Merge pull request #669 from BMorearty/ignore-invalid-byte-sequences

Ignore invalid byte sequences

CHANGELOG.md

@@ -11,6 +11,7 @@ unreleased
 
 * (breaking) Stop handling string filters as regular expressions, use the dedicated regex filter if you need that behaviour. See [#616](https://github.com/colszowka/simplecov/pull/616) (thanks @yujinakayama)
 * Avoid overwriting the last coverage results on unsuccessful test runs. See [#625](https://github.com/colszowka/simplecov/pull/625) (thanks @thomas07vt)
+* Don't crash on invalid UTF-8 byte sequences.
 
 0.15.1 (2017-09-11) ([changes](https://github.com/colszowka/simplecov/compare/v0.15.0...v0.15.1))
 =======

lib/simplecov/lines_classifier.rb

@@ -16,14 +16,28 @@ def self.no_cov_line
       /^(\s*)#(\s*)(\:#{SimpleCov.nocov_token}\:)/o
     end
 
+    def self.no_cov_line?(line)
+      line =~ no_cov_line
+    rescue ArgumentError
+      # E.g., line contains an invalid byte sequence in UTF-8
+      false
+    end
+
+    def self.whitespace_line?(line)
+      line =~ WHITESPACE_OR_COMMENT_LINE
+    rescue ArgumentError
+      # E.g., line contains an invalid byte sequence in UTF-8
+      false
+    end
+
     def classify(lines)
       skipping = false
 
       lines.map do |line|
-        if line =~ self.class.no_cov_line
+        if self.class.no_cov_line?(line)
           skipping = !skipping
           NOT_RELEVANT
-        elsif skipping || line =~ WHITESPACE_OR_COMMENT_LINE
+        elsif skipping || self.class.whitespace_line?(line)
           NOT_RELEVANT
         else
           RELEVANT

lib/simplecov/source_file.rb

@@ -182,7 +182,7 @@ def process_skipped_lines(lines)
       skipping = false
 
       lines.each do |line|
-        if line.src =~ SimpleCov::LinesClassifier.no_cov_line
+        if SimpleCov::LinesClassifier.no_cov_line?(line.src)
           skipping = !skipping
           line.skipped!
         elsif skipping

spec/lines_classifier_spec.rb

@@ -20,6 +20,15 @@
         expect(classified_lines.length).to eq 7
         expect(classified_lines).to all be_relevant
       end
+
+      it "determines invalid UTF-8 byte sequences as relevant" do
+        classified_lines = subject.classify [
+          "bytes = \"\xF1t\xEBrn\xE2ti\xF4n\xE0liz\xE6ti\xF8n\"",
+        ]
+
+        expect(classified_lines.length).to eq 1
+        expect(classified_lines).to all be_relevant
+      end
     end
 
     describe "not-relevant lines" do