workbook 0.6 → 0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ca12f4d088bcc71159ed61caae720bdc19457bc0
-  data.tar.gz: 95109a2df0f6c2c6759486fe94d3c61d28e4cf7d
+  metadata.gz: e6be5061a431a70bb33a5f09f77260bc6b43c806
+  data.tar.gz: c29da70505ab5d7e16820ec96c28600388ed56d3
 SHA512:
-  metadata.gz: e7b4eef2a1fcb1d4600379b17c7a08584387ca188c8a13bb2bffc4fadbf0315585d8ed7e2d057b2e664970bbdd5e3ac38dff8d032f77b924dca9f0d1d2f1911a
-  data.tar.gz: 89b85aeca814d7fe4f3dc5b6fcab22452d8a496dd45d125f9ad2fb6582a3bfc88144573db7bd5964a68a1201792cd37094cae90f5c1c0d099e1cf208e1d11d1f
+  metadata.gz: 6880c1ea1b7bc8bd49c27a7e19a08ffa74f7e62e628a9dfe4fb81c1a0cac65bc83099d428ec2973d9fc2ea7742a9faa6eb677866050efdbd2c4d2e8616431c3d
+  data.tar.gz: 54a41200b7ec799da9920120426fc2e883d208a1afd1dfdb135c5639316ec499316142b756e2265edf1134bcfb5bb55343d44d82667e04c52f81c63b9e77c0e7

data/README.md

@@ -59,7 +59,7 @@ Alternatively (more spreadsheet like) you can read cells like this (writing to b
 If you want to use an existing file as a template (which you can create in Excel to create nice looking templates),
 simply clone the row, and add it back:
 
-    b = Workbook::Book.import("template.xls")
+    b = Workbook::Book.open("template.xls")
     table = b.sheet.table
     template_row = table[1]            # can be any, but I typically have a well
                                     # formatted header row + an example template
@@ -78,7 +78,7 @@ simply clone the row, and add it back:
 Another typical use case is exporting a list of ActiveRecord-objects to xls (it is assumed that the headers of the excel-table correspond
 (like "Total order price" and `total_order_price` match) to the headers of the database-table ):
 
-    b = Workbook::Book.import("template.xls")
+    b = Workbook::Book.open("template.xls")
     table = b.sheet.table
     template_row = table[1]         # see above
     Order.where("created_at > ?", Time.now - 1.week).each do |order|

data/lib/workbook/column.rb

@@ -76,6 +76,18 @@ module Workbook
       @default = Cell.new(value)
     end
 
-
+    class << self
+      # Helps to convert from e.g. "AA" to 26
+      # @param [String] string that typically identifies a column
+      # @return [Integer]
+      def alpha_index_to_number_index string
+        string.upcase!
+        sum = 0
+        string.chars.each_with_index do | char, char_index|
+          sum = sum * 26 + char.unpack('U')[0]-64
+        end
+        return sum-1
+      end
+    end
   end
 end

data/lib/workbook/format.rb

@@ -99,7 +99,7 @@ module Workbook
       if self[:numberformat]
         if self[:numberformat].to_s.match("h")
           :time
-        elsif self[:numberformat].to_s.match("y")
+        elsif self[:numberformat].to_s.match(/y/i)
           :date
         end
       end

data/lib/workbook/modules/diff_sort.rb

@@ -52,21 +52,24 @@ module Workbook
       # create an overview of the differences between itself with another 'previous' table, returns a book with a single sheet and table (containing the diffs)
       #
       # @return [Workbook::Table] the return result
-      def diff other, options={:sort=>true,:ignore_headers=>false}
+      def diff other, options={}
+        options = {:sort=>true,:ignore_headers=>false}.merge(options)
 
         aligned = align(other, options)
         aself = aligned[:self]
         aother = aligned[:other]
+
         iteration_cols = []
         if options[:ignore_headers]
           iteration_cols = [aother.first.count,aself.first.count].max.times.collect
         else
           iteration_cols = (aother.header.to_symbols+aother.header.to_symbols).uniq
         end
+
         diff_table = diff_template
         maxri = (aself.count-1)
+
         for ri in 0..maxri do
-          row = diff_table[ri]
           row = diff_table[ri] = Workbook::Row.new(nil, diff_table)
           srow = aself[ri]
           orow = aother[ri]
@@ -74,24 +77,7 @@ module Workbook
           iteration_cols.each_with_index do |ch, ci|
             scell = srow[ch]
             ocell = orow[ch]
-            dcell = scell.nil? ? Workbook::Cell.new(nil) : scell
-            if (scell == ocell)
-              dcell.format = scell.format if scell
-            elsif scell.nil?
-              dcell = Workbook::Cell.new "(was: #{ocell.to_s})"
-              dcell.format = diff_template.template.create_or_find_format_by 'destroyed'
-            elsif ocell.nil?
-              dcell = scell.clone
-              fmt = scell.nil? ? :default : scell.format[:number_format]
-              f = diff_template.template.create_or_find_format_by 'created', fmt
-              f[:number_format] = scell.format[:number_format]
-              dcell.format = f
-            elsif scell != ocell
-              dcell = Workbook::Cell.new "#{scell.to_s} (was: #{ocell.to_s})"
-              f = diff_template.template.create_or_find_format_by 'updated'
-              dcell.format = f
-            end
-            row[ci]=dcell
+            row[ci] = create_diff_cell(scell, ocell)
           end
         end
         if !options[:ignore_headers]
@@ -101,6 +87,31 @@ module Workbook
         diff_table
       end
 
+      # creates a new cell describing the difference between two cells
+      #
+      # @return [Workbook::Cell] the diff cell
+      def create_diff_cell(scell, ocell)
+        dcell = scell.nil? ? Workbook::Cell.new(nil) : scell
+        if (scell == ocell)
+          dcell.format = scell.format if scell
+        elsif scell.nil?
+          dcell = Workbook::Cell.new "(was: #{ocell.to_s})"
+          dcell.format = diff_template.template.create_or_find_format_by 'destroyed'
+        elsif ocell.nil?
+          dcell = scell.clone
+          fmt = scell.nil? ? :default : scell.format[:number_format]
+          f = diff_template.template.create_or_find_format_by 'created', fmt
+          f[:number_format] = scell.format[:number_format]
+          dcell.format = f
+        elsif scell != ocell
+          dcell = Workbook::Cell.new "#{scell.to_s} (was: #{ocell.to_s})"
+          f = diff_template.template.create_or_find_format_by 'updated'
+          dcell.format = f
+        end
+
+        dcell
+      end
+
       # Return template table to write the diff result in; in case non exists a default is generated.
       #
       # @return [Workbook::Table] the empty table, linked to a book

data/lib/workbook/readers/csv_reader.rb

@@ -20,16 +20,18 @@ module Workbook
       def parse_csv csv_raw, options={}
         custom_date_converter = Workbook::Cell.new.string_optimistic_date_converter
         options = {
-          converters: [:float,:integer,:date,:date_time,custom_date_converter]
+          converters: [:all,custom_date_converter]
         }.merge(options)
 
         csv=nil
-        #begin
-        csv = csv_lib.parse(csv_raw,options)
+        begin
+          csv = csv_lib.parse(csv_raw,options)
 
