workbook 0.5 → 0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bc0e6be07c59fd70553ab1c6e7be1b47259d44fc
-  data.tar.gz: 2c38be86478a4e7af84cdcd2b44b9df3353d6fa1
+  metadata.gz: ca12f4d088bcc71159ed61caae720bdc19457bc0
+  data.tar.gz: 95109a2df0f6c2c6759486fe94d3c61d28e4cf7d
 SHA512:
-  metadata.gz: 122ccd6febc910869615018a44e2e34323c5d870e417013b0a33777005c78e94afc0b174bea6c88b1ab9a5d53dc2e01ac6edf9927f4d2f2da673577bbc949a20
-  data.tar.gz: 58ab99448e24d2207c5412c67370dc10232d55a5a97eaf78f090c150db5d09eb39297d2c80e4daf95fad33412e54f2f1fe8b02f6e5a5a994164b5be749e8aa5f
+  metadata.gz: e7b4eef2a1fcb1d4600379b17c7a08584387ca188c8a13bb2bffc4fadbf0315585d8ed7e2d057b2e664970bbdd5e3ac38dff8d032f77b924dca9f0d1d2f1911a
+  data.tar.gz: 89b85aeca814d7fe4f3dc5b6fcab22452d8a496dd45d125f9ad2fb6582a3bfc88144573db7bd5964a68a1201792cd37094cae90f5c1c0d099e1cf208e1d11d1f

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.open("template.xls")
+    b = Workbook::Book.import("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.open("template.xls")
+    b = Workbook::Book.import("template.xls")
     table = b.sheet.table
     template_row = table[1]         # see above
     Order.where("created_at > ?", Time.now - 1.week).each do |order|
@@ -152,6 +152,5 @@ Workbook uses the following gems:
 * [ruby-ole](http://code.google.com/p/ruby-ole/) Used in the Spreadsheet Gem (Copyright © 2007-2010 Charles Lowe; MIT)
 * [FasterCSV](http://fastercsv.rubyforge.org/) Used for reading CSV (comma separated text) and TXT (tab separated text) files (Copyright © James Edward Gray II; GPL2 & Ruby License)
 * [rchardet](http://rubyforge.org/projects/rchardet) Used for detecting encoding in CSV and TXT importers (Copyright © JMHodges; LGPL)
-* [roo](https://github.com/roo-rb/roo) Temporarily used for reading the newer .xlsx files (without formatting) (Copyright © 2008-2014 Thomas Preymesser, Ben Woosley, MIT License)
 * [axslx](https://github.com/randym/axlsx) Used for writing the newer .xlsx files (with formatting) (Copyright © 2011, 2012 Randy Morgan, MIT License)
 * [Nokogiri](http://nokogiri.org/) Used for reading ODS documents (Copyright © 2008 - 2012 Aaron Patterson, Mike Dalessio, Charles Nutter, Sergio Arbeo, Patrick Mahoney, Yoko Harada; MIT Licensed)

data/lib/workbook/book.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+require 'open-uri'
 require 'workbook/writers/xls_writer'
 require 'workbook/writers/xlsx_writer'
 require 'workbook/writers/html_writer'
@@ -47,15 +48,15 @@ module Workbook
 
     # @param [Workbook::Sheet, Array] sheet    create a new workbook based on an existing sheet, or initialize a sheet based on the array
     # @return [Workbook::Book]
-    def initialize sheet=Workbook::Sheet.new([], self, options={})
+    def initialize sheet=nil
       if sheet.is_a? Workbook::Sheet
         self.push sheet
-      else
-        self.push Workbook::Sheet.new(sheet, self, options)
+      elsif sheet
+        self.push Workbook::Sheet.new(sheet, self, {})
       end
     end
 
-    # @return [Workbook::Format] returns the template describing how the document should be/is formatted
+    # @return [Workbook::Template] returns the template describing how the document should be/is formatted
     def template
       @template ||= Workbook::Template.new
     end
@@ -70,7 +71,7 @@ module Workbook
     #
     # @return [String] the title of the workbook
     def title
-      @title ? @title : "untitled document"
+      (defined?(@title) and !@title.nil?) ? @title : "untitled document"
     end
 
     def title= t
@@ -115,7 +116,7 @@ module Workbook
     # @param [String] filename   a string with a reference to the file to be opened
     # @param [String] extension  an optional string enforcing a certain parser (based on the file extension, e.g. 'txt', 'csv' or 'xls')
     # @return [Workbook::Book] A new instance, based on the filename
-    def open filename, extension=nil, options={}
+    def import filename, extension=nil, options={}
       extension = file_extension(filename) unless extension
       if ['txt','csv','xml'].include?(extension)
         open_text filename, extension, options
@@ -131,7 +132,7 @@ module Workbook
     # @return [Workbook::Book] A new instance, based on the filename
     def open_binary filename, extension=nil, options={}
       extension = file_extension(filename) unless extension
-      f = File.open(filename,'rb')
+      f = open(filename)
       send("load_#{extension}".to_sym, f, options)
     end
 
@@ -141,9 +142,7 @@ module Workbook
     # @param [String] extension  an optional string enforcing a certain parser (based on the file extension, e.g. 'txt', 'csv' or 'xls')
     def open_text filename, extension=nil, options={}
       extension = file_extension(filename) unless extension
-      f = File.open(filename,'r')
-      t = f.read
-      t = text_to_utf8(t)
+      t = text_to_utf8(open(filename).read)
       send("load_#{extension}".to_sym, t, options)
     end
 
@@ -183,7 +182,9 @@ module Workbook
     #
     # @return [String] The file extension
     def file_extension(filename)
-      File.extname(filename).gsub('.','').downcase if filename
+      ext = File.extname(filename).gsub('.','').downcase if filename
+      # for remote files which has asset id after extension
+      ext.split('?')[0]
     end
 
     # Load the CSV data contained in the given StringIO or String object
@@ -215,7 +216,7 @@ module Workbook
       # @return [Workbook::Book] A new instance, based on the filename
       def open filename, extension=nil
         wb = self.new
-        wb.open filename, extension
+        wb.import filename, extension
         return wb
       end
 

data/lib/workbook/column.rb

@@ -3,7 +3,7 @@ module Workbook
 
   # Column helps us to store general properties of a column, and lets us easily perform operations on values within a column
   class Column
-    attr_accessor :limit, :table #character limit
+    attr_accessor :limit, :width #character limit
 
     def initialize(table=nil, options={})
       self.table = table
@@ -12,12 +12,12 @@ module Workbook
 
     # Returns column type, either :primary_key, :string, :text, :integer, :float, :decimal, :datetime, :date, :binary, :boolean
     def column_type
-      return @column_type if @column_type
+      return @column_type if defined?(@column_type)
       ind = self.index
       table[1..500].each do |row|
         if row[ind] and row[ind].cell_type
           cel_column_type = row[ind].cell_type
-          if cel_column_type == @column_type or @column_type.nil?
+          if !defined?(@column_type) or @column_type.nil? or cel_column_type == @column_type
             @column_type = cel_column_type
           else
             @column_type = :string
@@ -33,9 +33,16 @@ module Workbook
       table.columns.index self
     end
 
-    def table= t
-      raise(ArgumentError, "value should be nil or Workbook::Table") unless [NilClass,Workbook::Table].include? t.class
-      @table = t
+    # Set the table this column belongs to
+    # @param [Workbook::Table] table this column belongs to
+    def table= table
+      raise(ArgumentError, "value should be nil or Workbook::Table") unless [NilClass,Workbook::Table].include? table.class
+      @table = table
+    end
+
+    # @return [Workbook::Table]
+    def table
+      @table
     end
 
     def column_type= column_type

data/lib/workbook/format.rb

@@ -24,7 +24,11 @@ module Workbook
     # @param [Workbook::Format, Hash] options (e.g. :background, :color, :background_color, :font_weight (integer or css-type labels)
     # @return [String] the name of the format, default: nil
     def initialize options={}, name=nil
-      options.each {|k,v| self[k]=v}
+      if options.is_a? String
+        name = options
+      else
+        options.each {|k,v| self[k]=v}
+      end
       self.name = name
     end
 
@@ -89,5 +93,16 @@ module Workbook
       formats.each{|a| ff.merge!(a) }
       return ff
     end
+
+    # Formatting is sometimes the only way to detect the cells' type.
+    def derived_type
+      if self[:numberformat]
+        if self[:numberformat].to_s.match("h")
+          :time
+        elsif self[:numberformat].to_s.match("y")
+          :date
+        end
+      end
+    end
   end
 end

data/lib/workbook/modules/cell.rb

@@ -1,6 +1,7 @@
 # -*- encoding : utf-8 -*-
 require 'workbook/modules/type_parser'
 require 'workbook/nil_value'
+require 'date'
 
 module Workbook
   module Modules
@@ -63,7 +64,7 @@ module Workbook
       #
       # @return [Symbol] the type of cell, compatible with Workbook::Column'types
       def cell_type
-        tp = case value.class.to_s
+        case value.class.to_s
         when "String" then :string
         when "FalseClass" then :boolean
         when "TrueClass" then :boolean
@@ -118,7 +119,7 @@ module Workbook
       # @return [Workbook::Format] the current format
       def format
         # return @workbook_format if @workbook_format
-        if row and template and row.header? and !@workbook_format
+        if row and template and row.header? and !defined?(@workbook_format)
           @workbook_format = template.create_or_find_format_by(:header)
         else
           @workbook_format ||= Workbook::Format.new

data/lib/workbook/modules/diff_sort.rb

@@ -105,7 +105,7 @@ module Workbook
       #
       # @return [Workbook::Table] the empty table, linked to a book
       def diff_template
-        return @diff_template if @diff_template
+        return @diff_template if defined?(@diff_template)
         diffbook = Workbook::Book.new_diff_template
         difftable = diffbook.sheet.table
         @diff_template ||= difftable
@@ -175,7 +175,7 @@ module Workbook
 
       # returns a placeholder row, for internal use only
       def placeholder_row
-        if @placeholder_row != nil
+        if defined?(@placeholder_row) and !@placeholder_row.nil?
           return @placeholder_row
         else
           @placeholder_row = Workbook::Row.new [nil]

data/lib/workbook/modules/type_parser.rb

@@ -13,7 +13,7 @@ module Workbook
       # Return the different active string parsers
       # @return [Array<Symbol>] A list of parsers
       def string_parsers
-        @string_parsers ||= [:string_cleaner,:string_nil_converter,:string_integer_converter,:string_boolean_converter]
+        @string_parsers ||= [:string_cleaner,:string_integer_converter,:string_boolean_converter]
       end
 
       # Set the list of string parsers
@@ -32,8 +32,9 @@ module Workbook
       # Returns the parsed value (retrieved by calling #value)
       # @return [Object] The parsed object, ideally a date or integer when found to be a such...
       def parse options={}
-        options = {:detect_date=>false}.merge(options)
+        options = {:detect_date=>false, :convert_empty_to_nil=>true}.merge(options)
         string_parsers.push :string_optimistic_date_converter if options[:detect_date]
+        string_parsers.push :string_nil_converter if options[:convert_empty_to_nil]
         v = value
         string_parsers_as_procs.each do |p|
           if v.is_a? String

data/lib/workbook/readers/xls_reader.rb

@@ -2,7 +2,6 @@
 require 'spreadsheet'
 require 'workbook/readers/xls_shared'
 
-
 module Workbook
   module Readers
     module XlsReader
@@ -16,9 +15,10 @@ module Workbook
         rescue Ole::Storage::FormatError => e
           begin
             # Assuming it is a tab separated txt inside .xls
-            open(file_obj.path, 'txt')
-          rescue
-            raise e
+            import(file_obj.path, 'txt')
+          rescue Exception => ef
+
+            raise ef
           end
         end
 

data/lib/workbook/readers/xls_shared.rb

@@ -1,4 +1,7 @@
 # -*- encoding : utf-8 -*-
+
+require 'date'
+
 module Workbook
   module Readers
     module XlsShared
@@ -8,6 +11,7 @@ module Workbook
       # @param [String, nil] ms_nr_format (nil returns nil)
       # @return [String, nil]
       def ms_formatting_to_strftime ms_nr_format
+        ms_nr_format = num_fmt_id_to_ms_formatting(ms_nr_format) if ms_nr_format.is_a? Integer
         if ms_nr_format
           ms_nr_format = ms_nr_format.to_s.downcase
           return nil if ms_nr_format == 'general' or ms_nr_format == ""
@@ -34,6 +38,33 @@ module Workbook
         end
       end
 
