restructure project to Kotlin Multiplatform
- custom POM location removed (there are now two POMs, one for the 'Kotlin Multiplatform' publication, and another for Kotlin/JVM, and more are on the way, which would lead to a cluttered build dir) - renamed the directories (the directory name is how Kotlin Multiplatform chooses the published artifact ID, and there's no an easier way to change it.) - updated README examples, and link to `-jvm` variant guide
This commit is contained in:
Adam
parent
4df6d3f599
commit
dce203845e
16 changed files with 59 additions and 243 deletions
|
|
@ -0,0 +1,197 @@
|
|||
/*
|
||||
* Copyright 2001-2023 Geert Bevin (gbevin[remove] at uwyn dot com)
|
||||
* Copyright 2022-2023 Erik C. Thauvin (erik@thauvin.net)
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package net.thauvin.erik.urlencoder
|
||||
|
||||
import java.nio.charset.StandardCharsets
|
||||
import java.util.BitSet
|
||||
|
||||
/**
|
||||
* Most defensive approach to URL encoding and decoding.
|
||||
*
|
||||
* - Rules 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).
|
||||
*
|
||||
* - 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 `+`, which has the
|
||||
* potential to be misunderstood.
|
||||
*
|
||||
* - This library encodes with rules that will be decoded correctly in either case.
|
||||
*
|
||||
* @author Geert Bevin (gbevin(remove) at uwyn dot com)
|
||||
* @author Erik C. Thauvin (erik@thauvin.net)
|
||||
**/
|
||||
object UrlEncoderUtil {
|
||||
private val hexDigits = "0123456789ABCDEF".toCharArray()
|
||||
|
||||
// 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 val unreservedChars = BitSet('z'.code + 1).apply {
|
||||
set('-'.code)
|
||||
set('.'.code)
|
||||
for (c in '0'.code..'9'.code) {
|
||||
set(c)
|
||||
}
|
||||
for (c in 'A'.code..'Z'.code) {
|
||||
set(c)
|
||||
}
|
||||
set('_'.code)
|
||||
for (c in 'a'.code..'z'.code) {
|
||||
set(c)
|
||||
}
|
||||
}
|
||||
|
||||
// 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 fun Char.isUnreserved(): Boolean {
|
||||
return this <= 'z' && unreservedChars[code]
|
||||
}
|
||||
|
||||
private fun StringBuilder.appendEncodedDigit(digit: Int) {
|
||||
this.append(hexDigits[digit and 0x0F])
|
||||
}
|
||||
|
||||
private fun StringBuilder.appendEncodedByte(ch: Int) {
|
||||
this.append("%")
|
||||
this.appendEncodedDigit(ch shr 4)
|
||||
this.appendEncodedDigit(ch)
|
||||
}
|
||||
|
||||
/**
|
||||
* Transforms a provided [String] into a new string, containing decoded URL characters in the UTF-8
|
||||
* encoding.
|
||||
*/
|
||||
@JvmStatic
|
||||
@JvmOverloads
|
||||
fun decode(source: String, plusToSpace: Boolean = false): String {
|
||||
if (source.isEmpty()) {
|
||||
return source
|
||||
}
|
||||
|
||||
val length = source.length
|
||||
val out: StringBuilder by lazy { StringBuilder(length) }
|
||||
var ch: Char
|
||||
var bytesBuffer: ByteArray? = null
|
||||
var bytesPos = 0
|
||||
var i = 0
|
||||
var started = false
|
||||
while (i < length) {
|
||||
ch = source[i]
|
||||
if (ch == '%') {
|
||||
if (!started) {
|
||||
out.append(source, 0, i)
|
||||
started = true
|
||||
}
|
||||
if (bytesBuffer == null) {
|
||||
// the remaining characters divided by the length of the encoding format %xx, is the maximum number
|
||||
// of bytes that can be extracted
|
||||
bytesBuffer = ByteArray((length - i) / 3)
|
||||
}
|
||||
i++
|
||||
require(length >= i + 2) { "Illegal escape sequence" }
|
||||
try {
|
||||
val v = source.substring(i, i + 2).toInt(16)
|
||||
require(v in 0..0xFF) { "Illegal escape value" }
|
||||
bytesBuffer[bytesPos++] = v.toByte()
|
||||
i += 2
|
||||
} catch (e: NumberFormatException) {
|
||||
throw IllegalArgumentException("Illegal characters in escape sequence: $e.message", e)
|
||||
}
|
||||
} else {
|
||||
if (bytesBuffer != null) {
|
||||
out.append(String(bytesBuffer, 0, bytesPos, StandardCharsets.UTF_8))
|
||||
started = true
|
||||
bytesBuffer = null
|
||||
bytesPos = 0
|
||||
}
|
||||
if (plusToSpace && ch == '+') {
|
||||
if (!started) {
|
||||
out.append(source, 0, i)
|
||||
started = true
|
||||
}
|
||||
out.append(" ")
|
||||
} else if (started) {
|
||||
out.append(ch)
|
||||
}
|
||||
i++
|
||||
}
|
||||
}
|
||||
|
||||
if (bytesBuffer != null) {
|
||||
out.append(String(bytesBuffer, 0, bytesPos, StandardCharsets.UTF_8))
|
||||
}
|
||||
|
||||
return if (!started) source else out.toString()
|
||||
}
|
||||
|
||||
/**
|
||||
* Transforms a provided [String] object into a new string, containing only valid URL characters in the UTF-8
|
||||
* encoding.
|
||||
*
|
||||
* - Letters, numbers, unreserved (`_-!.'()*`) and allowed characters are left intact.
|
||||
*/
|
||||
@JvmStatic
|
||||
@JvmOverloads
|
||||
fun encode(source: String, allow: String = "", spaceToPlus: Boolean = false): String {
|
||||
if (source.isEmpty()) {
|
||||
return source
|
||||
}
|
||||
var out: StringBuilder? = null
|
||||
var ch: Char
|
||||
var i = 0
|
||||
while (i < source.length) {
|
||||
ch = source[i]
|
||||
if (ch.isUnreserved() || allow.indexOf(ch) != -1) {
|
||||
out?.append(ch)
|
||||
i++
|
||||
} else {
|
||||
if (out == null) {
|
||||
out = StringBuilder(source.length)
|
||||
out.append(source, 0, i)
|
||||
}
|
||||
val cp = source.codePointAt(i)
|
||||
when {
|
||||
cp < 0x80 -> {
|
||||
if (spaceToPlus && ch == ' ') {
|
||||
out.append('+')
|
||||
} else {
|
||||
out.appendEncodedByte(cp)
|
||||
}
|
||||
i++
|
||||
}
|
||||
Character.isBmpCodePoint(cp) -> {
|
||||
for (b in ch.toString().toByteArray(StandardCharsets.UTF_8)) {
|
||||
out.appendEncodedByte(b.toInt())
|
||||
}
|
||||
i++
|
||||
}
|
||||
Character.isSupplementaryCodePoint(cp) -> {
|
||||
val high = Character.highSurrogate(cp)
|
||||
val low = Character.lowSurrogate(cp)
|
||||
for (b in charArrayOf(high, low).concatToString().toByteArray(StandardCharsets.UTF_8)) {
|
||||
out.appendEncodedByte(b.toInt())
|
||||
}
|
||||
i += 2
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return out?.toString() ?: source
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,113 @@
|
|||
/*
|
||||
* Copyright 2001-2023 Geert Bevin (gbevin[remove] at uwyn dot com)
|
||||
* Copyright 2022-2023 Erik C. Thauvin (erik@thauvin.net)
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package net.thauvin.erik.urlencoder
|
||||
|
||||
import net.thauvin.erik.urlencoder.UrlEncoderUtil.decode
|
||||
import net.thauvin.erik.urlencoder.UrlEncoderUtil.encode
|
||||
import kotlin.test.*
|
||||
import kotlin.test.DefaultAsserter.assertEquals
|
||||
import kotlin.test.DefaultAsserter.assertSame
|
||||
|
||||
class UrlEncoderUtilTest {
|
||||
private val same = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_."
|
||||
|
||||
companion object {
|
||||
@JvmStatic
|
||||
var invalid = arrayOf("sdkjfh%", "sdkjfh%6", "sdkjfh%xx", "sdfjfh%-1")
|
||||
|
||||
@JvmStatic
|
||||
var validMap = arrayOf(
|
||||
Pair("a test &", "a%20test%20%26"),
|
||||
Pair(
|
||||
"!abcdefghijklmnopqrstuvwxyz%%ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~=",
|
||||
"%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.%7E%3D"
|
||||
),
|
||||
Pair("%#okékÉȢ smile!😁", "%25%23ok%C3%A9k%C3%89%C8%A2%20smile%21%F0%9F%98%81"),
|
||||
Pair(
|
||||
"\uD808\uDC00\uD809\uDD00\uD808\uDF00\uD808\uDD00", "%F0%92%80%80%F0%92%94%80%F0%92%8C%80%F0%92%84%80"
|
||||
)
|
||||
)
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Decode URL`() {
|
||||
for (m in validMap) {
|
||||
assertEquals(m.first, decode(m.second))
|
||||
}
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Decode with Exception`() {
|
||||
for (source in invalid) {
|
||||
assertFailsWith<IllegalArgumentException>(
|
||||
message = "decode($source)",
|
||||
block = { decode(source) }
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Decode when None needed`() {
|
||||
assertSame(same, decode(same))
|
||||
assertEquals("decode('')", decode(""), "")
|
||||
assertEquals("decode(' ')", decode(" "), " ")
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Decode with Plus to Space`() {
|
||||
assertEquals("foo bar", decode("foo+bar", true))
|
||||
assertEquals("foo bar foo", decode("foo+bar++foo", true))
|
||||
assertEquals("foo bar foo", decode("foo+%20bar%20+foo", true))
|
||||
assertEquals("foo + bar", decode("foo+%2B+bar", plusToSpace = true))
|
||||
assertEquals("foo+bar", decode("foo%2Bbar", plusToSpace = true))
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Encode URL`() {
|
||||
for (m in validMap) {
|
||||
assertEquals(m.second, encode(m.first))
|
||||
}
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Encode Empty or Blank`() {
|
||||
assertTrue(encode("", allow = "").isEmpty(), "encode('','')")
|
||||
assertEquals("encode('')", encode(""), "")
|
||||
assertEquals("encode(' ')", encode(" "), "%20")
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Encode when None needed`() {
|
||||
assertSame(encode(same), same)
|
||||
assertSame("with empty allow", encode(same, allow = ""), same)
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Encode with Allow`() {
|
||||
assertEquals("encode(x, =?)","?test=a%20test", encode("?test=a test", allow = "=?"))
|
||||
assertEquals("encode(aaa, a)", "aaa", encode("aaa", "a"))
|
||||
assertEquals("encode(' ')", " ", encode(" ", " ") )
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `Encode with Space to Plus`() {
|
||||
assertEquals("foo+bar", encode("foo bar", spaceToPlus = true))
|
||||
assertEquals("foo+bar++foo", encode("foo bar foo", spaceToPlus = true))
|
||||
assertEquals("foo bar", encode("foo bar", " ", true))
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue