roo 1.11.1 → 1.11.2

data/CHANGELOG

@@ -1,3 +1,12 @@
+== 1.11.2 (unreleased)
+
+* 4 bugfixes
+  * Fix that Roo::Spreadsheet.open wasn't tolerant to case differences.
+  * Fix that Roo::Excel2003XML loading was broken https://github.com/Empact/roo/pull/27
+  * Enable loading Roo::Csv files from uris, just as other file types https://github.com/Empact/roo/pull/31
+  * Fix that Excelx "m/d/yy h:mm" was improperly being interpreted as date rather
+    than datetime https://github.com/Empact/roo/pull/29
+
 == 1.11.1 2013-03-18
 
 * 1 bugfix

data/README.markdown

@@ -19,12 +19,12 @@ file but not the formula itself)
 
     require 'roo'
 
-    s = Openoffice.new("myspreadsheet.ods")      # creates an Openoffice Spreadsheet instance
-    s = Excel.new("myspreadsheet.xls")           # creates an Excel Spreadsheet instance
-    s = Google.new("myspreadsheetkey_at_google") # creates an Google Spreadsheet instance
-    s = Excelx.new("myspreadsheet.xlsx")         # creates an Excel Spreadsheet instance for Excel .xlsx files
+    s = Roo::Openoffice.new("myspreadsheet.ods")      # creates an Openoffice Spreadsheet instance
+    s = Roo::Excel.new("myspreadsheet.xls")           # creates an Excel Spreadsheet instance
+    s = Roo::Google.new("myspreadsheetkey_at_google") # creates an Google Spreadsheet instance
+    s = Roo::Excelx.new("myspreadsheet.xlsx")         # creates an Excel Spreadsheet instance for Excel .xlsx files
 
-    s.default_sheet = s.sheets.first  # first sheet in the spreadsheet file will be used
+    s.default_sheet = s.sheets.first             # first sheet in the spreadsheet file will be used
 
     # s.sheet is an array which holds the names of the sheets within
     # a spreadsheet.

data/VERSION

@@ -1 +1 @@
-1.11.1
+1.11.2

data/lib/roo.rb

@@ -2,29 +2,7 @@ module Roo
 
   VERSION = '1.10.3'
 
-  class Spreadsheet
-    class << self
-      def open(file)
-        file = File === file ? file.path : file
-        case File.extname(file)
-        when '.xls'
-          Roo::Excel.new(file)
-        when '.xlsx'
-          Roo::Excelx.new(file)
-        when '.ods'
-          Roo::Openoffice.new(file)
-        when '.xml'
-          Roo::Excel2003XML.new(file)
-        when ''
-          Roo::Google.new(file)
-        when '.csv'
-          Roo::Csv.new(file)
-        else
-          raise ArgumentError, "Don't know how to open file #{file}"
-        end
-      end
-    end
-  end
+  autoload :Spreadsheet, 'roo/spreadsheet'
 
   autoload :GenericSpreadsheet, 'roo/generic_spreadsheet'
   autoload :Openoffice,         'roo/openoffice'

data/lib/roo/csv.rb

@@ -19,6 +19,8 @@ class Roo::Csv < Roo::GenericSpreadsheet
     @last_column = Hash.new
   end
 
+  attr_reader :filename
+
   # Returns an array with the names of the sheets. In Csv class there is only
   # one dummy sheet, because a csv file cannot have more than one sheet.
   def sheets
@@ -56,6 +58,17 @@ class Roo::Csv < Roo::GenericSpreadsheet
     TYPE_MAP[value.class]
   end
 
