csv-utils 0.1.6 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b6af40dc417430366452f9b5ddc1670595fb16ca17ab8452b7842faaa0726343
-  data.tar.gz: 11db2a2e86c54f4f9593113cd2f1ddd9b712213beb7da49b0660501d63c148a5
+  metadata.gz: 8b1634cd26b21129c05cf1c5655e46ff3b81307135ce8dd686022cd8a4ff5adc
+  data.tar.gz: 53312f6841e32ddcae0e97cd9aab4513a47580c35a3ec39964f8933fdbbcff10
 SHA512:
-  metadata.gz: d97f0d8b564b3819713250b52f83a2b538862654423c9d932c77a0d188199949a31ed8acaf3fd0db7c1bcc00a57c1cdde2997553c2cd062429de691354472611
-  data.tar.gz: 1c486515fba9b72c9c37a4952f86f872947518fb82a2573e5868c57520085516f202acf146f2f276fe4fe88b20f49c304d391b30f9bdb96d8c82982d38109b03
+  metadata.gz: 5733c0ff8b730e957c46fc73b1080690dd79fb481b30f9591f4256507abc3ea46139d9758605c4c4e143e23781468b9adbd623812ceb105bb610a61943ffbc57
+  data.tar.gz: 4ce9256c44ed50fc289fbe2b0ce970b2798310d50b4f69dffe9fa57098b0acab0539049bd5c945b43768ea7cb3d97b2421e54bf4c069df7751bd3704b68db9ec

data/.ruby-gemset

@@ -0,0 +1 @@
+csv-utils

data/.ruby-version

@@ -0,0 +1 @@
+2.6.3

data/Gemfile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+source 'http://rubygems.org'
+
+gem 'inheritance-helper'
+
+group :development do
+  gem 'rake'
+  gem 'rubocop'
+end
+
+group :spec do
+  gem 'rspec'
+  gem 'simplecov'
+end

data/Gemfile.lock

@@ -0,0 +1,57 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    ast (2.4.1)
+    diff-lcs (1.3)
+    docile (1.3.2)
+    inheritance-helper (0.1.5)
+    parallel (1.19.2)
+    parser (2.7.1.4)
+      ast (~> 2.4.1)
+    rainbow (3.0.0)
+    rake (13.0.1)
+    regexp_parser (1.7.1)
+    rexml (3.2.4)
+    rspec (3.9.0)
+      rspec-core (~> 3.9.0)
+      rspec-expectations (~> 3.9.0)
+      rspec-mocks (~> 3.9.0)
+    rspec-core (3.9.2)
+      rspec-support (~> 3.9.3)
+    rspec-expectations (3.9.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-mocks (3.9.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-support (3.9.3)
+    rubocop (0.86.0)
+      parallel (~> 1.10)
+      parser (>= 2.7.0.1)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.7)
+      rexml
+      rubocop-ast (>= 0.0.3, < 1.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 2.0)
+    rubocop-ast (0.0.3)
+      parser (>= 2.7.0.1)
+    ruby-progressbar (1.10.1)
+    simplecov (0.18.5)
+      docile (~> 1.1)
+      simplecov-html (~> 0.11)
+    simplecov-html (0.12.2)
+    unicode-display_width (1.7.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  inheritance-helper
+  rake
+  rspec
+  rubocop
+  simplecov
+
+BUNDLED WITH
+   1.17.3

data/bin/csv-change-eol

@@ -0,0 +1,54 @@
+#!/usr/bin/env ruby
+
+require 'csv'
+
+def bold_string(str)
+  "\033[1m#{str}\033[0m"
+end
+  
+USAGE = "Usage: #{bold_string('csv-change-eol')} <csv_file> <end of line character sequence in hex>"
+
+def exit_on_error(msg)
+  $stderr.print <<STR
+Error: #{bold_string(msg)}
+
+#{USAGE}
+
+  End of line example: '7C5E7C0A' is '|^|\\n'
+   - 0A is new line
+   - 0D is carriage return
+
+  Goto: #{bold_string('http://www.asciitable.com/')} for help with the character sequence
+
+STR
+  exit 1
+end
+
+csv_file = ARGV.shift || exit_on_error('no csv file specified')
+eol_sequence = ARGV.shift || exit_on_error('no EOL character sequence specified')
+
+exit_on_error("file #{csv_file} not found") unless File.exist?(csv_file)
+exit_on_error("not a HEX sequece (#{eol_sequence})") unless eol_sequence =~ /\A[0-9a-f]+\z/i
+exit_on_error("incorrect number of characters in (#{eol_sequence}), should be even") unless eol_sequence.size.even?
+
+eol_sequence = [eol_sequence].pack('H*')
+
+
+escaped_csv_file =
+  if csv_file =~ /\.csv$/i
+    csv_file.sub(/(\.csv)$/i, '.escaped-eol\1')
+  else
+    csv_file + '.escaped-eol'
+  end
+
+
+File.open(escaped_csv_file, 'wb') do |out|
+  CSV.foreach(csv_file) do |row|
+    line = row.to_csv
+    line.rstrip!
+    line.concat(eol_sequence)
+    out.write line
+  end
+end
+
+puts escaped_csv_file

data/csv-utils.gemspec

@@ -2,7 +2,8 @@
 
 Gem::Specification.new do |s|
   s.name        = 'csv-utils'
-  s.version     = '0.1.6'
+  s.version     = '0.2.3'
+  s.licenses    = ['MIT']
   s.summary     = 'CSV Utils'
   s.description = 'Tools for debugging malformed CSV files'
   s.authors     = ['Doug Youch']
@@ -11,4 +12,6 @@ Gem::Specification.new do |s|
   s.files       = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   s.bindir      = 'bin'
   s.executables = s.files.grep(%r{^bin/}) { |f| File.basename(f) }
+
+  s.add_runtime_dependency 'inheritance-helper'
 end

data/lib/csv-utils.rb

@@ -0,0 +1,10 @@
+require 'csv'
+
+# Collection of tools for working with CSV files.
+module CSVUtils
+  autoload :CSVExtender, 'csv_utils/csv_extender'
+  autoload :CSVOptions, 'csv_utils/csv_options'
+  autoload :CSVReport, 'csv_utils/csv_report'
+  autoload :CSVRow, 'csv_utils/csv_row'
+  autoload :CSVSort, 'csv_utils/csv_sort'
+end

data/lib/csv_utils/csv_extender.rb

@@ -0,0 +1,76 @@
+# Utility class for appending data to a csv file.
+class CSVUtils::CSVExtender
+  attr_reader :csv_file,
+              :new_csv_file,
+              :csv_options
+
+  def initialize(csv_file, new_csv_file, csv_options = {})
+    @csv_file = csv_file
+    @new_csv_file = new_csv_file
+    @csv_options = csv_options
+  end
+
+  def append(additional_headers)
+    process(additional_headers) do |current_headers|
+      while (row = src.shift)
+        additional_columns = yield row, current_headers
+        dest << (row + additional_columns)
+      end
+    end
+  end
+
+  def append_in_batches(additional_headers, batch_size = 1_000)
+    process(additional_headers) do |current_headers|
+      batch = []
+
+      process_batch_proc = Proc.new do
+        additional_rows = yield batch, current_headers
+
+        batch.each_with_index do |row, idx|
+          dest << (row + additional_rows[idx])
+        end
+
+        batch = []
+      end
+
+      while (row = src.shift)
+        batch << row
+
+        process_batch_proc.call if batch.size >= batch_size
+      end
+
+      process_batch_proc.call if batch.size > 0
+    end
+  end
+
+  def process(additional_headers)
+    current_headers = append_headers(additional_headers)
+
+    yield current_headers
+
+    close
+  end
+
+  def src
+    @src ||= CSV.open(csv_file, 'rb', csv_options)
+  end
+
+  def dest
+    @dest ||= CSV.open(new_csv_file, 'wb', csv_options)
+  end
+
+  def close
+    src.close
+    dest.close
+  end
+
+  private
+
+  def append_headers(additional_headers)
+    return nil unless additional_headers
+
+    current_headers = src.shift
+    dest << (current_headers + additional_headers)
+    current_headers
+  end
+end

