reckon 0.2.0

data/.document

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

data/.gitignore

@@ -0,0 +1,22 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC
+.idea

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010 Andrew Cantino
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,17 @@
+= reckon
+
+Reckon automagically converts CSV files for use with the command-line accounting tool Ledger.  It also helps you to select the correct accounts associated with the CSV data using Bayesian machine learning.
+
+== Note on Patches/Pull Requests
+
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2010 Andrew Cantino. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,48 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "reckon"
+    gem.summary = %Q{Utility for interactively converting and labeling CSV files for the Ledger accounting tool.}
+    gem.description = %Q{Reckon automagically converts CSV files for use with the command-line accounting tool Ledger.  It also helps you to select the correct accounts associated with the CSV data using Bayesian machine learning.}
+    gem.email = "andrew@iterationlabs.com"
+    gem.homepage = "http://github.com/iterationlabs/reckon"
+    gem.authors = ["Andrew Cantino"]
+    gem.add_development_dependency "rspec", ">= 1.2.9"
+    gem.add_dependency('fastercsv', '>= 1.5.1')
+    gem.add_dependency('highline', '>= 1.5.2')
+    gem.add_dependency('terminal-table', '>= 1.4.2')
+    gem.executables << 'reckon'
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'spec/rake/spectask'
+Spec::Rake::SpecTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :spec => :check_dependencies
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "reckon #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.2.0

data/bin/reckon

@@ -0,0 +1,19 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'reckon'
+
+options = Reckon::App.parse_opts
+reckon = Reckon::App.new(options)
+
+if options[:print_table]
+  reckon.output_table
+  exit
+end
+
+if !reckon.money_column_indices
+  puts "I was unable to determine either a single or a pair of combined columns to use as the money column."
+  exit
+end
+
+reckon.walk_backwards

data/lib/reckon.rb

@@ -0,0 +1,12 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'fastercsv'
+require 'highline/import'
+require 'optparse'
+require 'time'
+require 'terminal-table'
+
+require File.expand_path(File.join(File.dirname(__FILE__), "reckon", "app"))
+require File.expand_path(File.join(File.dirname(__FILE__), "reckon", "ledger_parser"))
+