-        #rescue
-        # we're going to have another shot at it...
-        #end
+        rescue CSV::MalformedCSVError
+          csv_excel = csv_lib.parse(csv_raw,options.merge({:col_sep=>';'}))
+          csv = csv_excel if csv_excel[0].count > 1
+
+        end
 
         if csv==nil or csv[0].count == 1
           csv_excel = csv_lib.parse(csv_raw,options.merge({:col_sep=>';'}))

data/lib/workbook/readers/xls_reader.rb

@@ -12,7 +12,7 @@ module Workbook
           sp = Spreadsheet.open(file_obj, 'rb')
           template.add_raw sp
           parse_xls sp, options
-        rescue Ole::Storage::FormatError => e
+        rescue Ole::Storage::FormatError
           begin
             # Assuming it is a tab separated txt inside .xls
             import(file_obj.path, 'txt')

data/lib/workbook/readers/xlsx_reader.rb

@@ -146,29 +146,53 @@ module Workbook
         col
       end
       def parse_xlsx_row row
-        cells = row.css('c').collect{|a| parse_xlsx_cell(a)}
-        row = Workbook::Row.new(cells)
+        cells_with_pos = row.css('c').collect{|a| parse_xlsx_cell(a)}
+        row = Workbook::Row.new
+        cells_with_pos.each do |cell_with_pos|
+          position = cell_with_pos[:position]
+          col = position.match(/^[A-Z]*/).to_s
+          row[col] = cell_with_pos[:cell]
+        end
+        row = pad_xlsx_row(row)
+        row
+      end
+
+      def pad_xlsx_row(row)
+        row.each_with_index do |cell, index|
+          row[index]=Workbook::Cell.new(nil) if cell.nil? and !cell.is_a?(Workbook::Cell)
+        end
+        row
       end
+
       def parse_xlsx_cell cell
         # style_id = cell.attr('s')
         # p cell
         type = cell.attr('t')
         formatIndex = cell.attr('s').to_i
+        position = cell.attr('r')
+        formula = cell.css('f').text()
         value = cell.text
         fmt = template.formats[formatIndex]
+
         # puts type
         if type == "n" or type == nil
           if fmt.derived_type == :date
             value = xls_number_to_date(value)
           elsif fmt.derived_type == :time
             value = xls_number_to_time(value)
+          elsif formula == "TRUE()"
+            value = true
+          elsif formula == "FALSE()"
+            value = false
           elsif type == "n"
             value = value.match(/\./) ? value.to_f : value.to_i
           end
         elsif type == "s"
           value = @shared_strings[value.to_i]
         end
-        Workbook::Cell.new(value, format: fmt)
+        cell = Workbook::Cell.new(value, format: fmt)
+        cell.formula = formula
+        {cell: cell, position: position}
       end
       def parse_xlsx
       end

data/lib/workbook/row.rb

@@ -18,8 +18,9 @@ module Workbook
       cells = [] if cells==nil
       self.table= table
       cells.each do |c|
-        c = c.clone if options[:clone_cells]
-        unless c.is_a? Workbook::Cell
+        if c.is_a? Workbook::Cell
+          c = c.clone if options[:clone_cells]
+        else
           c = Workbook::Cell.new(c, {row:self})
           c.parse!(options[:cell_parse_options]) if options[:parse_cells_on_batch_creation]
         end
@@ -91,10 +92,11 @@ module Workbook
     end
 
 
-    # Overrides normal Array's []-function with support for symbols that identify a column based on the header-values
+    # Overrides normal Array's []-function with support for symbols that identify a column based on the header-values and / or
     #
     # @example Lookup using fixnum or header value encoded as symbol
     #   row[1] #=> <Cell value="a">
+    #   row["A"] #=> <Cell value="a">
     #   row[:a] #=> <Cell value="a">
     #
     # @param [Fixnum, Symbol, String] index_or_hash that identifies the column (strings are converted to symbols)
@@ -107,6 +109,9 @@ module Workbook
         rescue NoMethodError
         end
         return rv
+      elsif index_or_hash.is_a? String and index_or_hash.match(/^[A-Z]*$/)
+        # it looks like a column indicator
+        return to_a[Workbook::Column.alpha_index_to_number_index(index_or_hash)]
       elsif index_or_hash.is_a? String
         symbolized = Workbook::Cell.new(index_or_hash, {row:self}).to_sym
         self[symbolized]
@@ -130,6 +135,9 @@ module Workbook
       index = index_or_hash
       if index_or_hash.is_a? Symbol
         index = table_header_keys.index(index_or_hash)
+      elsif index_or_hash.is_a? String and index_or_hash.match(/^[A-Z]*$/)
+        # it looks like a column indicator
+        index = Workbook::Column.alpha_index_to_number_index(index_or_hash)
       elsif index_or_hash.is_a? String
         symbolized = Workbook::Cell.new(index_or_hash, {row:self}).to_sym
         index = table_header_keys.index(symbolized)

