mylookup 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6d2aec87813030f47044c072473c3ee422ee1852
+  data.tar.gz: d3e9aeec030a2fe15ae538151f6f3d73736fa754
+SHA512:
+  metadata.gz: a868b087ef7d1014bf70053f05f9b0452010af16c43cf2c00dc5c4dd8a38bbeea3a1909be33eb941f2c6c18f7e9190c1ba52b644f46071090c24cd72e3ef375f
+  data.tar.gz: 4682498bb757620f6004a963e3cef126ae39cd33df0b701239015a0d3880220e617e7372ba15a5c465c87dae81277c75b3b170e7a0ae215c186ce266b03d3fe2

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "vlookup"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/mylookup

@@ -0,0 +1,30 @@
+require 'mylookup'
+require 'optparse'
+
+options = {}
+options_parser = OptionParser.new do |opts|
+    opts.on("-l", "--left LEFT", "Path to the Left Table") do |left|
+       options[:left] = left 
+    end
+    opts.on("-r", "--right RIGHT", "Path to the Right Table") do |right|
+       options[:right] = right 
+    end
+    opts.on("--lefton LEFTON", "Left Table's matching column") do |lefton|
+       options[:lefton] = lefton 
+    end
+    opts.on("--righton RIGHTON", "Right Table's matching column") do |righton|
+       options[:righton] = righton 
+    end
+    opts.on("--leftsheet LEFTSHEET", "Left Table's sheet name") do |leftsheet|
+       options[:leftsheet] = leftsheet 
+    end
+    opts.on("--rightsheet RIGHTSHEET", "Right Table's sheet name") do |rightsheet|
+       options[:rightsheet] = rightsheet 
+    end
+    opts.on("v", "--[no-]verbose", "Run verbosely") do |v|
+       options[:verbose] = v 
+    end
+end
+
+options_parser.parse!
+Mylookup.run(options)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/mylookup.rb