data/lib/reckon/app.rb

@@ -0,0 +1,364 @@
+module Reckon
+  class App
+    VERSION = "Reckon 0.1"
+
+    attr_accessor :options, :csv_data, :accounts, :tokens, :money_column_indices, :date_column_index, :description_column_indices, :seen
+
+    def initialize(options = {})
+      self.options = options
+      self.tokens = {}
+      self.accounts = {}
+      self.seen = {}
+      learn!
+      parse
+      filter_csv
+      detect_columns
+    end
+
+    def filter_csv
+      if options[:ignore_columns]
+        new_columns = []
+        columns.each_with_index do |column, index|
+          new_columns << column unless options[:ignore_columns].include?(index + 1)
+        end
+        @columns = new_columns
+      end
+    end
+
+    def learn_from(ledger)
+      LedgerParser.new(ledger).entries.each do |entry|
+        entry[:accounts].each do |account|
+          learn_about_account( account[:name],
+                               [entry[:desc], account[:amount]].join(" ") ) unless account[:name] == options[:bank_account]
+          seen[entry[:date]] ||= {}
+          seen[entry[:date]][pretty_money(account[:amount])] = true
+        end
+      end
+    end
+
+    def already_seen?(row)
+      seen[row[:pretty_date]] && seen[row[:pretty_date]][row[:pretty_money]]
+    end
+
+    def learn!
+      if options[:existing_ledger_file]
+        fail "#{options[:existing_ledger_file]} doesn't exist!" unless File.exists?(options[:existing_ledger_file])
+        ledger_data = File.read(options[:existing_ledger_file])
+        learn_from(ledger_data)
+      end
+    end
+
+    def learn_about_account(account, data)
+      accounts[account] ||= 0
+      tokenize(data).each do |token|
+        tokens[token] ||= {}
+        tokens[token][account] ||= 0
+        tokens[token][account] += 1
+        accounts[account] += 1
+      end
+    end
+
+    def tokenize(str)
+      str.downcase.split(/[\s\-]/)
+    end
+
+    def walk_backwards
+      seen_anything_new = false
+      each_row_backwards do |row|
+        puts Terminal::Table.new(:rows => [ [ row[:pretty_date], row[:pretty_money], row[:description] ] ])
+
+        if already_seen?(row)
+          puts "NOTE: This row is very similar to a previous one!"
+          if !seen_anything_new
+            puts "Skipping..."
+            next
+          end
+        else
+          seen_anything_new = true
+        end
+
+        ledger = if row[:money] > 0
+          out_of_account = ask("Which account provided this income? ([account]/[q]uit/[s]kip) ") { |q| q.default = guess_account(row) }
+          finish if out_of_account == "quit" || out_of_account == "q"
+          if out_of_account == "skip" || out_of_account == "s"
+            puts "Skipping"
+            next
+          end
+
+          ledger_format( row,
+                         [options[:bank_account], row[:pretty_money]],
+                         [out_of_account, row[:pretty_money_negated]] )
+        else
+          into_account = ask("To which account did this money go? ([account]/[q]uit/[s]kip) ") { |q| q.default = guess_account(row) }
+          finish if into_account == "quit" || into_account == 'q'
+          if into_account == "skip" || into_account == 's'
+            puts "Skipping"
+            next
+          end
+
+          ledger_format( row,
+                         [into_account, row[:pretty_money_negated]],
+                         [options[:bank_account], row[:pretty_money]] )
+        end
+
+        learn_from(ledger)
+        output(ledger)
+      end
+    end
+
+    def finish
+      options[:output_file].close unless options[:output_file] == STDOUT
+      puts "Exiting."
+      exit
+    end
+
+    def output(ledger_line)
+      options[:output_file].puts ledger_line
+      options[:output_file].flush
+    end
+
+    def guess_account(row)
+      query_tokens = tokenize(row[:description])
+
+      search_vector = []
+      account_vectors = {}
+
+      query_tokens.each do |token|
+        idf = Math.log((accounts.keys.length + 1) / ((tokens[token] || {}).keys.length.to_f + 1))
