csv-import-analyzer 0.0.6 → 0.0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 40f1ef2bfdbd829eaa64dfa88f360ee722d60228
-  data.tar.gz: c0beeb4085de093f7d41b79e3688cfe36a2b6811
+  metadata.gz: 7ff8951a5c2ea050bfbbebf39617d1d735a4f6ea
+  data.tar.gz: f00f91d6123a435c54a5585a7a3d014cae46c67b
 SHA512:
-  metadata.gz: 94a4839a40f22301b36776b6155855f5bc49a162f3f6c3d9706c46b1105ecf4598c65969d76bc4fade7f1a2d9250fc32fe4fb3ce121657f18fd661bf71cf9ca5
-  data.tar.gz: e359dd8f516b2a96d3f799477975c2006639229ee40a9a9cccf18cca8893e16217c6f7ef1349df4ddd448dbbb7d2964c57854a5d7094808ab81b14fdebe8a4cf
+  metadata.gz: 474adc7c9f7e0946c2c86a6c14395569c9574fd4865bc907f43614df39386336959f3cc1b3b71e51a7fa6d2844e8426bf8be22475345a5bceb153cf7473662e5
+  data.tar.gz: b87c638ac9a94fee9fcc357566c50517db1dd30e3bf3c3d158eab05d128d4e17f2965f1a1a37472e7846c807dd4030805e4ac3ea8f6bf8c543327ab02142d53a

data/bin/CsvImportAnalyzer

@@ -0,0 +1,59 @@
+#!/usr/bin/env ruby
+require 'optparse'
+require 'csv-import-analyzer'
+
+# Default options for the executable
+options = {:input => nil, :metadata_output => nil, :processed_input => nil, :unique => 5, 
+  :chunk => 200, :database => [:mysql], :quote_convert => true, :replace_nulls => true, :check_bounds => true}
+
+# Parse the options using optparse
+# prases the input given through command line and set to the respective option
+# E.g. CsvImportAnalyzer -i "test.csv"
+#      ==> options[:input] = "test.csv"
+parser = OptionParser.new do |opts|
+      opts.banner = "Usage: CsvImportAnalyzer [options]"
+
+      opts.on('-i', '--input filename', 'Input file name') do |input|
+        options[:input] = input  # todo: be able to handle files not in the current directory
+      end
+      opts.on('-m', '--output-structure filename', 'Output the metadata of file') do |metadata_output|
+        options[:metadata_output] = metadata_output
+      end
+      opts.on('-o', '--output-cleaned filename', 'Output the cleaned csv file name, defaults to current driectory proccessed_(filename).csv ') do |processed_input|
+        options[:processed_input] = processed_input
+      end
+      opts.on('-u', '--unique unique', 'No of Unique values you need, default: 10') do |unique|
+        options[:unique] = unique
+      end
+      opts.on('-c', '--chunk size', 'Chunk size for predecting datatypes, default: 200') do |chunk|
+        options[:chunk] = chunk
+      end
+      # opts.on('-s', '--skip lines', 'skip the number of lines at the top, default: 0') do |skip|
+      #   options[:skip] = skip
+      # end
+      opts.on('-d', '--database type', 'MySQL or Postgres, Options: M or P, default: nil(print nothing)') do |database_type|
+        options[:database] = [database_type.upcase]
+      end
+      opts.on('-q', '--quotes conversion', 'Convert single quotes to double quotes, options: true or false, default: true') do |quote_convert|
+        options[:quote_convert] = quote_convert.upcase
+      end
+      opts.on('-r', '--replace nulls', 'replace empty, Null\'s, \N, NAN with NULL, options: true or false, default: true') do |replace_nulls|
+        options[:replace_nulls] = replace_nulls.upcase
+      end
+      opts.on('-h', '--help', 'Displays Help') do
+        puts opts
+        exit
+      end
+    end
+parser.parse!
+
+# Input validations
+# Make sure a filename is given to the executable
+filename = nil
+if options[:input] == nil
+  print " Requires a valid input file name! \n"
+  puts parser
+  exit
+end 
+
+puts CsvImportAnalyzer.process(options[:input], options)

data/csv-import-analyzer.gemspec

@@ -23,6 +23,6 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "pry", "~> 0.10"
   spec.add_development_dependency "rspec", "~> 3.0"
   spec.add_development_dependency "simplecov", "~> 0.9"
-  
+
   spec.add_runtime_dependency "smarter_csv", "~> 1.0", ">= 1.0.17"
 end

data/lib/csv-import-analyzer.rb

@@ -11,6 +11,7 @@ module CsvImportAnalyzer
   # returns FileNotFound if given file is invalid
   ###
   def process(filename, options = {})
+    return ArgumentError.new("A valid file needed to process") if filename.nil?
     if File::exist?(filename)
       CsvImportAnalyzer::CsvSanitizer.new().process(File.absolute_path(filename), options)
     else

data/lib/csv-import-analyzer/csv_sanitizer.rb

@@ -69,7 +69,7 @@ module CsvImportAnalyzer
       {
         :metadata_output => nil,      # To be set if metadata needs to be printed to a file
         :processed_input => nil,      # To be set if processed input is needed
-        :unique => 2,                 # Threshold for number of defaults values that needs to identified
+        :unique => 5,                 # Threshold for number of defaults values that needs to identified
         :check_bounds => true,        # Option to check for min - max bounds for each column [true => find the bounds]
         :datatype_analysis => 200,    # Number of rows to be sampled for datatype analysis
         :chunk => 200,                # Chunk size (no of rows) that needs to processed in-memory [Important not to load entire file into memory]

data/lib/csv-import-analyzer/version.rb

@@ -1,5 +1,5 @@
 module CsvImportAnalyzer
   module Version
-    VERSION = "0.0.6"
+    VERSION = "0.0.7"
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csv-import-analyzer
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.7
 platform: ruby
 authors:
 - Avinash Vallabhaneni
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-30 00:00:00.000000000 Z
+date: 2014-11-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -104,7 +104,8 @@ description: Santize large csv files and help in predicting datatypes including
   max values for easy import to SQL
 email:
 - avinash.vallab@gmail.com
-executables: []
+executables:
+- CsvImportAnalyzer
 extensions: []
 extra_rdoc_files: []
 files:
@@ -114,6 +115,7 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- bin/CsvImportAnalyzer
 - csv-import-analyzer.gemspec
 - lib/csv-import-analyzer.rb
 - lib/csv-import-analyzer/analyzer/csv_check_bounds.rb