sycsvpro 0.2.1 → 0.2.2

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    sycsvpro (0.2.1)
+    sycsvpro (0.2.2)
       gli (= 2.9.0)
       timeleap (~> 0.0.1)
 

data/README.md

@@ -731,6 +731,15 @@ Version 0.2.1
 * Dsl module has got 3 new methods #is\_integer?, #is\_float? and #str2num to
   convert strings that represent numbers to numericals
 
+Version 0.2.2
+-------------
+* Add the equalize switch to the spread sheet command line
+* Optimize performance of SpreadSheet#write
+* Introduce _r_ and _c_ arguments to SpreadSheet#write to indicate whether the
+  row and column labels should be written to the file. Row and column labels are
+  written per default for compatibility reasons
+* Catch encoding errors when creating spread sheet from file
+
 Documentation
 =============
 The class documentation can be found at 

data/bin/sycsvpro

@@ -430,6 +430,10 @@ command :spreadsheet do |c|
   c.arg_name '.|,'
   c.flag [:ds], default: '.'
 
+  c.desc 'In order to build spread sheets rows have to be of equal size. The '+
+         'e switch equalizes row sizes over all rows'
+  c.switch [:e, :equalize], :default_value => false
+
   c.desc 'The arithmetic operation with the table data'
   c.arg_name 'ARITHMETIC_OPERATION'
   c.flag [:o, :operation]
@@ -446,6 +450,7 @@ command :spreadsheet do |c|
                                      aliases:   options[:a],
                                      operation: options[:o],
                                      ds:        options[:ds],
+                                     equalize:  options[:e],
                                      print:     options[:p]).execute
     print 'done'
   end

data/lib/sycsvpro/dsl.rb

@@ -108,7 +108,7 @@ module Dsl
 
   # Remove non-UTF chars from string
   def str2utf8(str)
-    str.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '')
+    str.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: EMPTY)
   end
 
   # Retrieves the values scanned by a COMMA_SPLITTER_REGEX

data/lib/sycsvpro/not_available.rb

@@ -10,12 +10,13 @@ module Sycsvpro
   #    1 + na -> na
   class NotAvailable
 
+    # The string representation of NotAvailable
+    NA = "NA"
+
     class << self
 
       # Catches all expressions where na is the first argument
       def method_missing(name, *args, &block)
-        super if name == :to_ary
-        super if name == :to_str
         self
       end
 
@@ -25,9 +26,17 @@ module Sycsvpro
         [self,value]
       end
 
+      # Checks whether SpreadSheet responds to 'name'. The methods :to_ary and
+      # :to_str are excluded
+      def respond_to?(name)
+        return false if name == :to_ary
+        return false if name == :to_str
+        super
+      end
+
       # Returns NA as the string representation
       def to_s
-        "NA"
+        NA
       end
       
     end

data/lib/sycsvpro/spread_sheet.rb

@@ -82,6 +82,7 @@ module Sycsvpro
     # values::     flat array with values
     # rows::       indicates the row count in combination with values param
     # cols::       indicates the col count in combination with values param
+    # equalize::   If columns are of different size equalizes the column size
     # file::       file that contains values to create spread sheet with
     # ds::         decimal spearator '.' or ',' where '.' is default. The
     #              decimal separator is used when spread sheet is created from
@@ -325,12 +326,31 @@ module Sycsvpro
       @col_labels = opts[:cols] if opts[:cols]
     end
 
-    # Writes spread sheet to a file separated with ';'
-    def write(file)
+    # Writes spread sheet to a file separated with ';'. Accepts two boolean
+    # arguments to indicate whether the row and column labels should be saved
+    # along with the spread sheet's labels
+    # r:: when true row labels will be saved, default is true
+    # c:: when true column labels will be saved, default is true
+    def write(file, opts = {})
+      opts = {r: true, c: true}.merge(opts)
+
+      if opts[:r]
+        construct_row = -> row,i { row.insert(0,row_labels[i]).join(SEMICOLON) }
+      else
+        construct_row = -> row,i { row.join(SEMICOLON) }
+      end
+      
       File.open(file, 'w') do |out|
-        out.puts ";#{col_labels.join(';')}"
+        if opts[:c]
+          if opts[:r]
+            out.puts "#{SEMICOLON}#{col_labels.join(SEMICOLON)}"
+          else
+            out.puts col_labels.join(SEMICOLON) 
+          end
+        end
+
         rows.each_with_index do |row, i| 
-          out.puts "#{row_labels[i]};#{row.join(';')}"
+          out.puts construct_row.call row, i
         end
       end 
     end
@@ -399,14 +419,13 @@ module Sycsvpro
           end
           values.each_slice(col_count) { |row| rows << row }
         elsif opts[:file]
-          start_read = Time.now
-          File.readlines(opts[:file]).each do |line| 
+          File.foreach(opts[:file]) do |line| 
             next if line.chomp.empty?
-            rows << line.split(SEMICOLON).collect { |v| 
+            values = line.split(SEMICOLON) rescue str2utf8(line).split(SEMICOLON)
+            rows << values.collect { |v| 
               v.strip.empty? ? NotAvailable : str2num(v.chomp, opts[:ds])
             }
           end
-          STDERR.puts "Reading file in #{Time.now - start_read} seconds"
         end
 
