diff --git a/.github/workflows/gradle.yml b/.github/workflows/gradle.yml index ef31be6..396e6bf 100644 --- a/.github/workflows/gradle.yml +++ b/.github/workflows/gradle.yml @@ -12,7 +12,7 @@ jobs: strategy: matrix: - java-version: [ 11, 17, 19 ] + java-version: [ 11, 17 ] steps: - uses: actions/checkout@v2 @@ -27,35 +27,11 @@ jobs: - name: Grant execute permission for gradlew run: chmod +x gradlew - - name: Cache SonarCloud packages - if: matrix.java-version == env.SONAR_JDK - uses: actions/cache@v1 - with: - path: ~/.sonar/cache - key: ${{ runner.os }}-sonar - restore-keys: ${{ runner.os }}-sonar + - name: Checkout project sources + uses: actions/checkout@v2 - - name: Cache Gradle packages - uses: actions/cache@v2 - with: - path: | - ~/.gradle/caches - ~/.gradle/wrapper - key: ${{ runner.os }}-gradle-${{ matrix.java-version }}-${{ hashFiles('**/*.gradle*', '**/gradle-wrapper.properties') }} - restore-keys: | - ${{ runner.os }}-gradle-${{ matrix.java-version }}- + - name: Setup Gradle + uses: gradle/gradle-build-action@v2 - name: Test with Gradle - run: ./gradlew build check --stacktrace - - - name: SonarCloud - if: success() && matrix.java-version == env.SONAR_JDK - env: - GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }} - run: ./gradlew jacocoTestReport sonar --info - - - name: Cleanup Gradle Cache - run: | - rm -f ~/.gradle/caches/modules-2/modules-2.lock - rm -f ~/.gradle/caches/modules-2/gc.properties \ No newline at end of file + run: ./gradlew build check --stacktrace \ No newline at end of file diff --git a/README.md b/README.md index 4506f2d..daca475 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,5 @@ [![License](https://img.shields.io/badge/license-Apache%20License%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [![Nexus Snapshot](https://img.shields.io/nexus/s/com.uwyn/urlencoder?server=https%3A%2F%2Fs01.oss.sonatype.org%2F)](https://s01.oss.sonatype.org/content/repositories/snapshots/com/uwyn/urlencoder/) -[![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=gbevin_urlencoder&metric=alert_status)](https://sonarcloud.io/dashboard?id=gbevin_urlencoder) [![GitHub CI](https://github.com/gbevin/urlencoder/actions/workflows/gradle.yml/badge.svg)](https://github.com/gbevin/urlencoder/actions/workflows/gradle.yml) # URL Encoder for Java @@ -8,7 +7,7 @@ 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 Kotlin version can be found at [https://github.com/ethauvin/urlencoder](https://github.com/ethauvin/urlencoder). 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 @@ -23,7 +22,6 @@ also addresses this issue. UrlEncoder.encode("a test &"); // -> "a%20test%20%26" UrlEncoder.encode("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~"); // -> "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~" UrlEncoder.encode("%#okékÉȢ smile!😁"); // -> "%25%23ok%C3%A9k%C3%89%C8%A2%20smile%21%F0%9F%98%81" -UrlEncoder.encode("?test=a test", "?="); // -> ?test=a%20test UrlEncoder.decode("a%20test%20%26"); // -> "a test &" UrlEncoder.decode("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~"); // -> "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~" diff --git a/gradle/wrapper/gradle-wrapper.properties b/gradle/wrapper/gradle-wrapper.properties index 070cb70..ae04661 100644 --- a/gradle/wrapper/gradle-wrapper.properties +++ b/gradle/wrapper/gradle-wrapper.properties @@ -1,5 +1,5 @@ distributionBase=GRADLE_USER_HOME distributionPath=wrapper/dists -distributionUrl=https\://services.gradle.org/distributions/gradle-7.6-bin.zip +distributionUrl=https\://services.gradle.org/distributions/gradle-7.5.1-bin.zip zipStoreBase=GRADLE_USER_HOME zipStorePath=wrapper/dists diff --git a/lib/build.gradle.kts b/lib/build.gradle.kts index d4d2d43..c905fe5 100644 --- a/lib/build.gradle.kts +++ b/lib/build.gradle.kts @@ -2,8 +2,6 @@ plugins { `java-library` `maven-publish` signing - jacoco - id("org.sonarqube") version "3.5.0.2730" } group = "com.uwyn" @@ -12,7 +10,6 @@ base { archivesName.set("urlencoder") version = "0.9-SNAPSHOT" } - java { withJavadocJar() withSourcesJar() @@ -21,21 +18,6 @@ java { } } -tasks.jacocoTestReport { - reports { - xml.required.set(true) - } -} - -sonarqube { - properties { - property("sonar.projectName", rootProject.name) - property("sonar.projectKey", "gbevin_${rootProject.name}") - property("sonar.organization", "gbevin") - property("sonar.host.url", "https://sonarcloud.io") - property("sonar.sourceEncoding", "UTF-8") - } -} repositories { mavenCentral() } @@ -69,12 +51,6 @@ publishing { name.set("Geert Bevin") email.set("gbevin@uwyn.com") } - developer { - id.set("ethauvin") - name.set("Erik C. Thauvin") - email.set("erik@thauvin.net") - url.set("https://erik.thauvin.net/") - } } scm { connection.set("scm:git:https://github.com/gbevin/urlencoder.git") diff --git a/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java b/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java index d751011..76aade4 100644 --- a/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java +++ b/lib/src/main/java/com/uwyn/urlencoder/UrlEncoder.java @@ -13,156 +13,29 @@ import java.util.BitSet; * Rules determined by RFC 3986. * * @author Geert Bevin (gbevin[remove] at uwyn dot com) - * @author Erik C. Thauvin (erik@thauvin.net) * @since 1.0 */ -public final 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]); - } - - private UrlEncoder() { - // no-op - } - - /** - * Transforms a provided String 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 String 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; - var i = 0; - while(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]; - } - - 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(); - } - +public class UrlEncoder { /** * Transforms a provided String 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 String object. * @see #decode(String) * @since 1.0 */ - public static String encode(String source, char... allow) { - return encode(source, new String(allow)); - } - - /** - * Transforms a provided String 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 String object. - * @see #decode(String) - * @since 1.0 - */ - public static String encode(String source, String allow) { - if (source == null || source.isBlank()) { - return source; + public static String encode(String source) { + if (source == null) { + return null; } StringBuilder out = null; char ch; - var i = 0; - while(i < source.length()) { + for (var i = 0; i < source.length(); ) { ch = source.charAt(i); - if (isUnreservedUriChar(ch) || allow.indexOf(ch) != -1) { + if (isUnreservedUriChar(ch)) { if (out != null) { out.append(ch); } @@ -200,8 +73,115 @@ public final 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) { - return ch <= '~' && UNRESERVED_URI_CHARS.get(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 String 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 String 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(); } } diff --git a/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java b/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java index 530dd4c..3dc5fd2 100644 --- a/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java +++ b/lib/src/test/java/com/uwyn/urlencoder/UrlEncoderTest.java @@ -6,41 +6,48 @@ 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 { - private String[] invalid = {"sdkjfh%", "sdkjfh%6", "sdkjfh%xx", "sdfjfh%-1"}; - private String same = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVQXYZ0123456789-_.~"; - private Map 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 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!😁")); + } @Test - void testDecodeURL() { + public void testDecodeURL() { assertNull(UrlEncoder.decode(null)); - assertSame(same, UrlEncoder.decode(same)); - validMap.forEach((expected, source) -> assertEquals(expected, UrlEncoder.decode(source))); + 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")); - for (String i : invalid) { - assertThrows(IllegalArgumentException.class, () -> UrlEncoder.decode(i)); + 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); } } - - @Test - 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')); - } }