Sample using jruby-poi

reader.rb

 -*- coding: utf-8 -*-

# See
# 
#   $ jruby -S gem install jruby-pi
#   $ jruby reader.rb Book1.xslx
#  
#   Env:  
#           jruby: 1.6.8
#       jruby-poi: 0.8.2
# 
#   http://poi.apache.org/apidocs/org/apache/poi/xssf/usermodel/XSSFCell.html
#   http://poi.apache.org/apidocs/org/apache/poi/xssf/usermodel/XSSFSheet.html
#   http://poi.apache.org/apidocs/org/apache/poi/xssf/usermodel/XSSFWorkbook.html
#
require 'rubygems'
require 'poi'
require 'pp'

def get_info(filename)
  infos = {}
  workbook = POI::Workbook.open(filename)

  sheet_count = workbook.number_of_sheets
  (0...sheet_count).each do |sheet_index|

    matrix = {}
    sheet_name = workbook.sheet_at(sheet_index).sheet_name

    sheet = workbook.worksheets[sheet_name]
    sheet.rows.each do |row|
      pos_r = row.index
      row.cells.each_with_index {|c, pos_c|
        matrix[[pos_c, pos_r]] = "[#{c.poi_cell}] (#{c.poi_cell.getCellType()})"
      }
    end
    infos[sheet_name] = matrix
  end
  infos
end

if __FILE__ == $0
  filename = ARGV[0]
  sheets = get_info(filename)
  pp sheets
end

sample output

$ jruby reader.rb Book1.xlsx 
{"Sheet1"=>
  {[0, 0]=>"[a] (1)",
   [1, 0]=>"[b] (1)",
   [2, 0]=>"[c] (1)",
   [0, 1]=>"[1.0] (0)",
   [1, 1]=>"[2.0] (0)",
   [2, 1]=>"[3.0] (0)",
   [3, 1]=>"[SUM(A2:D2)] (2)",
   [0, 2]=>"[27-9-2012] (0)",
   [0, 5]=>"[5x5] (1)"},
 "Sheet2"=>{},
 "Sheet3"=>{}}

$