data/lib/csv_utils/csv_options.rb

@@ -0,0 +1,87 @@
+# Auto detect a csv files options
+module CSVUtils
+  class CSVOptions
+
+    # this list is from https://en.wikipedia.org/wiki/Byte_order_mark
+    BYTE_ORDER_MARKS = {
+      "\xEF\xBB\xBF".force_encoding('ASCII-8BIT') => 'UTF-8',
+      "\xFE\xFF".force_encoding('ASCII-8BIT') => 'UTF-16',
+      "\xFF\xFE".force_encoding('ASCII-8BIT') => 'UTF-16',
+      "\x00\x00\xFE\xFF".force_encoding('ASCII-8BIT') => 'UTF-32',
+      "\xFF\xFE\x00\x00".force_encoding('ASCII-8BIT') => 'UTF-32'
+    }
+
+    COL_SEPARATORS = [
+      "\x02",
+      "\t",
+      '|',
+      ','
+    ]
+
+    ROW_SEPARATORS = [
+      "\r\n",
+      "\n",
+      "\r"
+    ]
+
+    attr_reader :columns,
+                :byte_order_mark,
+                :encoding,
+                :col_separator,
+                :row_separator
+    
+
+    def initialize(io)
+      line =
+        if io.is_a?(String)
+          File.open(io, 'rb', &:readline)
+        else
+          io.readline
+        end
+
+      @col_separator = auto_detect_col_sep(line)
+      @row_separator = auto_detect_row_sep(line)
+      @byte_order_mark = get_byte_order_mark(line)
+      @encoding = get_character_encoding(@byte_order_mark)
+      @columns = get_number_of_columns(line) if @col_separator
+    end
+
+    def valid?
+      return false if @col_separator.nil? || @row_separator.nil?
+
+      true
+    end
+
+    def auto_detect_col_sep(line)
+      COL_SEPARATORS.detect { |sep| line.include?(sep) }
+    end
+
+    def auto_detect_row_sep(line)
+      ROW_SEPARATORS.detect { |sep| line.include?(sep) }
+    end
+
+    def get_headers(line)
+      headers = line.split(col_separator)
+      headers[0] = strip_byte_order_marks(headers[0])
+      headers
+    end
+
+    def get_number_of_columns(line)
+      get_headers(line).size
+    end
+
+    def get_byte_order_mark(line)
+      BYTE_ORDER_MARKS.keys.detect do |bom|
+        line =~ /\A#{bom}/
+      end
+    end
+
+    def get_character_encoding(bom)
+      BYTE_ORDER_MARKS[bom] || 'UTF-8'
+    end
+
+    def strip_byte_order_marks(header)
+      @byte_order_marks ? header.sub(@byte_order_marks, '') : header
+    end
+  end
+end

data/lib/csv_utils/csv_report.rb

@@ -0,0 +1,41 @@
+# Builds a csv file from csv rows
+module CSVUtils
+  class CSVReport
+    attr_reader :csv,
+                :must_close
+
+    def initialize(csv, headers = nil, csv_options = {}, &block)
+      @csv =
+        if csv.is_a?(String)
+          @must_close = true
+          mode = csv_options.delete(:mode) || 'wb'
+          CSV.open(csv, mode, csv_options)
+        else
+          @must_close = false
+          csv
+        end
+
+      generate(headers, &block) if block
+    end
+
+    def generate(headers = nil)
+      add_headers(headers) if headers
+      yield self
+      @csv.close if @must_close
+    end
+
+    def append(csv_row)
+      @csv <<
+        if csv_row.is_a?(Array)
+          csv_row
+        else
+          csv_row.to_a
+        end
+    end
+    alias << append
+
+    def add_headers(csv_row)
+      append(csv_row.is_a?(Array) ? csv_row : csv_row.csv_headers)
+    end
+  end
+end

data/lib/csv_utils/csv_row.rb

@@ -0,0 +1,57 @@
+require 'inheritance-helper'
+
+module CSVUtils
+  module CSVRow
+    def self.included(base)
+      base.extend InheritanceHelper::Methods
+      base.extend ClassMethods
+    end
+
+    module ClassMethods
+      def csv_columns
+        {}
+      end
+
+      def csv_column(header, options = {}, &block)
+        options[:header] ||= header.to_s
+
+        if block
+          options[:proc] = block
+        elsif options[:proc].nil?
+          options[:method] ||= header
+        end
+
+        add_value_to_class_method(:csv_columns, header => options)
+      end
+
+      def csv_headers
+        csv_columns.values.map { |column_options| csv_column_header(column_options) }
+      end
+
+      private
+
+      def csv_column_header(column_options)
+        column_options[:header]
+      end
+    end
+
+    def csv_row
+      self.class.csv_columns.values.map { |column_options| csv_column_value(column_options) }
+    end
+    alias_method :to_a, :csv_row
+
+    def csv_headers
+      self.class.csv_headers
+    end
+
+    private
+
+    def csv_column_value(column_options)
+      if column_options[:proc]
+        instance_eval(&column_options[:proc])
+      else
+        send(column_options[:method])
+      end
+    end
+  end
+end

