Add option to ActiveStorage::Blob to set extract_content_type_from_io

This adds a boolean argument called identify to ActiveStorage::Blob
methods #create_after_upload, #build_after_upload and #upload. It
allows a user to bypass the automatic content_type inference from
the io.

activestorage/CHANGELOG.md

@@ -1,3 +1,18 @@
+*   Pass in `identify: false` as an argument when providing a `content_type` for
+    `ActiveStorage::Attached::{One,Many}#attach` to bypass automatic content
+    type inference. For example:
+
+    ```ruby
+      @message.image.attach(
+        io: File.open('/path/to/file'),
+        filename: 'file.pdf',
+        content_type: 'application/pdf',
+        identify: false
+      )
+    ```
+
+    *Ryan Davidson*
+
 *   The Google Cloud Storage service properly supports streaming downloads.
     It now requires version 1.11 or newer of the google-cloud-storage gem.
 

activestorage/app/models/active_storage/blob.rb

@@ -44,21 +44,23 @@ class ActiveStorage::Blob < ActiveRecord::Base
     end
 
     # Returns a new, unsaved blob instance after the +io+ has been uploaded to the service.
-    def build_after_upload(io:, filename:, content_type: nil, metadata: nil)
+    # When providing a content type, pass <tt>identify: false</tt> to bypass automatic content type inference.
+    def build_after_upload(io:, filename:, content_type: nil, metadata: nil, identify: true)
       new.tap do |blob|
         blob.filename     = filename
         blob.content_type = content_type
         blob.metadata     = metadata
 
-        blob.upload io
+        blob.upload(io, identify: identify)
       end
     end
 
     # Returns a saved blob instance after the +io+ has been uploaded to the service. Note, the blob is first built,
     # then the +io+ is uploaded, then the blob is saved. This is done this way to avoid uploading (which may take
     # time), while having an open database transaction.
-    def create_after_upload!(io:, filename:, content_type: nil, metadata: nil)
+    # When providing a content type, pass <tt>identify: false</tt> to bypass automatic content type inference.
-      build_after_upload(io: io, filename: filename, content_type: content_type, metadata: metadata).tap(&:save!)
+    def create_after_upload!(io:, filename:, content_type: nil, metadata: nil, identify: true)
+      build_after_upload(io: io, filename: filename, content_type: content_type, metadata: metadata, identify: identify).tap(&:save!)
     end
 
     # Returns a saved blob _without_ uploading a file to the service. This blob will point to a key where there is
@@ -142,13 +144,14 @@ class ActiveStorage::Blob < ActiveRecord::Base
   #
   # Prior to uploading, we compute the checksum, which is sent to the service for transit integrity validation. If the
   # checksum does not match what the service receives, an exception will be raised. We also measure the size of the +io+
-  # and store that in +byte_size+ on the blob record.
+  # and store that in +byte_size+ on the blob record. The content type is automatically extracted from the +io+ unless
+  # you specify a +content_type+ and pass +identify+ as false.
   #
   # Normally, you do not have to call this method directly at all. Use the factory class methods of +build_after_upload+
   # and +create_after_upload!+.
-  def upload(io)
+  def upload(io, identify: true)
     self.checksum     = compute_checksum_in_chunks(io)
-    self.content_type = extract_content_type(io)
+    self.content_type = extract_content_type(io) if content_type.nil? || identify
     self.byte_size    = io.size
     self.identified   = true
 

activestorage/test/models/blob_test.rb

@@ -43,6 +43,16 @@ class ActiveStorage::BlobTest < ActiveSupport::TestCase
     assert_equal "text/plain", blob.content_type
   end
 
+  test "create after upload extracts content_type from io when no content_type given and identify: false" do
+    blob = create_blob content_type: nil, identify: false
+    assert_equal "text/plain", blob.content_type
+  end
+
+  test "create after upload uses content_type when identify: false" do
+    blob = create_blob data: "Article,dates,analysis\n1, 2, 3", filename: "table.csv", content_type: "text/csv", identify: false
+    assert_equal "text/csv", blob.content_type
+  end
+
   test "image?" do
     blob = create_file_blob filename: "racecar.jpg"
     assert_predicate blob, :image?

activestorage/test/test_helper.rb

@@ -50,8 +50,8 @@ class ActiveSupport::TestCase
   end
 
   private
-    def create_blob(data: "Hello world!", filename: "hello.txt", content_type: "text/plain")
+    def create_blob(data: "Hello world!", filename: "hello.txt", content_type: "text/plain", identify: true)
-      ActiveStorage::Blob.create_after_upload! io: StringIO.new(data), filename: filename, content_type: content_type
+      ActiveStorage::Blob.create_after_upload! io: StringIO.new(data), filename: filename, content_type: content_type, identify: identify
     end
 
     def create_file_blob(filename: "racecar.jpg", content_type: "image/jpeg", metadata: nil)

guides/source/active_storage_overview.md

@@ -319,6 +319,18 @@ type you provide if it can’t do that.
 @message.image.attach(io: File.open('/path/to/file'), filename: 'file.pdf', content_type: 'application/pdf')
 ```
 
+You can bypass the content type inference from the data by passing in
+`identify: false` along with the `content_type`.
+
+```ruby
+@message.image.attach(
+  io: File.open('/path/to/file'),
+  filename: 'file.pdf',
+  content_type: 'application/pdf'
+  identify: false
+)
+```
+
 If you don’t provide a content type and Active Storage can’t determine the
 file’s content type automatically, it defaults to application/octet-stream.