From 47aa927d65e483331f9b2010499b4c7f0bfb562c Mon Sep 17 00:00:00 2001 From: Masahiko Sawada Date: Mon, 22 Jun 2026 11:50:27 -0700 Subject: [PATCH v2 1/4] Move Copy[From|To]StateData to copy_state.h. Author: Reviewed-by: Discussion: https://postgr.es/m/ Backpatch-through: --- contrib/file_fdw/file_fdw.c | 2 +- src/backend/commands/copyfrom.c | 5 +- src/backend/commands/copyfromparse.c | 10 +- src/backend/commands/copyto.c | 88 +------- src/include/commands/copy.h | 2 +- src/include/commands/copy_state.h | 253 +++++++++++++++++++++++ src/include/commands/copyfrom_internal.h | 165 +-------------- 7 files changed, 273 insertions(+), 252 deletions(-) create mode 100644 src/include/commands/copy_state.h diff --git a/contrib/file_fdw/file_fdw.c b/contrib/file_fdw/file_fdw.c index 33a37d832ce..d152d05b92e 100644 --- a/contrib/file_fdw/file_fdw.c +++ b/contrib/file_fdw/file_fdw.c @@ -22,7 +22,7 @@ #include "catalog/pg_authid.h" #include "catalog/pg_foreign_table.h" #include "commands/copy.h" -#include "commands/copyfrom_internal.h" +#include "commands/copy_state.h" #include "commands/defrem.h" #include "commands/explain_format.h" #include "commands/explain_state.h" diff --git a/src/backend/commands/copyfrom.c b/src/backend/commands/copyfrom.c index 0087585b2c4..2c57b32f4de 100644 --- a/src/backend/commands/copyfrom.c +++ b/src/backend/commands/copyfrom.c @@ -30,6 +30,7 @@ #include "access/xact.h" #include "catalog/namespace.h" #include "commands/copyapi.h" +#include "commands/copy_state.h" #include "commands/copyfrom_internal.h" #include "commands/progress.h" #include "commands/trigger.h" @@ -1732,7 +1733,7 @@ BeginCopyFrom(ParseState *pstate, pg_encoding_to_char(GetDatabaseEncoding())))); } - cstate->copy_src = COPY_FILE; /* default */ + cstate->copy_src = COPY_SOURCE_FILE; /* default */ cstate->whereClause = whereClause; @@ -1861,7 +1862,7 @@ BeginCopyFrom(ParseState *pstate, if (data_source_cb) { progress_vals[1] = PROGRESS_COPY_TYPE_CALLBACK; - cstate->copy_src = COPY_CALLBACK; + cstate->copy_src = COPY_SOURCE_CALLBACK; cstate->data_source_cb = data_source_cb; } else if (pipe) diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c index 65fd5a0ab4f..0ff5db4b62d 100644 --- a/src/backend/commands/copyfromparse.c +++ b/src/backend/commands/copyfromparse.c @@ -184,7 +184,7 @@ ReceiveCopyBegin(CopyFromState cstate) for (i = 0; i < natts; i++) pq_sendint16(&buf, format); /* per-column formats */ pq_endmessage(&buf); - cstate->copy_src = COPY_FRONTEND; + cstate->copy_src = COPY_SOURCE_FRONTEND; cstate->fe_msgbuf = makeStringInfo(); /* We *must* flush here to ensure FE knows it can send. */ pq_flush(); @@ -252,7 +252,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread) switch (cstate->copy_src) { - case COPY_FILE: + case COPY_SOURCE_FILE: pgstat_report_wait_start(WAIT_EVENT_COPY_FROM_READ); bytesread = fread(databuf, 1, maxread, cstate->copy_file); pgstat_report_wait_end(); @@ -263,7 +263,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread) if (bytesread == 0) cstate->raw_reached_eof = true; break; - case COPY_FRONTEND: + case COPY_SOURCE_FRONTEND: while (maxread > 0 && bytesread < minread && !cstate->raw_reached_eof) { int avail; @@ -346,7 +346,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread) bytesread += avail; } break; - case COPY_CALLBACK: + case COPY_SOURCE_CALLBACK: bytesread = cstate->data_source_cb(databuf, minread, maxread); break; } @@ -1259,7 +1259,7 @@ CopyReadLine(CopyFromState cstate, bool is_csv) * after \. up to the protocol end of copy data. (XXX maybe better * not to treat \. as special?) */ - if (cstate->copy_src == COPY_FRONTEND) + if (cstate->copy_src == COPY_SOURCE_FRONTEND) { int inbytes; diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 6755bb698de..ef2038c9a5d 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -23,8 +23,8 @@ #include "access/tupconvert.h" #include "catalog/pg_inherits.h" #include "commands/copyapi.h" +#include "commands/copy_state.h" #include "commands/progress.h" -#include "executor/execdesc.h" #include "executor/executor.h" #include "executor/tuptable.h" #include "funcapi.h" @@ -42,76 +42,6 @@ #include "utils/snapmgr.h" #include "utils/wait_event.h" -/* - * Represents the different dest cases we need to worry about at - * the bottom level - */ -typedef enum CopyDest -{ - COPY_FILE, /* to file (or a piped program) */ - COPY_FRONTEND, /* to frontend */ - COPY_CALLBACK, /* to callback function */ -} CopyDest; - -/* - * This struct contains all the state variables used throughout a COPY TO - * 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 CopyToStateData -{ - /* format-specific routines */ - const CopyToRoutine *routine; - - /* low-level state data */ - CopyDest copy_dest; /* type of copy source/destination */ - FILE *copy_file; /* used if copy_dest == COPY_FILE */ - StringInfo fe_msgbuf; /* used for all dests during COPY TO */ - - 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 to */ - QueryDesc *queryDesc; /* executable query to copy from */ - List *attnumlist; /* integer list of attnums to copy */ - char *filename; /* filename, or NULL for STDOUT */ - bool is_program; /* is 'filename' a program to popen? */ - bool json_row_delim_needed; /* need delimiter before next row */ - StringInfo json_buf; /* reusable buffer for JSON output, - * initialized in BeginCopyTo */ - TupleDesc tupDesc; /* Descriptor for JSON output; for a column - * list this is a projected descriptor */ - Datum *json_projvalues; /* pre-allocated projection values, or - * NULL */ - bool *json_projnulls; /* pre-allocated projection nulls, or NULL */ - copy_data_dest_cb data_dest_cb; /* function for writing data */ - - CopyFormatOptions opts; - Node *whereClause; /* WHERE condition (or NULL) */ - List *partitions; /* OID list of partitions to copy data from */ - - /* - * Working state - */ - MemoryContext copycontext; /* per-copy execution context */ - - FmgrInfo *out_functions; /* lookup info for output functions */ - MemoryContext rowcontext; /* per-row evaluation context */ - uint64 bytes_processed; /* number of bytes processed so far */ -} CopyToStateData; - /* DestReceiver for COPY (query) TO */ typedef struct { @@ -559,7 +489,7 @@ SendCopyBegin(CopyToState cstate) } pq_endmessage(&buf); - cstate->copy_dest = COPY_FRONTEND; + cstate->copy_dest = COPY_DEST_FRONTEND; } static void @@ -606,7 +536,7 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { - case COPY_FILE: + case COPY_DEST_FILE: pgstat_report_wait_start(WAIT_EVENT_COPY_TO_WRITE); if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || @@ -642,11 +572,11 @@ CopySendEndOfRow(CopyToState cstate) } pgstat_report_wait_end(); break; - case COPY_FRONTEND: + case COPY_DEST_FRONTEND: /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; - case COPY_CALLBACK: + case COPY_DEST_CALLBACK: cstate->data_dest_cb(fe_msgbuf->data, fe_msgbuf->len); break; } @@ -667,7 +597,7 @@ CopySendTextLikeEndOfRow(CopyToState cstate) { switch (cstate->copy_dest) { - case COPY_FILE: + case COPY_DEST_FILE: /* Default line termination depends on platform */ #ifndef WIN32 CopySendChar(cstate, '\n'); @@ -675,7 +605,7 @@ CopySendTextLikeEndOfRow(CopyToState cstate) CopySendString(cstate, "\r\n"); #endif break; - case COPY_FRONTEND: + case COPY_DEST_FRONTEND: /* The FE/BE protocol uses \n as newline for all platforms */ CopySendChar(cstate, '\n'); break; @@ -1135,12 +1065,12 @@ BeginCopyTo(ParseState *pstate, /* See Multibyte encoding comment above */ cstate->encoding_embeds_ascii = PG_ENCODING_IS_CLIENT_ONLY(cstate->file_encoding); - cstate->copy_dest = COPY_FILE; /* default */ + cstate->copy_dest = COPY_DEST_FILE; /* default */ if (data_dest_cb) { progress_vals[1] = PROGRESS_COPY_TYPE_CALLBACK; - cstate->copy_dest = COPY_CALLBACK; + cstate->copy_dest = COPY_DEST_CALLBACK; cstate->data_dest_cb = data_dest_cb; } else if (pipe) diff --git a/src/include/commands/copy.h b/src/include/commands/copy.h index abecfe51098..5e710efff5b 100644 --- a/src/include/commands/copy.h +++ b/src/include/commands/copy.h @@ -99,7 +99,7 @@ typedef struct CopyFormatOptions List *convert_select; /* list of column names (can be NIL) */ } CopyFormatOptions; -/* These are private in commands/copy[from|to].c */ +/* These are defined in copy_state.h */ typedef struct CopyFromStateData *CopyFromState; typedef struct CopyToStateData *CopyToState; diff --git a/src/include/commands/copy_state.h b/src/include/commands/copy_state.h new file mode 100644 index 00000000000..52cbf5067eb --- /dev/null +++ b/src/include/commands/copy_state.h @@ -0,0 +1,253 @@ +/*------------------------------------------------------------------------- + * + * copy_state.h + * prototypes for COPY TO/COPY FROM execution state. + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/copy_state.h + * + *------------------------------------------------------------------------- + */ + +#ifndef COPY_STATE_H +#define COPY_STATE_H + +#include "commands/copy.h" +#include "commands/trigger.h" +#include "executor/execdesc.h" +#include "nodes/miscnodes.h" + +/* + * Represents the different source cases we need to worry about at + * the bottom level + */ +typedef enum CopySource +{ + COPY_SOURCE_FILE, /* from file (or a piped program) */ + COPY_SOURCE_FRONTEND, /* from frontend */ + COPY_SOURCE_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; + +/* + * This