v24-0003-Refactor-COPY-FROM-to-use-format-callback-functi.patch

From e1f2e5f906443487229b4c6aa664bfa9e3c7fbdc Mon Sep 17 00:00:00 2001
From: Masahiko Sawada <sawada.mshk@gmail.com>
Date: Mon, 18 Nov 2024 16:32:43 -0800
Subject: [PATCH v24 3/4] Refactor COPY FROM to use format callback functions.

This commit introduces a new CopyFromRoutine struct, which is a set of
callback routines to read tuples in a specific format. It also makes
COPY FROM with the existing formats (text, CSV, and binary) utilize
these format callbacks.

This change is a preliminary step towards making the COPY TO command
extensible in terms of output formats.

Similar to XXXX, this refactoring contributes to a performance
improvement by reducing the number of "if" branches that need to be
checked on a per-row basis when sending field representations in text
or CSV mode. The performance benchmark results showed up to a 10%
performance gain in text or CSV mode.

Author: Sutou Kouhei
Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada
Reviewed-by: Junwang Zhao
Discussion: https://postgr.es/m/20231204.153548.2126325458835528809.kou@clear-code.com
---
 src/backend/commands/copyfrom.c          | 201 ++++++++--
 src/backend/commands/copyfromparse.c     | 487 +++++++++++++----------
 src/include/commands/copy.h              |   2 -
 src/include/commands/copyapi.h           |  44 +-
 src/include/commands/copyfrom_internal.h |  12 +
 src/tools/pgindent/typedefs.list         |   1 +
 6 files changed, 501 insertions(+), 246 deletions(-)

diff --git a/src/backend/commands/copyfrom.c b/src/backend/commands/copyfrom.c
index 754cb49616..e77986f9a9 100644
--- a/src/backend/commands/copyfrom.c
+++ b/src/backend/commands/copyfrom.c
@@ -106,6 +106,157 @@ typedef struct CopyMultiInsertInfo
 /* non-export function prototypes */
 static void ClosePipeFromProgram(CopyFromState cstate);
 
+
+/*
+ * CopyFromRoutine implementations for text and CSV.
+ */
+
+/*
+ * CopyFromTextLikeInFunc
+ *
+ * Assign input function data for a relation's attribute in text/CSV format.
+ */
+static void
+CopyFromTextLikeInFunc(CopyFromState cstate, Oid atttypid,
+					   FmgrInfo *finfo, Oid *typioparam)
+{
+	Oid			func_oid;
+
+	getTypeInputInfo(atttypid, &func_oid, typioparam);
+	fmgr_info(func_oid, finfo);
+}
+
+/*
+ * CopyFromTextLikeStart
+ *
+ * Start of COPY FROM for text/CSV format.
+ */
+static void
+CopyFromTextLikeStart(CopyFromState cstate, TupleDesc tupDesc)
+{
+	AttrNumber	attr_count;
+
+	/*
+	 * If encoding conversion is needed, we need another buffer to hold the
+	 * converted input data.  Otherwise, we can just point input_buf to the
+	 * same buffer as raw_buf.
+	 */
+	if (cstate->need_transcoding)
+	{
+		cstate->input_buf = (char *) palloc(INPUT_BUF_SIZE + 1);
+		cstate->input_buf_index = cstate->input_buf_len = 0;
+	}
+	else
+		cstate->input_buf = cstate->raw_buf;
+	cstate->input_reached_eof = false;
+
+	initStringInfo(&cstate->line_buf);
+
+	/*
+	 * Create workspace for CopyReadAttributes results; used by CSV and text
+	 * format.
+	 */
+	attr_count = list_length(cstate->attnumlist);
+	cstate->max_fields = attr_count;
+	cstate->raw_fields = (char **) palloc(attr_count * sizeof(char *));
+}
+
+/*
+ * CopyFromTextLikeEnd
+ *
+ * End of COPY FROM for text/CSV format.
+ */
+static void
+CopyFromTextLikeEnd(CopyFromState cstate)
+{
+	/* nothing to do */
+}
+
+/*
+ * CopyFromRoutine implementation for "binary".
+ */
+
+/*
+ * CopyFromBinaryInFunc
+ *
+ * Assign input function data for a relation's attribute in binary format.
+ */
+static void
+CopyFromBinaryInFunc(CopyFromState cstate, Oid atttypid,
+					 FmgrInfo *finfo, Oid *typioparam)
+{
+	Oid			func_oid;
+
+	getTypeBinaryInputInfo(atttypid, &func_oid, typioparam);
+	fmgr_info(func_oid, finfo);
+}
+
+/*
+ * CopyFromBinaryStart
+ *
+ * Start of COPY FROM for binary format.
+ */
+static void
+CopyFromBinaryStart(CopyFromState cstate, TupleDesc tupDesc)
+{
+	/* Read and verify binary header */
+	ReceiveCopyBinaryHeader(cstate);
+}
+
+/*
+ * CopyFromBinaryEnd
+ *
+ * End of COPY FROM for binary format.
+ */
+static void
+CopyFromBinaryEnd(CopyFromState cstate)
+{
+	/* nothing to do */
+}
+
+/*
+ * Routines assigned to each format.
++
+ * CSV and text share the same implementation, at the exception of the
+ * per-row callback.
+ */
+static const CopyFromRoutine CopyFromRoutineText = {
+	.CopyFromInFunc = CopyFromTextLikeInFunc,
+	.CopyFromStart = CopyFromTextLikeStart,
+	.CopyFromOneRow = CopyFromTextOneRow,
+	.CopyFromEnd = CopyFromTextLikeEnd,
+};
+
+static const CopyFromRoutine CopyFromRoutineCSV = {
+	.CopyFromInFunc = CopyFromTextLikeInFunc,
+	.CopyFromStart = CopyFromTextLikeStart,
+	.CopyFromOneRow = CopyFromCSVOneRow,
+	.CopyFromEnd = CopyFromTextLikeEnd,
+};
+
+static const CopyFromRoutine CopyFromRoutineBinary = {
+	.CopyFromInFunc = CopyFromBinaryInFunc,
+	.CopyFromStart = CopyFromBinaryStart,
+	.CopyFromOneRow = CopyFromBinaryOneRow,
+	.CopyFromEnd = CopyFromBinaryEnd,
+};
+
+/*
+ * Define the COPY FROM routines to use for a format.
+ */
+static const CopyFromRoutine *
+CopyFromGetRoutine(CopyFormatOptions opts)
+{
+	if (opts.csv_mode)
+		return &CopyFromRoutineCSV;
+	else if (opts.binary)
+		return &CopyFromRoutineBinary;
+
+	/* default is text */
+	return &CopyFromRoutineText;
+}
+
+
 /*
  * error context callback for COPY FROM
  *
@@ -1396,7 +1547,6 @@ BeginCopyFrom(ParseState *pstate,
 				num_defaults;
 	FmgrInfo   *in_functions;
 	Oid		   *typioparams;
-	Oid			in_func_oid;
 	int		   *defmap;
 	ExprState **defexprs;
 	MemoryContext oldcontext;
@@ -1428,6 +1578,9 @@ BeginCopyFrom(ParseState *pstate,
 	/* Extract options from the statement node tree */
 	ProcessCopyOptions(pstate, &cstate->opts, true /* is_from */ , options);
 
+	/* Set format routine */
+	cstate->routine = CopyFromGetRoutine(cstate->opts);
+
 	/* Process the target relation */
 	cstate->rel = rel;
 
@@ -1583,25 +1736,6 @@ BeginCopyFrom(ParseState *pstate,
 	cstate->raw_buf_index = cstate->raw_buf_len = 0;
 	cstate->raw_reached_eof = false;
 
-	if (!cstate->opts.binary)
-	{
-		/*
-		 * If encoding conversion is needed, we need another buffer to hold
-		 * the converted input data.  Otherwise, we can just point input_buf
-		 * to the same buffer as raw_buf.
-		 */
-		if (cstate->need_transcoding)
-		{
-			cstate->input_buf = (char *) palloc(INPUT_BUF_SIZE + 1);
-			cstate->input_buf_index = cstate->input_buf_len = 0;
-		}
-		else
-			cstate->input_buf = cstate->raw_buf;
-		cstate->input_reached_eof = false;
-
-		initStringInfo(&cstate->line_buf);
-	}
-
 	initStringInfo(&cstate->attribute_buf);
 
 	/* Assign range table and rteperminfos, we'll need them in CopyFrom. */
@@ -1634,13 +1768,9 @@ BeginCopyFrom(ParseState *pstate,
 			continue;
 
 		/* Fetch the input function and typioparam info */
-		if (cstate->opts.binary)
-			getTypeBinaryInputInfo(att->atttypid,
-								   &in_func_oid, &typioparams[attnum - 1]);
-		else
-			getTypeInputInfo(att->atttypid,
-							 &in_func_oid, &typioparams[attnum - 1]);
-		fmgr_info(in_func_oid, &in_functions[attnum - 1]);
+		cstate->routine->CopyFromInFunc(cstate, att->atttypid,
+										&in_functions[attnum - 1],
+										&typioparams[attnum - 1]);
 
