remote_table 2.1.1 → 2.1.2

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    MWUyNDhjYmNhYmEyM2I0Yzc4ZjZmMjJjYTA5NTkzODM5N2Q3MjI1Ng==
+    NDMzYjM5MmViMDA2OTRjMDMwMjljYmJjMmJhNmExODNmMTkzYmI3OA==
   data.tar.gz: !binary |-
-    MWRlNzI0YTEzMjc5NWRkOTY1Nzk5Y2Q4NzgxYTc2MzliZTBmMDFmOA==
-!binary "U0hBNTEy":
+    MDkxZmI3MWM4ZTJjYWM3NDYxOGQzMzRiYzIyMGQ2ODAyOWY0NTNjNg==
+SHA512:
   metadata.gz: !binary |-
-    MDBlMDg5NTE2YzM3YTk5ZjI4M2U5OWNkZmFlOWQ3ZmUwOWI3MGM5NjZjYTgx
-    MDQ4Yjk1OTBhYzk2NjQxYzJiZGZiMDU0MGU3MmU5MTg4ZmU2ZWExNzEwYjYy
-    ODdiN2EzNWNjODA0NTJlOGVjMWNmY2ZmYjA0NzMyZGU5YWYzOGM=
+    OWU5NzM2OWM1MDljMTg3MzJiOWZjN2MxMzliYjhhZDdmNDYyY2E5ZWFhOTE2
+    MWI4YjA1NWM5YjhiMDYxMjA1ZDBkZTFiZTQ4OGJiMDlmNGVhNjg5Nzg2ZTkz
+    MmIxZTZmOGQyMmRhNTI4OTk5YjU1ODM0NjI1ZmIzYzMyZmFiNmI=
   data.tar.gz: !binary |-
-    YjkyMDdjYWYwMGQ2Mzg3OTU0N2Q4NDMzNmNkZGVkMzE1NGFiMWMzYWUzYzJh
-    NjBhNjdkYTQ2ZTc2Nzg3NTU0YzhkYTNlOTMyZTkyYTBjM2Q0YTk1NGVkMDgy
-    NTNjZGU5MzEyMTEyNDhmZGJiNmJkY2VjZmZjYmMxMmEyYjNjNWQ=
+    ZTFhMTk4ZjAyZTdkM2RmZmM1ZmEyZmI5ZWQzMWFkZTliZWIxNmMxMjdhYTBm
+    NDg0YTQ3YThlYzgxNTRhZTQ5YTYzMDU5ZGYxODkzNmIxOWMwMzk5YjMwZTA4
+    ODVmOGRkNDBmNmExMjUyOWRmNTMzN2U1MjFmZjUyNzZmMzM5OTE=

data/CHANGELOG

@@ -1,3 +1,9 @@
+2.1.2 / 2013-10-08
+
+* Bug fixes
+
+  * Correctly detect format from filename - don't get confused if a filename has "xls" in it (thanks @activefx #10)
+
 2.1.1 / 2013-03-25
 
 * Enhancements

data/lib/remote_table.rb

@@ -72,25 +72,25 @@ class RemoteTable
     # Guess file format from the basename. Since a file might be decompressed and/or pulled out of an archive with a glob, this usually can't be called until a file is downloaded.
     # @return [Symbol,nil]
     def guess_format(basename)
-      case basename.to_s.downcase
-      when /ods/, /open_?office/
+      case basename.to_s.downcase.strip
+      when /ods\z/, /open_?office\z/
         :ods
-      when /xlsx/, /excelx/
+      when /xlsx\z/, /excelx\z/
         :xlsx
-      when /xls/, /excel/
+      when /xls\z/, /excel\z/
         :xls
-      when /csv/, /tsv/, /delimited/
+      when /csv\z/, /tsv\z/, /delimited\z/
         # note that there is no RemoteTable::Csv class - it's normalized to :delimited
         :delimited
-      when /fixed_?width/
+      when /fixed_?width\z/
         :fixed_width
-      when /htm/
+      when /html?\z/
         :html
-      when /xml/
+      when /xml\z/
         :xml
-      when /yaml/, /yml/
+      when /yaml\z/, /yml\z/
         :yaml
-      when /shp/
+      when /shp\z/
         :shp
       end
     end
@@ -144,7 +144,7 @@ class RemoteTable
   }
 
