tabular 0.0.1 → 0.0.2

data/.gitignore

@@ -0,0 +1 @@
+pkg

data/README

@@ -2,12 +2,22 @@ Tabular is a Ruby library for reading, writing, and manipulating CSV, tab-delimi
 
 I extracted it from production code. Still extracting it, actually. I need to read structured data and manipulate it via a common interface before persisting it with ActiveRecord.
 
+Install
+-------
+sudo gem install tabular
+
+(The gem is hosted on Gemcutter, not RubyForge)
+
 
 Dependencies
 ------------
 For tab-delimited data: Ruby standard lib
-For CSV: FasterCSV
-For Excel: Spreadsheet gem
+
+For CSV: FasterCSV (http://fastercsv.rubyforge.org/)
+sudo gem install fastercsv
+
+For Excel: Spreadsheet gem (http://spreadsheet.rubyforge.org/)
+sudo gem install spreadsheet
 
 
 Examples
@@ -30,10 +40,14 @@ Table.read assumes that .txt files are tab-delimited, .csv files are comma-delim
 
 Table.new accepts an Array of Arrays.
 
-Table.new also accepts an options hash. Currently, :columns is the only option. Examples:
+Table.new also accepts an options hash.
+
+:columns option to map columns to a different key or type:
 :city_state => :location -- Maps :city_state column to :location. A column with a "City State" header would be accessed as row[:location]
 :flyer_approved  => { :column_type => :boolean } -- Coerce :flyer_approved column cells to booleans.
 
+:as => [:csv, :xls, :txt] to override file format
+
 
 Tests
 -----
@@ -43,4 +57,4 @@ There's basic test coverage. More comprehensive test coverage needs to be extrac
 Copyright
 ---------
 
-Copyright (c) 2009 Scott Willson. See LICENSE for details.
+Copyright (c) 2010 Scott Willson. See LICENSE for details.

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.0.2

data/lib/tabular/columns.rb

@@ -1,16 +1,19 @@
 module Tabular
   # The Table's header: a list of Columns.
   class Columns
+    include Enumerable
+    
     # +data+ -- array of header names
     # +columns_map+ -- see Table. Maps column names and type conversion.
     def initialize(data, columns_map = {})
-      @columns_map = columns_map
+      columns_map ||= {}
+      @columns_map = normalize_columns_map(columns_map)
       @column_indexes = {}
       @columns_by_key = {}
       index = 0
       @columns = nil
       @columns = data.map do |column|
-        new_column = Tabular::Column.new(column, columns_map)
+        new_column = Tabular::Column.new(column, @columns_map)
         unless new_column.key.blank?
           @column_indexes[new_column.key] = index
           @columns_by_key[new_column.key] = new_column
@@ -51,5 +54,21 @@ module Tabular
       end
       @columns << column
     end
+    
+    
+    private 
+    
+    def normalize_columns_map(columns_map)
+      normalized_columns_map = {}
+      columns_map.each do |key, value|
+        case value
+        when Hash, Symbol
+          normalized_columns_map[key.to_sym] = value
+        else
+          normalized_columns_map[key.to_sym] = value.to_sym
+        end
+      end
+      normalized_columns_map
+    end
   end
 end

data/lib/tabular/row.rb

@@ -3,12 +3,15 @@ module Tabular
   class Row
     include Enumerable
     
-    # +columns+ -- array of string
+    attr_reader :index
+    
+    # +table+ -- Table
     # +cell+ -- array (not neccessarily Strings)
-    def initialize(columns, cells = [])
-      @columns = columns
+    def initialize(table, cells = [])
+      @table = table
       @array = cells
       @hash = nil
+      @index = table.rows.size
     end
     
     # Cell value by symbol. E.g., row[:phone_number]
@@ -16,13 +19,13 @@ module Tabular
       hash[key]
     end
     
-    # Set cell value. Adds cell to end of Row and adds new Column if there is no Column fo +key_
+    # Set cell value. Adds cell to end of Row and adds new Column if there is no Column for +key_
     def []=(key, value)
-      if @columns.has_key?(key)
-        @array[@columns.index(key)] = value
+      if columns.has_key?(key)
+        @array[columns.index(key)] = value
       else
         @array << value
-        @columns << key
+        columns << key
       end
       hash[key] = value
     end
@@ -37,6 +40,16 @@ module Tabular
       @array.join(sep)
     end
     
+    def previous
+      if index > 0
+        @table.rows[index - 1]
+      end
+    end
+    
+    def columns
+      @table.columns
+    end
+    
     def to_hash
       hash.dup
     end
@@ -52,12 +65,11 @@ module Tabular
 
     protected
     
-    
     def hash #:nodoc:
       unless @hash
         @hash = Hash.new
-        @columns.each do |column|
-          index = @columns.index(column.key)
+        columns.each do |column|
+          index = columns.index(column.key)
           if index
             case column.column_type
             when :boolean

data/lib/tabular/table.rb

@@ -1,27 +1,44 @@
 module Tabular
   # Simple Enumerable list of Hashes. Use Table.read(file_path) to read file.
   class Table
-    attr_reader :columns, :rows
+    attr_reader :rows
     
