aws-s3 0.1.2 → 0.2.0

data/INSTALL

@@ -38,4 +38,8 @@ If your system has the Ruby libxml bindings installed (http://libxml.rubyforge.o
 
 === XML generation
 
-AWS::S3 also depends on the Builder library (http://builder.rubyforge.org/ and http://rubyforge.org/projects/builder/). This will also automatically be installed for you when using Rubygems.
+AWS::S3 also depends on the Builder library (http://builder.rubyforge.org/ and http://rubyforge.org/projects/builder/). This will also automatically be installed for you when using Rubygems.
+
+=== Content type inference
+
+AWS::S3 depends on the MIME::Types library (http://mime-types.rubyforge.org/) to infer the content type of an object that does not explicitly specify it. This library will automatically be installed for you when using Rubygems.

data/README

@@ -96,12 +96,9 @@ To add an object to a bucket you specify the name of the object, its value, and
   S3Object.store(
     file, 
     File.open(file), 
-    'jukebox', 
-    :content_type => 'audio/mpeg'
+    'jukebox'
   )
 
-Though strictly not required, you should specify the content type of the file so that when you go to download it your browser will know how to handle the file.
-
 You'll see your file has been added to it:
 
   music_bucket.objects
@@ -135,8 +132,20 @@ You can store an object on S3 by specifying a key, its data and the name of the
   S3Object.store(
     'headshot.jpg', 
     File.open('headshot.jpg'), 
-    'photos', 
-    :content_type => 'image/jpg'
+    'photos'
+  )
+
+The content type of the object will be infered by its extension. If the appropriate content type can not be infered, S3 defaults
+to <tt>binary/octect-stream</tt>.
+
+If you want to override this, you can explicitly indicate what content type the object should have with the <tt>:content_type</tt> option:
+
+  file = 'black-flowers.m4a'
+  S3Object.store(
+    file,
+    File.open(file),
+    'jukebox',
+    :content_type => 'audio/mp4a-latm'
   )
 
 You can read more about storing files on S3 in the documentation for S3Object.store.
@@ -188,7 +197,7 @@ You can find out the content type of your object with the <tt>content_type</tt>
 
 You can change the content type as well if you like:
 
-  song.content_type = 'application/octet-stream'
+  song.content_type = 'application/pdf'
   song.store
 
 (Keep in mind that due to limitiations in S3's exposed API, the only way to change things like the content_type
@@ -240,14 +249,12 @@ may be desirable for very large files so they are not read into memory all at on
   # Non streamed upload
   S3Object.store('simple-text-file.txt', 
                  'hello world!', 
-                 'marcel', 
-                 :content_type => 'text/plain')
+                 'marcel')
 
   # Streamed upload
   S3Object.store('roots.mpeg', 
                  File.open('roots.mpeg'), 
-                 'marcel', 
-                 :content_type => 'audio/mpeg')
+                 'marcel')
 
 
 == Setting the current bucket
@@ -265,8 +272,7 @@ For all methods that take a bucket name as an argument, the current bucket will
   other_song = '/Users/marcel/baby-please-come-home.mp3'
   JukeBoxSong.store(
     File.basename(other_song), 
-    File.open(other_song), 
-    :content_type => 'audio/mpeg'
+    File.open(other_song)
   )
 
 This time we didn't have to explicitly pass in the bucket name, as the JukeBoxSong class knows that it will
@@ -327,7 +333,7 @@ You can set a canned access level when you create a bucket or an object by using
     'kiss.jpg', 
     data, 
     'marcel', 
-    :content_type => 'image/jpg', :access => :public_read
+    :access => :public_read
   )
 
 Since the image we created is publicly readable, we can access it directly from a browser by going to the corresponding bucket name 

data/Rakefile

@@ -74,6 +74,7 @@ namespace :dist do
     
     s.add_dependency 'xml-simple'
     s.add_dependency 'builder'
+    s.add_dependency 'mime-types'
     s.rdoc_options  = ['--title', "AWS::S3 -- Support for Amazon S3's REST api",
                        '--main',  'README',
                        '--line-numbers', '--inline-source']

data/lib/aws/s3.rb

@@ -10,6 +10,7 @@ require 'date'
 $:.unshift(File.dirname(__FILE__))
 require 's3/extensions'
 require_library_or_gem 'builder' unless defined? Builder
+require_library_or_gem 'mime/types' unless defined? MIME::Types
 
