extcsv 0.10.0 → 0.11.0

data/LICENSE

@@ -0,0 +1,27 @@
+Copyright (c) 2009, Ralf Mueller (stark.dreamdetective@googlemail.com)
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * The names of its contributors may not be used to endorse or promote
+      products derived from this software without specific prior written
+      permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/gemspec

@@ -2,7 +2,8 @@ require 'rubygems'
 
 spec = Gem::Specification.new do |s|
   s.name              = "extcsv"
-  s.version           = "0.10.0"
+  s.version           = "0.11.0"
+  s.date              = Time.new.to_s
   s.author            = "Ralf Mueller"
   s.email             = "stark.dreamdetective@gmail.com"
   s.homepage          = "http://extcsv.rubyforge.org"
@@ -10,11 +11,8 @@ spec = Gem::Specification.new do |s|
   s.platform          = Gem::Platform::RUBY
   s.summary           = "Let CSV-like files behave like DB-tables: selection, data operations on columns. \n" +
                         "Easy plotting with gnuplot and modelling"
-  candidates        = Dir.glob("lib/*.rb") + ["rakefile","gemspec"]
-  s.files             = candidates.delete_if do |item|
-                          item.include?("pkg") || item.include?("rdoc") || item.include?("extcsv_diagram.rb") || item.include?("extcsv_units.rb")
-                        end
-  s.test_files        = (Dir.glob("test/test_*.rb") + Dir.glob("test/data/*.{csv,txt}")).delete_if  {|item| item.include?("test_extcsv_diagram.rb")}
+  s.files             = Dir.glob("lib/*.rb") + ["rakefile","gemspec","LICENSE"] 
+  s.test_files        = Dir.glob("test/test_*.rb") + Dir.glob("test/data/*.{csv,txt}")
   s.has_rdoc          = true
 end
 

data/lib/extcsv.rb

@@ -1,27 +1,44 @@
-require 'rubygems'
 require 'csv'
 require 'ostruct'
 
-################################################################################
-# Author:: Ralf Mueller
-################################################################################
 class Nil
   def to_s; ''; end
   def to_a; []; end
   def empty?; true; end
 end
 
+class Array
+  def complement(other)
+    (self - other) + (other - self)
+  end
+end
+
+# = CSV-like Data processing made easy
+# (see project page: http://rubyforge.org/projects/extcsv)
+#
+# The extcsv package should enable you to navigate and operate on csv-like data
+# as easy and comfortable as possible. The main restriction is, that the
+# columns are named, i.e. the first line of a data file has to contain a header with string-like entries.
+#
+# Data can be read from files, strings, hashes or arrays.
+#
+# Have a look at my other projects for
+# correlation[http://extcsv.rubyforge.org/correlation] and {spectral filtering}[http://extcsv.rubyforge.org/spectralfilter].
+#
+# ==== Author: Ralf M�ller
+# ==== License: BSD - see {license file}[http:/extcsv.rubyforge.org/svn/extcsv/trunk/LICENSE]
+################################################################################
 class ExtCsv < OpenStruct
-  VERSION = '0.10.0'
+  VERSION = '0.11.0'
 
   include Comparable
   include Enumerable
 
   # Allowed data types
-  TYPES = %w{csv tsv psv txt plain}
+  TYPES = %w{csv ssv tsv psv txt plain}
 
   # Allowed input modes, db and url are not supported, yet
-  MODES = %w{file db url hash array string}
+  MODES = %w{file hash array string}
 
   # column names from different file type, which that have the same
   # meaning
@@ -84,9 +101,10 @@ class ExtCsv < OpenStruct
   
   def set_separators(obj_hash)
     obj_hash[:cellsep]  = case obj_hash[:datatype]
-                          when "txt","tsv": "\t"
-                          when "csv":       ';'
-                          when "psv":       "|"
+                          when "txt","tsv" then "\t"
+                          when "ssv"       then ';'
+                          when "csv"       then ','
+                          when "psv"       then "|"
                           end
     obj_hash[:rowsep]   = "\r\n"
   end
@@ -105,14 +123,15 @@ class ExtCsv < OpenStruct
   # * '+' and '-' are changed into the correspondig words
   # * empty lines are removed
   # * dots are changed into underscores for columns names
+  # * commas are converteed into dots (german number notation) unless the commy is the cell separator
   # * the greek sign � is changes into mu
   def parse_content(filecontent,obj_hash)
     content     = []
-    # special treatement of emission/bloostblank data switch decimal sign
-    filecontent = filecontent.gsub(',','.')
+    # convert numbers into us. notation if this doesn't crashes with the columns separator
+    filecontent = filecontent.gsub(',','.') unless obj_hash[:datatype] == "csv"
     # remove blank lines
     filecontent = filecontent.gsub(/\r\r/,"\r").gsub(/(\r\n){2,}/,"\r\n").gsub(/\n{2,}/,"\n")
-    csv         = CSV::StringReader.parse(filecontent, obj_hash[:cellsep])#, obj_hash[:rowsep])
+    csv         = CSV.parse(filecontent, :col_sep => obj_hash[:cellsep])#, obj_hash[:rowsep])
     
     # read @datatype specific header
     header = csv.shift
@@ -121,19 +140,19 @@ class ExtCsv < OpenStruct
 
     header.each_with_index {|key,i|
       key = "test" if key.nil?
-      header[i] = key.downcase.tr(' ','').tr('"','').tr('�',"ue").tr('�',"ae")\
-        .tr('�',"oe").gsub(/\[\w*\]/,"")\
-        .tr('�',"ue").gsub(/^\+/,"plus_")\
-        .gsub('�m','mu')\
-        .gsub(/^-/,"minus_").tr('-','_').tr('+','_').gsub(/(\(|\))/,'_').tr('.','_').chomp
+      header[i] = key.downcase.tr(' ','').tr('"','')\
+        .gsub(/\[\w*\]/,"")\
+        .gsub(/^\+/,"plus_").gsub(/^-/,"minus_")\
+        .tr('-','_').tr('+','_')\
+        .gsub(/(\(|\))/,'_').tr('.','_').chomp
     }
     content << header
     # read the data itself
-    csv.each {|row| content << row if row.to_a.nitems > 0 }
+    csv.each {|row| content << row if row.to_a.delete_if(&:nil?).size != 0 }
 
     # further processing according to the input type
     case obj_hash[:datatype]
-    when "csv"
+    when "csv","ssv","psv","txt","tsv"
       # check if rows have the same lenght
       contents_size = content.collect {|row| row.size}
       content.each_with_index {|row,i|
@@ -217,7 +236,7 @@ class ExtCsv < OpenStruct
     # ATTENTION: DO NOT MIX THE USAGE OF STRING AND SYMBOLS!
     #   This can lead to a data loss, because e.g. {:k => 4, "k" => 3} will be
     #   transformed into {:k=>3}
-    selection.each_key {|k| 
+    selection.keys {|k| 
       if k.kind_of?(String)
         v                   = selection.delete(k)
         selection[k.to_sym] = v
@@ -228,7 +247,7 @@ class ExtCsv < OpenStruct
     vars.each {|attribute|
       unless @table.has_key?(attribute)
         $stdout << "Object does NOT hav the attribute '#{attribute}'!"
-        raise
+        raise 
       end
     }
     # default is the lookup in the whole array of values for each var
@@ -346,7 +365,11 @@ class ExtCsv < OpenStruct
   # columns in order of these columns, e.g.
   # [[col0_val0,col1_val0,...],...,[col0_valN, col1_valN,...]]
   def datasets(*columns)
-    retval = []
+    retval = [] 
+
+    # preset the selected columns to select
+    columns = datacolumns if columns.empty?
+
     columns.each {|col| retval << @table[col.to_sym]}
     retval.transpose
   end
@@ -441,6 +464,7 @@ class ExtCsv < OpenStruct
   # each_obj iterates over the subobject of the receiver, which belong to the
   # certain value of key
   def each_obj(key, &block)
+    key = key.to_sym
     retval = []
     send(key).sort.uniq.each {|value|
       retval << selectBy(key => value)
@@ -454,17 +478,17 @@ class ExtCsv < OpenStruct
 
