Add new COPY option LOG_VERBOSITY.

This commit adds a new COPY option LOG_VERBOSITY, which controls the
amount of messages emitted during processing. Valid values are
'default' and 'verbose'.

This is currently used in COPY FROM when ON_ERROR option is set to
ignore. If 'verbose' is specified, a NOTICE message is emitted for
each discarded row, providing additional information such as line
number, column name, and the malformed value. This helps users to
identify problematic rows that failed to load.

Author: Bharath Rupireddy
Reviewed-by: Michael Paquier, Atsushi Torikoshi, Masahiko Sawada
Discussion: https://www.postgresql.org/message-id/CALj2ACUk700cYhx1ATRQyRw-fBM%2BaRo6auRAitKGff7XNmYfqQ%40mail.gmail.com

1 files changed, 35 insertions, 0 deletions

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index 5682d5d054b..7ddd27f5c6e 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -967,7 +967,42 @@ NextCopyFrom(CopyFromState cstate, ExprContext *econtext,
 											(Node *) cstate->escontext,
 											&values[m]))
 			{
+				Assert(cstate->opts.on_error != COPY_ON_ERROR_STOP);
+
 				cstate->num_errors++;
+
+				if (cstate->opts.log_verbosity == COPY_LOG_VERBOSITY_VERBOSE)
+				{
+					/*
+					 * Since we emit line number and column info in the below
+					 * notice message, we suppress error context information
+					 * other than the relation name.
+					 */
+					Assert(!cstate->relname_only);
+					cstate->relname_only = true;
+
+					if (cstate->cur_attval)
+					{
+						char	   *attval;
+
+						attval = CopyLimitPrintoutLength(cstate->cur_attval);
+						ereport(NOTICE,
+								errmsg("skipping row due to data type incompatibility at line %llu for column %s: \"%s\"",
+									   (unsigned long long) cstate->cur_lineno,
+									   cstate->cur_attname,
+									   attval));
+						pfree(attval);
+					}
+					else
+						ereport(NOTICE,
+								errmsg("skipping row due to data type incompatibility at line %llu for column %s: null input",
+									   (unsigned long long) cstate->cur_lineno,
+									   cstate->cur_attname));
+
+					/* reset relname_only */
+					cstate->relname_only = false;
+				}
+
 				return true;
 			}