+      # Convert numFmtId to msmarkup
+      # @param [String, Integer] num_fmt_id numFmtId
+      # @return [String] number format (excel markup)
+      def num_fmt_id_to_ms_formatting num_fmt_id
+        # from: https://stackoverflow.com/questions/4730152/what-indicates-an-office-open-xml-cell-contains-a-date-time-value
+        {'0'=>nil, '1'=>'0', '2'=>'0.00', '3'=>'#,##0', '4'=>'#,##0.00',
+          '9'=>'0%', '10'=>'0.00%', '11'=>'0.00E+00', '12'=>'# ?/?',
+          '13'=>'# ??/??', '14'=>'mm-dd-yy', '15'=>'d-mmm-yy', '16'=>'d-mmm',
+          '17'=>'mmm-yy', '18'=>'h:mm AM/PM', '19'=>'h:mm:ss AM/PM',
+          '20'=>'h:mm', '21'=>'h:mm:ss', '22'=>'m/d/yy h:mm',
+          '37'=>'#,##0 ;(#,##0)', '38'=>'#,##0 ;[Red](#,##0)',
+          '39'=>'#,##0.00;(#,##0.00)', '40'=>'#,##0.00;[Red](#,##0.00)',
+          '44'=>'_("$"* #,##0.00_);_("$"* \(#,##0.00\);_("$"* "-"??_);_(@_)',
+          '45'=>'mm:ss', '46'=>'[h]:mm:ss', '47'=>'mmss.0', '48'=>'##0.0E+0',
+          '49'=>'@', '27'=>'[$-404]e/m/d', '30'=>'m/d/yy', '36'=>'[$-404]e/m/d',
+          '50'=>'[$-404]e/m/d', '57'=>'[$-404]e/m/d', '59'=>'t0', '60'=>'t0.00',
+          '61'=>'t#,##0', '62'=>'t#,##0.00', '67'=>'t0%', '68'=>'t0.00%',
+          '69'=>'t# ?/?', '70' => 't# ??/??'}[num_fmt_id.to_s]
+      end
+
+
+
+
+
+
+
+
       # Attempt to convert html-hex color value to xls color number
       #
       # @param [String] hex color
@@ -54,6 +85,14 @@ module Workbook
         return numberformat.gsub('%Y','yyyy').gsub('%A','dddd').gsub('%B','mmmm').gsub('%a','ddd').gsub('%b','mmm').gsub('%y','yy').gsub('%d','dd').gsub('%m','mm').gsub('%y','y').gsub('%y','%%y').gsub('%e','d')
       end
 
+      def xls_number_to_time number, base_date = DateTime.new(1899,12,30)
+        base_date + number.to_f
+      end
+
+      def xls_number_to_date number, base_date = Date.new(1899,12,30)
+        base_date + number.to_i
+      end
+
       XLS_COLORS = {:xls_color_1=>'#000000',
         :xls_color_2=>'#FFFFFF',
         :xls_color_3=>'#FF0000',

data/lib/workbook/readers/xlsx_reader.rb

@@ -1,39 +1,177 @@
 # -*- encoding : utf-8 -*-
-require 'roo'
 require 'workbook/readers/xls_shared'
 
-
 module Workbook
   module Readers
     module XlsxReader
       include Workbook::Readers::XlsShared
 
-      # Load method for .xlsm files, an office open file format, hence compatible with .xlsx (it emphasizes that it contains macros)
-      #
-      # @param [String, File] file_obj   a string with a reference to the file to be written to
       def load_xlsm file_obj, options={}
         self.load_xlsx file_obj, options
       end
       def load_xlsx file_obj, options={}
         file_obj = file_obj.path if file_obj.is_a? File
-        # file_obj = file_obj.match(/^\/(.*)/) ? file_obj : "./#{file_obj}"
-        # p "opening #{file_obj}"
-        sp = Roo::Excelx.new(file_obj)
-        template.add_raw sp, raw_object_class: Roo::Spreadsheet
-        parse_xlsx sp
-      end
-
-      def parse_xlsx xlsx_spreadsheet=template.raws[Roo::Spreadsheet], options={}
-        options = {:additional_type_parsing=>false}.merge options
-        sheet_index = 0
-        xlsx_spreadsheet.each_with_pagename do |sheet_name, sheet|
-          s = create_or_open_sheet_at(sheet_index)
-          sheet.each_with_index do |row, rowi|
-            s.table << row
+        sheets = {}
+        shared_string_file = ""
+        styles = ""
+        workbook = ""
+        workbook_rels = ""
+        Zip::File.open(file_obj) do |zipfile|
+          zipfile.entries.each do |file|
+            if file.name.match(/^xl\/worksheets\/(.*)\.xml$/)
+              sheets[file.name.sub(/^xl\//,'')] = zipfile.read(file.name)
+            elsif file.name.match(/xl\/sharedStrings.xml$/)
+              shared_string_file = zipfile.read(file.name)
+            elsif file.name.match(/xl\/workbook.xml$/)
+              workbook = zipfile.read(file.name)
+            elsif file.name.match(/xl\/_rels\/workbook.xml.rels$/)
+              workbook_rels = zipfile.read(file.name)
+            elsif file.name.match(/xl\/styles.xml$/)
+              styles = zipfile.read(file.name)
+            end
+            # content = zipfile.read(file.name) if file.name == "content.xml"
+          end
+        end
+
+        parse_xlsx_styles(styles)
+
+
+        relation_file = {}
+        Nokogiri::XML(workbook_rels).css("Relationships Relationship").each do |relship|
+          relation_file[relship.attr("Id")]=relship.attr("Target")
+        end
+
+        @shared_strings = parse_shared_string_file(shared_string_file)
+
+        Nokogiri::XML(workbook).css("sheets sheet").each do |sheet|
+          name = sheet.attr("name")
+          filename = relation_file[sheet.attr("r:id")]
+          state = sheet.attr("state")
+          if state != "hidden"
+            sheet = sheets[filename]
+            self.push parse_xlsx_sheet(sheet)
+            self.last.name = name
+          end
+        end
+
+        @shared_strings = nil
+        self.each do |sheet|
+          sheet.each do |table|
+            table.trim!
           end
-          sheet_index += 1
         end
       end
+
+      def parse_xlsx_styles(styles)
+        styles = Nokogiri::XML(styles)
+
+        fonts = parse_xlsx_fonts styles
+        backgrounds = extract_xlsx_backgrounds styles
+        customNumberFormats = extract_xlsx_number_formats styles
+
+
+        styles.css("cellXfs xf").each do |cellformat|
+          hash = {}
+          # <xf numFmtId="0" fontId="1" fillId="2" borderId="0" xfId="0" applyFont="1" applyFill="1" applyAlignment="1">
+          background_hash = backgrounds[cellformat.attr("applyFill").to_i]
+          hash.merge!(background_hash) if background_hash
+
+          font_hash = fonts[cellformat.attr("applyFill").to_i]
+          hash.merge!(font_hash) if font_hash
+
+          id = (cellformat.attr("numFmtId")).to_i
+          if id >= 164
+            hash[:numberformat] = customNumberFormats[id]
+          else
+            hash[:numberformat] = ms_formatting_to_strftime(id)
+          end
+          self.template.add_format Workbook::Format.new(hash)
+        end
+      end
+
+      # Extracts fonts descriptors from styles.xml
+      def parse_xlsx_fonts styles
+        styles.css("fonts font").collect do |font|
+          hash = {}
+          hash[:font_family] = font.css("name").first.attr("val") if font.css("name")
+          hash[:font_size] = font.css("sz").first.attr("val").to_i if font.css("name")
+          hash
+        end
+      end
+
+      # Extracts number formats from styles.xml
+      def extract_xlsx_number_formats styles
+        hash = {}
+        styles.css("numFmts numFmt").each do |fmt|
+          format_id = fmt.attr("numFmtId").to_i
+          parsed_format_string = ms_formatting_to_strftime(fmt.attr("formatCode"))
+          hash[format_id] = parsed_format_string
+        end
+        hash
+      end
+
+      def extract_xlsx_backgrounds styles
+        styles.css("fills fill").collect do |fill|
+          hash = {}
+          patternFill = fill.css("patternFill").first
+          # TODO: convert to html-hex
+          hash[:background] = patternFill.attr("patternType") if patternFill
+          hash
+        end
+      end
+
+      def parse_shared_string_file file
+        Nokogiri::XML(file).css("sst si t").collect{|a| a.text}
+      end
+      def parse_xlsx_sheet sheet_xml
+        sheet = Workbook::Sheet.new
+        table = sheet.table
+
+        noko_xml = Nokogiri::XML(sheet_xml)
+
+        rows = noko_xml.css('sheetData row').collect{|row| parse_xlsx_row(row)}
+        rows.each do |row|
+          table << row
+        end
+
+        columns = noko_xml.css('cols col').collect{|col| parse_xlsx_column(col) }
+        table.columns = columns
+
+        sheet
+      end
+
+      def parse_xlsx_column column
+        col = Workbook::Column.new()
+        col.width = column.attr("width").to_f
+        col
+      end
+      def parse_xlsx_row row
+        cells = row.css('c').collect{|a| parse_xlsx_cell(a)}
+        row = Workbook::Row.new(cells)
+      end
+      def parse_xlsx_cell cell
+        # style_id = cell.attr('s')
+        # p cell
+        type = cell.attr('t')
+        formatIndex = cell.attr('s').to_i
+        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 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)
+      end
+      def parse_xlsx
+      end
     end
   end
-end
+end