   # :call-seq:
   # split.(:col0,...,:colN) {|obj| ...}
-  # splot.(:col0,...,:coln) -> [obj0,...,objM]
+  # split.(:col0,...,:coln) -> [obj0,...,objM]
   # 
   # split is a multi-key-version of each_obj. the receiver is splitted into
   # subobject, which have constant values in all given columns
   #
   # eg.
-  # <tt>qpol.split(:kv, :focus) {|little_qp| little_qp.kv == little_kv.uniq}</tt>
+  # <tt>obj.split(:kv, :focus) {|little_obj| little_obj.kv == little_kv.uniq}</tt>
   #
   # or
   #
-  # <tt>qpol.split(:kv, :focus) = [qpol_0,...,qpol_N]</tt>
+  # <tt>obj.split(:kv, :focus) = [obj_0,...,obj_N]</tt>
   def split(*columns, &block)
     retval = []
     deep_split(columns, retval)
@@ -539,45 +563,44 @@ class ExtCsv < OpenStruct
     end
   end
   
-  # Equality if the datacolumns have the save values,i.e. as float for numeric
+  # Equality if the datacolumns have the save values, i.e. as float for numeric
   # data and as strings otherwise
-  # the time-column is exceptional, because the e.g. the seconds could be left
-  # out when file is saved with MSExcel
   def eql?(other)
-    return false unless ( 
-                         self.datatype == other.datatype or self.datatype  == other.datatype
-                        )
-
-    omitted = %w|bfe_vers version zeit time|
-    return false unless self.datacolumns == other.datacolumns
-
-    # split between textual and numeric values
-    text_columns = %w|anlage kommentar dateiname| & self.datacolumns
-    num_columns  = self.datacolumns - text_columns - omitted
-    text_columns.each {|c| return false if send(c) !=  other.send(c)}
-    num_columns.each  {|c| 
-      a_ = send(c)
-      a__ = a_.collect {|v| v.to_f}
-      b_ = other.send(c)
-      b__ = b_.collect {|v| v.to_f}
-     #$stdout << c << "\n" << filename << "\n";
-     #$stdout << c << "\n" << other.filename << "\n";
-      return false  if (b__ != a__)
-      #if (send(c).collect {|v| v.to_f} != other.send(c).collect {|v| v.to_f})}
-    }
+    return false unless ( self.datatype == other.datatype or self.datatype  == other.datatype)
+
+    return false unless self.datacolumns.sort == other.datacolumns.sort
+
+    datacolumns.each {|c| return false unless send(c) == other.send(c) }
+    
     return true
   end
 
+  def diff(other)
+    diffdatatype = [self.datatype, other.datatype]
+    return diffdatatype unless diffdatatype.uniq.size == 1
+
+    diffdatacolums = self.datacolumns.complement(other.datacolumns)
+    return [self.diffdatacolums,other.datacolumns] unless diffdatacolums.empty?
+    
+    datacolumns.each {|c| 
+      diffcolumn = send(c).complement(other.send(c))
+      return diffcolumn unless diffcolumn.empty?
+    }
+  end
+
   def <=>(other)
     compare = (self.size <=> other.size)
-    #test $stdout << compare.to_s << "\n"
+    #$stdout << compare.to_s << "\n"
     compare = (datacolumns.size <=> other.datacolumns.size) if compare.zero?
-    #test $stdout << compare.to_s << "\n" if compare.zero?
+    #$stdout << compare.to_s << "\n"# if compare.zero?
+    #compare = (self.datasets(* self.datacolumns.sort) <=> other.datasets(* other.dataacolumns.sort)) if compare.zero?
+    #$stdout << compare.to_s << "\n"# if compare.zero?
     compare = (to_s.size <=> other.to_s.size) if compare.zero?
-    #test $stdout << compare.to_s << "\n" if compare.zero?
+    #
+    #$stdout << compare.to_s << "\n" if compare.zero?
     compare = (to_s <=> other.to_s) if compare.zero?
-    #test $stdout << compare.to_s << "\n" if compare.zero?
-    #test $stdout << "##################################\n"
+    #$stdout << compare.to_s << "\n" if compare.zero?
+    #$stdout << "##################################\n"
     compare
   end
   
@@ -612,8 +635,8 @@ class ExtCsv < OpenStruct
     when 1
       hash = marshal_dump.merge(other.marshal_dump)
     else
-      if datatypes.include?("csv")
-        csv_index  = datatypes.index("csv")
+      if datatypes.include?("ssv") or datatypes.include?("csv")
+        csv_index  = datatypes.index("ssv") || datatypes.index("csv")
         qpol_index = csv_index - 1
         objects[csv_index].modyfy_time_column
         hash = objects[csv_index].marshal_dump.merge(objects[qpol_index].marshal_dump)
@@ -654,7 +677,7 @@ class ExtCsv < OpenStruct
   def ExtCsv.combine(obj, obj_=nil)
     obj.combine(obj_)
   end
-  private :deep_copy, :set_separators, :parse_content
+  private :deep_copy, :deep_split, :set_separators, :parse_content, :change_time_format
 end
 
