing header whitespace
         }) do |row_data_hash|
@@ -34,6 +40,7 @@ module JsonCsv
         hierarchical_hash = {}
         row_data_hash.each do |key, value|
           next if value.nil? || value == '' # ignore nil or empty string values
+
           put_value_at_json_path(hierarchical_hash, key, value, field_casting_rules)
         end
         # Clean up empty array elements, which may have come about from CSV data
@@ -53,11 +60,19 @@ module JsonCsv
         if json_path_pieces.length == 1
           # If the full_json_path_from_top matches one of the field_casting_rules,
           # then case this field to the specified cast type
-          full_json_path_from_top_as_field_casting_rule_pattern = real_json_path_to_field_casting_rule_pattern(full_json_path_from_top)
-          obj[json_path_pieces[0]] = field_casting_rules.key?(full_json_path_from_top_as_field_casting_rule_pattern) ? apply_field_casting_type(value, field_casting_rules[full_json_path_from_top_as_field_casting_rule_pattern]) : value
+          full_json_path_from_top_as_field_casting_rule_pattern =
+            real_json_path_to_field_casting_rule_pattern(full_json_path_from_top)
+          obj[json_path_pieces[0]] =
+            if field_casting_rules.key?(full_json_path_from_top_as_field_casting_rule_pattern)
+              apply_field_casting_type(value,
+                                       field_casting_rules[full_json_path_from_top_as_field_casting_rule_pattern])
+            else
+              value
+            end
         else
           obj[json_path_pieces[0]] ||= (json_path_pieces[1].is_a?(Integer) ? [] : {})
-          put_value_at_json_path(obj[json_path_pieces[0]], pieces_to_json_path(json_path_pieces[1..-1]), value, field_casting_rules, full_json_path_from_top)
+          put_value_at_json_path(obj[json_path_pieces[0]], pieces_to_json_path(json_path_pieces[1..]), value,
+                                 field_casting_rules, full_json_path_from_top)
         end
       end
 
@@ -68,19 +83,28 @@ module JsonCsv
       end
 
       def apply_field_casting_type(value, field_casting_type)
-        raise ArgumentError, "Invalid cast type #{field_casting_type}" unless FIELD_CASTING_TYPES.include?(field_casting_type)
+        unless FIELD_CASTING_TYPES.include?(field_casting_type)
+          raise ArgumentError,
+                "Invalid cast type #{field_casting_type}"
+        end
 
         case field_casting_type
         when TYPE_INTEGER
-          raise ArgumentError, "\"#{value}\" is not an integer" unless value =~ /^[0-9]+$/
+          raise ArgumentError, "\"#{value}\" is not an integer" unless /^[0-9]+$/.match?(value.to_s)
+
           value.to_i
         when TYPE_FLOAT
-          raise ArgumentError, "\"#{value}\" is not a float" unless value =~ /^[0-9]+(\.[0-9]+)*$/ || value =~ /^\.[0-9]+$/
+          unless value.to_s =~ /^[0-9]+(\.[0-9]+)*$/ || value.to_s =~ /^\.[0-9]+$/
+            raise ArgumentError,
+                  "\"#{value}\" is not a float"
+          end
+
           value.to_f
         when TYPE_BOOLEAN
-          if value.downcase == 'true'
+          case value.downcase
+          when 'true'
             true
-          elsif value.downcase == 'false'
+          when 'false'
             false
           else
             raise ArgumentError, "\"#{value}\" is not a boolean"
@@ -123,7 +147,6 @@ module JsonCsv
         end
         json_path
       end
-
     end
   end
 end

data/lib/json_csv/json_to_csv.rb

@@ -1,9 +1,10 @@
+# frozen_string_literal: true
+
 require 'json'
 require 'json_csv/csv_builder'
 
 module JsonCsv
   module JsonToCsv
-
     def self.included(base)
       base.extend ClassMethods
     end
@@ -26,21 +27,20 @@ module JsonCsv
       #     csv_builder.add(json_hash)
       #   end
       # end
-      def create_csv_for_json_records(csv_outfile_path, header_sort_comparator = DEFAULT_HEADER_SORT_COMPARATOR)
-        csv_temp_outfile_path = csv_outfile_path + '.temp'
+      def create_csv_for_json_records(csv_outfile_path, header_sort_comparator = DEFAULT_HEADER_SORT_COMPARATOR, &block)
+        csv_temp_outfile_path = "#{csv_outfile_path}.temp"
 
         begin
           # Step 1: Build CSV with unsorted headers in temp file
-          csv_headers = JsonCsv::CsvBuilder.create_csv_without_headers(csv_temp_outfile_path, 'wb') do |csv_builder|
-            yield csv_builder
-          end
+          csv_headers = JsonCsv::CsvBuilder.create_csv_without_headers(csv_temp_outfile_path, 'wb', &block)
 
           # Step 2: Sort CSV columns by header, based on column_header_comparator
-          original_to_sorted_index_map = JsonCsv::CsvBuilder.original_header_indexes_to_sorted_indexes(csv_headers, header_sort_comparator)
+          original_to_sorted_index_map = JsonCsv::CsvBuilder.original_header_indexes_to_sorted_indexes(
+            csv_headers, header_sort_comparator
+          )
           CSV.open(csv_outfile_path, 'wb') do |final_csv|
             # Open temporary CSV for reading
             CSV.open(csv_temp_outfile_path, 'rb') do |temp_csv|
-
               # write out ordered header row
               reordered_header_row = []
               csv_headers.each_with_index do |header, index|
@@ -82,8 +82,11 @@ module JsonCsv
         if obj.is_a?(Hash)
           obj.each do |key, val|
             if key_contains_unallowed_characters?(key)
-              raise ArgumentError, 'Cannot deal with hash keys that contain "[" or "]" or "." because these characters have special meanings in CSV headers.'
+              raise ArgumentError,
+                    'Cannot deal with hash keys that contain "[" or "]" or "." because '\
+                    'these characters have special meanings in CSV headers.'
             end
+
             path = parent_path + (parent_path.empty? ? '' : '.') + key
             flatten_hash(val, path, flat_hash_to_build)
           end
@@ -101,9 +104,9 @@ module JsonCsv
 
       def key_contains_unallowed_characters?(key)
         return true if key.index('[') || key.index(']') || key.index('.')
+
         false
       end
     end
-
   end
 end

data/lib/json_csv/utils.rb

@@ -1,6 +1,7 @@
+# frozen_string_literal: true
+
 module JsonCsv
   module Utils
-
     # Returns true for empty strings, empty arrays, or empty hashes.
     # Also returns true for strings that only contain whitespace.
     # Returns false for all other values, including booleans and numbers.
@@ -8,33 +9,41 @@ module JsonCsv
       return true if value.respond_to?(:empty?) && value.empty? # empty string, empty array, or empty hash
       return true if value.is_a?(String) && value.strip.empty? # string that only contains whitespace
       return true if value.nil?
+
       false
     end
 
+    def self.hash_or_array?(obj)
+      obj.is_a?(Hash) || obj.is_a?(Array)
+    end
+
+    # Given a Hash or Array, recursively removes all blank fields.
+    # Note: This method will raise an ArgumentError if the supplied object
+    # is a frozen Hash or Array.
     def self.recursively_remove_blank_fields!(hash_or_array)
-      return if hash_or_array.frozen? # We can't modify a frozen value, so we won't.
+      raise ArgumentError, 'Must supply a Hash or Array' unless hash_or_array?(hash_or_array)
+      raise ArgumentError, "Cannot modify frozen value: #{hash_or_array.inspect}" if hash_or_array.frozen?
 
-      if hash_or_array.is_a?(Array)
+      case hash_or_array
+      when Array
         # Recurse through non-empty elements
         hash_or_array.each do |element|
-          recursively_remove_blank_fields!(element) if element.is_a?(Hash) || element.is_a?(Array)
+          recursively_remove_blank_fields!(element) if hash_or_array?(element)
         end
 
         # Delete blank array element values on this array level (including empty object ({}) values)
         hash_or_array.delete_if do |element|
           removable_value?(element)
         end
-      elsif hash_or_array.is_a?(Hash)
+      when Hash
         hash_or_array.each_value do |value|
-          recursively_remove_blank_fields!(value) if value.is_a?(Hash) || value.is_a?(Array)
+          recursively_remove_blank_fields!(value) if hash_or_array?(value)
         end
 