data/lib/workbook/table.rb

@@ -177,7 +177,7 @@ module Workbook
     def [](index_or_string)
       if index_or_string.is_a? String
         match = index_or_string.match(/([A-Z]+)([0-9]*)/i)
-        col_index = alpha_index_to_number_index(match[1])
+        col_index = Workbook::Column.alpha_index_to_number_index(match[1])
         row_index = match[2].to_i - 1
         return self[row_index][col_index]
       elsif index_or_string.is_a? Range
@@ -201,7 +201,7 @@ module Workbook
     def []= (index_or_string, new_value)
       if index_or_string.is_a? String
         match = index_or_string.upcase.match(/([A-Z]*)([0-9]*)/)
-        cell_index = alpha_index_to_number_index(match[1])
+        cell_index = Workbook::Column.alpha_index_to_number_index(match[1])
         row_index = match[2].to_i - 1
         self[row_index][cell_index].value = new_value
       else
@@ -212,18 +212,6 @@ module Workbook
       end
     end
 
-    # Helps to convert from e.g. "AA" to 26
-    # @param [String] string that typically identifies a column
-    # @return [Integer]
-    def alpha_index_to_number_index string
-      string.upcase!
-      sum = 0
-      string.chars.each_with_index do | char, char_index|
-        sum = sum * 26 + char.unpack('U')[0]-64
-      end
-      return sum-1
-    end
-
     # remove all the trailing empty-rows (returning a trimmed clone)
     #
     # @param [Integer] desired_row_length of the rows

data/lib/workbook/version.rb

@@ -1,4 +1,4 @@
 # -*- encoding : utf-8 -*-
 module Workbook
-  VERSION = '0.6'
+  VERSION = '0.7'
 end

data/test/artifacts/semicolonseparated_in_csv.csv

@@ -0,0 +1,3 @@
+artikel;aantal;bedrag;reservering;aanmaaktijd_reservering;gastnummer;titel;voorletters;tussenvoegsels;naam;straat;huisnummer;postcode;woonplaats;email;tel_land;tel_net;tel_abon
+"Vriend - € 50";1;50.00;123;2016-10-27;7891;asdf;A.;;asdf;"asdf ";55;"1234 LM";AMSTERDAM;a@example.com;053;;123123
+"Vriend - € 35";1;35.00;123;2016-11-02;5676;"Dasdfr";B.;;asdf;"asdf asdf";12;"1234 NN";UTRECHT;b@example.com;+31;074;123123

data/test/test_column.rb

@@ -51,4 +51,15 @@ class TestColumn < Minitest::Test
     t[2].delete_at(3)
     assert_equal([:boolean, :float, :string, :integer], t.columns.collect{|a| a.column_type})
   end
+
+  def test_alpha_index_to_number_index
+    assert_equal(0,Workbook::Column.alpha_index_to_number_index("A"))
+    assert_equal(2,Workbook::Column.alpha_index_to_number_index("C"))
+    assert_equal(25,Workbook::Column.alpha_index_to_number_index("Z"))
+    assert_equal(26,Workbook::Column.alpha_index_to_number_index("AA"))
+    assert_equal(27,Workbook::Column.alpha_index_to_number_index("AB"))
+    assert_equal(51,Workbook::Column.alpha_index_to_number_index("AZ"))
+    assert_equal(52,Workbook::Column.alpha_index_to_number_index("BA"))
+    assert_equal((27*26)-1,Workbook::Column.alpha_index_to_number_index("ZZ"))
+  end
 end

