Fix decoding of filenames in zip files, when read by ZipFile.

Java always writes UTF-8 filenames in zip files, but harmony cunningly
always reads them back as ISO-8859-1. Fix that, and also set the flag
that says "these filenames are UTF-8" (the RI will do this from Java 7
on).

Note that this patch doesn't actually touch ZipFile because the bug is
in the package-private ZipEntry constructor that's used by
ZipFile.readCentralDirectory.

Bug: http://code.google.com/p/android/issues/detail?id=4690

4 files changed, 40 insertions, 19 deletions

diff --git a/archive/src/main/java/java/util/zip/ZipConstants.java b/archive/src/main/java/java/util/zip/ZipConstants.java
index 9fbce06..f0b1f69 100644
--- a/archive/src/main/java/java/util/zip/ZipConstants.java
+++ b/archive/src/main/java/java/util/zip/ZipConstants.java
@@ -30,4 +30,25 @@ interface ZipConstants {
             CENNAM = 28, CENEXT = 30, CENCOM = 32, CENDSK = 34, CENATT = 36,
             CENATX = 38, CENOFF = 42, ENDSUB = 8, ENDTOT = 10, ENDSIZ = 12,
             ENDOFF = 16, ENDCOM = 20;
+
+    /**
+     * General Purpose Bit Flags, Bit 3.
+     * If this bit is set, the fields crc-32, compressed
+     * size and uncompressed size are set to zero in the
+     * local header.  The correct values are put in the
+     * data descriptor immediately following the compressed
+     * data.  (Note: PKZIP version 2.04g for DOS only
+     * recognizes this bit for method 8 compression, newer
+     * versions of PKZIP recognize this bit for any
+     * compression method.)
+     */
+    public static final int GPBF_DATA_DESCRIPTOR_FLAG = 1 << 3; // android-added
+
+    /**
+     * General Purpose Bit Flags, Bit 11.
+     * Language encoding flag (EFS).  If this bit is set,
+     * the filename and comment fields for this file
+     * must be encoded using UTF-8.
+     */
+    public static final int GPBF_UTF8_FLAG = 1 << 11; // android-added
 }
diff --git a/archive/src/main/java/java/util/zip/ZipEntry.java b/archive/src/main/java/java/util/zip/ZipEntry.java
index 75466ce..d68aa2f 100644
--- a/archive/src/main/java/java/util/zip/ZipEntry.java
+++ b/archive/src/main/java/java/util/zip/ZipEntry.java
@@ -400,20 +400,16 @@ public class ZipEntry implements ZipConstants, Cloneable {
         }
 
         try {
-            /*
-             * The actual character set is "IBM Code Page 437".  As of
-             * Sep 2006, the Zip spec (APPNOTE.TXT) supports UTF-8.  When
-             * bit 11 of the GP flags field is set, the file name and
-             * comment fields are UTF-8.
-             *
-             * TODO: add correct UTF-8 support.
-             */
-            name = new String(nameBytes, "ISO-8859-1");
+            // BEGIN android-changed
+            // The RI has always assumed UTF-8. (If GPBF_UTF8_FLAG isn't set, the encoding is
+            // actually IBM-437.)
+            name = new String(nameBytes, "UTF-8");
             if (commentBytes != null) {
-                comment = new String(commentBytes, "ISO-8859-1");
+                comment = new String(commentBytes, "UTF-8");
             } else {
                 comment = null;
             }
+            // END android-changed
         } catch (UnsupportedEncodingException uee) {
             throw new InternalError(uee.getMessage());
         }
diff --git a/archive/src/main/java/java/util/zip/ZipInputStream.java b/archive/src/main/java/java/util/zip/ZipInputStream.java
index 554f5d5..ddebd6f 100644
--- a/archive/src/main/java/java/util/zip/ZipInputStream.java
+++ b/archive/src/main/java/java/util/zip/ZipInputStream.java
@@ -49,8 +49,6 @@ public class ZipInputStream extends InflaterInputStream implements ZipConstants
 
     static final int STORED = 0;
 
-    static final int ZIPDataDescriptorFlag = 8;
-
     static final int ZIPLocalHeaderVersionNeeded = 20;
 
     private boolean entriesEnd = false;
@@ -236,7 +234,7 @@ public class ZipInputStream extends InflaterInputStream implements ZipConstants
             throw new ZipException(Messages.getString("archive.22")); //$NON-NLS-1$
         }
         int flags = getShort(hdrBuf, LOCFLG - LOCVER);
-        hasDD = ((flags & ZIPDataDescriptorFlag) == ZIPDataDescriptorFlag);
+        hasDD = ((flags & GPBF_DATA_DESCRIPTOR_FLAG) == GPBF_DATA_DESCRIPTOR_FLAG);
         int cetime = getShort(hdrBuf, LOCTIM - LOCVER);
         int cemodDate = getShort(hdrBuf, LOCTIM - LOCVER + 2);
         int cecompressionMethod = getShort(hdrBuf, LOCHOW - LOCVER);
diff --git a/archive/src/main/java/java/util/zip/ZipOutputStream.java b/archive/src/main/java/java/util/zip/ZipOutputStream.java
index 21b4221..f85e253 100644
--- a/archive/src/main/java/java/util/zip/ZipOutputStream.java
+++ b/archive/src/main/java/java/util/zip/ZipOutputStream.java
@@ -54,8 +54,6 @@ public class ZipOutputStream extends DeflaterOutputStream implements
      */
     public static final int STORED = 0;
 
-    static final int ZIPDataDescriptorFlag = 8;
-
     static final int ZIPLocalHeaderVersionNeeded = 20;
 
     private String comment;
@@ -141,11 +139,12 @@ public class ZipOutputStream extends DeflaterOutputStream implements
             writeLong(out, currentEntry.size = def.getTotalIn());
         }
         // Update the CentralDirectory
+        // http://www.pkware.com/documents/casestudies/APPNOTE.TXT
+        int flags = currentEntry.getMethod() == STORED ? 0 : GPBF_DATA_DESCRIPTOR_FLAG;
         writeLong(cDir, CENSIG);
         writeShort(cDir, ZIPLocalHeaderVersionNeeded); // Version created
         writeShort(cDir, ZIPLocalHeaderVersionNeeded); // Version to extract
-        writeShort(cDir, currentEntry.getMethod() == STORED ? 0
-                : ZIPDataDescriptorFlag);
+        writeShort(cDir, flags);
         writeShort(cDir, currentEntry.getMethod());
         writeShort(cDir, currentEntry.time);
         writeShort(cDir, currentEntry.modDate);
@@ -283,16 +282,23 @@ public class ZipOutputStream extends DeflaterOutputStream implements
         if (currentEntry.getMethod() == -1) {
             currentEntry.setMethod(compressMethod);
         }
+        // BEGIN android-changed
+        // Local file header.
+        // http://www.pkware.com/documents/casestudies/APPNOTE.TXT
+        int flags = currentEntry.getMethod() == STORED ? 0 : GPBF_DATA_DESCRIPTOR_FLAG;
+        // Java always outputs UTF-8 filenames. (Before Java 7, the RI didn't set this flag and used
+        // modified UTF-8. From Java 7, it sets this flag and uses normal UTF-8.)
+        flags |= GPBF_UTF8_FLAG;
         writeLong(out, LOCSIG); // Entry header
         writeShort(out, ZIPLocalHeaderVersionNeeded); // Extraction version
-        writeShort(out, currentEntry.getMethod() == STORED ? 0
-                : ZIPDataDescriptorFlag);
+        writeShort(out, flags);
         writeShort(out, currentEntry.getMethod());
         if (currentEntry.getTime() == -1) {
             currentEntry.setTime(System.currentTimeMillis());
         }
         writeShort(out, currentEntry.time);
         writeShort(out, currentEntry.modDate);
+        // END android-changed
 
         if (currentEntry.getMethod() == STORED) {
             if (currentEntry.size == -1) {