+  def data
+    @data ||=
+      make_tmpdir do |tmpdir|
+        File.open(
+          uri?(filename) ?
+            open_from_uri(filename, tmpdir) :
+            filename
+        ) { |f| f.read }
+      end
+  end
+
   def read_cells(sheet=nil)
     sheet ||= @default_sheet
     @cell_type = {} unless @cell_type
@@ -65,7 +78,7 @@ class Roo::Csv < Roo::GenericSpreadsheet
     @first_column[sheet] = 1
     @last_column[sheet] = 1
     rownum = 1
-    CSV.foreach(@filename) do |row|
+    CSV.parse data do |row|
       row.each_with_index do |elem,i|
         @cell[[rownum,i+1]] = cell_postprocessing rownum,i+1, elem
         @cell_type[[rownum,i+1]] = celltype_class @cell[[rownum,i+1]]
@@ -78,41 +91,25 @@ class Roo::Csv < Roo::GenericSpreadsheet
     end
     @cells_read[sheet] = true
     #-- adjust @first_row if neccessary
-    loop do
-      if !row(@first_row[sheet]).any? and @first_row[sheet] < @last_row[sheet]
-        @first_row[sheet] += 1
-      else
-        break
-      end
+    while !row(@first_row[sheet]).any? and @first_row[sheet] < @last_row[sheet]
+      @first_row[sheet] += 1
     end
     #-- adjust @last_row if neccessary
-    loop do
-      if !row(@last_row[sheet]).any? and @last_row[sheet] and
-          @last_row[sheet] > @first_row[sheet]
-        @last_row[sheet] -= 1
-      else
-        break
-      end
+    while !row(@last_row[sheet]).any? and @last_row[sheet] and
+        @last_row[sheet] > @first_row[sheet]
+      @last_row[sheet] -= 1
     end
     #-- adjust @first_column if neccessary
-    loop do
-      if !column(@first_column[sheet]).any? and
+    while !column(@first_column[sheet]).any? and
           @first_column[sheet] and
           @first_column[sheet] < @last_column[sheet]
-        @first_column[sheet] += 1
-      else
-        break
-      end
+      @first_column[sheet] += 1
     end
     #-- adjust @last_column if neccessary
-    loop do
-      if !column(@last_column[sheet]).any? and
+    while !column(@last_column[sheet]).any? and
           @last_column[sheet] and
           @last_column[sheet] > @first_column[sheet]
-        @last_column[sheet] -= 1
-      else
-        break
-      end
+      @last_column[sheet] -= 1
     end
   end
 end # class Csv

data/lib/roo/excel2003xml.rb

@@ -2,6 +2,7 @@ require 'fileutils'
 require 'date'
 require 'base64'
 require 'cgi'
+require 'nokogiri'
 
 class Roo::Excel2003XML < Roo::GenericSpreadsheet
 
@@ -118,7 +119,7 @@ class Roo::Excel2003XML < Roo::GenericSpreadsheet
 
   def sheets
     @doc.xpath("/ss:Workbook/ss:Worksheet").map do |sheet|
-      sheet['Name']
+      sheet['ss:Name']
     end
   end
 
@@ -229,7 +230,7 @@ class Roo::Excel2003XML < Roo::GenericSpreadsheet
           end
           c.xpath('./ss:Data').each do |cell|
             formula = cell['Formula']
-            value_type = cell['Type'].downcase.to_sym
+            value_type = cell['ss:Type'].downcase.to_sym
             v =  cell.content
             str_v = v
             case value_type

data/lib/roo/excelx.rb

@@ -7,9 +7,6 @@ class Roo::Excelx < Roo::GenericSpreadsheet
     EXCEPTIONAL_FORMATS = {
       'h:mm am/pm' => :date,
       'h:mm:ss am/pm' => :date,
-      'm/d/yy h:mm' => :date,
-      '#,##0 ;[red](#,##0)' => :float,
-      '#,##0.00;[red](#,##0.00)' => :float
     }
 
     STANDARD_FORMATS = {
@@ -47,6 +44,8 @@ class Roo::Excelx < Roo::GenericSpreadsheet
       format = format.to_s.downcase
       if type = EXCEPTIONAL_FORMATS[format]
         type
+      elsif format.include?('#')
+        :float
       elsif format.include?('d') || format.include?('y')
         if format.include?('h') || format.include?('s')
           :datetime
@@ -405,7 +404,7 @@ class Roo::Excelx < Roo::GenericSpreadsheet
           # 2011-02-25 END
           # 2011-09-15 BEGIN
         when 'inlineStr'
-  	      :inlinestr
+          :inlinestr
           # 2011-09-15 END
         else
           format = attribute2format(s_attribute)
@@ -531,7 +530,7 @@ Datei xl/comments1.xml
 
