donibuchanan-roo 1.3.12 → 1.9.1.4

data/History.txt

@@ -1,3 +1,23 @@
+== 1.9.2 2009-?????
+
+* 1 bugfix
+  * double quoting of '"' fixed
+
+== 1.9.1 2009-11-10
+
+* 2 bugfixes
+  * syntax in nokogiri methods
+  * missing dependency ...rubyzip
+
+== 1.9.0 2009-10-29
+
+* 4 enhancements
+  * Ruby 1.9 compatible
+  * oo.aa42 as a shortcut of oo.cell('aa',42)
+  * oo.aa42('sheet1') as a shortcut of oo.cell('aa',42,'sheet1')
+  * oo.anton as a reference to a cell labelled 'anton' (or any other label name)
+    (currently only for Openoffice spreadsheets)
+
 == 1.2.3 2009-01-04
 
 * bugfix
@@ -89,8 +109,8 @@
   * some methods common to more than one class were factored out to the GenericSpreadsheet (virtual) class
 == 0.7.0 2007-11-23
 * 6 enhancements:
-  * Openoffice/Excel: the most methods can be called with an option 'sheet' 
-    parameter which will be used instead of the default sheet 
+  * Openoffice/Excel: the most methods can be called with an option 'sheet'
+    parameter which will be used instead of the default sheet
   * Excel: improved the speed of CVS output
   * Openoffice/Excel: new method #column
   * Openoffice/Excel: new method #find
@@ -118,7 +138,7 @@
 == 0.5.1 2007-08-26
 * 4 enhancements:
   * Openoffice: Exception if an illegal sheet-name is selected
-  * Openoffice/Excel: no need to set a default_sheet if there is only one in 
+  * Openoffice/Excel: no need to set a default_sheet if there is only one in
     the document
   * Excel: can now read zip-ed files
   * Excel: can now read files from http://-URL over the net
@@ -136,7 +156,7 @@
 == 0.4.0 2007-06-27
 * 7 enhancements:
   * robustness: Exception if no default_sheet was set
-  * new method reload() implemented 
+  * new method reload() implemented
   * about 15 % more method documentation
   * optimization: huge increase of speed (no need to use fixed borders anymore)
   * added the method 'formulas' which gives you all formulas in a spreadsheet
@@ -158,7 +178,7 @@
 
 == 0.2.6 2007-06-19
 * 1 bugfix:
-  * Openoffice: two or more consecutive cells with string content failed 
+  * Openoffice: two or more consecutive cells with string content failed
 
 == 0.2.5 2007-06-17
 
@@ -188,7 +208,7 @@
 
 == 0.2.2 2007-06-01
 * 1 bugfix:
-  * incorrect dependencies fixed 
+  * incorrect dependencies fixed
 
 == 0.2.0 2007-06-01
 * 1 major enhancement:

data/lib/roo/excel.rb

@@ -1,4 +1,7 @@
+require 'rubygems'
 require 'spreadsheet'
+#require 'lib/roo/generic_spreadsheet'
+#require 'parseexcel'
 CHARGUESS = begin
   require 'charguess'
   true
@@ -9,6 +12,26 @@ end
 # The Spreadsheet library has a bug in handling Excel 
 # base dates so if the file is a 1904 base date then 
 # dates are off by a day. 1900 base dates work fine
+module Spreadsheet
+  module Excel
+    class Row < Spreadsheet::Row
+      def _date data # :nodoc:
+        return data if data.is_a?(Date)
+        date = @worksheet.date_base + data.to_i
+        if LEAP_ERROR > @worksheet.date_base
+          date -= 1
+        end
+        date
+      end
+      public :_datetime
+    end
+  end
+end
+
+#=====================================================================
+# TODO:
+# redefinition of this method, the method in the spreadsheet gem has a bug
+# redefinition can be removed, if spreadsheet does it in the correct way
 module Spreadsheet
   module Excel
     class Row < Spreadsheet::Row
@@ -38,45 +61,10 @@ module Spreadsheet
         end
         DateTime.new(date.year, date.month, date.day, hour, min, sec)
       end
-      public :_date
-      public :_datetime
-    end
-    # patch for ruby-spreadsheet parsing formulas
-    class Reader
-      def read_formula worksheet, addr, work
-        row, column, xf, rtype, rval, rcheck, opts = work.unpack 'v3CxCx3v2'
-        formula = Formula.new
-        formula.shared = (opts & 0x08) > 0
-        formula.data = work[20..-1]
-        if rcheck != 0xffff || rtype > 3 
-          value, = work.unpack 'x6E'
-          unless value
-            # on architectures where sizeof(double) > 8
-            value, = work.unpack 'x6e'
-          end
-          formula.value = value
-        elsif rtype == 0
-          pos, op, len, work = get_next_chunk
-          if op == :string
-            formula.value = client read_string(work, 2), @workbook.encoding
-          else
-            # This seems to work but I don't know why :). It at least
-            # seems to correct the case we saw but doubtful it's the right fix
-            formula.value = client read_string(work[10..-1], 2), @workbook.encoding
-          end
-        elsif rtype == 1
-          formula.value = rval > 0
-        elsif rtype == 2
-          formula.value = Error.new rval
-        else
-          # leave the Formula value blank
-        end
-        set_cell worksheet, row, column, xf, formula
-      end
     end
   end
 end
-
+#=====================================================================
 
