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 FROM command
extensible in terms of input formats.

Similar to 2e4127b6d2d, 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 ~5% performance
gain in text or CSV mode.

Author: Sutou Kouhei <[email protected]>
Reviewed-by: Masahiko Sawada <[email protected]>
Reviewed-by: Michael Paquier <[email protected]>
Reviewed-by: Andres Freund <[email protected]>
Reviewed-by: Tomas Vondra <[email protected]>
Reviewed-by: Junwang Zhao <[email protected]>
Discussion: https://postgr.es/m/[email protected]

3 files changed, 60 insertions, 3 deletions

diff --git a/src/include/commands/copy.h b/src/include/commands/copy.h
index 06dfdfef721..7bc044e2816 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 bd2d386816e..2a2d2f9876b 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) 1996-2025, PostgreSQL Global Development Group
@@ -54,4 +54,52 @@ 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
+{
+	/*
+	 * Set input function information. This callback is called once at the
+	 * beginning of COPY FROM.
+	 *
+	 * '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);
+
+	/*
+	 * Start a COPY FROM. This callback is called once at the beginning of
+	 * COPY FROM.
+	 *
+	 * '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);
+
+	/*
+	 * Read one row from the source and fill *values and *nulls.
+	 *
+	 * '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 read.
+	 */
+	bool		(*CopyFromOneRow) (CopyFromState cstate, ExprContext *econtext,
+								   Datum *values, bool *nulls);
+
+	/*
+	 * End a COPY FROM. This callback is called once at the end of COPY FROM.
+	 */
+	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 1d8ac8f62e6..c8b22af22d8 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -58,6 +58,9 @@ typedef enum CopyInsertMethod
  */
 typedef struct CopyFromStateData
 {
+	/* format routine */
+	const struct CopyFromRoutine *routine;
+
 	/* low-level state data */
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
@@ -183,4 +186,12 @@ typedef struct CopyFromStateData
 extern void ReceiveCopyBegin(CopyFromState cstate);
 extern void ReceiveCopyBinaryHeader(CopyFromState cstate);
 
+/* One-row callbacks for built-in formats defined in copyfromparse.c */
+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 */