RubyGems - remote_table - Versions diffs - 1.2.4 → 1.3.0 - Mend

remote_table 1.2.4 → 1.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (18) hide show

data/README.rdoc +1 -1
data/lib/remote_table.rb +4 -13
data/lib/remote_table/format/delimited.rb +20 -21
data/lib/remote_table/format/fixed_width.rb +2 -1
data/lib/remote_table/format/mixins/processed_by_nokogiri.rb +7 -7
data/lib/remote_table/format/mixins/processed_by_roo.rb +30 -20
data/lib/remote_table/format/mixins/textual.rb +9 -9
data/lib/remote_table/local_file.rb +18 -80
data/lib/remote_table/properties.rb +52 -61
data/lib/remote_table/transformer.rb +3 -4
data/lib/remote_table/utils.rb +157 -0
data/lib/remote_table/version.rb +1 -1
data/remote_table.gemspec +1 -7
data/test/test_big.rb +2 -2
data/test/test_old_syntax.rb +20 -20
data/test/test_remote_table.rb +11 -0
metadata +28 -94
data/lib/remote_table/executor.rb +0 -37

data/lib/remote_table/transformer.rb CHANGED Viewed

@@ -14,10 +14,9 @@ class RemoteTable
     end
     def legacy_transformer
       return @legacy_transformer if @legacy_transformer
-      return unless t.options['transform']
-      transform_options = t.options['transform'].dup
-      transform_options.stringify_keys!
-      @legacy_transformer = transform_options['class'].new transform_options.except('class')
+      return unless t.options[:transform]
+      transform_options = t.options[:transform].symbolize_keys
+      @legacy_transformer = transform_options[:class].new transform_options.except(:class)
     end
   end
 end

data/lib/remote_table/utils.rb ADDED Viewed

@@ -0,0 +1,157 @@
+require 'fileutils'
+require 'posix/spawn'
+require 'tmpdir'
+class RemoteTable
+  class SpawnError < ::RuntimeError; end
+  module Utils
+    def self.tmp_path(ancestor)
+      basename = ::File.basename(ancestor).sub(/remote_table-[0-9]+-/, '')
+      ::Kernel.srand
+      ::File.join ::Dir.tmpdir, "remote_table-#{::Kernel.rand(1e11)}-#{basename}"
+    end
+    def self.spawn(*argv)
+      options = argv.extract_options!
+      if options[:in] or options[:out]
+        # capture these now because posix/spawn is known to bork them
+        in_out = options.slice(:in, :out).map { |k, v| ":#{k} => #{v.path}" }.join(', ')
+        # --
+        pid = ::POSIX::Spawn.spawn *argv, options
+        ::Process.waitpid pid
+        raise SpawnError, "[remote_table] spawn #{argv.join(' ')} (#{in_out}) failed with exit status #{$?.exitstatus}" unless $?.success?
+      else
+        child = ::POSIX::Spawn::Child.new *argv
+        raise SpawnError, "[remote_table] spawn #{argv.join(' ')}) failed with #{child.err}" unless child.success?
+      end
+      nil
+    end
+    def self.in_place(*args)
+      options = args.extract_options!
+      input = args.shift
+      argv = args
+      output = tmp_path input
+      ::File.open(input, 'r') do |f0|
+        ::File.open(output, 'wb') do |f1|
+          spawn *argv, :in => f0, :out => f1
+        end
+      end
+      ::FileUtils.mv output, input
+      nil
+    rescue SpawnError => e
+      if options[:ignore_error]
+        $stderr.puts "#{e.inspect} (ignoring error...)"
+        ::FileUtils.mv output, input
+      else
+        raise e
+      end
+    end
+    def self.download(uri, form_data = nil)
+      output = tmp_path uri.path
+      if uri.scheme == 'file'
+        $stderr.puts "[remote_table] Getting #{uri.path} from the local file system" if ::ENV['REMOTE_TABLE_VERBOSE'] == 'true'
+        ::FileUtils.cp uri.path, output
+        return output
+      end
+      argv = [ 'curl', '--location', '--show-error', '--silent', '--compressed', '--header', 'Expect: ' ]
+      if form_data
+        argv += [ '--data', form_data ]
+      end
+      argv += [ uri.to_s, '--output', output ]
+      # sabshere 7/20/11 make web requests move more slowly so you don't get accused of DOS
+      if ::ENV.has_key?('REMOTE_TABLE_DELAY_BETWEEN_REQUESTS')
+        ::Kernel.sleep ::ENV['REMOTE_TABLE_DELAY_BETWEEN_REQUESTS'].to_i
+      end
+      $stderr.puts "[remote_table] Downloading #{uri.to_s}" if ::ENV['REMOTE_TABLE_VERBOSE'] == 'true'
+      spawn *argv
+      output
+    end
+    def self.decompress(input, compression)
+      case compression
+      when :zip, :exe
+        Utils.unzip input
+      when :bz2
+        Utils.bunzip2 input
+      when :gz
+        Utils.gunzip input
+      else
+        raise ::ArgumentError, "[remote_table] Unrecognized compression #{compression}"
+      end
+    end
+    def self.unpack(input, packing)
+      case packing
+      when :tar
+        Utils.untar input
+      else
+        raise ::ArgumentError, "[remote_table] Unrecognized packing #{packing}"
+      end
+    end
+    def self.pick(input, options = {})
+      options = options.symbolize_keys
+      if (options[:filename] or options[:glob]) and not ::File.directory?(input)
+        raise ::RuntimeError, "[remote_table] Expecting #{input} to be a directory"
+      end
+      if filename = options[:filename]
+        src = ::File.join input, filename
+        raise(::RuntimeError, "[remote_table] Expecting #{src} to be a file") unless ::File.file?(src)
+        output = tmp_path src
+        ::FileUtils.mv src, output
+        ::FileUtils.rm_rf input if ::File.dirname(input).start_with?(::Dir.tmpdir)
+      elsif glob = options[:glob]
+        src = ::Dir[input+glob].first
+        raise(::RuntimeError, "[remote_table] Expecting #{glob} to find a file in #{input}") unless src and ::File.file?(src)
+        output = tmp_path src
+        ::FileUtils.mv src, output
+        ::FileUtils.rm_rf input if ::File.dirname(input).start_with?(::Dir.tmpdir)
+      else
+        output = tmp_path input
+        ::FileUtils.mv input, output
+      end
+      output
+    end
+    def self.gunzip(input)
+      output = tmp_path input
+      ::File.open(output, 'wb') do |f|
+        spawn 'gunzip', '--stdout', input, :out => f
+      end
+      ::FileUtils.rm_f input
+      output
+    end
+    def self.bunzip2(input)
+      output = tmp_path input
+      ::File.open(output, 'wb') do |f|
+        spawn 'bunzip2', '--stdout', input, :out => f
+      end
+      ::FileUtils.rm_f input
+      output
+    end
+    def self.untar(input)
+      dest_dir = tmp_path input
+      ::FileUtils.mkdir dest_dir
+      spawn 'tar', '-xf', input, '-C', dest_dir
+      ::FileUtils.rm_f input
+      dest_dir
+    end
+    def self.unzip(input)
+      dest_dir = tmp_path input
+      ::FileUtils.mkdir dest_dir
+      spawn 'unzip', '-qq', '-n', input, '-d', dest_dir
+      ::FileUtils.rm_f input
+      dest_dir
+    end
+  end
+end

data/lib/remote_table/version.rb CHANGED Viewed

@@ -1,3 +1,3 @@
 class RemoteTable
-  VERSION = "1.2.4"
+  VERSION = "1.3.0"
 end

data/remote_table.gemspec CHANGED Viewed

@@ -20,15 +20,9 @@ Gem::Specification.new do |s|
   s.require_paths = ["lib"]
   s.add_runtime_dependency 'activesupport', '>=2.3.4'
-  s.add_runtime_dependency 'roo', '~>1.9'
+  s.add_runtime_dependency 'roo', '>=1.9'
   s.add_runtime_dependency 'fixed_width-multibyte' # TODO replace with fixed_width once timon gets off vacation
   s.add_runtime_dependency 'i18n' # activesupport?
-  s.add_runtime_dependency 'builder' # roo?
-  s.add_runtime_dependency 'zip' # roo
-  s.add_runtime_dependency 'nokogiri', '>=1.4.1' # roo
-  s.add_runtime_dependency 'spreadsheet' #roo
-  s.add_runtime_dependency 'google-spreadsheet-ruby' #roo
-  s.add_runtime_dependency 'escape', '>=0.0.4'
   s.add_runtime_dependency 'posix-spawn'
   s.add_runtime_dependency 'ensure-encoding'
   s.add_runtime_dependency 'fastercsv', '>=1.5.0'

data/test/test_big.rb CHANGED Viewed

@@ -41,9 +41,9 @@ class TestBig < Test::Unit::TestCase
   should "send form data, follow redirects and use a filename glob" do
     url = 'http://www.transtats.bts.gov/DownLoad_Table.asp?Table_ID=293&Has_Group=3&Is_Zipped=0'
-    form_data = 'UserTableName=T_100_Segment__All_Carriers&DBShortName=Air_Carriers&RawDataTable=T_T100_SEGMENT_ALL_CARRIER&sqlstr=+SELECT+DEPARTURES_SCHEDULED%2CDEPARTURES_PERFORMED%2CPAYLOAD%2CSEATS%2CPASSENGERS%2CFREIGHT%2CMAIL%2CDISTANCE%2CRAMP_TO_RAMP%2CAIR_TIME%2CUNIQUE_CARRIER%2CAIRLINE_ID%2CUNIQUE_CARRIER_NAME%2CUNIQUE_CARRIER_ENTITY%2CREGION%2CCARRIER%2CCARRIER_NAME%2CCARRIER_GROUP%2CCARRIER_GROUP_NEW%2CORIGIN%2CORIGIN_CITY_NAME%2CORIGIN_CITY_NUM%2CORIGIN_STATE_ABR%2CORIGIN_STATE_FIPS%2CORIGIN_STATE_NM%2CORIGIN_COUNTRY%2CORIGIN_COUNTRY_NAME%2CORIGIN_WAC%2CDEST%2CDEST_CITY_NAME%2CDEST_CITY_NUM%2CDEST_STATE_ABR%2CDEST_STATE_FIPS%2CDEST_STATE_NM%2CDEST_COUNTRY%2CDEST_COUNTRY_NAME%2CDEST_WAC%2CAIRCRAFT_GROUP%2CAIRCRAFT_TYPE%2CAIRCRAFT_CONFIG%2CYEAR%2CQUARTER%2CMONTH%2CDISTANCE_GROUP%2CCLASS%2CDATA_SOURCE+FROM++T_T100_SEGMENT_ALL_CARRIER+WHERE+Month+%3D1+AND+YEAR%3D2008&varlist=DEPARTURES_SCHEDULED%2CDEPARTURES_PERFORMED%2CPAYLOAD%2CSEATS%2CPASSENGERS%2CFREIGHT%2CMAIL%2CDISTANCE%2CRAMP_TO_RAMP%2CAIR_TIME%2CUNIQUE_CARRIER%2CAIRLINE_ID%2CUNIQUE_CARRIER_NAME%2CUNIQUE_CARRIER_ENTITY%2CREGION%2CCARRIER%2CCARRIER_NAME%2CCARRIER_GROUP%2CCARRIER_GROUP_NEW%2CORIGIN%2CORIGIN_CITY_NAME%2CORIGIN_CITY_NUM%2CORIGIN_STATE_ABR%2CORIGIN_STATE_FIPS%2CORIGIN_STATE_NM%2CORIGIN_COUNTRY%2CORIGIN_COUNTRY_NAME%2CORIGIN_WAC%2CDEST%2CDEST_CITY_NAME%2CDEST_CITY_NUM%2CDEST_STATE_ABR%2CDEST_STATE_FIPS%2CDEST_STATE_NM%2CDEST_COUNTRY%2CDEST_COUNTRY_NAME%2CDEST_WAC%2CAIRCRAFT_GROUP%2CAIRCRAFT_TYPE%2CAIRCRAFT_CONFIG%2CYEAR%2CQUARTER%2CMONTH%2CDISTANCE_GROUP%2CCLASS%2CDATA_SOURCE&grouplist=&suml=&sumRegion=&filter1=title%3D&filter2=title%3D&geo=All%A0&time=January&timename=Month&GEOGRAPHY=All&XYEAR=2008&FREQUENCY=1&AllVars=All&VarName=DEPARTURES_SCHEDULED&VarDesc=DepScheduled&VarType=Num&VarName=DEPARTURES_PERFORMED&VarDesc=DepPerformed&VarType=Num&VarName=PAYLOAD&VarDesc=Payload&VarType=Num&VarName=SEATS&VarDesc=Seats&VarType=Num&VarName=PASSENGERS&VarDesc=Passengers&VarType=Num&VarName=FREIGHT&VarDesc=Freight&VarType=Num&VarName=MAIL&VarDesc=Mail&VarType=Num&VarName=DISTANCE&VarDesc=Distance&VarType=Num&VarName=RAMP_TO_RAMP&VarDesc=RampToRamp&VarType=Num&VarName=AIR_TIME&VarDesc=AirTime&VarType=Num&VarName=UNIQUE_CARRIER&VarDesc=UniqueCarrier&VarType=Char&VarName=AIRLINE_ID&VarDesc=AirlineID&VarType=Num&VarName=UNIQUE_CARRIER_NAME&VarDesc=UniqueCarrierName&VarType=Char&VarName=UNIQUE_CARRIER_ENTITY&VarDesc=UniqCarrierEntity&VarType=Char&VarName=REGION&VarDesc=CarrierRegion&VarType=Char&VarName=CARRIER&VarDesc=Carrier&VarType=Char&VarName=CARRIER_NAME&VarDesc=CarrierName&VarType=Char&VarName=CARRIER_GROUP&VarDesc=CarrierGroup&VarType=Num&VarName=CARRIER_GROUP_NEW&VarDesc=CarrierGroupNew&VarType=Num&VarName=ORIGIN&VarDesc=Origin&VarType=Char&VarName=ORIGIN_CITY_NAME&VarDesc=OriginCityName&VarType=Char&VarName=ORIGIN_CITY_NUM&VarDesc=OriginCityNum&VarType=Num&VarName=ORIGIN_STATE_ABR&VarDesc=OriginState&VarType=Char&VarName=ORIGIN_STATE_FIPS&VarDesc=OriginStateFips&VarType=Char&VarName=ORIGIN_STATE_NM&VarDesc=OriginStateName&VarType=Char&VarName=ORIGIN_COUNTRY&VarDesc=OriginCountry&VarType=Char&VarName=ORIGIN_COUNTRY_NAME&VarDesc=OriginCountryName&VarType=Char&VarName=ORIGIN_WAC&VarDesc=OriginWac&VarType=Num&VarName=DEST&VarDesc=Dest&VarType=Char&VarName=DEST_CITY_NAME&VarDesc=DestCityName&VarType=Char&VarName=DEST_CITY_NUM&VarDesc=DestCityNum&VarType=Num&VarName=DEST_STATE_ABR&VarDesc=DestState&VarType=Char&VarName=DEST_STATE_FIPS&VarDesc=DestStateFips&VarType=Char&VarName=DEST_STATE_NM&VarDesc=DestStateName&VarType=Char&VarName=DEST_COUNTRY&VarDesc=DestCountry&VarType=Char&VarName=DEST_COUNTRY_NAME&VarDesc=DestCountryName&VarType=Char&VarName=DEST_WAC&VarDesc=DestWac&VarType=Num&VarName=AIRCRAFT_GROUP&VarDesc=AircraftGroup&VarType=Num&VarName=AIRCRAFT_TYPE&VarDesc=AircraftType&VarType=Char&VarName=AIRCRAFT_CONFIG&VarDesc=AircraftConfig&VarType=Num&VarName=YEAR&VarDesc=Year&VarType=Num&VarName=QUARTER&VarDesc=Quarter&VarType=Num&VarName=MONTH&VarDesc=Month&VarType=Num&VarName=DISTANCE_GROUP&VarDesc=DistanceGroup&VarType=Num&VarName=CLASS&VarDesc=Class&VarType=Char&VarName=DATA_SOURCE&VarDesc=DataSource&VarType=Char'
+    form_data = 'UserTableName=T_100_Segment__All_Carriers&DBShortName=Air_Carriers&RawDataTable=T_T100_SEGMENT_ALL_CARRIER&sqlstr=+SELECT+DEPARTURES_SCHEDULED%2CDEPARTURES_PERFORMED%2CPAYLOAD%2CSEATS%2CPASSENGERS%2CFREIGHT%2CMAIL%2CDISTANCE%2CRAMP_TO_RAMP%2CAIR_TIME%2CUNIQUE_CARRIER%2CAIRLINE_ID%2CUNIQUE_CARRIER_NAME%2CUNIQUE_CARRIER_ENTITY%2CREGION%2CCARRIER%2CCARRIER_NAME%2CCARRIER_GROUP%2CCARRIER_GROUP_NEW%2CORIGIN%2CORIGIN_CITY_NAME%2CORIGIN_STATE_ABR%2CORIGIN_STATE_FIPS%2CORIGIN_STATE_NM%2CORIGIN_COUNTRY%2CORIGIN_COUNTRY_NAME%2CORIGIN_WAC%2CDEST%2CDEST_CITY_NAME%2CDEST_STATE_ABR%2CDEST_STATE_FIPS%2CDEST_STATE_NM%2CDEST_COUNTRY%2CDEST_COUNTRY_NAME%2CDEST_WAC%2CAIRCRAFT_GROUP%2CAIRCRAFT_TYPE%2CAIRCRAFT_CONFIG%2CYEAR%2CQUARTER%2CMONTH%2CDISTANCE_GROUP%2CCLASS%2CDATA_SOURCE+FROM++T_T100_SEGMENT_ALL_CARRIER+WHERE+Month+%3D1+AND+YEAR%3D2008&varlist=DEPARTURES_SCHEDULED%2CDEPARTURES_PERFORMED%2CPAYLOAD%2CSEATS%2CPASSENGERS%2CFREIGHT%2CMAIL%2CDISTANCE%2CRAMP_TO_RAMP%2CAIR_TIME%2CUNIQUE_CARRIER%2CAIRLINE_ID%2CUNIQUE_CARRIER_NAME%2CUNIQUE_CARRIER_ENTITY%2CREGION%2CCARRIER%2CCARRIER_NAME%2CCARRIER_GROUP%2CCARRIER_GROUP_NEW%2CORIGIN%2CORIGIN_CITY_NAME%2CORIGIN_STATE_ABR%2CORIGIN_STATE_FIPS%2CORIGIN_STATE_NM%2CORIGIN_COUNTRY%2CORIGIN_COUNTRY_NAME%2CORIGIN_WAC%2CDEST%2CDEST_CITY_NAME%2CDEST_STATE_ABR%2CDEST_STATE_FIPS%2CDEST_STATE_NM%2CDEST_COUNTRY%2CDEST_COUNTRY_NAME%2CDEST_WAC%2CAIRCRAFT_GROUP%2CAIRCRAFT_TYPE%2CAIRCRAFT_CONFIG%2CYEAR%2CQUARTER%2CMONTH%2CDISTANCE_GROUP%2CCLASS%2CDATA_SOURCE&grouplist=&suml=&sumRegion=&filter1=title%3D&filter2=title%3D&geo=All%A0&time=January&timename=Month&GEOGRAPHY=All&XYEAR=2008&FREQUENCY=1&AllVars=All&VarName=DEPARTURES_SCHEDULED&VarDesc=DepScheduled&VarType=Num&VarName=DEPARTURES_PERFORMED&VarDesc=DepPerformed&VarType=Num&VarName=PAYLOAD&VarDesc=Payload&VarType=Num&VarName=SEATS&VarDesc=Seats&VarType=Num&VarName=PASSENGERS&VarDesc=Passengers&VarType=Num&VarName=FREIGHT&VarDesc=Freight&VarType=Num&VarName=MAIL&VarDesc=Mail&VarType=Num&VarName=DISTANCE&VarDesc=Distance&VarType=Num&VarName=RAMP_TO_RAMP&VarDesc=RampToRamp&VarType=Num&VarName=AIR_TIME&VarDesc=AirTime&VarType=Num&VarName=UNIQUE_CARRIER&VarDesc=UniqueCarrier&VarType=Char&VarName=AIRLINE_ID&VarDesc=AirlineID&VarType=Num&VarName=UNIQUE_CARRIER_NAME&VarDesc=UniqueCarrierName&VarType=Char&VarName=UNIQUE_CARRIER_ENTITY&VarDesc=UniqCarrierEntity&VarType=Char&VarName=REGION&VarDesc=CarrierRegion&VarType=Char&VarName=CARRIER&VarDesc=Carrier&VarType=Char&VarName=CARRIER_NAME&VarDesc=CarrierName&VarType=Char&VarName=CARRIER_GROUP&VarDesc=CarrierGroup&VarType=Num&VarName=CARRIER_GROUP_NEW&VarDesc=CarrierGroupNew&VarType=Num&VarName=ORIGIN&VarDesc=Origin&VarType=Char&VarName=ORIGIN_CITY_NAME&VarDesc=OriginCityName&VarType=Char&VarName=ORIGIN_STATE_ABR&VarDesc=OriginState&VarType=Char&VarName=ORIGIN_STATE_FIPS&VarDesc=OriginStateFips&VarType=Char&VarName=ORIGIN_STATE_NM&VarDesc=OriginStateName&VarType=Char&VarName=ORIGIN_COUNTRY&VarDesc=OriginCountry&VarType=Char&VarName=ORIGIN_COUNTRY_NAME&VarDesc=OriginCountryName&VarType=Char&VarName=ORIGIN_WAC&VarDesc=OriginWac&VarType=Num&VarName=DEST&VarDesc=Dest&VarType=Char&VarName=DEST_CITY_NAME&VarDesc=DestCityName&VarType=Char&VarName=DEST_STATE_ABR&VarDesc=DestState&VarType=Char&VarName=DEST_STATE_FIPS&VarDesc=DestStateFips&VarType=Char&VarName=DEST_STATE_NM&VarDesc=DestStateName&VarType=Char&VarName=DEST_COUNTRY&VarDesc=DestCountry&VarType=Char&VarName=DEST_COUNTRY_NAME&VarDesc=DestCountryName&VarType=Char&VarName=DEST_WAC&VarDesc=DestWac&VarType=Num&VarName=AIRCRAFT_GROUP&VarDesc=AircraftGroup&VarType=Num&VarName=AIRCRAFT_TYPE&VarDesc=AircraftType&VarType=Char&VarName=AIRCRAFT_CONFIG&VarDesc=AircraftConfig&VarType=Num&VarName=YEAR&VarDesc=Year&VarType=Num&VarName=QUARTER&VarDesc=Quarter&VarType=Num&VarName=MONTH&VarDesc=Month&VarType=Num&VarName=DISTANCE_GROUP&VarDesc=DistanceGroup&VarType=Num&VarName=CLASS&VarDesc=Class&VarType=Char&VarName=DATA_SOURCE&VarDesc=DataSource&VarType=Char'
     t = RemoteTable.new :url => url, :form_data => form_data, :compression => :zip, :glob => '/*.csv'
-    assert_equal 'United States of America', t.rows.first['DEST_COUNTRY_NAME']
+    assert_equal 'United States', t.rows.first['DEST_COUNTRY_NAME']
   end
   # should "provide a row_hash on demand" do

data/test/test_old_syntax.rb CHANGED Viewed

@@ -16,12 +16,14 @@ $test2_rows.freeze
 class TestOldSyntax < Test::Unit::TestCase
   should "open an XLSX like an array (numbered columns)" do
     t = RemoteTable.new(:url => 'www.customerreferenceprogram.org/uploads/CRP_RFP_template.xlsx', :headers => false)
+    assert_equal "Requirements", t.rows[0][0]
     assert_equal "Software-As-A-Service", t.rows[5][0]
   end
   should "open an XLSX with custom headers" do
     t = RemoteTable.new(:url => 'www.customerreferenceprogram.org/uploads/CRP_RFP_template.xlsx', :headers => %w{foo bar baz})
-    assert_equal "Secure encryption of all data", t.rows[5]['foo']
+    assert_equal "Requirements", t.rows[0]['foo']
+    assert_equal "Software-As-A-Service", t.rows[5]['foo']
   end
   should "open an XLSX" do
@@ -114,27 +116,25 @@ class TestOldSyntax < Test::Unit::TestCase
   end
   %w{ csv ods xls }.each do |format|
-    eval %{
-      should "read #{format}" do
-        t = RemoteTable.new(:url => 'http://cloud.github.com/downloads/seamusabshere/remote_table/test2.#{format}')
-        # no blank headers
-        assert t.rows.all? { |row| row.keys.all?(&:present?) }
-        # correct values
-        t.rows.each_with_index do |row, index|
-          assert_equal row.except('row_hash'), $test2_rows[index]
-        end
+    should "read #{format}" do
+      t = RemoteTable.new(:url => "http://cloud.github.com/downloads/seamusabshere/remote_table/test2.#{format}")
+      # no blank headers
+      assert t.rows.all? { |row| row.keys.all?(&:present?) }
+      # correct values
+      t.rows.each_with_index do |row, index|
+        assert_equal $test2_rows[index], row.except('row_hash')
       end
-      should "read #{format}, keeping blank rows" do
-        t = RemoteTable.new(:url => 'http://cloud.github.com/downloads/seamusabshere/remote_table/test2.#{format}', :keep_blank_rows => true)
-        # no blank headers
-        assert t.rows.all? { |row| row.keys.all?(&:present?) }
-        # correct values
-        t.rows.each_with_index do |row, index|
-          assert_equal row.except('row_hash'), $test2_rows_with_blanks[index]
-        end
+    end
+    should "read #{format}, keeping blank rows" do
+      t = RemoteTable.new(:url => "http://cloud.github.com/downloads/seamusabshere/remote_table/test2.#{format}", :keep_blank_rows => true)
+      # no blank headers
+      assert t.rows.all? { |row| row.keys.all?(&:present?) }
+      # correct values
+      t.rows.each_with_index do |row, index|
+        assert_equal $test2_rows_with_blanks[index], row.except('row_hash')
       end
-    }
+    end
   end
   should "read fixed width correctly" do

data/test/test_remote_table.rb CHANGED Viewed

@@ -124,4 +124,15 @@ class TestRemoteTable < Test::Unit::TestCase
     t = RemoteTable.new 'https://openflights.svn.sourceforge.net/svnroot/openflights/openflights/data/airports.dat', :headers => false#, :encoding => 'UTF-8'
     assert_equal 'Goroka', t[0][1]
   end
+  should "read only certain rows of an XLSX" do
+    t = RemoteTable.new 'www.customerreferenceprogram.org/uploads/CRP_RFP_template.xlsx', :crop => 11..16, :headers => false
+    assert_equal "Permissioning and access groups for all content", t[0][0]
+    assert_equal "Manage Multiple Incentive Programs for Participants", t[4][0]
+    t = RemoteTable.new 'www.customerreferenceprogram.org/uploads/CRP_RFP_template.xlsx', :crop => 11..16, :headers => %w{ col1 }
+    assert_equal "Permissioning and access groups for all content", t[0]['col1']
+    assert_equal "Manage Multiple Incentive Programs for Participants", t[4]['col1']
+  end
 end

