Merge pull request #20 from scpike/extra-magic-overlays

Handle .docx, .xlsx, and .pptx with extra magic

README.md

@@ -15,6 +15,17 @@ Usage
     MimeMagic.by_magic(File.open('test.html'))
     # etc...
 
+Extra magic overlay
+=====
+
+Microsoft Office 2007+ formats (xlsx, docx, and pptx) are not supported by the mime database at freedesktop.org. These files are all zipped collections of xml files and will be detected as "application/zip". Mimemagic comes with extra magic you can overlay on top of the defaults to correctly detect these file types. Enable it like this:
+
+    require 'mimemagic'
+    require 'mimemagic/overlay'
+    MimeMagic.by_magic(File.open('test.xlsx'))
+
+You can add your own magic with `MimeMagic.add`. See `lib/mimemagic/overlay.rb`.
+
 API
 ===
 

lib/mimemagic/overlay.rb

+# Extra magic
+
+[['application/vnd.openxmlformats-officedocument.presentationml.presentation', [[0..2000, 'ppt/']]],
+ ['application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', [[0..2000, 'xl/']]],
+ ['application/vnd.openxmlformats-officedocument.wordprocessingml.document', [[0..2000, 'word/']]]].each do |magic|
+  MimeMagic.add(magic[0], magic: magic[1])
+end

test/mimemagic_test.rb

@@ -50,9 +50,16 @@ describe 'MimeMagic' do
     MimeMagic.by_path('').should.equal nil
   end
 
+  it 'should recognize xlsx as zip without magic' do
+    file = "test/files/application.vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    MimeMagic.by_magic(File.read(file)).should.equal "application/zip"
+    MimeMagic.by_magic(File.open(file, 'rb')).should.equal "application/zip"
+  end
+
   it 'should recognize by magic' do
+    require "mimemagic/overlay"
     Dir['test/files/*'].each do |file|
-      mime = file[11..-1].gsub('.', '/')
+      mime = file[11..-1].sub('.', '/')
       MimeMagic.by_magic(File.read(file)).should.equal mime
       MimeMagic.by_magic(File.open(file, 'rb')).should.equal mime
     end