roo 1.0.2 → 1.1.0

data/History.txt

@@ -1,3 +1,10 @@
+== 1.1.0 2008-07-26
+* 2 major enhancements
+  * Excel: speed improvements
+  * Changed the behaviour of reading files with the false type
+* 2 bugfixex
+  * Excel: last_row in Excel class did not work properly under some circumstances
+  * all: fixed a bug in #to_xml if there is an empty sheet
 == 1.0.2 2008-07-04
 * 2 bugfixes
   * Excelx: fixed a bug when there are .xml.rels files in the XLSX archive

data/Manifest.txt

@@ -21,6 +21,7 @@ test/false_encoding.xls
 test/Bibelbund1.ods
 test/Bibelbund.ods
 test/Bibelbund.xls
+test/Bibelbund.xlsx
 test/Bibelbund.csv
 test/bbu.xls
 test/bbu.xlsx
@@ -55,6 +56,8 @@ test/bode-v1.xls.zip
 test/bode-v1.ods.zip
 test/ric.ods
 test/bug-row-column-fixnum-float.xls
+test/emptysheets.ods
+test/emptysheets.xls
 website/index.html
 website/index.txt
 website/javascripts/rounded_corners_lite.inc.js

data/Rakefile

@@ -106,8 +106,22 @@ end
 desc 'Generate and upload website files'
 task :website => [:website_generate, :website_upload]
 
+#-- prey: BEGIN
+require 'fileutils'
+include FileUtils::Verbose
+desc 'Test the local installation'
+task :test_local_installation do
+  # gehe nach $GEM_PATH und starte dort rake test
+  # cd(ENV['GEM_PATH']+"roo-1.1.0") do
+  cd("/usr/lib/ruby/gems/1.8/gems/roo-1.1.0") do
+    sh %{sudo rake test}
+  end
+  puts 'local installation test done'
+end
+#-- prey: END
+
 desc 'Release the website and new gem version'
-task :deploy => [:check_log_params, :check_version, :website, :release ] do
+task :deploy => [:check_log_params, :check_version, :test_local_installation, :website, :release ] do
   puts "Remember to create SVN tag:"
   puts "svn copy svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/trunk " +
     "svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/tags/REL-#{VERS} "

data/lib/roo/excel.rb

@@ -20,16 +20,20 @@ class Excel < GenericSpreadsheet
 
   # Creates a new Excel spreadsheet object.
   # Parameter packed: :zip - File is a zip-file
-  def initialize(filename, packed = nil)
+  def initialize(filename, packed = nil, file_warning = :error)
+    super()
+    @file_warning = file_warning
     @tmpdir = "oo_"+$$.to_s
     unless File.exists?(@tmpdir)
       FileUtils::mkdir(@tmpdir)
     end
     filename = open_from_uri(filename) if filename[0,7] == "http://"
     filename = unzip(filename) if packed and packed == :zip
-    if File.extname(filename) != ".xls"
-      warn "are you sure, this is an excel file?"
-    end
+    #if File.extname(filename).downcase != ".xls"
+    #  warn "are you sure, this is an excel file?"
+    #end
+    #@file_warning = :error
+    file_type_check(filename,'.xls','an Excel')
     @filename = filename
     begin
       unless File.file?(@filename)
@@ -45,12 +49,16 @@ class Excel < GenericSpreadsheet
       #if ENV["roo_local"] != "thomas-p"
     ensure
       FileUtils::rm_r(@tmpdir)
-    #end
+      #end
     end
+    @cell = Hash.new
+    @cell_type = Hash.new
+    @formula = Hash.new
     @first_row = Hash.new
     @last_row = Hash.new
     @first_column = Hash.new
     @last_column = Hash.new
+    @header_line = 1
     @cells_read = Hash.new
   end
 
@@ -68,18 +76,7 @@ class Excel < GenericSpreadsheet
           @workbook.worksheet(i).name
         )
       else
-        # result << platform_specific_iconv(inject_null_characters(@workbook.worksheet(i).name))
         result << platform_specific_iconv(@workbook.worksheet(i).name)
-        #case RUBY_PLATFORM.downcase
-        #when /darwin/
-        #  result << Iconv.new('utf-8','utf-8').iconv(
-        #    @workbook.worksheet(i).name
-        #  )
-        #else
-        #  result << Iconv.new('utf-8','unicode').iconv(
-        #    @workbook.worksheet(i).name
-        #  )
-        #end # case
       end
     end
     return result
@@ -101,127 +98,31 @@ class Excel < GenericSpreadsheet
   # returns the content of a cell. The upper left corner is (1,1) or ('A',1)
   def cell(row,col,sheet=nil)
     sheet = @default_sheet unless sheet
+    read_cells(sheet) unless @cells_read[sheet]
     row,col = normalize(row,col)
-    worksheet = @workbook.worksheet(sheet_no(sheet))
-    skip = 0
-    line = 1
-    worksheet.each(skip) { |row_par| #TODO: nicht jedesmal durch alle Zeilen gehen, sonder aus interner Repraesentation holen?
-      if line == row
-        if row_par == nil
-          return nil
-        end
-        cell = row_par.at(col-1)
-        return nil unless cell
-        case cell.type
-        when :numeric then return cell.to_f
-        when :text then return cell.to_s('utf-8')
-          # when :date then return cell.date
-        when :date 
-          if cell.to_s.to_f < 1.0
-            f = cell.to_s.to_f*24.0*60.0*60.0
-            secs = f.round
-            h = (secs / 3600.0).floor
-            secs = secs - 3600*h
-            m = (secs / 60.0).floor
-            secs = secs - 60*m
-            s = secs
-            return h*3600+m*60+s
-          else
-            return cell.date
-          end
-        else
-          return nil # cell.to_s('utf-8')
-        end
-      end
-      line += 1
-    }
+    if celltype(row,col,sheet) == :date
+      yyyy,mm,dd = @cell[sheet]["#{row},#{col}"].split('-')
+      return Date.new(yyyy.to_i,mm.to_i,dd.to_i)
+    end
+    return @cell[sheet]["#{row},#{col}"]
   end
 
-  # returns the type of a cell: :float, :string, :date, :time
+  # returns the type of a cell:
+  # * :float
+  # * :string,
+  # * :date
+  # * :percentage
+  # * :formula
+  # * :time
   def celltype(row,col,sheet=nil)
     sheet = @default_sheet unless sheet
+    read_cells(sheet) unless @cells_read[sheet]
     row,col = normalize(row,col)
-
-    worksheet = @workbook.worksheet(sheet_no(sheet))
-    skip = 0
-    line = 1
-    worksheet.each(skip) { |row_par|
-      if line == row
-        return nil unless row_par
-        cell = row_par.at(col-1)
-        return nil unless cell
-        case cell.type
-        when :numeric
-          return :float
-        when :text
-          return :string
-        when :date
-          if cell.to_s.to_f < 1.0
-            return :time
-          else
-            return :date
-          end
-        else
-          return cell.type.to_sym
-        end
-      end
-      line += 1
-    }
-  end
-
-  # returns all values in this row as an array
-  # row numbers are 1,2,3,... like in the spreadsheet
-  def row(rownumber,sheet=nil)
-    sheet = @default_sheet unless sheet
-    worksheet = @workbook.worksheet(sheet_no(sheet))
-    #therow = worksheet.row(rownumber-1)
-    result = []
-    worksheet.row(rownumber-1).each {|cell|
-      if cell
-        case cell.type
-        when :numeric then result << cell.to_f
-        when :text then result << cell.to_s('utf-8')
-        when :date then result << cell.date
-        else
-          result << cell.to_s('utf-8')
-        end
-      else
-        result << nil
-      end
-    }
-    return result
-  end
-
-  # returns all values in this column as an array
-  # column numbers are 1,2,3,... like in the spreadsheet
-  def column(columnnumber,sheet=nil)
-    if columnnumber.class == String
-      columnnumber = Openoffice.letter_to_number(columnnumber)
+    if @formula[sheet]["#{row},#{col}"]
+      return :formula
+    else
+      @cell_type[sheet]["#{row},#{col}"]
     end
-    sheet = @default_sheet unless sheet
-    worksheet = @workbook.worksheet(sheet_no(sheet))
-    skip = 0
-    result = []
-    worksheet.each(skip) { |row_par|
-      if defined? row_par.at(columnnumber-1)
-        cell = row_par.at(columnnumber-1)
-        #if defined? cell = row_par.at(columnnumber-1)
-        if cell
-          case cell.type
-          when :numeric then result << cell.to_f
-          when :text    then result << cell.to_s('utf-8')
-          when :date    then result << cell.date
-          else
-            result << cell.to_s('utf-8')
-          end
-        else
-          result << nil
-        end
-      else
-        result << nil
-      end
-    }
-    result
   end
 
   # returns the first non empty column
@@ -304,7 +205,9 @@ class Excel < GenericSpreadsheet
       # parsexcel liefert (mir unverstaendlich) eine Zeile als letzte Zeile
       # zurueck, die aber leer ist. Deshalb Korrekturfunktion, die wirklich
       # die letzte nicht leere Zeile liefert.
-      while empty_row? row(lr,sheet)
+      # 2008-07-23 meine Loesung funtionierte auch noch nicht unter allen
+      # Umstaenden row() == nil ergaenzt
+      while row(lr,sheet) == nil || empty_row?(row(lr,sheet))
         lr -= 1
       end
     end
@@ -332,9 +235,8 @@ class Excel < GenericSpreadsheet
 
   def empty_row?(row)
     content = false
-    row.each {|elem|
+    row.compact.each {|elem|
       if elem != ''
-        #if elem.class == String and elem.size > 0
         content = true
       end
     }
@@ -380,4 +282,82 @@ class Excel < GenericSpreadsheet
     result
   end
 
+  # helper function to set the internal representation of cells
+  def set_cell_values(sheet,x,y,i,v,vt,formula,tr,str_v)
+    key = "#{y},#{x+i}"
+    @cell_type[sheet] = {} unless @cell_type[sheet]
+    @cell_type[sheet][key] = vt 
+    @formula[sheet] = {} unless @formula[sheet]
+    @formula[sheet][key] = formula  if formula
+    @cell[sheet]    = {} unless @cell[sheet]
+    case @cell_type[sheet][key]
+    when :float
+      @cell[sheet][key] = v.to_f
+    when :string
+      @cell[sheet][key] = str_v
+    when :date
+      @cell[sheet][key] = v 
+    when :percentage
+      @cell[sheet][key] = v.to_f
+    when :time
+      @cell[sheet][key] = v 
+    else
+      @cell[sheet][key] = v
+    end
+  end
+
+  # read all cells in the selected sheet
+  def read_cells(sheet=nil)
+    sheet = @default_sheet unless sheet
+    raise ArgumentError, "Error: sheet '#{sheet||'nil'}' not valid" if @default_sheet == nil and sheet==nil
+    raise RangeError unless self.sheets.include? sheet
+    worksheet = @workbook.worksheet(sheet_no(sheet))
+    skip = 0
+    x =1
+    y=1
+    i=0
+    worksheet.each(skip) { |row_par| 
+      if row_par
+        x =1
+        row_par.each do # |void|  
+          cell = row_par.at(x-1)
+          if cell
+            case cell.type
+            when :numeric
+              vt = :float
+              v = cell.to_f
+            when :text
+              vt = :string
+              str_v = cell.to_s('utf-8')
+            when :date
+              if cell.to_s.to_f < 1.0
+                vt = :time
+                f = cell.to_s.to_f*24.0*60.0*60.0
+                secs = f.round
+                h = (secs / 3600.0).floor
+                secs = secs - 3600*h
+                m = (secs / 60.0).floor
+                secs = secs - 60*m
+                s = secs
+                v = h*3600+m*60+s
+              else
+                vt = :date
+                v = cell.date
+                v = sprintf("%04d-%02d-%02d",v.year,v.month,v.day)
+              end
+            else
+              vt = cell.type.to_sym
+              v = nil
+            end # case
+            formula = tr = nil #TODO:???
+            set_cell_values(sheet,x,y,i,v,vt,formula,tr,str_v)
+          end # if cell
+          x += 1
+        end
+      end
+      y += 1
+    }
+    @cells_read[sheet] = true
+  end
+
 end

data/lib/roo/excelx.rb

@@ -5,7 +5,7 @@ require 'fileutils'
 require 'zip/zipfilesystem'
 require 'date'
 #require 'base64'
-require 'logger'
+
 class  String
   def end_with?(str)
     self[-str.length,str.length] == str
@@ -13,22 +13,24 @@ class  String
 end
 
 class Excelx < GenericSpreadsheet
-  #$log = Logger.new("excelx.log",5,100*1024)
-  #$log.level = Logger::DEBUG
   @@nr = 0
 
   # initialization and opening of a spreadsheet file
   # values for packed: :zip
-  def initialize(filename, packed=nil) #, create = false)
+  def initialize(filename, packed=nil, file_warning = :error) #, create = false)
+    super()
+    @file_warning = file_warning
     @tmpdir = "oo_"+$$.to_s
     unless File.exists?(@tmpdir)
       FileUtils::mkdir(@tmpdir)
     end
     filename = open_from_uri(filename) if filename[0,7] == "http://"
     filename = unzip(filename) if packed and packed == :zip
-    if File.extname(filename) != ".xlsx"
-      warn "are you sure, this is an Excel-xlsx file?"
-    end
+    #if File.extname(filename).downcase != ".xlsx"
+    #  warn "are you sure, this is an Excel-xlsx file?"
+    #end
+    #@file_warning = :error
+    file_type_check(filename,'.xlsx','an Excel-xlsx')
     @cells_read = Hash.new
     @filename = filename
     begin
@@ -72,6 +74,7 @@ class Excelx < GenericSpreadsheet
     @first_column = Hash.new
     @last_column = Hash.new
     @header_line = 1
+    @excelx_type = Hash.new
   end
 
   # Returns the content of a spreadsheet-cell.
@@ -106,7 +109,7 @@ class Excelx < GenericSpreadsheet
   # true, if there is a formula
   def formula?(row,col,sheet=nil)
     sheet = @default_sheet unless sheet
-    read_cells unless @cells_read[sheet]
+    read_cells(sheet) unless @cells_read[sheet]
     row,col = normalize(row,col)
     formula(row,col) != nil
   end
@@ -134,17 +137,30 @@ class Excelx < GenericSpreadsheet
   # * :string,
   # * :date
   # * :percentage
+  # * :formula
+  # * :time
   def celltype(row,col,sheet=nil)
     sheet = @default_sheet unless sheet
     read_cells(sheet) unless @cells_read[sheet]
     row,col = normalize(row,col)
-    if @formula and @formula[sheet] and @formula[sheet]["#{row},#{col}"]
+    # if @formula and @formula[sheet] and @formula[sheet]["#{row},#{col}"]
+    if @formula[sheet]["#{row},#{col}"]
       return :formula
     else
       @cell_type[sheet]["#{row},#{col}"]
     end
   end
 
+  # returns the internal type of a excel cell
+  # * :numeric_or_formula
+  # * :string  
+  def excelx_type(row,col,sheet=nil)
+   sheet = @default_sheet unless sheet
+    read_cells(sheet) unless @cells_read[sheet]
+    row,col = normalize(row,col)
+    :numeric_or_formula
+  end
+  
   # returns an array of sheet names in the spreadsheet
   def sheets
     return_sheets = []
@@ -168,43 +184,6 @@ class Excelx < GenericSpreadsheet
     @cell[sheet].inspect
   end
 
