Percent codec optimization

httpcore5/src/main/java/org/apache/hc/core5/net/PercentCodec.java

@@ -30,6 +30,7 @@
 import java.nio.ByteBuffer;
 import java.nio.CharBuffer;
 import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
 import java.nio.charset.StandardCharsets;
 import java.util.BitSet;
 
@@ -179,7 +180,22 @@ static void encode(final StringBuilder buf, final CharSequence content, final Ch
             return;
         }
         final CharBuffer cb = CharBuffer.wrap(content);
-        final ByteBuffer bb = (charset != null ? charset : StandardCharsets.UTF_8).encode(cb);
+        ByteBuffer bb = null;
+        while (cb.hasRemaining()) {
+            final char ch = cb.get();
+            if (safechars.get(ch)) {
+                buf.append(ch);
+            } else if (blankAsPlus && ch == ' ') {
+                buf.append("+");
+            } else {
+                cb.position(cb.position() - 1);
+                bb = (charset != null ? charset : StandardCharsets.UTF_8).encode(cb);
+                break;
+            }
+        }
+        if (bb == null) {
+            return;
+        }
         while (bb.hasRemaining()) {
             final int b = bb.get() & 0xff;
             if (safechars.get(b)) {
@@ -217,8 +233,10 @@ static String decode(final CharSequence content, final Charset charset, final bo
         if (content == null) {
             return null;
         }
-        final ByteBuffer bb = ByteBuffer.allocate(content.length());
         final CharBuffer cb = CharBuffer.wrap(content);
+        final CharBuffer result = CharBuffer.allocate(content.length());
+        ByteBuffer bb = null;
+        CharsetDecoder charsetDecoder = null;
         while (cb.hasRemaining()) {
             final char c = cb.get();
             if (c == '%' && cb.remaining() >= 2) {
@@ -227,20 +245,42 @@ static String decode(final CharSequence content, final Charset charset, final bo
                 final int u = Character.digit(uc, RADIX);
                 final int l = Character.digit(lc, RADIX);
                 if (u != -1 && l != -1) {
+                    if (bb == null) {
+                        bb = ByteBuffer.allocate(cb.remaining() + 1);
+                    }
+                    if (charsetDecoder == null) {
+                        charsetDecoder = (charset != null ? charset : StandardCharsets.UTF_8).newDecoder();
+                    }
                     bb.put((byte) ((u << 4) + l));
                 } else {
-                    bb.put((byte) '%');
-                    bb.put((byte) uc);
-                    bb.put((byte) lc);
+                    flushBin(bb, result, charsetDecoder);
+                    result.put('%');
+                    result.put(uc);
+                    result.put(lc);
                 }
-            } else if (plusAsBlank && c == '+') {
-                bb.put((byte) ' ');
             } else {
-                bb.put((byte) c);
+                flushBin(bb, result, charsetDecoder);
+                if (plusAsBlank && c == '+') {
+                    result.put(' ');
+                } else {
+                    result.put(c);
+                }
             }
         }
-        bb.flip();
-        return (charset != null ? charset : StandardCharsets.UTF_8).decode(bb).toString();
+        flushBin(bb, result, charsetDecoder);
+        result.flip();
+        return result.toString();
+    }
+
+    static void flushBin(final ByteBuffer bb, final CharBuffer result, final CharsetDecoder charsetDecoder) {
+        if (bb == null) {
+            return;
+        }
+        if (bb.position() > 0) {
+            bb.flip();
+            charsetDecoder.decode(bb, result, true);
+            bb.compact();
+        }
     }
 
     public static String decode(final CharSequence content, final Charset charset) {

httpcore5/src/test/java/org/apache/hc/core5/net/TestPercentCodec.java

@@ -116,4 +116,12 @@ void testPercentCodecEncodeIsNotRfc7639Canonical() {
         assertEquals("%7C", PercentCodec.encode("|", StandardCharsets.UTF_8));
     }
 
+    @Test
+    void decodeIllegalChars() {
+        final String s = "1\u012E2\u012E3\u012E4";
+        assertEquals(s, PercentCodec.decode(s, StandardCharsets.UTF_8));
+        assertEquals(s, PercentCodec.decode("1\u012E2%C4%AE3\u012E4", StandardCharsets.UTF_8));
+        assertEquals(s, PercentCodec.decode("1%C4%AE2%C4%AE3%C4%AE4", StandardCharsets.UTF_8));
+    }
+
 }