   def read_labels
     @label ||= Hash[@workbook_doc.xpath("//xmlns:definedName").map do |defined_name|
-	    # "Sheet1!$C$5"
+      # "Sheet1!$C$5"
       sheet, coordinates = defined_name.text.split('!$', 2)
       col,row = coordinates.split('$')
       [defined_name['name'], [sheet,row,col]]
@@ -549,10 +548,10 @@ Datei xl/comments1.xml
           }
         end
         # if entry.to_s.end_with?('sharedStrings.xml')
-	# at least one application creates this file with another (incorrect?)
-	# casing. It doesn't hurt, if we ignore here the correct casing - there
-	# won't be both names in the archive.
-	# Changed the casing of all the following filenames.
+        # at least one application creates this file with another (incorrect?)
+        # casing. It doesn't hurt, if we ignore here the correct casing - there
+        # won't be both names in the archive.
+        # Changed the casing of all the following filenames.
         if entry.to_s.downcase.end_with?('sharedstrings.xml')
           open(tmpdir+'/'+'roo_sharedStrings.xml','wb') {|f|
             f << zip.read(entry)

data/lib/roo/generic_spreadsheet.rb

@@ -524,6 +524,7 @@ class Roo::GenericSpreadsheet
       '.xls' => 'Roo::Excel.new',
       '.xlsx' => 'Roo::Excelx.new',
       '.csv' => 'Roo::Csv.new',
+      '.xml' => 'Roo::Excel2003XML.new',
     }
     if packed == :zip
 	    # lalala.ods.zip => lalala.ods
@@ -532,7 +533,7 @@ class Roo::GenericSpreadsheet
 	    filename = File.basename(filename,File.extname(filename))
     end
     case ext
-    when '.ods', '.xls', '.xlsx', '.csv'
+    when '.ods', '.xls', '.xlsx', '.csv', '.xml'
       correct_class = "use #{new_expression[ext]} to handle #{ext} spreadsheet files. This has #{File.extname(filename).downcase}"
     else
       raise "unknown file type: #{ext}"

data/lib/roo/spreadsheet.rb

@@ -0,0 +1,25 @@
+module Roo
+  class Spreadsheet
+    class << self
+      def open(file)
+        file = File === file ? file.path : file
+        case File.extname(file).downcase
+        when '.xls'
+          Roo::Excel.new(file)
+        when '.xlsx'
+          Roo::Excelx.new(file)
+        when '.ods'
+          Roo::Openoffice.new(file)
+        when '.xml'
+          Roo::Excel2003XML.new(file)
+        when ''
+          Roo::Google.new(file)
+        when '.csv'
+          Roo::Csv.new(file)
+        else
+          raise ArgumentError, "Don't know how to open file #{file}"
+        end
+      end
+    end
+  end
+end

data/roo.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "roo"
-  s.version = "1.11.1"
+  s.version = "1.11.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Thomas Preymesser", "Hugh McGowan", "Ben Woosley"]
-  s.date = "2013-03-18"
+  s.date = "2013-04-10"
   s.description = "Roo can access the contents of various spreadsheet files. It can handle\n* Openoffice\n* Excel\n* Google spreadsheets\n* Excelx\n* Libreoffice\n* CSV"
   s.email = "ruby.ruby.ruby.roo@gmail.com"
   s.extra_rdoc_files = [
@@ -38,10 +38,13 @@ Gem::Specification.new do |s|
     "lib/roo/google.rb",
     "lib/roo/openoffice.rb",
     "lib/roo/roo_rails_helper.rb",
+    "lib/roo/spreadsheet.rb",
     "lib/roo/worksheet.rb",
     "roo.gemspec",
     "scripts/txt2html",
+    "spec/lib/roo/excel2003xml_spec.rb",
     "spec/lib/roo/excelx/format_spec.rb",
+    "spec/lib/roo/spreadsheet_spec.rb",
     "spec/spec_helper.rb",
     "test/all_ss.rb",
     "test/files/1900_base.xls",
@@ -162,7 +165,7 @@ Gem::Specification.new do |s|
   s.rubyforge_project = "roo"
   s.rubygems_version = "1.8.24"
   s.summary = "Roo can access the contents of various spreadsheet files."
-  s.test_files = ["spec/lib/roo/excelx/format_spec.rb", "spec/spec_helper.rb", "test/all_ss.rb", "test/files/1900_base.xls", "test/files/1904_base.xls", "test/files/Bibelbund.csv", "test/files/Bibelbund.ods", "test/files/Bibelbund.xls", "test/files/Bibelbund.xlsx", "test/files/Bibelbund.xml", "test/files/Bibelbund1.ods", "test/files/Pfand_from_windows_phone.xlsx", "test/files/bad_excel_date.xls", "test/files/bbu.ods", "test/files/bbu.xls", "test/files/bbu.xlsx", "test/files/bbu.xml", "test/files/bode-v1.ods.zip", "test/files/bode-v1.xls.zip", "test/files/boolean.ods", "test/files/boolean.xls", "test/files/boolean.xlsx", "test/files/boolean.xml", "test/files/borders.ods", "test/files/borders.xls", "test/files/borders.xlsx", "test/files/borders.xml", "test/files/bug-row-column-fixnum-float.xls", "test/files/bug-row-column-fixnum-float.xml", "test/files/comments.ods", "test/files/comments.xls", "test/files/comments.xlsx", "test/files/csvtypes.csv", "test/files/datetime.ods", "test/files/datetime.xls", "test/files/datetime.xlsx", "test/files/datetime.xml", "test/files/datetime_floatconv.xls", "test/files/datetime_floatconv.xml", "test/files/dreimalvier.ods", "test/files/emptysheets.ods", "test/files/emptysheets.xls", "test/files/emptysheets.xlsx", "test/files/emptysheets.xml", "test/files/excel2003.xml", "test/files/false_encoding.xls", "test/files/false_encoding.xml", "test/files/formula.ods", "test/files/formula.xls", "test/files/formula.xlsx", "test/files/formula.xml", "test/files/formula_parse_error.xls", "test/files/formula_parse_error.xml", "test/files/formula_string_error.xlsx", "test/files/html-escape.ods", "test/files/matrix.ods", "test/files/matrix.xls", "test/files/named_cells.ods", "test/files/named_cells.xls", "test/files/named_cells.xlsx", "test/files/no_spreadsheet_file.txt", "test/files/numbers1.csv", "test/files/numbers1.ods", "test/files/numbers1.xls", "test/files/numbers1.xlsx", "test/files/numbers1.xml", "test/files/only_one_sheet.ods", "test/files/only_one_sheet.xls", "test/files/only_one_sheet.xlsx", "test/files/only_one_sheet.xml", "test/files/paragraph.ods", "test/files/paragraph.xls", "test/files/paragraph.xlsx", "test/files/paragraph.xml", "test/files/prova.xls", "test/files/ric.ods", "test/files/simple_spreadsheet.ods", "test/files/simple_spreadsheet.xls", "test/files/simple_spreadsheet.xlsx", "test/files/simple_spreadsheet.xml", "test/files/simple_spreadsheet_from_italo.ods", "test/files/simple_spreadsheet_from_italo.xls", "test/files/simple_spreadsheet_from_italo.xml", "test/files/so_datetime.csv", "test/files/style.ods", "test/files/style.xls", "test/files/style.xlsx", "test/files/style.xml", "test/files/time-test.csv", "test/files/time-test.ods", "test/files/time-test.xls", "test/files/time-test.xlsx", "test/files/time-test.xml", "test/files/type_excel.ods", "test/files/type_excel.xlsx", "test/files/type_excelx.ods", "test/files/type_excelx.xls", "test/files/type_openoffice.xls", "test/files/type_openoffice.xlsx", "test/files/whitespace.ods", "test/files/whitespace.xls", "test/files/whitespace.xlsx", "test/files/whitespace.xml", "test/rm_sub_test.rb", "test/rm_test.rb", "test/test_generic_spreadsheet.rb", "test/test_helper.rb", "test/test_roo.rb"]
+  s.test_files = ["spec/lib/roo/excel2003xml_spec.rb", "spec/lib/roo/excelx/format_spec.rb", "spec/lib/roo/spreadsheet_spec.rb", "spec/spec_helper.rb", "test/all_ss.rb", "test/files/1900_base.xls", "test/files/1904_base.xls", "test/files/bad_excel_date.xls", "test/files/bbu.ods", "test/files/bbu.xls", "test/files/bbu.xlsx", "test/files/bbu.xml", "test/files/Bibelbund.csv", "test/files/Bibelbund.ods", "test/files/Bibelbund.xls", "test/files/Bibelbund.xlsx", "test/files/Bibelbund.xml", "test/files/Bibelbund1.ods", "test/files/bode-v1.ods.zip", "test/files/bode-v1.xls.zip", "test/files/boolean.ods", "test/files/boolean.xls", "test/files/boolean.xlsx", "test/files/boolean.xml", "test/files/borders.ods", "test/files/borders.xls", "test/files/borders.xlsx", "test/files/borders.xml", "test/files/bug-row-column-fixnum-float.xls", "test/files/bug-row-column-fixnum-float.xml", "test/files/comments.ods", "test/files/comments.xls", "test/files/comments.xlsx", "test/files/csvtypes.csv", "test/files/datetime.ods", "test/files/datetime.xls", "test/files/datetime.xlsx", "test/files/datetime.xml", "test/files/datetime_floatconv.xls", "test/files/datetime_floatconv.xml", "test/files/dreimalvier.ods", "test/files/emptysheets.ods", "test/files/emptysheets.xls", "test/files/emptysheets.xlsx", "test/files/emptysheets.xml", "test/files/excel2003.xml", "test/files/false_encoding.xls", "test/files/false_encoding.xml", "test/files/formula.ods", "test/files/formula.xls", "test/files/formula.xlsx", "test/files/formula.xml", "test/files/formula_parse_error.xls", "test/files/formula_parse_error.xml", "test/files/formula_string_error.xlsx", "test/files/html-escape.ods", "test/files/matrix.ods", "test/files/matrix.xls", "test/files/named_cells.ods", "test/files/named_cells.xls", "test/files/named_cells.xlsx", "test/files/no_spreadsheet_file.txt", "test/files/numbers1.csv", "test/files/numbers1.ods", "test/files/numbers1.xls", "test/files/numbers1.xlsx", "test/files/numbers1.xml", "test/files/only_one_sheet.ods", "test/files/only_one_sheet.xls", "test/files/only_one_sheet.xlsx", "test/files/only_one_sheet.xml", "test/files/paragraph.ods", "test/files/paragraph.xls", "test/files/paragraph.xlsx", "test/files/paragraph.xml", "test/files/Pfand_from_windows_phone.xlsx", "test/files/prova.xls", "test/files/ric.ods", "test/files/simple_spreadsheet.ods", "test/files/simple_spreadsheet.xls", "test/files/simple_spreadsheet.xlsx", "test/files/simple_spreadsheet.xml", "test/files/simple_spreadsheet_from_italo.ods", "test/files/simple_spreadsheet_from_italo.xls", "test/files/simple_spreadsheet_from_italo.xml", "test/files/so_datetime.csv", "test/files/style.ods", "test/files/style.xls", "test/files/style.xlsx", "test/files/style.xml", "test/files/time-test.csv", "test/files/time-test.ods", "test/files/time-test.xls", "test/files/time-test.xlsx", "test/files/time-test.xml", "test/files/type_excel.ods", "test/files/type_excel.xlsx", "test/files/type_excelx.ods", "test/files/type_excelx.xls", "test/files/type_openoffice.xls", "test/files/type_openoffice.xlsx", "test/files/whitespace.ods", "test/files/whitespace.xls", "test/files/whitespace.xlsx", "test/files/whitespace.xml", "test/rm_sub_test.rb", "test/rm_test.rb", "test/test_generic_spreadsheet.rb", "test/test_helper.rb", "test/test_roo.rb"]
 
