eco-helpers 3.2.12 → 3.2.14

data/lib/eco/csv/split.rb

@@ -3,14 +3,17 @@ module Eco
     class Split
       include Eco::Language::AuxiliarLogger
 
+      MAX_ROWS_DEFAULT = 1_000_000
+
       attr_reader :filename
 
-      def initialize(filename, max_rows:, start_at: nil, **kargs)
+      def initialize(filename, max_rows: :unused, start_at: nil, **kargs)
         msg = "File '#{filename}' does not exist"
         raise ArgumentError, msg unless ::File.exist?(filename)
 
         @filename = filename
         @max_rows = max_rows
+        @max_rows = MAX_ROWS_DEFAULT if max_rows == :unused
         @start_at = start_at
         @params   = kargs
 
@@ -34,16 +37,17 @@ module Eco
         @out_files ||= []
       end
 
-      # @yield [idx, file] a block to spot the filename
+      # @yield [row, ridx, fidx, file] block to spot if the row should be included
       # @yieldparam idx [Integer] the number of the file
       # @yieldparam file [String] the default name of the file
-      # @yieldreturn [String] the filename of the file `idx`.
-      #   - If `nil` it will create its own filename convention
+      # @yieldparam fidx [Integer] the number of the file
+      # @yieldparam file [String] the default name of the file
+      # @yieldreturn [Bollean] whether the row should be included
       # @return [Array<String>] names of the generated files
-      def call(&block)
+      def call(&filter)
         stream.for_each(start_at_idx: start_at) do |row, ridx|
           self.total_count += 1
-          copy_row(row, ridx, &block)
+          copy_row(row, ridx, &filter)
         end
 
         out_files
@@ -56,33 +60,42 @@ module Eco
 
       attr_reader :params
       attr_reader :idx, :max_rows, :start_at
-      attr_reader :headers, :row_idx
+      attr_reader :headers, :row_idx, :out_row_idx
+      attr_reader :last_cut_desc
 
       attr_accessor :exception
 
-      def copy_row(row, ridx, &block)
+      def copy_row(row, ridx)
         @headers ||= row.headers
         @row_idx   = ridx
 
-        current_csv(ridx) do |csv, fidx, file_out|
+        current_csv(row) do |csv, fidx, file_out|
           included   = true
-          included &&= !block || yield(row, ridx, fidx, file_out)
+          included &&= yield(row, ridx, fidx, file_out) if block_given?
           next unless included
 
+          @out_row_idx    += 1
           self.copy_count += 1
           csv             << row.fields
         end
       end
 
-      def current_csv(ridx)
-        if split?(ridx) || @csv.nil?
-          puts "Split at row #{row_idx}"
+      def current_csv(row)
+        if (cut = split?(row, &splitter)) || @csv.nil?
+          cut = nil if cut.is_a?(TrueClass) || cut.to_s.empty? || !cut
+          msg = "Split at row #{row_idx}"
+          msg << " (cut: #{cut})" unless cut.nil?
+          puts msg
+
+          @last_cut_desc = cut unless cut.nil?
+
           @csv&.close
 
-          out_filename = generate_name(next_idx)
+          out_filename = generate_name(next_idx, desc: last_cut_desc)
           @csv         = ::CSV.open(out_filename, "w")
           @csv        << headers
           out_files   << out_filename
+          @out_row_idx = 0
         end
 
         yield(@csv, idx, out_files.last) if block_given?
@@ -90,8 +103,19 @@ module Eco
         @csv
       end
 
-      def split?(ridx)
-        ((ridx + 1) % max_rows).zero?
+      # @note client scripts can tweak this method.
+      def split?(row)
+        return yield(row, row_idx) if block_given?
+
+        ((row_idx + 1) % max_rows).zero?
+      end
+
+      def splitter
+        @splitter ||= params[:splitter]
+      end
+
+      def splitter?
+        splitter.is_a?(Proc)
       end
 
       def next_idx
@@ -103,11 +127,15 @@ module Eco
       end
 
       def stream
-        @stream ||= Eco::CSV::Stream.new(filename, **params)
+        @stream ||= Eco::CSV::Stream.new(
+          filename,
+          **params
+        )
       end
 
-      def generate_name(fidx)
-        File.join(input_dir, "#{input_name}_#{file_number(fidx)}#{input_ext}")
+      def generate_name(fidx, desc: nil)
+        desc = "_#{desc}" unless desc.nil?
+        File.join(input_dir, "#{input_name}_#{file_number(fidx)}#{desc}#{input_ext}")
       end
 
       def file_number(num)

data/lib/eco/csv/stream.rb

@@ -3,6 +3,16 @@ module Eco
     class Stream
       include Eco::Language::AuxiliarLogger
 
+      CSV_PARAMS = %i[
+        col_sep row_sep quote_char
+        headers skip_blanks skip_lines
+        nil_value empty_value
+        converters unconverted_fields
+        return_headers header_converters
+        liberal_parsing
+        field_size_limit
+      ].freeze
+
       attr_reader :filename
 
       def initialize(filename, **kargs)
@@ -16,9 +26,42 @@ module Eco
         init
       end
 
+      def eof?
+        started? && !row
+      end
+
+      def started?
+        @started ||= false
+      end
+
+      def shift
+        raise ArgumentError, 'Expecting block, but not given.' unless block_given?
+
+        @started = true
+        yield(row, next_idx) if (self.row = csv.shift)
+      rescue StandardError => err
+        self.exception = err
+        raise
+      ensure
+        unless row || !fd.is_a?(::File)
+          fd.close
+          @fd = nil
+        end
+
+        if exception
+          # Give some feedback if it crashes
+          msg  = []
+          msg << "Last row IDX: #{idx}"
+          msg << "Last row content: #{row.to_h.pretty_inspect}"
+          puts msg
+          log(:debug) { msg.join("\n") }
+        end
+      end
+
       def for_each(start_at_idx: 0)
         raise ArgumentError, 'Expecting block, but not given.' unless block_given?
 
+        @started = true
         move_to_idx(start_at_idx)
 
         yield(row, next_idx) while (self.row = csv.shift)
@@ -38,6 +81,7 @@ module Eco
       end
 
       def move_to_idx(start_at_idx)
+        @started       = true
         start_at_idx ||= 0
         next_idx while (idx < start_at_idx) && (self.row = csv.shift)
       end
@@ -58,12 +102,18 @@ module Eco
         return @csv if instance_variable_defined?(:@csv)
 
         @fd  = ::File.open(filename, 'r')
-        @csv = Eco::CSV.new(fd, **params)
+        @csv = Eco::CSV.new(fd, **params.slice(*csv_params))
       end
 
       def init
         @idx ||= 0 # rubocop:disable Naming/MemoizedInstanceVariableName
       end
+
+      def csv_params
+        return self.class::CSV_PARAMS if self.class.const_defined?(:CSV_PARAMS)
+
+        CSV_PARAMS
+      end
     end
   end
 end

data/lib/eco/csv.rb

@@ -19,7 +19,7 @@ module Eco
       end
 
       # Splits the csv `filename` into `max_rows`
-      # @yield [row, ridx, fidx, file]
+      # @yield [row, ridx, fidx, file] block to spot if the row should be included
       # @yieldparam row [Integer] the row
       # @yieldparam ridx [Integer] the index of the row in the source file
       # @yieldparam fidx [Integer] the number of the file
@@ -29,15 +29,18 @@ module Eco
       # @param max_rows [Integer] number of rows per file
       # @param start_at [Integer] row that sets the starting point.
       #   Leave empty for the full set of rows.
+      # @param kargs [Hash] additional parameters
+      #   - `:splitter` [Proc] custom splitter (criteria)
+      #     - Receives the row idx and the row itself
       # @return [Eco::CSV::Split]
-      def split(filename, max_rows:, start_at: nil, **kargs, &block)
+      def split(filename, max_rows: :unused, start_at: nil, **kargs, &filter)
         Eco::CSV::Split.new(
           filename,
           max_rows: max_rows,
           start_at: start_at,
           **kargs
         ).tap do |splitter|
-          splitter.call(&block)
+          splitter.call(&filter)
         end
       end
 

data/lib/eco/version.rb

@@ -1,3 +1,3 @@
 module Eco
-  VERSION = '3.2.12'.freeze
+  VERSION = '3.2.14'.freeze
 end

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: eco-helpers
 version: !ruby/object:Gem::Version
-  version: 3.2.12
+  version: 3.2.14
 platform: ruby
 authors:
 - Oscar Segura
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-01-19 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: byebug
@@ -536,7 +535,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 6.7.0
-description:
 email:
 - oscar@ecoportal.co.nz
 executables: []
@@ -796,18 +794,25 @@ files:
 - lib/eco/api/usecases/default/people/utils/switch_supervisor_case.rb
 - lib/eco/api/usecases/default/people/utils/transfer_account_case.rb
 - lib/eco/api/usecases/default/utils.rb
+- lib/eco/api/usecases/default/utils/add_page_id_case.rb
+- lib/eco/api/usecases/default/utils/cli/add_page_id_cli.rb
 - lib/eco/api/usecases/default/utils/cli/entries_to_csv_cli.rb
 - lib/eco/api/usecases/default/utils/cli/group_csv_cli.rb
 - lib/eco/api/usecases/default/utils/cli/json_to_csv_cli.rb
+- lib/eco/api/usecases/default/utils/cli/merge_csv_cli.rb
 - lib/eco/api/usecases/default/utils/cli/sort_csv_cli.rb
 - lib/eco/api/usecases/default/utils/cli/split_csv_cli.rb
 - lib/eco/api/usecases/default/utils/cli/split_json_cli.rb
+- lib/eco/api/usecases/default/utils/cli/track_files_cli.rb
 - lib/eco/api/usecases/default/utils/entries_to_csv_case.rb
 - lib/eco/api/usecases/default/utils/group_csv_case.rb
+- lib/eco/api/usecases/default/utils/group_csv_case/file_handler.rb
 - lib/eco/api/usecases/default/utils/json_to_csv_case.rb
+- lib/eco/api/usecases/default/utils/merge_csv_case.rb
 - lib/eco/api/usecases/default/utils/sort_csv_case.rb
 - lib/eco/api/usecases/default/utils/split_csv_case.rb
 - lib/eco/api/usecases/default/utils/split_json_case.rb
+- lib/eco/api/usecases/default/utils/track_files_case.rb
 - lib/eco/api/usecases/default_cases.rb
 - lib/eco/api/usecases/default_cases/create_case.rb
 - lib/eco/api/usecases/default_cases/delete_sync_case.rb
@@ -1083,7 +1088,6 @@ licenses:
 - MIT
 metadata:
   rubygems_mfa_required: 'true'
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -1098,8 +1102,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.23
-signing_key:
+rubygems_version: 4.0.8
 specification_version: 4
 summary: eco-helpers to manage people api cases
 test_files: []