     # Assumes .txt = tab-delimited, .csv = CSV, .xls = Excel. Assumes first row is the header.
     # Normalizes column names to lower-case with underscores.
     def self.read(file_path, *options)
       raise "Could not find '#{file_path}'" unless File.exists?(file_path)
+      options = extract_options(options)
+      as = options.delete(:as)
       
-      case File.extname(file_path)
-      when ".xls", ".xlsx"
+      if as.present?
+        format = as
+      else
+        format = case File.extname(file_path)
+        when ".xls", ".xlsx"
+          :xls
+        when ".txt"
+          :txt
+        when ".csv"
+          :csv
+        end
+      end
+      
+      case format
+      when :xls
         require "spreadsheet"
         # Row#to_a coerces Excel data to Strings, but we want Dates and Numbers
         data = []
         Spreadsheet.open(file_path).worksheets.first.each do |excel_row|
           data << excel_row.inject([]) { |row, cell| row << cell; row }
         end
-      when ".txt"
+      when :txt
         require "csv"
         data = ::CSV.open(file_path, "r","\t").collect { |row| row }
-      when ".csv"
+      when :csv
         require "fastercsv"
         data = FasterCSV.read(file_path)
+      else
+        raise "Cannot read '#{format}' format. Expected :xls, :xlsx, :txt, or :csv"
       end
       
       Table.new data, options
@@ -31,20 +48,16 @@ module Tabular
     # Maps rows to Hash-like Tabular::Rows.
     #
     # Options:
-    # :column => { :original_name => :preferred_name, :column_name => { :column_type => :boolean } }
+    # :columns => { :original_name => :preferred_name, :column_name => { :column_type => :boolean } }
     def initialize(rows = [], *options)
-      if options
-        options = options.flatten.first || {}
-      else
-        options = {}
-      end
+      options = Table.extract_options(options)
+      @rows = []
       
       rows.each do |row|
-        if columns
-          @rows << Tabular::Row.new(columns, row)
+        if @columns
+          self << row
         else
           @columns = Tabular::Columns.new(row, options[:columns])
-          @rows = []
         end
       end
     end
@@ -54,12 +67,31 @@ module Tabular
       rows[index]
     end
     
+    def <<(row)
+      @rows << Tabular::Row.new(self, row)
+    end
+    
     def inspect
       rows.map { |row| row.join(",") }.join("\n")
     end
     
+    def columns
+      @columns || Tabular::Columns.new([])
+    end
+    
     def to_s
       "#<#{self.class} #{rows.size}>"
     end
+
+
+    private
+    
+    def self.extract_options(options)
+      if options
+        options.flatten.first || {}
+      else
+        {}
+      end
+    end
   end
 end

data/tabular.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{tabular}
-  s.version = "0.0.1"
+  s.version = "0.0.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Scott Willson"]
-  s.date = %q{2009-12-15}
+  s.date = %q{2010-06-07}
   s.description = %q{Tabular is a Ruby library for reading, writing, and manipulating CSV, tab-delimited and Excel data.}
   s.email = %q{scott.willson@gmail.cpm}
   s.extra_rdoc_files = [
@@ -17,7 +17,8 @@ Gem::Specification.new do |s|
      "README"
   ]
   s.files = [
-    "LICENSE",
+    ".gitignore",
+     "LICENSE",
      "README",
      "Rakefile",
      "VERSION",
@@ -33,6 +34,7 @@ Gem::Specification.new do |s|
      "test/fixtures/blank.txt",
      "test/fixtures/excel.xls",
      "test/fixtures/sample.csv",
+     "test/fixtures/sample.lif",
      "test/helper.rb",
      "test/row_test.rb",
      "test/table_test.rb"
@@ -40,7 +42,7 @@ Gem::Specification.new do |s|
   s.homepage = %q{http://github.com/scottwillson/tabular}
   s.rdoc_options = ["--charset=UTF-8"]
   s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.3.5}
+  s.rubygems_version = %q{1.3.7}
   s.summary = %q{Read, write, and manipulate CSV, tab-delimited and Excel data}
   s.test_files = [
     "test/column_test.rb",
@@ -54,7 +56,7 @@ Gem::Specification.new do |s|
     current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
     s.specification_version = 3
 
-    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
     else
     end
   else

data/test/fixtures/sample.lif

@@ -0,0 +1,5 @@
+"Place ","Number","Last Name","First Name","Team","Category Raced"
+"1","189","Willson","Scott","Gentle Lover","Senior Men 1/2/3","11",,"11"
+"2","190","Phinney","Harry","CCCP","Senior Men 1/2/3","9",,
+"3","10a","Holland","Steve","Huntair","Senior Men 1/2/3",,"3",
+"dnf","100","Bourcier","Paul","Hutch's","Senior Men 1/2/3",,,"1"

data/test/row_test.rb

@@ -3,7 +3,7 @@ require "helper"
 module Tabular
   class RowTest < Test::Unit::TestCase
     def test_new
-      row = Row.new([])
+      row = Row.new(Table.new)
       assert_equal nil, row[:city], "[]"
       
       assert_equal "", row.join, "join"
@@ -16,8 +16,8 @@ module Tabular
     end
     
     def test_set
-      columns = Columns.new([ "planet", "star" ])
-      row = Row.new(columns, [ "Mars", "Sun" ])
+      table = Table.new([[ "planet", "star" ]])
+      row = Row.new(table, [ "Mars", "Sun" ])
       
       assert_equal "Sun", row[:star], "row[:star]"
       
@@ -29,29 +29,37 @@ module Tabular
     end
     
     def test_join
-      columns = Columns.new([ "planet", "star" ])
-      row = Row.new(columns, [ "Mars", "Sun" ])
+      table = Table.new([[ "planet", "star" ]])
+      row = Row.new(table, [ "Mars", "Sun" ])
       assert_equal "MarsSun", row.join, "join"
       assert_equal "Mars-Sun", row.join("-"), "join '-'"
     end
     
     def test_to_hash
-      columns = Columns.new([ "planet", "star" ])
-      row = Row.new(columns, [ "Mars", "Sun" ])
+      table = Table.new([[ "planet", "star" ]])
+      row = Row.new(table, [ "Mars", "Sun" ])
       assert_equal({ :planet => "Mars", :star => "Sun"}, row.to_hash, "to_hash")
     end
     
     def test_inspect
-      columns = Columns.new([ "planet", "star" ])
-      row = Row.new(columns, [ "Mars", "Sun" ])
+      table = Table.new([[ "planet", "star" ]])
+      row = Row.new(table, [ "Mars", "Sun" ])
       assert_equal "{:planet=>\"Mars\", :star=>\"Sun\"}", row.inspect, "inspect"
     end
     
     def test_to_s
-      columns = Columns.new([ "planet", "star" ])
-      row = Row.new(columns, [ "Mars", "Sun" ])
+      table = Table.new([[ "planet", "star" ]])
+      row = Row.new(table, [ "Mars", "Sun" ])
       assert_equal "Mars, Sun", row.to_s, "to_s"
     end
+    
+    def test_previous
+      table = Table.new([[ "planet", "star" ]])
+      table << [ "Mars", "Sun" ]
+      table << [ "Jupiter", "Sun" ]
+      assert_equal nil, table.rows.first.previous, "previous of first Row"
+      assert_equal "Mars", table.rows.last.previous[:planet], "previous"
+    end
   end
 end
 

data/test/table_test.rb

@@ -32,6 +32,21 @@ module Tabular
       table = Table.read(File.expand_path(File.dirname(__FILE__) + "/fixtures/excel.xls"))
       assert_equal Date.new(2006, 1, 20), table[0][:date], "0.0"
     end
+    
+    def test_read_as
+      table = Table.read(File.expand_path(File.dirname(__FILE__) + "/fixtures/sample.lif"), :as => :csv)
+      assert_equal 4, table.rows.size, "rows"
+    end
+    
+    def test_column_map
+      data = [
+        [ "nom", "equipe", "homme" ],
+        [ "Hinault", "Team Z", "true" ]
+      ]
+      table = Table.new(data, :columns => { :nom => :name, :equipe => :team, :homme => { :column_type => :boolean } })
+      assert_equal "Hinault", table.rows.first[:name], ":name"
+      assert_equal "Team Z", table.rows.first[:team], ":team"
+      assert_equal true, table.rows.first[:homme], "boolean"
+    end
   end
 end
-

metadata

@@ -1,7 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: tabular
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 2
+  version: 0.0.2
 platform: ruby
 authors: 
 - Scott Willson
@@ -9,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-15 00:00:00 -08:00
+date: 2010-06-07 00:00:00 -07:00
 default_executable: 
 dependencies: []
 
@@ -23,6 +29,7 @@ extra_rdoc_files:
 - LICENSE
 - README
 files: 
+- .gitignore
 - LICENSE
 - README
 - Rakefile
@@ -39,6 +46,7 @@ files:
 - test/fixtures/blank.txt
 - test/fixtures/excel.xls
 - test/fixtures/sample.csv
+- test/fixtures/sample.lif
 - test/helper.rb
 - test/row_test.rb
 - test/table_test.rb
@@ -52,21 +60,27 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Read, write, and manipulate CSV, tab-delimited and Excel data