encoding: Restore old lookup order in xmlOpenCharEncodingHandler

When looking up encodings with xmlLookupCharEncodingHandler, the
returned handler can have a different name than requested
(capitalization, internal aliases). This should eventually be fixed.
For now we revert part of commit 5b893fa, start the lookup with
xmlFindHandler and add an explicit check for UTF-8.

Should fix the encoding name issue mentioned in #749.

Author: nwellnhof

encoding.c

@@ -1160,7 +1160,7 @@ xmlParseCharEncoding(const char* name)
     if (!strcmp(upper, "SHIFT_JIS")) return(XML_CHAR_ENCODING_SHIFT_JIS);
     if (!strcmp(upper, "EUC-JP")) return(XML_CHAR_ENCODING_EUC_JP);
 
-    return(XML_CHAR_ENCODING_NONE);
+    return(XML_CHAR_ENCODING_ERROR);
 }
 
 /**
@@ -1935,7 +1935,9 @@ int
 xmlOpenCharEncodingHandler(const char *name, int output,
                            xmlCharEncodingHandler **out) {
     const char *nalias;
+    const char *norig;
     xmlCharEncoding enc;
+    int ret;
 
     if (out == NULL)
         return(XML_ERR_ARGUMENT);
@@ -1944,30 +1946,32 @@ xmlOpenCharEncodingHandler(const char *name, int output,
     if (name == NULL)
         return(XML_ERR_ARGUMENT);
 
+    if ((xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF-8") == 0) ||
+        (xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF8") == 0))
+        return(XML_ERR_OK);
+
     /*
      * Do the alias resolution
      */
+    norig = name;
     nalias = xmlGetEncodingAlias(name);
     if (nalias != NULL)
 	name = nalias;
 
+    ret = xmlFindHandler(name, output, out);
+    if (*out != NULL)
+        return(0);
+    if (ret != XML_ERR_UNSUPPORTED_ENCODING)
+        return(ret);
+
     /*
-     * UTF-16 needs the built-in handler which is only available via
-     * xmlFindHandler.
+     * Fallback using the canonical names
+     *
+     * TODO: We should make sure that the name of the returned
+     * handler equals norig.
      */
-    if (xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF16") == 0) {
-        name = "UTF-16";
-    } else if (xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF-16") != 0) {
-        enc = xmlParseCharEncoding(name);
-        if (enc != XML_CHAR_ENCODING_NONE) {
-            int res = xmlLookupCharEncodingHandler(enc, out);
-
-            if (res != XML_ERR_UNSUPPORTED_ENCODING)
-                return(res);
-        }
-    }
-
-    return(xmlFindHandler(name, output, out));
+    enc = xmlParseCharEncoding(norig);
+    return(xmlLookupCharEncodingHandler(enc, out));
 }
 
 /**

testparser.c

@@ -49,7 +49,8 @@ testUnsupportedEncoding(void) {
     xmlFreeDoc(doc);
 
     error = xmlGetLastError();
-    if (error->code != XML_ERR_UNSUPPORTED_ENCODING ||
+    if (error == NULL ||
+        error->code != XML_ERR_UNSUPPORTED_ENCODING ||
         error->level != XML_ERR_WARNING ||
         strcmp(error->message, "Unsupported encoding: #unsupported\n") != 0)
     {