[CF 4810] v19 - COPY ON_ERROR 'NULL'

This branch was automatically generated by a robot using patches from an
email thread registered at:

https://commitfest.postgresql.org/patch/4810

The branch will be overwritten each time a new patch version is posted to
the thread, and also periodically to check for bitrot caused by changes
on the master branch.

Patch(es): https://www.postgresql.org/message-id/CACJufxF0c3k5O8up9NOY-m02nyJ0f6N1tKxZwjCewTqvvFmbLw@mail.gmail.com
Author(s): jian he

Author: Commitfest Bot

doc/src/sgml/ref/copy.sgml

@@ -412,23 +412,37 @@ COPY { <replaceable class="parameter">table_name</replaceable> [ ( <replaceable
       Specifies how to behave when encountering an error converting a column's
       input value into its data type.
       An <replaceable class="parameter">error_action</replaceable> value of
-      <literal>stop</literal> means fail the command, while
-      <literal>ignore</literal> means discard the input row and continue with the next one.
+      <literal>stop</literal> means fail the command,
+      <literal>ignore</literal> means discard the input row and continue with the next one,
+      and <literal>set_null</literal> means replace column containing invalid
+      input value with <literal>NULL</literal> and move to the next field.
       The default is <literal>stop</literal>.
      </para>
      <para>
-      The <literal>ignore</literal> option is applicable only for <command>COPY FROM</command>
+      The <literal>ignore</literal> and <literal>set_null</literal>
+      options are applicable only for <command>COPY FROM</command>
       when the <literal>FORMAT</literal> is <literal>text</literal> or <literal>csv</literal>.
      </para>
+    <para>
+      For <literal>ignore</literal> option, a <literal>NOTICE</literal> message
+      containing the ignored row count is emitted at the end of the <command>COPY
+      FROM</command> if at least one row was discarded.
+      For <literal>set_null</literal> option,
+      a <literal>NOTICE</literal> message indicating the number of rows
+      where invalid input values were replaced with null is emitted
+      at the end of the <command>COPY FROM</command> if at least one row was replaced.
+     </para>
      <para>
-      A <literal>NOTICE</literal> message containing the ignored row count is
-      emitted at the end of the <command>COPY FROM</command> if at least one
-      row was discarded. When <literal>LOG_VERBOSITY</literal> option is set to
-      <literal>verbose</literal>, a <literal>NOTICE</literal> message
+      When <literal>LOG_VERBOSITY</literal> option is set to <literal>verbose</literal>,
+      for <literal>ignore</literal> option, a <literal>NOTICE</literal> message
       containing the line of the input file and the column name whose input
-      conversion has failed is emitted for each discarded row.
+      conversion has failed is emitted for each discarded row;
+      for <literal>set_null</literal> option, a <literal>NOTICE</literal>
+      message containing the line of the input file and the column name where
+      value was replaced with <literal>NULL</literal> for each input conversion
+      failure.
       When it is set to <literal>silent</literal>, no message is emitted
-      regarding ignored rows.
+      regarding input conversion failed rows.
      </para>
     </listitem>
    </varlistentry>
@@ -476,7 +490,8 @@ COPY { <replaceable class="parameter">table_name</replaceable> [ ( <replaceable
      </para>
      <para>
       This is currently used in <command>COPY FROM</command> command when
-      <literal>ON_ERROR</literal> option is set to <literal>ignore</literal>.
+      <literal>ON_ERROR</literal> option is set to <literal>ignore</literal>
+      or <literal>set_null</literal>.
       </para>
     </listitem>
    </varlistentry>

src/backend/commands/copy.c

@@ -417,12 +417,14 @@ defGetCopyOnErrorChoice(DefElem *def, ParseState *pstate, bool is_from)
 				 parser_errposition(pstate, def->location)));
 
 	/*
-	 * Allow "stop", or "ignore" values.
+	 * Allow "stop", "ignore", "set_null" values.
 	 */
 	if (pg_strcasecmp(sval, "stop") == 0)
 		return COPY_ON_ERROR_STOP;
 	if (pg_strcasecmp(sval, "ignore") == 0)
 		return COPY_ON_ERROR_IGNORE;
+	if (pg_strcasecmp(sval, "set_null") == 0)
+		return COPY_ON_ERROR_SET_NULL;
 
 	ereport(ERROR,
 			(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
@@ -932,7 +934,7 @@ ProcessCopyOptions(ParseState *pstate,
 				(errcode(ERRCODE_SYNTAX_ERROR),
 				 errmsg("only ON_ERROR STOP is allowed in BINARY mode")));
 
-	if (opts_out->reject_limit && !opts_out->on_error)
+	if (opts_out->reject_limit && opts_out->on_error != COPY_ON_ERROR_IGNORE)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 		/*- translator: first and second %s are the names of COPY option, e.g.

src/backend/commands/copyfrom.c

@@ -1467,14 +1467,22 @@ CopyFrom(CopyFromState cstate)
 	/* Done, clean up */
 	error_context_stack = errcallback.previous;
 
-	if (cstate->opts.on_error != COPY_ON_ERROR_STOP &&
-		cstate->num_errors > 0 &&
+	if (cstate->num_errors > 0 &&
 		cstate->opts.log_verbosity >= COPY_LOG_VERBOSITY_DEFAULT)
-		ereport(NOTICE,
-				errmsg_plural("%" PRIu64 " row was skipped due to data type incompatibility",
-							  "%" PRIu64 " rows were skipped due to data type incompatibility",
-							  cstate->num_errors,
-							  cstate->num_errors));
+	{
+		if (cstate->opts.on_error == COPY_ON_ERROR_IGNORE)
+			ereport(NOTICE,
+					errmsg_plural("%" PRIu64 " row was skipped due to data type incompatibility",
+								  "%" PRIu64 " rows were skipped due to data type incompatibility",
+								  cstate->num_errors,
+								  cstate->num_errors));
+		else if (cstate->opts.on_error == COPY_ON_ERROR_SET_NULL)
+			ereport(NOTICE,
+					errmsg_plural("invalid values in %" PRIu64 " row was replaced with null due to data type incompatibility",
+								  "invalid values in %" PRIu64 " rows were replaced with null due to data type incompatibility",
+								  cstate->num_errors,
+								  cstate->num_errors));
+	}
 
 	if (bistate != NULL)
 		FreeBulkInsertState(bistate);
@@ -1614,6 +1622,19 @@ BeginCopyFrom(ParseState *pstate,
 		}
 	}
 
+	if (cstate->opts.on_error == COPY_ON_ERROR_SET_NULL)
+	{
+		int	attr_count = list_length(cstate->attnumlist);
+
+		cstate->domain_with_constraint = (bool *) palloc0(attr_count * sizeof(bool));
+		foreach_int(attno, cstate->attnumlist)
+		{
+			int			i = foreach_current_index(attno);
+			Form_pg_attribute att = TupleDescAttr(tupDesc, attno - 1);
+			cstate->domain_with_constraint[i] = DomainHasConstraints(att->atttypid);
+		}
+	}
+
 	/* Set up soft error handler for ON_ERROR */
 	if (cstate->opts.on_error != COPY_ON_ERROR_STOP)
 	{
@@ -1622,10 +1643,11 @@ BeginCopyFrom(ParseState *pstate,
 		cstate->escontext->error_occurred = false;
 
 		/*
-		 * Currently we only support COPY_ON_ERROR_IGNORE. We'll add other
-		 * options later
+		 * Currently we only support COPY_ON_ERROR_IGNORE, COPY_ON_ERROR_SET_NULL.
+		 * We'll add other options later
 		 */
-		if (cstate->opts.on_error == COPY_ON_ERROR_IGNORE)
+		if (cstate->opts.on_error == COPY_ON_ERROR_IGNORE ||
+			cstate->opts.on_error == COPY_ON_ERROR_SET_NULL)
 			cstate->escontext->details_wanted = false;
 	}
 	else

src/backend/commands/copyfromparse.c

@@ -956,6 +956,7 @@ CopyFromTextLikeOneRow(CopyFromState cstate, ExprContext *econtext,
 	int			fldct;
 	int			fieldno;
 	char	   *string;
+	bool		current_row_erroneous = false;
 
 	tupDesc = RelationGetDescr(cstate->rel);
 	attr_count = list_length(cstate->attnumlist);
@@ -1033,7 +1034,8 @@ CopyFromTextLikeOneRow(CopyFromState cstate, ExprContext *econtext,
 		}
 