         rows
@@ -435,10 +454,10 @@ module Sycsvpro
       #   * not nil
       #   * at least one row
       def check_validity_of(rows)
-        raise "rows need to be arrays"              if !rows_are_arrays?(rows)
-        raise "needs at least one row"              if rows.empty?
-        raise "rows must be of same column size. "+
-              "Use equalize: true flag to fix."     if !same_column_size?(rows)
+        raise "rows need to be arrays"             if !rows_are_arrays?(rows)
+        raise "needs at least one row"             if rows.empty?
+        raise "rows must be of same column size. Use "+
+              "'equalize: true' flag to fix this." if !same_column_size?(rows)
       end
 
       # Checks whether all rows have the same column size. Returns true if
@@ -522,7 +541,8 @@ module Sycsvpro
       # a spread sheet
       def process(operator, s)
         s = coerce(s) || s
-        raise "operand needs to be a SpreadSheet, Numeric or Array" unless s.is_a?(SpreadSheet)
+        raise "operand needs to be a SpreadSheet, "+
+              "Numeric or Array" unless s.is_a?(SpreadSheet)
         result = []
         rlabel = []
         clabel = []

data/lib/sycsvpro/spread_sheet_builder.rb

@@ -25,23 +25,25 @@ module Sycsvpro
     #                            aliases:   "a,b",
     #                            operation: "(a*b).transpose",
     #                            ds:        ",",
+    #                            equalize:  "true",
     #                            print:     "true").execute
     #
-    # outfile:   file where the result of the operation is written to
-    # files:     files that hold the spread sheet data
-    # r:         indication whether the corresponding file has row labels
-    # c:         indication whether the corresponding file has column labels
-    # aliases:   symbols that correspond to the spread sheet created from the
-    #            files. The symbols are used in the operation. The symbols have
-    #            to be choosen carefully not to conflict with existing methods
-    #            and variables
-    # ds:        decimal spearator '.' or ',' where '.' is default
-    # operation: arithmetic operation on spread sheets using the aliases as
-    #            place holders for the spread sheets. The last evaluated
-    #            operation is returned as result and saved to outfile in case
-    #            the result is a spread sheet. In all other cases the result can
-    #            be printed with the print flag.
-    # print:     print the result
+    # outfile::   file where the result of the operation is written to
+    # files::     files that hold the spread sheet data
+    # r::         indication whether the corresponding file has row labels
+    # c::         indication whether the corresponding file has column labels
+    # aliases::   symbols that correspond to the spread sheet created from the
+    #             files. The symbols are used in the operation. The symbols have
+    #             to be choosen carefully not to conflict with existing methods
+    #             and variables
+    # ds::        decimal spearator '.' or ',' where '.' is default
+    # equalize::  indicates whether different column sizes should be equalized
+    # operation:: arithmetic operation on spread sheets using the aliases as
+    #             place holders for the spread sheets. The last evaluated
+    #             operation is returned as result and saved to outfile in case
+    #             the result is a spread sheet. In all other cases the result 
+    #             can be printed with the print flag.
+    # print::     print the result
     def initialize(opts = {})
       @print     = opts[:print]
       @operands  = create_operands(opts)
@@ -96,6 +98,7 @@ module Sycsvpro
         operands = {}
         opts[:aliases].split(',').each_with_index do |a,i|
           operands[a] = SpreadSheet.new(file: files[i], ds: opts[:ds], 
+                                        equalize: opts[:equalize],
                                         r: rlabels[i], c: clabels[i])
         end
 

data/lib/sycsvpro/version.rb

@@ -1,5 +1,5 @@
 # Operating csv files
 module Sycsvpro
   # Version number of sycsvpro
-  VERSION = '0.2.1'
+  VERSION = '0.2.2'
 end

data/spec/sycsvpro/spread_sheet_spec.rb

@@ -7,8 +7,8 @@ module Sycsvpro
     # Creation of spread sheets
     it "should ensure all rows have the same column size" do
       expect { SpreadSheet.new([1,2], [3,4,5]) }.to raise_error(RuntimeError,
-                    "rows must be of same column size. Use equalize: true "+
-                    "flag to fix.")
+                    "rows must be of same column size. Use 'equalize: true' "+
+                    "flag to fix this.")
     end
 
     it "should not accept non arrays as rows" do
@@ -115,6 +115,48 @@ module Sycsvpro
       Dir.glob(file).size.should eq 1
     end
 
