csv_madness 0.0.6 → 0.0.10

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    ZGQ4MTA4MGJlYjA1MzIwOTU4NzEyODViMmFhYmYwMTA2YjQzMmY2MQ==
-  data.tar.gz: !binary |-
-    ZTRkOWNjMjYyNTNmMjA3YzMwZThlMzAyOWRjMTM0ZWYwMTQ3NWE0MA==
+SHA256:
+  metadata.gz: 63380347571236804849e35c32c5463efc6e71151e992a3e3f18f8d2673fc110
+  data.tar.gz: 8c58382266af7f1091a80dc89eb6900a4efb8a5f956fe5801aa77ea5d5e4f05f
 SHA512:
-  metadata.gz: !binary |-
-    MzAzNTJmNjU5YmM2NjUxODY4YjRkMDkwMDc5NTQxOWIxZWRjMjRmYmU1YzFh
-    Zjg2ZjA5ZGZlZTEyNjg1NjFmNzE5NzY3NTFhNzY3ZTIyNDFhZGIzZTEzOGI5
-    ZDUzMjZjYjJkODdiM2M1M2JiMjZiMGNlMTViNWE2Yzk1ZjU1YjI=
-  data.tar.gz: !binary |-
-    MjJlYzI1YTQxMzU4NzA0MmVlNzFkYzVmNDE3NjYyMDM5YmI3Y2JmMmQyOWZk
-    OGQ0NzFhODUyMzRjNWI3ZWRlZDQ3YmQ0NGU0Zjc4ZDFmNWRkMWY4MDc4OTdi
-    YjkwY2U1MGY3MmVhNTY2NTYzYzc1ZDViZWViMTg0OTE5OGU1ZTE=
+  metadata.gz: 3b8ca366e680bf629fbb081145a8b254e5a121102b0772a40095893e06bc1f46f1f081c64cfa60efb1cbe69e633685c65b406795601c237157a8af63a5ce4d3c
+  data.tar.gz: 298b6b68d6bed7254ae7177b6fd24f8bfccb765435df5fbd5e9bfabb618db3bf386c276c741ca5fbab2bd9d8168c011010579ccca3bbfe7af0a19a2cffe163ad

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/CHANGELOG.markdown

@@ -1,6 +1,10 @@
 Changelog
 =========
 
+0.0.10
+------
+
+
 0.0.6
 -----
 

data/Gemfile

@@ -7,14 +7,8 @@ source "http://rubygems.org"
 # Include everything needed to run rake, tests, features, etc.
 
 group :development do
-  # gem "shoulda", ">= 3.5"
-  # gem "rdoc", "~> 3.12"
-  # gem "bundler", "~> 1.5"
-  # gem "jeweler", "~> 2"
   gem "fun_with_testing"
-  # gem "debugger"
 end
 
-# gem "fun_with_files", "~> 0.0", ">= 0.0.7"
-# gem "fun_with_version_strings", "~> 0.0"
-gem 'fun_with_gems', '~> 0.0', ">= 0.0.2"
+gem 'fun_with_gems', '~> 0.0', ">= 0.0.6"
+gem 'csv'     # removed from core

data/README.rdoc

@@ -7,62 +7,62 @@ CSV Madness tries to remove what little pain is left from Ruby's CSV class.  Loa
 
 == Why should I use it?
 
-I like brief code and I cannot lie.  
+I like brief code and I cannot lie.
 
 
 == Examples
 
 CsvMadness makes some assumptions about your CSV file.  It does assume headers, for example.  
 
-The simplest case is when your columns are nicely named.  For example, if you have a csv file named <tt>~/data/people.csv</tt>:
+The simplest case is when your columns are nicely named.  For example, if you have a csv file named `~/data/people.csv`:
+
+    "id","fname","lname","age","born"
+    "1","Mary","Moore","27","1986-04-08 15:06:10"
+    "2","Bill","Paxton","39","1974-02-22"
+    "3","Charles","Darwin","72",""
+    "4","Chuck","Norris","57","1901-03-02"
 
-<code>
-"id","fname","lname","age","born"
-"1","Mary","Moore","27","1986-04-08 15:06:10"
-"2","Bill","Paxton","39","1974-02-22"
-"3","Charles","Darwin","72",""
-"4","Chuck","Norris","57","1901-03-02"
-</code>
 
 ... then you can write code like so:
 
-'''require 'csv_madness'
-sheet = CsvMadness.load( "~/data/people.csv" )
-sheet.columns   # => [:id, :fname, :lname, :age, :born]
-sheet.records.map(&:id) # => ["1", "2", "3", "4"]
-sheet.set_column_type(:id, :float)
-sheet.records.map(&:id) # => [1.0, 2.0, 3.0, 4.0]
-sheet.alter_column(:id) do |id|
-  id + rand() - 0.5
-end    
+    require 'csv_madness'
+    
+    sheet = CsvMadness.load( "~/data/people.csv" )
+    sheet.columns   # => [:id, :fname, :lname, :age, :born]
+    sheet.records.map(&:id) # => ["1", "2", "3", "4"]
+    sheet.set_column_type(:id, :float)
+    sheet.records.map(&:id) # => [1.0, 2.0, 3.0, 4.0]
+    sheet.alter_column(:id) do |id|
+      id + rand() - 0.5
+    end    
+
+    sheet.records.map(&:id) # => [0.7186, 2.30134, 2.90132, 4.30124]  (your results may vary)
+    mary = sheet[0]
 
-sheet.records.map(&:id) # => [0.7186, 2.30134, 2.90132, 4.30124]  (your results may vary)
-mary = sheet[0]
+    "#{mary.lname}, #{mary.fname} (#{mary.id})"  # => "Moore, Mary (1)"
 
-"#{mary.lname}, #{mary.fname} (#{mary.id})"  # => "Moore, Mary (1)"
-'''
 
 If you're not satisfied with your column names, you can send your own, in the column order.  An index can also be provided, which will allow you to use <tt>.fetch()</tt> to find specific records quickly:
 
-'''require 'csv_madness'
-sheet = CsvMadness.load( "~/data/people.csv", 
-                         columns: [:uid, :first_name, :last_name, :years_on_planet, :birthday],
-                         index: :uid )
+    require 'csv_madness'
+    sheet = CsvMadness.load( "~/data/people.csv", 
+                             columns: [:uid, :first_name, :last_name, :years_on_planet, :birthday],
+                             index: :uid )
+
+    sheet.fetch("2").years_on_planet      # => "39"
 
-sheet.fetch("2").years_on_planet      # => "39"
-'''
 
 **Note:** you can provide multiple indexes as an array.  However many columns you index, you'll run into trouble if the index isn't unique for each record.  (that may change in the future)
 
 
 It's useful to clean up your files.  Say you have:
 
-""""id","fname","lname","age","  born  "
-"1 ","Mary  ","Moore","27","1986-04-08 15:06:10"
-"","  Bill ","Paxton",,"  Feb. 22, 1974  "
-,"Charles "," Darwin","72 ",
-"4","Chuck","Norris",,"  2 March 1901   "
-"""
+    "id","fname","lname","age","  born  "
+    "1 ","Mary  ","Moore","27","1986-04-08 15:06:10"
+    "","  Bill ","Paxton",,"  Feb. 22, 1974  "
+    "3","Charles "," Darwin","72 "
+    "4","Chuck","Norris",,"  2 March 1901   "
+
 
 Ick.  Missing IDs, inconsistent date formats, leading and trailing whitespace...  We can fix this.
 
@@ -163,27 +163,35 @@ You could do something similar to clean and standardize phone numbers, detect an
 
 You have an array of objects.  You want to write them to a spreadsheet.
 
-```ruby
     sb = CsvMadness::Builder.new do |sb|
       sb.column( :id )
-      sb.column( :addressee,              "addressee_custom" )
-      sb.column( :street_address,         "primary_address.street_address" )
-      sb.column( :supplemental_address_1, "primary_address.supplemental_address_1" )
-      sb.column( :city,                   "primary_address.city" )
-      sb.column( :state_code,             "primary_address.state_code" )
-      sb.column( :formatted_zip,          "primary_address.formatted_zip" )
-      sb.column( :phone,                  "phones.first.phone" )
-      sb.column( :leader,                 "congregation_fieldset.congregation_leader" )
-      sb.column( :denomination,           "congregation_fieldset.denomination" )
-      sb.column( :email,                  "emails.first.email" )
+      sb.column( :addressee,      "addressee_custom" )
+      sb.column( :street,         "primary_address.street_address" )
+      sb.column( :street2,        "primary_address.supplemental_address_1" )
+      sb.column( :city,           "primary_address.city" )
+      sb.column( :state_code,     "primary_address.state_code" )
+      sb.column( :formatted_zip,  "primary_address.formatted_zip" )
+      sb.column( :phone,          "phones.first.phone" )
+      sb.column( :contact,        "congregation_fieldset.congregation_leader" )
+      sb.column( :email,          "emails.first.email" )
+      sb.column( :greeting ) do |contact|
+        if contact.business?
+          "To our friends at #{contact.organization_name},"
+        elsif contact.person?
+          "Dear #{ contact.title } #{ contact.last_name }"
+        end
+      end
+      
     end
 
     sheet = sb.build( [address1, address2, address3...] )
-```
+    
+    outfile = FunWith::Files::FilePath.home.join( "Documents", "addresses", "address_records.csv" )
+    sheet.write_to_file( outfile )
 
 === Documentation is incomplete ===
 
-There are lots of other features, but they'll take time to test and document.
+There are other features, but they'll take time to test and document.
 
