reckon 0.7.1 → 0.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 13ec00f6b1277d98d6df6264af61020310ab5bf61197412a116a2f61901e6214
-  data.tar.gz: cf1b1e21a64fac57a5796b64f53da971a48c4bb3f439be94fd847441c5b36a0f
+  metadata.gz: 5984a4f8cd36d4e14f013c14bb111725f8681b90768b6710679820d1325a02e5
+  data.tar.gz: b392d89078a7679f01a344799512ec0467cfe8cad101374a5b8fd198c7e39480
 SHA512:
-  metadata.gz: 450fb569cf8509563edd5fb36239965b9cd29b28d544399bcc10cf510a146d68fb56c3dd1737a1904cd7f23ab3453128d522fb07159068bbc6ed2d44cb0fe1d6
-  data.tar.gz: 461bade5035f16c278131102df52b91e39a365b18c3e73875730616b5489f07f7c0528094da13a06558791b4238d1d6cc495452b14c917b15eef5eea2719e909
+  metadata.gz: ae9b8348e93294d45354f1b96045305dd480b23cd34dcaca3f958fcbc866582000faa1711ea6cbb552578ffe98f126943221b98af298757b86e6dfa54c623f9d
+  data.tar.gz: f43e7128e198c9b73fc40b148cbe281d0bc02aeec90d576615e24fe98789a1846553121319152bffb3a9ca966fd26e1b3916da90480979c5d55106e06dbfe7f2

data/.github/workflows/ruby.yml

@@ -34,10 +34,10 @@ jobs:
           - 2.3.7
     steps:
     - uses: actions/checkout@v2
+    - name: Update package
+      run: sudo apt-get update
     - name: Install packages
-      run: sudo apt-get -y install ledger hledger
-    - name: Install bundler
-      run: sudo gem install -v 1.17.3 bundler
+      run: sudo apt-get -y install ledger hledger expect
     - name: Set up Ruby
     # To automatically get bug fixes and new Ruby versions for ruby/setup-ruby,
     # change this to (see https://github.com/ruby/setup-ruby#versioning):
@@ -45,6 +45,6 @@ jobs:
       # uses: ruby/setup-ruby@473e4d8fe5dd94ee328fdfca9f8c9c7afc9dae5e
       with:
         ruby-version: ${{ matrix.ruby-version }}
-        bundler-cache: true # runs 'bundle install' and caches installed gems automatically
+        bundler-cache: true # runs 'bundle install' and caches installed gems
     - name: Run tests
       run: bundle exec rake test_all

data/CHANGELOG.md

@@ -1,6 +1,21 @@
 # Changelog
 
-## [v0.7.1](https://github.com/cantino/reckon/tree/v0.7.1) (2021-02-06)
+## [v0.7.2](https://github.com/cantino/reckon/tree/v0.7.2) (2021-04-22)
+
+[Full Changelog](https://github.com/cantino/reckon/compare/v0.7.1...v0.7.2)
+
+**Closed issues:**
+
+- \[feature request\] Better format for large transactions [\#108](https://github.com/cantino/reckon/issues/108)
+- cosine similarity not comparing documents correctly [\#106](https://github.com/cantino/reckon/issues/106)
+
+**Merged pull requests:**
+
+- Add thousands separator in money output.  Fixes \#108. [\#109](https://github.com/cantino/reckon/pull/109) ([benprew](https://github.com/benprew))
+- Cosine similarity should use all docs tokens. not just matched tokens. [\#107](https://github.com/cantino/reckon/pull/107) ([benprew](https://github.com/benprew))
+- Test getting expect working with actions [\#105](https://github.com/cantino/reckon/pull/105) ([benprew](https://github.com/benprew))
+
+## [v0.7.1](https://github.com/cantino/reckon/tree/v0.7.1) (2021-02-07)
 
 [Full Changelog](https://github.com/cantino/reckon/compare/v0.7.0...v0.7.1)
 
@@ -135,7 +150,6 @@
 - Fix bugs in ledger file parsing.  Fixes \#56. [\#81](https://github.com/cantino/reckon/pull/81) ([benprew](https://github.com/benprew))
 - Better file encoding suggestions [\#80](https://github.com/cantino/reckon/pull/80) ([benprew](https://github.com/benprew))
 - :bug: fix matching algorithm, add logging and a spec helper.  Fixes \#73 [\#79](https://github.com/cantino/reckon/pull/79) ([benprew](https://github.com/benprew))
-- bug: invalid header lines should be ignored, not parsed. [\#78](https://github.com/cantino/reckon/pull/78) ([benprew](https://github.com/benprew))
 - convert default date format to iso8601 [\#77](https://github.com/cantino/reckon/pull/77) ([benprew](https://github.com/benprew))
 - Fix rspec failure for ruby 2.3 and 2.4 [\#69](https://github.com/cantino/reckon/pull/69) ([BlackEdder](https://github.com/BlackEdder))
 - Allow setting of money and date columns by index [\#67](https://github.com/cantino/reckon/pull/67) ([cantino](https://github.com/cantino))
@@ -188,6 +202,7 @@
 