data/test/test_readers_csv_reader.rb

@@ -99,5 +99,9 @@ module Readers
       w = Workbook::Book.read("2013-03-19,JV,211,032,1,DBG A,,13,0147,\n", :csv, {converters: []})
       assert_equal("2013-03-19,JV,211,032,1,DBG A,,13,0147,\n",w.sheet.table.to_csv)
     end
+    def test_semi_colon_separated_csv
+      w = Workbook::Book.open(File.join(File.dirname(__FILE__), 'artifacts/semicolonseparated_in_csv.csv'))
+      assert_equal("artikel,aantal,bedrag,reservering,aanmaaktijd_reservering,gastnummer,titel,voorletters,tussenvoegsels,naam,straat,huisnummer,postcode,woonplaats,email,tel_land,tel_net,tel_abon\nVriend - € 50,1,50.0,123,2016-10-27,7891,asdf,A.,,asdf,asdf ,55,1234 LM,AMSTERDAM,a@example.com,43,,123123\nVriend - € 35,1,35.0,123,2016-11-02,5676,Dasdfr,B.,,asdf,asdf asdf,12,1234 NN,UTRECHT,b@example.com,31,60,123123\n", w.sheet.table.to_csv)
+    end
   end
 end

data/test/test_readers_txt_reader.rb

@@ -39,7 +39,7 @@ module Readers
       assert_equal(Date.new(2012,2,22),w.sheet.table[1][:a].value)
       assert_equal("c",w.sheet.table[2][:a].value)
       assert_equal(DateTime.new(2012,1,22,11),w.sheet.table[3][:a].value)
-      assert_equal(42000,w.sheet.table[3][:b].value)
+      assert_equal("42000",w.sheet.table[3][:b].value.to_s)
       assert_nil(w.sheet.table[2][:c].value)
     end
 

data/test/test_readers_xlsx_reader.rb

@@ -33,9 +33,30 @@ module Readers
       assert_equal("2",w.sheet.table[1][1].value.to_s)
       assert_equal(2,w.sheet.table[1][1].value)
     end
+    def test_different_types_xlsx
+      w = Workbook::Book.open File.join(File.dirname(__FILE__), 'artifacts/excel_different_types.xlsx')
+      t = w.sheet.table
+      assert_equal("ls",t["D4"].value)
+      assert_equal(true,t["C3"].value)
+      assert_equal("c",t["C1"].value)
+      assert_equal(222,t["B3"].value)
+      assert_equal(4.23,t["C2"].value)
+      assert(t["A4"].value.is_a?(Date))
+      assert((DateTime.new(2012,1,22,11)-t["A4"].value) < 0.00001)
+      assert_equal(42000,t["B4"].value)
+      assert_equal(42000.22323,t["D2"].value)
+      assert(t["A2"].value.is_a?(Date))
+      assert((Date.new(2012,2,22)-t["A2"].value) < 0.00001)
+      assert((Date.new(2014,12,27)-t["B2"].value) < 0.00001)
+    end
     def test_bit_table_xlsx
       b = Workbook::Book.open File.join(File.dirname(__FILE__), 'artifacts/bigtable.xlsx')
       assert_equal(553, b.sheet.table.count)
     end
+    def test_xlsx_with_empty_start
+      b = Workbook::Book.open File.join(File.dirname(__FILE__), 'artifacts/xlsx_with_empty_start.xlsx')
+      t = b.sheet.table
+      assert_nil(t["A3"].value)
+    end
   end
 end

data/test/test_row.rb

@@ -244,13 +244,22 @@ class TestRow < Minitest::Test
     row[1]= 12
     assert_equal(12, table.last["b"])
     assert_nil(table.last["a"])
+  end
 