-  # returns all values in this row as an array
-  # row numbers are 1,2,3,... like in the spreadsheet
-  def row(rownumber,sheet=nil)
-    sheet = @default_sheet unless sheet
-    read_cells(sheet) unless @cells_read[sheet]
-    result = []
-    tmp_arr = []
-    @cell[sheet].each_pair {|key,value|
-      y,x = key.split(',')
-      x = x.to_i
-      y = y.to_i
-      if y == rownumber
-        tmp_arr[x] = value
-      end
-    }
-    result = tmp_arr[1..-1]
-    while result[-1] == nil
-      result = result[0..-2]
-    end
-    result
-  end
-
-  # returns all values in this column as an array
-  # column numbers are 1,2,3,... like in the spreadsheet
-  def column(columnnumber,sheet=nil)
-    if columnnumber.class == String
-      columnnumber = GenericSpreadsheet.letter_to_number(columnnumber)
-    end
-    sheet = @default_sheet unless sheet
-    read_cells(sheet) unless @cells_read[sheet]
-    result = []
-    first_row(sheet).upto(last_row(sheet)) do |row|
-      result << cell(row,columnnumber,sheet)
-    end
-    result
-  end
-
   # returns each formula in the selected sheet as an array of elements
   # [row, col, formula]
   def formulas(sheet=nil)
@@ -225,7 +204,7 @@ class Excelx < GenericSpreadsheet
   private
 
   # helper function to set the internal representation of cells
-  def set_cell_values(sheet,x,y,i,v,vt,formula,tr,str_v)
+  def set_cell_values(sheet,x,y,i,v,vt,formula,tr,str_v,excelx_type=nil)
     key = "#{y},#{x+i}"
     @cell_type[sheet] = {} unless @cell_type[sheet]
     @cell_type[sheet][key] = vt
@@ -244,10 +223,12 @@ class Excelx < GenericSpreadsheet
     when :time
       #hms = v.split(':')
       #@cell[sheet][key] = hms[0].to_i*3600 + hms[1].to_i*60 + hms[2].to_i
-    @cell[sheet][key] = v.to_f*(24*60*60)
+      @cell[sheet][key] = v.to_f*(24*60*60)
     else
       @cell[sheet][key] = v
     end
+    @excelx_type[sheet] = {} unless @excelx_type[sheet]
+    @excelx_type[sheet][key] = excelx_type
   end
 
   def split_coord(s)
@@ -258,7 +239,7 @@ class Excelx < GenericSpreadsheet
       letter += s[i,1]
       i+=1
     end
-    while i<s.length and "01234567890".include?(s[i,1])
+    while i<s.length and "0123456789".include?(s[i,1])
       number = number*10 + s[i,1].to_i
       i+=1
     end
@@ -276,10 +257,11 @@ class Excelx < GenericSpreadsheet
   end
 