 		/*
-		 * If ON_ERROR is specified with IGNORE, skip rows with soft errors
+		 * If ON_ERROR is specified with IGNORE, skip rows with soft errors.
+		 * If ON_ERROR is specified with SET_NULL, try to replace with null.
 		 */
 		else if (!InputFunctionCallSafe(&in_functions[m],
 										string,
@@ -1044,7 +1046,50 @@ CopyFromTextLikeOneRow(CopyFromState cstate, ExprContext *econtext,
 		{
 			Assert(cstate->opts.on_error != COPY_ON_ERROR_STOP);
 
-			cstate->num_errors++;
+			if (cstate->opts.on_error == COPY_ON_ERROR_IGNORE)
+				cstate->num_errors++;
+			else if (cstate->opts.on_error == COPY_ON_ERROR_SET_NULL)
+			{
+				cstate->escontext->error_occurred = false;
+				Assert(cstate->domain_with_constraint != NULL);
+
+				/*
+				 * If the column type is a domain with constraints, an
+				 * additional InputFunctionCallSafe may be needed to raise
+				 * errors for domain constraint violations.
+				*/
+				if (!cstate->domain_with_constraint[m] ||
+					InputFunctionCallSafe(&in_functions[m],
+										  NULL,
+										  typioparams[m],
+										  att->atttypmod,
+										  (Node *) cstate->escontext,
+										  &values[m]))
+				{
+					nulls[m] = true;
+					values[m] = (Datum) 0;
+				}
+				else if (string == NULL)
+					ereport(ERROR,
+							errcode(ERRCODE_NOT_NULL_VIOLATION),
+							errmsg("domain %s does not allow null values", format_type_be(typioparams[m])),
+							errdatatype(typioparams[m]));
+				else
+					ereport(ERROR,
+							errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+							errmsg("invalid input value for domain %s: \"%s\"",
+								   format_type_be(typioparams[m]), string));
+
+				/*
+				 * We count only the number of rows (not individual fields)
+				 * where ON_ERROR SET_NULL was successfully applied.
+				*/
+				if (!current_row_erroneous)
+				{
+					current_row_erroneous = true;
+					cstate->num_errors++;
+				}
+			}
 
 			if (cstate->opts.log_verbosity == COPY_LOG_VERBOSITY_VERBOSE)
 			{
@@ -1061,24 +1106,37 @@ CopyFromTextLikeOneRow(CopyFromState cstate, ExprContext *econtext,
 					char	   *attval;
 
 					attval = CopyLimitPrintoutLength(cstate->cur_attval);
-					ereport(NOTICE,
-							errmsg("skipping row due to data type incompatibility at line %" PRIu64 " for column \"%s\": \"%s\"",
-								   cstate->cur_lineno,
-								   cstate->cur_attname,
-								   attval));
+
+					if (cstate->opts.on_error == COPY_ON_ERROR_IGNORE)
+						ereport(NOTICE,
+								errmsg("skipping row due to data type incompatibility at line %" PRIu64 " for column \"%s\": \"%s\"",
+									   cstate->cur_lineno,
+									   cstate->cur_attname,
+									   attval));
+					else if (cstate->opts.on_error == COPY_ON_ERROR_SET_NULL)
+						ereport(NOTICE,
+								errmsg("setting to null due to data type incompatibility at line %" PRIu64 " for column \"%s\": \"%s\"",
+									   cstate->cur_lineno,
+									   cstate->cur_attname,
+									   attval));
 					pfree(attval);
 				}
 				else
-					ereport(NOTICE,
-							errmsg("skipping row due to data type incompatibility at line %" PRIu64 " for column \"%s\": null input",
-								   cstate->cur_lineno,
-								   cstate->cur_attname));
-
+				{
+					if (cstate->opts.on_error == COPY_ON_ERROR_IGNORE)
+						ereport(NOTICE,
+								errmsg("skipping row due to data type incompatibility at line %" PRIu64 " for column \"%s\": null input",
+									   cstate->cur_lineno,
+									   cstate->cur_attname));
+				}
 				/* reset relname_only */
 				cstate->relname_only = false;
 			}
 
-			return true;
+			if (cstate->opts.on_error == COPY_ON_ERROR_IGNORE)
+				return true;
+			else if (cstate->opts.on_error == COPY_ON_ERROR_SET_NULL)
+				continue;
 		}
 
 		cstate->cur_attname = NULL;

src/bin/psql/tab-complete.in.c

@@ -3353,7 +3353,7 @@ match_previous_words(int pattern_id,
 
 	/* Complete COPY <sth> FROM filename WITH (ON_ERROR */
 	else if (Matches("COPY|\\copy", MatchAny, "FROM", MatchAny, "WITH", "(", "ON_ERROR"))
-		COMPLETE_WITH("stop", "ignore");
+		COMPLETE_WITH("stop", "ignore", "set_null");
 
 	/* Complete COPY <sth> FROM filename WITH (LOG_VERBOSITY */
 	else if (Matches("COPY|\\copy", MatchAny, "FROM", MatchAny, "WITH", "(", "LOG_VERBOSITY"))

src/include/commands/copy.h

@@ -35,6 +35,7 @@ typedef enum CopyOnErrorChoice
 {
 	COPY_ON_ERROR_STOP = 0,		/* immediately throw errors, default */
 	COPY_ON_ERROR_IGNORE,		/* ignore errors */
+	COPY_ON_ERROR_SET_NULL,		/* set error field to null */
 } CopyOnErrorChoice;
 
 /*

src/include/commands/copyfrom_internal.h

@@ -108,6 +108,13 @@ typedef struct CopyFromStateData
 								 * att */
 	bool	   *defaults;		/* if DEFAULT marker was found for
 								 * corresponding att */
+	/*
+	 * Set to true if the corresponding attribute's data type is a domain with
+	 * constraints.  This field is usually NULL, except when ON_ERROR is set to
+	 * SET_NULL.
+	*/
+	bool	   *domain_with_constraint;
+
 	bool		volatile_defexprs;	/* is any of defexprs volatile? */
 	List	   *range_table;	/* single element list of RangeTblEntry */
 	List	   *rteperminfos;	/* single element list of RTEPermissionInfo */

src/test/regress/expected/copy2.out

@@ -81,6 +81,10 @@ COPY x from stdin (on_error ignore, on_error ignore);
 ERROR:  conflicting or redundant options
 LINE 1: COPY x from stdin (on_error ignore, on_error ignore);
                                             ^
+COPY x from stdin (on_error set_null, on_error ignore);
+ERROR:  conflicting or redundant options
+LINE 1: COPY x from stdin (on_error set_null, on_error ignore);
+                                              ^
 COPY x from stdin (log_verbosity default, log_verbosity verbose);
 ERROR:  conflicting or redundant options
 LINE 1: COPY x from stdin (log_verbosity default, log_verbosity verb...
@@ -92,6 +96,10 @@ COPY x from stdin (format BINARY, null 'x');
 ERROR:  cannot specify NULL in BINARY mode
 COPY x from stdin (format BINARY, on_error ignore);
 ERROR:  only ON_ERROR STOP is allowed in BINARY mode
+COPY x from stdin (format BINARY, on_error set_null);
+ERROR:  only ON_ERROR STOP is allowed in BINARY mode
+COPY x from stdin (on_error set_null, reject_limit 2);
+ERROR:  COPY REJECT_LIMIT requires ON_ERROR to be set to IGNORE
 COPY x from stdin (on_error unsupported);
 ERROR:  COPY ON_ERROR "unsupported" not recognized
 LINE 1: COPY x from stdin (on_error unsupported);
@@ -124,6 +132,10 @@ COPY x to stdout (format BINARY, on_error unsupported);
 ERROR:  COPY ON_ERROR cannot be used with COPY TO
 LINE 1: COPY x to stdout (format BINARY, on_error unsupported);
                                          ^
+COPY x to stdout (on_error set_null);
+ERROR:  COPY ON_ERROR cannot be used with COPY TO
+LINE 1: COPY x to stdout (on_error set_null);
+                          ^
 COPY x from stdin (log_verbosity unsupported);
 ERROR:  COPY LOG_VERBOSITY "unsupported" not recognized
 LINE 1: COPY x from stdin (log_verbosity unsupported);
@@ -776,6 +788,51 @@ CONTEXT:  COPY check_ign_err
 NOTICE:  skipping row due to data type incompatibility at line 8 for column "k": "a"
 CONTEXT:  COPY check_ign_err
 NOTICE:  6 rows were skipped due to data type incompatibility
+CREATE DOMAIN d_int_not_null AS INT NOT NULL CHECK(value > 0);
+CREATE DOMAIN d_int_positive_maybe_null AS INT CHECK(value > 0);
+CREATE TABLE t_on_error_null (a d_int_not_null, b d_int_positive_maybe_null, c INT);
+\pset null NULL
+--fail, column a cannot set to null value
+COPY t_on_error_null FROM STDIN WITH (on_error set_null);
+ERROR:  domain d_int_not_null does not allow null values
+CONTEXT:  COPY t_on_error_null, line 1, column a: null input
+--fail, column a is domain with not-null constraint
+COPY t_on_error_null FROM STDIN WITH (on_error set_null);
+ERROR:  invalid input value for domain d_int_not_null: "ss"
+CONTEXT:  COPY t_on_error_null, line 1, column a: "ss"
+--fail, column a cannot set to null value
+COPY t_on_error_null FROM STDIN WITH (on_error set_null);
+ERROR:  invalid input value for domain d_int_not_null: "-1"
+CONTEXT:  COPY t_on_error_null, line 1, column a: "-1"
+--fail. less data
+COPY t_on_error_null FROM STDIN WITH (delimiter ',', on_error set_null);
+ERROR:  missing data for column "c"
+CONTEXT:  COPY t_on_error_null, line 1: "1,1"
+--fail. extra data
+COPY t_on_error_null FROM STDIN WITH (delimiter ',', on_error set_null);
+ERROR:  extra data after last expected column
+CONTEXT:  COPY t_on_error_null, line 1: "1,2,3,4"
+--ok
+COPY t_on_error_null FROM STDIN WITH (on_error set_null, log_verbosity verbose);
+NOTICE:  setting to null due to data type incompatibility at line 1 for column "b": "x1"
+CONTEXT:  COPY t_on_error_null
+NOTICE:  setting to null due to data type incompatibility at line 1 for column "c": "yx"
+CONTEXT:  COPY t_on_error_null
+NOTICE:  setting to null due to data type incompatibility at line 2 for column "b": "zx"
+CONTEXT:  COPY t_on_error_null
+NOTICE:  setting to null due to data type incompatibility at line 3 for column "c": "ea"
+CONTEXT:  COPY t_on_error_null
+NOTICE:  invalid values in 3 rows were replaced with null due to data type incompatibility
+-- check inserted content
+select * from t_on_error_null;
+ a  |  b   |  c   
+----+------+------
+ 10 | NULL | NULL
+ 11 | NULL |   12
+ 13 |   14 | NULL
+(3 rows)
+
+\pset null ''
 -- tests for on_error option with log_verbosity and null constraint via domain
 CREATE DOMAIN dcheck_ign_err2 varchar(15) NOT NULL;
 CREATE TABLE check_ign_err2 (n int, m int[], k int, l dcheck_ign_err2);
@@ -835,6 +892,9 @@ DROP VIEW instead_of_insert_tbl_view;
 DROP VIEW instead_of_insert_tbl_view_2;
 DROP FUNCTION fun_instead_of_insert_tbl();
 DROP TABLE check_ign_err;
+DROP TABLE t_on_error_null;
+DROP DOMAIN d_int_not_null;
+DROP DOMAIN d_int_positive_maybe_null;
 DROP TABLE check_ign_err2;
 DROP DOMAIN dcheck_ign_err2;
 DROP TABLE hard_err;