Fix COPY FROM when database encoding is SQL_ASCII.

hlinnaka · hlinnaka · commit f82595ac903e · 2022-05-29T23:57:16.000+03:00
In the codepath when no encoding conversion is required, the check for incomplete character at the end of input incorrectly used server encoding's max character length, instead of the client's. Usually the server and client encodings are the same when we're not performing encoding conversion, but SQL_ASCII is an exception. In the passing, also fix some outdated comments that still talked about the old COPY protocol. It was removed in v14. Per bug #17501 from Vitaly Voronov. Backpatch to v14 where this was introduced. Discussion: https://www.postgresql.org/message-id/17501-128b1dd039362ae6@postgresql.org
diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
@@ -443,7 +443,7 @@ CopyConvertBuf(CopyFromState cstate)
 			 * least one character, and a failure to do so means that we've
 			 * hit an invalid byte sequence.
 			 */
-			if (cstate->raw_reached_eof || unverifiedlen >= pg_database_encoding_max_length())
+			if (cstate->raw_reached_eof || unverifiedlen >= pg_encoding_max_length(cstate->file_encoding))
 				cstate->input_reached_error = true;
 			return;
 		}
@@ -1124,14 +1124,12 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * TODO: We could just force four bytes of read-ahead and avoid the
+		 * many calls to IF_NEED_REFILL_AND_NOT_EOF_CONTINUE().  That was
+		 * unsafe with the old v2 COPY protocol, but we don't support that
+		 * anymore.
 		 */
 		if (input_buf_ptr >= copy_buf_len || need_data)
 		{
@@ -1166,9 +1164,6 @@ CopyReadLineText(CopyFromState cstate)
 			 * Force fetch of the next character if we don't already have it.
 			 * We need to do this before changing CSV state, in case one of
 			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
 			 */
 			if (c == '\\' || c == '\r')
 			{
