iron-import 0.5.0

data/spec/importer/data_reader_spec.rb

@@ -0,0 +1,93 @@
+describe Importer::DataReader do
+
+  before do
+    @importer = Importer.new
+    @reader = Importer::DataReader.new(@importer, :test)
+  end
+
+  it 'should parse integers' do
+    {
+      '1234' => 1234,
+      '-2' => -2,
+      '5.00' => 5,
+      'foo' => nil,
+      '' => nil,
+      55 => 55,
+      3.0 => 3
+    }.each_pair do |val, res|
+      @reader.parse_value(val, :integer).should == res
+    end
+  end
+  
+  it 'should parse floats' do
+    {
+      '1.256' => 1.256,
+      '-20.3' => -20.3,
+      '5.00' => 5.0,
+      'foo' => nil,
+      '' => nil,
+      55 => 55.0,
+      '3' => 3.0
+    }.each_pair do |val, res|
+      @reader.parse_value(val, :float).should == res
+    end
+  end
+  
+  it 'should parse strings' do
+    {
+      'blah' => 'blah',
+      " spaces \t" => 'spaces',
+      '' => nil,
+      255 => '255',
+      -1.5 => '-1.5'
+    }.each_pair do |val, res|
+      @reader.parse_value(val, :string).should == res
+    end
+  end
+  
+  it 'should parse cents' do
+    {
+      '$123.00' => 12300,
+      '5' => 500,
+      '0.5' => 50,
+      '-95' => -9500,
+      52 => 5200,
+      1.0 => 100,
+      1.25 => 125
+    }.each_pair do |val, res|
+      @reader.parse_value(val, :cents).should == res
+    end
+  end
+  
+  it 'should parse dates' do
+    {
+      '1/5/73' => Date.new(1973,1,5),
+      '05/30/01' => Date.new(2001,5,30),
+      '2005-12-10' => Date.new(2005,12,10),
+      '4/10/14 22:28' => Date.new(2014,4,10),
+      '5/10/2014, 10:28:07 PM' => Date.new(2014,5,10),
+      Date.new(2000,4,1) => Date.new(2000,4,1)
+    }.each_pair do |val, res|
+      @reader.parse_value(val, :date).should == res
+    end
+  end
+  
+  it 'should build an instance based on format' do
+    Importer::DataReader.for_format(@importer, :csv).should be_a(Importer::CsvReader)
+    Importer::DataReader.for_format(@importer, :xls).should be_a(Importer::XlsReader)
+    Importer::DataReader.for_format(@importer, :xlsx).should be_a(Importer::XlsxReader)
+    Importer::DataReader.for_format(@importer, :foo).should be_nil
+  end
+  
+  it 'should build an instance based on a path' do
+    Importer::DataReader.for_path(@importer, '/tmp/foo.csv').should be_a(Importer::CsvReader)
+    Importer::DataReader.for_path(@importer, 'BAR.XLS').should be_a(Importer::XlsReader)
+    Importer::DataReader.for_path(@importer, '/tmp/nog_bog.xlsx').should be_a(Importer::XlsxReader)
+    Importer::DataReader.for_path(@importer, '/tmp/blinkin.bmp').should be_nil
+  end
+  
+  it 'should build an instance based on stream' do
+    Importer::DataReader.for_stream(@importer, mock(original_filename: "nanodrop.xlsx", content_type: "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet")).should be_a(Importer::XlsxReader)
+  end
+  
+end

data/spec/importer/importer_spec.rb

@@ -0,0 +1,28 @@
+describe Importer do
+
+  it 'should respond to build' do
+    Importer.should respond_to(:build)
+  end
+  
+  it 'should import a test csv file' do
+    importer = Importer.build do
+      column :number
+      column :string
+      column :date
+      column :cost
+    end
+    importer.import(SpecHelper.sample_path('simple.csv')).should be_true
+    count = 0
+    found = false
+    importer.process do |row|
+      count += 1
+      if row.line == 4
+        found = true
+        row[:date].should == '2004-02-01'
+      end
+    end
+    found.should be_true
+    count.should == 3
+  end
+  
+end

data/spec/importer/row_spec.rb

@@ -0,0 +1,37 @@
+describe Importer::Row do
+
+  before do
+    @importer = Importer.new
+    @sheet = @importer.default_sheet
+    @row = Importer::Row.new(@sheet, 5)
+  end
+
+  it 'should store and retrieve values' do
+    @row.set_values(:a => 1, :b => 2)
+    @row.values.should == {:a => 1, :b => 2}
+  end
+
+  it 'should allow [] access' do
+    @row.set_values(:a => 1, :b => 2)
+    @row[:b].should == 2
+  end
+
+  it 'should test for value presence in all columns' do
+    @row.set_values(:a => 1, :b => 2)
+    @row.should be_all
+    @row.set_values(:a => 1, :b => nil)
+    @row.should_not be_all
+  end
+
+  it 'should test for specific value\'s presence' do
+    @row.set_values(:a => 1, :b => 2, :c => nil)
+    @row.all?(:a, :b).should be_true
+    @row.all?(:c).should be_false
+  end
+
+  it 'should be empty? with zero values' do
+    @row.set_values(:a => nil, :b => nil)
+    @row.should be_empty
+  end
+
+end

data/spec/importer/sheet_spec.rb

@@ -0,0 +1,65 @@
+describe Importer::Sheet do
+
+  before do
+    @importer = Importer.new
+    @sheet = @importer.default_sheet
+  end
+
+  it 'should respond to build' do
+    @sheet.should respond_to(:build)
+    @sheet.build do
+      column :foo
+    end
+    @sheet.columns.count.should == 1
+  end
+  
+  it 'should define columns' do
+    @sheet.column(:foo)
+    @sheet.columns.count.should == 1
+  end
+  
+  it 'should find headers automatically' do
+    # Define a few sample columns
+    @sheet.column(:alpha)
+    @sheet.column(:gamma)
+    # Some dummy data
+    rows = [
+      ['', '', '', ''],
+      ['Alpha', 'Beta', 'Gamma', 'Epsilon']
+    ]
+    
+    # Parse it!
+    @sheet.parse_header(rows).should be_true
+    
+    @sheet.column(:alpha).data.index.should == 0
+    @sheet.column(:gamma).data.index.should == 2
+    @sheet.data.start_row.should == 3
+  end
+  
+  it 'should record an error if a column can\'t be found' do
+    # Define a few sample columns
+    @sheet.column(:alpha)
+    @sheet.column(:gamma)
+    # Some dummy data
+    rows = [
+      ['', '', '', ''],
+      ['Bob', 'Beta', 'Gamma', 'Epsilon']
+    ]
+    
+    # Parse it!
+    @sheet.parse_header(rows).should be_false
+    @importer.errors.count.should == 1
+    @importer.error_summary.should =~ /unable to locate required column header/i
+  end
+  
+  it 'should match by sheet name or number' do
+    @sheet.id = 5
+    @sheet.match_sheet?('foo', 3).should be_false
+    @sheet.match_sheet?('foo', 4).should be_true
+    
+    @sheet.id = 'Sheet 5'
+    @sheet.match_sheet?('Sheet', 4).should be_false
+    @sheet.match_sheet?('Sheet 5', 3).should be_true
+  end
+
+end

data/spec/importer/xlsx_reader_spec.rb

@@ -0,0 +1,35 @@
+describe Importer::XlsxReader do
+
+  it 'should load our nanodrop data' do
+    importer = Importer.build do
+      column :sample_id do
+        required!
+        validate do |val|
+          raise 'Invalid ID' unless val.match(/[0-9]{3,}\.[0-9]\z/)
+        end
+      end
+      column :a260 do
+        type :float
+      end
+      column :a280 do
+        type :float
+      end
+      column :factor do
+        type :integer
+      end
+      
+      # Skip empty rows
+      filter do |row|
+        row.all?
+      end
+    end
+    res = importer.import(SpecHelper.sample_path('nanodrop.xlsx'))
+    importer.error_summary.should be_nil
+    res.should be_true
+    importer.default_sheet.dump.should == [
+      {:sample_id => 'Windsor_buccal_500.1', :a260 => 2.574, :a280 => 1.277, :factor => 50},
+      {:sample_id => 'Weston_fecal_206.2', :a260 => 0.746, :a280 => 0.351, :factor => 50}
+    ]
+  end
+  
+end

data/spec/samples/simple.csv

@@ -0,0 +1,4 @@
+Number,"String",Date,Cost
+123,Abc,5/13/77,8.99
+,,,
+5.0,"String with end spaces   ",2004-02-01,10

data/spec/spec_helper.rb

@@ -0,0 +1,21 @@
+# Set up development requirements
+require 'roo'
+
+# Require our library
+require File.expand_path(File.join(File.dirname(__FILE__), '..', 'lib', 'iron', 'import'))
+
+# Config RSpec options
+RSpec.configure do |config|
+  config.color = true
+  config.add_formatter 'documentation'
+  config.backtrace_exclusion_patterns = [/rspec/]
+end
+
+module SpecHelper
+  
+  # Helper to find sample file paths
+  def self.sample_path(file)
+    File.expand_path(File.join(File.dirname(__FILE__), 'samples', file))
+  end
+  
+end

metadata

@@ -0,0 +1,128 @@
+--- !ruby/object:Gem::Specification
+name: iron-import
+version: !ruby/object:Gem::Version
+  version: 0.5.0
+platform: ruby
+authors:
+- Rob Morris
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-03-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: iron-extensions
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.2.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.2.1
+- !ruby/object:Gem::Dependency
+  name: iron-dsl
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+- !ruby/object:Gem::Dependency
+  name: roo
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+description: Simple yet powerful library for importing tabular data including support
+  for auto-detecting column order, parsing/validating cell data, aggregating errors,
+  etc.
+email:
+- rob@irongaze.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- History.txt
+- LICENSE
+- README.rdoc
+- Version.txt
+- lib/iron/import.rb
+- lib/iron/import/column.rb
+- lib/iron/import/csv_reader.rb
+- lib/iron/import/data_reader.rb
+- lib/iron/import/error.rb
+- lib/iron/import/importer.rb
+- lib/iron/import/row.rb
+- lib/iron/import/sheet.rb
+- lib/iron/import/xls_reader.rb
+- lib/iron/import/xlsx_reader.rb
+- spec/importer/column_spec.rb
+- spec/importer/csv_reader_spec.rb
+- spec/importer/data_reader_spec.rb
+- spec/importer/importer_spec.rb
+- spec/importer/row_spec.rb
+- spec/importer/sheet_spec.rb
+- spec/importer/xlsx_reader_spec.rb
+- spec/samples/nanodrop.xlsx
+- spec/samples/simple.csv
+- spec/samples/test-products.xls
+- spec/spec_helper.rb
+homepage: http://irongaze.com
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 1.9.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.3
+signing_key: 
+specification_version: 4
+summary: CSV, XLS, and XLSX import automation support
+test_files: []