 require 's3/base'
 require 's3/version'
@@ -42,12 +43,8 @@ AWS::S3::S3Object.class_eval do
 end
 
 require_library_or_gem 'xmlsimple' unless defined? XmlSimple
-# XmlSimple is a very convenient way of dealing with the xml needs of this library, but unfortunately
-# it is powered by REXML which is both very slow (even for me who does not privilege performance)
-# and consumes way too much memory (beach balls a MacBookPro with 2GB of memory for 2 minutes while parsing 60KB of xml).
-#
-# So, if libxml is installed, we use the FasterXmlSimple library, that provides most of the functionality of XmlSimple
-# except it uses the xml/libxml library for xml parsing. If libxml isn't installed, we just fall back on
+# If libxml is installed, we use the FasterXmlSimple library, that provides most of the functionality of XmlSimple
+# except it uses the xml/libxml library for xml parsing (rather than REXML). If libxml isn't installed, we just fall back on
 # XmlSimple.
 AWS::S3::Parsing.parser =
   begin

data/lib/aws/s3/acl.rb

@@ -16,7 +16,7 @@ module AWS
     #     'kiss.jpg', 
     #     data, 
     #     'marcel', 
-    #     :content_type => 'image/jpg', :access => :public_read
+    #     :access => :public_read
     #   )
     # 
     # Since the image we created is publicly readable, we can access it directly from a browser by going to the corresponding bucket name 

data/lib/aws/s3/base.rb

@@ -114,8 +114,7 @@ module AWS #:nodoc:
         #   other_song = '/Users/marcel/baby-please-come-home.mp3'
         #   JukeBoxSong.store(
         #     File.basename(other_song), 
-        #     File.open(other_song), 
-        #     :content_type => 'audio/mpeg'
+        #     File.open(other_song)
         #   )
         # 
         # This time we didn't have to explicitly pass in the bucket name, as the JukeBoxSong class knows that it will

data/lib/aws/s3/bucket.rb

@@ -38,12 +38,9 @@ module AWS
     #   S3Object.store(
     #     file, 
     #     File.open(file), 
-    #     'jukebox', 
-    #     :content_type => 'audio/mpeg'
+    #     'jukebox'
     #   )
-    # 
-    # Though strictly not required, you should specify the content type of the file so that when you go to download it your browser will know how to handle the file.
-    # 
+    #
     # You'll see your file has been added to it:
     # 
     #   music_bucket.objects

data/lib/aws/s3/object.rb

@@ -8,8 +8,20 @@ module AWS
     #   S3Object.store(
     #     'headshot.jpg', 
     #     File.open('headshot.jpg'), 
-    #     'photos', 
-    #     :content_type => 'image/jpg'
+    #     'photos'
+    #   )
+    #
+    # The content type of the object will be infered by its extension. If the appropriate content type can not be infered, S3 defaults
+    # to <tt>binary/octect-stream</tt>.
+    #
+    # If you want to override this, you can explicitly indicate what content type the object should have with the <tt>:content_type</tt> option:
+    # 
+    #   file = 'black-flowers.m4a'
+    #   S3Object.store(
+    #     file,
+    #     File.open(file),
+    #     'jukebox',
+    #     :content_type => 'audio/mp4a-latm'
     #   )
     #
     # You can read more about storing files on S3 in the documentation for S3Object.store.
@@ -61,7 +73,7 @@ module AWS
     # 
     # You can change the content type as well if you like:
     # 
-    #   song.content_type = 'application/octet-stream'
+    #   song.content_type = 'application/pdf'
     #   song.store
     # 
     # (Keep in mind that due to limitiations in S3's exposed API, the only way to change things like the content_type
@@ -197,17 +209,19 @@ module AWS
         #   # Non streamed upload
         #   S3Object.store('simple-text-file.txt', 
         #                  'hello world!', 
-        #                  'marcel', 
-        #                  :content_type => 'text/plain')
+        #                  'marcel')
         #
         #   # Streamed upload
         #   S3Object.store('roots.mpeg', 
         #                  File.open('roots.mpeg'), 
-        #                  'marcel', 
-        #                  :content_type => 'audio/mpeg')
+        #                  'marcel')
         def store(key, data, bucket = nil, options = {})
           validate_key!(key)
-          put(path!(bucket, key, options), options, data) # Don't call .success? on response. We want to get the etag.
+          # Must build path before infering content type in case bucket is being used for options
+          path = path!(bucket, key, options)
+          infer_content_type!(key, options)
+          
+          put(path, options, data) # Don't call .success? on response. We want to get the etag.
         end
         alias_method :create, :store
         alias_method :save,   :store
@@ -259,12 +273,19 @@ module AWS
           end
           '/' << File.join(bucket_name(bucket), name)
         end
-        
+    
         private
           
           def validate_key!(key)
             raise InvalidKeyName.new(key) unless key && key.size <= 1024
           end
+          
+          def infer_content_type!(key, options)
+            return if options.has_key?(:content_type)
+            if mime_type = MIME::Types.type_for(key).first
+              options[:content_type] = mime_type.content_type
+            end
+          end
       end
       
       class Value < String #:nodoc:

data/lib/aws/s3/version.rb

@@ -2,9 +2,9 @@ module AWS
   module S3
     module VERSION #:nodoc:
       MAJOR    = '0'
-      MINOR    = '1'
-      TINY     = '2' 
-      BETA     =  nil # Time.now.to_i.to_s
+      MINOR    = '2'
+      TINY     = '0' 
+      BETA     = nil # Time.now.to_i.to_s
     end
     
     Version = [VERSION::MAJOR, VERSION::MINOR, VERSION::TINY, VERSION::BETA].compact * '.'

data/test/object_test.rb

@@ -40,6 +40,22 @@ class ObjectTest < Test::Unit::TestCase
     end
   end
   
+  def test_content_type_inference
+    [
+      ['foo.jpg',  {},                             'image/jpeg'],
+      ['foo.txt',  {},                             'text/plain'],
+      ['foo',      {},                             nil],
+      ['foo.asdf', {},                             nil],
+      ['foo.jpg',  {:content_type => nil},         nil],
+      ['foo',      {:content_type => 'image/jpg'}, 'image/jpg'],
+      ['foo.jpg',  {:content_type => 'image/png'}, 'image/png'],
+      ['foo.asdf', {:content_type => 'image/jpg'}, 'image/jpg']
+    ].each do |key, options, content_type|
+      S3Object.send(:infer_content_type!, key, options)
+      assert_equal content_type, options[:content_type]
+    end
+  end
+  
   def test_object_has_owner
     assert_kind_of Owner, @object.owner 
   end

data/test/remote/object_test.rb

@@ -264,4 +264,31 @@ class RemoteS3ObjectTest < Test::Unit::TestCase
       object.delete
     end
   end
+    
+  def test_content_type_inference
+    # Confirm appropriate content type is infered when not specified
+
+    content_type_objects = {'foo.jpg' => 'image/jpeg', 'no-extension-specified' => 'binary/octet-stream', 'foo.txt' => 'text/plain'}
+    content_type_objects.each_key  do |key|
+      S3Object.store(key, 'fake data', TEST_BUCKET) # No content type explicitly set
+    end
+
+    content_type_objects.each do |key, content_type|
+      assert_equal content_type, S3Object.about(key, TEST_BUCKET)['content-type']
+    end
+    
+    # Confirm we can update the content type
+    
+    assert_nothing_raised do
+      object = S3Object.find('no-extension-specified', TEST_BUCKET)
+      object.content_type = 'application/pdf'
+      object.store
+    end
+    
+    assert_equal 'application/pdf', S3Object.about('no-extension-specified', TEST_BUCKET)['content-type']
+    
+  ensure
+    # Get rid of objects we just created
+    content_type_objects.each_key {|key| S3Object.delete(key, TEST_BUCKET) }
+  end
 end

metadata

@@ -3,7 +3,7 @@ rubygems_version: 0.9.0
 specification_version: 1
 name: aws-s3
 version: !ruby/object:Gem::Version 
-  version: 0.1.2
+  version: 0.2.0
 date: 2006-11-30 00:00:00 -06:00
 summary: Client library for Amazon's Simple Storage Service's REST API
 require_paths: 
@@ -123,3 +123,12 @@ dependencies:
       - !ruby/object:Gem::Version 
         version: 0.0.0
     version: 
+- !ruby/object:Gem::Dependency 
+  name: mime-types
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Version::Requirement 
+    requirements: 
+    - - ">"
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
+    version: