mirror of
https://github.com/gbevin/urlencoder.git
synced 2025-04-25 07:17:11 -07:00
Merge remote-tracking branch 'origin/main'
This commit is contained in:
commit
a53a9c4f76
4 changed files with 156 additions and 148 deletions
|
|
@ -16,26 +16,147 @@ import java.util.BitSet;
|
|||
* @since 1.0
|
||||
*/
|
||||
public class UrlEncoder {
|
||||
static final BitSet UNRESERVED_URI_CHARS;
|
||||
private static final char[] HEX_DIGITS = "0123456789ABCDEF".toCharArray();
|
||||
|
||||
static {
|
||||
// see https://www.rfc-editor.org/rfc/rfc3986#page-13
|
||||
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;
|
||||
}
|
||||
|
||||
private static void appendUrlEncodedByte(StringBuilder out, int ch) {
|
||||
out.append("%");
|
||||
appendUrlEncodedDigit(out, ch >> 4);
|
||||
appendUrlEncodedDigit(out, ch);
|
||||
}
|
||||
|
||||
private static void appendUrlEncodedDigit(StringBuilder out, int digit) {
|
||||
out.append(HEX_DIGITS[digit & 0x0F]);
|
||||
}
|
||||
|
||||
/**
|
||||
* Transforms a provided <code>String</code> URL into a new string,
|
||||
* containing decoded URL characters in the UTF-8 encoding.
|
||||
*
|
||||
* @param source The string URL that has to be decoded
|
||||
* @return The decoded <code>String</code> object.
|
||||
* @see #encode(String, String)
|
||||
* @since 1.0
|
||||
*/
|
||||
public static String decode(String source) {
|
||||
if (source == null || source.isBlank()) {
|
||||
return source;
|
||||
}
|
||||
|
||||
var length = source.length();
|
||||
StringBuilder out = null;
|
||||
char ch;
|
||||
byte[] bytes_buffer = null;
|
||||
var bytes_pos = 0;
|
||||
for (var i = 0; i < length; ) {
|
||||
ch = source.charAt(i);
|
||||
|
||||
if (ch == '%') {
|
||||
if (out == null) {
|
||||
out = new StringBuilder(length);
|
||||
out.append(source, 0, i);
|
||||
}
|
||||
|
||||
if (bytes_buffer == null) {
|
||||
// the remaining characters divided by the length
|
||||
// of the encoding format %xx, is the maximum number of
|
||||
// bytes that can be extracted
|
||||
bytes_buffer = new byte[(length - i) / 3];
|
||||
bytes_pos = 0;
|
||||
}
|
||||
|
||||
i += 1;
|
||||
if (length < i + 2) {
|
||||
throw new IllegalArgumentException("Illegal escape sequence");
|
||||
}
|
||||
try {
|
||||
var v = Integer.parseInt(source, i, i + 2, 16);
|
||||
if (v < 0 || v > 0xFF) {
|
||||
throw new IllegalArgumentException("Illegal escape value");
|
||||
}
|
||||
|
||||
bytes_buffer[bytes_pos++] = (byte) v;
|
||||
|
||||
i += 2;
|
||||
} catch (NumberFormatException e) {
|
||||
throw new IllegalArgumentException("Illegal characters in escape sequence: " + e.getMessage());
|
||||
}
|
||||
} else {
|
||||
if (bytes_buffer != null) {
|
||||
out.append(new String(bytes_buffer, 0, bytes_pos, StandardCharsets.UTF_8));
|
||||
|
||||
bytes_buffer = null;
|
||||
bytes_pos = 0;
|
||||
}
|
||||
|
||||
if (out != null) {
|
||||
out.append(ch);
|
||||
}
|
||||
|
||||
i += 1;
|
||||
}
|
||||
}
|
||||
|
||||
if (out == null) {
|
||||
return source;
|
||||
}
|
||||
|
||||
if (bytes_buffer != null) {
|
||||
out.append(new String(bytes_buffer, 0, bytes_pos, StandardCharsets.UTF_8));
|
||||
}
|
||||
|
||||
return out.toString();
|
||||
}
|
||||
|
||||
/**
|
||||
* Transforms a provided <code>String</code> object into a new string,
|
||||
* containing only valid URL characters in the UTF-8 encoding.
|
||||
*
|
||||
* @param source The string that has to be transformed into a valid URL
|
||||
* string.
|
||||
* @param allow Additional characters to allow.
|
||||
* @return The encoded <code>String</code> object.
|
||||
* @see #decode(String)
|
||||
* @since 1.0
|
||||
*/
|
||||
public static String encode(String source) {
|
||||
if (source == null) {
|
||||
return null;
|
||||
public static String encode(String source, char... allow) {
|
||||
return encode(source, new String(allow));
|
||||
}
|
||||
|
||||
/**
|
||||
* Transforms a provided <code>String</code> object into a new string,
|
||||
* containing only valid URL characters in the UTF-8 encoding.
|
||||
*
|
||||
* @param source The string that has to be transformed into a valid URL
|
||||
* string.
|
||||
* @param allow Additional characters to allow.
|
||||
* @return The encoded <code>String</code> object.
|
||||
* @see #decode(String)
|
||||
* @since 1.0
|
||||
*/
|
||||
public static String encode(String source, String allow) {
|
||||
if (source == null || source.isBlank()) {
|
||||
return source;
|
||||
}
|
||||
|
||||
StringBuilder out = null;
|
||||
char ch;
|
||||
for (var i = 0; i < source.length(); ) {
|
||||
ch = source.charAt(i);
|
||||
if (isUnreservedUriChar(ch)) {
|
||||
if (isUnreservedUriChar(ch) || allow.indexOf(ch) != -1) {
|
||||
if (out != null) {
|
||||
out.append(ch);
|
||||
}
|
||||
|
|
@ -73,115 +194,8 @@ public class UrlEncoder {
|
|||
return out.toString();
|
||||
}
|
||||
|
||||
static final BitSet UNRESERVED_URI_CHARS;
|
||||
|
||||
static {
|
||||
// see https://www.rfc-editor.org/rfc/rfc3986#page-13
|
||||
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;
|
||||
}
|
||||
|
||||
// see https://www.rfc-editor.org/rfc/rfc3986#page-13
|
||||
private static boolean isUnreservedUriChar(char ch) {
|
||||
if (ch > '~') return false;
|
||||
return UNRESERVED_URI_CHARS.get(ch);
|
||||
}
|
||||
|
||||
private static final char[] HEX_DIGITS = "0123456789ABCDEF".toCharArray();
|
||||
|
||||
private static void appendUrlEncodedDigit(StringBuilder out, int digit) {
|
||||
out.append(HEX_DIGITS[digit & 0x0F]);
|
||||
}
|
||||
|
||||
private static void appendUrlEncodedByte(StringBuilder out, int ch) {
|
||||
out.append("%");
|
||||
appendUrlEncodedDigit(out, ch >> 4);
|
||||
appendUrlEncodedDigit(out, ch);
|
||||
}
|
||||
|
||||
/**
|
||||
* Transforms a provided <code>String</code> URL into a new string,
|
||||
* containing decoded URL characters in the UTF-8 encoding.
|
||||
*
|
||||
* @param source The string URL that has to be decoded
|
||||
* @return The decoded <code>String</code> object.
|
||||
* @see #encode(String)
|
||||
* @since 1.0
|
||||
*/
|
||||
public static String decode(String source) {
|
||||
if (source == null) {
|
||||
return source;
|
||||
}
|
||||
|
||||
var length = source.length();
|
||||
StringBuilder out = null;
|
||||
char ch;
|
||||
byte[] bytes_buffer = null;
|
||||
var bytes_pos = 0;
|
||||
for (var i = 0; i < length; ) {
|
||||
ch = source.charAt(i);
|
||||
|
||||
if (ch == '%') {
|
||||
if (out == null) {
|
||||
out = new StringBuilder(source.length());
|
||||
out.append(source, 0, i);
|
||||
}
|
||||
|
||||
if (bytes_buffer == null) {
|
||||
// the remaining characters divided by the length
|
||||
// of the encoding format %xx, is the maximum number of
|
||||
// bytes that can be extracted
|
||||
bytes_buffer = new byte[(length - i) / 3];
|
||||
bytes_pos = 0;
|
||||
}
|
||||
|
||||
i += 1;
|
||||
if (length < i + 2) {
|
||||
throw new IllegalArgumentException("Illegal escape sequence");
|
||||
}
|
||||
try {
|
||||
var v = Integer.parseInt(source, i, i + 2, 16);
|
||||
if (v < 0 || v > 0xFF) {
|
||||
throw new IllegalArgumentException("Illegal escape value");
|
||||
}
|
||||
|
||||
bytes_buffer[bytes_pos++] = (byte) v;
|
||||
|
||||
i += 2;
|
||||
} catch (NumberFormatException e) {
|
||||
throw new IllegalArgumentException("Illegal characters in escape sequence" + e.getMessage());
|
||||
}
|
||||
} else {
|
||||
if (bytes_buffer != null) {
|
||||
out.append(new String(bytes_buffer, 0, bytes_pos, StandardCharsets.UTF_8));
|
||||
|
||||
bytes_buffer = null;
|
||||
bytes_pos = 0;
|
||||
}
|
||||
|
||||
if (out != null) {
|
||||
out.append(ch);
|
||||
}
|
||||
|
||||
i += 1;
|
||||
}
|
||||
}
|
||||
|
||||
if (out == null) {
|
||||
return source;
|
||||
}
|
||||
|
||||
if (bytes_buffer != null) {
|
||||
out.append(new String(bytes_buffer, 0, bytes_pos, StandardCharsets.UTF_8));
|
||||
}
|
||||
|
||||
return out.toString();
|
||||
return ch <= '~' && UNRESERVED_URI_CHARS.get(ch);
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -6,48 +6,41 @@ package com.uwyn.urlencoder;
|
|||
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
import java.util.Map;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
import static org.junit.jupiter.api.Assertions.assertTrue;
|
||||
|
||||
class UrlEncoderTest {
|
||||
@Test
|
||||
public void testEncodeURL() {
|
||||
assertNull(UrlEncoder.encode(null));
|
||||
assertEquals("a%20test%20%26", UrlEncoder.encode("a test &"));
|
||||
String valid = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~";
|
||||
assertSame(valid, UrlEncoder.encode(valid));
|
||||
assertEquals("%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~%3D", UrlEncoder.encode("!abcdefghijklmnopqrstuvwxyz%%ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~="));
|
||||
assertEquals("%25%23ok%C3%A9k%C3%89%C8%A2%20smile%21%F0%9F%98%81", UrlEncoder.encode("%#okékÉȢ smile!😁"));
|
||||
}
|
||||
private String[] invalid = {"sdkjfh%", "sdkjfh%6", "sdkjfh%xx", "sdfjfh%-1"};
|
||||
private String same = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~";
|
||||
private Map<String, String> validMap = Map.of(
|
||||
"a test &", "a%20test%20%26",
|
||||
"!abcdefghijklmnopqrstuvwxyz%%ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~=",
|
||||
"%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~%3D",
|
||||
"%#okékÉȢ smile!😁", "%25%23ok%C3%A9k%C3%89%C8%A2%20smile%21%F0%9F%98%81"
|
||||
);
|
||||
|
||||
@Test
|
||||
public void testDecodeURL() {
|
||||
assertNull(UrlEncoder.decode(null));
|
||||
assertEquals("a test &", UrlEncoder.decode("a%20test%20%26"));
|
||||
String valid = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~";
|
||||
assertSame(valid, UrlEncoder.decode(valid));
|
||||
assertEquals("!abcdefghijklmnopqrstuvwxyz%%ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~=", UrlEncoder.decode("%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~%3D"));
|
||||
assertEquals("%#okékÉȢ smile!😁", UrlEncoder.decode("%25%23ok%C3%A9k%C3%89%C8%A2%20smile%21%F0%9F%98%81"));
|
||||
assertSame(same, UrlEncoder.decode(same));
|
||||
validMap.forEach((expected, source) -> assertEquals(expected, UrlEncoder.decode(source)));
|
||||
|
||||
try {
|
||||
UrlEncoder.decode("sdkjfh%");
|
||||
fail();
|
||||
} catch (Exception e) {
|
||||
assertTrue(e instanceof IllegalArgumentException);
|
||||
}
|
||||
|
||||
try {
|
||||
UrlEncoder.decode("sdkjfh%6");
|
||||
fail();
|
||||
} catch (Exception e) {
|
||||
assertTrue(e instanceof IllegalArgumentException);
|
||||
}
|
||||
|
||||
try {
|
||||
UrlEncoder.decode("sdkjfh%xx");
|
||||
fail();
|
||||
} catch (Exception e) {
|
||||
assertTrue(e instanceof IllegalArgumentException);
|
||||
for (String i : invalid) {
|
||||
assertThrows(IllegalArgumentException.class, () -> UrlEncoder.decode(i));
|
||||
}
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testEncodeURL() {
|
||||
assertNull(UrlEncoder.encode(null));
|
||||
assertTrue(UrlEncoder.encode("").isEmpty());
|
||||
assertSame(same, UrlEncoder.encode(same));
|
||||
assertSame(same, UrlEncoder.encode(same, ""));
|
||||
validMap.forEach((source, expected) -> assertEquals(expected, UrlEncoder.encode(source)));
|
||||
|
||||
assertEquals("?test=a%20test", UrlEncoder.encode("?test=a test", "?="));
|
||||
assertEquals("?test=a%20test", UrlEncoder.encode("?test=a test", '?', '='));
|
||||
assertEquals("aaa", UrlEncoder.encode("aaa", 'a'));
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue