iostreams 1.10.3 → 2.0.0

metadata

@@ -1,17 +1,28 @@
 --- !ruby/object:Gem::Specification
 name: iostreams
 version: !ruby/object:Gem::Version
-  version: 1.10.3
+  version: 2.0.0
 platform: ruby
 authors:
 - Reid Morrison
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-10-27 00:00:00.000000000 Z
-dependencies: []
-description:
-email:
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: csv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -22,7 +33,6 @@ files:
 - lib/io_streams/builder.rb
 - lib/io_streams/bzip2/reader.rb
 - lib/io_streams/bzip2/writer.rb
-- lib/io_streams/deprecated.rb
 - lib/io_streams/encode/reader.rb
 - lib/io_streams/encode/writer.rb
 - lib/io_streams/errors.rb
@@ -57,7 +67,6 @@ files:
 - lib/io_streams/tabular/parser/hash.rb
 - lib/io_streams/tabular/parser/json.rb
 - lib/io_streams/tabular/parser/psv.rb
-- lib/io_streams/tabular/utility/csv_row.rb
 - lib/io_streams/utils.rb
 - lib/io_streams/version.rb
 - lib/io_streams/writer.rb
@@ -65,60 +74,15 @@ files:
 - lib/io_streams/zip/reader.rb
 - lib/io_streams/zip/writer.rb
 - lib/iostreams.rb
-- test/builder_test.rb
-- test/bzip2_reader_test.rb
-- test/bzip2_writer_test.rb
-- test/deprecated_test.rb
-- test/encode_reader_test.rb
-- test/encode_writer_test.rb
-- test/files/embedded_lines_test.csv
-- test/files/multiple_files.zip
-- test/files/spreadsheet.xlsx
-- test/files/test.csv
-- test/files/test.json
-- test/files/test.psv
-- test/files/text file.txt
-- test/files/text.txt
-- test/files/text.txt.bz2
-- test/files/text.txt.gz
-- test/files/text.txt.gz.zip
-- test/files/text.zip
-- test/files/text.zip.gz
-- test/files/unclosed_quote_large_test.csv
-- test/files/unclosed_quote_test.csv
-- test/files/unclosed_quote_test2.csv
-- test/files/utf16_test.csv
-- test/gzip_reader_test.rb
-- test/gzip_writer_test.rb
-- test/io_streams_test.rb
-- test/line_reader_test.rb
-- test/line_writer_test.rb
-- test/minimal_file_reader.rb
-- test/path_test.rb
-- test/paths/file_test.rb
-- test/paths/http_test.rb
-- test/paths/matcher_test.rb
-- test/paths/s3_test.rb
-- test/paths/sftp_test.rb
-- test/pgp_reader_test.rb
-- test/pgp_test.rb
-- test/pgp_writer_test.rb
-- test/record_reader_test.rb
-- test/record_writer_test.rb
-- test/row_reader_test.rb
-- test/row_writer_test.rb
-- test/stream_test.rb
-- test/tabular_test.rb
-- test/test_helper.rb
-- test/utils_test.rb
-- test/xlsx_reader_test.rb
-- test/zip_reader_test.rb
-- test/zip_writer_test.rb
 homepage: https://iostreams.rocketjob.io
 licenses:
 - Apache-2.0
-metadata: {}
-post_install_message:
+metadata:
+  bug_tracker_uri: https://github.com/reidmorrison/iostreams/issues
+  changelog_uri: https://github.com/reidmorrison/iostreams/blob/v2.0.0/CHANGELOG.md
+  documentation_uri: https://iostreams.rocketjob.io
+  source_code_uri: https://github.com/reidmorrison/iostreams/tree/v2.0.0
+  rubygems_mfa_required: 'true'
 rdoc_options: []
 require_paths:
 - lib
@@ -126,64 +90,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.5'
+      version: '3.2'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
-signing_key:
+rubygems_version: 3.6.9
 specification_version: 4
-summary: Input and Output streaming for Ruby.
-test_files:
-- test/builder_test.rb
-- test/bzip2_reader_test.rb
-- test/bzip2_writer_test.rb
-- test/deprecated_test.rb
-- test/encode_reader_test.rb
-- test/encode_writer_test.rb
-- test/files/embedded_lines_test.csv
-- test/files/multiple_files.zip
-- test/files/spreadsheet.xlsx
-- test/files/test.csv
-- test/files/test.json
-- test/files/test.psv
-- test/files/text file.txt
-- test/files/text.txt
-- test/files/text.txt.bz2
-- test/files/text.txt.gz
-- test/files/text.txt.gz.zip
-- test/files/text.zip
-- test/files/text.zip.gz
-- test/files/unclosed_quote_large_test.csv
-- test/files/unclosed_quote_test.csv
-- test/files/unclosed_quote_test2.csv
-- test/files/utf16_test.csv
-- test/gzip_reader_test.rb
-- test/gzip_writer_test.rb
-- test/io_streams_test.rb
-- test/line_reader_test.rb
-- test/line_writer_test.rb
-- test/minimal_file_reader.rb
-- test/path_test.rb
-- test/paths/file_test.rb
-- test/paths/http_test.rb
-- test/paths/matcher_test.rb
-- test/paths/s3_test.rb
-- test/paths/sftp_test.rb
-- test/pgp_reader_test.rb
-- test/pgp_test.rb
-- test/pgp_writer_test.rb
-- test/record_reader_test.rb
-- test/record_writer_test.rb
-- test/row_reader_test.rb
-- test/row_writer_test.rb
-- test/stream_test.rb
-- test/tabular_test.rb
-- test/test_helper.rb
-- test/utils_test.rb
-- test/xlsx_reader_test.rb
-- test/zip_reader_test.rb
-- test/zip_writer_test.rb
+summary: 'Streaming I/O for Ruby: compression, encryption, format, and storage transparent
+  to your code.'
+test_files: []

data/lib/io_streams/deprecated.rb

@@ -1,216 +0,0 @@
-module IOStreams
-  UTF8_ENCODING   = Encoding.find("UTF-8").freeze
-  BINARY_ENCODING = Encoding.find("BINARY").freeze
-
-  # Deprecated IOStreams from v0.x. Do not use, will be removed soon.
-  module Deprecated
-    def self.included(base)
-      base.extend ClassMethods
-    end
-
-    module ClassMethods
-      # DEPRECATED. Use `#path` or `#io`
-      # Examples:
-      #   IOStreams.path("data.zip").reader { |f| f.read(100) }
-      #
-      #   IOStreams.path(file_name).option(:encode, encoding: "BINARY").reader { |f| f.read(100) }
-      #
-      #   io_stream = StringIO.new("Hello World")
-      #   IOStreams.stream(io_stream).reader { |f| f.read(100) }
-      def reader(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.reader(&block)
-      end
-
-      # DEPRECATED
-      def each_line(file_name_or_io, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.each(:line, **args, &block)
-      end
-
-      # DEPRECATED
-      def each_row(file_name_or_io, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.each(:array, **args, &block)
-      end
-
-      # DEPRECATED
-      def each_record(file_name_or_io, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.each(:hash, **args, &block)
-      end
-
-      # DEPRECATED. Use `#path` or `#io`
-      # Examples:
-      #   IOStreams.path("data.zip").writer { |f| f.write("Hello World") }
-      #
-      #   IOStreams.path(file_name).option(:encode, encoding: "BINARY").writer { |f| f.write("Hello World") }
-      #
-      #   io_stream = StringIO.new("Hello World")
-      #   IOStreams.stream(io_stream).writer { |f| f.write("Hello World") }
-      def writer(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.writer(&block)
-      end
-
-      # DEPRECATED
-      def line_writer(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.writer(:line, **args, &block)
-      end
-
-      # DEPRECATED
-      def row_writer(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.writer(:array, **args, &block)
-      end
-
-      # DEPRECATED
-      def record_writer(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.writer(:hash, **args, &block)
-      end
-
-      # Copies the source file/stream to the target file/stream.
-      # Returns [Integer] the number of bytes copied
-      #
-      # Example: Copy between 2 files
-      #   IOStreams.copy('a.csv', 'b.csv')
-      #
-      # Example: Read content from a Xlsx file and write it out in CSV form.
-      #   IOStreams.copy('a.xlsx', 'b.csv')
-      #
-      # Example:
-      #   # Read content from a JSON file and write it out in CSV form.
-      #   #
-      #   # The output header for the CSV file is extracted from the first row in the JSON file.
-      #   # If the first JSON row does not contain all the column names then they will be ignored
-      #   # for the rest of the file.
-      #   IOStreams.copy('a.json', 'b.csv')
-      #
-      # Example:
-      #   # Read a PSV file and write out a CSV file from it.
