feat: ✨ Adds first implementation

Author: jycr

README.md

@@ -1 +1,49 @@
-# java-data-url-handler
+[![License MIT](https://img.shields.io/github/license/jycr/java-data-url-handler)](https://opensource.org/license/mit)
+[![Publish package to the Maven Central Repository](https://github.com/jycr/java-data-url-handler/actions/workflows/publish_to_maven_central.yml/badge.svg)](https://github.com/jycr/java-data-url-handler/actions/workflows/publish_to_maven_central.yml)
+[![Version on Maven Central](https://img.shields.io/maven-central/v/io.github.jycr/java-data-url-handler)](https://search.maven.org/artifact/io.github.jycr/java-data-url-handler)
+[![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=jycr_java-data-url-handler&metric=alert_status)](https://sonarcloud.io/summary/new_code?id=jycr_java-data-url-handler)
+
+# java-data-url-handler
+
+When adding this library as a dependency in your project, you will be able to handle "data URLs" ([RFC-2397](https://datatracker.ietf.org/doc/html/rfc2397)) in your application.
+
+## Prerequisites
+
+You need Java >= 11 to use this library.
+
+## Usage
+
+When you want to get the content of a "data URL":
+
+```java
+import java.io.IOException;
+import java.io.InputStream;
+import java.net.URI;
+import java.nio.charset.StandardCharsets;
+
+public class Test {
+	public static void main(String[] args) throws IOException {
+        URL url = URI.create("data:text/plain,Hello%2C%20World!").toURL();
+        try(InputStream in = url.openStream()) {
+            System.out.println(new String(in.readAllBytes(), StandardCharsets.UTF_8));
+        }
+    }
+}
+```
+
+Without this library, you will get an error like this:
+
+```
+Exception in thread "main" java.net.MalformedURLException: unknown protocol: data
+	at java.base/java.net.URL.<init>(URL.java:779)
+	at java.base/java.net.URL.<init>(URL.java:654)
+	at java.base/java.net.URL.<init>(URL.java:590)
+```
+
+With this library in your classpath, you can handle the data URL and get the content of the data URL.
+
+The output of the code above will be:
+
+```
+Hello, World!
+```

src/main/java/io/github/jycr/javadataurlhandler/DataUriConnection.java

@@ -0,0 +1,103 @@
+package io.github.jycr.javadataurlhandler;
+
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.UnsupportedEncodingException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.net.URLConnection;
+import java.net.URLDecoder;
+import java.nio.charset.Charset;
+import java.util.Base64;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import static java.nio.charset.StandardCharsets.US_ASCII;
+
+/**
+ * The data scheme URLConnection.
+ * <p>The data URI scheme Data protocol Syntax:</p>
+ * <pre>data:[<mediatype>][;base64],<data></pre>
+ *
+ * @see <a href="https://www.rfc-editor.org/rfc/rfc2397#section-2">RFC-2397</a>
+ * @see <a href="https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs">mdn web docs - Data URLs</a>
+ */
+public class DataUriConnection extends URLConnection {
+
+	/**
+	 * Syntax of data URL scheme:
+	 * <pre>
+	 * dataurl    := "data:" [ mediatype ] [ ";base64" ] "," data
+	 * mediatype  := [ type "/" subtype ] *( ";" parameter )
+	 * data       := *urlchar
+	 * parameter  := attribute "=" value
+	 * </pre>
+	 */
+	private static final Pattern DATA_URL_SCHEME_PATTERN = Pattern.compile("data:(<mediatype>?(<contentType>?.*?/.*?)?(?:;(<paramKey>?.*?)=(<paramValue>?.*?))?)(?:;(<base64Flag>?base64)?)?,(<data>?.*)");
+
+	private static final Charset DEFAULT_CONTENT_CHARSET = US_ASCII;
+	/**
+	 * Default mime type for data protocol.
+	 * See: <a href="https://www.rfc-editor.org/rfc/rfc2397#section-2">RFC-2397 - Description</a>
+	 */
+	private static final String DEFAULT_MEDIATYPE = "text/plain;charset=" + DEFAULT_CONTENT_CHARSET.name();
+
+	private final boolean valid;
+	private final Charset charset;
+	private final boolean isBase64;
+	private final String data;
+	private final String mediatype;
+
+	public DataUriConnection(final URL url) throws MalformedURLException {
+		super(url);
+		final Matcher matcher = DATA_URL_SCHEME_PATTERN.matcher(url.toString());
+		this.valid = matcher.matches();
+		if (!this.valid) {
+			throw new MalformedURLException("Invalid data URL: " + url);
+		}
+		this.data = matcher.group("data");
+
+		String mediatypeGroup = matcher.group("mediatype");
+		this.mediatype = (mediatypeGroup != null && !mediatypeGroup.isEmpty()) ? mediatypeGroup : DEFAULT_MEDIATYPE;
+		this.isBase64 = "base64".equals(matcher.group("base64Flag"));
+
+		String paramKey = matcher.group("paramKey");
+		String paramValue = matcher.group("paramValue");
+		this.charset = "charset".equals(paramKey) ? Charset.forName(paramValue) : DEFAULT_CONTENT_CHARSET;
+	}
+
+	@Override
+	public void connect() {
+		if (this.valid) {
+			this.connected = true;
+		}
+	}
+
+	@Override
+	public InputStream getInputStream() throws IOException {
+		if (!connected) {
+			throw new IOException();
+		}
+		return new ByteArrayInputStream(getData());
+	}
+
+	/**
+	 * <p>Returns the value of the content-type defined in data URL.</p>
+	 * <p>This value is optional and if not defined, value is <code>{@value #DEFAULT_MEDIATYPE}</code></p>
+	 */
+	@Override
+	public String getContentType() {
+		if (!connected) {
+			return null;
+		}
+		return mediatype;
+	}
+
+	private byte[] getData() throws UnsupportedEncodingException {
+		if (isBase64) {
+			return Base64.getDecoder().decode(data);
+		}
+		return URLDecoder.decode(data, charset).getBytes(data);
+	}
+}

src/main/java/io/github/jycr/javadataurlhandler/DataUriHandler.java

@@ -0,0 +1,13 @@
+package io.github.jycr.javadataurlhandler;
+
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.net.URLConnection;
+import java.net.URLStreamHandler;
+
+public class DataUriHandler extends URLStreamHandler {
+	@Override
+	protected URLConnection openConnection(final URL url) throws MalformedURLException {
+		return new DataUriConnection(url);
+	}
+}

src/main/java/io/github/jycr/javadataurlhandler/DataUriHandlerProvider.java

@@ -0,0 +1,16 @@
+package io.github.jycr.javadataurlhandler;
+
+import java.net.URLStreamHandler;
+import java.net.spi.URLStreamHandlerProvider;
+
+public class DataUriHandlerProvider extends URLStreamHandlerProvider {
+    public static final String DATA_PROTOCOL = "data";
+
+	@Override
+	public URLStreamHandler createURLStreamHandler(String protocol) {
+        if(DATA_PROTOCOL.equals(protocol)){
+            return new DataUriHandler();
+        }
+        return null;
+	}
+}

src/main/resources/META-INF/services/java.net.spi.URLStreamHandlerProvider

@@ -0,0 +1 @@
+io.github.jycr.javadataurlhandler.DataUriHandlerProvider

src/test/java/io/github/jycr/javadataurlhandler/DataUriConnectionTest.java

@@ -0,0 +1,131 @@
+package io.github.jycr.javadataurlhandler;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.net.URI;
+import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
+
+import org.assertj.core.api.AbstractObjectAssert;
+import org.assertj.core.api.SoftAssertions;
+import org.junit.jupiter.api.Test;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+class DataUriConnectionTest {
+	@Test
+	void testMinimal() throws IOException {
+		assertDataUriAsString(
+				"data:,A%20brief%20note",
+				"text/plain;charset=US-ASCII",
+				StandardCharsets.US_ASCII,
+				12
+		)
+				.isEqualTo("A brief note");
+	}
+
+	@Test
+	void testImage() throws IOException {
+		DataUriConnection connection = assertDataUri(
+				"data:image/gif;base64,R0lGODdhMAAwAPAAAAAAAP///ywAAAAAMAAwAAAC8IyPqcvt3wCcDkiLc7C0qwyGHhSWpjQu5yqmCYsapyuvUUlvONmOZtfzgFzByTB10QgxOR0TqBQejhRNzOfkVJ+5YiUqrXF5Y5lKh/DeuNcP5yLWGsEbtLiOSpa/TPg7JpJHxyendzWTBfX0cxOnKPjgBzi4diinWGdkF8kjdfnycQZXZeYGejmJlZeGl9i2icVqaNVailT6F5iJ90m6mvuTS4OK05M0vDk0Q4XUtwvKOzrcd3iq9uisF81M1OIcR7lEewwcLp7tuNNkM3uNna3F2JQFo97Vriy/Xl4/f1cf5VWzXyym7PHhhx4dbgYKAAA7",
+				"image/gif",
+				StandardCharsets.US_ASCII,
+				273
+		);
+		assertThat(connection.getInputStream().readAllBytes())
+				.isEqualTo(new byte[]{
+						71, 73, 70, 56, 55, 97, 48, 0, 48, 0, -16, 0, 0, 0, 0, 0, -1, -1, -1, 44, 0, 0, 0, 0, 48, 0, 48, 0, 0, 2, -16, -116, -113, -87, -53,
+						-19, -33, 0, -100, 14, 72, -117, 115, -80, -76, -85, 12, -122, 30, 20, -106, -90, 52, 46, -25, 42, -90, 9, -117, 26, -89, 43, -81, 81,
+						73, 111, 56, -39, -114, 102, -41, -13, -128, 92, -63, -55, 48, 117, -47, 8, 49, 57, 29, 19, -88, 20, 30, -114, 20, 77, -52, -25, -28,
+						84, -97, -71, 98, 37, 42, -83, 113, 121, 99, -103, 74, -121, -16, -34, -72, -41, 15, -25, 34, -42, 26, -63, 27, -76, -72, -114, 74,
+						-106, -65, 76, -8, 59, 38, -110, 71, -57, 39, -89, 119, 53, -109, 5, -11, -12, 115, 19, -89, 40, -8, -32, 7, 56, -72, 118, 40, -89,
+						88, 103, 100, 23, -55, 35, 117, -7, -14, 113, 6, 87, 101, -26, 6, 122, 57, -119, -107, -105, -122, -105, -40, -74, -119, -59, 106,
+						104, -43, 90, -118, 84, -6, 23, -104, -119, -9, 73, -70, -102, -5, -109, 75, -125, -118, -45, -109, 52, -68, 57, 52, 67, -123, -44,
+						-73, 11, -54, 59, 58, -36, 119, 120, -86, -10, -24, -84, 23, -51, 76, -44, -30, 28, 71, -71, 68, 123, 12, 28, 46, -98, -19, -72, -45,
+						100, 51, 123, -115, -99, -83, -59, -40, -108, 5, -93, -34, -43, -82, 44, -65, 94, 94, 63, 127, 87, 31, -27, 85, -77, 95, 44, -90, -20,
+						-15, -31, -121, 30, 29, 110, 6, 10, 0, 0, 59
+				});
+	}
+
+	@Test
+	void testGreekCharaters() throws IOException {
+		assertDataUriAsString(
+				"data:text/plain;charset=iso-8859-7,%D6%EF%E9%ED%E9%EA%DE%E9%E1+%E3%F1%DC%EC%EC%E1%F4%E1",
+				"text/plain;charset=ISO-8859-7",
+				Charset.forName("ISO-8859-7"),
+				18
+		)
+				.isEqualTo("Φοινικήια γράμματα");
+	}
+
+	@Test
+	void testApplicationData() throws IOException {
+		assertDataUriAsString(
+				"data:application/vnd-xxx-query,select_vcount,fcol_from_fieldtable/local",
+				"application/vnd-xxx-query",
+				StandardCharsets.US_ASCII,
+				40
+		)
+				.isEqualTo("select_vcount,fcol_from_fieldtable/local");
+	}
+
+	@Test
+	void testPlainText() throws IOException {
+		assertDataUriAsString(
+				"data:text/plain,Hello%2C%20World!",
+				"text/plain;charset=US-ASCII",
+				StandardCharsets.US_ASCII,
+				13
+		)
+				.isEqualTo("Hello, World!");
+	}
+
+	private AbstractObjectAssert<?, String> assertDataUriAsString(
+			String dataUri,
+			String expectedContentType,
+			Charset expectedCharset,
+			long expectedContentLength
+	) throws IOException {
+		DataUriConnection connection = assertDataUri(dataUri, expectedContentType, expectedCharset, expectedContentLength);
+
+		return assertThat(connection.getContent())
+				.describedAs("Content")
+				.isInstanceOf(InputStream.class)
+				.extracting(content -> {
+					try {
+						return ((InputStream) content).readAllBytes();
+					} catch (IOException e) {
+						throw new RuntimeException(e);
+					}
+				})
+				.extracting(content -> new String(content, expectedCharset))
+				;
+	}
+
+
+	private DataUriConnection assertDataUri(
+			String dataUri,
+			String expectedContentType,
+			Charset expectedCharset,
+			long expectedContentLength
+	) throws IOException {
+		DataUriConnection connection = new DataUriConnection(URI.create(dataUri).toURL());
+		connection.connect();
+		SoftAssertions assertions = new SoftAssertions();
+		assertions.assertThat(connection.getContentType())
+		          .describedAs("Content type")
+		          .isEqualTo(expectedContentType);
+		assertions.assertThat(connection.getCharset())
+		          .describedAs("Charset")
+		          .isEqualTo(expectedCharset);
+		assertions.assertThat(connection.getContentLengthLong())
+		          .describedAs("Content length")
+		          .isEqualTo(expectedContentLength);
+		assertions.assertThat(connection.getContentEncoding())
+		          .describedAs("Content encoding")
+		          .isNull();
+		assertions.assertAll();
+
+		return connection;
+	}
+}

src/test/java/io/github/jycr/javadataurlhandler/DataUriHandlerProviderTest.java

@@ -0,0 +1,18 @@
+package io.github.jycr.javadataurlhandler;
+
+import java.net.spi.URLStreamHandlerProvider;
+
+import org.junit.jupiter.api.Test;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+class DataUriHandlerProviderTest {
+
+	@Test
+	void testCreateURLStreamHandler() {
+		URLStreamHandlerProvider provider = new DataUriHandlerProvider();
+		assertThat(provider.createURLStreamHandler("data")).isNotNull();
+		assertThat(provider.createURLStreamHandler("foo")).isNull();
+		assertThat(provider.createURLStreamHandler("http")).isNull();
+	}
+}

src/test/java/io/github/jycr/javadataurlhandler/DataUriHandlerTest.java

@@ -0,0 +1,26 @@
+package io.github.jycr.javadataurlhandler;
+
+import java.net.MalformedURLException;
+import java.net.URI;
+import java.net.URL;
+import java.net.URLConnection;
+
+import org.junit.jupiter.api.Test;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+class DataUriHandlerTest {
+
+	@Test
+	void testOpenConnection() throws MalformedURLException {
+		// Given
+		URL dataUrl = URI.create("data:text/plain,Hello%2C%20World!").toURL();
+		DataUriHandler handler = new DataUriHandler();
+
+		// When
+		URLConnection urlConnection = handler.openConnection(dataUrl);
+
+		// Then
+		assertThat(urlConnection).isNotNull();
+	}
+}