[commons-io] branch master updated: [IO-414] don't write a BOM on every (or any) line (#492)

[ggregory]

This is an automated email from the ASF dual-hosted git repository.

ggregory pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/commons-io.git


The following commit(s) were added to refs/heads/master by this push:
     new 469ef769 [IO-414] don't write a BOM on every (or any) line (#492)
469ef769 is described below

commit 469ef769dfda5da478bdf802d883bf28874ded79
Author: Elliotte Rusty Harold <elh...@users.noreply.github.com>
AuthorDate: Sat Oct 7 10:44:10 2023 -0400

    [IO-414] don't write a BOM on every (or any) line (#492)
    
    * don't write a BOM on every (or any) line
    
    * detab
    
    * don't write a BOM on every (or any) line
    
    * whitespace
    
    * checkstyle
    
    * Remove trailing whitespace
    
    ---------
    
    Co-authored-by: Gary Gregory <garydgreg...@users.noreply.github.com>
---
 src/main/java/org/apache/commons/io/IOUtils.java     | 13 +++++++++++--
 src/test/java/org/apache/commons/io/IOUtilsTest.java |  9 +++++++++
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/src/main/java/org/apache/commons/io/IOUtils.java 
b/src/main/java/org/apache/commons/io/IOUtils.java
index 6d1ebe7e..3382e865 100644
--- a/src/main/java/org/apache/commons/io/IOUtils.java
+++ b/src/main/java/org/apache/commons/io/IOUtils.java
@@ -45,6 +45,7 @@ import java.nio.channels.Channels;
 import java.nio.channels.ReadableByteChannel;
 import java.nio.channels.Selector;
 import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.util.Arrays;
 import java.util.Collection;
@@ -3828,11 +3829,15 @@ public class IOUtils {
      * an {@link OutputStream} line by line, using the specified character
      * encoding and the specified line ending.
      *
+     * UTF-16 is written big-endian with no byte order mark.
+     * For little endian, use UTF-16LE. For a BOM, write it to the stream
+     * before calling this method.
+     *
      * @param lines the lines to write, null entries produce blank lines
      * @param lineEnding the line separator to use, null is system default
      * @param output the {@link OutputStream} to write to, not null, not closed
      * @param charset the charset to use, null means platform default
-     * @throws NullPointerException if the output is null
+     * @throws NullPointerException if output is null
      * @throws IOException          if an I/O error occurs
      * @since 2.3
      */
@@ -3844,7 +3849,11 @@ public class IOUtils {
         if (lineEnding == null) {
             lineEnding = System.lineSeparator();
         }
-        final Charset cs = Charsets.toCharset(charset);
+        Charset cs = Charsets.toCharset(charset);
+        // don't write a BOM
+        if (cs == StandardCharsets.UTF_16) {
+            cs = StandardCharsets.UTF_16BE;
+        }
         final byte[] eolBytes = lineEnding.getBytes(cs);
         for (final Object line : lines) {
             if (line != null) {
diff --git a/src/test/java/org/apache/commons/io/IOUtilsTest.java 
b/src/test/java/org/apache/commons/io/IOUtilsTest.java
index e361e885..0a3e7d39 100644
--- a/src/test/java/org/apache/commons/io/IOUtilsTest.java
+++ b/src/test/java/org/apache/commons/io/IOUtilsTest.java
@@ -1761,4 +1761,13 @@ public class IOUtilsTest {
         }
     }
 
+    @Test
+    public void testWriteLines() throws IOException {
+        final String[] data = {"The", "quick"};
+        final ByteArrayOutputStream out = new ByteArrayOutputStream();
+        IOUtils.writeLines(Arrays.asList(data), "\n", out, "UTF-16");
+        final String result = new String(out.toByteArray(), 
StandardCharsets.UTF_16);
+        assertEquals("The\nquick\n", result);
+    }
+
 }