Split copy.c into four files.

Copy.c has grown really large. Split it into more manageable parts:

- copy.c now contains only a few functions that are common to COPY FROM
  and COPY TO.

- copyto.c contains code for COPY TO.

- copyfrom.c contains code for initializing COPY FROM, and inserting the
  tuples to the correct table.

- copyfromparse.c contains code for reading from the client/file/program,
  and parsing the input text/CSV/binary format into tuples.

All of these parts are fairly complicated, and fairly independent of each
other. There is a patch being discussed to implement parallel COPY FROM,
which will add a lot of new code to the COPY FROM path, and another patch
which would allow INSERTs to use the same multi-insert machinery as COPY
FROM, both of which will require refactoring that code. With those two
patches, there's going to be a lot of code churn in copy.c anyway, so now
seems like a good time to do this refactoring.

The CopyStateData struct is also split. All the formatting options, like
FORMAT, QUOTE, ESCAPE, are put in a new CopyFormatOption struct, which
is used by both COPY FROM and TO. Other state data are kept in separate
CopyFromStateData and CopyToStateData structs.

Reviewed-by: Soumyadeep Chakraborty, Erik Rijkers, Vignesh C, Andres Freund
Discussion: https://www.postgresql.org/message-id/8e15b560-f387-7acc-ac90-763986617bfb%40iki.fi

contrib/file_fdw/file_fdw.c

@@ -105,7 +105,7 @@ typedef struct FileFdwExecutionState
 	bool		is_program;		/* true if filename represents an OS command */
 	List	   *options;		/* merged COPY options, excluding filename and
 								 * is_program */
-	CopyState	cstate;			/* COPY execution state */
+	CopyFromState cstate;		/* COPY execution state */
 } FileFdwExecutionState;
 
 /*
@@ -655,7 +655,7 @@ fileBeginForeignScan(ForeignScanState *node, int eflags)
 	char	   *filename;
 	bool		is_program;
 	List	   *options;
-	CopyState	cstate;
+	CopyFromState cstate;
 	FileFdwExecutionState *festate;
 
 	/*
@@ -677,6 +677,7 @@ fileBeginForeignScan(ForeignScanState *node, int eflags)
 	 */
 	cstate = BeginCopyFrom(NULL,
 						   node->ss.ss_currentRelation,
+						   NULL,
 						   filename,
 						   is_program,
 						   NULL,
@@ -752,6 +753,7 @@ fileReScanForeignScan(ForeignScanState *node)
 
 	festate->cstate = BeginCopyFrom(NULL,
 									node->ss.ss_currentRelation,
+									NULL,
 									festate->filename,
 									festate->is_program,
 									NULL,
@@ -1107,7 +1109,7 @@ file_acquire_sample_rows(Relation onerel, int elevel,
 	char	   *filename;
 	bool		is_program;
 	List	   *options;
-	CopyState	cstate;
+	CopyFromState cstate;
 	ErrorContextCallback errcallback;
 	MemoryContext oldcontext = CurrentMemoryContext;
 	MemoryContext tupcontext;
@@ -1125,7 +1127,7 @@ file_acquire_sample_rows(Relation onerel, int elevel,
 	/*
 	 * Create CopyState from FDW options.
 	 */
-	cstate = BeginCopyFrom(NULL, onerel, filename, is_program, NULL, NIL,
+	cstate = BeginCopyFrom(NULL, onerel, NULL, filename, is_program, NULL, NIL,
 						   options);
 
 	/*

src/backend/commands/Makefile

@@ -24,6 +24,9 @@ OBJS = \
 	constraint.o \
 	conversioncmds.o \
 	copy.o \
+	copyfrom.o \
+	copyfromparse.o \
+	copyto.o \
 	createas.o \
 	dbcommands.o \
 	define.o \

src/backend/replication/logical/tablesync.c

@@ -749,7 +749,7 @@ copy_table(Relation rel)
 	LogicalRepRelation lrel;
 	WalRcvExecResult *res;
 	StringInfoData cmd;
-	CopyState	cstate;
+	CopyFromState cstate;
 	List	   *attnamelist;
 	ParseState *pstate;
 
@@ -800,7 +800,7 @@ copy_table(Relation rel)
 										 NULL, false, false);
 
 	attnamelist = make_copy_attnamelist(relmapentry);
-	cstate = BeginCopyFrom(pstate, rel, NULL, false, copy_read_data, attnamelist, NIL);
+	cstate = BeginCopyFrom(pstate, rel, NULL, NULL, false, copy_read_data, attnamelist, NIL);
 