   include ::Enumerable
-  
+
   # The URL of the local or remote file.
   #
   # @example Local
@@ -185,23 +185,23 @@ class RemoteTable
   # Whether to warn the user on multiple downloads. Defaults to true.
   # @return [true,false]
   attr_reader :warn_on_multiple_downloads
-  
+
   # Headers specified by the user: +:first_row+ (the default), +false+, or a list of headers.
   # @return [:first_row,false,Array<String>]
   attr_reader :headers
-    
+
   # The sheet specified by the user as a number or a string.
   # @return[String,Integer]
   attr_reader :sheet
-  
+
   # Whether to keep blank rows. Default is false.
   # @return [true,false]
   attr_reader :keep_blank_rows
-  
+
   # Form data to POST in the download request. It should probably be in +application/x-www-form-urlencoded+.
   # @return [String]
   attr_reader :form_data
-  
+
   # How many rows to skip at the beginning of the file or table. Default is 0.
   # @return [Integer]
   attr_reader :skip
@@ -209,15 +209,15 @@ class RemoteTable
   # The original encoding of the source file. Default is UTF-8. Previously passed as +:encoding+.
   # @return [String]
   attr_reader :internal_encoding
-  
+
   # The delimiter, a.k.a. column separator. Passed to Ruby CSV as +:col_sep+. Default is :delimited.
   # @return [String]
   attr_reader :delimiter
-  
+
   # The XPath used to find rows in HTML or XML.
   # @return [String]
   attr_reader :row_xpath
-  
+
   # The XPath used to find columns in HTML or XML.
   # @return [String]
   attr_reader :column_xpath
@@ -225,11 +225,11 @@ class RemoteTable
   # The CSS selector used to find rows in HTML or XML.
   # @return [String]
   attr_reader :row_css
-  
+
   # The CSS selector used to find columns in HTML or XML.
   # @return [String]
   attr_reader :column_css
-  
+
   # The format of the source file. Can be +:xlsx+, +:xls+, +:delimited+, +:ods+, +:fixed_width+, +:html+, +:xml+, +:yaml+.
   # @return [Symbol]
   attr_reader :format
@@ -241,7 +241,7 @@ class RemoteTable
   # The packing type. Guessed from URL if not provided. Only +:tar+ is supported.
   # @return [Symbol]
   attr_reader :packing
-  
+
   # The glob used to pick a file out of an archive.
   #
   # @return [String]
@@ -249,7 +249,7 @@ class RemoteTable
   # @example Pick out the only CSV in a ZIP file
   #   RemoteTable.new 'http://www.fueleconomy.gov/FEG/epadata/08data.zip', :glob => '/*.csv'
   attr_reader :glob
-  
+
   # The filename, which can be used to pick a file out of an archive.
   #
   # @return [String]
@@ -267,7 +267,7 @@ class RemoteTable
   #   # ALMOST
   #   RemoteTable.new 'file:///atoz.txt', :cut => '1,12,13,15,19,20'
   attr_reader :cut
-  
+
   # Use a range of rows in a plaintext file.
   #
   # @return [Range]
@@ -278,7 +278,7 @@ class RemoteTable
   #                   :select => proc { |row| CbecsEnergyIntensity::NAICS_CODE_SYNTHESIZER.call(row) },
   #                   :crop => (21..37))
   attr_reader :crop
-  
+
   # The fixed-width schema, given as a multi-dimensional array.
   #
   # @return [Array<Array{String,Integer,Hash}>]
@@ -293,15 +293,15 @@ class RemoteTable
   #                                [  'spacer',  12 ],
   #                                [  'header6', 10, { :type => :string } ]])
   attr_reader :schema
-  
+
   # If you somehow already defined a fixed-width schema (so you can re-use it?), specify it here.
   # @return [String,Symbol]
   attr_reader :schema_name
-  
+
   # A proc that decides whether to include a row. Previously passed as +:select+.
   # @return [Proc]
   attr_reader :pre_select
-  
+
   # A proc that decides whether to include a row. Previously passed as +:reject+.
   # @return [Proc]
   attr_reader :pre_reject
@@ -309,14 +309,14 @@ class RemoteTable
   # Settings to create a transformer.
   # @return [Hash]
   attr_reader :transform_settings
-  
-  # A hash of settings to initialize an Errata instance to be used on every row. Previously passed as +:errata+.
+
+  # A hash to initialize an Errata instance to be used on every row. Applied after creating +row_hash+ and before passing to +:synthesize+ procs, etc. Previously passed as +:errata+.
   #
   # See the Errata library at https://github.com/seamusabshere/errata
   #
   # @return [Hash]
   attr_reader :errata_settings
-  
+
   # The format of the source file. Can be specified as: :xlsx, :xls, :delimited (aka :csv), :ods, :fixed_width, :html, :xml, :yaml
   #
   # Note: treats all +docs.google.com+ and +spreadsheets.google.com+ URLs as +:delimited+.
@@ -332,6 +332,8 @@ class RemoteTable
 
   # Create a new RemoteTable, which is an Enumerable.
   #
+  # Options are set at creation using any of the attributes listed... RDoc will say they're "read-only" because you can't set/change them after creation.
+  #
   # Does not immediately download/parse... it's lazy-loading.
   #
   # @overload initialize(settings)
@@ -402,7 +404,7 @@ class RemoteTable
     @errata_settings = grab settings, :errata_settings
 
     @other_options = settings
-    
+
     @transformer = Transformer.new self
     @local_copy = LocalCopy.new self
   end
@@ -445,7 +447,7 @@ class RemoteTable
 
