Support multi-line headers in COPY FROM command.

The COPY FROM command now accepts a non-negative integer for the HEADER option,
allowing multiple header lines to be skipped. This is useful when the input
contains multi-line headers that should be ignored during data import.

Author: Shinya Kato <shinya11.kato@gmail.com>
Co-authored-by: Fujii Masao <masao.fujii@gmail.com>
Reviewed-by: Yugo Nagata <nagata@sraoss.co.jp>
Discussion: https://postgr.es/m/CAOzEurRPxfzbxqeOPF_AGnAUOYf=Wk0we+1LQomPNUNtyZGBZw@mail.gmail.com

src/backend/commands/copy.c

@@ -322,11 +322,13 @@ DoCopy(ParseState *pstate, const CopyStmt *stmt,
 }
 
 /*
- * Extract a CopyHeaderChoice value from a DefElem.  This is like
- * defGetBoolean() but also accepts the special value "match".
+ * Extract the CopyFormatOptions.header_line value from a DefElem.
+ *
+ * Parses the HEADER option for COPY, which can be a boolean, a non-negative
+ * integer (number of lines to skip), or the special value "match".
  */
-static CopyHeaderChoice
-defGetCopyHeaderChoice(DefElem *def, bool is_from)
+static int
+defGetCopyHeaderOption(DefElem *def, bool is_from)
 {
 	/*
 	 * If no parameter value given, assume "true" is meant.
@@ -335,20 +337,27 @@ defGetCopyHeaderChoice(DefElem *def, bool is_from)
 		return COPY_HEADER_TRUE;
 
 	/*
-	 * Allow 0, 1, "true", "false", "on", "off", or "match".
+	 * Allow 0, 1, "true", "false", "on", "off", a non-negative integer, or
+	 * "match".
 	 */
 	switch (nodeTag(def->arg))
 	{
 		case T_Integer:
-			switch (intVal(def->arg))
 			{
-				case 0:
-					return COPY_HEADER_FALSE;
-				case 1:
-					return COPY_HEADER_TRUE;
-				default:
-					/* otherwise, error out below */
-					break;
+				int			ival = intVal(def->arg);
+
+				if (ival < 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+							 errmsg("a negative integer value cannot be "
+									"specified for %s", def->defname)));
+
+				if (!is_from && ival > 1)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("cannot use multi-line header in COPY TO")));
+
+				return ival;
 			}
 			break;
 		default:
@@ -381,7 +390,8 @@ defGetCopyHeaderChoice(DefElem *def, bool is_from)
 	}
 	ereport(ERROR,
 			(errcode(ERRCODE_SYNTAX_ERROR),
-			 errmsg("%s requires a Boolean value or \"match\"",
+			 errmsg("%s requires a Boolean value, a non-negative integer, "
+					"or the string \"match\"",
 					def->defname)));
 	return COPY_HEADER_FALSE;	/* keep compiler quiet */
 }
@@ -566,7 +576,7 @@ ProcessCopyOptions(ParseState *pstate,
 			if (header_specified)
 				errorConflictingDefElem(defel, pstate);
 			header_specified = true;
-			opts_out->header_line = defGetCopyHeaderChoice(defel, is_from);
+			opts_out->header_line = defGetCopyHeaderOption(defel, is_from);
 		}
 		else if (strcmp(defel->defname, "quote") == 0)
 		{
@@ -769,7 +779,7 @@ ProcessCopyOptions(ParseState *pstate,
 				 errmsg("COPY delimiter cannot be \"%s\"", opts_out->delim)));
 
 	/* Check header */
-	if (opts_out->binary && opts_out->header_line)
+	if (opts_out->binary && opts_out->header_line != COPY_HEADER_FALSE)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 		/*- translator: %s is the name of a COPY option, e.g. ON_ERROR */

src/backend/commands/copyfromparse.c

@@ -771,21 +771,30 @@ static pg_attribute_always_inline bool
 NextCopyFromRawFieldsInternal(CopyFromState cstate, char ***fields, int *nfields, bool is_csv)
 {
 	int			fldct;
-	bool		done;
+	bool		done = false;
 
 	/* only available for text or csv input */
 	Assert(!cstate->opts.binary);
 
 	/* on input check that the header line is correct if needed */
-	if (cstate->cur_lineno == 0 && cstate->opts.header_line)
+	if (cstate->cur_lineno == 0 && cstate->opts.header_line != COPY_HEADER_FALSE)
 	{
 		ListCell   *cur;
 		TupleDesc	tupDesc;
+		int			lines_to_skip = cstate->opts.header_line;
+
+		/* If set to "match", one header line is skipped */
+		if (cstate->opts.header_line == COPY_HEADER_MATCH)
+			lines_to_skip = 1;
 
 		tupDesc = RelationGetDescr(cstate->rel);
 
-		cstate->cur_lineno++;
-		done = CopyReadLine(cstate, is_csv);
+		for (int i = 0; i < lines_to_skip; i++)
+		{
+			cstate->cur_lineno++;
+			if ((done = CopyReadLine(cstate, is_csv)))
+				break;
+		}
 
 		if (cstate->opts.header_line == COPY_HEADER_MATCH)
 		{

src/backend/commands/copyto.c

@@ -199,7 +199,7 @@ CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc)
 														  cstate->file_encoding);
 
 	/* if a header has been requested send the line */
-	if (cstate->opts.header_line)
+	if (cstate->opts.header_line == COPY_HEADER_TRUE)
 	{
 		ListCell   *cur;
 		bool		hdr_delim = false;

src/include/commands/copy.h

@@ -20,15 +20,12 @@
 #include "tcop/dest.h"
 
 /*
- * Represents whether a header line should be present, and whether it must
- * match the actual names (which implies "true").
+ * Represents whether a header line must match the actual names
+ * (which implies "true"), and whether it should be present.
  */
-typedef enum CopyHeaderChoice
-{
-	COPY_HEADER_FALSE = 0,
-	COPY_HEADER_TRUE,
-	COPY_HEADER_MATCH,
-} CopyHeaderChoice;
+#define COPY_HEADER_MATCH	-1
+#define COPY_HEADER_FALSE	0
+#define COPY_HEADER_TRUE	1
 
 /*
  * Represents where to save input processing errors.  More values to be added
@@ -64,7 +61,8 @@ typedef struct CopyFormatOptions
 	bool		binary;			/* binary format? */
 	bool		freeze;			/* freeze rows on loading? */
 	bool		csv_mode;		/* Comma Separated Value format? */
-	CopyHeaderChoice header_line;	/* header line? */
+	int			header_line;	/* number of lines to skip or COPY_HEADER_XXX
+								 * value (see the above) */
 	char	   *null_print;		/* NULL marker string (server encoding!) */
 	int			null_print_len; /* length of same */
 	char	   *null_print_client;	/* same converted to file encoding */

src/test/regress/expected/copy.out

@@ -81,6 +81,29 @@ copy copytest4 to stdout (header);
 c1	colname with tab: \t
 1	a
 2	b
+-- test multi-line header line feature
+create temp table copytest5 (c1 int);
+copy copytest5 from stdin (format csv, header 2);
+copy copytest5 to stdout (header);
+c1
+1
+2
+truncate copytest5;
+copy copytest5 from stdin (format csv, header 4);
+select count(*) from copytest5;
+ count 
+-------
+     0
+(1 row)
+
+truncate copytest5;
+copy copytest5 from stdin (format csv, header 5);
+select count(*) from copytest5;
+ count 
+-------
+     0
+(1 row)
+
 -- test copy from with a partitioned table
 create table parted_copytest (
 	a int,
@@ -224,7 +247,7 @@ alter table header_copytest add column c text;
 copy header_copytest to stdout with (header match);
 ERROR:  cannot use "match" with HEADER in COPY TO
 copy header_copytest from stdin with (header wrong_choice);
-ERROR:  header requires a Boolean value or "match"
+ERROR:  header requires a Boolean value, a non-negative integer, or the string "match"
 -- works
 copy header_copytest from stdin with (header match);
 copy header_copytest (c, a, b) from stdin with (header match);

src/test/regress/expected/copy2.out

@@ -132,6 +132,12 @@ COPY x from stdin with (reject_limit 1);
 ERROR:  COPY REJECT_LIMIT requires ON_ERROR to be set to IGNORE
 COPY x from stdin with (on_error ignore, reject_limit 0);
 ERROR:  REJECT_LIMIT (0) must be greater than zero
+COPY x from stdin with (header -1);
+ERROR:  a negative integer value cannot be specified for header
+COPY x from stdin with (header 2.5);
+ERROR:  header requires a Boolean value, a non-negative integer, or the string "match"
+COPY x to stdout with (header 2);
+ERROR:  cannot use multi-line header in COPY TO
 -- too many columns in column list: should fail
 COPY x (a, b, c, d, e, d, c) from stdin;
 ERROR:  column "d" specified more than once

src/test/regress/sql/copy.sql

@@ -94,6 +94,36 @@ this is just a line full of junk that would error out if parsed
 
 copy copytest4 to stdout (header);
 
+-- test multi-line header line feature
+
+create temp table copytest5 (c1 int);
+
+copy copytest5 from stdin (format csv, header 2);
+this is a first header line.
+this is a second header line.
+1
+2
+\.
+copy copytest5 to stdout (header);
+
+truncate copytest5;
+copy copytest5 from stdin (format csv, header 4);
+this is a first header line.
+this is a second header line.
+1
+2
+\.
+select count(*) from copytest5;
+
+truncate copytest5;
+copy copytest5 from stdin (format csv, header 5);
+this is a first header line.
+this is a second header line.
+1
+2
+\.
+select count(*) from copytest5;
+
 -- test copy from with a partitioned table
 create table parted_copytest (
 	a int,

src/test/regress/sql/copy2.sql

@@ -90,6 +90,9 @@ COPY x to stdout (format BINARY, on_error unsupported);
 COPY x from stdin (log_verbosity unsupported);
 COPY x from stdin with (reject_limit 1);
 COPY x from stdin with (on_error ignore, reject_limit 0);
+COPY x from stdin with (header -1);
+COPY x from stdin with (header 2.5);
+COPY x to stdout with (header 2);
 
 -- too many columns in column list: should fail
 COPY x (a, b, c, d, e, d, c) from stdin;

src/tools/pgindent/typedefs.list

@@ -521,7 +521,6 @@ CopyFormatOptions
 CopyFromRoutine
 CopyFromState
 CopyFromStateData
-CopyHeaderChoice
 CopyInsertMethod
 CopyLogVerbosityChoice
 CopyMethod