metadata CHANGED Viewed

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: remote_table
 version: !ruby/object:Gem::Version
-  version: 1.2.4
+  version: 1.3.0
   prerelease:
 platform: ruby
 authors:
@@ -10,11 +10,11 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2011-11-29 00:00:00.000000000Z
+date: 2011-12-27 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
-  requirement: &2164990540 !ruby/object:Gem::Requirement
+  requirement: &2165420280 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -22,21 +22,21 @@ dependencies:
         version: 2.3.4
   type: :runtime
   prerelease: false
-  version_requirements: *2164990540
+  version_requirements: *2165420280
 - !ruby/object:Gem::Dependency
   name: roo
-  requirement: &2164990040 !ruby/object:Gem::Requirement
+  requirement: &2165419500 !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ~>
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '1.9'
   type: :runtime
   prerelease: false
-  version_requirements: *2164990040
+  version_requirements: *2165419500
 - !ruby/object:Gem::Dependency
   name: fixed_width-multibyte
-  requirement: &2164989660 !ruby/object:Gem::Requirement
+  requirement: &2165418920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,32 +44,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2164989660
+  version_requirements: *2165418920
 - !ruby/object:Gem::Dependency
   name: i18n
-  requirement: &2164989200 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *2164989200
-- !ruby/object:Gem::Dependency
-  name: builder
-  requirement: &2164988780 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *2164988780
-- !ruby/object:Gem::Dependency
-  name: zip
-  requirement: &2164988360 !ruby/object:Gem::Requirement
+  requirement: &2165418440 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -77,54 +55,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2164988360
-- !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: &2164987860 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: 1.4.1
-  type: :runtime
-  prerelease: false
-  version_requirements: *2164987860
-- !ruby/object:Gem::Dependency
-  name: spreadsheet
-  requirement: &2164987440 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *2164987440
-- !ruby/object:Gem::Dependency
-  name: google-spreadsheet-ruby
-  requirement: &2164986980 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *2164986980
-- !ruby/object:Gem::Dependency
-  name: escape
-  requirement: &2164986480 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: 0.0.4
-  type: :runtime
-  prerelease: false
-  version_requirements: *2164986480
+  version_requirements: *2165418440
 - !ruby/object:Gem::Dependency
   name: posix-spawn
-  requirement: &2164986060 !ruby/object:Gem::Requirement
+  requirement: &2165407660 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -132,10 +66,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2164986060
+  version_requirements: *2165407660
 - !ruby/object:Gem::Dependency
   name: ensure-encoding
-  requirement: &2164985600 !ruby/object:Gem::Requirement
+  requirement: &2165407140 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -143,10 +77,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2164985600
+  version_requirements: *2165407140
 - !ruby/object:Gem::Dependency
   name: fastercsv
-  requirement: &2164985100 !ruby/object:Gem::Requirement
+  requirement: &2165406380 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -154,10 +88,10 @@ dependencies:
         version: 1.5.0
   type: :runtime
   prerelease: false
-  version_requirements: *2164985100
+  version_requirements: *2165406380
 - !ruby/object:Gem::Dependency
   name: hash_digest
-  requirement: &2164984680 !ruby/object:Gem::Requirement
+  requirement: &2165405380 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -165,10 +99,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2164984680
+  version_requirements: *2165405380
 - !ruby/object:Gem::Dependency
   name: errata
-  requirement: &2164984140 !ruby/object:Gem::Requirement
+  requirement: &2165404500 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -176,10 +110,10 @@ dependencies:
         version: 0.2.0
   type: :development
   prerelease: false
-  version_requirements: *2164984140
+  version_requirements: *2165404500
 - !ruby/object:Gem::Dependency
   name: test-unit
-  requirement: &2165000080 !ruby/object:Gem::Requirement
+  requirement: &2165404080 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -187,10 +121,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2165000080
+  version_requirements: *2165404080
 - !ruby/object:Gem::Dependency
   name: shoulda
-  requirement: &2164999620 !ruby/object:Gem::Requirement
+  requirement: &2165403480 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -198,10 +132,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2164999620
+  version_requirements: *2165403480
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2164999200 !ruby/object:Gem::Requirement
+  requirement: &2165403060 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -209,7 +143,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2164999200
+  version_requirements: *2165403060
 description: Gives you a standard way to parse various formats and treat them as an
   array of hashes.
 email:
@@ -226,7 +160,6 @@ files:
 - README.rdoc
 - Rakefile
 - lib/remote_table.rb
-- lib/remote_table/executor.rb
 - lib/remote_table/format.rb
 - lib/remote_table/format/delimited.rb
 - lib/remote_table/format/excel.rb
@@ -241,6 +174,7 @@ files:
 - lib/remote_table/local_file.rb
 - lib/remote_table/properties.rb
 - lib/remote_table/transformer.rb
+- lib/remote_table/utils.rb
 - lib/remote_table/version.rb
 - remote_table.gemspec
 - test/helper.rb