Made the encoding even more defensive
This commit is contained in:
parent
e20c096cfe
commit
a7b67c39af
6 changed files with 57 additions and 34 deletions
|
@ -21,7 +21,7 @@ plugins {
|
|||
id("signing")
|
||||
}
|
||||
|
||||
description = "A simple library to encode/decode URL parameters"
|
||||
description = "A simple defensive library to encode/decode URL components"
|
||||
group = "net.thauvin.erik"
|
||||
version = "1.0.1-SNAPSHOT"
|
||||
|
||||
|
@ -193,7 +193,7 @@ publishing {
|
|||
artifactId = rootProject.name
|
||||
artifact(javadocJar)
|
||||
pom {
|
||||
name.set(mavenName)
|
||||
name.set("$mavenName for Kotlin")
|
||||
description.set(project.description)
|
||||
url.set(mavenUrl)
|
||||
licenses {
|
||||
|
|
|
@ -1,13 +1,15 @@
|
|||
<?xml version='1.0' encoding='UTF-8'?>
|
||||
<SmellBaseline>
|
||||
<ManuallySuppressedIssues/>
|
||||
<CurrentIssues>
|
||||
<ID>ComplexCondition:UrlEncoder.kt$UrlEncoder$hasOption && args.size == 2 || !hasOption && args.size == 1</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$0x80</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$0xFF</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$16</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$3</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$4</ID>
|
||||
<ID>NestedBlockDepth:UrlEncoder.kt$UrlEncoder$@JvmStatic fun encode(source: String, allow: String): String</ID>
|
||||
</CurrentIssues>
|
||||
<ManuallySuppressedIssues/>
|
||||
<CurrentIssues>
|
||||
<ID>ComplexCondition:UrlEncoder.kt$UrlEncoder$hasOption && args.size == 2 || !hasOption &&
|
||||
args.size == 1
|
||||
</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$0x80</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$0xFF</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$16</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$3</ID>
|
||||
<ID>MagicNumber:UrlEncoder.kt$UrlEncoder$4</ID>
|
||||
<ID>NestedBlockDepth:UrlEncoder.kt$UrlEncoder$@JvmStatic fun encode(source: String, allow: String): String</ID>
|
||||
</CurrentIssues>
|
||||
</SmellBaseline>
|
||||
|
|
|
@ -9,8 +9,8 @@
|
|||
<groupId>net.thauvin.erik</groupId>
|
||||
<artifactId>urlencoder</artifactId>
|
||||
<version>1.0.1-SNAPSHOT</version>
|
||||
<name>UrlEncoder</name>
|
||||
<description>A simple library to encode/decode URL parameters</description>
|
||||
<name>UrlEncoder for Kotlin</name>
|
||||
<description>A simple defensive library to encode/decode URL components</description>
|
||||
<url>https://github.com/ethauvin/urlencoder</url>
|
||||
<licenses>
|
||||
<license>
|
||||
|
|
|
@ -22,22 +22,31 @@ import java.util.BitSet
|
|||
import kotlin.system.exitProcess
|
||||
|
||||
/**
|
||||
* URL parameters encoding and decoding.
|
||||
* Most defensive approach to URL encoding and decoding.
|
||||
*
|
||||
* - Rules determined by [RFC 3986](https://www.rfc-editor.org/rfc/rfc3986#page-13),
|
||||
* - 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).
|
||||
*
|
||||
* @author Geert Bevin (gbevin[remove] at uwyn dot com)
|
||||
* - 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 UrlEncoder {
|
||||
private val hexDigits = "0123456789ABCDEF".toCharArray()
|
||||
internal val usage =
|
||||
"Usage : java -jar urlencoder-*all.jar [-ed] text" + System.lineSeparator() +
|
||||
"Encode and decode URL parameters." + System.lineSeparator() + " -e encode (default) " +
|
||||
"Encode and decode URL components defensively." + System.lineSeparator() + " -e encode (default) " +
|
||||
System.lineSeparator() + " -d decode"
|
||||
|
||||
// see https://www.rfc-editor.org/rfc/rfc3986#page-13
|
||||
private val unreservedChars = BitSet('~'.code + 1).apply {
|
||||
// and https://url.spec.whatwg.org/#application-x-www-form-urlencoded-percent-encode-set
|
||||
private val unreservedChars = BitSet('z'.code + 1).apply {
|
||||
set('-')
|
||||
set('.')
|
||||
for (c in '0'..'9') {
|
||||
|
@ -50,14 +59,14 @@ object UrlEncoder {
|
|||
for (c in 'a'.code..'z'.code) {
|
||||
set(c)
|
||||
}
|
||||
set('~')
|
||||
}
|
||||
|
||||
private fun BitSet.set(c: Char) = this.set(c.code)
|
||||
|
||||
// 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 <= '~' && unreservedChars.get(code)
|
||||
return this <= 'z' && unreservedChars.get(code)
|
||||
}
|
||||
|
||||
private fun StringBuilder.appendEncodedDigit(digit: Int) {
|
||||
|
@ -130,7 +139,7 @@ object UrlEncoder {
|
|||
* 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.
|
||||
* - Letters, numbers, unreserved (`_-!.'()*`) and allowed characters are left intact.
|
||||
*/
|
||||
@JvmStatic
|
||||
fun encode(source: String, allow: String): String {
|
||||
|
@ -177,7 +186,7 @@ object UrlEncoder {
|
|||
* 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.
|
||||
* - Letters, numbers, unreserved (`_-!.'()*`) and allowed characters are left intact.
|
||||
*/
|
||||
@JvmStatic
|
||||
fun encode(source: String, vararg allow: Char): String {
|
||||
|
@ -187,7 +196,7 @@ object UrlEncoder {
|
|||
/**
|
||||
* Encodes and decodes URLs from the command line.
|
||||
*
|
||||
* - `kotlin -cp urlencoder-*.jar net.thauvin.erik.urlencoder.UrlEncoder`
|
||||
* - `java -jar urlencoder-*all.jar <text>`
|
||||
*/
|
||||
@JvmStatic
|
||||
fun main(args: Array<String>) {
|
||||
|
@ -200,7 +209,7 @@ object UrlEncoder {
|
|||
}
|
||||
exitProcess(result.status)
|
||||
} catch (e: IllegalArgumentException) {
|
||||
System.err.println("${UrlEncoder::class.java.simpleName}: ${e.message}");
|
||||
System.err.println("${UrlEncoder::class.java.simpleName}: ${e.message}")
|
||||
exitProcess(1)
|
||||
}
|
||||
}
|
||||
|
|
|
@ -34,7 +34,7 @@ import org.junit.jupiter.params.provider.ValueSource
|
|||
import java.util.stream.Stream
|
||||
|
||||
class UrlEncoderTest {
|
||||
private val same = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~"
|
||||
private val same = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_."
|
||||
|
||||
companion object {
|
||||
@JvmStatic
|
||||
|
@ -45,7 +45,7 @@ class UrlEncoderTest {
|
|||
arguments("a test &", "a%20test%20%26"),
|
||||
arguments(
|
||||
"!abcdefghijklmnopqrstuvwxyz%%ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~=",
|
||||
"%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~%3D"
|
||||
"%21abcdefghijklmnopqrstuvwxyz%25%25ABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.%7E%3D"
|
||||
),
|
||||
arguments("%#okékÉȢ smile!😁", "%25%23ok%C3%A9k%C3%89%C8%A2%20smile%21%F0%9F%98%81"),
|
||||
arguments(
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue