-
-
Save enebo/76886a06f38b18d54c24ed93d273ade7 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
diff --git a/core/src/main/java/org/jruby/RubyString.java b/core/src/main/java/org/jruby/RubyString.java | |
index a1a06fefba..deb9ccd27d 100644 | |
--- a/core/src/main/java/org/jruby/RubyString.java | |
+++ b/core/src/main/java/org/jruby/RubyString.java | |
@@ -3208,7 +3208,7 @@ public class RubyString extends RubyObject implements CharSequence, EncodingCapa | |
final int patternLen = pattern.size(); | |
final Encoding patternEnc = this.checkEncoding(pattern); | |
- int beg = StringSupport.index(this, pattern, 0, patternEnc); | |
+ int beg = StringSupport.index(getByteList(), pattern.getByteList(), 0, patternEnc); | |
int begz; | |
if (beg < 0) { | |
if (useBackref) context.setBackRef(context.nil); | |
@@ -3258,7 +3258,7 @@ public class RubyString extends RubyObject implements CharSequence, EncodingCapa | |
} | |
cp = spBeg + offset; | |
if (offset > spLen) break; | |
- beg = StringSupport.index(this, pattern, offset, patternEnc); | |
+ beg = StringSupport.index(getByteList(), pattern.getByteList(), offset, patternEnc); | |
} while (beg >= 0); | |
if (spLen > offset) dest.cat(spBytes, cp, spLen - offset, str_enc); | |
diff --git a/core/src/main/java/org/jruby/util/StringSupport.java b/core/src/main/java/org/jruby/util/StringSupport.java | |
index 5790ac76bb..6ee1c5d759 100644 | |
--- a/core/src/main/java/org/jruby/util/StringSupport.java | |
+++ b/core/src/main/java/org/jruby/util/StringSupport.java | |
@@ -1616,6 +1616,38 @@ public final class StringSupport { | |
return string.getCodeRange() == CR_7BIT || encoding.maxLength() == 1; | |
} | |
+ /** | |
+ * | |
+ * @param source string to find index within | |
+ * @param other string to match in source | |
+ * @param offset in bytes to start looking | |
+ * @param enc encoding to use to walk the source string. | |
+ * @return | |
+ */ | |
+ public static int index(ByteList source, ByteList other, int offset, Encoding enc) { | |
+ int sourceLen = source.realSize(); | |
+ int sourceBegin = source.begin(); | |
+ int otherLen = other.realSize(); | |
+ | |
+ if (otherLen == 0) return offset; | |
+ if (sourceLen - offset < otherLen) return -1; | |
+ | |
+ byte[] sourceBytes = source.getUnsafeBytes(); | |
+ int p = sourceBegin + offset; | |
+ int end = p + sourceLen; | |
+ | |
+ while (true) { | |
+ int pos = source.indexOf(other, p - sourceBegin); | |
+ if (pos < 0) return pos; | |
+ pos -= (p - sourceBegin); | |
+ int t = enc.rightAdjustCharHead(sourceBytes, p, p + pos, end); | |
+ if (t == p + pos) return pos + offset; | |
+ if ((sourceLen -= t - p) <= 0) return -1; | |
+ offset += t - p; | |
+ p = t; | |
+ } | |
+ } | |
+ | |
public static int index(CodeRangeable sourceString, CodeRangeable otherString, int offset, Encoding enc) { | |
if (otherString.scanForCodeRange() == CR_BROKEN) return -1; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment