database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-25 13:17:41 +03:00
Code Activity

Support multi-line headers in COPY FROM command.

Browse Source 
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
This commit is contained in:
Fujii Masao
2025-07-03 15:27:26 +09:00
parent fd7d7b7191
commit bc2f348e87
10 changed files with 138 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/backend/commands/copy.c
View File

@@ -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 */

17
src/backend/commands/copyfromparse.c
View File

@@ -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)
{

2
src/backend/commands/copyto.c
View File

@@ -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;