@@ -0,0 +1,156 @@
+require "mylookup/version"
+require "mylookup/validator"
+require "mylookup/processor"
+
+#= Entry point to startup the application
+module Mylookup
+
+    # Entry point method that starts the whole app
+    def self.run(opts)
+        validate_options opts 
+        l_src  = source_type opts[:left], opts[:leftsheet], :left
+        r_src = source_type opts[:right], opts[:rightsheet], :right
+        options = {
+            :left       => opts[:left],
+            :right      => opts[:right],
+            :lefton     => opts[:lefton],
+            :righton    => opts[:righton],
+            :leftsheet  => opts[:leftsheet],
+            :rightsheet => opts[:rightsheet],
+            :verbose    => opts[:verbose],
+            :l_src   => l_src, 
+            :r_src   => r_src,
+        }
+        validate_sources l_src, r_src, options
+        processor = Processor.new(options)
+        processor.process
+    end
+
+    # Health check up on options entered
+    def self.validate_options opts
+        unless opts[:left]
+            puts "[Error]: Left database/file name must be defined"
+            exit
+        else
+            unless opts[:leftsheet]
+                puts "[Warning]        : Left table name must be defined in case of source being MongoDB"
+                puts "[Warning--cont'd]: First/Default sheet is assumed to be Left Table/Sheet "
+            else
+                unless opts[:lefton]
+                    puts "[Error]: Left table/sheet matching column must be defined" 
+                    exit
+                end
+            end
+        end
+        unless opts[:right]
+            puts "[Error]: Right Database/File name must be defined"
+            exit
+        else
+            unless opts[:rightsheet]
+                puts "[Warning]        : Right Collection name must be defined in case of source being MongoDB"
+                puts "[Warning--cont'd]: First/Default Sheet is assumed to be Right Table/Sheet "
+            else
+                unless opts[:righton]
+                    puts "[Error]: Right table/sheet matching column must be defined" 
+                    exit
+                end
+            end
+        end
+        return true
+    end
+
+    # Validates the existence of fields/sheets of the left and right tables
+    def self.validate_sources l_src, r_src, ops
+        l_path, l_tbl, l_col = ops[:left], ops[:leftsheet], ops[:lefton]
+        r_path, r_tbl, r_col = ops[:right], ops[:rightsheet], ops[:righton]
+        if l_src == :excel
+            sht_comment, col_comment = validate_excel_attribs(l_path, l_tbl, l_col, :left)
+            puts "[Info]: Left Table => #{sht_comment} | #{col_comment}" if ops[:verbose]
+        elsif l_src == :mongo
+            db = File.split(l_path)[1]
+            valid, comment = validate_mongo_field_existence l_tbl, db, l_col
+            puts "[Info]: Left Table => #{comment}" if ops[:verbose]
+        end
+        if r_src == :excel
+            sht_comment, col_comment = validate_excel_attribs(r_path, r_tbl, r_col, :right)
+            puts "[Info]: Right Table => #{sht_comment} | #{col_comment}" if ops[:verbose]
+        elsif r_src == :mongo
+            db = File.split(r_path)[1]
+            valid, comment = validate_mongo_field_existence r_tbl, db, r_col
+            puts "[Info]: Right Table => #{comment}" if ops[:verbose]
+        end
+    end
+
+    # Validates the existence of sheet and matching column in an excel file
+    def self.validate_excel_attribs path, sht_name, col_name, src_type
+        valid, sht_comment = validate_excel_sheet_existence sht_name, path 
+        valid, col_comment = validate_excel_column_existence col_name, sht_name, path, src_type
+        return sht_comment, col_comment
+    end
+
+    # Validates and gives the type of the file whether it is an excel file or
+    # Mongo DB collection
+    def self.source_type file_name, sht, what_tbl
+        unless file_name
+            puts "[Error]: #{what_tbl.to_s.capitalize} Table's path must be given"
+            exit
+        else
+            valid, comment = validate_file_existence file_name, sht
+            comment =~ /mongodb/i ? :mongo : :excel
+        end
+    end
+
+    # Validates whether the given file does exist or not
+    def self.validate_file_existence path, sht
+        valid, comment = Validator::FileValidator.new(path, coll: sht).validate
+        unless valid
+            puts "[Error]: #{comment}"
+            exit
+        else
+            return valid, comment
+        end
+    end
+    
+    # Validates whether the given sheet does exist or not
+    def self.validate_excel_sheet_existence sht, path
+        sht_name = sht
+        sht_name = 0 unless sht_name
+        validator = Validator::ExcelAttribValidator.new(path, sht_name)
+        valid, comment = validator.validate_sheet
+        unless valid
+            puts "[Error]: #{comment}"
+            exit
+        else
+            return valid, comment
+        end
+    end
+
+    # Validates whether the given column does exist or not
+    def self.validate_excel_column_existence col, sht, path, what_tbl
+        unless col
+            puts "[Error]: #{what_tbl.to_s.capitalize} Table's matching column must be given" 
+            exit
+        end
+        validator = Validator::ExcelAttribValidator.new(path, sht)
+        valid, comment = validator.validate_column col
+        unless valid
+            puts "[Error]: #{comment}"
+            exit
+        else
+            return valid, comment
+        end
+    end
+
+    # Validates whether the given column does exist or not
+    def self.validate_mongo_field_existence coll_name, db_name, field
+        validator = Validator::MongoAttribValidator.new(coll_name, db_name, field)
+        valid, comment = validator.validate_field
+        unless valid
+            puts "[Error]: #{comment}"
+            exit
+        else
+            return valid, comment
+        end
+    end
+
+end

data/lib/mylookup/connector.rb

@@ -0,0 +1,66 @@
+#= Module containing connectors to databases
+
+module Connector
+
+    #== Defines MongoDB connection properties
+    class MongoConnector
+        require 'mongo'
+
+        attr_accessor :client, :coll, :coll_name, :db_name, :host, :port
+
+        def initialize(coll_name, db_name: 'ccsdm', host: 'localhost', port: '27017')
+            @coll_name, @db_name, @host, @port = coll_name, db_name, host, port
+            Mongo::Logger.logger.level = Logger::WARN
+            @conn_str = @host + ':' + @port
+            @client = Mongo::Client.new([@conn_str], :database => @db_name)
+            @coll = @client[@coll_name]
+        end
+
+        # Queries and returns number of documents in the collection
+        def recs qry
+            @coll.find(qry).count
+        end
+
+        def collection_exists?
+            recs({}) > 0
+        end
+
+        def field_exists? field
+            @coll.find({}).projection({ '_id' => 0 }).limit(1).collect { |doc| doc }[0].keys.include? field
+        end
+
+        public :recs, :collection_exists?
+    end
+
+    class ExcelReadConnector
+        require 'roo'
+        
+        def initialize(path)
+            @path = path
+            @wb = Roo::Excelx.new(@path) 
+            @sheets = @wb.sheets
+        end
+
+        def sheet_exists? sht_name
+            @sheets.include? sht_name
+        end
+
+        def column_exists? sht, col_name 
+            @wb.sheet(sht).row(1).include? col_name
+        end
+    end
+
+    class ExcelWriteConnector
+        require 'rubyXL'
+
+        attr_accessor :wb, :ws
+
+        def initialize(path)
+            @path = path
+            @wb = RubyXL::Workbook.new
+            @ws = @wb.worksheets[0]
+        end
+
+    end
+
+end 