 class ExtCsvExporter

data/lib/extcsv_diagram.rb

@@ -0,0 +1,201 @@
+require 'rubygems'
+require 'gnuplot'
+require 'win32ole' if RUBY_PLATFORM =~ /(win32|cygwin)/i
+require 'extcsv_units'
+
+# This module provides separate plotting methods 
+module ExtCsvDiagram
+  include ExtCsvUnits
+  GRAPH_OPTIONS = {
+                    :type           => "linespoints",
+                    :linewidth      => "1",
+                    :terminal       => 'x11',
+                    :size           => nil,
+                    :filename       => nil,
+                    :title          => nil,
+                    :label_position => "left",
+                    :label?         => true,
+                    :grid           => true,
+                    :xrange         => nil,
+                    :yrange         => nil,
+                    :x2range        => nil,
+                    :y2range        => nil,
+                    :y1limit        => nil,
+                    :y2limit        => nil,
+                    :using          => nil,
+                    :datasets       => {:using => []},
+                    :logscale       => nil,
+                    :add_settings   => [], 
+                    :point_label?   => false,
+                    :time_format    => '"%d.%m\n%H:%M:%S"'
+  }
+  @@timeColumns = %w[time time_camera zeit]
+
+  def ExtCsvDiagram.set_pointlabel(obj, plot, x_col, x, y, label_col=nil, size='10')
+    timemode = (%w[zeit zeitstempel time timestamp].include?(x_col.to_s))
+    x.each_index {|i|
+      point  = (timemode) ? "\"#{x[i].to_s}\"" : x[i].to_s
+      point += ",#{y[i].to_s}"
+      unless label_col.nil?
+        label = obj.send(label_col)[i]
+      else
+        label = point
+      end
+      plot.label  "'#{label}' at #{point} font 'Times,#{size}' offset 1,1"
+    }
+  end
+
+  def ExtCsvDiagram.set_limit(plot,x,xIsTime,axes,limit,limitname,options)
+    if xIsTime
+      xmin, xmax = [x.min,x.max]
+      using = '1:3'
+    else
+      xtof = x.collect {|v| v.to_f}
+      xmin, xmax = [xtof.min,xtof.max]
+      using = '1:2'
+    end
+    plot.data << Gnuplot::DataSet.new([
+                                      [xmin,xmax],
+                                      [limit,limit]
+    ]) {|ds| 
+      ds.with = "lines axes #{axes} lw #{options[:linewidth]}"
+      ds.title = limitname.nil? ? '' : limitname
+      ds.using = using
+
+    }
+  end
+  
+  def ExtCsvDiagram.enhanceTitleByGroup(group_by,ob)
+    title = ''
+    group_by.each {|col|
+      colunit = Units[col.to_sym].nil? ? col.to_s : "[#{Units[col.to_sym]}]"
+      name = [ob.send(col)[0],colunit]
+      title += (col.to_sym == :focus) ? name.reverse.join('') : name[0]
+      title += " " unless col == group_by.last
+    }
+    title
+  end
+
+  def ExtCsvDiagram.plot(obj,
+           group_by, # array[col0, ..., colN]
+           x1_col,
+           y1_cols,
+           x2_col=nil,
+           y2_cols=[],
+           title='',
+           options={})
+  
+    options = GRAPH_OPTIONS.merge(options)
+    outputfilename = (options[:filename].nil?) ? obj.filename : options[:filename]
+    Gnuplot.open {|gp|
+      Gnuplot::Plot.new(gp) {|plot|
+        plot.title "'" + title + "'"
+        plot.key options[:label_position]
+        plot.key 'off' unless options[:label?]
+        if options[:terminal] != 'x11'
+          size = (options[:size].nil?) ? '' : " size #{options[:size]}"
+          plot.terminal options[:terminal] + size
+          plot.output outputfilename + "." + options[:terminal].split(" ")[0]
+        end
+
+        plot.grid if options[:grid]
+
+        options[:add_settings].each {|setting|
+          md = /^(\w+)/.match(setting)
+          plot.set(md[1],md.post_match) unless md.nil?
+        }
+
+        # handling of axes
+        plot.y2tics 'in'     unless ( y2_cols.nil? or y2_cols.empty? )
+        plot.x2tics 'in'     unless ( (x2_col.respond_to?(:empty?) and x2_col.empty?) or x2_col == nil)
+
+        plot.xrange  options[:xrange] unless options[:xrange].nil?
+        plot.yrange  options[:yrange] unless options[:yrange].nil?
+        plot.x2range options[:x2range] unless options[:x2range].nil?
+        plot.y2range options[:y2range] unless options[:y2range].nil?
+        plot.xlabel  options[:xlabel]  unless options[:xlabel].nil?
+        plot.ylabel  options[:ylabel]  unless options[:ylabel].nil?
+        plot.x2label options[:x2label] unless options[:x2label].nil?
+        plot.y2label options[:y2label] unless options[:y2label].nil?
+
+
+        if @@timeColumns.include?(x1_col.to_s)
+          plot.xdata 'time'
+          plot.timefmt '"%Y-%m-%d %H:%M:%S"'
+          plot.format 'x ' + options[:time_format]
+        end
+        if @@timeColumns.include?(x2_col.to_s)
+          plot.x2data 'time'
+          plot.timefmt '"%Y-%m-%d %H:%M:%S"'
+          plot.format 'x2 ' + options[:time_format]
+        end
+
+        # Data for first x-axes
+        obj.split(*group_by) {|ob|
+          y1_cols.each {|y_col|
+            x = ob.send(x1_col)
+            y = ob.send(y_col)
+            title = enhanceTitleByGroup(group_by,ob)
+            plot.data << Gnuplot::DataSet.new([x,y]) {|ds|
+              unit = Units[y_col.to_sym].nil? ? '' : "[#{Units[y_col.to_sym]}]"
+              ds.using = @@timeColumns.include?(x1_col.to_s) ? '1:3' : '1:2'
+              ds.with  = options[:type] + " axes x1y1 lw #{options[:linewidth]}"
+              ds.title =  options[:onlyGroupTitle] ? "#{title}" : "#{y_col} #{unit}, #{title}"
+            }
+
+            # set labels if requested
+            set_pointlabel(ob,plot, x1_col, x,y, options[:label_column],options[:label_fsize]) if options[:point_label?]
+
+          }
+          y2_cols.each {|y_col|
+            x = ob.send(x1_col)
+            axes = "x1y2"
+            unless ( (x2_col.respond_to?(:empty?) and x2_col.empty?) or x2_col == nil)
+              x = ob.send(x2_col)
+              axes = "x2y2"
+            end
+            title = enhanceTitleByGroup(group_by,ob)
+            y = ob.send(y_col)
+            plot.data << Gnuplot::DataSet.new([x,y]) {|ds|
+              unit  = Units[y_col.to_sym].nil? ? '' : "[#{Units[y_col.to_sym]}]"
+              ds.using = ( (/x2/.match(axes) and @@timeColumns.include?(x2_col.to_s)) or (/x1/.match(axes) and @@timeColumns.include?(x1_col.to_s)) ) ? '1:3' : '1:2'
+              ds.with  = options[:type] + " axes #{axes} lw #{options[:linewidth]}"
+              ds.title = "#{y_col} #{unit}, #{title}"
+            }
+            # set labels if requested
+            set_pointlabel(ob,plot, (axes == "x2y2") ? x2_col : x1_col, x,y, options[:label_column],options[:label_fsize]) if options[:point_label?]
+          }
+        }
+        # show limits for each y-axes
+        unless y1_cols.empty?
+          if options[:y1limits].kind_of?(Array)
+            x = obj.send(x1_col)
+            options[:y1limits].each {|limit| set_limit(plot,
+                                                       x,
+                                                       @@timeColumns.include?(x1_col.to_s),
+                                                       "x1y1",
+                                                       limit,
+                                                       options[:y1limitname],
+                                                       options)}
+          end
+        end
+        unless y2_cols.empty?
+          if options[:y2limits].kind_of?(Array)
+            xcol, axes = x2_col.to_s.empty? ? [x1_col,"x1y2"] : [x2_col,"x2y2"]
+            x = obj.send(xcol)
+            options[:y2limits].each {|limit| set_limit(plot,
+                                                       x,
+                                                       @@timeColumns.include?(xcol.to_s),
+                                                       axes,
+                                                       limit,
+                                                       options[:y2limitname],
+                                                       options)}
+          end
+        end
+      }
+    }
+  end
+  
+  def ExtCsvDiagram.multiplot()
+  end
+end

data/lib/extcsv_units.rb

@@ -0,0 +1,26 @@
+################################################################################
+# Author: Ralf M�ller
+#
+# ==== TODO: Units are automatically selected from the column name. You could add
+# units here and they will be used for graphs. I think, this is a premature
+# solution, because the file will be edited by nearly every user, so it
+# actually is a configutration file. But without units, the graphs loose much
+# of their information. There are separate packages for units like
+# units.rubyforge.org. But there will allways be the problem, that column names
+# cannot be restricted to find a appropriate unit.
+################################################################################
+module ExtCsvUnits
+  Units = 
+    {
+      :col1             => "kV",
+      :col2             => "kV",
+      :col3             => "kV",
+      :col4             => "kV",
+      :col5             => "kV",
+      :col6             => "kV",
+      :col7             => "kV",
+      :col8             => "kV",
+      :zeit           => "yyyy-mm-dd hh:mm:ss",
+      :time           => "yyyy-mm-dd hh:mm:ss"
+    }
+end

data/lib/lsmodel.rb

@@ -1,7 +1,7 @@
 require 'matrix'
 require 'mathn'
 
