parseexcel_mod 0.0.1

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in parseexcel_mod.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 t0pep0
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README

@@ -0,0 +1,95 @@
+Spreadsheet::ParseExcel - Get information from an Excel file.
+
+============
+Version: 0.5.3
+Date: 2011-04-22
+
+Short Description: 
+This is databasically's version of the parseexcel gem and is not actively maintained as the original gem is no longer maintained. This version was created to resolve a bug reading Unicode characters. The resulting error is as follows:
+
+  undefined method `&' for "\x00":String
+
+This version of the library resolves this error.
+
+Spreadsheet::ParseExcel allows you to get information out of a 
+simple Excel file
+This Package is an - as of today incomplete - translation of 
+Kawai Takanoris Perl-Module.
+
+
+Requirements
+------------
+
+  * ruby 1.8
+	
+Install
+-------
+
+  De-Compress archive and enter its top directory.
+  Then type:
+
+    $ ruby install.rb config
+    $ ruby install.rb setup
+   ($ su)
+    # ruby install.rb install
+
+  You can also install files into your favorite directory
+  by supplying install.rb with some options. Try "ruby install.rb --help".
+  More information can be found in the redistributed file usage-en.txt
+
+
+Usage
+-----
+#!/usr/bin/env ruby
+
+require 'parseexcel'
+
+# your first step is always reading in the file.
+# that gives you a workbook-object, which has one or more worksheets,
+# just like in Excel you have the possibility of multiple worksheets.
+workbook = Spreadsheet::ParseExcel.parse(path_to_file)
+
+# usually, you want the first worksheet:
+worksheet = workbook.worksheet(0)
+
+# now you can either iterate over all rows, skipping the first number of
+# rows (in case you know they just contain column headers)
+skip = 2
+worksheet.each(skip) { |row|
+  # a row is actually just an Array of Cells..
+  first_cell = row.at(0)
+
+  # how you get data out of the cell depends on what datatype you
+  # expect:
+
+  # if you expect a String, you can pass an encoding and (iconv
+  # required) the content of the cell will be converted.
+  str = row.at(1).to_s('latin1')
+
+  # if you expect a Float:
+  float = row.at(2).to_f
+
+  # if you expect an Integer:
+  int = row.at(3).to_i
+
+  # if you expect a Date:
+  date = row.at(4).date
+
+  # ParseExcel makes a guess at what Datatype a cell has. At the moment,
+        # possible values are: :date, :numeric, :text
+        celltype = first_cell.type
+}
+
+# if you know exactly which row your data resides in, you may just
+# retrieve that row, which is again simply an Array of Cells
+row = worksheet.row(26)
+
+
+License
+-------
+
+	LGPL
+
+	
+URL: http://download.ywesee.com/parseexcel
+Author: Hannes Wyss <hwyss@ywesee.com>

data/README.md

@@ -0,0 +1,29 @@
+# ParseexcelMod
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'parseexcel_mod'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install parseexcel_mod
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/lib/parseexcel_mod.rb

@@ -0,0 +1,4 @@
+#!/usr/bin/env ruby
+# ParseExcel -- parseexcel -- 29.08.2006 -- hwyss@ywesee.com
+
+require 'parseexcel_mod/parseexcel_mod'

