archive/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2025-08-26 22:34:27 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

8314774: Optimize URLEncoder

Browse source 
Reviewed-by: redestad, dfuchs
This commit is contained in:
Glavo 2023-09-19 13:49:58 +00:00 • committed by Claes Redestad
parent 7c5f2a2db9
commit f25c920fd3
2 changed files with 75 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

76
src/java.base/share/classes/java/net/URLEncoder.java
View file

@ -32,6 +32,7 @@ import java.nio.charset.IllegalCharsetNameException;
import java.nio.charset.UnsupportedCharsetException ;
import java.util.BitSet;
import java.util.Objects;
import java.util.HexFormat;
import java.util.function.IntPredicate;
import jdk.internal.util.ImmutableBitSetPredicate;
@ -81,7 +82,6 @@ import jdk.internal.util.StaticProperty;
*/
public class URLEncoder {
private static final IntPredicate DONT_NEED_ENCODING;
private static final int CASE_DIFF = ('a' - 'A');
private static final String DEFAULT_ENCODING_NAME;
static {
@ -138,6 +138,11 @@ public class URLEncoder {
DEFAULT_ENCODING_NAME = StaticProperty.fileEncoding();
}
private static void encodeByte(StringBuilder out, byte b) {
out.append('%');
HexFormat.of().withUpperCase().toHexDigits(out, b);
}
/**
* You can't call the constructor.
*/
@ -222,20 +227,30 @@ public class URLEncoder {
public static String encode(String s, Charset charset) {
Objects.requireNonNull(charset, "charset");
boolean needToChange = false;
StringBuilder out = new StringBuilder(s.length());
CharArrayWriter charArrayWriter = new CharArrayWriter();
int i;
for (i = 0; i < s.length(); i++) {
char c = s.charAt(i);
if (!DONT_NEED_ENCODING.test(c) || c == ' ') {
break;
}
}
if (i == s.length()) {
return s;
}
for (int i = 0; i < s.length();) {
int c = s.charAt(i);
//System.out.println("Examining character: " + c);
StringBuilder out = new StringBuilder(s.length() << 1);
CharArrayWriter charArrayWriter = new CharArrayWriter();
if (i > 0) {
out.append(s, 0, i);
}
while (i < s.length()) {
char c = s.charAt(i);
if (DONT_NEED_ENCODING.test(c)) {
if (c == ' ') {
c = '+';
needToChange = true;
}
//System.out.println("Storing: " + c);
out.append((char)c);
out.append(c);
i++;
} else {
// convert to external encoding before hex conversion
@ -245,27 +260,14 @@ public class URLEncoder {
* If this character represents the start of a Unicode
* surrogate pair, then pass in two characters. It's not
* clear what should be done if a byte reserved in the
* surrogate pairs range occurs outside of a legal
* surrogate pairs range occurs outside a legal
* surrogate pair. For now, just treat it as if it were
* any other character.
*/
if (c >= 0xD800 && c <= 0xDBFF) {
/*
System.out.println(Integer.toHexString(c)
+ " is high surrogate");
*/
if ( (i+1) < s.length()) {
int d = s.charAt(i+1);
/*
System.out.println("\tExamining "
+ Integer.toHexString(d));
*/
if (d >= 0xDC00 && d <= 0xDFFF) {
/*
System.out.println("\t"
+ Integer.toHexString(d)
+ " is low surrogate");
*/
if (Character.isHighSurrogate(c)) {
if ((i + 1) < s.length()) {
char d = s.charAt(i + 1);
if (Character.isLowSurrogate(d)) {
charArrayWriter.write(d);
i++;
}
@ -274,29 +276,15 @@ public class URLEncoder {
i++;
} while (i < s.length() && !DONT_NEED_ENCODING.test((c = s.charAt(i))));
charArrayWriter.flush();
String str = charArrayWriter.toString();
byte[] ba = str.getBytes(charset);
for (byte b : ba) {
out.append('%');
char ch = Character.forDigit((b >> 4) & 0xF, 16);
// converting to use uppercase letter as part of
// the hex value if ch is a letter.
if (Character.isLetter(ch)) {
ch -= CASE_DIFF;
}
out.append(ch);
ch = Character.forDigit(b & 0xF, 16);
if (Character.isLetter(ch)) {
ch -= CASE_DIFF;
}
out.append(ch);
encodeByte(out, b);
}
charArrayWriter.reset();
needToChange = true;
}
}
return (needToChange? out.toString() : s);
return out.toString();
}
}