   # read all cells in the selected sheet
-  def read_cells(sheet=nil)
+  def ALTER_ANSATZ_read_cells(sheet=nil)
     sheet = @default_sheet unless sheet
     sheet_found = false
     raise ArgumentError, "Error: sheet '#{sheet||'nil'}' not valid" if @default_sheet == nil and sheet==nil
+ raise RangeError unless self.sheets.include? sheet
     n = self.sheets.index(sheet)
     @sheet_doc[n].each_element do |worksheet|
       worksheet.each_element do |elem|
@@ -291,8 +273,9 @@ class Excelx < GenericSpreadsheet
                   if row.attributes['t'] == 's'
                     tmp_type = :shared
                   end
-                  if row.attributes['s'] == '2'
-                    tmp_type = :date
+                  if row.attributes['s'] == '2' #or
+                     #row.attributes['s'] == '1' # 2008-07-26
+                    tmp_type = :time
                   elsif row.attributes['s'] == '1' and row.attributes['t'] == nil # and ergaenzt 2008-07-03
                     tmp_type = :formula
                   end
@@ -305,8 +288,17 @@ class Excelx < GenericSpreadsheet
                     end
                     if cell.name == 'v'
                       if tmp_type == :formula and f_element_found == false
+                        #if cell.text.to_f < 1.0 # 2008-07-26
                         tmp_type = :time
+                        #else # 2008-07-26
+                        #tmp_type = :date #2008-07-26
+                        #end #2008-07-26
                       end
+                      if tmp_type == :time #2008-07-26
+                        if cell.text.to_f >= 1.0 # 2008-07-26
+                          tmp_type = :date # 2008-07-26
+                        end # 2008-07-26
+                      end # 2008-07-26
                       if tmp_type == :shared
                         vt = :string
                         str_v = @shared_table[cell.text.to_i]
@@ -326,7 +318,86 @@ class Excelx < GenericSpreadsheet
                       x,y = split_coordinate(row.attributes['r'])
                       tr=nil #TODO: ???s
                       set_cell_values(sheet,x,y,0,v,vt,formula,tr,str_v)
-                    #$log.debug "#{sheet},#{x},#{y},0,#{v},#{vt},#{formula},#{tr},#{str_v})"
+                    end
+                  end
+                end
+              end
+            end
+          end
+        end
+      end
+    end
+    sheet_found = true #TODO:
+    if !sheet_found
+      raise RangeError
+    end
+    @cells_read[sheet] = true
+  end
+
+# read all cells in the selected sheet
+  def read_cells(sheet=nil)
+    sheet = @default_sheet unless sheet
+    sheet_found = false
+    raise ArgumentError, "Error: sheet '#{sheet||'nil'}' not valid" if @default_sheet == nil and sheet==nil
+ raise RangeError unless self.sheets.include? sheet
+    n = self.sheets.index(sheet)
+    @sheet_doc[n].each_element do |worksheet|
+      worksheet.each_element do |elem|
+        if elem.name == 'sheetData'
+          elem.each_element do |sheetdata|
+            if sheetdata.name == 'row'
+              sheetdata.each_element do |row|
+                if row.name == 'c'
+                  if row.attributes['t'] == 's'
+                    tmp_type = :shared
+                  end
+                  if row.attributes['s'] == '2' #or
+                     #row.attributes['s'] == '1' # 2008-07-26
+                    tmp_type = :time
+                  elsif row.attributes['s'] == '1' and row.attributes['t'] == nil # and ergaenzt 2008-07-03
+                    tmp_type = :formula
+                  end
+                  formula = nil
+                  f_element_found = false
+                  row.each_element do |cell|
+                    if cell.name == 'f'
+                      f_element_found = true
+                      formula = cell.text
+                    end
+                    if cell.name == 'v'
+                      if tmp_type == :formula and f_element_found == false
+                        #if cell.text.to_f < 1.0 # 2008-07-26
+                        tmp_type = :time
+                        #else # 2008-07-26
+                        #tmp_type = :date #2008-07-26
+                        #end #2008-07-26
+                      end
+                      if tmp_type == :time #2008-07-26
+                        if cell.text.to_f >= 1.0 # 2008-07-26
+                          tmp_type = :date # 2008-07-26
+                        end # 2008-07-26
+                      end # 2008-07-26
+                      excelx_type = :numeric_or_formula
+                      if tmp_type == :shared
+                        vt = :string
+                        str_v = @shared_table[cell.text.to_i]
+                        excelx_type = :string
+                      elsif tmp_type == :date
+                        vt = :date
+                        v = cell.text
+                      elsif tmp_type == :time
+                        vt = :time
+                        v = cell.text
+                      elsif tmp_type == :formula
+                        vt = :formula
+                        v = cell.text.to_f #TODO: !!!!
+                      else
+                        vt = :float
+                        v = cell.text
+                      end
+                      x,y = split_coordinate(row.attributes['r'])
+                      tr=nil #TODO: ???s
+                      set_cell_values(sheet,x,y,0,v,vt,formula,tr,str_v,excelx_type)
                     end
                   end
                 end