 	/* Do the copy */
 	(void) CopyFrom(cstate);

src/include/commands/copy.h

@@ -19,26 +19,71 @@
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 
-/* CopyStateData is private in commands/copy.c */
-typedef struct CopyStateData *CopyState;
+/*
+ * A struct to hold COPY options, in a parsed form. All of these are related
+ * to formatting, except for 'freeze', which doesn't really belong here, but
+ * it's expedient to parse it along with all the other options.
+ */
+typedef struct CopyFormatOptions
+{
+	/* parameters from the COPY command */
+	int			file_encoding;	/* file or remote side's character encoding,
+								 * -1 if not specified */
+	bool		binary;			/* binary format? */
+	bool		freeze;			/* freeze rows on loading? */
+	bool		csv_mode;		/* Comma Separated Value format? */
+	bool		header_line;	/* CSV header line? */
+	char	   *null_print;		/* NULL marker string (server encoding!) */
+	int			null_print_len; /* length of same */
+	char	   *null_print_client;	/* same converted to file encoding */
+	char	   *delim;			/* column delimiter (must be 1 byte) */
+	char	   *quote;			/* CSV quote char (must be 1 byte) */
+	char	   *escape;			/* CSV escape char (must be 1 byte) */
+	List	   *force_quote;	/* list of column names */
+	bool		force_quote_all;	/* FORCE_QUOTE *? */
+	bool	   *force_quote_flags;	/* per-column CSV FQ flags */
+	List	   *force_notnull;	/* list of column names */
+	bool	   *force_notnull_flags;	/* per-column CSV FNN flags */
+	List	   *force_null;		/* list of column names */
+	bool	   *force_null_flags;	/* per-column CSV FN flags */
+	bool		convert_selectively;	/* do selective binary conversion? */
+	List	   *convert_select; /* list of column names (can be NIL) */
+} CopyFormatOptions;
+
+/* These are private in commands/copy[from|to].c */
+typedef struct CopyFromStateData *CopyFromState;
+typedef struct CopyToStateData *CopyToState;
+
 typedef int (*copy_data_source_cb) (void *outbuf, int minread, int maxread);
 
 extern void DoCopy(ParseState *state, const CopyStmt *stmt,
 				   int stmt_location, int stmt_len,
 				   uint64 *processed);
 
-extern void ProcessCopyOptions(ParseState *pstate, CopyState cstate, bool is_from, List *options);
-extern CopyState BeginCopyFrom(ParseState *pstate, Relation rel, const char *filename,
+extern void ProcessCopyOptions(ParseState *pstate, CopyFormatOptions *ops_out, bool is_from, List *options);
+extern CopyFromState BeginCopyFrom(ParseState *pstate, Relation rel, Node *whereClause,
+							   const char *filename,
 							   bool is_program, copy_data_source_cb data_source_cb, List *attnamelist, List *options);
-extern void EndCopyFrom(CopyState cstate);
-extern bool NextCopyFrom(CopyState cstate, ExprContext *econtext,
+extern void EndCopyFrom(CopyFromState cstate);
+extern bool NextCopyFrom(CopyFromState cstate, ExprContext *econtext,
 						 Datum *values, bool *nulls);
-extern bool NextCopyFromRawFields(CopyState cstate,
+extern bool NextCopyFromRawFields(CopyFromState cstate,
 								  char ***fields, int *nfields);
 extern void CopyFromErrorCallback(void *arg);
 
-extern uint64 CopyFrom(CopyState cstate);
+extern uint64 CopyFrom(CopyFromState cstate);
 
 extern DestReceiver *CreateCopyDestReceiver(void);
 
+/*
+ * internal prototypes
+ */
+extern CopyToState BeginCopyTo(ParseState *pstate, Relation rel, RawStmt *query,
+							   Oid queryRelId, const char *filename, bool is_program,
+							   List *attnamelist, List *options);
+extern void EndCopyTo(CopyToState cstate);
+extern uint64 DoCopyTo(CopyToState cstate);
+extern List *CopyGetAttnums(TupleDesc tupDesc, Relation rel,
+							List *attnamelist);
+
 #endif							/* COPY_H */