 
 

data/Rakefile

@@ -1,22 +1,13 @@
 # encoding: utf-8
+require 'fun_with_gems'
+require_relative File.join( "lib", "csv_madness" )
 
-require 'rubygems'
-require 'bundler'
+self.extend( FunWith::Gems::Rakefile )
+rakefile_setup CsvMadness
 
-begin
-  Bundler.setup(:default, :development)
-rescue Bundler::BundlerError => e
-  $stderr.puts e.message
-  $stderr.puts "Run `bundle install` to install missing gems"
-  exit e.status_code
-end
-
-require 'rake'
-
-require 'jeweler'
-
-Jeweler::Tasks.new do |gem|
-  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+gem_specification do |gem|
+# gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+# dependencies defined in Gemfile
   gem.name = "csv_madness"
   gem.homepage = "http://github.com/darthschmoo/csv_madness"
   gem.license = "MIT"
@@ -24,39 +15,9 @@ Jeweler::Tasks.new do |gem|
   gem.description = "CSV Madness removes what little pain is left from Ruby's CSV class.  Load a CSV file, and get back an array of objects with customizable getter/setter methods."
   gem.email = "keeputahweird@gmail.com"
   gem.authors = ["Bryce Anderson"]
-  
-  # dependencies defined in Gemfile
-  gem.files = Dir.glob( File.join( ".", "lib", "**", "*.rb" ) ) + 
-              Dir.glob( File.join( ".", "test", "**", "*" ) ) +
-              %w( Gemfile Rakefile LICENSE.txt README.rdoc VERSION CHANGELOG.markdown )
-    
-end
 
-Jeweler::RubygemsDotOrgTasks.new
-
-require 'rake/testtask'
-Rake::TestTask.new(:test) do |test|
-  test.libs << 'lib' << 'test'
-  test.pattern = 'test/**/test_*.rb'
-  test.verbose = true
+  # dependencies defined in Gemfile
+  add_specification_files( gem, :default )
 end
 
-# require 'rcov/rcovtask'
-# Rcov::RcovTask.new do |test|
-#   test.libs << 'test'
-#   test.pattern = 'test/**/test_*.rb'
-#   test.verbose = true
-#   test.rcov_opts << '--exclude "gems/*"'
-# end
-
-task :default => :test
-
-require 'rdoc/task'
-Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ""
-
-  rdoc.rdoc_dir = 'rdoc'
-  rdoc.title = "csv_madness #{version}"
-  rdoc.rdoc_files.include('README*')
-  rdoc.rdoc_files.include('lib/**/*.rb')
-end
+setup_gem_boilerplate

data/VERSION

@@ -1 +1 @@
-0.0.6
+0.0.10

data/lib/csv_madness/builder.rb

@@ -1,13 +1,18 @@
 module CsvMadness
   class Builder
+    attr_accessor :label
+    
     def initialize( &block )
       @columns = {}
       @column_syms = []
+      @column_counters  = {}
+
       @module = Module.new   # for extending
       self.extend( @module )
-      yield self
+      yield self if block_given?
     end
 
+
     def column( sym, method_path = nil, &block )
       warn( "#{sym} already defined. Overwriting." ) if @column_syms.include?( sym )
       
@@ -20,6 +25,24 @@ module CsvMadness
                         Proc.new(&sym)
                       end
     end
+    
+    def column_names
+      @column_syms
+    end
+    
+    def constant_column( sym, const )
+      cproc = Utils::ConstProc.proc_for( const )
+      column( sym, &cproc )
+    end
+    
+    def blank_column( sym )
+      constant_column( sym, nil )
+    end
+    
+    def counter_column( sym, initial_value = 0 )
+      column( sym, &Utils::CounterProc.counter( initial_value ) )
+    end
+      
 
