spreadsheetx 0.1.1 → 0.2.0

data/Gemfile

@@ -2,6 +2,7 @@ source "http://rubygems.org"
 # Add dependencies required to use your gem here.
 # Example:
 gem "zipruby", "~> 0.3.6"
+gem "libxml-ruby", "~> 2.0.9"
 
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.

data/Gemfile.lock

@@ -3,10 +3,11 @@ GEM
   specs:
     diff-lcs (1.1.2)
     git (1.2.5)
-    jeweler (1.6.3)
+    jeweler (1.6.4)
       bundler (~> 1.0)
       git (>= 1.2.5)
       rake
+    libxml-ruby (2.0.9)
     rake (0.9.2)
     rcov (0.9.9)
     rspec (2.3.0)
@@ -25,6 +26,7 @@ PLATFORMS
 DEPENDENCIES
   bundler (~> 1.0.0)
   jeweler (~> 1.6.2)
+  libxml-ruby (~> 2.0.9)
   rcov
   rspec (~> 2.3.0)
   zipruby (~> 0.3.6)

data/VERSION

@@ -1 +1 @@
-0.1.1
+0.2.0

data/lib/spreadsheetx.rb

@@ -1,7 +1,7 @@
 # zipruby is nice as it can modify an existing zip file, perfect for our usecase 
 require 'zipruby'
-# we use this because it comes with ruby
-require 'rexml/document'
+# we use this because it is WAY faster than rexml
+require 'xml'
 # for copying files
 require 'fileutils'
 # 

data/lib/spreadsheetx/workbook.rb

@@ -19,10 +19,15 @@ module SpreadsheetX
 
           #parse the XML and build the worksheets
           @worksheets = []
-          REXML::Document.new(file_contents).elements.each('workbook/sheets/sheet') do |node|
-            sheet_id = node.attributes['sheetId'].to_i
-            r_id = node.attributes['r:id'].gsub('rId','').to_i
-            name = node.attributes['name'].to_s
+          # parse the XML and hold the doc
+          xml_doc = XML::Document.string(file_contents)
+          # set the default namespace
+          xml_doc.root.namespaces.default_prefix = 'spreadsheetml'
+          
+          xml_doc.find('spreadsheetml:sheets/spreadsheetml:sheet').each do |node|
+            sheet_id = node['sheetId'].to_i
+            r_id = node['id'].gsub('rId','').to_i
+            name = node['name'].to_s
             @worksheets.push SpreadsheetX::Worksheet.new(archive, sheet_id, r_id, name)
           end
           

data/lib/spreadsheetx/worksheet.rb

@@ -18,8 +18,10 @@ module SpreadsheetX
 
         # read contents of this file
         file_contents = f.read 
-        #parse the XML and hold the doc
-        @xml_doc = REXML::Document.new(file_contents)
+        # parse the XML and hold the doc
+        @xml_doc = XML::Document.string(file_contents)
+        # set the default namespace
+        @xml_doc.root.namespaces.default_prefix = 'spreadsheetml'
 
       end
       
@@ -30,35 +32,55 @@ module SpreadsheetX
       
       cell_id = SpreadsheetX::Worksheet.cell_id(col_number, row_number)
       
-      rows = @xml_doc.get_elements("worksheet/sheetData/row[@r=#{row_number}]")
+      row = @xml_doc.find_first("spreadsheetml:sheetData/spreadsheetml:row[@r=#{row_number}]")
+      
       # was this row found
-      if rows.empty?
+      unless row
         # build a new row
-        row = @xml_doc.elements['worksheet'].elements['sheetData'].add_element('row', {'r' => row_number})
-      else
-        # x path returns an array, but we know there is only one row with this number
-        row = rows.first
+        row = XML::Node.new('row')
+        row['r'] = row_number.to_s
+        # add it to the other rows
+        @xml_doc.find_first('spreadsheetml:sheetData') << row
       end
       
-      cells = row.get_elements("c[@r='#{cell_id}']")
-      if cells.empty?
-        cell = row.add_element('c', {'r' => cell_id})
-      else
-        # x path returns an array, but we know there is only one row with this number
-        cell = cells.first
+      cell = row.find_first("spreadsheetml:c[@r='#{cell_id}']")
+      # was this row found
+      unless cell
+        # build a new cell
+        cell = XML::Node.new('c')
+        cell['r'] = cell_id
+        # add it to the other rows
+        row << cell
       end
       
-      # first clear out any existing values
-      cell.delete_element('*')
-
-      # now we put the value in the cell
+      # create the node which represents the value in the cell
       if val.kind_of? String
-        cell.attributes['t'] = 'inlineStr'
-        cell.add_element('is').add_element('t').add_text(val)
+        
+        # put the strings inline to make life easier
+        cell['t'] = 'inlineStr'
+        
+        # the string node looke like <is><t>string</t></is>
+        is = XML::Node.new('is')
+        t = XML::Node.new('t')
+        t.content = val
+        
+        cell_value = ( is << t )
+        
       else
-        cell.attributes['t'] = nil
-        cell.add_element('v').add_text(val.to_s)
+        
+        # incase this was an inline string, clear out this attribute
+        cell['t'] = ''
+        
+        cell_value = XML::Node.new('v')
+        cell_value.content = val.to_s
+
       end
+      
+      # first clear out any existing values (nodes)
+      cell.find('*').each{|n| n.remove! }
+
+      # now we put the value in the cell
+      cell << cell_value
 
     end
     
@@ -66,8 +88,8 @@ module SpreadsheetX
     # NOTE: this is the count of those rows, not the length of the document
     def row_count
       count = 0
-      @xml_doc.elements.each('worksheet/sheetData/row'){ count+=1 }
-      count
+      # target the sheetData rows
+      @xml_doc.find('spreadsheetml:sheetData/spreadsheetml:row').count
     end
 
     # returns the xml representation of this worksheet
@@ -77,6 +99,7 @@ module SpreadsheetX
     
     # turns a cell address into its excel name, 1,1 = A1  2,3 = C2 etc.
     def self.cell_id(col_number, row_number)
+      raise 'There is no row 0, start at 1 instead' if row_number < 1
       letter = 'A'
       # some day, speed this up
       (col_number.to_i-1).times{letter = letter.succ}

data/spec/spreadsheetx_spec.rb

@@ -50,7 +50,6 @@ describe "Spreadsheetx" do
     SpreadsheetX::Worksheet.cell_id(26, 4).should == 'Z4'
     SpreadsheetX::Worksheet.cell_id(820, 496).should == 'AEN496'
     
-    
   end
   
   it "allows cell values to be updated" do
@@ -81,5 +80,43 @@ describe "Spreadsheetx" do
     workbook.save(new_xlsx_file)
   
   end
+
+  it "handles large numbers of rows and cols" do
+    
+    # a valid xlsx file used for testing
+    empty_xlsx_file = "#{File.dirname(__FILE__)}/../templates/spec.xlsx"
+    workbook = SpreadsheetX.open(empty_xlsx_file)
+  
+    500.times do |row|
+      6.times do |col|
+        random_string = (0...30).map{65.+(rand(25)).chr}.join
+        # ump the row because there is no row 0
+        workbook.worksheets.last.update_cell(col, (row+1), random_string)
+      end
+    end
+
+    new_xlsx_file = "#{File.dirname(__FILE__)}/../templates/spec_large_data.xlsx"
+    workbook.save(new_xlsx_file)
+  
+  end
+
+  it "handles various types of content" do
+  
+    # a valid xlsx file used for testing
+    empty_xlsx_file = "#{File.dirname(__FILE__)}/../templates/spec.xlsx"
+    workbook = SpreadsheetX.open(empty_xlsx_file)
+  
+    workbook.worksheets.last.update_cell(9, 9, Time.now)
+    workbook.worksheets.last.update_cell(9, 10, 'A string')
+    workbook.worksheets.last.update_cell(9, 11, 10.3)
+    workbook.worksheets.last.update_cell(9, 12, 53)
+    workbook.worksheets.last.update_cell(9, 13, nil)
+
+    new_xlsx_file = "#{File.dirname(__FILE__)}/../templates/spec_various_content.xlsx"
+    workbook.save(new_xlsx_file)
+  
+  end
+  
+  
   
 end

data/spreadsheetx.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{spreadsheetx}
-  s.version = "0.1.1"
+  s.version = "0.2.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Craig Ulliott"]
-  s.date = %q{2011-07-02}
+  s.date = %q{2011-07-09}
   s.description = %q{Using an existing xlsx file as a template, it allows you to modify cell values and add rows and columns.  Facilitating a templateized approach to creating a new xlsx spreadsheet}
   s.email = %q{craigulliott@gmail.com}
   s.extra_rdoc_files = [
@@ -44,12 +44,14 @@ Gem::Specification.new do |s|
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_runtime_dependency(%q<zipruby>, ["~> 0.3.6"])
+      s.add_runtime_dependency(%q<libxml-ruby>, ["~> 2.0.9"])
       s.add_development_dependency(%q<rspec>, ["~> 2.3.0"])
       s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.6.2"])
       s.add_development_dependency(%q<rcov>, [">= 0"])
     else
       s.add_dependency(%q<zipruby>, ["~> 0.3.6"])
+      s.add_dependency(%q<libxml-ruby>, ["~> 2.0.9"])
       s.add_dependency(%q<rspec>, ["~> 2.3.0"])
       s.add_dependency(%q<bundler>, ["~> 1.0.0"])
       s.add_dependency(%q<jeweler>, ["~> 1.6.2"])
@@ -57,6 +59,7 @@ Gem::Specification.new do |s|
     end
   else
     s.add_dependency(%q<zipruby>, ["~> 0.3.6"])
+    s.add_dependency(%q<libxml-ruby>, ["~> 2.0.9"])
     s.add_dependency(%q<rspec>, ["~> 2.3.0"])
     s.add_dependency(%q<bundler>, ["~> 1.0.0"])
     s.add_dependency(%q<jeweler>, ["~> 1.6.2"])

metadata

@@ -2,7 +2,7 @@
 name: spreadsheetx
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.1.1
+  version: 0.2.0
 platform: ruby
 authors: 
 - Craig Ulliott
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-07-02 00:00:00 -05:00
+date: 2011-07-09 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -25,8 +25,19 @@ dependencies:
   prerelease: false
   version_requirements: *id001
 - !ruby/object:Gem::Dependency 
-  name: rspec
+  name: libxml-ruby
   requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: 2.0.9
+  type: :runtime
+  prerelease: false
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ~>
@@ -34,10 +45,10 @@ dependencies:
         version: 2.3.0
   type: :development
   prerelease: false
-  version_requirements: *id002
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: bundler
-  requirement: &id003 !ruby/object:Gem::Requirement 
+  requirement: &id004 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ~>
@@ -45,10 +56,10 @@ dependencies:
         version: 1.0.0
   type: :development
   prerelease: false
-  version_requirements: *id003
+  version_requirements: *id004
 - !ruby/object:Gem::Dependency 
   name: jeweler
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  requirement: &id005 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ~>
@@ -56,10 +67,10 @@ dependencies:
         version: 1.6.2
   type: :development
   prerelease: false
-  version_requirements: *id004
+  version_requirements: *id005
 - !ruby/object:Gem::Dependency 
   name: rcov
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  requirement: &id006 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -67,7 +78,7 @@ dependencies:
         version: "0"
   type: :development
   prerelease: false
-  version_requirements: *id005
+  version_requirements: *id006
 description: Using an existing xlsx file as a template, it allows you to modify cell values and add rows and columns.  Facilitating a templateized approach to creating a new xlsx spreadsheet
 email: craigulliott@gmail.com
 executables: []
@@ -107,7 +118,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: -680141844261039746
+      hash: -772800674702882304
       segments: 
       - 0
       version: "0"