 **Merged pull requests:**
 
+- bug: invalid header lines should be ignored, not parsed. [\#78](https://github.com/cantino/reckon/pull/78) ([benprew](https://github.com/benprew))
 - Better ISO 8601 dates support [\#49](https://github.com/cantino/reckon/pull/49) ([vzctl](https://github.com/vzctl))
 - Unattended mode and custom tokens support [\#47](https://github.com/cantino/reckon/pull/47) ([vzctl](https://github.com/vzctl))
 - \[RFC\] Implement issue \#40: Tab completion [\#46](https://github.com/cantino/reckon/pull/46) ([BlackEdder](https://github.com/BlackEdder))
@@ -201,6 +216,7 @@
 
 - Fix --encoding option [\#41](https://github.com/cantino/reckon/pull/41) ([mamciek](https://github.com/mamciek))
 - Bumped version number [\#37](https://github.com/cantino/reckon/pull/37) ([BlackEdder](https://github.com/BlackEdder))
+- Ing csv [\#30](https://github.com/cantino/reckon/pull/30) ([BlackEdder](https://github.com/BlackEdder))
 
 ## [v0.3.9](https://github.com/cantino/reckon/tree/v0.3.9) (2014-02-20)
 
@@ -217,15 +233,12 @@
 - Date format [\#35](https://github.com/cantino/reckon/pull/35) ([BlackEdder](https://github.com/BlackEdder))
 - Added example from a french bank [\#34](https://github.com/cantino/reckon/pull/34) ([BlackEdder](https://github.com/BlackEdder))
 - Austrian example [\#33](https://github.com/cantino/reckon/pull/33) ([BlackEdder](https://github.com/BlackEdder))
-- Ing csv [\#30](https://github.com/cantino/reckon/pull/30) ([BlackEdder](https://github.com/BlackEdder))
 - Further improvements in nationwide csv handling [\#29](https://github.com/cantino/reckon/pull/29) ([BlackEdder](https://github.com/BlackEdder))
 - Refactor: Add money class [\#28](https://github.com/cantino/reckon/pull/28) ([BlackEdder](https://github.com/BlackEdder))
 - Initial split of CSVparser from class App [\#27](https://github.com/cantino/reckon/pull/27) ([BlackEdder](https://github.com/BlackEdder))
 - Updated version of pull request 24: Allow for other currency symbols while calculating money\_score [\#26](https://github.com/cantino/reckon/pull/26) ([BlackEdder](https://github.com/BlackEdder))
 - Change double column detection [\#23](https://github.com/cantino/reckon/pull/23) ([BlackEdder](https://github.com/BlackEdder))
-- Added optional argument to contains\_header to skip multiple header lines [\#22](https://github.com/cantino/reckon/pull/22) ([BlackEdder](https://github.com/BlackEdder))
 - Add a Bitdeli Badge to README [\#20](https://github.com/cantino/reckon/pull/20) ([bitdeli-chef](https://github.com/bitdeli-chef))
-- Update README to show latest usage info [\#19](https://github.com/cantino/reckon/pull/19) ([purcell](https://github.com/purcell))
 
 ## [v0.3.8](https://github.com/cantino/reckon/tree/v0.3.8) (2013-07-03)
 
@@ -242,6 +255,7 @@
 
 **Merged pull requests:**
 
+- Update README to show latest usage info [\#19](https://github.com/cantino/reckon/pull/19) ([purcell](https://github.com/purcell))
 - add support for spanish dates dd/mm/yyyy closes \#13 [\#14](https://github.com/cantino/reckon/pull/14) ([mauromorales](https://github.com/mauromorales))
 - fix issue showing true when parsing the currency option related to \#7 [\#12](https://github.com/cantino/reckon/pull/12) ([mauromorales](https://github.com/mauromorales))
 
@@ -251,6 +265,7 @@
 
 **Merged pull requests:**
 
+- Added optional argument to contains\_header to skip multiple header lines [\#22](https://github.com/cantino/reckon/pull/22) ([BlackEdder](https://github.com/BlackEdder))
 - Updated the sources to allow for custom curreny [\#11](https://github.com/cantino/reckon/pull/11) ([ghost](https://github.com/ghost))
 - Add --account option on the commandline [\#10](https://github.com/cantino/reckon/pull/10) ([copiousfreetime](https://github.com/copiousfreetime))
 

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    reckon (0.7.1)
+    reckon (0.7.2)
       chronic (>= 0.3.0)
       highline (>= 1.5.2)
       rchardet (>= 1.8.0)

data/Rakefile

@@ -17,6 +17,6 @@ task :test_all do
 end
 
 task :integration_tests do
-  puts `./spec/integration/test.sh`
-  raise 'Integration tests failed' if $CHILD_STATUS.exitstatus != 0
+  cmd = 'prove -v ./spec/integration/test.sh'
+  raise 'Integration tests failed' unless system(cmd)
 end

data/bin/build-new-version.sh

@@ -5,7 +5,7 @@ set -e
 VERSION=$1
 
 echo "Install github_changelog_generator"
-gem install --user github_changelog_generator
+# gem install --user github_changelog_generator
 
 echo "Update 'lib/reckon/version.rb'"
 echo -e "module Reckon\n  VERSION=\"$VERSION\"\nend" > lib/reckon/version.rb

data/bin/reckon

@@ -13,6 +13,9 @@ reckon = Reckon::App.new(options)
 
 if options[:print_table]
   reckon.output_table
+  if options[:table_output_file]
+    File.open(options[:table_output_file], 'w') { |fh| reckon.output_table fh }
+  end
   exit
 end
 

data/lib/reckon/app.rb

@@ -20,10 +20,10 @@ module Reckon
       learn!
     end
 
-    def interactive_output(str)
+    def interactive_output(str, fh = $stdout)
       return if options[:unattended]
 
-      puts str
+      fh.puts str
     end
 
     def learn!
@@ -161,7 +161,7 @@ module Reckon
       rows.sort_by { |n| [n[:date], -n[:money], n[:description]] }.each { |row| yield row }
     end
 
-    def print_transaction(rows)
+    def print_transaction(rows, fh = $stdout)
       str = "\n"
       header = %w[Date Amount Description Note]
       maxes = header.map(&:length)
@@ -185,7 +185,7 @@ module Reckon
         str += "\n"
       end
 
-      interactive_output str
+      interactive_output str, fh
     end
 
     def ask_account_question(msg, row)
@@ -280,12 +280,12 @@ module Reckon
       exit
     end
 
-    def output_table
+    def output_table(fh = $stdout)
       rows = []
       each_row_backwards do |row|
         rows << row
       end
-      print_transaction(rows)
+      print_transaction(rows, fh)
     end
   end
 end

data/lib/reckon/cosine_similarity.rb

@@ -1,47 +1,52 @@
 require 'matrix'
 require 'set'
 
-# Implementation of consine similarity using TF-IDF for vectorization.
-# Used to suggest which account a transaction should be assigned to
+# Implementation of cosine similarity using TF-IDF for vectorization.
+#
+# In information retrieval, tf–idf, short for term frequency–inverse document frequency,
+# is a numerical statistic that is intended to reflect how important a word is to a
+# document in a collection or corpus
+#
+# Cosine Similarity a measurement to determine how similar 2 documents are to each other.
+#
+# These weights and measures are used to suggest which account a transaction should be
+# assigned to.
 module Reckon
   class CosineSimilarity
+    DocumentInfo = Struct.new(:tokens, :accounts)
+
     def initialize(options)
+      @docs = DocumentInfo.new({}, {})
       @options = options
-      @tokens = {}
-      @accounts = Hash.new(0)
     end
 
     def add_document(account, doc)
-      tokenize(doc).each do |n|
+      tokens = tokenize(doc)
+      LOGGER.info "doc tokens: #{tokens}"
+      tokens.each do |n|
         (token, count) = n
 
-        @tokens[token] ||= {}
-        @tokens[token][account] ||= 0
-        @tokens[token][account] += count
-        @accounts[account] += count
+        @docs.tokens[token] ||= Hash.new(0)
+        @docs.tokens[token][account] += count
+        @docs.accounts[account] ||= Hash.new(0)
+        @docs.accounts[account][token] += count
       end
     end
 
     # find most similar documents to query
     def find_similar(query)
-      (query_scores, corpus_scores) = td_idf_scores_for(query)
+      LOGGER.info "find_similar #{query}"
 
-      query_vector = Vector.elements(query_scores, false)
+      accounts = docs_to_check(query).map do |a|
+        [a, tfidf(@docs.accounts[a])]
+      end
 
-      # For each doc, calculate the similarity to the query
-      suggestions = corpus_scores.map do |account, scores|
-        acct_vector = Vector.elements(scores, false)
+      q = tfidf(tokenize(query))
 
-        acct_query_dp = acct_vector.inner_product(query_vector)
-        # similarity is a float between 1 and -1, where 1 is exactly the same and -1 is
-        # exactly opposite
-        # see https://en.wikipedia.org/wiki/Cosine_similarity
-        # cos(theta) = (A . B) / (||A|| ||B||)
-        # where A . B is the "dot product" and ||A|| is the magnitude of A
-        # ruby has the 'matrix' library we can use to do these calculations.
+      suggestions = accounts.map do |a, d|
         {
-          similarity: acct_query_dp / (acct_vector.magnitude * query_vector.magnitude),
-          account: account,
+          similarity: calc_similarity(q, d),
+          account: a
         }
       end.select { |n| n[:similarity] > 0 }.sort_by { |n| -n[:similarity] }
 
@@ -52,50 +57,51 @@ module Reckon
 
     private
 
-    def td_idf_scores_for(query)
-      query_tokens = tokenize(query)
-      corpus = Set.new
-      corpus_scores = {}
-      query_scores = []
-      num_docs = @accounts.length
-
-      query_tokens.each do |n|
-        (token, _count) = n
-        next unless @tokens[token]
-        corpus = corpus.union(Set.new(@tokens[token].keys))
+    def docs_to_check(query)
+      return tokenize(query).reduce(Set.new) do |corpus, t|
+        corpus.union(Set.new(@docs.tokens[t[0]]&.keys))
       end
+    end
 
-      query_tokens.each do |n|
-        (token, count) = n
-
-        # if no other docs have token, ignore it
-        next unless @tokens[token]
+    def tfidf(tokens)
+      scores = {}
 
-        ## First, calculate scores for our query as we're building scores for the corpus
-        query_scores << calc_tf_idf(
-          count,
-          query_tokens.length,
-          @tokens[token].length,
-          num_docs
+      tokens.each do |t, n|
+        scores[t] = calc_tf_idf(
+          n,
+          tokens.length,
+          @docs.tokens[t]&.length&.to_f || 0,
+          @docs.accounts.length
         )
-
-        ## Next, calculate for the corpus, where our "account" is a document
-        corpus.each do |account|
-          corpus_scores[account] ||= []
-
-          corpus_scores[account] << calc_tf_idf(
-            (@tokens[token][account] || 0),
-            @accounts[account].to_f,
-            @tokens[token].length.to_f,
-            num_docs
-          )
-        end
       end
-      [query_scores, corpus_scores]
+
+      return scores
     end
 
-    def calc_tf_idf(token_count, num_words_in_doc, df, num_docs)
+    # Cosine similarity is used to compare how similar 2 documents are. Returns a float
+    # between 1 and -1, where 1 is exactly the same and -1 is exactly opposite.
+    #
+    # see https://en.wikipedia.org/wiki/Cosine_similarity
+    # cos(theta) = (A . B) / (||A|| ||B||)
+    # where A . B is the "dot product" and ||A|| is the magnitude of A
+    #
+    # The variables A and B are the set of unique terms in q and d.
+    #
+    # For example, when q = "big red balloon" and d ="small green balloon" then the
+    # variables are (big,red,balloon,small,green) and a = (1,1,1,0,0) and b =
+    # (0,0,1,1,1).
+    #
+    # query and doc are hashes of token => tf/idf score
+    def calc_similarity(query, doc)
+      tokens = Set.new(query.keys + doc.keys)
+
+      a = Vector.elements(tokens.map { |n| query[n] || 0 }, false)
+      b = Vector.elements(tokens.map { |n| doc[n] || 0 }, false)
+
+      return a.inner_product(b) / (a.magnitude * b.magnitude)
+    end
 
+    def calc_tf_idf(token_count, num_words_in_doc, df, num_docs)
       # tf(t,d) = count of t in d / number of words in d
       tf = token_count / num_words_in_doc.to_f
 
@@ -109,14 +115,13 @@ module Reckon
     end
 
     def tokenize(str)
-      mk_tokens(str).inject(Hash.new(0)) do |memo, n|
+      mk_tokens(str).each_with_object(Hash.new(0)) do |n, memo|
         memo[n] += 1
-        memo
       end.to_a
     end
 
     def mk_tokens(str)
-      str.downcase.tr(';', ' ').tr("'", '').split(/[^a-z0-9.]+/)
+      str.downcase.tr(';', ' ').tr("'", '').split(/[^a-z0-9.]+/).reject(&:empty?)
     end
   end
 end

data/lib/reckon/money.rb

@@ -50,11 +50,18 @@ module Reckon
         return @amount_raw[0] == '-' ? @amount_raw[1..-1] : "-#{@amount_raw}"
       end
 
-      if @suffixed
-        (@amount >= 0 ? " " : "") + sprintf("%0.2f #{@currency}", @amount * (negate ? -1 : 1))
-      else
-        (@amount >= 0 ? " " : "") + sprintf("%0.2f", @amount * (negate ? -1 : 1)).gsub(/^((\-)|)(?=\d)/, "\\1#{@currency}")
-      end
+      amt = pretty_amount(@amount * (negate ? -1 : 1))
+      amt = if @suffixed
+              "#{amt} #{@currency}"
+            else
+              amt.gsub(/^((-)|)(?=\d)/, "\\1#{@currency}")
+            end
+
+      return (@amount >= 0 ? " " : "") + amt
+    end
+
+    def pretty_amount(amount)
+      sprintf("%0.2f", amount).reverse.gsub(/(\d{3})(?=\d)/, '\\1,').reverse
     end
 
     def parse(value, options = {})

data/lib/reckon/options.rb

@@ -85,6 +85,10 @@ module Reckon
           options[:account_tokens_file] = a
         end
 
+        opts.on("", "--table-output-file FILE") do |n|
+          options[:table_output_file] = n
+        end
+
         options[:default_into_account] = 'Expenses:Unknown'
         opts.on("", "--default-into-account NAME", "Default into account") do |a|
           options[:default_into_account] = a

data/lib/reckon/version.rb

@@ -1,3 +1,3 @@
 module Reckon
-  VERSION="0.7.1"
+  VERSION="0.7.2"
 end

data/spec/cosine_training_and_test.rb

@@ -0,0 +1,52 @@
+#!/usr/bin/env ruby
+
+require 'pp'
+
+require 'reckon'
+
+ledger_file = ARGV[0]
+account = ARGV[1]
+seed = ARGV[2] ? ARGV[2].to_i : Random.new_seed
+
+ledger = Reckon::LedgerParser.new(File.read(ledger_file))
+matcher = Reckon::CosineSimilarity.new({})
+
+train = []
+test = []
+
+def has_account(account, entry)
+  entry[:accounts].map { |a| a[:name] }.include?(account)
+end
+
+entries = ledger.entries.select { |e| has_account(account, e) }
+
+r = Random.new(seed)
+entries.length.times do |i|
+  r.rand < 0.9 ? train << i : test << i
+end
+
+train.each do |i|
+  entry = entries[i]
+  entry[:accounts].each do |a|
+    matcher.add_document(
+      a[:name],
+      [entry[:desc], a[:amount]].join(" ")
+    )
+  end
+end
+
+result = [nil] * test.length
+test.each do |i|
+  entry = entries[i]
+  matches = matcher.find_similar(
+    entry[:desc] + " " + entry[:accounts][0][:amount].to_s
+  )
+
+  if !matches[0] || !has_account(matches[0][:account], entry)
+    result[i] = [entry, matches]
+  end
+end
+
+# pp result.compact
+puts "using #{seed} as random seed"
+puts "true: #{result.count(nil)} false: #{result.count { |v| !v.nil? }}"

data/spec/integration/another_bank_example/output.ledger

@@ -1,5 +1,5 @@
 2003-12-24	CREDIT; Some Company vendorpymt PPD ID: 5KL3832735
-	Assets:Bank:Checking			 $2105.00
+	Assets:Bank:Checking			 $2,105.00
 	Income:Unknown			
 
 2004-12-24	CREDIT; PAYPAL TRANSFER PPD ID: PAYPALSDSL
@@ -15,11 +15,11 @@
 	Expenses:Unknown			
 
 2007-12-24	CREDIT; Blarg BLARG REVENUE PPD ID: 00jah78563
-	Assets:Bank:Checking			 $1558.52
+	Assets:Bank:Checking			 $1,558.52
 	Income:Unknown			
 
 2008-12-24	CREDIT; Some Company vendorpymt PPD ID: 59728JSL20
-	Assets:Bank:Checking			 $3520.00
+	Assets:Bank:Checking			 $3,520.00
 	Income:Unknown			
 
 2009-12-24	DEBIT; GITHUB 041287430274 CA 12/22GITHUB 04

data/spec/integration/ask_for_account/cli_input.exp

@@ -0,0 +1,33 @@
+#!/usr/bin/expect -f
+
+
+set timeout 7
+match_max 100000
+expect "What is this account named in Ledger  |Assets:Bank:Checking|?\r
+\[1G▽\[6n"
+send -- "\[45;2R"
+expect -exact "\[1G\[K\[6n"
+send -- "\[45;1R"
+expect  "\[1G\[K\[1G\[1G"
+send -- "T"
+expect  "\[1GT\[K\[1G\[2G"
+send -- "e"
+expect "\[1GTe\[K\[1G\[3G"
+send -- "s"
+expect "\[1GTes\[K\[1G\[4G"
+send -- "t"
+expect "\[1GTest\[K\[1G\[5G"
+send -- ":"
+expect "\[1GTest:\[K\[1G\[6G"
+send -- ":"
+expect "\[1GTest::\[K\[1G\[7G"
+send -- "B"
+expect "\[1GTest::B\[K\[1G\[8G"
+send -- "a"
+expect "\[1GTest::Ba\[K\[1G\[9G"
+send -- "n"
+expect "\[1GTest::Ban\[K\[1G\[10G"
+send -- "k"
+expect "\[1GTest::Bank\[K\[1G\[11G"
+send -- "\r"
+expect eof

data/spec/integration/ask_for_account/expected_output

@@ -0,0 +1,11 @@
+
+    Date    |   Amount   |                    Description                     | Note |
+ 2003-12-24 |  $2,105.00 | CREDIT; Some Company vendorpymt PPD ID: 5KL3832735 |      |
+ 2004-12-24 |   -$116.22 |         CREDIT; PAYPAL TRANSFER PPD ID: PAYPALSDSL |      |
+ 2005-12-24 |     -$0.96 | DEBIT; WEBSITE-BALANCE-10DEC09 12 12/10WEBSITE-BAL |      |
+ 2006-12-24 |      $0.23 | DEBIT; WEBSITE-BALANCE-17DEC09 12 12/17WEBSITE-BAL |      |
+ 2007-12-24 |  $1,558.52 |     CREDIT; Blarg BLARG REVENUE PPD ID: 00jah78563 |      |
+ 2008-12-24 |  $3,520.00 | CREDIT; Some Company vendorpymt PPD ID: 59728JSL20 |      |
+ 2009-12-24 |     -$7.00 |       DEBIT; GITHUB 041287430274 CA 12/22GITHUB 04 |      |
+ 2010-12-24 |    -$20.00 |                                  CHECK; CHECK 2656 |      |
+ 2011-12-24 |    -$85.00 |         DEBIT; HOST 037196321563 MO 12/22SLICEHOST |      |

data/spec/integration/ask_for_account/input.csv

@@ -0,0 +1,9 @@
+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

data/spec/integration/ask_for_account/test_args

@@ -0,0 +1 @@
+-f input.csv -p

data/spec/integration/broker_canada_example/output.ledger

@@ -8,7 +8,7 @@
 
 2013-06-19	2013-06-24; Buy; ISHARES S&P/TSX CAPPED REIT IN; XRE; 300; 15.90; CDN; CAD
 	Income:Unknown			
-	Assets:Bank:Checking			-$4779.95
+	Assets:Bank:Checking			-$4,779.95
 
 2013-06-27	2013-06-27; Dividend; ICICI BK SPONSORED ADR; IBN; 100; USD
 	Assets:Bank:Checking			 $66.70
@@ -19,7 +19,7 @@
 	Income:Unknown			
 
 2014-01-07	2014-01-10; Sell; BMO NASDAQ 100 EQTY HEDGED TO; ZQQ; -300; 27.44; CDN; CAD
-	Assets:Bank:Checking			 $8222.05
+	Assets:Bank:Checking			 $8,222.05
 	Income:Unknown			
 
 2014-01-07	2014-01-07; Interest; BMO S&P/TSX EQUAL WEIGHT BKS I; ZEB; 250; CAD

data/spec/integration/chase/account_tokens_and_regex/output.ledger

@@ -1,5 +1,5 @@
 2009-12-10	CREDIT; Some Company vendorpymt PPD ID: 5KL3832735
-	Assets:Bank:Checking			 $2105.00
+	Assets:Bank:Checking			 $2,105.00
 	Income:Unknown			
 
 2009-12-11	CREDIT; PAYPAL TRANSFER PPD ID: PAYPALSDSL
@@ -15,11 +15,11 @@
 	Assets:Bank:Checking			-$12.23
 
 2009-12-23	CREDIT; Some Company vendorpymt PPD ID: 59728JSL20
-	Assets:Bank:Checking			 $3520.00
+	Assets:Bank:Checking			 $3,520.00
 	Income:Unknown			
 
 2009-12-23	CREDIT; Blarg BLARG REVENUE PPD ID: 00jah78563
-	Assets:Bank:Checking			 $1558.52
+	Assets:Bank:Checking			 $1,558.52
 	Income:Unknown			
 
 2009-12-24	DEBIT; GITHUB 041287430274 CA 12/22GITHUB 04

data/spec/integration/chase/default_account_names/output.ledger

@@ -1,5 +1,5 @@
 2009-12-10	CREDIT; Some Company vendorpymt PPD ID: 5KL3832735
-	Assets:Bank:Checking			 $2105.00
+	Assets:Bank:Checking			 $2,105.00
 	Income:Default			
 
 2009-12-11	CREDIT; PAYPAL TRANSFER PPD ID: PAYPALSDSL
@@ -15,11 +15,11 @@
 	Assets:Bank:Checking			-$12.23
 
 2009-12-23	CREDIT; Some Company vendorpymt PPD ID: 59728JSL20
-	Assets:Bank:Checking			 $3520.00
+	Assets:Bank:Checking			 $3,520.00
 	Income:Default			
 
 2009-12-23	CREDIT; Blarg BLARG REVENUE PPD ID: 00jah78563
-	Assets:Bank:Checking			 $1558.52
+	Assets:Bank:Checking			 $1,558.52
 	Income:Default			
 
 2009-12-24	DEBIT; GITHUB 041287430274 CA 12/22GITHUB 04

data/spec/integration/chase/learn_from_existing/output.ledger

@@ -1,5 +1,5 @@
 2009-12-10	CREDIT; Some Company vendorpymt PPD ID: 5KL3832735
-	Assets:Bank:Checking			 $2105.00
+	Assets:Bank:Checking			 $2,105.00
 	Income:Unknown			
 
 2009-12-11	CREDIT; PAYPAL TRANSFER PPD ID: PAYPALSDSL
@@ -15,11 +15,11 @@
 	Assets:Bank:Checking			-$12.23
 
 2009-12-23	CREDIT; Some Company vendorpymt PPD ID: 59728JSL20
-	Assets:Bank:Checking			 $3520.00
+	Assets:Bank:Checking			 $3,520.00
 	Income:Unknown			
 
 2009-12-23	CREDIT; Blarg BLARG REVENUE PPD ID: 00jah78563
-	Assets:Bank:Checking			 $1558.52
+	Assets:Bank:Checking			 $1,558.52
 	Income:Unknown			
 
 2009-12-24	DEBIT; GITHUB 041287430274 CA 12/22GITHUB 04

data/spec/integration/chase/simple/output.ledger

@@ -1,5 +1,5 @@
 2009-12-10	CREDIT; Some Company vendorpymt PPD ID: 5KL3832735
-	Assets:Bank:Checking			 $2105.00
+	Assets:Bank:Checking			 $2,105.00
 	Income:Unknown			
 
 2009-12-11	CREDIT; PAYPAL TRANSFER PPD ID: PAYPALSDSL
@@ -15,11 +15,11 @@
 	Assets:Bank:Checking			-$12.23
 
 2009-12-23	CREDIT; Some Company vendorpymt PPD ID: 59728JSL20
-	Assets:Bank:Checking			 $3520.00
+	Assets:Bank:Checking			 $3,520.00
 	Income:Unknown			
 
 2009-12-23	CREDIT; Blarg BLARG REVENUE PPD ID: 00jah78563
-	Assets:Bank:Checking			 $1558.52
+	Assets:Bank:Checking			 $1,558.52
 	Income:Unknown			
 
 2009-12-24	DEBIT; GITHUB 041287430274 CA 12/22GITHUB 04

data/spec/integration/danish_kroner_nordea_example/output.ledger

@@ -4,7 +4,7 @@
 
 2012-09-12	Dankort-nota B.J. TRADING E 14660; 12-09-2012; 26164,80
 	Expenses:Unknown			
-	Assets:Bank:Checking			-$3452.90
+	Assets:Bank:Checking			-$3,452.90
 
 2012-10-12	Visa kob DKK 995,00 WWW.ASOS.COM 00000; 12-10-2012; 27939,54
 	Expenses:Unknown			

data/spec/integration/extratofake/output.ledger

@@ -3,7 +3,7 @@
 	Income:Unknown			
 
 2012-11-01	Proventos; 496774
-	Assets:Bank:Checking			 $1000.00
+	Assets:Bank:Checking			 $1,000.00
 	Income:Unknown			
 
 2012-11-01	0000-9; Transferência on line - 01/11 4885 256620-6 XXXXXXXXXXXXX; 224885000256620

data/spec/integration/harder_date_example/output.ledger

@@ -1,5 +1,5 @@
 2009-11-04	TRANSFER CREDIT INTERNET TRANSFER; INTERNET TRANSFER; 1234.00
-	Assets:Bank:Checking			 $1234.00
+	Assets:Bank:Checking			 $1,234.00
 	Income:Unknown			
 
 2009-11-10	TRANSFER DEBIT INTERNET TRANSFER; INTERNET TRANSFER MORTGAGE; 0.00
@@ -16,5 +16,5 @@
 
 2011-11-04	TRANSFER DEBIT INTERNET TRANSFER; INTERNET TRANSFER SAV TO MECU; 0.00
 	Income:Unknown			
-	Assets:Bank:Checking			-$1234.00
+	Assets:Bank:Checking			-$1,234.00
 

data/spec/integration/test.sh

@@ -4,10 +4,12 @@
 
 set -Euo pipefail
 
+
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 TEST_DIFF=""
 OUTPUT=""
-RECKON_CMD="env RUBYLIB=$SCRIPT_DIR/../../lib:$RUBYLIB reckon -v"
+RECKON_CMD="reckon -v"
+export RUBYLIB=$SCRIPT_DIR/../../lib:${RUBYLIB:-}
 export PATH="$SCRIPT_DIR/../../bin:$PATH"
 
 main () {
@@ -21,16 +23,20 @@ main () {
 
     echo > test.log
 
+    NUM_TESTS=$(echo "$TESTS" |wc -l)
+
+    echo "1..$NUM_TESTS"
+
+    I=1
+
     for t in $TESTS; do
-        OUTPUT_FILE=$(mktemp)
         TEST_DIR=$(dirname "$t")
         pushd "$TEST_DIR" >/dev/null || exit 1
-        echo "$TEST_DIR Running..."
-        TEST_CMD="$RECKON_CMD -o $OUTPUT_FILE $(cat test_args)"
-        TEST_LOG=$(eval "$TEST_CMD" 2>&1)
-        ERROR=0
-
-        compare_output "$OUTPUT_FILE"
+        if [[ -e "cli_input.exp" ]]; then
+            cli_test
+        else
+            unattended_test
+        fi
 
         popd >/dev/null || exit 1
         # have to save output after popd
@@ -38,11 +44,41 @@ main () {
         echo -e "TEST_CMD\n$TEST_LOG" >> test.log
 
         if [[ $ERROR -ne 0 ]]; then
+            echo -e "not ok $I - $TEST_DIR"
+            tail -n25 test.log
             exit 1
+        else
+            echo -e "ok $I - $TEST_DIR"
         fi
+        I=$(($I + 1))
     done
 }
 
+cli_test () {
+    OUTPUT_FILE=$(mktemp)
+    TEST_CMD="$RECKON_CMD --table-output-file $OUTPUT_FILE $(cat test_args)"
+    TEST_CMD="expect -d -c 'spawn $TEST_CMD' cli_input.exp"
+    TEST_LOG=$(eval "$TEST_CMD" 2>&1)
+    ERROR=0
+    TEST_DIFF=$(diff -u "$OUTPUT_FILE" "expected_output")
+
+    # ${#} is character length, test that there was no output from diff
+    if [ ${#TEST_DIFF} -eq 0 ]; then
+        ERROR=0
+    else
+        ERROR=1
+    fi
+}
+
+unattended_test() {
+    OUTPUT_FILE=$(mktemp)
+    TEST_CMD="$RECKON_CMD -o $OUTPUT_FILE $(cat test_args)"
+    TEST_LOG=$(eval "$TEST_CMD" 2>&1)
+    ERROR=0
+
+    compare_output "$OUTPUT_FILE"
+}
+
 test_fail () {
     STATUS=$?
     if [[ $STATUS -ne 0 ]]; then
@@ -55,7 +91,13 @@ compare_output_for () {
     OUTPUT_FILE=$1
     LEDGER=$2
 
-    TEST_DIFF=$(diff -u <($LEDGER -f output.ledger r --date-format %F 2>&1) <($LEDGER -f "$OUTPUT_FILE" r --date-format %F 2>&1) )
+    EXPECTED_FILE=$(mktemp)
+    ACTUAL_FILE=$(mktemp)
+
+    $LEDGER -f output.ledger r >"$EXPECTED_FILE" 2>&1 || return 1
+    $LEDGER -f output.ledger r >"$ACTUAL_FILE" 2>&1 || return 1
+
+    TEST_DIFF=$(diff -u "$EXPECTED_FILE" "$ACTUAL_FILE")
 
     # ${#} is character length, test that there was no output from diff
     if [ ${#TEST_DIFF} -eq 0 ]; then
@@ -69,11 +111,9 @@ compare_output () {
     OUTPUT_FILE=$1
 
     for n in {ledger,hledger}; do
-        echo -n "  - $n..."
         if compare_output_for "$OUTPUT_FILE" "$n"; then
-            echo "SUCCESS!"
+            ERROR=0
         else
-            echo "FAILED!"
             ERROR=1
             return 0
         fi

data/spec/reckon/app_spec.rb

@@ -16,7 +16,7 @@ describe Reckon::App do
     describe "each_row_backwards" do
       it "should return rows with hashes" do
         @rows[0][:pretty_date].should == "2009-12-10"
-        @rows[0][:pretty_money].should == " $2105.00"
+        @rows[0][:pretty_money].should == " $2,105.00"
         @rows[0][:description].should == "CREDIT; Some Company vendorpymt PPD ID: 5KL3832735"
         @rows[1][:pretty_date].should == "2009-12-11"
         @rows[1][:pretty_money].should == " $116.22"

data/spec/reckon/csv_parser_spec.rb

@@ -242,7 +242,7 @@ describe Reckon::CSVParser do
   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(4).should == " $1,558.52"
       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"
@@ -251,7 +251,7 @@ describe Reckon::CSVParser do
     it "work with other currencies such as €" do
       euro_bank = Reckon::CSVParser.new(file: fixture_path('some_other.csv'), currency: "€", suffixed: false )
       euro_bank.pretty_money_for(1).should == "-€20.00"
-      euro_bank.pretty_money_for(4).should == " €1558.52"
+      euro_bank.pretty_money_for(4).should == " €1,558.52"
       euro_bank.pretty_money_for(7).should == "-€116.22"
       euro_bank.pretty_money_for(5).should == " €0.23"
       euro_bank.pretty_money_for(6).should == "-€0.96"
@@ -260,7 +260,7 @@ describe Reckon::CSVParser do
     it "work with suffixed currencies such as SEK" do
       swedish_bank = Reckon::CSVParser.new(file: fixture_path('some_other.csv'), currency: 'SEK', suffixed: true )
       swedish_bank.pretty_money_for(1).should == "-20.00 SEK"
-      swedish_bank.pretty_money_for(4).should == " 1558.52 SEK"
+      swedish_bank.pretty_money_for(4).should == " 1,558.52 SEK"
       swedish_bank.pretty_money_for(7).should == "-116.22 SEK"
       swedish_bank.pretty_money_for(5).should == " 0.23 SEK"
       swedish_bank.pretty_money_for(6).should == "-0.96 SEK"

data/spec/reckon/money_spec.rb

@@ -32,17 +32,17 @@ describe Reckon::Money do
   describe "pretty" do
     it "work with negative and positive numbers" do
       expect(Reckon::Money.new(-20.00).pretty).to eq("-$20.00")
-      expect(Reckon::Money.new(1558.52).pretty).to eq(" $1558.52")
+      expect(Reckon::Money.new(1558.52).pretty).to eq(" $1,558.52")
     end
 
     it "work with other currencies such as €" do
       expect(Reckon::Money.new(-20.00, currency: "€", suffixed: false).pretty).to eq("-€20.00")
-      expect(Reckon::Money.new(1558.52, currency: "€", suffixed: false).pretty).to eq(" €1558.52")
+      expect(Reckon::Money.new(1558.52, currency: "€", suffixed: false).pretty).to eq(" €1,558.52")
     end
 
     it "work with suffixed currencies such as SEK" do
       expect(Reckon::Money.new(-20.00, currency: "SEK", suffixed: true).pretty).to eq("-20.00 SEK")
-      expect(Reckon::Money.new(1558.52, currency: "SEK", suffixed: true).pretty).to eq(" 1558.52 SEK")
+      expect(Reckon::Money.new(1558.52, currency: "SEK", suffixed: true).pretty).to eq(" 1,558.52 SEK")
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: reckon
 version: !ruby/object:Gem::Version
-  version: 0.7.1
+  version: 0.7.2
 platform: ruby
 authors:
 - Andrew Cantino
@@ -10,7 +10,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-02-07 00:00:00.000000000 Z
+date: 2021-04-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -130,6 +130,7 @@ files:
 - lib/reckon/options.rb
 - lib/reckon/version.rb
 - reckon.gemspec
+- spec/cosine_training_and_test.rb
 - spec/data_fixtures/51-sample.csv
 - spec/data_fixtures/51-tokens.yml
 - spec/data_fixtures/73-sample.csv
@@ -162,6 +163,10 @@ files:
 - spec/integration/another_bank_example/input.csv
 - spec/integration/another_bank_example/output.ledger
 - spec/integration/another_bank_example/test_args
+- spec/integration/ask_for_account/cli_input.exp
+- spec/integration/ask_for_account/expected_output
+- spec/integration/ask_for_account/input.csv
+- spec/integration/ask_for_account/test_args
 - spec/integration/austrian_example/input.csv
 - spec/integration/austrian_example/output.ledger
 - spec/integration/austrian_example/test_args