src/include/commands/copyfrom_internal.h

+/*-------------------------------------------------------------------------
+ *
+ * copyfrom_internal.h
+ *	  Internal definitions for COPY FROM command.
+ *
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/commands/copyfrom_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef COPYFROM_INTERNAL_H
+#define COPYFROM_INTERNAL_H
+
+#include "commands/copy.h"
+#include "commands/trigger.h"
+
+/*
+ * Represents the different source cases we need to worry about at
+ * the bottom level
+ */
+typedef enum CopySource
+{
+	COPY_FILE,					/* from file (or a piped program) */
+	COPY_OLD_FE,				/* from frontend (2.0 protocol) */
+	COPY_NEW_FE,				/* from frontend (3.0 protocol) */
+	COPY_CALLBACK				/* from callback function */
+} CopySource;
+
+/*
+ *	Represents the end-of-line terminator type of the input
+ */
+typedef enum EolType
+{
+	EOL_UNKNOWN,
+	EOL_NL,
+	EOL_CR,
+	EOL_CRNL
+} EolType;
+
+/*
+ * Represents the heap insert method to be used during COPY FROM.
+ */
+typedef enum CopyInsertMethod
+{
+	CIM_SINGLE,					/* use table_tuple_insert or fdw routine */
+	CIM_MULTI,					/* always use table_multi_insert */
+	CIM_MULTI_CONDITIONAL		/* use table_multi_insert only if valid */
+} CopyInsertMethod;
+
+/*
+ * This struct contains all the state variables used throughout a COPY FROM
+ * operation.
+ *
+ * Multi-byte encodings: all supported client-side encodings encode multi-byte
+ * characters by having the first byte's high bit set. Subsequent bytes of the
+ * character can have the high bit not set. When scanning data in such an
+ * encoding to look for a match to a single-byte (ie ASCII) character, we must
+ * use the full pg_encoding_mblen() machinery to skip over multibyte
+ * characters, else we might find a false match to a trailing byte. In
+ * supported server encodings, there is no possibility of a false match, and
+ * it's faster to make useless comparisons to trailing bytes than it is to
+ * invoke pg_encoding_mblen() to skip over them. encoding_embeds_ascii is true
+ * when we have to do it the hard way.
+ */
+typedef struct CopyFromStateData
+{
+	/* low-level state data */
+	CopySource	copy_src;		/* type of copy source */
+	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
+	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
+	bool		reached_eof;	/* true if we read to end of copy data (not
+								 * all copy_src types maintain this) */
+
+	EolType		eol_type;		/* EOL type of input */
+	int			file_encoding;	/* file or remote side's character encoding */
+	bool		need_transcoding;	/* file encoding diff from server? */
+	bool		encoding_embeds_ascii;	/* ASCII can be non-first byte? */
+
+	/* parameters from the COPY command */
+	Relation	rel;			/* relation to copy from */
+	List	   *attnumlist;		/* integer list of attnums to copy */
+	char	   *filename;		/* filename, or NULL for STDIN */
+	bool		is_program;		/* is 'filename' a program to popen? */
+	copy_data_source_cb data_source_cb; /* function for reading data */
+
+	CopyFormatOptions opts;
+	bool	   *convert_select_flags;	/* per-column CSV/TEXT CS flags */
+	Node	   *whereClause;	/* WHERE condition (or NULL) */
+
+	/* these are just for error messages, see CopyFromErrorCallback */
+	const char *cur_relname;	/* table name for error messages */
+	uint64		cur_lineno;		/* line number for error messages */
+	const char *cur_attname;	/* current att for error messages */
+	const char *cur_attval;		/* current att value for error messages */
+
+	/*
+	 * Working state
+	 */
+	MemoryContext copycontext;	/* per-copy execution context */
+
+	AttrNumber	num_defaults;
+	FmgrInfo   *in_functions;	/* array of input functions for each attrs */
+	Oid		   *typioparams;	/* array of element types for in_functions */
+	int		   *defmap;			/* array of default att numbers */
+	ExprState **defexprs;		/* array of default att expressions */
+	bool		volatile_defexprs;	/* is any of defexprs volatile? */
+	List	   *range_table;
+	ExprState  *qualexpr;
+
+	TransitionCaptureState *transition_capture;
+
+	/*
+	 * These variables are used to reduce overhead in COPY FROM.
+	 *
+	 * attribute_buf holds the separated, de-escaped text for each field of
+	 * the current line.  The CopyReadAttributes functions return arrays of
+	 * pointers into this buffer.  We avoid palloc/pfree overhead by re-using
+	 * the buffer on each cycle.
+	 *
+	 * In binary COPY FROM, attribute_buf holds the binary data for the
+	 * current field, but the usage is otherwise similar.
+	 */
+	StringInfoData attribute_buf;
+
+	/* field raw data pointers found by COPY FROM */
+
+	int			max_fields;
+	char	  **raw_fields;
+
+	/*
+	 * Similarly, line_buf holds the whole input line being processed. The
+	 * input cycle is first to read the whole line into line_buf, convert it
+	 * to server encoding there, and then extract the individual attribute
+	 * fields into attribute_buf.  line_buf is preserved unmodified so that we
+	 * can display it in error messages if appropriate.  (In binary mode,
+	 * line_buf is not used.)
+	 */
+	StringInfoData line_buf;
+	bool		line_buf_converted; /* converted to server encoding? */
+	bool		line_buf_valid; /* contains the row being processed? */
+
+	/*
+	 * Finally, raw_buf holds raw data read from the data source (file or
+	 * client connection).  In text mode, CopyReadLine parses this data
+	 * sufficiently to locate line boundaries, then transfers the data to
+	 * line_buf and converts it.  In binary mode, CopyReadBinaryData fetches
+	 * appropriate amounts of data from this buffer.  In both modes, we
+	 * guarantee that there is a \0 at raw_buf[raw_buf_len].
+	 */
+#define RAW_BUF_SIZE 65536		/* we palloc RAW_BUF_SIZE+1 bytes */
+	char	   *raw_buf;
+	int			raw_buf_index;	/* next byte to process */
+	int			raw_buf_len;	/* total # of bytes stored */
+	/* Shorthand for number of unconsumed bytes available in raw_buf */
+#define RAW_BUF_BYTES(cstate) ((cstate)->raw_buf_len - (cstate)->raw_buf_index)
+} CopyFromStateData;
+
+extern void ReceiveCopyBegin(CopyFromState cstate);
+extern void ReceiveCopyBinaryHeader(CopyFromState cstate);
+
+#endif							/* COPYFROM_INTERNAL_H */