         # Delete blank hash values on this hash level (including empty object ({}) values)
         hash_or_array.delete_if do |_key, value|
           removable_value?(value)
         end
-      else
-        raise ArgumentError, 'Must supply a hash or array.'
       end
 
       hash_or_array
@@ -44,21 +53,37 @@ module JsonCsv
     # modifying the object's nested child hashes or array.
     # Note: This method modifies hash values, but does not
     # modify hash keys.
-    def self.recursively_strip_value_whitespace!(obj)
-      if obj.is_a?(Array)
-        obj.each do |element|
-          recursively_strip_value_whitespace!(element)
+    def self.recursively_strip_value_whitespace!(obj, replace_frozen_strings_when_stripped: false)
+      case obj
+      when Array
+        obj.each_with_index do |element, ix|
+          if element.is_a?(String) && replace_frozen_strings_when_stripped
+            stripped_string = element.strip
+            obj[ix] = stripped_string if stripped_string != obj[ix]
+          else
+            recursively_strip_value_whitespace!(
+              element,
+              replace_frozen_strings_when_stripped: replace_frozen_strings_when_stripped
+            )
+          end
         end
-      elsif obj.is_a?(Hash)
-        obj.each_value do |value|
-          recursively_strip_value_whitespace!(value)
+      when Hash
+        obj.each do |key, value|
+          if value.is_a?(String) && replace_frozen_strings_when_stripped
+            stripped_string = obj[key].strip
+            obj[key] = stripped_string if stripped_string != obj[key]
+          else
+            recursively_strip_value_whitespace!(
+              value,
+              replace_frozen_strings_when_stripped: replace_frozen_strings_when_stripped
+            )
+          end
         end
-      elsif obj.is_a?(String)
+      when String
         obj.strip!
       end
 
       obj
     end
-
   end
 end

data/lib/json_csv/version.rb

@@ -1,9 +1,9 @@
-module JsonCsv
+# frozen_string_literal: true
 
-  VERSION = '0.0.7'.freeze
+module JsonCsv
+  VERSION = '1.1.0'
 
   def self.version
     VERSION
   end
-
 end

data/lib/json_csv.rb

@@ -1,6 +1,8 @@
-require "json_csv/version"
-require "json_csv/json_to_csv"
-require "json_csv/csv_to_json"
+# frozen_string_literal: true
+
+require 'json_csv/version'
+require 'json_csv/json_to_csv'
+require 'json_csv/csv_to_json'
 
 module JsonCsv
   include JsonCsv::JsonToCsv

data/lib/tasks/json_csv/ci.rake

@@ -1,7 +1,8 @@
+# frozen_string_literal: true
+
 require 'json_csv'
 
 namespace :json_csv do
-
   begin
     # This code is in a begin/rescue block so that the Rakefile is usable
     # in an environment where RSpec is unavailable (i.e. production).
@@ -21,18 +22,18 @@ namespace :json_csv do
       task.fail_on_error = true
     end
   rescue LoadError => e
-    puts "[Warning] Exception creating rspec rake tasks.  This message can be ignored in environments that intentionally do not pull in the RSpec gem (i.e. production)."
+    puts '[Warning] Exception creating rspec rake tasks.  This message can be ignored in '\
+      'environments that intentionally do not pull in the RSpec gem (i.e. production).'
     puts e
   end
 
-  desc "CI build"
+  desc 'CI build'
   task ci: ['json_csv:rubocop'] do
-    Rake::Task["json_csv:rspec"].invoke
+    Rake::Task['json_csv:rspec'].invoke
   end
 
-  desc "CI build"
+  desc 'CI build'
   task :ci_nocop do
-    Rake::Task["json_csv:rspec"].invoke
+    Rake::Task['json_csv:rspec'].invoke
   end
-
 end

data/lib/tasks/json_csv.rake

@@ -1,8 +1,8 @@
-namespace :json_csv do
+# frozen_string_literal: true
 
-  desc "Hello!"
-  task :hello do
+namespace :json_csv do
+  desc 'Hello!'
+  task hello: :environment do
     puts 'Hello!'
   end
-
 end

metadata

@@ -1,11 +1,11 @@
 --- !ruby/object:Gem::Specification
 name: json_csv
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 1.1.0
 platform: ruby
 authors:
 - Eric O'Hanlon
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
 date: 2018-02-18 00:00:00.000000000 Z
@@ -39,33 +39,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '3.7'
 - !ruby/object:Gem::Dependency
-  name: rubocop
+  name: rubocul
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.51.0
+        version: 4.0.6
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.51.0
-- !ruby/object:Gem::Dependency
-  name: rubocop-rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 1.20.1
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 1.20.1
+        version: 4.0.6
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
@@ -99,7 +85,7 @@ homepage: https://github.com/cul/json_csv
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -107,16 +93,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.6.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.14
-signing_key: 
+rubygems_version: 3.0.3.1
+signing_key:
 specification_version: 4
 summary: A library for converting json to csv...and back!
 test_files: []