data/lib/mylookup/processor.rb

@@ -0,0 +1,61 @@
+require 'mylookup/reader'
+require 'mylookup/writer'
+
+#= class containing the functionalities of handling the whole show
+class Processor
+
+    def initialize(opts)
+       @l_db, @l_tbl, @l_on = opts[:left], opts[:leftsheet], opts[:lefton]
+       @r_db, @r_tbl, @r_on = opts[:right], opts[:rightsheet], opts[:righton]
+       @verbose = opts[:verbose]
+       @l_src, @r_src = opts[:l_src], opts[:r_src] 
+       @l_reader, @r_reader = nil, nil
+       @l_data, @r_data, @matched, @unmatched = nil, nil, nil, nil
+       if @l_src == :excel
+           @l_reader = FileReader::Excel.new(@l_db, @l_tbl, @l_on)
+       else
+           @l_reader = FileReader::MongoDB.new(@l_on, @l_tbl, db_name: @l_db)
+       end
+       if @r_src == :excel
+           @r_reader = FileReader::Excel.new(@r_db, @r_tbl, @r_on)
+       else
+           @r_reader = FileReader::MongoDB.new(@r_on, @r_tbl, db_name: @r_db)
+       end
+    end
+
+    def process
+        puts "Processing initiating..." 
+        read_data
+        mylookup
+        write_unmatched unless @unmatched.empty?
+    end
+
+    def mylookup
+        puts "Executing mylookup..."
+        @unmatched = @l_data - @r_data
+        @matched = @l_data - @unmatched
+        puts "[Info]: Left Table size: #{@l_data.size} row(s)"
+        puts "Matched: #{@matched.size} row(s) Unmatched: #{@unmatched.size} row(s)"
+        puts "Matched: #{(@matched.size.to_f*100/@l_data.size.to_f).round(2)}%"
+    end
+
+    def write_unmatched
+        writer = FileWriter::Excel.new('unmatched.xlsx', @unmatched, @l_on) 
+        writer.write
+    end
+
+    def read_data
+        puts "Reading Left Table data..."
+        l_comment = @l_reader.read
+        @l_data = @l_reader.data
+        puts "Reading Right Table data..."
+        r_comment = @r_reader.read
+        @r_data = @r_reader.data
+        puts "[Info]: LEFT =>#{l_comment}"
+        puts "[Info]: RIGHT=>#{r_comment}"
+    end
+
+    private :read_data, :mylookup, :write_unmatched
+    public :process
+
+end

data/lib/mylookup/reader.rb

@@ -0,0 +1,61 @@
+require 'mylookup/connector'
+
+
+#= Contains funtionalities of reading data
+module FileReader
+
+    #== Contains the functionalities of reading Excel data
+    class Excel < Connector::ExcelReadConnector
+        attr_reader :data
+
+        def initialize(path, sht_name, col_name)
+            super(path)
+            @sht = @wb.sheet(sht_name)
+            @col = col_name
+            @data = nil
+        end
+
+        def read(match: {}, hide: {}, q_meth: :find)
+            aoa = @sht.parse(@col.to_sym => @col)
+            @data = aoa.collect { |item| item[@col.to_sym].to_s.downcase }
+            @data = @data.uniq
+            return "Excel Data contains #{@data.size} row(s)\nExcel First Record => #{@data[0]}"
+        end
+
+        public :read
+
+    end
+
+    #== Contains the reading functionalities of MongoDB data
+    class MongoDB < Connector::MongoConnector
+        attr_reader :data
+
+        def initialize(col_name, coll_name, db_name: 'ccsdm', host: 'localhost', port: '27017')
+            super(coll_name, db_name: db_name, host: host, port: port) 
+            @col = col_name
+            @data = [] 
+        end
+
+        def read(hide: { '_id' => 0 }, q_meth: :agg, match: {})
+            if q_meth == :find
+                @coll.find(match).projection(hide).each do |doc|
+                    @data = @data + [doc[@col].to_s.downcase]
+                end
+                @data = @data.uniq
+            elsif q_meth == :agg
+                qry = [
+                    { '$match'   => match },
+                    { '$group'   => { '_id' => { @col => '$' + @col } } },
+                    { '$project' => { '_id' => 0, @col => '$_id.' + @col } }
+                ]
+                @coll.aggregate(qry).each do |doc|
+                    @data = @data + [doc[@col].to_s.downcase]
+                end
+            end
+            return "Mongo Data contains #{@data.size} row(s)\nMongo First Record => #{@data[0]}"
+        end
+
+        public :read
+    end
+
+end 

data/lib/mylookup/validator.rb

@@ -0,0 +1,97 @@
+#= Validation module to checks all the base rules in input options
+
+require 'mylookup/connector'
+
+module Validator
+
+    #== Excel file attributes and properties validator
+    class ExcelAttribValidator < Connector::ExcelReadConnector
+
+        def initialize(path, sht)
+            super(path)
+            @sht = sht
+        end
+        
+        def validate_sheet
+            if sheet_exists? @sht
+                [true, "#{@sht} sheet in #{@path} exists"]
+            else
+                [false, "#{@sht} sheet in #{@path} DOES NOT exist!"]
+            end
+        end
+
+        def validate_column col_name
+            if column_exists? @sht, col_name 
+                [true, "#{col_name} column in #{@sht} sheet of #{@path} exists"]
+            else
+                [false, "#{col_name} column in #{@sht} sheet of #{@path} DOES NOT exist!"]
+            end
+        end
+
+        public :validate_sheet, :validate_column
+
+    end
+
+    #== MongoDB collection attributes and properties validator
+    class MongoAttribValidator < Connector::MongoConnector
+
+        def initialize(coll_name, db, field)
+            super(coll_name, db_name: db)
+            @field = field
+        end
+
+        def validate_field
+            if field_exists? @field
+                [true, "'#{@field}' field exists in '#{@coll_name}' collection"]
+            else
+                [false, "'#{@field}' field DOES NOT exist in '#{@coll_name}' collection"]
+            end
+        end
+
+        public :validate_field
+
+    end 
+
+    #== File Validator to validate the input paths of a file
+    class FileValidator
+
+        def initialize(path, coll: '')
+            @path = path
+            @coll = coll 
+        end
+
+        def validate
+            if is_excel_file
+                if excel_file_exists
+                    [true, "#{@path} does exist"]
+                else
+                    return [false, "#{@path} does not exist"]
+                end
+            else
+                if @path =~ /\./i
+                    return false, "#{@path} is neither an excel file nor a MongoDB collection" 
+                else
+                    db = File.split(@path)[1]
+                    mongo_conn = Connector::MongoConnector.new(@coll, db_name: db)
+                    unless mongo_conn.collection_exists?
+                        return [false, "'#{@path}' collection in MongoDB does not exist"]
+                    else
+                        return true, "'#{@path}' is a MongoDB collection"
+                    end
+                end
+            end
+        end
+
+        def excel_file_exists
+            File.file?(@path)
+        end
+
+        def is_excel_file
+            @path[-5, 5] == '.xlsx'
+        end
+
+        private :is_excel_file, :excel_file_exists
+
+    end
+
+end

data/lib/mylookup/version.rb

@@ -0,0 +1,3 @@
+module Mylookup
+  VERSION = "0.1.0"
+end

data/lib/mylookup/writer.rb

@@ -0,0 +1,43 @@
+require 'mylookup/connector'
+
+
+#=Contains functionalities of writing data
+module FileWriter
+
+    #== Contains the functionalities of writing data in Excel
+    class Excel < Connector::ExcelWriteConnector
+
+        def initialize(path, data, header)
+            super(path)
+            @data = data
+            @header = header
+        end
+
+        def write
+            puts "Writing Data in Excel"
+            begin
+                write_header
+                write_data
+            rescue StandardError => err
+                puts "[Error]: Error occured while writing in Excel!!!"
+                puts err
+            end
+        end
+
+        def write_header
+            @ws.add_cell(0, 0, @header)
+        end
+
+        def write_data
+            @data.each_with_index do |d, i|
+                @ws.add_cell(i+1, 0, d.to_s.upcase)
+            end
+            @wb.write(@path)
+        end
+
+        private :write_header, :write_data
+        public :write
+    end
+
+end
+

metadata

@@ -0,0 +1,159 @@
+--- !ruby/object:Gem::Specification
+name: mylookup
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- jeyaraj
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-08-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+- !ruby/object:Gem::Dependency
+  name: rubyXL
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.3.26
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.3.26
+- !ruby/object:Gem::Dependency
+  name: roo
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.7.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.7.0
+- !ruby/object:Gem::Dependency
+  name: mongo
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.4.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.4.1
+description: Does mylookup on Excel file or MongoDB collections
+email:
+- jeyaraj.durairaj@gmail.com
+executables:
+- console
+- mylookup
+- setup
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/console
+- bin/mylookup
+- bin/setup
+- lib/mylookup.rb
+- lib/mylookup/connector.rb
+- lib/mylookup/processor.rb
+- lib/mylookup/reader.rb
+- lib/mylookup/validator.rb
+- lib/mylookup/version.rb
+- lib/mylookup/writer.rb
+homepage: https://github.com/jeydurai/mylookup
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.12
+signing_key: 
+specification_version: 4
+summary: Simulates Excel's Mylookup function
+test_files: []