 # ruby-spreadsheet has a font object so we're extending it 
 # with our own functionality but still providing full access
@@ -86,9 +74,9 @@ module ExcelFontExtensions
     #From ruby-spreadsheet doc: 100 <= weight <= 1000, bold => 700, normal => 400
     case weight
     when 700    
-     true
+      true
     else
-     false
+      false
     end   
   end
 
@@ -134,6 +122,7 @@ class Excel < GenericSpreadsheet
       #end
     end
     @cell = Hash.new
+    @read_first_100_rows = Hash.new
     @cell_type = Hash.new
     @formula = Hash.new
     @first_row = Hash.new
@@ -158,8 +147,11 @@ class Excel < GenericSpreadsheet
   def cell(row,col,sheet=nil)
     sheet = @default_sheet unless sheet
     raise ArgumentError unless sheet
-    read_cells(sheet) unless @cells_read[sheet]
-    raise "should be read" unless @cells_read[sheet]
+     unless @cells_read[sheet] or (@read_first_100_rows[sheet] and row < 100)
+        read_cells(sheet) 
+        raise "should be read" unless @cells_read[sheet]
+    end
+  
     row,col = normalize(row,col)
     if celltype(row,col,sheet) == :date
       yyyy,mm,dd = @cell[sheet][[row,col]].split('-')
@@ -182,7 +174,9 @@ class Excel < GenericSpreadsheet
   # * :datetime
   def celltype(row,col,sheet=nil)
     sheet = @default_sheet unless sheet
-    read_cells(sheet) unless @cells_read[sheet]
+     unless @cells_read[sheet] or (@read_first_100_rows[sheet] and row < 100)
+        read_cells(sheet) 
+    end
     row,col = normalize(row,col)
     begin
       if @formula[sheet][[row,col]]
@@ -227,6 +221,41 @@ class Excel < GenericSpreadsheet
     @cell[sheet].inspect
   end
 
+   # returns the row,col values of the labelled cell
+  # (nil,nil) if label is not defined
+  # sheet parameter is not really needed because label names are global
+  # to the whole spreadsheet
+  def label(labelname,sheet=nil)
+    sheet = @default_sheet unless sheet
+    read_cells(sheet) unless @cells_read[sheet]
+    if @labels.has_key? labelname
+      return @labels[labelname][1].to_i,
+        GenericSpreadsheet.letter_to_number(@labels[labelname][2]),
+        @labels[labelname][0]
+    else
+      return nil,nil,nil
+    end
+  end
+  def first_row(sheet=nil)
+    if sheet == nil
+      sheet = @default_sheet
+    end
+    read_first_100_rows(sheet) unless @read_first_100_rows[sheet] or @cells_read[sheet]
+    if @first_row[sheet]
+      return @first_row[sheet]
+    end
+    impossible_value = 999_999 # more than a spreadsheet can hold
+    result = impossible_value
+    @cell[sheet].each_pair {|key,value|
+      y,x = key # _to_string(key).split(',')
+      y = y.to_i
+      result = [result, y].min if value
+    } if @cell[sheet]
+    result = nil if result == impossible_value
+    @first_row[sheet] = result
+    result
+  end
+  
   private
 
   # converts name of a sheet to index (0,1,2,..)
@@ -338,9 +367,14 @@ class Excel < GenericSpreadsheet
       @cell[sheet][key] = v
     end
   end
-
+  
+  def read_first_100_rows(sheet=nil)
+    read_cells(sheet, 100)
+    @cells_read[sheet] = false
+    @read_first_100_rows[sheet] = true
+  end
   # read all cells in the selected sheet
-  def read_cells(sheet=nil)
+  def read_cells(sheet=nil, limit=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
@@ -353,6 +387,7 @@ class Excel < GenericSpreadsheet
     row_index=1
     worksheet.each(0) do |row| 
       (0..row.size).each do |cell_index|
+        
         cell = row.at(cell_index)
         next if cell.nil?  #skip empty cells
         next if cell.class == Spreadsheet::Formula && cell.value.nil? # skip empty formla cells
@@ -368,6 +403,9 @@ class Excel < GenericSpreadsheet
         set_cell_values(sheet,row_index,col_index,0,v,vt,formula,tr,font)
       end #row
       row_index += 1
+      unless limit.nil? or (row_index < limit )
+        break
+      end
     end # worksheet
     @cells_read[sheet] = true
   end
@@ -414,8 +452,8 @@ class Excel < GenericSpreadsheet
         datetime = row.datetime(idx)
       end    
       if datetime.hour != 0 or
-         datetime.min != 0 or
-         datetime.sec != 0 
+          datetime.min != 0 or
+          datetime.sec != 0
         value_type = :datetime
         value = datetime
       else