Merge pull request #28 from Earlopain/invalid-encoding-stuff

Handle invalid encoded strings

lib/unicode/display_width.rb

@@ -47,7 +47,14 @@ class DisplayWidth
 
     # Returns monospace display width of string
     def self.of(string, ambiguous = nil, overwrite = nil, old_options = {}, **options)
-      string = string.encode(Encoding::UTF_8) unless string.encoding == Encoding::UTF_8
+      # Binary strings don't make much sense when calculating display width.
+      # Assume it's valid UTF-8
+      if string.encoding == Encoding::BINARY && !string.force_encoding(Encoding::UTF_8).valid_encoding?
+        # Didn't work out, go back to binary
+        string.force_encoding(Encoding::BINARY)
+      end
+
+      string = string.encode(Encoding::UTF_8, invalid: :replace, undef: :replace) unless string.encoding == Encoding::UTF_8
       options = normalize_options(string, ambiguous, overwrite, old_options, **options)
 
       width = 0
@@ -236,4 +243,3 @@ def of(string, **kwargs)
     end
   end
 end
-

spec/display_width_spec.rb

@@ -183,6 +183,17 @@
     it 'works with non-utf8 Unicode encodings' do
       expect( 'À'.encode("UTF-16LE").display_width ).to eq 1
     end
+
+    it 'works with a string that is invalid in its encoding' do
+      s = "\x81\x39".dup.force_encoding(Encoding::SHIFT_JIS)
+
+      # Would print as �9 on the terminal
+      expect( s.display_width ).to eq 2
+    end
+
+    it 'works with a binary encoded string that is valid in UTF-8' do
+      expect( '€'.b.display_width ).to eq 1
+    end
   end
 
   describe '[emoji]' do