+    it "should write to file without row labels" do
+      file = File.join(File.dirname(__FILE__), "files/spread_sheet_out.csv")
+
+      s1 = SpreadSheet.new(['A', 'B', 'C'],['I',1,2,3],['II',4,5,6], 
+                           r: true, c: true)
+      s1.write(file, r: false)
+
+      lines = File.readlines(file)
+
+      content = ["A;B;C\n", "1;2;3\n", "4;5;6\n"]
+
+      lines.should eq content
+    end
+
+    it "should write to file without column labels" do
+      file = File.join(File.dirname(__FILE__), "files/spread_sheet_out.csv")
+
+      s1 = SpreadSheet.new(['A', 'B', 'C'],['I',1,2,3],['II',4,5,6], 
+                           r: true, c: true)
+      s1.write(file, c: false)
+
+      lines = File.readlines(file)
+
+      content = ["I;1;2;3\n", "II;4;5;6\n"]
+
+      lines.should eq content
+    end
+ 
+    it "should only write data to file" do
+      file = File.join(File.dirname(__FILE__), "files/spread_sheet_out.csv")
+
+      s1 = SpreadSheet.new(['A', 'B', 'C'],['I',1,2,3],['II',4,5,6], 
+                           r: true, c: true)
+      s1.write(file, r: false, c: false)
+
+      lines = File.readlines(file)
+
+      content = ["1;2;3\n", "4;5;6\n"]
+
+      lines.should eq content
+    end
+ 
     # Manipulating spread sheets
 
     it "should transpose rows and columns" do

data/sycsvpro.rdoc

@@ -5,7 +5,7 @@ SYNOPSIS
     sycsvpro [global options] command [command options] [arguments...]
 
 VERSION
-    0.2.0
+    0.2.2
 
 GLOBAL OPTIONS
     -f, --file=FILE    - CSV file to operate on (default: none)
@@ -20,22 +20,27 @@ COMMANDS
     analyze     - Analyze the CSV file regarding columns, rows and content
     calc        - Process operations on columns. Optionally add a sum row for columns withnumber values
     collect     - Collect values of specified rows and columns from the file and group them in categories
-    count       - Counts the occurences of column values. Uses column values as headings with count as values. Columns with a condition will be added as new columns
-                  and the condition will be set as column name. Optionally adds a sum row
+    count       - Counts the occurences of column values. Uses column values as headings with count as values.
+                  Columns with a condition will be added as new columns and the condition will be set as
+                  column name. Optionally adds a sum row
     edit        - Creates a script/insert file or opens a script/insert file for editing if it exists
     execute     - Executes the code provided in a file
     extract     - Extract specified rows and columns from the file
     help        - Shows a list of commands or help for one command
-    insert      - Inserts rows from a file to a csv-file. You can for instance add sum operations in Excel or LibreOffice style if you want to process the resulting
-                  file in Excel or LibreOffice
+    insert      - Inserts rows from a file to a csv-file. You can for instance add sum operations in Excel or
+                  LibreOffice style if you want to process the resulting file in Excel or LibreOffice
     join        - Join two files based on a joint column value
-    list        - Lists script or insert files in the scripts directory with optionally listing methods of script files
+    list        - Lists script or insert files in the scripts directory with optionally listing methods of
+                  script files
     map         - Map values in columns to new values
-    merge       - Merge multiple files based on a common column value with a key value at the first column of a row
+    merge       - Merge multiple files based on a common column value with a key value at the first column of
+                  a row
     sort        - Sort rows based on column values. It is possible to sort on multiple columns
-    spreadsheet - Do arithmetic operation with table like data. The table has to have rows with same size. Arithmetic operations are *, /, + and - where the results
-                  can be concatenated. Complete functions can be looked up at https://rubygems.org/gem/sycsvpro
-    table       - Associates columns to a key value. A key value can be a combination of multiple column values. Values associated can be generated from an arithmetic
-                  or string operation. Header columns can be generated dynamically based on column values
+    spreadsheet - Do arithmetic operation with table like data. The table has to have rows with same size.
+                  Arithmetic operations are *, /, + and - where the results can be concatenated. Complete
+                  functions can be looked up at https://rubygems.org/gem/sycsvpro
+    table       - Associates columns to a key value. A key value can be a combination of multiple column
+                  values. Values associated can be generated from an arithmetic or string operation. Header
+                  columns can be generated dynamically based on column values
     transpose   - Transposes rows and columns
     unique      - Remove duplicate rows from a file. Duplicates are identified by key columns

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sycsvpro
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-11 00:00:00.000000000 Z
+date: 2014-10-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake