GzipCompressorOutputStream no longer percent-endcodes in US-ASCII a file

name or comment that the Charset in GzipParameters.setFileNameCharset(Charset) cannot encode
apache · Nov 7, 2024 · d0e5f6c · d0e5f6c
1 parent ec7bc35
commit d0e5f6c
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 38 deletions.
diff --git a/src/changes/changes.xml b/src/changes/changes.xml
@@ -53,14 +53,16 @@ The <action> type attribute can be add,update,fix,remove.
       <action type="add" dev="ggregory" due-to="Gary Gregory">Add GzipParameters.setModificationInstant(Instant).</action>
       <action type="add" dev="ggregory" due-to="Gary Gregory">Add GzipParameters.OS, setOS(OS), getOS().</action>
       <action type="add" dev="ggregory" due-to="Gary Gregory">Add GzipParameters.toString().</action>
-      <action type="add" dev="ggregory" due-to="vincexjl, Gary Gregory, Piotr P. Karwasz">Add GzipParameters.setFileNameCharset(Charset) and getFileNameCharset().</action>
+      <action type="add" dev="ggregory" issue="COMPRESS-638" due-to="vincexjl, Gary Gregory, Piotr P. Karwasz">Add GzipParameters.setFileNameCharset(Charset) and getFileNameCharset() to override the default ISO-8859-1 Charset #602.</action>
       <!-- UPDATE -->
       <action type="update" dev="ggregory" due-to="Dependabot, Gary Gregory">Bump org.apache.commons:commons-parent from 72 to 78 #563, #567, #574, #582, #587, #595.</action>
       <action type="update" dev="ggregory" due-to="Dependabot, Gary Gregory">Bump com.github.luben:zstd-jni from 1.5.6-4 to 1.5.6-7 #565, #578, #601.</action>
       <action type="update" dev="ggregory" due-to="Dependabot, Gary Gregory">Bump org.apache.commons:commons-lang3 from 3.16.0 to 3.17.0 #568.</action>
       <action type="update" dev="ggregory" due-to="Dependabot, Gary Gregory">Bump commons-io:commons-io from 2.16.1 to 2.17.0 #575.</action>
       <action type="update" dev="ggregory" due-to="Dependabot, Gary Gregory">Bump com.github.marschall:memoryfilesystem from 2.8.0 to 2.8.1 #577.</action>
-      <action type="update" dev="ggregory" due-to="Dependabot, Gary Gregory">Bump org.ow2.asm:asm from 9.7 to 9.7.1 #586.</action>     
+      <action type="update" dev="ggregory" due-to="Dependabot, Gary Gregory">Bump org.ow2.asm:asm from 9.7 to 9.7.1 #586.</action>
+      <!-- REMOVE -->
+      <action type="remove" dev="ggregory" issue="COMPRESS-638" due-to="vincexjl, Gary Gregory, Piotr P. Karwasz">GzipCompressorOutputStream no longer percent-endcodes in US-ASCII a file name or comment that the Charset in GzipParameters.setFileNameCharset(Charset) cannot encode.</action>     
     </release>
     <release version="1.27.1" date="2024-08-16" description="This is a feature and maintenance release. Java 8 or later is required.">
      <action type="fix" issue="COMPRESS-686" dev="ggregory" due-to="Richard Blank, Gary Gregory">Compression into BZip2 format has unexpected end of file when using a BufferedOutputStream.</action>

diff --git a/src/main/java/org/apache/commons/compress/compressors/gzip/GzipCompressorOutputStream.java b/src/main/java/org/apache/commons/compress/compressors/gzip/GzipCompressorOutputStream.java
@@ -20,12 +20,9 @@
 
 import java.io.IOException;
 import java.io.OutputStream;
-import java.net.URI;
-import java.net.URISyntaxException;
 import java.nio.ByteBuffer;
 import java.nio.ByteOrder;
 import java.nio.charset.Charset;
-import java.nio.charset.StandardCharsets;
 import java.util.zip.CRC32;
 import java.util.zip.Deflater;
 import java.util.zip.GZIPInputStream;
@@ -122,29 +119,6 @@ public void finish() throws IOException {
         }
     }
 
-    /**
-     * Gets the bytes encoded in the {@value GzipUtils#GZIP_ENCODING} Charset.
-     * <p>
-     * If the string cannot be encoded directly with {@value GzipUtils#GZIP_ENCODING}, then use URI-style percent encoding.
-     * </p>
-     *
-     * @param string          The string to encode.
-     * @param charset Overrides the default charset
-     * @return bytes encoded with the given charset if non-null, otherwise use {@value GzipUtils#GZIP_ENCODING} or {@link StandardCharsets#US_ASCII} if
-     *         GZIP_ENCODING fails.
-     * @throws IOException When an ASCII encoded error occurs.
-     */
-    private byte[] getBytes(final String string, final Charset charset) throws IOException {
-        if (charset.newEncoder().canEncode(string)) {
-            return string.getBytes(charset);
-        }
-        try {
-            return new URI(null, null, string, null).toASCIIString().getBytes(StandardCharsets.US_ASCII);
-        } catch (final URISyntaxException e) {
-            throw new IOException(string, e);
-        }
-    }
-
     /**
      * {@inheritDoc}
      *
@@ -167,11 +141,9 @@ public void write(final byte[] buffer, final int offset, final int length) throw
         }
         if (length > 0) {
             deflater.setInput(buffer, offset, length);
-
             while (!deflater.needsInput()) {
                 deflate();
             }
-
             crc.update(buffer, offset, length);
         }
     }
@@ -182,15 +154,15 @@ public void write(final int b) throws IOException {
     }
 
     /**
-     * Writes a NUL-terminated String.
+     * Writes a NUL-terminated String encoded with the {@code charset}.
      *
      * @param value The String to write.
-     * @param parameters Specifies the Charset to use.
+     * @param charset Specifies the Charset to use.
      * @throws IOException if an I/O error occurs.
      */
-    private void write(final String value, final GzipParameters parameters) throws IOException {
+    private void write(final String value, final Charset charset) throws IOException {
         if (value != null) {
-            out.write(getBytes(value, parameters.getFileNameCharset()));
+            out.write(value.getBytes(charset));
             out.write(0);
         }
     }
@@ -215,8 +187,8 @@ private void writeHeader(final GzipParameters parameters) throws IOException {
         }
         buffer.put((byte) parameters.getOperatingSystem());
         out.write(buffer.array());
-        write(fileName, parameters);
-        write(comment, parameters);
+        write(fileName, parameters.getFileNameCharset());
+        write(comment, parameters.getFileNameCharset());
     }
 
     private void writeTrailer() throws IOException {

diff --git a/...est/java/org/apache/commons/compress/compressors/gzip/GzipCompressorOutputStreamTest.java b/...est/java/org/apache/commons/compress/compressors/gzip/GzipCompressorOutputStreamTest.java
@@ -107,7 +107,7 @@ public void testFileNameAscii() throws IOException {
     }
 
     /**
-     * Tests COMPRESS-638.
+     * Tests COMPRESS-638. Use {@link GzipParameters#setFileNameCharset(Charset)} if you want non-ISO-8859-1 characters.
      *
      * GZip RFC requires ISO 8859-1 (LATIN-1).
      *
@@ -116,6 +116,6 @@ public void testFileNameAscii() throws IOException {
     @Test
     public void testFileNameChinesePercentEncoded() throws IOException {
         // "Test Chinese name"
-        testFileName("%E6%B5%8B%E8%AF%95%E4%B8%AD%E6%96%87%E5%90%8D%E7%A7%B0.xml", EXPECTED_FILE_NAME);
+        testFileName("??????.xml", EXPECTED_FILE_NAME);
     }
 }