src/java.instrument/unix/native/libinstrument/EncodingSupport_md.c

@@ -1,7 +1,7 @@
 /*
- * Copyright (c) 2004, 2012, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2004, 2018, Oracle and/or its affiliates. All rights reserved.
  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
  *
  * This code is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 only, as
  * published by the Free Software Foundation.  Oracle designates this

@@ -61,11 +61,11 @@
  * Initialize all utf processing.
  */
 static void
 utfInitialize(void)
 {
-    char *codeset;
+    const char* codeset;
 
     /* Set the locale from the environment */
     (void)setlocale(LC_ALL, "");
 
     /* Get the codeset name */

@@ -75,10 +75,24 @@
         return;
     }
 
     UTF_DEBUG(("Codeset = %s\n", codeset));
 
+#ifdef MACOSX
+    /* On Mac, if US-ASCII, but with no env hints, use UTF-8 */
+    const char* env_lang = getenv("LANG");
+    const char* env_lc_all = getenv("LC_ALL");
+    const char* env_lc_ctype = getenv("LC_CTYPE");
+
+    if (strcmp(codeset,"US-ASCII") == 0 &&
+        (env_lang == NULL || strlen(env_lang) == 0) &&
+        (env_lc_all == NULL || strlen(env_lc_all) == 0) &&
+        (env_lc_ctype == NULL || strlen(env_lc_ctype) == 0)) {    
+        codeset = "UTF-8";
+    }
+#endif
+    
     /* If we don't need this, skip it */
     if (strcmp(codeset, "UTF-8") == 0 || strcmp(codeset, "utf8") == 0 ) {
         UTF_DEBUG(("NO iconv() being used because it is not needed\n"));
         return;
     }

@@ -144,10 +158,11 @@
             output[outputLen] = 0;
             return outputLen;
         }
 
         /* Failed to do the conversion */
+        UTF_DEBUG(("iconv() failed to do the conversion\n"));
         return -1;
     }
 
     /* Just copy bytes */
     outputLen = len;