 		/* Get default info if available */
 		defexprs[attnum - 1] = NULL;
@@ -1775,20 +1905,7 @@ BeginCopyFrom(ParseState *pstate,
 
 	pgstat_progress_update_multi_param(3, progress_cols, progress_vals);
 
-	if (cstate->opts.binary)
-	{
-		/* Read and verify binary header */
-		ReceiveCopyBinaryHeader(cstate);
-	}
-
-	/* create workspace for CopyReadAttributes results */
-	if (!cstate->opts.binary)
-	{
-		AttrNumber	attr_count = list_length(cstate->attnumlist);
-
-		cstate->max_fields = attr_count;
-		cstate->raw_fields = (char **) palloc(attr_count * sizeof(char *));
-	}
+	cstate->routine->CopyFromStart(cstate, tupDesc);
 
 	MemoryContextSwitchTo(oldcontext);
 
@@ -1801,6 +1918,8 @@ BeginCopyFrom(ParseState *pstate,
 void
 EndCopyFrom(CopyFromState cstate)
 {
+	cstate->routine->CopyFromEnd(cstate);
+
 	/* No COPY FROM related resources except memory. */
 	if (cstate->is_program)
 	{
diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index d1d43b53d8..0447c4df7e 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -140,8 +140,8 @@ static const char BinarySignature[11] = "PGCOPY\n\377\r\n\0";
 
 
 /* non-export function prototypes */
-static bool CopyReadLine(CopyFromState cstate);
-static bool CopyReadLineText(CopyFromState cstate);
+static bool CopyReadLine(CopyFromState cstate, bool is_csv);
+static pg_attribute_always_inline bool CopyReadLineText(CopyFromState cstate, bool is_csv);
 static int	CopyReadAttributesText(CopyFromState cstate);
 static int	CopyReadAttributesCSV(CopyFromState cstate);
 static Datum CopyReadBinaryAttribute(CopyFromState cstate, FmgrInfo *flinfo,
@@ -741,8 +741,8 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
  *
  * NOTE: force_not_null option are not applied to the returned fields.
  */
-bool
-NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
+static pg_attribute_always_inline bool
+NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields, bool is_csv)
 {
 	int			fldct;
 	bool		done;
@@ -759,13 +759,17 @@ NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
 		tupDesc = RelationGetDescr(cstate->rel);
 
 		cstate->cur_lineno++;
-		done = CopyReadLine(cstate);
+		done = CopyReadLine(cstate, is_csv);
 
 		if (cstate->opts.header_line == COPY_HEADER_MATCH)
 		{
 			int			fldnum;
 
-			if (cstate->opts.csv_mode)
+			/*
+			 * is_csv will be optimized away by compiler, as argument is
+			 * constant at caller.
+			 */
+			if (is_csv)
 				fldct = CopyReadAttributesCSV(cstate);
 			else
 				fldct = CopyReadAttributesText(cstate);
@@ -809,7 +813,7 @@ NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
 	cstate->cur_lineno++;
 
 	/* Actually read the line into memory here */
-	done = CopyReadLine(cstate);
+	done = CopyReadLine(cstate, is_csv);
 
 	/*
 	 * EOF at start of line means we're done.  If we see EOF after some
@@ -819,8 +823,13 @@ NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
 	if (done && cstate->line_buf.len == 0)
 		return false;
 
-	/* Parse the line into de-escaped field values */
-	if (cstate->opts.csv_mode)
+	/*
+	 * Parse the line into de-escaped field values
+	 *
+	 * is_csv will be optimized away by compiler, as argument is constant at
+	 * caller.
+	 */
+	if (is_csv)
 		fldct = CopyReadAttributesCSV(cstate);
 	else
 		fldct = CopyReadAttributesText(cstate);
@@ -831,233 +840,299 @@ NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
 }
 
 /*
- * Read next tuple from file for COPY FROM. Return false if no more tuples.
+ * CopyFromTextLikeOneRow
  *
- * 'econtext' is used to evaluate default expression for each column that is
- * either not read from the file or is using the DEFAULT option of COPY FROM.
- * It can be NULL when no default values are used, i.e. when all columns are
- * read from the file, and DEFAULT option is unset.
+ * Copy one row to a set of `values` and `nulls` for the text and CSV
+ * formats.
  *
- * 'values' and 'nulls' arrays must be the same length as columns of the
- * relation passed to BeginCopyFrom. This function fills the arrays.
+ * Workhorse for CopyFromTextOneRow() and CopyFromCSVOneRow().
  */
-bool
-NextCopyFrom(CopyFromState cstate, ExprContext *econtext,
-			 Datum *values, bool *nulls)
+static pg_attribute_always_inline bool
+CopyFromTextLikeOneRow(CopyFromState cstate,
+					   ExprContext *econtext,
+					   Datum *values,
+					   bool *nulls,
+					   bool is_csv)
 {
 	TupleDesc	tupDesc;
-	AttrNumber	num_phys_attrs,
-				attr_count,
-				num_defaults = cstate->num_defaults;
+	AttrNumber	attr_count;
 	FmgrInfo   *in_functions = cstate->in_functions;
 	Oid		   *typioparams = cstate->typioparams;
-	int			i;
-	int		   *defmap = cstate->defmap;
 	ExprState **defexprs = cstate->defexprs;
+	char	  **field_strings;
+	ListCell   *cur;
+	int			fldct;
+	int			fieldno;
+	char	   *string;
 
 	tupDesc = RelationGetDescr(cstate->rel);
-	num_phys_attrs = tupDesc->natts;
 	attr_count = list_length(cstate->attnumlist);
 
-	/* Initialize all values for row to NULL */
-	MemSet(values, 0, num_phys_attrs * sizeof(Datum));
-	MemSet(nulls, true, num_phys_attrs * sizeof(bool));
-	MemSet(cstate->defaults, false, num_phys_attrs * sizeof(bool));
+	/* read raw fields in the next line */
+	if (!NextCopyFromRawFields(cstate, &field_strings, &fldct, is_csv))
+		return false;
 
-	if (!cstate->opts.binary)
-	{
-		char	  **field_strings;
-		ListCell   *cur;
-		int			fldct;
-		int			fieldno;
-		char	   *string;
+	/* check for overflowing fields */
+	if (attr_count > 0 && fldct > attr_count)
+		ereport(ERROR,
+				(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
+				 errmsg("extra data after last expected column")));
 
-		/* read raw fields in the next line */
-		if (!NextCopyFromRawFields(cstate, &field_strings, &fldct))
-			return false;
+	fieldno = 0;
+
+	/* Loop to read the user attributes on the line. */
+	foreach(cur, cstate->attnumlist)
+	{
+		int			attnum = lfirst_int(cur);
+		int			m = attnum - 1;
+		Form_pg_attribute att = TupleDescAttr(tupDesc, m);
 
-		/* check for overflowing fields */
-		if (attr_count > 0 && fldct > attr_count)
+		if (fieldno >= fldct)
 			ereport(ERROR,
 					(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-					 errmsg("extra data after last expected column")));
-
-		fieldno = 0;
+					 errmsg("missing data for column \"%s\"",
+							NameStr(att->attname))));
+		string = field_strings[fieldno++];
 
-		/* Loop to read the user attributes on the line. */
-		foreach(cur, cstate->attnumlist)
+		if (cstate->convert_select_flags &&
+			!cstate->convert_select_flags[m])
 		{
-			int			attnum = lfirst_int(cur);
-			int			m = attnum - 1;
-			Form_pg_attribute att = TupleDescAttr(tupDesc, m);
-
-			if (fieldno >= fldct)
-				ereport(ERROR,
-						(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-						 errmsg("missing data for column \"%s\"",
-								NameStr(att->attname))));
-			string = field_strings[fieldno++];
-
-			if (cstate->convert_select_flags &&
-				!cstate->convert_select_flags[m])
-			{
-				/* ignore input field, leaving column as NULL */
-				continue;
-			}
+			/* ignore input field, leaving column as NULL */
+			continue;
+		}
 
-			if (cstate->opts.csv_mode)
+		if (is_csv)
+		{
+			if (string == NULL &&
+				cstate->opts.force_notnull_flags[m])
 			{
-				if (string == NULL &&
-					cstate->opts.force_notnull_flags[m])
-				{
-					/*
-					 * FORCE_NOT_NULL option is set and column is NULL -
-					 * convert it to the NULL string.
-					 */
-					string = cstate->opts.null_print;
-				}
-				else if (string != NULL && cstate->opts.force_null_flags[m]
-						 && strcmp(string, cstate->opts.null_print) == 0)
-				{
-					/*
-					 * FORCE_NULL option is set and column matches the NULL
-					 * string. It must have been quoted, or otherwise the
-					 * string would already have been set to NULL. Convert it
-					 * to NULL as specified.
-					 */
-					string = NULL;
-				}
+				/*
+				 * FORCE_NOT_NULL option is set and column is NULL - convert
+				 * it to the NULL string.
+				 */
+				string = cstate->opts.null_print;
 			}
-
-			cstate->cur_attname = NameStr(att->attname);
-			cstate->cur_attval = string;
-
-			if (string != NULL)
-				nulls[m] = false;
-
-			if (cstate->defaults[m])
+			else if (string != NULL && cstate->opts.force_null_flags[m]
+					 && strcmp(string, cstate->opts.null_print) == 0)
 			{
 				/*
-				 * The caller must supply econtext and have switched into the
-				 * per-tuple memory context in it.
+				 * FORCE_NULL option is set and column matches the NULL
+				 * string. It must have been quoted, or otherwise the string
+				 * would already have been set to NULL. Convert it to NULL as
+				 * specified.
 				 */
-				Assert(econtext != NULL);
-				Assert(CurrentMemoryContext == econtext->ecxt_per_tuple_memory);
-
-				values[m] = ExecEvalExpr(defexprs[m], econtext, &nulls[m]);
+				string = NULL;
 			}
+		}
+
+		cstate->cur_attname = NameStr(att->attname);
+		cstate->cur_attval = string;
 
