[GR-64899] Fix binary Regexp compilation to TRegex

PullRequest: truffleruby/4530

Author: eregon

CHANGELOG.md

@@ -23,6 +23,7 @@ Compatibility:
 
 Performance:
 
+* Use TRegex for binary Regexps with non-US-ASCII characters in the pattern like `/[\x80-\xff]/n` (#3858, @eregon).
 
 Changes:
 

spec/ruby/core/regexp/linear_time_spec.rb

@@ -7,6 +7,10 @@
       Regexp.linear_time?('a').should == true
     end
 
+    it "returns true if matching can be done in linear time for a binary Regexp" do
+      Regexp.linear_time?(/[\x80-\xff]/n).should == true
+    end
+
     it "return false if matching can't be done in linear time" do
       Regexp.linear_time?(/(a)\1/).should == false
       Regexp.linear_time?("(a)\\1").should == false

src/main/java/org/truffleruby/core/regexp/TRegexCache.java

@@ -9,8 +9,6 @@
  */
 package org.truffleruby.core.regexp;
 
-import java.nio.charset.UnsupportedCharsetException;
-
 import com.oracle.truffle.api.CompilerDirectives;
 import com.oracle.truffle.api.CompilerDirectives.TruffleBoundary;
 import com.oracle.truffle.api.interop.InteropLibrary;
@@ -139,6 +137,11 @@ public static String toTRegexEncoding(RubyEncoding encoding) {
 
     @TruffleBoundary
     private static Object compileTRegex(RubyContext context, RubyRegexp regexp, boolean atStart, RubyEncoding enc) {
+        String tRegexEncoding = TRegexCache.toTRegexEncoding(enc);
+        if (tRegexEncoding == null) {
+            return null;
+        }
+
         String processedRegexpSource;
         RubyEncoding[] fixedEnc = new RubyEncoding[]{ null };
         final TStringBuilder tstringBuilder;
@@ -155,21 +158,16 @@ private static Object compileTRegex(RubyContext context, RubyRegexp regexp, bool
         var tstring = tstringBuilder.toTString();
         try {
             processedRegexpSource = TStringUtils.toJavaStringOrThrow(tstring, tstringBuilder.getRubyEncoding());
-        } catch (CannotConvertBinaryRubyStringToJavaString | UnsupportedCharsetException e) {
-            // Some strings cannot be converted to Java strings, e.g. strings with the
-            // BINARY encoding containing characters higher than 127.
-            // Also, some charsets might not be supported on the JVM and therefore
-            // a conversion to j.l.String might be impossible.
-            return null;
+        } catch (CannotConvertBinaryRubyStringToJavaString e) {
+            // A BINARY regexp with non-US-ASCII bytes, pass it as "raw bytes" instead.
+            // TRegex knows how to interpret those bytes correctly as we pass the encoding name as well.
+            var latin1string = tstring.forceEncodingUncached(Encodings.BINARY.tencoding,
+                    Encodings.ISO_8859_1.tencoding);
+            processedRegexpSource = TStringUtils.toJavaStringOrThrow(latin1string, Encodings.ISO_8859_1);
         }
 
         String flags = optionsToFlags(regexp.options, atStart);
 
-        String tRegexEncoding = TRegexCache.toTRegexEncoding(enc);
-        if (tRegexEncoding == null) {
-            return null;
-        }
-
         String ignoreAtomicGroups = context.getOptions().TRUFFLE_REGEX_IGNORE_ATOMIC_GROUPS
                 ? ",IgnoreAtomicGroups=true"
                 : "";