data/lib/csv_utils/csv_sort.rb

@@ -0,0 +1,112 @@
+require 'fileutils'
+
+# Utility class for sorting the rows for a csv file
+class CSVUtils::CSVSort
+  attr_reader :csv_file,
+              :new_csv_file,
+              :has_headers,
+              :csv_options,
+              :headers
+
+  def initialize(csv_file, new_csv_file, has_headers = true, csv_options = {})
+    @csv_file = csv_file
+    @new_csv_file = new_csv_file
+    @has_headers = has_headers
+    @csv_options = csv_options
+    @csv_part_files = []
+    @files_to_delete = []
+  end
+
+  def sort(batch_size = 100_000, &block)
+    create_sorted_csv_part_files(batch_size, &block)
+    merge_csv_part_files(&block)
+  end
+
+  private
+
+  def merge_sort_csv_files(src_csv_file1, src_csv_file2, dest_csv_file)
+    src1 = CSV.open(src_csv_file1, 'rb', csv_options)
+    src2 = CSV.open(src_csv_file2, 'rb', csv_options)
+    dest = CSV.open(dest_csv_file, 'wb', csv_options)
+
+    if @headers
+      dest << @headers
+      src1.shift
+      src2.shift
+    end
+
+    row1 = src1.shift
+    row2 = src2.shift
+
+    append_row1_proc = Proc.new do
+      dest << row1
+      row1 = src1.shift
+    end
+
+    append_row2_proc = Proc.new do
+      dest << row2
+      row2 = src2.shift
+    end
+
+    while row1 || row2
+      if row1.nil?
+        append_row2_proc.call
+      elsif row2.nil?
+        append_row1_proc.call
+      elsif yield(row1, row2) <= 0
+        append_row1_proc.call
+      else
+        append_row2_proc.call
+      end
+    end
+
+    src1.close
+    src2.close
+    dest.close
+  end
+
+  def create_sorted_csv_part_files(batch_size, &block)
+    src = CSV.open(csv_file, 'rb', csv_options)
+
+    @headers = src.shift if has_headers
+
+    batch = []
+    create_batch_part_proc = Proc.new do
+      batch.sort!(&block)
+      @csv_part_files << "#{new_csv_file}.part.#{@csv_part_files.size}"
+      CSV.open(@csv_part_files.last, 'wb', csv_options) do |csv|
+        csv << @headers if @headers
+        batch.each { |row| csv << row }
+      end
+      batch = []
+    end
+
+    while (row = src.shift)
+      batch << row
+      create_batch_part_proc.call if batch.size >= batch_size
+    end
+
+    create_batch_part_proc.call if batch.size > 0
+
+    src.close
+  end
+
+  def merge_csv_part_files(&block)
+    file_merge_cnt = 0
+
+    while @csv_part_files.size > 1
+      file_merge_cnt += 1
+
+      csv_part_file1 = @csv_part_files.shift
+      csv_part_file2 = @csv_part_files.shift
+      @csv_part_files << "#{new_csv_file}.merge.#{file_merge_cnt}"
+
+      merge_sort_csv_files(csv_part_file1, csv_part_file2, @csv_part_files.last, &block)
+
+      File.unlink(csv_part_file1)
+      File.unlink(csv_part_file2)
+    end
+
+    FileUtils.mv(@csv_part_files.last, new_csv_file)
+  end
+end

data/script/console

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+$LOAD_PATH << File.expand_path('../lib', __dir__)
+require 'csv-utils'
+require 'irb'
+IRB.start(__FILE__)

metadata

@@ -1,33 +1,61 @@
 --- !ruby/object:Gem::Specification
 name: csv-utils
 version: !ruby/object:Gem::Version
-  version: 0.1.6
+  version: 0.2.3
 platform: ruby
 authors:
 - Doug Youch
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2019-07-30 00:00:00.000000000 Z
-dependencies: []
+date: 2020-07-08 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: inheritance-helper
+  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'
 description: Tools for debugging malformed CSV files
 email: dougyouch@gmail.com
 executables:
+- csv-change-eol
 - csv-find-error
 - csv-readline
 extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".ruby-gemset"
+- ".ruby-version"
+- Gemfile
+- Gemfile.lock
 - LICENSE
 - README.md
+- bin/csv-change-eol
 - bin/csv-find-error
 - bin/csv-readline
 - csv-utils.gemspec
+- lib/csv-utils.rb
+- lib/csv_utils/csv_extender.rb
+- lib/csv_utils/csv_options.rb
+- lib/csv_utils/csv_report.rb
+- lib/csv_utils/csv_row.rb
+- lib/csv_utils/csv_sort.rb
+- script/console
 homepage: https://github.com/dougyouch/csv-utils
-licenses: []
+licenses:
+- MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -42,8 +70,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.0.8
+signing_key:
 specification_version: 4
 summary: CSV Utils
 test_files: []