   if s.respond_to? :specification_version then
     s.specification_version = 3

data/spec/lib/roo/excel2003xml_spec.rb

@@ -0,0 +1,15 @@
+require 'spec_helper'
+
+describe Roo::Excel2003XML do
+  describe '.new' do
+    context 'with an xml file' do
+      let(:path) { 'test/files/datetime.xml' }
+
+      it 'loads the file' do
+        expect {
+          Roo::Excel2003XML.new(path)
+        }.to_not raise_error
+      end
+    end
+  end
+end

data/spec/lib/roo/excelx/format_spec.rb

@@ -21,11 +21,12 @@ describe Roo::Excelx::Format do
       'h:mm:ss AM/PM' => :date,
       'h:mm' => :time,
       'h:mm:ss' => :time,
-      'm/d/yy h:mm' => :date,
+      'm/d/yy h:mm' => :datetime,
       '#,##0 ;(#,##0)' => :float,
       '#,##0 ;[Red](#,##0)' => :float,
       '#,##0.00;(#,##0.00)' => :float,
       '#,##0.00;[Red](#,##0.00)' => :float,
+      '#,##0_);[Red](#,##0)' => :float,
       'mm:ss' => :time,
       '[h]:mm:ss' => :time,
       'mmss.0' => :time,
@@ -36,6 +37,7 @@ describe Roo::Excelx::Format do
       'dd/mm/yy' => :date,
       'hh:mm:ss' => :time,
       "dd/mm/yy\\ hh:mm" => :datetime,
+      'dd/mmm/yy\\ hh:mm' => :datetime,
       'dd/mmm/yy' => :date, # 2011-05-21
       'yyyy-mm-dd' => :date, # 2011-09-16
       'yyyy-mm-dd;@' => :date

data/spec/lib/roo/spreadsheet_spec.rb

@@ -0,0 +1,14 @@
+require 'spec_helper'
+
+describe Roo::Spreadsheet do
+  describe '.open' do
+    context 'when the file extension is uppercase' do
+      let(:filename) { 'file.XLS' }
+
+      it 'loads the proper type' do
+        Roo::Excel.should_receive(:new).with(filename)
+        Roo::Spreadsheet.open(filename)
+      end
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: roo
 version: !ruby/object:Gem::Version
-  version: 1.11.1
+  version: 1.11.2
   prerelease: 
 platform: ruby
 authors:
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-03-18 00:00:00.000000000 Z
+date: 2013-04-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: spreadsheet
@@ -118,10 +118,13 @@ files:
 - lib/roo/google.rb
 - lib/roo/openoffice.rb
 - lib/roo/roo_rails_helper.rb
+- lib/roo/spreadsheet.rb
 - lib/roo/worksheet.rb
 - roo.gemspec
 - scripts/txt2html
+- spec/lib/roo/excel2003xml_spec.rb
 - spec/lib/roo/excelx/format_spec.rb
+- spec/lib/roo/spreadsheet_spec.rb
 - spec/spec_helper.rb
 - test/all_ss.rb
 - test/files/1900_base.xls
@@ -260,23 +263,24 @@ signing_key:
 specification_version: 3
 summary: Roo can access the contents of various spreadsheet files.
 test_files:
+- spec/lib/roo/excel2003xml_spec.rb
 - spec/lib/roo/excelx/format_spec.rb
+- spec/lib/roo/spreadsheet_spec.rb
 - spec/spec_helper.rb
 - test/all_ss.rb
 - test/files/1900_base.xls
 - test/files/1904_base.xls
+- test/files/bad_excel_date.xls
+- test/files/bbu.ods
+- test/files/bbu.xls
+- test/files/bbu.xlsx
+- test/files/bbu.xml
 - test/files/Bibelbund.csv
 - test/files/Bibelbund.ods
 - test/files/Bibelbund.xls
 - test/files/Bibelbund.xlsx
 - test/files/Bibelbund.xml
 - test/files/Bibelbund1.ods
-- test/files/Pfand_from_windows_phone.xlsx
-- test/files/bad_excel_date.xls
-- test/files/bbu.ods
-- test/files/bbu.xls
-- test/files/bbu.xlsx
-- test/files/bbu.xml
 - test/files/bode-v1.ods.zip
 - test/files/bode-v1.xls.zip
 - test/files/boolean.ods
@@ -334,6 +338,7 @@ test_files:
 - test/files/paragraph.xls
 - test/files/paragraph.xlsx
 - test/files/paragraph.xml
+- test/files/Pfand_from_windows_phone.xlsx
 - test/files/prova.xls
 - test/files/ric.ods
 - test/files/simple_spreadsheet.ods