+        tf = 1.0 / query_tokens.length.to_f
+        search_vector << tf*idf
+
+        accounts.each do |account, total_terms|
+          tf = (tokens[token] && tokens[token][account]) ? tokens[token][account] / total_terms.to_f : 0
+          account_vectors[account] ||= []
+          account_vectors[account] << tf*idf
+        end
+      end
+
+      # Should I normalize the vectors?  Probably unnecessary due to tf-idf and short documents.
+
+      account_vectors = account_vectors.to_a.map do |account, account_vector|
+        { :cosine => (0...account_vector.length).to_a.inject(0) { |m, i| m + search_vector[i] * account_vector[i] },
+          :account => account }
+      end
+
+      account_vectors.sort! {|a, b| b[:cosine] <=> a[:cosine] }
+      account_vectors.first && account_vectors.first[:account]
+    end
+
+    def ledger_format(row, line1, line2)
+      out = "#{row[:pretty_date]}\t#{row[:description]}\n"
+      out += "\t#{line1.first}\t\t\t\t\t#{line1.last}\n"
+      out += "\t#{line2.first}\t\t\t\t\t#{line2.last}\n\n"
+      out
+    end
+
+    def money_for(index)
+      value = money_column_indices.inject("") { |m, i| m + columns[i][index] }
+      cleaned_value = value.gsub(/[^\d\.]/, '').to_f
+      cleaned_value *= -1 if value =~ /[\(\-]/
+      cleaned_value
+    end
+
+    def pretty_money_for(index, negate = false)
+      pretty_money(money_for(index), negate)
+    end
+
+    def pretty_money(amount, negate = false)
+      (amount >= 0 ? " " : "") + sprintf("%0.2f", amount * (negate ? -1 : 1)).gsub(/^((\-)|)(?=\d)/, '\1$')
+    end
+
+    def date_for(index)
+      value = columns[date_column_index][index]
+      value = [$1, $2, $3].join("/") if value =~ /^(\d{4})(\d{2})(\d{2})\d+\[\d+\:GMT\]$/ # chase format
+      Time.parse(value)
+    end
+
+    def pretty_date_for(index)
+      date_for(index).strftime("%Y/%m/%d")
+    end
+
+    def description_for(index)
+      description_column_indices.map { |i| columns[i][index] }.join("; ").squeeze(" ")
+    end
+
+    def output_table
+      output = Terminal::Table.new do |t|
+        t.headings = 'Date', 'Amount', 'Description'
+        each_row_backwards do |row|
+          t << [ row[:pretty_date], row[:pretty_money], row[:description] ]
+        end
+      end
+      puts output
+    end
+
+    def evaluate_columns(cols)
+      results = []
+      found_likely_money_column = false
+      cols.each_with_index do |column, index|
+        money_score = date_score = possible_neg_money_count = possible_pos_money_count = 0
+        column.each do |entry|
+          entry = entry.strip
+          money_score += 10 if entry[/^[\-\+\(]{0,2}\$/]
+          money_score += entry.gsub(/[^\d\.\-\+,\(\)]/, '').length
+          money_score -= 100 if entry.length > 17
+          money_score -= 20 if entry !~ /^[\$\+\.\-,\d\(\)]+$/
+          possible_neg_money_count += 1 if entry =~ /^\$?[\-\(]\$?\d+/
+          possible_pos_money_count += 1 if entry =~ /^\+?\$?\+?\d+/
+          date_score += 10 if entry =~ /^[\-\/\.\d:\[\]]+$/
+          date_score += entry.gsub(/[^\-\/\.\d:\[\]]/, '').length
+          date_score -= entry.gsub(/[\-\/\.\d:\[\]]/, '').length * 2
+          date_score += 30 if entry =~ /^\d+[:\/\.]\d+[:\/\.]\d+([ :]\d+[:\/\.]\d+)?$/
+          date_score += 10 if entry =~ /^\d+\[\d+:GMT\]$/i
+        end
+
+        if possible_neg_money_count > (column.length / 5.0) && possible_pos_money_count > (column.length / 5.0)
+          money_score += 10 * column.length
+          found_likely_money_column = true
+        end
+
+        results << { :index => index, :money_score => money_score, :date_score => date_score }
+      end
+
+      return [results, found_likely_money_column]
+    end
+
+    def merge_columns(a, b)
+      output_columns = []
+      columns.each_with_index do |column, index|
+        if index == a
+          new_column = []
+          column.each_with_index do |row, row_index|
+            new_column << row + " " + columns[b][row_index]
+          end
+          output_columns << new_column
+        elsif index == b
+          # skip