   # @deprecated
   alias :each_row :each
-  
+
   # @return [Array<Hash,Array>] All rows.
   def to_a
     if fully_cached?
@@ -457,7 +459,7 @@ class RemoteTable
 
   # @deprecated
   alias :rows :to_a
-  
+
   # Get a row by row number. Zero-based.
   #
   # @return [Hash,Array]
@@ -468,7 +470,7 @@ class RemoteTable
       to_a[row_number]
     end
   end
-  
+
   # Clear the row cache in case it helps your GC.
   #
   # @return [nil]
@@ -494,7 +496,7 @@ class RemoteTable
   end
 
   private
-  
+
   def mark_download!
     @download_count_mutex.synchronize do
       @download_count += 1
@@ -502,12 +504,12 @@ class RemoteTable
     if warn_on_multiple_downloads and download_count > 1
       ::Kernel.warn "[remote_table] #{url} has been downloaded #{download_count} times."
     end
-  end 
-  
+  end
+
   def fully_cached!
     @fully_cached = true
   end
-  
+
   def fully_cached?
     !!@fully_cached
   end

data/lib/remote_table/processed_by_roo.rb

@@ -6,27 +6,25 @@ class RemoteTable
 
     # Yield each row using Roo.
     def _each
-      # sometimes Roo forgets to require iconv.
-      require 'iconv'
       require 'roo'
 
       spreadsheet = roo_class.new local_copy.path, nil, :ignore
       if sheet
         spreadsheet.default_sheet = sheet
       end
-      
+
       first_row = if crop
         crop.first + 1
       else
         skip + 1
       end
-        
+
       last_row = if crop
         crop.last
       else
         spreadsheet.last_row
       end
-      
+
       if not headers
 
         # create an array to represent this row
@@ -48,7 +46,7 @@ class RemoteTable
         end
 
       else
-        
+
         # create a hash to represent this row
         current_headers = ::ActiveSupport::OrderedHash.new
         if headers == :first_row

data/lib/remote_table/version.rb

@@ -1,3 +1,3 @@
 class RemoteTable
-  VERSION = "2.1.1"
+  VERSION = "2.1.2"
 end

data/remote_table.gemspec

@@ -16,9 +16,9 @@ Gem::Specification.new do |s|
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
   s.require_paths = ["lib"]
-  
+
   s.add_runtime_dependency 'activesupport', '>=2.3.4'
-  s.add_runtime_dependency 'roo', '>= 1.10.3'
+  s.add_runtime_dependency 'roo', '>= 1.11'
   s.add_runtime_dependency 'fixed_width-multibyte', '>=0.2.3'
   s.add_runtime_dependency 'i18n' # activesupport?
   s.add_runtime_dependency 'unix_utils', '>=0.0.8'

data/test/test_remote_table.rb

@@ -165,4 +165,33 @@ describe RemoteTable do
     t = RemoteTable.new :url => 'http://www.fueleconomy.gov/FEG/epadata/00data.zip', :filename => 'G6080900.xls', :format => nil
     t[0]['Class'].must_equal 'TWO SEATERS'
   end
+
+  {
+    'foo.ods' => :ods,
+    'foo.open_office' => :ods,
+    'foo.xlsx' => :xlsx,
+    'foo.excelx' => :xlsx,
+    'foo.xls' => :xls,
+    'foo.excel' => :xls,
+    'foo.csv' => :delimited,
+    'foo.tsv' => :delimited,
+    'foo.delimited' => :delimited,
+    'foo.fixed_width' => :fixed_width,
+    'foo.htm' => :html,
+    'foo.html' => :html,
+    'foo.xml' => :xml,
+    'foo.yaml' => :yaml,
+    'foo.yml' => :yaml,
+    'foo.shp' => :shp
+  }.each do |basename, format|
+    it "detects the #{format} format from the filename #{basename}" do
+      RemoteTable.guess_format(basename).must_equal format
+    end
+  end
+
+  it "detects the correct extension name without confusion from basename" do
+    [ 'foo.xls', 'xlsx.xls', 'foo_xls' ].each do |basename|
+      RemoteTable.guess_format(basename).must_equal :xls
+    end
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: remote_table
 version: !ruby/object:Gem::Version
-  version: 2.1.1
+  version: 2.1.2
 platform: ruby
 authors:
 - Seamus Abshere
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-03-25 00:00:00.000000000 Z
+date: 2013-10-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -31,14 +31,14 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 1.10.3
+        version: '1.11'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 1.10.3
+        version: '1.11'
 - !ruby/object:Gem::Dependency
   name: fixed_width-multibyte
   requirement: !ruby/object:Gem::Requirement
@@ -283,7 +283,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: remotetable
-rubygems_version: 2.0.3
+rubygems_version: 2.1.5
 signing_key: 
 specification_version: 4
 summary: Open Google Docs spreadsheets, local or remote XLSX, XLS, ODS, CSV (comma