     # Three :on_error values:
     #    :print  => Put an error message in the cell instead of a value
@@ -27,23 +50,34 @@ module CsvMadness
     #    :ignore => Hand back an empty cell
     # 
     # Although ideally it should be configurable by column...   
-    def build( objects, opts = { :on_error => :print } )
+    def build( objects, opts = {} )
+      @progress_mode = choose_progress_mode( opts[:progress] )
+      debugger unless defined?( @show_progress )
+      
+      @on_error      = opts.fetch(:on_error){ :print }
+      @verbose       = opts.fetch(:verbose){ false }
+      
       spreadsheet = CsvMadness::Sheet.new( @column_syms )
+      
+      @objects = objects
+      @objects = @objects.records if @objects.is_a?( CsvMadness::Sheet )
 
-      for object in objects
-        STDOUT << "."
+      for object in @objects
         record = {}
         for sym in @column_syms
           record[sym] = build_cell( object, sym, opts )
         end
-
+        
         spreadsheet.add_record( record )  # hash form
+        show_progress
       end
+      
+      _reset_counter_columns
 
       spreadsheet
     end
 
-    def build_cell( object, sym, opts = { :on_error => :print } )
+    def build_cell( object, sym, opts = {} )
       column = @columns[sym]
 
       case column
@@ -52,10 +86,12 @@ module CsvMadness
       when Proc
         build_cell_by_proc( object, column, opts )
       else
-        "no idea what to do"
+        debugger
+        "no idea what to do with #{column.inspect} (#{column.class})"
       end
     end
 
+    # ?????
     def def( method_name, &block )
       @module.send( :define_method, method_name, &block )
     end
@@ -63,7 +99,7 @@ module CsvMadness
     protected
     def build_cell_by_pathstring( object, str, opts )
       handle_cell_build_error( :build_cell_by_pathstring, opts ) do
-        for method in str.split(".").map(&:to_sym)
+        for method in str.split(".")
           object = object.send(method)
         end
 
@@ -82,9 +118,9 @@ module CsvMadness
         yield
       end
     rescue Exception => e
-      case opts[:on_error]
+      case @on_error
       when nil, :print
-        puts "error #{e.message} #{caller}" if opts[:verbose]
+        puts "error #{e.message} #{caller}" if @verbose
         "ERROR: #{e.message} (#{caller}())"
       when :raise
         puts "Re-raisinge error #{e.message}.  Set opts[:on_error] to :print or :ignore if you want Builder to continue on errors."
@@ -93,5 +129,54 @@ module CsvMadness
         ""
       end
     end
+    
+    def _reset_counter_columns
+      for sym, column in @columns
+        column.reset if column.is_a?( Utils::CounterProc )
+      end
+    end
+    
+    # 
+    def choose_progress_mode( m )
+      case m
+      when true
+        @show_progress = true
+        @progress_mode = progress_bar_available? ? :tty : :stdout
+      when false, nil
+        @show_progress = false
+        @progress_mode = :none
+      when Symbol
+        @show_progress = (m == :none) ? false : true
+        @progress_mode = m
+      else
+        warn "unknown progress mode #{m.inspect}"
+        choose_progress_mode( false )
+      end
+    end
+    
+    def show_progress
+      if @show_progress
+        @progress_mode ||= progress_bar_available? ? :tty : :stdout
+        
+        case @progress_mode
+        when :tty
+          @tty_progress_bar ||= TTY::ProgressBar.new( "Building spreadsheet :current/:total (:percent) [:bar]", total: @objects.length )
+          @tty_progress_bar.advance(1)
+        when :stdout
+          STDOUT << "."
+        when :counter
+          unless defined?( @tty_progress_count )
+            puts ""
+            @tty_progress_count = 1
+          end
+          
+          print "\r#{@tty_progress_count}/#{@objects.length} records written                    "
+        end
+      end
+    end
+    
+    def progress_bar_available?
+      defined?(TTY) && defined?(TTY::ProgressBar)
+    end
   end
 end

data/lib/csv_madness/column.rb

@@ -0,0 +1,30 @@
+module CsvMadness
+  class Column
+    include ColumnMethods::CoreMethods
+    include ColumnMethods::FetchMethods
+    include ColumnMethods::TypingMethods
+    include ColumnMethods::ErrorMethods
+    include ColumnMethods::DefaultValueMethods
+    
+    attr_accessor :spreadsheet,
+                  :index,
+                  :name,
+                  :type_conversion
+    
+    
+    def initialize( _sheet, _name, _index, _type )
+      self.name    = convert_column_name( nm )
+      self.index   = index
+      self.aliases = @opts[:aliases]
+      self.set_type( opts[:type] )
+    end
+    
+    def get_cell( record )
+      record.data[self.index]
+    end
+    
+    def set_cell( record, value )
+      record.data[self.index] = self.type_convert( value )
+    end
+  end
+end

data/lib/csv_madness/column_methods/core_methods.rb

@@ -0,0 +1,6 @@
+module CsvMadness
+  module ColumnMethods
+    module CoreMethods
+    end
+  end
+end

data/lib/csv_madness/column_methods/default_value_methods.rb

@@ -0,0 +1,7 @@
+module CsvMadness
+  module ColumnMethods
+    module DefaultValueMethods
+      attr_accessor :default_value
+    end
+  end
+end

data/lib/csv_madness/column_methods/error_methods.rb

@@ -0,0 +1,19 @@
+module CsvMadness
+  module ColumnMethods
+    module ErrorMethods
+      # When a conversion fails, what happens?
+      # 
+      # debug   : enters debugger (test mode)
+      # ignore  : no message is given and the default value is returned ("" for string, 0 for integer, 0.0 for float)?
+      # stdout  : message printed to stdout
+      # stderr  : message printed to stderr
+      # cell    : message appears in the cell
+      attr_accessor :warning_style
+      
+      
+      attr_accessor :error_message
+      
+      
+    end
+  end
+end

data/lib/csv_madness/column_methods/fetch_methods.rb

@@ -0,0 +1,11 @@
+module CsvMadness
+  module ColumnMethods
+    module FetchMethods
+      def contents
+        self.spreadsheet.records.map do |record|
+          self.get_cell( record )
+        end 
+      end
+    end
+  end
+end

data/lib/csv_madness/column_methods/typing_methods.rb

@@ -0,0 +1,24 @@
+module CsvMadness
+  module ColumnMethods
+    module TypingMethods
+      def type_convert( value )
+        if self.type_conversion
+          self.type_conversion.call( value )
+        else
+          value
+        end
+      end
+
+      def set_type( type )
+        self.type_conversion = TypeConversion[@opts[:type]]
+        self.convert_column_to_type
+      end
+
+      def convert_column_to_type
+        for record in self.spreadsheet.records
+          set_cell( record, get_cell( record ) )
+        end
+      end
+    end
+  end
+end

data/lib/csv_madness/column_set.rb

@@ -0,0 +1,5 @@
+module CsvMadness
+  class ColumnSet < Array
+    
+  end
+end

data/lib/csv_madness/column_type.rb

@@ -0,0 +1,74 @@
+module CsvMadness
+  class ColumnType
+    COLUMN_TYPE_LOOKUP = {
+      :integer => ColumnTypes::IntegerType,
+      :date    => ColumnTypes::DateType,
+      :string  => ColumnTypes::StringType,
+      # :number  => ColumnTypes::NumberType,
+      :float   => ColumnTypes::FloatType
+    }
+    
+    DEFAULT_ERROR_MESSAGES = {
+      
+    }
+    
+    
+    # What is returned when a conversion fails?
+    #
+    # :default : the type conversion returns
+    # :blank   : the cell becomes a nil
+    # :stderr  : send warning message to stderr and return a nil
+    # :stdout  : send warning message to stdout and return a nil
+    # :sheet   : write the warning message into the sheet itself
+    attr_accessor :conversion_error_value
+    
+    
+    def self.[]( t )
+      COLUMN_TYPE_LOOKUP[t]
+    end
+    
+    def initialize( opts = {} )
+      
+    end
+    
+    # default_hierarchy
+    
+    
+    
+    def standard_opts( overrides )
+      
+      
+    end
+    
+    
+    def conversion_error_message( input )
+      
+    end
+    
+    def handle_conversion_errors( input, &block )
+      begin
+        yield if block_given?
+      rescue ArgumentError
+        
+      end
+    end
+    
+    def self.default_value
+      nil
+    end
+    
+    def default
+      self.default_value || self.class.default_value || nil
+    end
+    
+    protected
+    def build_error_message( input, e )
+      if input =~ /CsvMadness::TypeError/
+        input
+      else
+        "CsvMadness::TypeError::#{ }"
+      end
+    end
+    
+  end
+end

data/lib/csv_madness/column_types/date.rb

@@ -0,0 +1,14 @@
+module CsvMadness
+  module ColumnTypes
+    class DateType < CsvMadness::ColumnType
+      # Blank inputs return nil.  Other inputs may raise a date error
+      def self.convert( input )
+        if input.fwf_blank?
+          self.default_value
+        elsif input.is_a?(String)
+          Date.parse( input )
+        end
+      end
+    end
+  end
+end