+  def test_find_by_column_string
+    b = Workbook::Book.new
+    table = b.sheet.table
+    table << Workbook::Row.new(["b","a"])
+    row = Workbook::Row.new([],table)
+    row[1]= 12
+    assert_equal(12, table.last["B"])
+    assert_nil(table.last["A"])
   end
 
   def test_row_hash_index_string_assignment
     b = Workbook::Book.new
     table = b.sheet.table
-    table << Workbook::Row.new(["a","b"])
+    table << Workbook::Row.new(["a","b","d"])
     row = Workbook::Row.new([],table)
     row[1]= 12
     assert_equal(12, table.last.last.value)
@@ -258,6 +267,8 @@ class TestRow < Minitest::Test
     assert_equal(15, table.last.last.value)
     row["b"]= 18
     assert_equal(18, table.last.last.value)
+    row["C"]= 2
+    assert_equal(2, table.last[2].value)
   end
 
   def test_trim!

data/test/test_table.rb

@@ -111,19 +111,6 @@ class TestTable< Minitest::Test
     assert_equal(4,t["B4"].value)
   end
 
-  def test_alpha_index_to_number_index
-    w = Workbook::Book.new
-    t = w.sheet.table
-    assert_equal(0,t.alpha_index_to_number_index("A"))
-    assert_equal(2,t.alpha_index_to_number_index("C"))
-    assert_equal(25,t.alpha_index_to_number_index("Z"))
-    assert_equal(26,t.alpha_index_to_number_index("AA"))
-    assert_equal(27,t.alpha_index_to_number_index("AB"))
-    assert_equal(51,t.alpha_index_to_number_index("AZ"))
-    assert_equal(52,t.alpha_index_to_number_index("BA"))
-    assert_equal((27*26)-1,t.alpha_index_to_number_index("ZZ"))
-  end
-
   def test_multirowselect_through_collections
     w = Workbook::Book.new [["a","b"],[1,2],[3,4]]
     t = w.sheet.table

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: workbook
 version: !ruby/object:Gem::Version
-  version: '0.6'
+  version: '0.7'
 platform: ruby
 authors:
 - Maarten Brouwers
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-03-06 00:00:00.000000000 Z
+date: 2017-03-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-prof
@@ -199,6 +199,7 @@ files:
 - test/artifacts/heavy.xlsx
 - test/artifacts/integer_test.xlsx
 - test/artifacts/native_xlsx.xlsx
+- test/artifacts/semicolonseparated_in_csv.csv
 - test/artifacts/sheet_with_combined_cells.ods
 - test/artifacts/sheetduplication.xls
 - test/artifacts/simple_csv.csv
@@ -209,6 +210,7 @@ files:
 - test/artifacts/simple_sheet_many_sheets.xls
 - test/artifacts/txt_in_xls.xls
 - test/artifacts/xls_with_txt_extension.txt
+- test/artifacts/xlsx_with_empty_start.xlsx
 - test/artifacts/zip_in_xls.xls
 - test/helper.rb
 - test/test_book.rb
@@ -278,6 +280,7 @@ test_files:
 - test/artifacts/heavy.xlsx
 - test/artifacts/integer_test.xlsx
 - test/artifacts/native_xlsx.xlsx
+- test/artifacts/semicolonseparated_in_csv.csv
 - test/artifacts/sheet_with_combined_cells.ods
 - test/artifacts/sheetduplication.xls
 - test/artifacts/simple_csv.csv
@@ -288,6 +291,7 @@ test_files:
 - test/artifacts/simple_sheet_many_sheets.xls
 - test/artifacts/txt_in_xls.xls
 - test/artifacts/xls_with_txt_extension.txt
+- test/artifacts/xlsx_with_empty_start.xlsx
 - test/artifacts/zip_in_xls.xls
 - test/helper.rb
 - test/test_book.rb