JS: Skip files with unsupported file encoding

Author: asgerf

javascript/extractor/src/com/semmle/js/extractor/FileExtractor.java

@@ -5,7 +5,7 @@
 import java.io.FileInputStream;
 import java.io.FileReader;
 import java.io.IOException;
-import java.nio.charset.Charset;
+import java.nio.charset.CharacterCodingException;
 import java.nio.charset.StandardCharsets;
 import java.nio.file.Path;
 import java.util.LinkedHashSet;
@@ -17,6 +17,7 @@
 import com.semmle.js.extractor.trapcache.ITrapCache;
 import com.semmle.util.data.StringUtil;
 import com.semmle.util.exception.Exceptions;
+import com.semmle.util.exception.ResourceError;
 import com.semmle.util.extraction.ExtractorOutputConfig;
 import com.semmle.util.files.FileUtil;
 import com.semmle.util.io.WholeIO;
@@ -438,7 +439,16 @@ public Integer extract(File f, ExtractorState state) throws IOException {
     }
 
     // populate source archive
-    String source = new WholeIO(config.getDefaultEncoding()).strictread(f);
+    WholeIO wholeIO = new WholeIO(config.getDefaultEncoding(), true);
+    String source = wholeIO.read(f);
+    if (source == null) {
+      if (wholeIO.getLastException() instanceof CharacterCodingException) {
+        System.err.println("Skipped due to unsupported character encoding: " + f);
+        return 0;
+      } else {
+        throw new ResourceError("Failed to read file " + f, wholeIO.getLastException());
+      }
+    }
     outputConfig.getSourceArchive().add(f, source);
 
     // extract language-independent bits