data/lib/parseexcel_mod/format.rb

@@ -0,0 +1,119 @@
+#!/usr/bin/env ruby
+#
+#	Spreadsheet::ParseExcel -- Extract Data from an Excel File
+#	Copyright (C) 2003 ywesee -- intellectual capital connected
+#
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2.1 of the License, or (at your option) any later version.
+#
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+#
+#	ywesee - intellectual capital connected, Winterthurerstrasse 52, CH-8006 Z�rich, Switzerland
+#	hwyss@ywesee.com
+#
+# Format -- Spreadsheet::ParseExcel -- 10.06.2003 -- hwyss@ywesee.com 
+
+module Spreadsheet
+	module ParseExcel
+		class Format
+			@@fmt_strs = {
+				0x00 => "@",
+				0x01 => "0",
+				0x02 => "0.00",
+				0x03 => "#,##0",
+				0x04 => "#,##0.00",
+				0x05 => "($#,##0_);($#,##0)",
+				0x06 => "($#,##0_);[RED]($#,##0)",
+				0x07 => "($#,##0.00_);($#,##0.00_)",
+				0x08 => "($#,##0.00_);[RED]($#,##0.00_)",
+				0x09 => "0%",
+				0x0A => "0.00%",
+				0x0B => "0.00E+00",
+				0x0C => "# ?/?",
+				0x0D => "# ??/??",
+				0x0E => "m-d-yy",
+				0x0F => "d-mmm-yy",
+				0x10 => "d-mmm",
+				0x11 => "mmm-yy",
+				0x12 => "h:mm AM/PM",
+				0x13 => "h:mm:ss AM/PM",
+				0x14 => "h:mm",
+				0x15 => "h:mm:ss",
+				0x16 => "m-d-yy h:mm",
+		    #0x17-0x24 -- national differences?
+				0x25 => "(#,##0_);(#,##0)",
+				0x26 => "(#,##0_);[RED](#,##0)",
+				0x27 => "(#,##0.00);(#,##0.00)",
+				0x28 => "(#,##0.00);[RED](#,##0.00)",
+				0x29 => "_(*#,##0_);_(*(#,##0);_(*\"-\"_);_(@_)",
+				0x2A => "_($*#,##0_);_($*(#,##0);_(*\"-\"_);_(@_)",
+				0x2B => "_(*#,##0.00_);_(*(#,##0.00);_(*\"-\"??_);_(@_)",
+				0x2C => "_($*#,##0.00_);_($*(#,##0.00);_(*\"-\"??_);_(@_)",
+				0x2D => "mm:ss",
+				0x2E => "[h]:mm:ss",
+				0x2F => "mm:ss.0",
+				0x30 => "##0.0E+0",
+				0x31 => "@",
+			}
+      begin
+        require 'iconv'
+        iconv = Iconv.new('utf16le', 'latin1')
+        @@fmt_strs = @@fmt_strs.inject({}) { |memo, (key, val)|
+          memo.store(key, iconv.iconv(val))
+          memo
+        }
+      rescue
+        warn("default formats are encoded in ISO-8859-1")
+      end
+			attr_accessor :font_no, :fmt_idx, :lock, :hidden, :style, :key_123
+			attr_accessor :align_h, :wrap, :align_v, :just_last, :rotate, :indent
+			attr_accessor :shrink, :merge, :read_dir, :encoding
+			attr_accessor :border_style, :border_color, :border_diag, :fill
+			@@date_pattern = /(\0?d\0?d|\0?m\0?m|\0?y\0?y|\0?h|\0?s\0?s)/i
+			def initialize(params={})
+				params.each { |key, val|
+					mthd = key.to_s + '='
+					if(self.respond_to?(mthd))
+						self.send(mthd, val)
+					end
+				}
+			end
+			def add_text_format(idx, fmt_str)
+				@@fmt_strs.store(idx, fmt_str)
+			end
+			def cell_type(cell)
+				if(cell.numeric)
+					if([0x0E..0x16, 0x2D..0x2F].any? { |range| range.include?(@fmt_idx.to_i) })
+						:date
+					elsif((fmt = @@fmt_strs[@fmt_idx]) && @@date_pattern.match(fmt))
+						:date
+					else
+						:numeric
+					end
+				else
+					:text
+				end
+			end
+			def text_format(str, code=:_native_)
+				(code == :_native_) ? str : str.unpack('n*').pack('C*')
+			end
+      def to_s(target_encoding=nil)
+        fmt_str = @@fmt_strs[@fmt_idx].to_s
+        if(target_encoding)
+          Iconv.new(target_encoding, @encoding).iconv(fmt_str)
+        else
+          fmt_str.dup
+        end
+      end
+		end
+	end
+end

data/lib/parseexcel_mod/olestorage.rb

@@ -0,0 +1,365 @@
+#!/usr/bin/env ruby
+#
+#	Spreadsheet::ParseExcel -- Extract Data from an Excel File
+#	Copyright (C) 2003 ywesee -- intellectual capital connected
+#
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2.1 of the License, or (at your option) any later version.
+#
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+#
+#	ywesee - intellectual capital connected, Winterthurerstrasse 52, CH-8006 Z�rich, Switzerland
+#	hwyss@ywesee.com
+#
+# OLEReader -- Spreadsheet::ParseExcel -- 05.06.2003 -- hwyss@ywesee.com 
+
+require 'date'
+require 'stringio'
+
+module OLE
+	class UnknownFormatError < RuntimeError; end
+	class DateTime
+		attr_reader :year, :month, :day, :hour, :min, :sec, :msec
+		def initialize(year, month=1, day=1, hour=0, min=0, sec=0, msec=0)
+			@year = year
+			@month = month
+			@day = day
+			@hour = hour
+			@min = min
+			@sec = sec
+			@msec = msec
+		end
+		def date
+			begin
+				Date.new(@year, @month, @day)
+			rescue ArgumentError
+			end
+		end
+		class << self
+			def month_days(month, year)
+				case month % 12
+				when 0,1,3,5,7,8,10
+					31
+				when 4,6,9,11
+					30
+				else
+					Date.leap?(year) ? 29 : 28
+				end
+			end
+			def parse(datetime)
+				#1.Divide Day and Time
+				big_dt = datetime.split(//).reverse.inject(0) { |inj, char|
+					inj *= 0x100
+					inj += char.to_i
+				}
+				msec = big_dt % 10000000
+				big_dt /= 10000000
+				day = (big_dt / (24*60*60)) + 1
+				time = big_dt % (24*60*60)
+				#2. Year->Day(1601/1/2?)
+				year = 1601
+				attr_reader :year, :month, :day, :hour, :min, :sec, :msec
+				ydays = year_days(year)
+				while(day > ydays)
+					day -= ydays
+					year += 1
+					ydays = year_days(year)
+				end
+				month = 1
+				1.upto(11) { |month|
+					mdays = month_days(month, year)
+					break if(day <= mdays)
+					day -= mdays
+				}
+				#3. Hour->iSec
+				hour = time / 3600
+				min = (time % 3600) / 60
+				sec = time % 60
+				new(year, month, day, hour, min, sec, msec)
+			end
+			def year_days(year)
+				Date.leap?(year) ? 366 : 365
+			end
+		end
+	end
+	class Storage 
+		PpsType_Root  = 5
+		PpsType_Dir   = 1
+		PpsType_File  = 2
+		DataSizeSmall = 0x1000
+		LongIntSize   = 4
+		PpsSize       = 0x80
+		attr_reader :header
+		def initialize(filename)
+      if(filename.respond_to?(:seek))
+        @fh_owner = false
+        @fh = filename
+      else 
+        @fh_owner = true
+        @fh = File.open(filename, "r")
+      end
+			@fh.binmode
+			@header = get_header
+		end
+    def close
+      @fh.close if(@fh_owner)
+    end
+		module PPS
+			class Node
+				attr_reader :no, :type, :prev_pps, :next_pps, :data
+				attr_reader :dir_pps, :time_1st, :time_2nd, :start_block, :size
+				attr_reader :name
+				def initialize(no, datastr)
+					@no = no
+					#def init(datastr)
+					nm_size, @type, @prev_pps, 
+					@next_pps, @dir_pps = datastr[0x40,16].unpack('vvVVV')
+					@time_1st = DateTime.parse(datastr[0x64, 8])
+					@time_2nd = DateTime.parse(datastr[0x6C, 8])
+					@start_block, @size = datastr[0x74,8].unpack('VV')
+					nm_size -= 2 if(nm_size > 2)
+					@name = datastr[0,nm_size]
+					#end
+				end
+				def get_data(header)
+				end
+				private
+			end
+			class Root < Node
+				def get_data(header)
+					@data = header.get_big_data(@start_block, @size)
+				end
+			end
+			class Dir  < Node
+			end
+			class File < Node
+				def get_data(header)
+					@data = if(@size < DataSizeSmall)
+						header.get_small_data(@start_block, @size)
+					else 
+						header.get_big_data(@start_block, @size)
+					end
+				end
+			end
+		end
+		class << self
+			def is_normal_block?(block)
+				block < 0xFFFFFFFC
+			end
+			def pps_factory(pos, datastr)
+				nm_size, type = datastr[0x40,4].unpack('vC')
+				nm_size -= 2 if(nm_size > 2)
+				nm = datastr[0,nm_size]
+				klass = {
+					PpsType_Root  => PPS::Root,
+					PpsType_Dir   => PPS::Dir,
+					PpsType_File  => PPS::File,
+				}[type] or raise("unknown pps_type: #{type} / #{nm}")
+				klass.new(pos, datastr)
+			end
+		end
+		class Header
+			attr_reader :big_block_size, :small_block_size, :bdb_count, :root_start
+			attr_reader :sbd_start, :sbd_count, :extra_bbd_start, :extra_bbd_count
+			attr_reader :bbd_info
+			def initialize(fh)
+				@fh = fh
+				@pps_table = {}
+				#BIG BLOCK SIZE
+				exp = get_info(0x1E, 2, 'v') or raise UnknownFormatError.new
+				@big_block_size = (2 ** exp)
+				#SMALL BLOCK SIZE
+				exp = get_info(0x20, 2, 'v') or raise UnknownFormatError.new
+                                @small_block_size = (2 ** exp) 
+				#BDB Count
+				@bdb_count = get_info(0x2C, 4, 'V') or raise UnknownFormatError.new
+				#START BLOCK
+				@root_start = get_info(0x30, 4, 'V') or raise UnknownFormatError.new 
+				#SMALL BD START
+				@sbd_start = get_info(0x3C, 4, 'V') or raise UnknownFormatError.new
+				#SMALL BD COUNT
+				@sbd_count = get_info(0x40, 4, 'V') or raise UnknownFormatError.new
+				#EXTRA BBD START
+				@extra_bbd_start = get_info(0x44, 4, 'V') or raise UnknownFormatError.new
+				#EXTRA BBD COUNT
+				@extra_bbd_count = get_info(0x48, 4, 'V')  or raise UnknownFormatError.new
+				#GET BBD INFO
+				@bbd_info = get_bbd_info
+				#GET ROOT PPS
+				@root = get_nth_pps(0)
+			end
+			def get_bbd_info
+				bdb_count = @bdb_count
+				first_count = (@big_block_size - 0x4C) / LongIntSize
+				bdl_count = (@big_block_size / LongIntSize) - 1
+				#1. 1st BDlist
+				@fh.seek(0x4C)
+				get_count = [first_count, bdb_count].min
+				buff = @fh.read(LongIntSize * get_count)
+				bdl_list = buff.unpack("V#{get_count}")
+				bdb_count -= get_count
+				#2. Extra BDList
+				block = @extra_bbd_start
+				while((bdb_count > 0) && Storage.is_normal_block?(block))
+					set_file_pos(block, 0)
+					get_count = [bdb_count, bdl_count].min
+					buff = @fh.read(LongIntSize * get_count)
+					bdl_list += buff.unpack("V#{get_count}")
+					bdb_count -= get_count
+					buff = @fh.read(LongIntSize)
+					block = buff.unpack('V').first
+				end
+				#3.Get BDs
+				bd_table = {}
+				block_no = 0
+				bd_count = @big_block_size / LongIntSize
+				bdl_list.each { |bdl|
+					set_file_pos(bdl, 0)
+					buff = @fh.read(@big_block_size)
+					array = buff.unpack("V#{bd_count}")
+					bd_count.times { |idx|
+						bd_table.store(block_no, array[idx]) unless(array[idx]==block_no.next)
+						block_no += 1
+					}
+				}
+				bd_table
+			end
+			def get_big_data(block, size)
+				result = ''
+				return result unless Storage.is_normal_block?(block)
+				rest = size
+				keys = @bbd_info.keys.sort
+				while(rest > 0)
+					res = keys.select { |key| key >= block }
+					nkey = res.first
+					idx = nkey - block
+					nxt = @bbd_info[nkey]
+					set_file_pos(block, 0)
+					get_size = [rest, @big_block_size * idx.next].min
+					result << @fh.read(get_size)
+					rest -= get_size
+					block = nxt
+				end
+				result
+			end
+			def get_info(pos, len, fmt)
+				@fh.seek(pos)
+				if(buff = @fh.read(len))
+					buff.unpack(fmt).first
+				end
+			end
+			def get_next_block_no(block)
+				@bbd_info[block] || block.next
+			end
+			def get_next_small_block_no(block)
+				base = @big_block_size / LongIntSize
+				nth = block / base
+				pos = block % base
+				blk = get_nth_block_no(@sbd_start, nth)
+				set_file_pos(blk, pos * LongIntSize)
+				@fh.read(LongIntSize).unpack('V').first
+			end
+			def get_nth_block_no(start_block, nth)
+				nxt = start_block
+				nth.times { |idx| 
+					nxt = get_next_block_no(nxt)
+					return nil unless Storage.is_normal_block?(nxt)
+				}
+				nxt
+			end
+			def get_nth_pps(pos)
+				@pps_table.fetch(pos) {
+					base_count = @big_block_size / PpsSize
+					pps_block = pos / base_count
+					pps_pos = pos % base_count
+					
+					block = get_nth_block_no(@root_start, pps_block) or return 
+					set_file_pos(block, PpsSize*pps_pos)
+					buff = @fh.read(PpsSize) or return 
+					pps = Storage.pps_factory(pos, buff)
+					pps.get_data(self)
+					@pps_table.store(pos, pps)
+				}
+			end
+			def get_small_data(block, size)
+				result = ''
+				rest = size
+				while(rest > 0)
+					set_file_pos_small(block)
+					get_size = [rest, @small_block_size].min
+					result << @fh.read(get_size)
+					rest -= @small_block_size
+					block = get_next_small_block_no(block)
+				end
+				result
+			end
+			def sb_start
+				@root.start_block
+			end
+			def sb_size
+				@root.size
+			end
+			def set_file_pos(block, pos)
+				@fh.seek((block+1) * @big_block_size + pos)
+			end
+			def set_file_pos_small(block)
+				base = @big_block_size / @small_block_size
+				nth = block / base
+				pos = block % base
+				blk = get_nth_block_no(sb_start, nth)
+				set_file_pos(blk, pos * @small_block_size)
+			end
+		end
+		def search_pps(names, cse=false, no=0, done=[])
+			#1. Check it self
+			return [] if(done.include?(no))
+			done.push(no)
+			pps = @header.get_nth_pps(no) or return []
+			cond = if(cse) 
+				Proc.new { |name|
+					/^#{Regexp.escape pps.name}$/i.match(name)
+				} 
+			else
+				Proc.new { |name| name == pps.name }
+			end
+			result = if(names.any? { |name| cond.call(name) })
+				[pps]
+			else
+				[]
+			end
+			#2. Check Child, Previous, Next PPSs
+			[ pps.dir_pps, pps.prev_pps, pps.next_pps ].each { |node|
+				unless(node == 0xFFFFFFFF)
+					result += search_pps(names, cse, node, done)
+				end
+			}
+			result	
+		end
+		private
+		def get_header
+			#0. Check ID
+			@fh.rewind
+			unless(@fh.read(8) == "\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1")
+        #raise UnknownFormatError
+      end
+			Header.new(@fh)
+		end
+	end
+	def asc2ucs(str)
+		str.split(//).join("\000") + "\000"
+	end
+	module_function :asc2ucs
+end
+
+=begin
+ToDo: Merge with Daniel J. Bergers OLEWriter
+=end