csv-utils 0.2.1 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '083044bd714b955ff9d5f6a44cf6d4cb3344cf7f649b105d81a94b3ddb1c9425'
-  data.tar.gz: 5fa1cd9acacf10c275a23176e36722e189f8e6d8a85e1bfc7faf18eb45a1ca31
+  metadata.gz: 7b3f6bdded232bf3be2009d4bbb5ab99e083cd9f48dff5fabe89324f5217550a
+  data.tar.gz: 86b130f177d173a74bc1611c5677cc6bad5053e953a1a5fabfeabee494e372c8
 SHA512:
-  metadata.gz: de36fb6c80a68b33c92f3c943a665c419ac1287f5b4b2901c1a60f45964d4b13c2199f53e8dd779b2947d6c86439fa1b1b781cc5ba2225656b2d8b50f690e4cc
-  data.tar.gz: 0a6b5a9301f2386c2ad5bf3009ca77f949a92510ebb606844a1e6bf9fcc573f524966e68d1d8cec7db9778be3c93fb58a006fee9008e531c53a2c5391af6c0c3
+  metadata.gz: dd0a299cbe4b153f122d605bbb1b2ab08726194d58010e909090048f1cef0e384d08c8a3a59683b8108c1dc3766deacac46a9063af35e57502f6fe3c92b855ff
+  data.tar.gz: e4233e0c38338d24a6105d465745092146a65e03f297442fabada13ecf380db70740196726ec2d40a8f92828b6cfbc6945c0274701091cb2687af549126e34fa

data/bin/csv-validator

@@ -0,0 +1,60 @@
+#!/usr/bin/env ruby
+
+require 'csv'
+begin
+  require 'rchardet'
+rescue LoadError
+  $stderr.puts 'gem install rchardet'
+  exit 1
+end
+
+def utf8?(str)
+  str
+    .force_encoding('utf-8')
+    .valid_encoding?
+end
+
+def convert_to_utf8(str, current_encoding)
+  str.force_encoding(current_encoding)
+  return nil unless str.valid_encoding?
+
+  str.encode('utf-8')
+end
+
+def detect_encoding(col)
+  CharDet.detect(col)['encoding']
+end
+
+csv = CSV.open(ARGV[0], 'rb')
+out = CSV.open(ARGV[1], 'wb') if ARGV[1]
+
+headers = csv.shift
+out << headers if out
+csv_lineno = 1
+
+while (row = csv.shift)
+  csv_lineno += 1
+
+  unless row.size == headers.size
+    $stderr.puts "row(#{csv_lineno}): invalid number of columns, expected #{headers.size} got #{row.size}"
+  end
+
+  converted = false
+  row.each_with_index do |col, idx|
+    next if utf8?(col)
+
+    $stderr.puts "row(#{csv_lineno}),col(#{idx + 1}): none UTF-8 characters found in \"#{col}\""
+    if (col_utf8_encoded = convert_to_utf8(col, detect_encoding(col)))
+      converted = true
+      puts "row(#{csv_lineno}),col(#{idx + 1}): converted to UTF-8 from #{detect_encoding(col)} \"#{col_utf8_encoded}\""
+      row[idx] = col_utf8_encoded
+    else
+      $stderr.puts "row(#{csv_lineno}),col(#{idx + 1}): unknown character encoding"
+    end
+  end
+
+  out << row if out && converted
+end
+
+csv.close
+out.close if out

data/csv-utils.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name        = 'csv-utils'
-  s.version     = '0.2.1'
+  s.version     = '0.3.2'
   s.licenses    = ['MIT']
   s.summary     = 'CSV Utils'
   s.description = 'Tools for debugging malformed CSV files'

data/lib/csv-utils.rb

@@ -6,4 +6,7 @@ module CSVUtils
   autoload :CSVOptions, 'csv_utils/csv_options'
   autoload :CSVReport, 'csv_utils/csv_report'
   autoload :CSVRow, 'csv_utils/csv_row'
+  autoload :CSVSort, 'csv_utils/csv_sort'
+  autoload :CSVTransformer, 'csv_utils/csv_transformer'
+  autoload :CSVWrapper, 'csv_utils/csv_wrapper'
 end

data/lib/csv_utils/csv_extender.rb

@@ -1,20 +1,15 @@
 # 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
+  def initialize(src_csv, dest_csv, csv_options = {})
+    @src_csv = CSVUtils::CSVWrapper.new(src_csv, 'rb', csv_options)
+    @dest_csv = CSVUtils::CSVWrapper.new(dest_csv, 'wb', csv_options)
   end
 
   def append(additional_headers)
     process(additional_headers) do |current_headers|
-      while (row = src.shift)
+      while (row = @src_csv.shift)
         additional_columns = yield row, current_headers
-        dest << (row + additional_columns)
+        @dest_csv << (row + additional_columns)
       end
     end
   end
@@ -27,13 +22,13 @@ class CSVUtils::CSVExtender
         additional_rows = yield batch, current_headers
 
         batch.each_with_index do |row, idx|
-          dest << (row + additional_rows[idx])
+          @dest_csv << (row + additional_rows[idx])
         end
 
         batch = []
       end
 
-      while (row = src.shift)
+      while (row = @src_csv.shift)
         batch << row
 
         process_batch_proc.call if batch.size >= batch_size
@@ -43,6 +38,8 @@ class CSVUtils::CSVExtender
     end
   end
 
+  private
+
   def process(additional_headers)
     current_headers = append_headers(additional_headers)
 
@@ -51,26 +48,16 @@ class CSVUtils::CSVExtender
     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
+    @src_csv.close
+    @dest_csv.close
   end
 
-  private
-
   def append_headers(additional_headers)
     return nil unless additional_headers
 
-    current_headers = src.shift
-    dest << (current_headers + additional_headers)
+    current_headers = @src_csv.shift
+    @dest_csv << (current_headers + additional_headers)
     current_headers
   end
 end

data/lib/csv_utils/csv_report.rb

@@ -4,7 +4,7 @@ module CSVUtils
     attr_reader :csv,
                 :must_close
 
-    def initialize(csv, csv_options = {}, &block)
+    def initialize(csv, headers = nil, csv_options = {}, &block)
       @csv =
         if csv.is_a?(String)
           @must_close = true
@@ -15,10 +15,11 @@ module CSVUtils
           csv
         end
 
-      generate(&block) if block
+      generate(headers, &block) if block
     end
 
-    def generate
+    def generate(headers = nil)
+      add_headers(headers) if headers
       yield self
       @csv.close if @must_close
     end

data/lib/csv_utils/csv_row.rb

@@ -23,10 +23,16 @@ module CSVUtils
 
         add_value_to_class_method(:csv_columns, header => options)
       end
-    end
 
-    def csv_headers
-      self.class.csv_columns.values.map { |column_options| csv_column_header(column_options) }
+      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
@@ -34,12 +40,12 @@ module CSVUtils
     end
     alias_method :to_a, :csv_row
 
-    private
-
-    def csv_column_header(column_options)
-      column_options[:header]
+    def csv_headers
+      self.class.csv_headers
     end
 
+    private
+
     def csv_column_value(column_options)
       if column_options[:proc]
         instance_eval(&column_options[:proc])

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/lib/csv_utils/csv_transformer.rb

@@ -0,0 +1,119 @@
+# Transforms a CSV given a series of steps
+class CSVUtils::CSVTransformer
+  attr_reader :headers
+
+  def initialize(src_csv, dest_csv, csv_options = {})
+    @src_csv = CSVUtils::CSVWrapper.new(src_csv, 'rb', csv_options)
+    @dest_csv = CSVUtils::CSVWrapper.new(dest_csv, 'wb', csv_options)
+  end
+
+  def read_headers
+    @headers = @src_csv.shift
+    self
+  end
+
+  def additional_data(&block)
+    steps << [:additional_data, @headers, block]
+    self
+  end
+
+  def select(&block)
+    steps << [:select, @headers, block]
+    self
+  end
+
+  def reject(&block)
+    steps << [:reject, @headers, block]
+    self
+  end
+
+  def map(new_headers, &block)
+    steps << [:map, @headers, block]
+    @headers = new_headers
+    self
+  end
+
+  def append(additional_headers, &block)
+    steps << [:append, @headers, block]
+
+    if additional_headers
+      @headers += additional_headers
+    else
+      @headers = nil
+    end
+
+    self
+  end
+
+  def each(&block)
+    steps << [:each, @headers, block]
+    self
+  end
+
+  def set_headers(headers)
+    @headers = headers
+    self
+  end
+
+  def process(batch_size = 10_000, &block)
+    batch = []
+
+    @dest_csv << @headers if @headers
+
+    steps_proc = Proc.new do
+      steps.each do |step_type, current_headers, proc|
+        batch = process_step(step_type, current_headers, batch, &proc)
+      end
+
+      batch.each { |row| @dest_csv << row }
+
+      batch = []
+    end
+                   
+    while (row = @src_csv.shift)
+      batch << row
+      steps_proc.call if batch.size >= batch_size
+    end
+
+    steps_proc.call if batch.size > 0
+
+    @src_csv.close
+    @dest_csv.close
+  end
+
+  private
+
+  def steps
+    @steps ||= []
+  end
+
+
+  def process_step(step_type, current_headers, batch, &block)
+    case step_type
+    when :select
+      batch.select! do |row|
+        block.call row, current_headers, @additional_data
+      end
+    when :reject
+      batch.reject! do |row|
+        block.call row, current_headers, @additional_data
+      end
+    when :map
+      batch.map! do |row|
+        block.call row, current_headers, @additional_data
+      end
+    when :append
+      batch.map! do |row|
+        row + block.call(row, current_headers, @additional_data)
+      end
+    when :additional_data
+      @additional_data = block.call(batch, current_headers)
+    when :each
+      batch.each do |row|
+        block.call(row, current_headers, @additional_data)
+      end
+    end
+
+    batch
+  end
+end

data/lib/csv_utils/csv_wrapper.rb

@@ -0,0 +1,47 @@
+# Wraps a CSV object, if wrapper opens the csv file it will close it
+class CSVUtils::CSVWrapper
+  attr_reader :csv
+
+  def initialize(csv, mode, csv_options)
+    open(csv, mode, csv_options)
+  end
+
+  def self.open(file, mode, csv_options = {})
+    csv = new(file, mode, csv_options)
+
+    if block_given?
+      yield csv
+      csv.close
+    else
+      csv
+    end
+  end
+
+  def open(csv, mode, csv_options)
+    if csv.is_a?(String)
+      @close_when_done = true
+      @csv = CSV.open(csv, mode, csv_options)
+    else
+      @close_when_done = false
+      @csv = csv
+    end
+  end
+
+  def <<(row)
+    csv << row
+  end
+
+  def shift
+    csv.shift
+  end
+
+  def close
+    csv.close if close_when_done?
+  end
+
+  private
+
+  def close_when_done?
+    @close_when_done
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csv-utils
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.2
 platform: ruby
 authors:
 - Doug Youch
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-07-04 00:00:00.000000000 Z
+date: 2020-07-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: inheritance-helper
@@ -30,6 +30,7 @@ executables:
 - csv-change-eol
 - csv-find-error
 - csv-readline
+- csv-validator
 extensions: []
 extra_rdoc_files: []
 files:
@@ -43,12 +44,16 @@ files:
 - bin/csv-change-eol
 - bin/csv-find-error
 - bin/csv-readline
+- bin/csv-validator
 - 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
+- lib/csv_utils/csv_transformer.rb
+- lib/csv_utils/csv_wrapper.rb
 - script/console
 homepage: https://github.com/dougyouch/csv-utils
 licenses: