[RUN-4592] Remove BOM from strings in StringFromFile Java action

build.gradle

@@ -25,7 +25,7 @@ mxMarketplace {
     moduleLicense = 'Apache V2'
     appDirectory = "src/CommunityCommons"
     versionPathPrefix = "_Version " // the path prefix within the module to the version folder
-    includeFiles = ["$mprDir/License.txt", "$mprDir/SiemensMendixCommunityCommons__11.0.0__READMEOSS.html"]
+    includeFiles = ["$mprDir/License.txt", "$mprDir/SiemensMendixCommunityCommons__11.0.1__READMEOSS.html"]
     syncJavaDependenciesBeforeBuild = true
 }
 

marketplace/release-notes/11.0.1.txt

@@ -0,0 +1 @@
+- The StringFromFile Java action now removes BOM from strings. (Ticket #242904)

src/CommunityCommons/javasource/communitycommons/StringUtils.java

@@ -36,6 +36,7 @@
 import javax.swing.text.html.parser.ParserDelegator;
 
 import org.apache.commons.io.IOUtils;
+import org.apache.commons.io.input.BOMInputStream;
 import org.apache.commons.text.StringEscapeUtils;
 import org.owasp.html.PolicyFactory;
 import org.owasp.html.Sanitizers;
@@ -222,10 +223,14 @@ public static String stringFromFile(IContext context, FileDocument source, Chars
 			return null;
 		}
 		try (InputStream f = Core.getFileDocumentContent(context, source.getMendixObject())) {
-			return IOUtils.toString(f, charset);
+			return stringFromInputStream(f, charset);
 		}
 	}
 
+	public static String stringFromInputStream(InputStream inputStream, Charset charset) throws IOException {
+		return IOUtils.toString(BOMInputStream.builder().setInputStream(inputStream).get(), charset);
+	}
+
 	public static void stringToFile(IContext context, String value, FileDocument destination) throws IOException {
 		stringToFile(context, value, destination, StandardCharsets.UTF_8);
 	}

src/test/communitycommons/StringUtilsTest.java

@@ -14,6 +14,10 @@
 import org.owasp.html.PolicyFactory;
 import org.owasp.html.Sanitizers;
 
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.charset.Charset;
 import java.security.DigestException;
 import java.security.NoSuchAlgorithmException;
 
@@ -170,4 +174,32 @@ public void testHash() throws DigestException, NoSuchAlgorithmException {
 		assertEquals(StringUtils.hash(originalString), StringUtils.hash(originalString, length));
 		assertEquals(StringUtils.hash(originalString), hashedString);
 	}
+
+	@Test
+	public void testStringFromInputStream() throws IOException {
+		Charset utf8 = Charset.forName("UTF-8");
+		Charset utf16 = Charset.forName("UTF-16");
+		Charset utf16be = Charset.forName("UTF-16BE");
+		Charset utf16le = Charset.forName("UTF-16LE");
+
+		String text = "hello";
+
+		assertEquals(text, testStringFromInputStream(text, utf8));
+		assertEquals(text, testStringFromInputStream(text, utf16));
+		assertEquals(text, testStringFromInputStream(text, utf16be));
+		assertEquals(text, testStringFromInputStream(text, utf16le));
+
+		// BOM should be removed (UTF-8)
+		byte[] UTF8BOM = { (byte) 0xEF, (byte) 0xBB, (byte) 0xBF };
+		String textUTF8BOM = new String(UTF8BOM) + text;
+		assertEquals(text, testStringFromInputStream(textUTF8BOM, utf8));
+	}
+
+	private String testStringFromInputStream(String text, Charset charset) throws IOException {
+		return StringUtils.stringFromInputStream(stringToInputStream(text, charset), charset);
+	}
+
+	private InputStream stringToInputStream(String str, Charset charset) {
+		return new ByteArrayInputStream(str.getBytes(charset));
+	}
 }