Add 'noError' argument to encoding conversion functions.

With the 'noError' argument, you can try to convert a buffer without
knowing the character boundaries beforehand. The functions now need to
return the number of input bytes successfully converted.

This is is a backwards-incompatible change, if you have created a custom
encoding conversion with CREATE CONVERSION. This adds a check to
pg_upgrade for that, refusing the upgrade if there are any user-defined
encoding conversions. Custom conversions are very rare, there are no
commonly used extensions that I know of that uses that feature. No other
objects can depend on conversions, so if you do have one, you can fairly
easily drop it before upgrading, and recreate it after the upgrade with
an updated version.

Add regression tests for built-in encoding conversions. This doesn't cover
every conversion, but it covers all the internal functions in conv.c that
are used to implement the conversions.

Reviewed-by: John Naylor
Discussion: https://www.postgresql.org/message-id/e7861509-3960-538a-9025-b75a61188e01%40iki.fi

src/backend/utils/error/elog.c

@@ -2271,6 +2271,8 @@ write_console(const char *line, int len)
 	 * Conversion on non-win32 platforms is not implemented yet. It requires
 	 * non-throw version of pg_do_encoding_conversion(), that converts
 	 * unconvertable characters to '?' without errors.
+	 *
+	 * XXX: We have a no-throw version now. It doesn't convert to '?' though.
 	 */
 #endif