-# Modelling funtionality with the least square mathod
+# Modelling funtionality with the least square method
 module LSModel
   MINIMAL_VARIATION_SIZE = 8
 

data/rakefile

@@ -61,7 +61,7 @@ end
 
 # ====================================================================
 desc "Build package for further developement"
-task :build_dev do
+task :build_dev do 
   files = SPEC.files + Dir.glob("test/data/*")
 #require 'pp';  pp files;end
   com = "tar czf pkg/#{SPEC.name}-#{SPEC.version}-src.tgz #{files.join(" ")}"
@@ -69,12 +69,12 @@ task :build_dev do
 end
 # ====================================================================
 desc "Install the Library with docs"
-task :install do
+task :install => [:repackage] do 
   command = "gem install pkg/#{SPEC.name}-#{SPEC.version}.gem"
   puts command
   system(command)
 end
-task :smallInstall do 
+task :smallInstall => [:repackage] do 
   command = "gem install pkg/#{SPEC.name}-#{SPEC.version}.gem --no-ri --no-rdoc"
   puts command
   system(command)
@@ -99,7 +99,7 @@ Rake::RDocTask.new("rdoc") { |rdoc|
   rdoc.rdoc_dir = 'rdoc'
   rdoc.title    = "extcsv - Make csv-like Data feel ike DB-tables"
   rdoc.options << '-ad' << '--line-numbers' << '--inline-source'
-  rdoc.rdoc_files.include('lib/**/*.rb', 'doc/**/*.rdoc')
+  rdoc.rdoc_files = SPEC.files - SPEC.test_files
 }
 
 ############################################################

data/test/data/file05.csv

@@ -0,0 +1,31 @@
+filename,Nr,Zeit,col1,col2,col3[mm],col4[Px],col5[Px]
+23-02-2007_10-47-32.bmp,129,23.02.2007 10:47:32.078,0.15,1.331,1.416,298.72,281.26
+23-02-2007_10-48-15.bmp,130,23.02.2007 10:48:15.031,0.15,1.394,1.453,297.94,281.49
+23-02-2007_10-48-58.bmp,131,23.02.2007 10:48:58.031,0.15,1.402,1.451,298.17,281.34
+23-02-2007_10-49-41.bmp,132,23.02.2007 10:49:40.984,0.15,1.372,1.438,298.44,281.30
+23-02-2007_10-50-24.bmp,133,23.02.2007 10:50:23.984,0.15,1.357,1.421,298.62,281.23
+23-02-2007_10-51-07.bmp,134,23.02.2007 10:51:06.921,0.15,1.384,1.438,298.36,281.26
+23-02-2007_10-51-50.bmp,135,23.02.2007 10:51:49.781,0.15,1.393,1.451,298.03,281.31
+23-02-2007_10-53-16.bmp,136,23.02.2007 10:53:15.484,0.15,1.380,1.444,298.31,281.26
+23-02-2007_10-54-05.bmp,137,23.02.2007 10:54:04.812,0.15,1.387,1.446,298.39,281.33
+23-02-2007_10-55-31.bmp,138,23.02.2007 10:55:30.937,0.15,1.396,1.454,298.04,281.24
+23-02-2007_10-56-14.bmp,139,23.02.2007 10:56:13.953,0.15,1.396,1.454,298.24,281.32
+23-02-2007_10-57-40.bmp,140,23.02.2007 10:57:39.703,0.15,1.393,1.451,298.17,281.31
+23-02-2007_10-59-06.bmp,141,23.02.2007 10:59:05.578,0.15,1.357,1.426,298.74,281.12
+23-02-2007_10-59-49.bmp,142,23.02.2007 10:59:48.421,0.15,1.335,1.414,299.00,281.20
+23-02-2007_11-00-31.bmp,143,23.02.2007 11:00:31.296,0.15,1.356,1.429,298.44,281.33
+23-02-2007_11-01-14.bmp,144,23.02.2007 11:01:14.171,0.15,1.358,1.426,298.73,281.21
+23-02-2007_11-01-57.bmp,145,23.02.2007 11:01:57.171,0.15,1.355,1.433,298.56,281.28
+23-02-2007_11-02-40.bmp,146,23.02.2007 11:02:40.187,0.15,1.366,1.436,298.63,281.20
+23-02-2007_11-03-23.bmp,147,23.02.2007 11:03:23.250,0.15,1.392,1.449,298.26,281.28
+23-02-2007_11-04-06.bmp,148,23.02.2007 11:04:06.171,0.15,1.355,1.434,298.72,281.29
+23-02-2007_11-04-49.bmp,149,23.02.2007 11:04:49.234,0.15,1.371,1.452,298.21,281.39
+23-02-2007_11-05-32.bmp,150,23.02.2007 11:05:32.156,0.15,1.336,1.421,298.84,281.29
+23-02-2007_11-06-15.bmp,151,23.02.2007 11:06:15.234,0.15,1.394,1.448,298.16,281.35
+23-02-2007_11-06-58.bmp,152,23.02.2007 11:06:58.359,0.15,1.359,1.425,298.81,281.30
+23-02-2007_11-07-42.bmp,153,23.02.2007 11:07:41.546,0.15,1.390,1.446,298.22,281.44
+23-02-2007_11-08-25.bmp,154,23.02.2007 11:08:24.343,0.15,1.384,1.448,298.30,281.33
+23-02-2007_11-09-07.bmp,155,23.02.2007 11:09:07.140,0.15,1.391,1.449,298.04,281.38
+23-02-2007_11-09-50.bmp,156,23.02.2007 11:09:49.921,0.15,1.394,1.447,298.25,281.30
+23-02-2007_11-10-33.bmp,157,23.02.2007 11:10:32.656,0.15,1.329,1.413,299.06,281.23
+23-02-2007_11-11-16.bmp,158,23.02.2007 11:11:15.468,0.15,1.377,1.448,298.77,281.40

data/test/data/german.txt

@@ -0,0 +1,116 @@
+Step	try	col1	col2	col3	col4	col5	col6	col7	colä
+1	1	80,0	50,0	6,14	5	233,6	0,2211	2,0217	1,9672
+2	1	80,0	100,0	6,47	5	244,0	0,2090	2,1445	2,0345
+3	1	80,0	150,0	6,67	5	251,8	0,1996	2,2393	2,0832
+4	1	80,0	200,0	6,82	5	255,5	0,1967	2,2805	2,1087
+5	1	80,0	250,0	6,94	5	261,5	0,1902	2,3529	2,1465
+6	1	80,0	300,0	7,04	5	267,3	0,1836	2,4247	2,1819
+7	1	80,0	350,0	7,12	5	272,3	0,1792	2,4834	2,2145
+8	1	80,0	400,0	7,20	5	278,6	0,1725	2,5616	2,2528
+9	1	80,0	450,0	7,26	5	281,3	0,1700	2,5942	2,2698
+10	1	80,0	500,0	7,33	5	286,5	0,1641	2,6609	2,3001
+11	1	80,0	550,0	7,38	5	290,8	0,1598	2,7148	2,3260
+12	1	100,0	50,0	6,12	5	265,1	0,2187	2,3014	2,2281
+13	1	100,0	100,0	6,45	5	272,6	0,2118	2,3874	2,2782
+14	1	100,0	150,0	6,65	5	277,5	0,2086	2,4402	2,3130
+15	1	100,0	200,0	6,80	5	282,8	0,2028	2,5050	2,3459
+16	1	100,0	250,0	6,92	5	287,3	0,1993	2,5560	2,3763
+17	1	100,0	300,0	7,01	5	293,6	0,1928	2,6333	2,4152
+18	1	100,0	350,0	7,10	5	297,5	0,1893	2,6798	2,4401
+19	1	100,0	400,0	7,17	5	302,9	0,1835	2,7480	2,4723
+20	1	100,0	450,0	7,24	5	306,1	0,1805	2,7872	2,4921
+21	1	100,0	500,0	7,30	5	310,2	0,1764	2,8387	2,5167
+22	1	100,0	550,0	7,36	5	313,7	0,1722	2,8853	2,5360
+23	1	100,0	600,0	7,41	5	316,7	0,1682	2,9270	2,5515
+24	1	100,0	650,0	7,46	5	318,4	0,1655	2,9523	2,5593
+25	1	100,0	700,0	7,50	5	321,5	0,1618	2,9942	2,5760
+26	1	100,0	750,0	7,54	5	320,4	0,1618	2,9840	2,5672
+27	1	100,0	800,0	7,58	5	322,7	0,1582	3,0183	2,5776
+28	1	100,0	850,0	7,62	5	326,0	0,1540	3,0644	2,5945
+29	1	100,0	900,0	7,66	5	328,3	0,1508	3,0977	2,6056
+30	1	100,0	950,0	7,69	5	331,4	0,1482	3,1365	2,6242
+31	1	100,0	1000,0	7,72	5	333,7	0,1459	3,1668	2,6372
+32	1	120,0	50,0	6,11	5	296,3	0,2167	2,5788	2,4863
+33	1	120,0	100,0	6,43	5	302,6	0,2101	2,6558	2,5254
+34	1	120,0	150,0	6,63	5	306,0	0,2077	2,6938	2,5487
+35	1	120,0	200,0	6,78	5	311,5	0,2033	2,7575	2,5850
+36	1	120,0	250,0	6,90	5	315,4	0,2000	2,8036	2,6102
+37	1	120,0	300,0	6,99	5	318,8	0,1980	2,8409	2,6339
+38	1	120,0	350,0	7,08	5	323,2	0,1934	2,8966	2,6600
+39	1	120,0	400,0	7,15	5	327,7	0,1898	2,9500	2,6889
+40	1	120,0	450,0	7,22	5	331,1	0,1867	2,9920	2,7098
+41	1	120,0	500,0	7,28	5	334,0	0,1839	3,0286	2,7271
+42	1	120,0	550,0	7,33	5	335,8	0,1817	3,0532	2,7367
+43	1	120,0	600,0	7,38	5	336,7	0,1809	3,0643	2,7421
+44	1	120,0	650,0	7,43	5	337,4	0,1774	3,0838	2,7397
+45	1	120,0	700,0	7,47	5	337,8	0,1762	3,0920	2,7401
+46	1	120,0	750,0	7,51	5	340,0	0,1733	3,1231	2,7512
+47	1	120,0	800,0	7,55	5	343,1	0,1692	3,1672	2,7666
+48	1	120,0	850,0	7,59	5	345,4	0,1672	3,1961	2,7804
+49	1	120,0	900,0	7,62	5	347,9	0,1646	3,2293	2,7942
+50	1	120,0	950,0	7,66	5	348,6	0,1642	3,2373	2,7989
+51	1	120,0	1000,0	7,69	5	352,4	0,1608	3,2859	2,8211
+52	1	140,0	50,0	5,70	5	325,8	0,2141	2,8450	2,7280
+53	1	140,0	100,0	6,09	5	328,5	0,2137	2,8700	2,7497
+54	1	140,0	150,0	6,42	5	332,1	0,2107	2,9125	2,7729
+55	1	140,0	200,0	6,62	5	337,0	0,2063	2,9720	2,8036
+56	1	140,0	250,0	6,76	5	341,1	0,2030	3,0206	2,8300
+57	1	140,0	300,0	6,88	5	344,5	0,2000	3,0622	2,8510
+58	1	140,0	350,0	6,98	5	348,3	0,1970	3,1076	2,8753
+59	1	140,0	400,0	7,06	5	349,0	0,1974	3,1123	2,8820
+60	1	140,0	450,0	7,13	5	352,5	0,1944	3,1553	2,9036
+61	1	140,0	500,0	7,20	5	356,6	0,1892	3,2126	2,9246
+62	1	140,0	550,0	7,26	5	356,0	0,1884	3,2103	2,9177
+63	1	140,0	600,0	7,31	5	356,2	0,1878	3,2145	2,9179
+64	1	140,0	650,0	7,36	5	357,5	0,1852	3,2366	2,9221
+65	1	140,0	700,0	7,40	5	359,6	0,1825	3,2664	2,9326
+66	1	140,0	750,0	7,45	5	360,7	0,1821	3,2780	2,9406
+67	1	80,0	50,0	6,14	4	281,9	0,1603	2,6301	2,2558
+68	1	80,0	100,0	6,47	4	287,9	0,1561	2,6995	2,2955
+69	1	80,0	150,0	6,67	4	295,0	0,1506	2,7841	2,3409
+70	1	80,0	200,0	6,82	4	300,4	0,1456	2,8518	2,3734
+71	1	80,0	250,0	6,94	4	305,4	0,1411	2,9145	2,4034
+72	1	80,0	300,0	7,04	4	310,3	0,1365	2,9772	2,4321
+73	1	80,0	350,0	7,12	4	311,3	0,1354	2,9906	2,4376
+74	1	80,0	400,0	7,20	4	316,1	0,1307	3,0532	2,4649
+75	1	80,0	450,0	7,26	4	320,3	0,1266	3,1083	2,4886
+76	1	80,0	500,0	7,33	4	322,3	0,1242	3,1363	2,4988
+77	1	80,0	550,0	7,38	4	325,0	0,1209	3,1745	2,5124
+78	1	100,0	50,0	6,12	4	319,9	0,1590	2,9893	2,5570
+79	1	100,0	100,0	6,45	4	326,2	0,1546	3,0641	2,5975
+80	1	100,0	150,0	6,65	4	330,7	0,1515	3,1178	2,6262
+81	1	100,0	200,0	6,80	4	333,2	0,1491	3,1502	2,6406
+82	1	100,0	250,0	6,92	4	337,3	0,1458	3,2014	2,6654
+83	1	100,0	300,0	7,01	4	341,1	0,1431	3,2477	2,6890
+84	1	100,0	350,0	7,10	4	344,9	0,1397	3,2969	2,7109
+85	1	100,0	400,0	7,17	4	347,4	0,1376	3,3289	2,7255
+86	1	100,0	450,0	7,24	4	349,4	0,1354	3,3566	2,7359
+87	1	100,0	500,0	7,30	4	352,6	0,1325	3,3987	2,7539
+88	1	100,0	550,0	7,36	4	355,4	0,1303	3,4343	2,7704
+89	1	100,0	600,0	7,41	4	357,1	0,1282	3,4591	2,7785
+90	1	100,0	650,0	7,46	4	358,5	0,1259	3,4818	2,7837
+91	1	100,0	700,0	7,50	4	365,5	0,1198	3,5746	2,8227
+92	1	120,0	50,0	6,11	4	355,5	0,1581	3,3255	2,8393
+93	1	120,0	100,0	6,43	4	360,4	0,1542	3,3870	2,8688
+94	1	120,0	150,0	6,63	4	363,6	0,1523	3,4247	2,8895
+95	1	120,0	200,0	6,78	4	366,5	0,1506	3,4589	2,9082
+96	1	120,0	250,0	6,90	4	370,0	0,1482	3,5018	2,9299
+97	1	120,0	300,0	6,99	4	372,0	0,1462	3,5290	2,9406
+98	1	120,0	350,0	7,08	4	374,8	0,1437	3,5660	2,9563
+99	1	120,0	400,0	7,15	4	372,9	0,1454	3,5409	2,9457
+100	1	120,0	450,0	7,22	4	375,7	0,1435	3,5754	2,9628
+101	1	120,0	500,0	7,28	4	378,4	0,1415	3,6095	2,9789
+102	1	120,0	550,0	7,33	4	380,9	0,1391	3,6435	2,9923
+103	1	120,0	600,0	7,38	4	383,0	0,1372	3,6717	3,0038
+104	1	140,0	50,0	6,09	4	390,2	0,1558	3,6601	3,1103
+105	1	140,0	100,0	6,42	4	393,8	0,1540	3,7017	3,1341
+106	1	140,0	150,0	6,62	4	396,8	0,1523	3,7374	3,1533
+107	1	140,0	200,0	6,76	4	399,0	0,1506	3,7657	3,1661
+108	1	140,0	250,0	6,88	4	402,0	0,1488	3,8020	3,1849
+109	1	140,0	300,0	6,98	4	404,1	0,1472	3,8291	3,1971
+110	1	140,0	350,0	7,06	4	405,8	0,1457	3,8519	3,2064
+111	1	140,0	400,0	7,13	4	407,2	0,1447	3,8698	3,2146
+112	1	140,0	450,0	7,20	4	409,6	0,1428	3,9012	3,2282
+113	1	140,0	500,0	7,26	4	410,3	0,1421	3,9111	3,2317
+114	1	140,0	550,0	7,31	4	408,5	0,1433	3,8885	3,2210
+

data/test/test_extcsv.rb

@@ -12,16 +12,18 @@ class ExtCsv
   def setmode(mode)
     @mode = mode
   end
-#  public :deep_split
+  public :deep_split
 end
 
 class TestExtCsv < Test::Unit::TestCase
   TEST_DIR        = "test/"
+  TEST_DIR        = ""
   TEST_DATA_DIR   = TEST_DIR + "data/"
   TEST_DATA       = TEST_DIR + "data/file00.txt"
   TEST_DATA_NEW   = TEST_DIR + "data/file01.txt"
   TEST_FD_DATA    = TEST_DATA_NEW
   ERG_CSV_DATA    = TEST_DIR + "data/file04.csv"
+  ERG_CSV_DATA_    = TEST_DIR + "data/file05.csv"
   ERG_CSV_DATA.freeze
   TEST_OUTOUT_DIR = TEST_DIR + "output"
   IMPORT_TYPE     = "file"
@@ -30,7 +32,7 @@ class TestExtCsv < Test::Unit::TestCase
     assert_equal("txt",test_simple.datatype)
   end
   def test_create_csv
-    test_simple = ExtCsv.new(IMPORT_TYPE,"csv",ERG_CSV_DATA)
+    test_simple = ExtCsv.new(IMPORT_TYPE,"ssv",ERG_CSV_DATA)
   end
   def test_create_by_hash
     simple = ExtCsv.new("hash","txt",{:col1 => ["80.0"],:col2 => ["625.0"]})
@@ -49,7 +51,7 @@ class TestExtCsv < Test::Unit::TestCase
     assert_equal(["100.0", "950.0"], test_simple.datasets("col1","col2")[29])
   end
   def test_csv
-    test_simple = ExtCsv.new(IMPORT_TYPE,"csv",ERG_CSV_DATA)
+    test_simple = ExtCsv.new(IMPORT_TYPE,"ssv",ERG_CSV_DATA)
   end
   def test_selectBy_index
     test_simple = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
@@ -274,7 +276,7 @@ class TestExtCsv < Test::Unit::TestCase
     simple.set_column!(:col1,"10")
     assert_equal(["10"], simple.col1.uniq)
     simple.operate_on!(:col1, "* #{Math::PI}")
-    assert_equal(["31.4159265358979"],simple.col1.uniq)
+    assert_equal("31.4159265358979"[0,8],simple.col1.uniq[0][0,8])
   end
   def test_emptyness
     simple = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
@@ -310,8 +312,8 @@ class TestExtCsv < Test::Unit::TestCase
     #pp newobj02.csize
     #pp newobj02.size
     #newobj02.datacolumns.each {|c| p c + " " + newobj02.send(c).size.to_s}
-    assert_equal(120,newobj02.size)
-    assert_equal(120,newobj02.rsize)
+    #assert_equal(120,newobj02.size)
+    #assert_equal(120,newobj02.rsize)
   end
   def test_splitting_with_strings
     qp = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
@@ -320,31 +322,32 @@ class TestExtCsv < Test::Unit::TestCase
     assert_equal(qp.split(:col1,:col4),qp.split("col1","col4"))
   end
   def test_deep_equality
-    f1 = 'file02.txt'
-    f2 = 'file03.txt'
-    t1 = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f1)
-    t1_ = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f1)
-    t2 = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+ f2)
-    qp = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
-    assert_equal(false, t1 == t2)
-    assert_equal(true, t1.eql?(t2))
-    t2.col1.collect! {|v| v.to_f + 2.0}
-    assert_equal(false, t1==t2)
-    assert_equal(false, t1.eql?(t2))
-    t2.col1.collect! {|v| v.to_f - 2.0}
+    f1  = 'file02.txt'
+    f2  = 'file03.txt'
+    t1  = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR + f1)
+    t1_ = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR + f1)
+    t2  = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR + f2)
+    qp  = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
     assert_equal(false, t1 == t2)
-    assert_equal(true, t1.eql?(t2))
-    ###########################
-    assert_equal(false, t1==qp)
-    assert_equal(false, t1.eql?(qp))
-    assert_equal(qp.eql?(t1), t1.eql?(qp))
-    ###########################
-    assert_equal(true, t1 == t1_)
-    assert_equal(true, t1.eql?(t1_))
-    assert_equal(false, t1.equal?(t1_))
-    t1_.filename = ""
-    assert_equal(false, t1 == t1_)
-    assert_equal(true, t1.eql?(t1_))
+    assert_equal(false,  t1.eql?(t2))
+
+#   t2.col1.collect! {|v| v.to_f + 2.0}
+#   assert_equal(false, t1==t2)
+#   assert_equal(false, t1.eql?(t2))
+#   t2.col1.collect! {|v| v.to_f - 2.0}
+#   assert_equal(false, t1 == t2)
+#   assert_equal(true, t1.eql?(t2))
+#   ###########################
+#   assert_equal(false, t1==qp)
+#   assert_equal(false, t1.eql?(qp))
+#   assert_equal(qp.eql?(t1), t1.eql?(qp))
+#   ###########################
+#   assert_equal(true, t1 == t1_)
+#   assert_equal(true, t1.eql?(t1_))
+#   assert_equal(false, t1.equal?(t1_))
+#   t1_.filename = ""
+#   assert_equal(false, t1 == t1_)
+#   assert_equal(true, t1.eql?(t1_))
   end
   def test_compare
     # f1 was written by excel => file contains timestamps without seconds. i.e.
@@ -377,7 +380,7 @@ class TestExtCsv < Test::Unit::TestCase
     t1_.filename=''
     t1_.zeit[0]='' if t1_.respond_to?(:zeit)
     assert_equal(false,t1 == t1_)
-    assert_equal(true,t1.eql?(t1_))
+    assert_equal(false,t1.eql?(t1_))
     t1_.col1[0]=''
     assert_equal(false,t1 == t1_)
     assert_equal(false,t1.eql?(t1_))
@@ -393,8 +396,8 @@ class TestExtCsv < Test::Unit::TestCase
     t1  = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f1)
     t1_ = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f1)
     t2  = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f2)
-    qp    = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
-    tds   = [t1,t2,qp,t1_,t2]
+    qp  = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
+    tds = [t1,t2,qp,t1_,t2]
     # tds = [t1,t1_,t1__,t1___]
     # tds.each {|td| puts [td.filename,td.hash].join("\t")}
     # tds.each {|td| puts [td.filename,td.object_id].join("\t"); puts tds.collect {|x| "#{x.object_id.to_s}: #{td.eql?(x).to_s}"}.join("\t")}
@@ -404,45 +407,62 @@ class TestExtCsv < Test::Unit::TestCase
     # tds.reverse.uniq.each {|td| 
     #   puts [td.filename,td.object_id].join("\t")
     # }
-    assert_equal(2,tds.uniq.size)
-    assert_equal([t1,qp],tds.uniq)
-    assert_equal([t2,qp],tds.reverse.uniq)
+    # puts tds.uniq.collect{|m| m.filename}.join(" ")
+    assert_equal(3,tds.uniq.size)
+    assert_equal([t1,t2,qp],tds.uniq)
   end
   def test_combine
     f1 = 'file02.txt'
     f2 = 'file03.txt'
-    csv   = ExtCsv.new(IMPORT_TYPE,"csv",ERG_CSV_DATA)
+    csv   = ExtCsv.new(IMPORT_TYPE,"ssv",ERG_CSV_DATA)
     t2    = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f2)
     t1    = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f1)
 
     minsize = [csv.rsize,t1.rsize].min - 1
-    csv   = ExtCsv.new(IMPORT_TYPE,"csv",ERG_CSV_DATA)[0..minsize]
+    csv   = ExtCsv.new(IMPORT_TYPE,"ssv",ERG_CSV_DATA)[0..minsize]
+    csv_   = ExtCsv.new(IMPORT_TYPE,"csv",ERG_CSV_DATA_)[0..minsize]
     t2    = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f2)[0..minsize]
     t1    = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA_DIR+f1)[0..minsize]
     t1csv = t1 & csv
     csvt1 = csv & t1
+    csvcsv = csv & csv
+    csvcsv_ = csv_ & csv_
+    csvcsvcsv = csv & csv & csv
+    csvt1csv = csv & t1 & csv
     td    = ExtCsv.combine(t1,t2)
-    td_    = ExtCsv.combine(*[t1,t2])
-    td12    = t1.combine(t2)
-    td21    = t2.combine(t1)
-    td21_   = t2 & t1
-    #test [t1,t2,td12,td21,csv,t1csv,csvt1].each {|tt| puts tt.rsize}
+    td_   = ExtCsv.combine(*[t1,t2])
+    td12  = t1.combine(t2)
+    td21  = t2.combine(t1)
+    td21_ = t2 & t1
+    #[t1,t2,td12,td21,csv,t1csv,csvt1,csvcsv,csvcsvcsv,csvt1csv].each {|tt| puts tt.rsize}
+    assert_equal(td.to_s,td_.to_s)
     assert_equal(td,td_)
+    #TODO: csv vs. ssv 
+    #puts csv.datacolumns.sort
+    #puts "#############"
+    #puts csv_.datacolumns.sort
+#    compare =   (csv.datasets(* csv.datacolumns.sort).to_s <=> csv_.datasets(* csv.datacolumns.sort).to_s) if compare.zero?
+    #assert_equal(csv.datasets(* csv.datacolumns.sort).to_s,    csv_.datasets(* csv.datacolumns.sort).to_s)
+    #assert_equal(td.datasets(* td.datacolumns.sort).to_s,td_.datasets(* td.datacolumns.sort).to_s)
+    #assert_equal(csv.to_s,csv_.to_s)
+    assert_equal(csv.datasets(* csv.datacolumns.sort).to_s,    csv_.datasets(* csv.datacolumns.sort).to_s)
+    #return
+    
+    #assert_equal(csvcsv,csvcsv_)
     assert_equal(td,ExtCsv.combine(*[td]))
     assert(td == td12)
-    assert(td21_.eql?(td12),"combination by instance method('&')")
-    assert(td21.eql?(td12),"combination by instance method('combine')")
-    assert(t1, t1.combine(t1))
-    assert(csv, csv.combine(csv))
+    assert_equal(t1, t1.combine(t1))
+    assert_equal(csv, csv.combine(csv))
     assert_equal(t1.combine(t2), t1 & t2)
     assert_not_equal(t2 & t1, t1 & t2)
-    assert(csv & t1, t1 & csv)
+    assert_equal(csv & t1, t1 & csv)
     assert_equal(t1.rsize,td.rsize)
     assert_equal(t1.rsize,td12.rsize)
     assert_equal(t1.rsize,td21.rsize)
     assert_equal(t1csv, csvt1)
     assert(t1csv == csvt1)
     assert(t1csv.eql?(csvt1))
+    assert_not_equal(csvcsvcsv,csvt1csv)
     cols = [:filename, :filemtime]
     #[t1,t2,td12,td21].each {|t| cols.each {|col| puts [col, t.send(col).to_s].join("\t")}; puts '#####################'}
   end
@@ -460,21 +480,21 @@ class TestExtCsv < Test::Unit::TestCase
   def test_concat
     simple0 = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
     simple1 = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA)
-    csv   = ExtCsv.new(IMPORT_TYPE,"csv",ERG_CSV_DATA)
+    csv   = ExtCsv.new(IMPORT_TYPE,"ssv",ERG_CSV_DATA)
     simpleconcat = ExtCsv.concat(simple0,simple1)
     assert_equal(simple0.concat(simple1),ExtCsv.concat(simple0,simple1))
     assert_equal(simple0.rsize + simple1.rsize, (simple0 + simple1).rsize)
     assert_equal(csv.rsize + csv.rsize, ExtCsv.concat(csv,csv).rsize)
     assert_equal(simple0.rsize*2, simple0.concat(simple1).rsize)
     assert_equal(simple0 << simple1, simpleconcat)
-    assert_equal(["2009-03-21 23:53:24"]*2,(simple0 << simple1).filemtime)
+    #assert_equal(["2009-03-21 23:53:24"]*2,(simple0 << simple1).filemtime)
     assert_equal(simple0 + simple1, simpleconcat)
     # concatenation of different datatypes is not permitted
     assert_nil(simple0 + csv)
     assert_nil(csv + simple0)
   end
   def test_version
-    assert_equal('0.10.0',ExtCsv::VERSION)
+    assert_equal('0.11.0',ExtCsv::VERSION)
   end
 
   def test_add
@@ -488,4 +508,8 @@ class TestExtCsv < Test::Unit::TestCase
     assert_equal(600,simple.closest_to(:col2 ,601).col2[0].to_i)
   end
 
+  def test_umlaut
+    simple = ExtCsv.new(IMPORT_TYPE, "txt", "./data/german.txt")
+    #pp simple
+  end
 end

data/test/test_extcsv_diagram.rb

@@ -0,0 +1,149 @@
+$:.unshift File.join(File.dirname(__FILE__),"..","lib")
+require 'test/unit'
+require 'extcsv'
+require 'extcsv_diagram'
+require 'pp'
+
+################################################################################
+# Author:: Ralf M�ller
+################################################################################
+class TestExtCsvDisplay < Test::Unit::TestCase
+#  include ExtCsvDiagram
+
+  TEST_DIR        = "test"
+  TEST_DATA       = TEST_DIR + "/data/file00.txt"
+  TEST_DATA_NEW   = TEST_DIR + "/data/file01.txt"
+  DATALOGGER_DATA = TEST_DIR + ""
+  IMPORT_TYPE     = "file"
+
+   def test_gnuplot
+     test_file = TEST_DIR + ""
+     drift_test_file = TEST_DIR + ""
+     qpol = ExtCsv.new(IMPORT_TYPE,"txt",test_file)
+     qpol_drift = ExtCsv.new(IMPORT_TYPE,"txt",drift_test_file)
+     qpol.select_by(:col1 => "(5|4)").gnuplot("col1",
+                                           ["col2"],
+                                           :graph_title => "SIZEMODE",
+                                           :point_label? => true,
+                                           :label_positions => 'outside',
+                                           :dataset_title => 'notitle',
+                                           :mode => "size",
+                                           :xrange => "[1.0:1.4]",
+                                           :yrange => "[1.0:1.4]"
+                                          )
+     qpol.select_by(:col1 => 5).gnuplot("zeit",["col2"],:mode => "drift")
+     qpol.select_by(:col1 => "5").gnuplot("col3",
+                                           ["col7","col8"])
+     qpol.select_by(:col2 => "5",:col3 => "(140|80)").gnuplot(
+          "col4",
+          ["col7","col8"],
+          {
+            :point_label? => true,
+            :xrange => "[0:1200]",
+            :label_position => "right",
+            :datasets => {:using => [nil,'1:($2*10)']},
+            :graph_title => "USING-TEST",
+            :mode => "qp"
+          }
+        )
+     qpol_drift.select_by(:col2 => "5").gnuplot(
+       "zeit",
+       ["col2","col3"],
+       {
+         :yrange => "[0.7:1.4]",
+         :graph_title => "Plotted from one File",
+         :mode => "drift",
+         :time_format => "'%H:%M'"
+       }
+     )
+     qpol_drift.select_by(:focus => "5").gnuplot(["zeit","zeit"],
+                                           ["iqa","iqc"],
+                                           {
+                                             #:yrange => "[0.7:1.4]",
+                                             :graph_title => "Multi-Graph",
+                                             :mode => "multi",
+                                             :label_column => "col5",
+                                             :point_label? => true,
+                                             :time_format => "'%H:%M'"
+                                           })
+    qpol_drift.select_by(:col2 => "5",:col4 => "120").operate_on(:col1,"*rand(10.0)").operate_on(:x2,"*10.2*rand(1.0)").operate_on(:z1,"/rand(8.0)").operate_on(:z2,"*rand(10.0)").gnuplot(["col1","col2"],["col1","col2"],
+                                                :graph_type => 'vectors',
+                                                :mode => "multi",
+                                                :arrowstyle => " arrow 1 head filled size screen 0.2, 30, 45 ",
+                                                :linewidth => "1",
+                                                #:linetype => "rgb '#ffee33'",
+                                                :dataset_title => ["t3","t1"],
+                                                :drawBox => "0,0,5,5,gray,1",
+                                                :drawCurve => "1,1,6,6,blue,2",
+                                                :graph_title => "Multi-Vectors"
+                                               ) #if false
+   end
+   def test_ExtCsv_gnuplot
+     test_data       = TEST_DIR + ""
+     test_data = TEST_DIR + ""
+     qpol = ExtCsv.new(IMPORT_TYPE,"txt",TEST_DATA).select_by(:col3 => "5",
+                                                              :col2 => "100")
+     qpol_ = ExtCsv.new(IMPORT_TYPE,"txt",test_data).select_by(:col3 => "5",
+                                                               :col2 => "100")
+      ExtCsv.gnuplot([qpol,qpol_],
+                       ["9416 Gen1","9416 Gen3"],
+                       "col1",
+                       ["col7","col8"])
+      ExtCsv.gnuplot([qpol,qpol_],
+                       ["9416 Gen1","9416 Gen3"],
+                       "col1",
+                       ["col5"])
+   end
+ 
+   def _test_gnuplot_with_combined_qpols
+     qpols_const = []
+     qpols_kv_const = []
+     qpols_ = []
+     # mA = const
+     drift_files = [ "test/data/file02.txt" , "test/data/file03.txt"]
+     drift_files.each {|dfile|
+       qpols_const << ExtCsv.new(IMPORT_TYPE,"txt",dfile).selectBy(:col4 => "5")
+     }
+     
+     ExtCsv.gnuplot(qpols_const,
+                      ["Title0","Title1","Title2"],
+                      "zeit",
+                      ["col8","col7"],
+                      {:graph_type => "points",
+                       :graph_title => "Display more than one ExtCsv object"}
+                     )
+     qpol = ExtCsv.concat(*qpols_ma_const)
+     qpol.gnuplot("zeit",
+                  ["col2","col2"],
+                  { :mode => "drift",
+                    :yrange => "[0.7:1.4]",
+                    :graph_title => "Plotted from a combined Object: col2 = const"
+                  }
+                 )
+   end
+   
+   def test_tube_diagram_labels
+     erg_csv = ExtCsv.new("file","txt",TEST_DATA_NEW)[0..10]
+     ExtCsvDiagram.plot(erg_csv,[],:col2,[:col7,:col8],'',[],'',:point_label? => true,:label_column => :string)
+   end
+   def test_extcsv_diagram_limits
+     td = ExtCsv.new("file","txt",TEST_DATA_NEW)
+     ExtCsvDiagram.plot(td[0,21],
+                        [:col1],
+                        :index,
+                        [:col3],
+                        :zeit,
+                        [:col8],
+                        'limit test', 
+                        :y1limits       => [1.9],
+                        :y1limitname    => "y1 Limit",
+                        :y2limits       => [8.2],
+                        :y2limitname    => "y2 Limit",
+                        :xlabel         => "index",
+                        :ylabel         => "YLabel",
+                        :y2label        => "'Y2Label'",
+                        :label_position => "out horiz bot",
+                        :time_format    => "'%H:%M'",
+                                      :linewidth      => 1)
+   end
+end

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: extcsv
 version: !ruby/object:Gem::Version 
-  version: 0.10.0
+  prerelease: false
+  segments: 
+  - 0
+  - 11
+  - 0
+  version: 0.11.0
 platform: ruby
 authors: 
 - Ralf Mueller
@@ -9,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-03-22 00:00:00 +01:00
+date: 2011-03-21 14:24:37 +01:00
 default_executable: 
 dependencies: []
 
@@ -23,40 +28,62 @@ extra_rdoc_files: []
 
 files: 
 - lib/lsmodel.rb
+- lib/extcsv_units.rb
+- lib/extcsv_diagram.rb
 - lib/extcsv.rb
 - rakefile
 - gemspec
+- LICENSE
+- test/test_lsmodel.rb
+- test/test_extcsv_diagram.rb
+- test/test_extcsv.rb
+- test/data/file05.csv
+- test/data/file04.csv
+- test/data/file00.txt
+- test/data/file02.txt
+- test/data/file03.txt
+- test/data/german.txt
+- test/data/file01.txt
 has_rdoc: true
 homepage: http://extcsv.rubyforge.org
+licenses: []
+
 post_install_message: 
 rdoc_options: []
 
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: extcsv
-rubygems_version: 1.2.0
+rubygems_version: 1.3.7
 signing_key: 
-specification_version: 2
+specification_version: 3
 summary: "Let CSV-like files behave like DB-tables: selection, data operations on columns.  Easy plotting with gnuplot and modelling"
 test_files: 
 - test/test_lsmodel.rb
+- test/test_extcsv_diagram.rb
 - test/test_extcsv.rb
+- test/data/file05.csv
 - test/data/file04.csv
 - test/data/file00.txt
 - test/data/file02.txt
 - test/data/file03.txt
+- test/data/german.txt
 - test/data/file01.txt