struct contains all the state variables used throughout a COPY FROM + * operation. + */ +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_SOURCE_FILE */ + StringInfo fe_msgbuf; /* used if copy_src == COPY_SOURCE_FRONTEND */ + + 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? */ + Oid conversion_proc; /* encoding conversion function */ + + /* 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 */ + bool relname_only; /* don't output line number, att, etc. */ + + /* + * Working state + */ + MemoryContext copycontext; /* per-copy execution context */ + + AttrNumber num_defaults; /* count of att that are missing and have + * default value */ + FmgrInfo *in_functions; /* array of input functions for each attrs */ + Oid *typioparams; /* array of element types for in_functions */ + ErrorSaveContext *escontext; /* soft error trapped during in_functions + * execution */ + uint64 num_errors; /* total number of rows which contained soft + * errors */ + int *defmap; /* array of default att numbers related to + * missing att */ + ExprState **defexprs; /* array of default att expressions for all + * att */ + bool *defaults; /* if DEFAULT marker was found for + * corresponding att */ + bool simd_enabled; /* use SIMD to scan for special chars? */ + + /* + * True if the corresponding attribute's is a constrained domain. This + * will be populated only when ON_ERROR is SET_NULL, otherwise 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 */ + 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, 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_valid; /* contains the row being processed? */ + + /* + * input_buf holds input data, already converted to database encoding. + * + * In text mode, CopyReadLine parses this data sufficiently to locate line + * boundaries, then transfers the data to line_buf. We guarantee that + * there is a \0 at input_buf[input_buf_len] at all times. (In binary + * mode, input_buf is not used.) + * + * If encoding conversion is not required, input_buf is not a separate + * buffer but points directly to raw_buf. In that case, input_buf_len + * tracks the number of bytes that have been verified as valid in the + * database encoding, and raw_buf_len is the total number of bytes stored + * in the buffer. + */ +#define INPUT_BUF_SIZE 65536 /* we palloc INPUT_BUF_SIZE+1 bytes */ + char *input_buf; + int input_buf_index; /* next byte to process */ + int input_buf_len; /* total # of bytes stored */ + bool input_reached_eof; /* true if we reached EOF */ + bool input_reached_error; /* true if a conversion error happened */ + /* Shorthand for number of unconsumed bytes available in input_buf */ +#define INPUT_BUF_BYTES(cstate) ((cstate)->input_buf_len - (cstate)->input_buf_index) + + /* + * raw_buf holds raw input data read from the data source (file or client + * connection), not yet converted to the database encoding. Like with + * 'input_buf', 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 */ + bool raw_reached_eof; /* true if we reached EOF */ + + /* Shorthand for number of unconsumed bytes available in raw_buf */ +#define RAW_BUF_BYTES(cstate) ((cstate)->raw_buf_len - (cstate)->raw_buf_index) + + uint64 bytes_processed; /* number of bytes processed so far */ +} CopyFromStateData; + +/* + * Represents the different dest cases we need to worry about at + * the bottom level + */ +typedef enum CopyDest +{ + COPY_DEST_FILE, /* to file (or a piped program) */ + COPY_DEST_FRONTEND, /* to frontend */ + COPY_DEST_CALLBACK, /* to callback function */ +} CopyDest; + +/* + * This struct contains all the state variables used throughout a COPY TO + * 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 CopyToStateData +{ + /* format-specific routines */ + const struct CopyToRoutine *routine; + + /* low-level state data */ + CopyDest copy_dest; /* type of copy source/destination */ + FILE *copy_file; /* used if copy_dest == COPY_DEST_FILE */ + StringInfo fe_msgbuf; /* used for all dests during COPY TO */ + + 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 to */ + QueryDesc *queryDesc; /* executable query to copy from */ + List *attnumlist; /* integer list of attnums to copy */ + char *filename; /* filename, or NULL for STDOUT */ + bool is_program; /* is 'filename' a program to popen? */ + bool json_row_delim_needed; /* need delimiter before next row */ + StringInfo json_buf; /* reusable buffer for JSON output, + * initialized in BeginCopyTo */ + TupleDesc tupDesc; /* Descriptor for JSON output; for a column + * list this is a projected descriptor */ + Datum *json_projvalues; /* pre-allocated projection values, or + * NULL */ + bool *json_projnulls; /* pre-allocated projection nulls, or NULL */ + copy_data_dest_cb data_dest_cb; /* function for writing data */ + + CopyFormatOptions opts; + Node *whereClause; /* WHERE condition (or NULL) */ + List *partitions; /* OID list of partitions to copy data from */ + + /* + * Working state + */ + MemoryContext copycontext; /* per-copy execution context */ + + FmgrInfo *out_functions; /* lookup info for output functions */ + MemoryContext rowcontext; /* per-row evaluation context */ + uint64 bytes_processed; /* number of bytes processed so far */ +} CopyToStateData; + +#endif /* COPY_STATE_H */ diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h index 9d3e244ee55..f7afade9a39 100644 --- a/src/include/commands/copyfrom_internal.h +++ b/src/include/commands/copyfrom_internal.h @@ -14,31 +14,7 @@ #ifndef COPYFROM_INTERNAL_H #define COPYFROM_INTERNAL_H -#include "commands/copy.h" -#include "commands/trigger.h" -#include "nodes/miscnodes.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_FRONTEND, /* from frontend */ - 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; +#include "commands/copy_state.h" /* * Represents the insert method to be used during COPY FROM. @@ -52,145 +28,6 @@ typedef enum CopyInsertMethod * ExecForeignBatchInsert only if valid */ } CopyInsertMethod; -/* - * This struct contains all the state variables used throughout a COPY FROM - * operation. - */ -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 */ - StringInfo fe_msgbuf; /* used if copy_src == COPY_FRONTEND */ - - 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? */ - Oid conversion_proc; /* encoding conversion function */ - - /* 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 */ - bool relname_only; /* don't output line number, att, etc. */ - - /* - * Working state - */ - MemoryContext copycontext; /* per-copy execution context */ - - AttrNumber num_defaults; /* count of att that are missing and have - * default value */ - FmgrInfo *in_functions; /* array of input functions for each attrs */ - Oid *typioparams; /* array of element types for in_functions */ - ErrorSaveContext *escontext; /* soft error trapped during in_functions - * execution */ - uint64 num_errors; /* total number of rows which contained soft - * errors */ - int *defmap; /* array of default att numbers related to - * missing att */ - ExprState **defexprs; /* array of default att expressions for all - * att */ - bool *defaults; /* if DEFAULT marker was found for - * corresponding att */ - bool simd_enabled; /* use SIMD to scan for special chars? */ - - /* - * True if the corresponding attribute's is a constrained domain. This - * will be populated only when ON_ERROR is SET_NULL, otherwise 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 */ - 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, 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_valid; /* contains the row being processed? */ - - /* - * input_buf holds input data, already converted to database encoding. - * - * In text mode, CopyReadLine parses this data sufficiently to locate line - * boundaries, then transfers the data to line_buf. We guarantee that - * there is a \0 at input_buf[input_buf_len] at all times. (In binary - * mode, input_buf is not used.) - * - * If encoding conversion is not required, input_buf is not a separate - * buffer but points directly to raw_buf. In that case, input_buf_len - * tracks the number of bytes that have been verified as valid in the - * database encoding, and raw_buf_len is the total number of bytes stored - * in the buffer. - */ -#define INPUT_BUF_SIZE 65536 /* we palloc INPUT_BUF_SIZE+1 bytes */ - char *input_buf; - int input_buf_index; /* next byte to process */ - int input_buf_len; /* total # of bytes stored */ - bool input_reached_eof; /* true if we reached EOF */ - bool input_reached_error; /* true if a conversion error happened */ - /* Shorthand for number of unconsumed bytes available in input_buf */ -#define INPUT_BUF_BYTES(cstate) ((cstate)->input_buf_len - (cstate)->input_buf_index) - - /* - * raw_buf holds raw input data read from the data source (file or client - * connection), not yet converted to the database encoding. Like with - * 'input_buf', 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 */ - bool raw_reached_eof; /* true if we reached EOF */ - - /* Shorthand for number of unconsumed bytes available in raw_buf */ -#define RAW_BUF_BYTES(cstate) ((cstate)->raw_buf_len - (cstate)->raw_buf_index) - - uint64 bytes_processed; /* number of bytes processed so far */ -} CopyFromStateData; - extern void ReceiveCopyBegin(CopyFromState cstate); extern void ReceiveCopyBinaryHeader(CopyFromState cstate); -- 2.54.0