+		if (string != NULL)
+			nulls[m] = false;
+
+		if (cstate->defaults[m])
+		{
 			/*
-			 * If ON_ERROR is specified with IGNORE, skip rows with soft
-			 * errors
+			 * The caller must supply econtext and have switched into the
+			 * per-tuple memory context in it.
 			 */
-			else if (!InputFunctionCallSafe(&in_functions[m],
-											string,
-											typioparams[m],
-											att->atttypmod,
-											(Node *) cstate->escontext,
-											&values[m]))
-			{
-				Assert(cstate->opts.on_error != COPY_ON_ERROR_STOP);
+			Assert(econtext != NULL);
+			Assert(CurrentMemoryContext == econtext->ecxt_per_tuple_memory);
 
-				cstate->num_errors++;
+			values[m] = ExecEvalExpr(defexprs[m], econtext, &nulls[m]);
+		}
 
-				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 ON_ERROR is specified with IGNORE, skip rows with soft errors
+		 */
+		else if (!InputFunctionCallSafe(&in_functions[m],
+										string,
+										typioparams[m],
+										att->atttypmod,
+										(Node *) cstate->escontext,
+										&values[m]))
+		{
+			Assert(cstate->opts.on_error != COPY_ON_ERROR_STOP);
 
-					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;
+			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));
 
-				return true;
+				/* reset relname_only */
+				cstate->relname_only = false;
 			}
 
-			cstate->cur_attname = NULL;
-			cstate->cur_attval = NULL;
+			return true;
 		}
 
-		Assert(fieldno == attr_count);
+		cstate->cur_attname = NULL;
+		cstate->cur_attval = NULL;
 	}
-	else
-	{
-		/* binary */
-		int16		fld_count;
-		ListCell   *cur;
 
-		cstate->cur_lineno++;
+	Assert(fieldno == attr_count);
 
-		if (!CopyGetInt16(cstate, &fld_count))
-		{
-			/* EOF detected (end of file, or protocol-level EOF) */
-			return false;
-		}
+	return true;
+}
 
-		if (fld_count == -1)
-		{
-			/*
-			 * Received EOF marker.  Wait for the protocol-level EOF, and
-			 * complain if it doesn't come immediately.  In COPY FROM STDIN,
-			 * this ensures that we correctly handle CopyFail, if client
-			 * chooses to send that now.  When copying from file, we could
-			 * ignore the rest of the file like in text mode, but we choose to
-			 * be consistent with the COPY FROM STDIN case.
-			 */
-			char		dummy;
 
-			if (CopyReadBinaryData(cstate, &dummy, 1) > 0)
-				ereport(ERROR,
-						(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-						 errmsg("received copy data after EOF marker")));
-			return false;
-		}
+/*
+ * CopyFromTextOneRow
+ *
+ * Per-row callback for COPY FROM with text format.
+ */
+bool
+CopyFromTextOneRow(CopyFromState cstate,
+				   ExprContext *econtext,
+				   Datum *values,
+				   bool *nulls)
+{
+	return CopyFromTextLikeOneRow(cstate, econtext, values, nulls, false);
+}
+
+/*
+ * CopyFromCSVOneRow
+ *
+ * Per-row callback for COPY FROM with CSV format.
+ */
+bool
+CopyFromCSVOneRow(CopyFromState cstate,
+				  ExprContext *econtext,
+				  Datum *values,
+				  bool *nulls)
+{
+	return CopyFromTextLikeOneRow(cstate, econtext, values, nulls, true);
+}
+
+/*
+ * CopyFromBinaryOneRow
+ *
+ * Copy one row to a set of `values` and `nulls` for the binary format.
+ */
+bool
+CopyFromBinaryOneRow(CopyFromState cstate, ExprContext *econtext,
+					 Datum *values, bool *nulls)
+{
+	TupleDesc	tupDesc;
+	AttrNumber	attr_count;
+	FmgrInfo   *in_functions = cstate->in_functions;
+	Oid		   *typioparams = cstate->typioparams;
+	int16		fld_count;
+	ListCell   *cur;
+
+	tupDesc = RelationGetDescr(cstate->rel);
+	attr_count = list_length(cstate->attnumlist);
+
+	cstate->cur_lineno++;
 
-		if (fld_count != attr_count)
+	if (!CopyGetInt16(cstate, &fld_count))
+	{
+		/* EOF detected (end of file, or protocol-level EOF) */
+		return false;
+	}
+
+	if (fld_count == -1)
+	{
+		/*
+		 * Received EOF marker.  Wait for the protocol-level EOF, and complain
+		 * if it doesn't come immediately.  In COPY FROM STDIN, this ensures
+		 * that we correctly handle CopyFail, if client chooses to send that
+		 * now.  When copying from file, we could ignore the rest of the file
+		 * like in text mode, but we choose to be consistent with the COPY
+		 * FROM STDIN case.
+		 */
+		char		dummy;
+
+		if (CopyReadBinaryData(cstate, &dummy, 1) > 0)
 			ereport(ERROR,
 					(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-					 errmsg("row field count is %d, expected %d",
-							(int) fld_count, attr_count)));
+					 errmsg("received copy data after EOF marker")));
+		return false;
+	}
 
-		foreach(cur, cstate->attnumlist)
-		{
-			int			attnum = lfirst_int(cur);
-			int			m = attnum - 1;
-			Form_pg_attribute att = TupleDescAttr(tupDesc, m);
-
-			cstate->cur_attname = NameStr(att->attname);
-			values[m] = CopyReadBinaryAttribute(cstate,
-												&in_functions[m],
-												typioparams[m],
-												att->atttypmod,
-												&nulls[m]);
-			cstate->cur_attname = NULL;
-		}
+	if (fld_count != attr_count)
+		ereport(ERROR,
+				(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
+				 errmsg("row field count is %d, expected %d",
+						(int) fld_count, attr_count)));
+
+	foreach(cur, cstate->attnumlist)
+	{
+		int			attnum = lfirst_int(cur);
+		int			m = attnum - 1;
+		Form_pg_attribute att = TupleDescAttr(tupDesc, m);
+
+		cstate->cur_attname = NameStr(att->attname);
+		values[m] = CopyReadBinaryAttribute(cstate,
+											&in_functions[m],
+											typioparams[m],
+											att->atttypmod,
+											&nulls[m]);
+		cstate->cur_attname = NULL;
 	}
 
+	return true;
+}
+
+/*
+ * Read next tuple from file for COPY FROM. Return false if no more tuples.
+ *
+ * 'econtext' is used to evaluate default expression for each column that is
+ * either not read from the file or is using the DEFAULT option of COPY FROM.
+ * It can be NULL when no default values are used, i.e. when all columns are
+ * read from the file, and DEFAULT option is unset.
+ *
+ * 'values' and 'nulls' arrays must be the same length as columns of the
+ * relation passed to BeginCopyFrom. This function fills the arrays.
+ */
+bool
+NextCopyFrom(CopyFromState cstate, ExprContext *econtext,
+			 Datum *values, bool *nulls)
+{
+	TupleDesc	tupDesc;
+	AttrNumber	num_phys_attrs,
+				num_defaults = cstate->num_defaults;
+	int			i;
+	int		   *defmap = cstate->defmap;
+	ExprState **defexprs = cstate->defexprs;
+
+	tupDesc = RelationGetDescr(cstate->rel);
+	num_phys_attrs = tupDesc->natts;
+
+	/* Initialize all values for row to NULL */
+	MemSet(values, 0, num_phys_attrs * sizeof(Datum));
+	MemSet(nulls, true, num_phys_attrs * sizeof(bool));
+	MemSet(cstate->defaults, false, num_phys_attrs * sizeof(bool));
+
+	if (!cstate->routine->CopyFromOneRow(cstate, econtext, values, nulls))
+		return false;
+
 	/*
 	 * Now compute and insert any defaults available for the columns not
 	 * provided by the input data.  Anything not processed here or above will
@@ -1087,7 +1162,7 @@ NextCopyFrom(CopyFromState cstate, ExprContext *econtext,
  * in the final value of line_buf.
  */
 static bool
-CopyReadLine(CopyFromState cstate)
+CopyReadLine(CopyFromState cstate, bool is_csv)
 {
 	bool		result;
 
@@ -1095,7 +1170,7 @@ CopyReadLine(CopyFromState cstate)
 	cstate->line_buf_valid = false;
 
 	/* Parse data and transfer into line_buf */
-	result = CopyReadLineText(cstate);
+	result = CopyReadLineText(cstate, is_csv);
 
 	if (result)
 	{
@@ -1162,8 +1237,8 @@ CopyReadLine(CopyFromState cstate)
 /*
  * CopyReadLineText - inner loop of CopyReadLine for text mode
  */
-static bool
-CopyReadLineText(CopyFromState cstate)
+static pg_attribute_always_inline bool
+CopyReadLineText(CopyFromState cstate, bool is_csv)
 {
 	char	   *copy_input_buf;
 	int			input_buf_ptr;
@@ -1178,7 +1253,11 @@ CopyReadLineText(CopyFromState cstate)
 	char		quotec = '\0';
 	char		escapec = '\0';
 
-	if (cstate->opts.csv_mode)
+	/*
+	 * is_csv will be optimized away by compiler, as argument is constant at
+	 * caller.
+	 */
+	if (is_csv)
 	{
 		quotec = cstate->opts.quote[0];
 		escapec = cstate->opts.escape[0];
@@ -1255,7 +1334,11 @@ CopyReadLineText(CopyFromState cstate)
 		prev_raw_ptr = input_buf_ptr;
 		c = copy_input_buf[input_buf_ptr++];
 
-		if (cstate->opts.csv_mode)
+		/*
+		 * is_csv will be optimized away by compiler, as argument is constant
+		 * at caller.
+		 */
+		if (is_csv)
 		{
 			/*
 			 * If character is '\r', we may need to look ahead below.  Force
@@ -1294,7 +1377,7 @@ CopyReadLineText(CopyFromState cstate)
 		}
 
 		/* Process \r */
-		if (c == '\r' && (!cstate->opts.csv_mode || !in_quote))
+		if (c == '\r' && (!is_csv || !in_quote))
 		{
 			/* Check for \r\n on first line, _and_ handle \r\n. */
 			if (cstate->eol_type == EOL_UNKNOWN ||
@@ -1322,10 +1405,10 @@ CopyReadLineText(CopyFromState cstate)
 					if (cstate->eol_type == EOL_CRNL)
 						ereport(ERROR,
 								(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-								 !cstate->opts.csv_mode ?
+								 !is_csv ?
 								 errmsg("literal carriage return found in data") :
 								 errmsg("unquoted carriage return found in data"),
-								 !cstate->opts.csv_mode ?
+								 !is_csv ?
 								 errhint("Use \"\\r\" to represent carriage return.") :
 								 errhint("Use quoted CSV field to represent carriage return.")));
 
@@ -1339,10 +1422,10 @@ CopyReadLineText(CopyFromState cstate)
 			else if (cstate->eol_type == EOL_NL)
 				ereport(ERROR,
 						(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-						 !cstate->opts.csv_mode ?
+						 !is_csv ?
 						 errmsg("literal carriage return found in data") :
 						 errmsg("unquoted carriage return found in data"),
-						 !cstate->opts.csv_mode ?
+						 !is_csv ?
 						 errhint("Use \"\\r\" to represent carriage return.") :
 						 errhint("Use quoted CSV field to represent carriage return.")));
 			/* If reach here, we have found the line terminator */
@@ -1350,15 +1433,15 @@ CopyReadLineText(CopyFromState cstate)
 		}
 
 		/* Process \n */
-		if (c == '\n' && (!cstate->opts.csv_mode || !in_quote))
+		if (c == '\n' && (!is_csv || !in_quote))
 		{
 			if (cstate->eol_type == EOL_CR || cstate->eol_type == EOL_CRNL)
 				ereport(ERROR,
 						(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-						 !cstate->opts.csv_mode ?
+						 !is_csv ?
 						 errmsg("literal newline found in data") :
 						 errmsg("unquoted newline found in data"),
-						 !cstate->opts.csv_mode ?
+						 !is_csv ?
 						 errhint("Use \"\\n\" to represent newline.") :
 						 errhint("Use quoted CSV field to represent newline.")));
 			cstate->eol_type = EOL_NL;	/* in case not set yet */
@@ -1370,7 +1453,7 @@ CopyReadLineText(CopyFromState cstate)
 		 * Process backslash, except in CSV mode where backslash is a normal
 		 * character.
 		 */
-		if (c == '\\' && !cstate->opts.csv_mode)
+		if (c == '\\' && !is_csv)
 		{
 			char		c2;
 
diff --git a/src/include/commands/copy.h b/src/include/commands/copy.h
index 4002a7f538..f2409013fb 100644
--- a/src/include/commands/copy.h
+++ b/src/include/commands/copy.h
@@ -107,8 +107,6 @@ extern CopyFromState BeginCopyFrom(ParseState *pstate, Relation rel, Node *where
 extern void EndCopyFrom(CopyFromState cstate);
 extern bool NextCopyFrom(CopyFromState cstate, ExprContext *econtext,
 						 Datum *values, bool *nulls);
-extern bool NextCopyFromRawFields(CopyFromState cstate,
-								  char ***fields, int *nfields);
 extern void CopyFromErrorCallback(void *arg);
 extern char *CopyLimitPrintoutLength(const char *str);
 
diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h
index 99981b1579..224fda172e 100644
--- a/src/include/commands/copyapi.h
+++ b/src/include/commands/copyapi.h
@@ -1,7 +1,7 @@
 /*-------------------------------------------------------------------------
  *
  * copyapi.h
- *	  API for COPY TO handlers
+ *	  API for COPY TO/FROM handlers
  *
  *
  * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
@@ -56,4 +56,46 @@ typedef struct CopyToRoutine
 	void		(*CopyToEnd) (CopyToState cstate);
 } CopyToRoutine;
 
+/*
+ * API structure for a COPY FROM format implementation.	 Note this must be
+ * allocated in a server-lifetime manner, typically as a static const struct.
+ */
+typedef struct CopyFromRoutine
+{
+	/*
+	 * Called when COPY FROM is started to set up the input functions
+	 * associated with the relation's attributes writing to.  `finfo` can be
+	 * optionally filled to provide the catalog information of the input
+	 * function.  `typioparam` can be optionally filled to define the OID of
+	 * the type to pass to the input function.	`atttypid` is the OID of data
+	 * type used by the relation's attribute.
+	 */
+	void		(*CopyFromInFunc) (CopyFromState cstate, Oid atttypid,
+								   FmgrInfo *finfo, Oid *typioparam);
+
+	/*
+	 * Called when COPY FROM is started.
+	 *
+	 * `tupDesc` is the tuple descriptor of the relation where the data needs
+	 * to be copied.  This can be used for any initialization steps required
+	 * by a format.
+	 */
+	void		(*CopyFromStart) (CopyFromState cstate, TupleDesc tupDesc);
+
+	/*
+	 * Copy one row to a set of `values` and `nulls` of size tupDesc->natts.
+	 *
+	 * 'econtext' is used to evaluate default expression for each column that
+	 * is either not read from the file or is using the DEFAULT option of COPY
+	 * FROM.  It is NULL if no default values are used.
+	 *
+	 * Returns false if there are no more tuples to copy.
+	 */
+	bool		(*CopyFromOneRow) (CopyFromState cstate, ExprContext *econtext,
+								   Datum *values, bool *nulls);
+
+	/* Called when COPY FROM has ended. */
+	void		(*CopyFromEnd) (CopyFromState cstate);
+} CopyFromRoutine;
+
 #endif							/* COPYAPI_H */
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index cad52fcc78..c11b5ff3cc 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -15,6 +15,7 @@
 #define COPYFROM_INTERNAL_H
 
 #include "commands/copy.h"
+#include "commands/copyapi.h"
 #include "commands/trigger.h"
 #include "nodes/miscnodes.h"
 
@@ -58,6 +59,9 @@ typedef enum CopyInsertMethod
  */
 typedef struct CopyFromStateData
 {
+	/* format routine */
+	const CopyFromRoutine *routine;
+
 	/* low-level state data */
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
@@ -183,4 +187,12 @@ typedef struct CopyFromStateData
 extern void ReceiveCopyBegin(CopyFromState cstate);
 extern void ReceiveCopyBinaryHeader(CopyFromState cstate);
 
+/* Callbacks for CopyFromRoutine->CopyFromOneRow */
+extern bool CopyFromTextOneRow(CopyFromState cstate, ExprContext *econtext,
+							   Datum *values, bool *nulls);
+extern bool CopyFromCSVOneRow(CopyFromState cstate, ExprContext *econtext,
+							  Datum *values, bool *nulls);
+extern bool CopyFromBinaryOneRow(CopyFromState cstate, ExprContext *econtext,
+								 Datum *values, bool *nulls);
+
 #endif							/* COPYFROM_INTERNAL_H */
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e3334d9485..7fab5c479e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -492,6 +492,7 @@ ConvertRowtypeExpr
 CookedConstraint
 CopyDest
 CopyFormatOptions
+CopyFromRoutine
 CopyFromState
 CopyFromStateData
 CopyHeaderChoice
-- 
2.43.5