parseexcel 0.5.1.1 → 0.5.2

data/README

@@ -1,7 +1,7 @@
 Spreadsheet::ParseExcel - Get information from an Excel file.
 ============
-Version: 0.5.1.1
-Date: 2006-08-29
+Version: 0.5.2
+Date: 2007-07-19
 
 Short Description:
 Spreadsheet::ParseExcel allows you to get information out of a 

data/lib/parseexcel/olestorage.rb

@@ -100,17 +100,18 @@ module OLE
 		PpsSize       = 0x80
 		attr_reader :header
 		def initialize(filename)
-      case filename
-      when StringIO, File
+      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
+      @fh.close if(@fh_owner)
     end
 		module PPS
 			class Node
@@ -217,7 +218,7 @@ module OLE
 					bdl_list += buff.unpack("V#{get_count}")
 					bdb_count -= get_count
 					buff = @fh.read(LongIntSize)
-					block = buff.unpack('V')
+					block = buff.unpack('V').first
 				end
 				#3.Get BDs
 				bd_table = {}

data/lib/parseexcel/parser.rb

@@ -67,8 +67,9 @@ module Spreadsheet
 =begin
 				0x83    => :h_center,          # HCENTER
 				0x84    => :v_center,          # VCENTER
+=end
 				0x85    => :bound_sheet,       # BoundSheet
-
+=begin
 				0x92    => :palette,           # Palette, fgp
 
 				0x99    => :standard_width,    # Standard Col
@@ -129,7 +130,6 @@ module Spreadsheet
         0x81    => :ws_bool,           # WSBOOL
         0x83    => :h_center,          # HCENTER
         0x84    => :v_center,          # VCENTER
-        0x85    => :bound_sheet,       # BoundSheet
 
         0x92    => :palette,           # Palette, fgp
 
@@ -150,6 +150,7 @@ module Spreadsheet
 					[2].pack('L').unpack('H8').first != '02000000'
 				}
 				@buff = ''
+        @sheet_names = {}
 				#1.2 Set Event Handler
 				set_event_handlers(params[:event_handlers] || EVENT_TABLE)
 				if(params[:add_handlers].is_a? Hash)
@@ -180,17 +181,13 @@ module Spreadsheet
 					@workbook.format = (format || Format.new)
 					
 					#3. Parse content
-					pos = 0
+					@global_pos = pos = 0
 					work = biff[pos, 4]
 					pos += 4
 					ef_flag = false
 					blen = biff.length
 					while(pos <= blen)
 						op, len = work.unpack('v2')
-						#puts "*"*33
-						#puts sprintf("0x%03x %i ->%s<-", op, len, work.inspect[0,200])
-						#p "#{biff.length} / #{pos}"
-						#p work, op, len
 						if(len)
 							work = biff[pos, len]
 							pos += len
@@ -201,7 +198,6 @@ module Spreadsheet
 						elsif(op == 0x0A) #EOF
 							ef_flag = nil
 						end
-						#puts "ef_flag: =>#{ef_flag}<="
 						unless(ef_flag)	
 							#1. Formula String, but not string (0x207)
 							if(!@prev_pos.nil? && @proc_table.include?(op) && op != 0x207)
@@ -225,6 +221,7 @@ module Spreadsheet
 							end
 							(@prev_prc = op) unless(op == CONTINUE) 
 						end
+            @global_pos = pos
 						work = biff[pos, 4] if((pos+4) <= blen)
 						pos += 4
 						if(@parse_abort)
@@ -325,7 +322,6 @@ module Spreadsheet
 				
 				#Workbook Global
 				if(dtype == 0x5)
-					#puts "dtype: #{dtype}(0x5)"
 					@workbook.version = version
 					@workbook.biffversion = if(version == VERSION_EXCEL95) 
 						VERSION_BIFF5 
@@ -338,23 +334,20 @@ module Spreadsheet
 				
 				#Worksheet or Dialogsheet
 				elsif(dtype != 0x20)
-					#puts "dtype: #{dtype}(!0x20)"
 					unless(@prev_sheet_idx.nil?)
-						#puts "we have a prev_sheet_index - make a new sheet"
 						@curr_sheet_idx = @prev_sheet_idx += 1
 						@current_sheet = @workbook.worksheet(@curr_sheet_idx)	
+            @current_sheet.name = @sheet_names[@global_pos]
 						if(work.length > 4)
 							@current_sheet.sheet_version, 
 							@current_sheet.sheet_type, = work.unpack('v2') 
 						end
 					else
-						#puts "no current sheet_index so far..."
 						@workbook.biffversion = (op/0x100).to_i
 						if([VERSION_BIFF2, 
 								VERSION_BIFF3, 
 								VERSION_BIFF4,
 							].include?(@workbook.biffversion))
-							#puts "found biffversion #{sprintf('%04x', @workbook.biffversion)}"
 							@workbook.version = @workbook.biffversion
 							@workbook.worksheet(@workbook.sheet_count)
 							@curr_sheet_idx = 0
@@ -379,6 +372,16 @@ module Spreadsheet
 				}
 				cell_factory(row, col, param)
 			end
+      def bound_sheet(op, len, work)
+        pos, = work[0,4].unpack('V')
+        str = ""
+        if(@workbook.biffversion.to_i >= VERSION_BIFF8)
+          str = conv_biff8_string(work[5..-1])
+        else
+          str = simple_string(work[6..-1])
+        end
+        @sheet_names.store(pos, str)
+      end
 			def cell_factory(row, col, params)
 				return if @current_sheet.nil?
 				fmt = params[:format_no]
@@ -388,8 +391,6 @@ module Spreadsheet
 					params[:encoding] = @encoding 
 				end
 				cell = Worksheet::Cell.new(params)
-				#p format
-				#cell.type = @workbook.format.cell_type(cell) unless format.nil?
 				@current_sheet.add_cell(row, col, cell)
 			end
 			def codepage(op, len, work)
@@ -435,7 +436,6 @@ module Spreadsheet
 						str << byte.chr << "\0"
 					}
 				end
-				#puts [uncompressed, pos, len, rcnt, ecnt].inspect
 				[str, uncompressed, pos, len, rcnt, ecnt]
 			end
 			def conv_biff8_data(work, conv_flag=false)
@@ -444,7 +444,6 @@ module Spreadsheet
 				spos = pos + len + rcnt*4
 				epos = spos + ecnt
 				#4.1 Get Rich and Ext
-				#puts "work: #{work.length} < epos: #{epos} ?"
 				if(work.length < epos)
 					[
 						[nil, high, nil, nil],
@@ -528,7 +527,7 @@ module Spreadsheet
 				if(flag == 0xffff)
 					kind = work[6,1].unpack('c')
 					val = work[8,1].unpack('c')
-					if(1..2.include?(kind))
+					if((1..2).include?(kind))
 						txt = decode_bool_err(val, kind == 2)
 						params = {
 							:kind				=>	:formula_bool,
@@ -613,7 +612,6 @@ module Spreadsheet
 				pos = 4
 
 				scol.upto(ecol) { |col|
-					#puts "unpacking: #{work[pos,6].inspect}"
 					fmt, val = unpack_rk_rec(work[pos,6])
 					params = {
 						:kind				=>	:mul_rk,
@@ -631,15 +629,17 @@ module Spreadsheet
 				pos = 4
 
 				scol.upto(ecol) { |col|
-					fmt, = work[pos,2].unpack('v')
-					params = {
-						:kind				=>	:mul_blank,
-						:value			=>	'',
-						:format_no	=>	fmt,
-						:numeric		=>	false,
-					}
-					cell_factory(row, col, params)
-					pos += 2
+          if(snip = work[pos,2])
+            fmt, = snip.unpack('v')
+            params = {
+              :kind				=>	:mul_blank,
+              :value			=>	'',
+              :format_no	=>	fmt,
+              :numeric		=>	false,
+            }
+            cell_factory(row, col, params)
+            pos += 2
+          end
 				}
 			end
 =begin
@@ -823,44 +823,34 @@ module Spreadsheet
 				#1. Continue
 				#1.1 Before No Data No
 				if(cnt.nil? || @buff == '')
-					#puts "cnt was nil or buff was empty"
 					@buff << work
 				#1.1 No PrevCond
 				elsif(@prev_cond.nil?)
-					#puts "no prev_cond, adding work to buffer"
 					@buff << work[1..-1]
 				else
-					#puts "else..."
 					cnt1st = work[0] # 1st byte of Continue may be a GR byte
 					stp, lens = @prev_info
 					lenb = @buff.length
 
-					#puts "cnt1st, @prev_cond"
-					#p cnt1st, @prev_cond
-
 					#1.1 Not in String
 					if(lenb >= (stp + lens))
-						#puts "lenb (#{lenb}) >= stp + lens (#{stp+lens})"
 						@buff << work
 					#1.2 Same code (Unicode or ASCII)
 					elsif(((@prev_cond ? 1 : 0) & 0x01) == (cnt1st & 0x01))
-						#puts "same code"
 						@buff << work[1..-1]
 					#1.3 Diff code (Unicode or ASCII)
 					else
-						#puts "codes differ"
-						diff = stp + lens - lenb
 						if(ibool(cnt1st & 0x01))
-							#puts "new code is unicode"
 							dum, gr = @buff.unpack('vc')
 							@buff[2,1] = [gr | 0x01].pack('c')
 							(lenb-stp).downto(1) { |idx|
 								@buff[stp+idx,0] = "\x00"
 							}
 						else
-							#puts "old code is unicode"
-							(diff/2).downto(1) { |idx|
-								work[idx+1,0] = "\x00"
+						  diff = stp + lens - lenb
+							#(diff/2).downto(1) { |idx|
+							(work.length).downto(1) { |idx|
+								work[idx,0] = "\x00"
 							}
 						end
 						@buff << work[1..-1]
@@ -871,14 +861,11 @@ module Spreadsheet
 
 				while(@buff.length >= 4)
 					buff, len, stpos, lens = conv_biff8_data(@buff, true)
-					#puts buff.inspect
 					unless(buff[0].nil?)
 						pkg_str = Worksheet::PkgString.new(*buff)
 						@workbook.add_pkg_str(pkg_str)
-						#puts pkg_str
 						@buff = @buff[len..-1]
 					else
-						#puts "code convert, breaking with @prev_cond: #{buff[1]} and @prev_info: [#{stpos}, #{lens}]"
 						@prev_cond = buff[1]
 						@prev_info = [stpos, lens]
 						break
@@ -893,27 +880,22 @@ module Spreadsheet
 				null = "\0\0\0\0"
 				res = nil
 				if(ptn == 0)
-					#puts "ptn==0"
 					res, = ((@bigendian) ? swk + null : null + lwk).unpack('d')
 				elsif(ptn == 1)
-					#puts "ptn==1"
 					swk[3] &= [(swk[3,1].unpack('c').first & 0xFC)].pack('c')[0]
 					lwk[0] &= [(lwk[0,1].unpack('c').first & 0xFC)].pack('c')[0]
 					res = ((@bigendian) ? swk + null : null + lwk).unpack('d').first.to_f / 100.0
 				elsif(ptn == 2)
-					#puts "ptn==2"
 					bin, = swk.unpack('B32')
 					wklb = [((bin[0,1]*2) + bin[0,30])].pack('B32')
 					wkl = (@bigendian) ? wklb : wklb.unpack('c4').reverse.pack('c4')
 					res, = wkl.unpack('i')
 				else
-					#puts "ptn==#{ptn}"
 					ub, = swk.unpack('B32')
 					wklb = [((ub[0,1]*2) + ub[0,30])].pack('B32')
 					wkl = (@bigendian) ? wklb : wklb.unpack('c4').reverse.pack('c4')
 					res = wkl.unpack('i').first / 100.00
 				end
-				#p lwk, swk, swk[3,1], res if([5,12].include? res)
 				[ef, res]
 			end
 			def ws_bool(op, len, work) # DK: P452
@@ -1022,9 +1004,6 @@ module Spreadsheet
         if(@encoding)
           params.store(:encoding, @encoding)
         end
-				#p "**"*33
-				#p work
-				#p idx
 				@workbook.add_cell_format(Format.new(params))
 			end
 		end

data/lib/parseexcel/workbook.rb

@@ -62,8 +62,12 @@ module Spreadsheet
 			def sheet_count
 				@worksheets.size
 			end
-			def worksheet(idx)
-				@worksheets[idx] ||= Worksheet.new
+      def worksheet(idx, encoding=nil)
+        if(idx.is_a?(Integer))
+          @worksheets[idx] ||= Worksheet.new
+        else
+          @worksheets.find { |sheet| sheet.name(encoding) == idx }
+        end
 			end
 		end
 	end

data/lib/parseexcel/worksheet.rb

@@ -33,7 +33,7 @@ module Spreadsheet
 				:scale, :page_start, :fit_width, :fit_height, :header_margin,
 				:footer_margin, :copies, :left_to_right, :no_pls, :no_color, :draft,
 				:notes, :no_orient, :use_page, :landscape, :sheet_version, :sheet_type,
-				:header, :footer, :page_fit
+				:header, :footer, :page_fit, :name
 			class Cell
 				attr_accessor :value, :kind, :numeric, :code, :book, :format_no,
 					:format, :rich, :encoding, :annotation
@@ -86,6 +86,9 @@ module Spreadsheet
 					msec = time.to_i
 					OLE::DateTime.new(year,month,day,hour,min,sec,msec)
 				end
+        def encoding=(enc)
+          @encoding = enc
+        end
 				def to_i
 					@value.to_i
 				end
@@ -94,7 +97,11 @@ module Spreadsheet
 				end
 				def to_s(target_encoding=nil)
 					if(target_encoding)
-						Iconv.new(target_encoding, @encoding).iconv(@value.to_s)
+            begin
+						  Iconv.new(target_encoding, @encoding).iconv(@value)
+            rescue
+						  Iconv.new(target_encoding, 'ascii').iconv(@value.to_s)
+            end
 					else
 						@value.to_s
 					end
@@ -135,6 +142,13 @@ module Spreadsheet
 			def each(skip=0, &block)
 				@cells[skip..-1].each(&block)
 			end
+      def name(target_encoding=nil)
+        if(target_encoding)
+          Iconv.new(target_encoding, 'UTF-16LE').iconv(@name.to_s)
+        else
+          @name
+        end
+      end
       def num_rows
         @cells.size
       end

data/test/test_parser.rb

@@ -24,7 +24,7 @@ class StubParserWorksheet
 	attr_accessor :resolution, :v_resolution
 	attr_accessor :header_margin, :footer_margin, :copies, :left_to_right
 	attr_accessor :no_pls, :no_color, :draft, :notes, :no_orient, :use_page
-	attr_accessor :landscape 
+	attr_accessor :landscape, :name
 	def initialize
 		@cells = []
 	end
@@ -515,9 +515,9 @@ class TestParser < Test::Unit::TestCase
 	end
 	def test_str_wk7
 		@parser.buff = "fo"
-		@parser.prev_cond = true
+		@parser.prev_cond = 1
 		@parser.prev_info = [1,2]
-		@parser.str_wk("\x00o", true)
+		@parser.str_wk("\x01o", true)
 		assert_equal("foo", @parser.buff)
 	end
 	def test_str_wk8
@@ -678,6 +678,7 @@ class TestParser2 < Test::Unit::TestCase
 		cell0 = sheet.cell(0,0)
 		assert_equal('cellcontent', cell0.to_s('latin1'))
 		assert_equal('cellcomment', cell0.annotation)
+    assert_equal('HW', cell0.annotation.author)
 		cell1 = sheet.cell(1,1)
 		assert_equal('cellcontent', cell1.to_s('latin1'))
 		assert_equal('annotation', cell1.annotation)
@@ -707,12 +708,12 @@ class TestParser2 < Test::Unit::TestCase
 		assert_equal('hello', cell0.to_s('latin1'))
 		ann = cell0.annotation
 		assert_equal("david surmon:\nnow is the time for all good men to come to the aid of their country!", ann)
-		assert_equal('david surmon', ann.author)
+		assert_equal('F', ann.author)
 		cell1 = sheet.cell(0,1)
 		assert_equal('there', cell1.to_s('latin1'))
 		ann = cell1.annotation
 		assert_equal("david surmon:\nwhat should this comment be? Now what?", ann)
-		assert_equal('david surmon', ann.author)
+		assert_equal('F', ann.author)
 		cell2 = sheet.cell(0,2)
 		assert_equal('whos', cell2.to_s('latin1'))
 		cell3 = sheet.cell(1,0)
@@ -724,10 +725,17 @@ class TestParser2 < Test::Unit::TestCase
 		assert_nothing_raised { 
 			book = @parser.parse(source)
 		}
+		sheet = book.worksheet(0)
+    assert_equal('First Worksheet', sheet.name('latin1'))
 		sheet = book.worksheet(1)
+    assert_equal('Second Worksheet', sheet.name('latin1'))
 		cell0 = sheet.cell(0,0)
 		assert_equal('version', cell0.to_s('latin1'))
 		cell1 = sheet.cell(1,0)
 		assert_equal(1, cell1.to_i)
+		sheet = book.worksheet(2)
+    assert_equal('Third Worksheet', sheet.name('latin1'))
+    assert_equal(sheet, book.worksheet('Third Worksheet', 'latin1'))
+    assert_equal(sheet, book.worksheet("T\0h\0i\0r\0d\0 \0W\0o\0r\0k\0s\0h\0e\0e\0t\0"))
 	end
 end

metadata

@@ -1,10 +1,10 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.8.11
+rubygems_version: 0.9.4
 specification_version: 1
 name: parseexcel
 version: !ruby/object:Gem::Version 
-  version: 0.5.1.1
-date: 2006-08-29 00:00:00 +02:00
+  version: 0.5.2
+date: 2007-07-19 00:00:00 +02:00
 summary: Reads Excel documents on any platform
 require_paths: 
 - lib
@@ -25,39 +25,38 @@ required_ruby_version: !ruby/object:Gem::Version::Requirement
 platform: ruby
 signing_key: 
 cert_chain: 
+post_install_message: 
 authors: 
 - Hannes Wyss
 files: 
-- lib/parseexcel
 - lib/parseexcel.rb
-- lib/parseexcel/worksheet.rb
 - lib/parseexcel/format.rb
 - lib/parseexcel/olestorage.rb
-- lib/parseexcel/workbook.rb
-- lib/parseexcel/parser.rb
 - lib/parseexcel/parseexcel.rb
-- test/data
+- lib/parseexcel/parser.rb
+- lib/parseexcel/workbook.rb
+- lib/parseexcel/worksheet.rb
 - test/suite.rb
 - test/test_format.rb
+- test/test_olestorage.rb
+- test/test_parser.rb
 - test/test_workbook.rb
 - test/test_worksheet.rb
-- test/test_parser.rb
-- test/test_olestorage.rb
+- test/data/annotation.xls
 - test/data/bar.xls
+- test/data/comment.5.0.xls
+- test/data/comment.xls
 - test/data/dates.xls
+- test/data/float.5.0.xls
+- test/data/float.xls
 - test/data/foo.xls
 - test/data/image.xls
 - test/data/nil.xls
 - test/data/umlaut.5.0.xls
 - test/data/umlaut.biff8.xls
-- test/data/float.5.0.xls
-- test/data/float.xls
 - test/data/uncompressed.str.xls
-- test/data/comment.xls
-- test/data/comment.5.0.xls
-- test/data/annotation.xls
-- README
 - COPYING
+- README
 - usage-en.txt
 test_files: 
 - test/suite.rb