+        else
+          output_columns << column
+        end
+      end
+      output_columns
+    end
+
+    def detect_columns
+      results, found_likely_money_column = evaluate_columns(columns)
+
+      if found_likely_money_column
+        self.money_column_indices = [ results.sort { |a, b| b[:money_score] <=> a[:money_score] }.first[:index] ]
+      else
+        0.upto(columns.length - 2) do |i|
+          _, found_likely_money_column = evaluate_columns(merge_columns(i, i+1))
+
+          if found_likely_money_column
+            self.money_column_indices = [ i, i+1 ]
+            break
+          end
+        end
+      end
+
+      if money_column_indices
+        results.reject! {|i| money_column_indices.include?(i[:index]) }
+        self.date_column_index = results.sort { |a, b| b[:date_score] <=> a[:date_score] }.first[:index]
+        results.reject! {|i| i[:index] == date_column_index }
+
+        self.description_column_indices = results.map { |i| i[:index] }
+      end
+    end
+
+    def each_row_backwards
+      rows = []
+      (0...columns.first.length).to_a.each do |index|
+        rows << { :date => date_for(index), :pretty_date => pretty_date_for(index),
+                  :pretty_money => pretty_money_for(index), :pretty_money_negated => pretty_money_for(index, :negate),
+                  :money => money_for(index), :description => description_for(index) }
+      end
+      rows.sort { |a, b| a[:date] <=> b[:date] }.each do |row|
+        yield row
+      end
+    end
+
+    def columns
+      @columns ||= begin
+        last_row_length = nil
+        csv_data.inject([]) do |memo, row|
+          fail "Input CSV must have consistent row lengths." if last_row_length && row.length != last_row_length
+          unless row.all? { |i| i.nil? || i.length == 0 }
+            row.each_with_index do |entry, index|
+              memo[index] ||= []
+              memo[index] << entry.strip
+            end
+            last_row_length = row.length
+          end
+          memo
+        end
+      end
+    end
+
+    def parse
+      self.csv_data = FasterCSV.parse(options[:string] || File.read(options[:file]))
+    end
+
+    def self.parse_opts(args = ARGV)
+      options = { :output_file => STDOUT }
+      parser = OptionParser.new do |opts|
+        opts.banner = "Usage: Reckon.rb [options]"
+        opts.separator ""
+
+        opts.on("-f", "--file FILE", "The CSV file to parse") do |file|
+          options[:file] = file
+        end
+
+        opts.on("-v", "--[no-]verbose", "Run verbosely") do |v|
+          options[:verbose] = v
+        end
+
+        opts.on("-p", "--print-table", "Print out the parsed CSV in table form") do |p|
+          options[:print_table] = p
+        end
+
+        opts.on("-o", "--output-file FILE", "The ledger file to append to") do |o|
+          options[:output_file] = File.open(o, 'a')
+        end
+
+        opts.on("-l", "--learn-from FILE", "An existing ledger file to learn accounts from") do |l|
+          options[:existing_ledger_file] = l
+        end
+
+        opts.on("", "--ignore-columns 1,2,5", "Columns to ignore in the CSV file - the first column is column 1") do |ignore|
+          options[:ignore_columns] = ignore.split(",").map { |i| i.to_i }
+        end
+
+        opts.on_tail("-h", "--help", "Show this message") do
+          puts opts
+          exit
+        end
+
+        opts.on_tail("--version", "Show version") do
+          puts VERSION
+          exit
+        end
+
+        opts.parse!(args)
+      end
+
+      unless options[:file]
+        options[:file] = ask("What CSV file should I parse? ")
+        unless options[:file].length > 0
+          puts "\nYou must provide a CSV file to parse.\n"
+          puts parser
+          exit
+        end
+      end
+
+      unless options[:bank_account]
+        options[:bank_account] = ask("What is the account name of this bank account in Ledger? ") do |q|
+          q.validate = /^.{2,}$/
+          q.default = "Assets:Bank:Checking"
+        end
+      end
+
+      options
+    end
+  end
+end

data/lib/reckon/ledger_parser.rb

@@ -0,0 +1,62 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+
+module Reckon
+  class LedgerParser
+
+    attr_accessor :entries
+
+    def initialize(ledger, options = {})
+      @entries = []
+      parse(ledger)
+    end
+
+    def parse(ledger)
+      @entries = []
+      date = desc = nil
+      accounts = []
+      ledger.strip.split("\n").each do |entry|
+        next if entry =~ /^\s*$/ || entry =~ /^[^ \t\d]/
+        if entry =~ /^([\d\/]+)(\=[\d\/]+)?(\s+[\*!]?\s*.*?)$/
+          @entries << { :date => date.strip, :desc => desc.strip, :accounts => balance(accounts) } if date
+          date = $1
+          desc = $3
+          accounts = []
+        elsif date && entry =~ /^\s+([a-z\s:_\-]+)(\s*$|(\s+[\$\.,\-\d\+]+)($|\s+($|[^\$\.,\-\d\+])))/i
+          accounts << { :name => $1.strip, :amount => clean_money($3) }
+        else
+          @entries << { :date => date.strip, :desc => desc.strip, :accounts => balance(accounts) } if date
+          date = desc = nil
+          accounts = []
+        end
+      end
+      @entries << { :date => date.strip, :desc => desc.strip, :accounts => balance(accounts) } if date
+    end
+
+    def balance(accounts)
+      if accounts.any? { |i| i[:amount].nil? }
+        sum = accounts.inject(0) {|m, account| m + (account[:amount] || 0) }
+        count = 0
+        accounts.each do |account|
+          if account[:amount].nil?
+            count += 1
+            account[:amount] = 0 - sum
+          end
+        end
+        if count > 1
+          puts "Warning: unparsable entry due to more than one missing money value."
+          p accounts
+          puts
+        end
+      end
+
+      accounts
+    end
+
+    def clean_money(money)
+      return nil if money.nil? || money.length == 0
+      money.gsub(/[\$,]/, '').to_f
+    end
+  end
+end

data/reckon.gemspec

@@ -0,0 +1,70 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{reckon}
+  s.version = "0.2.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Andrew Cantino"]
+  s.date = %q{2010-11-06}
+  s.description = %q{Reckon automagically converts CSV files for use with the command-line accounting tool Ledger.  It also helps you to select the correct accounts associated with the CSV data using Bayesian machine learning.}
+  s.email = %q{andrew@iterationlabs.com}
+  s.executables = ["reckon", "reckon"]
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "bin/reckon",
+     "lib/reckon.rb",
+     "lib/reckon/app.rb",
+     "lib/reckon/ledger_parser.rb",
+     "reckon.gemspec",
+     "spec/reckon/app_spec.rb",
+     "spec/reckon/ledger_parser_spec.rb",
+     "spec/spec.opts",
+     "spec/spec_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/iterationlabs/reckon}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{Utility for interactively converting and labeling CSV files for the Ledger accounting tool.}
+  s.test_files = [
+    "spec/reckon/app_spec.rb",
+     "spec/reckon/ledger_parser_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_runtime_dependency(%q<fastercsv>, [">= 1.5.1"])
+      s.add_runtime_dependency(%q<highline>, [">= 1.5.2"])
+      s.add_runtime_dependency(%q<terminal-table>, [">= 1.4.2"])
+    else
+      s.add_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_dependency(%q<fastercsv>, [">= 1.5.1"])
+      s.add_dependency(%q<highline>, [">= 1.5.2"])
+      s.add_dependency(%q<terminal-table>, [">= 1.4.2"])
+    end
+  else
+    s.add_dependency(%q<rspec>, [">= 1.2.9"])
+    s.add_dependency(%q<fastercsv>, [">= 1.5.1"])
+    s.add_dependency(%q<highline>, [">= 1.5.2"])
+    s.add_dependency(%q<terminal-table>, [">= 1.4.2"])
+  end
+end
+