-      #   IOStreams.copy('a.psv', 'b.csv')
-      #
-      # Example:
-      #   # Copy between 2 files, encrypting the target file with Symmetric Encryption
-      #   # Since the target file_name already includes `.enc` in the filename, it is automatically
-      #   # encrypted.
-      #   IOStreams.copy('a.csv', 'b.csv.enc')
-      #
-      # Example:
-      #   # Copy between 2 files, encrypting the target file with Symmetric Encryption
-      #   # Since the target file_name does not include `.enc` in the filename, to encrypt it
-      #   # the encryption stream is added.
-      #   IOStreams.copy('a.csv', 'b', target_options: [:enc])
-      #
-      # Example:
-      #   # Copy between 2 files, encrypting the target file with Symmetric Encryption
-      #   # Since the target file_name does not include `.enc` in the filename, to encrypt it
-      #   # the encryption stream is added, along with the optional compression option.
-      #   IOStreams.copy('a.csv', 'b', target_options: [enc: { compress: true }])
-      #
-      # Example:
-      #   # Create a pgp encrypted file.
-      #   # For PGP Encryption the recipients email address is required.
-      #   IOStreams.copy('a.xlsx', 'b.csv.pgp', target_options: [:csv, pgp: { recipient_email: 'user@nospam.org' }])
-      #
-      # Example: Copy between 2 existing streams
-      #   IOStreams.reader('a.csv') do |source_stream|
-      #     IOStreams.writer('b.csv.enc') do |target_stream|
-      #       IOStreams.copy(source_stream, target_stream)
-      #     end
-      #   end
-      #
-      # Example:
-      #   # Copy between 2 csv files, reducing the number of columns present and encrypting the
-      #   # target file with Symmetric Encryption
-      #   output_headers = %w[name address]
-      #   IOStreams.copy(
-      #     'a.csv',
-      #     'b.csv.enc',
-      #     target_options: [csv:{headers: output_headers}, enc: {compress: true}]
-      #   )
-      #
-      # Example:
-      #   # Copy a locally encrypted file to AWS S3.
-      #   # Decrypts the file, then compresses it with gzip as it is being streamed into S3.
-      #   # Useful for when the entire bucket is encrypted on S3.
-      #   IOStreams.copy('a.csv.enc', 's3://my_bucket/b.csv.gz')
-      def copy(source_file_name_or_io, target_file_name_or_io, buffer_size: nil, source_options: {}, target_options: {})
-        # TODO: prevent stream conversions when reader and writer streams are the same!
-        reader(source_file_name_or_io, **source_options) do |source_stream|
-          writer(target_file_name_or_io, **target_options) do |target_stream|
-            IO.copy_stream(source_stream, target_stream)
-          end
-        end
-      end
-
-      # DEPRECATED
-      def reader_stream?(file_name_or_io)
-        file_name_or_io.respond_to?(:read)
-      end
-
-      # DEPRECATED
-      def writer_stream?(file_name_or_io)
-        file_name_or_io.respond_to?(:write)
-      end
-
-      # DEPRECATED. Use Path#compressed?
-      def compressed?(file_name)
-        Path.new(file_name).compressed?
-      end
-
-      # DEPRECATED. Use Path#encrypted?
-      def encrypted?(file_name)
-        Path.new(file_name).encrypted?
-      end
-
-      # DEPRECATED
-      def line_reader(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.reader(:line, **args, &block)
-      end
-
-      # DEPRECATED
-      def row_reader(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.reader(:line, **args, &block)
-      end
-
-      # DEPRECATED
-      def record_reader(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil, **args, &block)
-        path = build_path(file_name_or_io, streams: streams, file_name: file_name, encoding: encoding, encode_cleaner: encode_cleaner, encode_replace: encode_replace)
-        path.reader(:hash, **args, &block)
-      end
-
-      private
-
-      def build_path(file_name_or_io, streams: nil, file_name: nil, encoding: nil, encode_cleaner: nil, encode_replace: nil)
-        path = new(file_name_or_io)
-        path.file_name(file_name) if file_name
-
-        apply_old_style_streams(path, streams) if streams
-
-        if encoding || encode_cleaner || encode_replace
-          path.option_or_stream(:encode, encoding: encoding, cleaner: encode_cleaner, replace: encode_replace)
-        end
-
-        path
-      end
-
-      # Applies old form streams to the path
-      def apply_old_style_streams(path, streams)
-        if streams.is_a?(Symbol)
-          path.stream(streams)
-        elsif streams.is_a?(Array)
-          streams.each { |stream| apply_old_style_streams(path, stream) }
-        elsif streams.is_a?(Hash)
-          streams.each_pair { |stream, options| path.stream(stream, **options) }
-        else
-          raise ArgumentError, "Invalid old style stream supplied: #{params.inspect}"
-        end
-      end
-    end
-  end
-end

data/lib/io_streams/tabular/utility/csv_row.rb

@@ -1,105 +0,0 @@
-require "csv"
-module IOStreams
-  class Tabular
-    module Utility
-      # For parsing a single line of CSV at a time
-      # 2 to 3 times better performance than CSV.parse_line and considerably less
-      # garbage collection required.
-      #
-      # Note: Only used prior to Ruby 2.6
-      class CSVRow < ::CSV
-        UTF8_ENCODING = Encoding.find("UTF-8").freeze
-
-        def initialize(encoding = UTF8_ENCODING)
-          @io = StringIO.new("".force_encoding(encoding))
-          super(@io, row_sep: "")
-        end
-
-        # Parse a single line of CSV data
-        # Parameters
-        #   line [String]
-        #     A single line of CSV data without any line terminators
-        def parse(line)
-          return if IOStreams::Utils.blank?(line)
-          return if @skip_lines&.match(line)
-
-          in_extended_col = false
-          csv             = []
-          parts           = line.split(@col_sep, -1)
-          csv << nil if parts.empty?
-
-          # This loop is the hot path of csv parsing. Some things may be non-dry
-          # for a reason. Make sure to benchmark when refactoring.
-          parts.each do |part|
-            if in_extended_col
-              # If we are continuing a previous column
-              if part[-1] == @quote_char && part.count(@quote_char).odd?
-                # extended column ends
-                csv.last << part[0..-2]
-                raise MalformedCSVError, "Missing or stray quote in line #{lineno + 1}" if csv.last =~ @parsers[:stray_quote]
-
-                csv.last.gsub!(@quote_char * 2, @quote_char)
-                in_extended_col = false
-              else
-                csv.last << part
-                csv.last << @col_sep
-              end
-            elsif part[0] == @quote_char
-              # If we are starting a new quoted column
-              if part[-1] != @quote_char || part.count(@quote_char).odd?
-                # start an extended column
-                csv << part[1..-1]
-                csv.last << @col_sep
-                in_extended_col = true
-              else
-                # regular quoted column
-                csv << part[1..-2]
-                raise MalformedCSVError, "Missing or stray quote in line #{lineno + 1}" if csv.last =~ @parsers[:stray_quote]
-
-                csv.last.gsub!(@quote_char * 2, @quote_char)
-              end
-            elsif part =~ @parsers[:quote_or_nl]
-              # Unquoted field with bad characters.
-              if part =~ @parsers[:nl_or_lf]
-                raise MalformedCSVError, "Unquoted fields do not allow \\r or \\n (line #{lineno + 1})."
-              else
-                raise MalformedCSVError, "Illegal quoting in line #{lineno + 1}."
-              end
-            else
-              # Regular ole unquoted field.
-              csv << (part.empty? ? nil : part)
-            end
-          end
-
-          # Replace tacked on @col_sep with @row_sep if we are still in an extended
-          # column.
-          csv[-1][-1] = @row_sep if in_extended_col
-
-          raise MalformedCSVError, "Unclosed quoted field on line #{lineno + 1}." if in_extended_col
-
-          @lineno += 1
-
-          # save fields unconverted fields, if needed...
-          unconverted = csv.dup if @unconverted_fields
-
-          # convert fields, if needed...
-          csv         = convert_fields(csv) unless @use_headers || @converters.empty?
-          # parse out header rows and handle CSV::Row conversions...
-          csv         = parse_headers(csv) if @use_headers
-
-          # inject unconverted fields and accessor, if requested...
-          add_unconverted_fields(csv, unconverted) if @unconverted_fields && (!csv.respond_to? :unconverted_fields)
-
-          csv
-        end
-
-        # Return the supplied array as a single line CSV string.
-        def render(row)
-          row.map(&@quote).join(@col_sep) + @row_sep # quote and separate
-        end
-
-        alias to_csv render
-      end
-    end
-  end
-end