diff --git a/README.md b/README.md
index c5d2660..84f4da9 100644
--- a/README.md
+++ b/README.md
@@ -8,28 +8,21 @@
# URL Encoder for Java
-A simple defensive library to encode/decode URL components.
+A simple library to encode/decode URL parameters.
This library was extracted from the [RIFE2 Web Application Framework](https://rife2.com).
A Kotlin version can also be found at [https://github.com/ethauvin/urlencoder](https://github.com/ethauvin/urlencoder).
-The rules are determined by combining the unreserved character set from
-[RFC 3986](https://www.rfc-editor.org/rfc/rfc3986#page-13) with the
-percent-encode set from
-[application/x-www-form-urlencoded](https://url.spec.whatwg.org/#application-x-www-form-urlencoded-percent-encode-set).
+For decades, we've been using [java.net.URLEncoder](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/net/URLEncoder.html)
+because of its improper naming. It is actually intended to encode HTML form
+parameters, not URLs, causing the wrong escape sequences to be used.
-Both specs above support percent decoding of two hexadecimal digits to a
-binary octet, however their unreserved set of characters differs and
-`application/x-www-form-urlencoded` adds conversion of space to `+`,
-that has the potential to be misunderstood.
+Additionally, `java.net.URLEncoder` allocates memory even when no encoding is
+necessary, significantly impacting performance. This library has a negligible
+performance impact when a specified string doesn't need to be encoded.
-This class encodes with rules that will be decoded correctly in either case.
-
-Additionally, this library allocates no memory when encoding isn't needed and
-does the work in a single pass without multiple loops. Both of these
-optimizations have a significantly beneficial impact on performance of encoding
-compared to other solutions like the standard `URLEncoder` in the JDK or
-`UriUtils` in Spring.
+Android's [Uri.encode](https://developer.android.com/reference/android/net/Uri#encode(java.lang.String,%20java.lang.String))
+also addresses the same issues.
## Examples (TL;DR)
@@ -64,7 +57,7 @@ You have two options:
The usage is as follows:
```
-Encode and decode URL components defensively.
+Encode and decode URL parameters.
-e encode (default)
-d decode
```
diff --git a/lib/build.gradle.kts b/lib/build.gradle.kts
index 87a3442..04e2a21 100644
--- a/lib/build.gradle.kts
+++ b/lib/build.gradle.kts
@@ -13,7 +13,7 @@ plugins {
}
group = "com.uwyn"
-version = "1.2.0"
+version = "1.1.0"
val mavenName = "UrlEncoder"
val javaMainClass = "$group.${rootProject.name}.$mavenName"
@@ -112,7 +112,7 @@ publishing {
from(components["java"])
pom {
name.set(mavenName)
- description.set("A simple defensive library to encode/decode URL components")
+ description.set("A simple library to encode/decode URL parameters")
url.set("https://github.com/gbevin/urlencoder")
licenses {
license {
diff --git a/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java b/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java
index 0c53377..7a2de08 100644
--- a/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java
+++ b/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java
@@ -8,19 +8,9 @@ import java.nio.charset.StandardCharsets;
import java.util.*;
/**
- * Most defensive approach to URL encoding and decoding.
+ * URL encoding and decoding.
*
- * Rules determined by combining the unreserved character set from
- * RFC 3986 with
- * the percent-encode set from
- * application/x-www-form-urlencoded.
- *
- * Both specs above support percent decoding of two hexadecimal digits to a
- * binary octet, however their unreserved set of characters differs and
- * {@code application/x-www-form-urlencoded} adds conversion of space to +,
- * which has the potential to be misunderstood.
- *
- * This class encodes with rules that will be decoded correctly in either case.
+ * Rules determined by RFC 3986.
*
* @author Geert Bevin (gbevin[remove] at uwyn dot com)
* @author Erik C. Thauvin (erik@thauvin.net)
@@ -32,14 +22,14 @@ public final class UrlEncoder {
static {
// see https://www.rfc-editor.org/rfc/rfc3986#page-13
- // and https://url.spec.whatwg.org/#application-x-www-form-urlencoded-percent-encode-set
- var unreserved = new BitSet('z' + 1);
+ var unreserved = new BitSet('~' + 1);
unreserved.set('-');
unreserved.set('.');
for (int c = '0'; c <= '9'; ++c) unreserved.set(c);
for (int c = 'A'; c <= 'Z'; ++c) unreserved.set(c);
unreserved.set('_');
for (int c = 'a'; c <= 'z'; ++c) unreserved.set(c);
+ unreserved.set('~');
UNRESERVED_URI_CHARS = unreserved;
}
@@ -225,9 +215,8 @@ public final class UrlEncoder {
}
// see https://www.rfc-editor.org/rfc/rfc3986#page-13
- // and https://url.spec.whatwg.org/#application-x-www-form-urlencoded-percent-encode-set
private static boolean isUnreservedUriChar(char ch) {
- return ch <= 'z' && UNRESERVED_URI_CHARS.get(ch);
+ return ch <= '~' && UNRESERVED_URI_CHARS.get(ch);
}
static class MainResult {
@@ -264,7 +253,7 @@ public final class UrlEncoder {
if (!valid_arguments) {
return new MainResult("Usage : java -jar urlencoder-*.jar [-ed] text" + System.lineSeparator() +
- "Encode and decode URL components defensively." + System.lineSeparator() +
+ "Encode and decode URL parameters." + System.lineSeparator() +
" -e encode (default)" + System.lineSeparator() +
" -d decode", 1);
}
diff --git a/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java b/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java
index 99cf385..ecf6624 100644
--- a/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java
+++ b/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java
@@ -16,7 +16,7 @@ import static org.junit.jupiter.api.Assertions.*;
import static org.junit.jupiter.params.provider.Arguments.arguments;
class UrlEncoderTest {
- private final String same = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.";
+ private final String same = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~";
private static Stream invalid() {
return Stream.of("sdkjfh%", "sdkjfh%6", "sdkjfh%xx", "sdfjfh%-1");
@@ -27,7 +27,7 @@ class UrlEncoderTest {
arguments("a test &", "a%20test%20%26"),
arguments(
"!abcdefghijklmnopqrstuvwxyz%%ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~=",
- "%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.%7E%3D"
+ "%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~%3D"
),
arguments("%#okékÉȢ smile!😁", "%25%23ok%C3%A9k%C3%89%C8%A2%20smile%21%F0%9F%98%81"),
arguments(