data/spec/reckon/app_spec.rb

@@ -0,0 +1,138 @@
+#!/usr/bin/env ruby
+
+require File.dirname(__FILE__) + '/../spec_helper'
+require 'rubygems'
+require 'reckon'
+
+describe Reckon::App do
+  before do
+    @chase = Reckon::App.new(:string => CHASE_CSV)
+    @some_other_bank = Reckon::App.new(:string => SOME_OTHER_CSV)
+    @two_money_columns = Reckon::App.new(:string => TWO_MONEY_COLUMNS_BANK)
+    @simple_csv = Reckon::App.new(:string => SIMPLE_CSV)
+  end
+
+  describe "columns" do
+    it "should return the csv transposed" do
+      @simple_csv.columns.should == [["entry1", "entry4"], ["entry2", "entry5"], ["entry3", "entry6"]]
+      @chase.columns.length.should == 4
+    end
+  end
+
+  describe "detect_columns" do
+    it "should detect the money column" do
+      @chase.money_column_indices.should == [3]
+      @some_other_bank.money_column_indices.should == [3]
+      @two_money_columns.money_column_indices.should == [3, 4]
+    end
+
+    it "should detect the date column" do
+      @chase.date_column_index.should == 1
+      @some_other_bank.date_column_index.should == 1
+      @two_money_columns.date_column_index.should == 0
+    end
+
+    it "should consider all other columns to be description columns" do
+      @chase.description_column_indices.should == [0, 2]
+      @some_other_bank.description_column_indices.should == [0, 2]
+      @two_money_columns.description_column_indices.should == [1, 2, 5]
+    end
+  end
+
+  describe "each_index_backwards" do
+    it "should hit every index" do
+      count = 0
+      @chase.each_row_backwards { count += 1}
+      count.should == 9
+    end
+  end
+
+  describe "money_for" do
+    it "should return the appropriate fields" do
+      @chase.money_for(1).should == -20
+      @chase.money_for(4).should == 1558.52
+      @chase.money_for(7).should == -116.22
+      @some_other_bank.money_for(1).should == -20
+      @some_other_bank.money_for(4).should == 1558.52
+      @some_other_bank.money_for(7).should == -116.22
+      @two_money_columns.money_for(0).should == -76
+      @two_money_columns.money_for(1).should == 327.49
+      @two_money_columns.money_for(2).should == -800
+      @two_money_columns.money_for(3).should == -88.55
+      @two_money_columns.money_for(4).should == 88.55
+    end
+  end
+
+  describe "date_for" do
+    it "should return a parsed date object" do
+      @chase.date_for(1).should == Time.parse("2009/12/24")
+      @some_other_bank.date_for(1).should == Time.parse("2010/12/24")
+    end
+  end
+
+  describe "description_for" do
+    it "should return the combined fields that are not money for date fields" do
+      @chase.description_for(1).should == "CHECK; CHECK 2656"
+      @chase.description_for(7).should == "CREDIT; PAYPAL TRANSFER PPD ID: PAYPALSDSL"
+    end
+  end
+
+  describe "pretty_money_for" do
+    it "work with negative and positive numbers" do
+      @some_other_bank.pretty_money_for(1).should == "-$20.00"
+      @some_other_bank.pretty_money_for(4).should == " $1558.52"
+      @some_other_bank.pretty_money_for(7).should == "-$116.22"
+      @some_other_bank.pretty_money_for(5).should == " $0.23"
+      @some_other_bank.pretty_money_for(6).should == "-$0.96"
+    end
+  end
+
+  describe "merge_columns" do
+    it "should work on adjacent columns" do
+      @simple_csv.merge_columns(0,1).should == [["entry1 entry2", "entry4 entry5"], ["entry3", "entry6"]]
+    end
+
+    it "should work on non-adjacent columns" do
+      @simple_csv.merge_columns(0,2).should == [["entry1 entry3", "entry4 entry6"], ["entry2", "entry5"]]
+    end
+  end
+
+
+
+  # Data
+
+  SIMPLE_CSV = "entry1,entry2,entry3\nentry4,entry5,entry6"
+
+  CHASE_CSV = (<<-CSV).strip
+    DEBIT,20091224120000[0:GMT],"HOST 037196321563 MO        12/22SLICEHOST",-85.00
+    CHECK,20091224120000[0:GMT],"CHECK 2656",-20.00
+    DEBIT,20091224120000[0:GMT],"GITHUB 041287430274 CA           12/22GITHUB 04",-7.00
+    CREDIT,20091223120000[0:GMT],"Some Company vendorpymt                 PPD ID: 59728JSL20",3520.00
+    CREDIT,20091223120000[0:GMT],"Blarg BLARG REVENUE                  PPD ID: 00jah78563",1558.52
+    DEBIT,20091221120000[0:GMT],"WEBSITE-BALANCE-17DEC09 12        12/17WEBSITE-BAL",-12.23
+    DEBIT,20091214120000[0:GMT],"WEBSITE-BALANCE-10DEC09 12        12/10WEBSITE-BAL",-20.96
+    CREDIT,20091211120000[0:GMT],"PAYPAL           TRANSFER                   PPD ID: PAYPALSDSL",-116.22
+    CREDIT,20091210120000[0:GMT],"Some Company vendorpymt                 PPD ID: 5KL3832735",2105.00
+  CSV
+
+  SOME_OTHER_CSV = (<<-CSV).strip
+    DEBIT,2011/12/24,"HOST 037196321563 MO        12/22SLICEHOST",($85.00)
+    CHECK,2010/12/24,"CHECK 2656",($20.00)
+    DEBIT,2009/12/24,"GITHUB 041287430274 CA           12/22GITHUB 04",($7.00)
+    CREDIT,2008/12/24,"Some Company vendorpymt                 PPD ID: 59728JSL20",$3520.00
+    CREDIT,2007/12/24,"Blarg BLARG REVENUE                  PPD ID: 00jah78563",$1558.52
+    DEBIT,2006/12/24,"WEBSITE-BALANCE-17DEC09 12        12/17WEBSITE-BAL",$.23
+    DEBIT,2005/12/24,"WEBSITE-BALANCE-10DEC09 12        12/10WEBSITE-BAL",($0.96)
+    CREDIT,2004/12/24,"PAYPAL           TRANSFER                   PPD ID: PAYPALSDSL",($116.22)
+    CREDIT,2003/12/24,"Some Company vendorpymt                 PPD ID: 5KL3832735",$2105.00
+  CSV
+
+  TWO_MONEY_COLUMNS_BANK = (<<-CSV).strip
+    4/1/2008,Check - 0000000122,122,-$76.00,"","$1,750.06"
+    3/28/2008,BLARG    R SH 456930,"","",+$327.49,"$1,826.06"
+    3/27/2008,Check - 0000000112,112,-$800.00,"","$1,498.57"
+    3/26/2008,Check - 0000000251,251,-$88.55,"","$1,298.57"
+    3/26/2008,Check - 0000000251,251,"","+$88.55","$1,298.57"
+  CSV
+
+end

data/spec/reckon/ledger_parser_spec.rb

@@ -0,0 +1,101 @@
+#!/usr/bin/env ruby
+
+require File.dirname(__FILE__) + '/../spec_helper'
+require 'rubygems'
+require 'reckon'
+require 'pp'
+
+describe Reckon::LedgerParser do
+  before do
+    @ledger = Reckon::LedgerParser.new(EXAMPLE_LEDGER)
+  end
+
+  describe "parse" do
+    it "should ignore non-standard entries" do
+      @ledger.entries.length.should == 5
+    end
+
+    it "should parse entries correctly" do
+      @ledger.entries.first[:desc].should == "* Checking balance"
+      @ledger.entries.first[:date].should == "2004/05/01"
+      @ledger.entries.first[:accounts].first[:name].should == "Assets:Bank:Checking"
+      @ledger.entries.first[:accounts].first[:amount].should == 1000
+      @ledger.entries.first[:accounts].last[:name].should == "Equity:Opening Balances"
+      @ledger.entries.first[:accounts].last[:amount].should == -1000
+
+      @ledger.entries.last[:desc].should == "(100) Credit card company"
+      @ledger.entries.last[:date].should == "2004/05/27"
+      @ledger.entries.last[:accounts].first[:name].should == "Liabilities:MasterCard"
+      @ledger.entries.last[:accounts].first[:amount].should == 20.24
+      @ledger.entries.last[:accounts].last[:name].should == "Assets:Bank:Checking"
+      @ledger.entries.last[:accounts].last[:amount].should == -20.24
+    end
+  end
+
+  describe "balance" do
+    it "it should balance out missing account values" do
+      @ledger.balance([
+          { :name => "Account1", :amount => 1000 },
+          { :name => "Account2", :amount => nil }
+      ]).should == [ { :name => "Account1", :amount => 1000 }, { :name => "Account2", :amount => -1000 } ]
+    end
+
+    it "it should balance out missing account values" do
+      @ledger.balance([
+          { :name => "Account1", :amount => 1000 },
+          { :name => "Account2", :amount => 100 },
+          { :name => "Account3", :amount => -200 },
+          { :name => "Account4", :amount => nil }
+      ]).should == [
+          { :name => "Account1", :amount => 1000 },
+          { :name => "Account2", :amount => 100 },
+          { :name => "Account3", :amount => -200 },
+          { :name => "Account4", :amount => -900 }
+      ]
+    end
+
+    it "it should work on normal values too" do
+      @ledger.balance([
+          { :name => "Account1", :amount => 1000 },
+          { :name => "Account2", :amount => -1000 }
+      ]).should == [ { :name => "Account1", :amount => 1000 }, { :name => "Account2", :amount => -1000 } ]
+    end
+  end
+
+  # Data
+
+  EXAMPLE_LEDGER = (<<-LEDGER).strip
+= /^Expenses:Books/
+  (Liabilities:Taxes)             -0.10
+
+~ Monthly
+  Assets:Bank:Checking          $500.00
+  Income:Salary
+
+2004/05/01 * Checking balance
+  Assets:Bank:Checking        $1,000.00
+  Equity:Opening Balances
+
+2004/05/01 * Investment balance
+  Assets:Brokerage              50 AAPL @ $30.00
+  Equity:Opening Balances
+
+; blah
+!account blah
+
+!end
+
+D $1,000
+
+2004/05/14 * Pay day
+  Assets:Bank:Checking          $500.00
+  Income:Salary
+
+2004/05/27 Book Store
+  Expenses:Books                 $20.00
+  Liabilities:MasterCard
+2004/05/27 (100) Credit card company
+  Liabilities:MasterCard         $20.24
+  Assets:Bank:Checking
+  LEDGER
+end

data/spec/spec.opts

@@ -0,0 +1 @@
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'reckon'
+require 'spec'
+require 'spec/autorun'
+
+Spec::Runner.configure do |config|
+
+end

metadata

@@ -0,0 +1,148 @@
+--- !ruby/object:Gem::Specification 
+name: reckon
+version: !ruby/object:Gem::Version 
+  hash: 23
+  prerelease: false
+  segments: 
+  - 0
+  - 2
+  - 0
+  version: 0.2.0
+platform: ruby
+authors: 
+- Andrew Cantino
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-11-06 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 13
+        segments: 
+        - 1
+        - 2
+        - 9
+        version: 1.2.9
+  type: :development
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: fastercsv
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 1
+        segments: 
+        - 1
+        - 5
+        - 1
+        version: 1.5.1
+  type: :runtime
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: highline
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 7
+        segments: 
+        - 1
+        - 5
+        - 2
+        version: 1.5.2
+  type: :runtime
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: terminal-table
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 1
+        - 4
+        - 2
+        version: 1.4.2
+  type: :runtime
+  version_requirements: *id004
+description: Reckon automagically converts CSV files for use with the command-line accounting tool Ledger.  It also helps you to select the correct accounts associated with the CSV data using Bayesian machine learning.
+email: andrew@iterationlabs.com
+executables: 
+- reckon
+- reckon
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- bin/reckon
+- lib/reckon.rb
+- lib/reckon/app.rb
+- lib/reckon/ledger_parser.rb
+- reckon.gemspec
+- spec/reckon/app_spec.rb
+- spec/reckon/ledger_parser_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: http://github.com/iterationlabs/reckon
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Utility for interactively converting and labeling CSV files for the Ledger accounting tool.
+test_files: 
+- spec/reckon/app_spec.rb
+- spec/reckon/ledger_parser_spec.rb
+- spec/spec_helper.rb