Merge branch 'sverk/r16/utf8-atoms'

* sverk/r16/utf8-atoms:
  erl_interface: Fix bug when transcoding atoms from and to UTF8
  erl_interface: Changed erlang_char_encoding interface
  erts: Testcase doing unicode atom printout with ~w
  erl_interface: even more utf8 atom stuff
  erts: Fix bug in analyze_utf8 causing faulty latin1 detection
  Add UTF-8 node name support for epmd
  workaround...
  Fix merge conflict with hasse
  UTF-8 atom documentation
  test case
  erl_interface: utf8 atoms continued
  Add utf8 atom distribution test cases
  atom fixes for NIFs and atom_to_binary
  UTF-8 support for distribution
  Implement UTF-8 atom support for jinterface
  erl_interface: Enable decode of unicode atoms
  stdlib: Fix printing of unicode atoms
  erts: Change internal representation of atoms to utf8
  erts: Refactor rename DFLAG(S)_INTERNAL_TAGS for conformity

Conflicts:
	erts/emulator/beam/io.c

OTP-10753

1 files changed, 52 insertions, 12 deletions

diff --git a/lib/jinterface/java_src/com/ericsson/otp/erlang/OtpInputStream.java b/lib/jinterface/java_src/com/ericsson/otp/erlang/OtpInputStream.java
index ae5f4ee072..c2a79af841 100644
--- a/lib/jinterface/java_src/com/ericsson/otp/erlang/OtpInputStream.java
+++ b/lib/jinterface/java_src/com/ericsson/otp/erlang/OtpInputStream.java
@@ -351,26 +351,64 @@ public class OtpInputStream extends ByteArrayInputStream {
      */
     public String read_atom() throws OtpErlangDecodeException {
 	int tag;
-	int len;
+	int len = -1;
 	byte[] strbuf;
 	String atom;
 
 	tag = read1skip_version();
 
-	if (tag != OtpExternal.atomTag) {
-	    throw new OtpErlangDecodeException(
-		    "wrong tag encountered, expected " + OtpExternal.atomTag
-			    + ", got " + tag);
-	}
+	switch (tag) {
 
-	len = read2BE();
+	case OtpExternal.atomTag:
+	    len = read2BE();
+	    strbuf = new byte[len];
+	    this.readN(strbuf);
+	    try {
+		atom = new String(strbuf, "ISO-8859-1");
+	    } catch (final java.io.UnsupportedEncodingException e) {
+		throw new OtpErlangDecodeException(
+		    "Failed to decode ISO-8859-1 atom");
+	    }
+	    if (atom.length() > OtpExternal.maxAtomLength) {
+		/*
+		 * Throwing an exception would be better I think,
+		 * but truncation seems to be the way it has
+		 * been done in other parts of OTP...
+		 */
+		atom = atom.substring(0, OtpExternal.maxAtomLength);
+	    }
+	    break;
 
-	strbuf = new byte[len];
-	this.readN(strbuf);
-	atom = OtpErlangString.newString(strbuf);
+	case OtpExternal.smallAtomUtf8Tag:
+	    len = read1();
+	    /* fall through */
+	case OtpExternal.atomUtf8Tag:
+	    if (len < 0) {
+		len = read2BE();
+	    }
+	    strbuf = new byte[len];
+	    this.readN(strbuf);
+	    try {
+		atom = new String(strbuf, "UTF-8");
+	    } catch (final java.io.UnsupportedEncodingException e) {
+		throw new OtpErlangDecodeException(
+		    "Failed to decode UTF-8 atom");
+	    }
+	    if (atom.codePointCount(0, atom.length()) > OtpExternal.maxAtomLength) {
+		/*
+		 * Throwing an exception would be better I think,
+		 * but truncation seems to be the way it has
+		 * been done in other parts of OTP...
+		 */
+		final int[] cps = OtpErlangString.stringToCodePoints(atom);
+		atom = new String(cps, 0, OtpExternal.maxAtomLength);
+	    }
+	    break;
 
-	if (atom.length() > OtpExternal.maxAtomLength) {
-	    atom = atom.substring(0, OtpExternal.maxAtomLength);
+	default:
+	    throw new OtpErlangDecodeException(
+		"wrong tag encountered, expected " + OtpExternal.atomTag
+		+ ", or "  + OtpExternal.atomUtf8Tag + ", got " + tag);
 	}
 
 	return atom;
@@ -1152,6 +1190,8 @@ public class OtpInputStream extends ByteArrayInputStream {
 	    return new OtpErlangLong(this);
 
 	case OtpExternal.atomTag:
+	case OtpExternal.smallAtomUtf8Tag:
+	case OtpExternal.atomUtf8Tag:
 	    return new OtpErlangAtom(this);
 
 	case OtpExternal.floatTag: