1
0
mirror of https://github.com/postgres/postgres.git synced 2025-10-27 00:12:01 +03:00

Refactor CopyReadAttributes{CSV,Text}() to use a callback in COPY FROM

CopyReadAttributes{CSV,Text}() are used to parse lines for text and CSV
format.  This reduces the number of "if" branches that need to be
checked when parsing fields in CSV and text mode when dealing with a
COPY FROM, something that can become more noticeable with more
attributes and more lines to process.

Extracted from a larger patch by the same author.

Author: Sutou Kouhei
Discussion: https://postgr.es/m/20231204.153548.2126325458835528809.kou@clear-code.com
This commit is contained in:
Michael Paquier
2024-02-05 09:46:02 +09:00
parent 774bcffe4a
commit 95fb5b4902
3 changed files with 30 additions and 16 deletions

View File

@@ -1776,6 +1776,11 @@ BeginCopyFrom(ParseState *pstate,
cstate->max_fields = attr_count;
cstate->raw_fields = (char **) palloc(attr_count * sizeof(char *));
if (cstate->opts.csv_mode)
cstate->copy_read_attributes = CopyReadAttributesCSV;
else
cstate->copy_read_attributes = CopyReadAttributesText;
}
MemoryContextSwitchTo(oldcontext);

View File

@@ -25,10 +25,10 @@
* is copied into 'line_buf', with quotes and escape characters still
* intact.
*
* 4. CopyReadAttributesText/CSV() function takes the input line from
* 'line_buf', and splits it into fields, unescaping the data as required.
* The fields are stored in 'attribute_buf', and 'raw_fields' array holds
* pointers to each field.
* 4. CopyReadAttributesText/CSV() function (via copy_read_attribute) takes
* the input line from 'line_buf', and splits it into fields, unescaping
* the data as required. The fields are stored in 'attribute_buf', and
* 'raw_fields' array holds pointers to each field.
*
* If encoding conversion is not required, a shortcut is taken in step 2 to
* avoid copying the data unnecessarily. The 'input_buf' pointer is set to
@@ -152,8 +152,6 @@ 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 int CopyReadAttributesText(CopyFromState cstate);
static int CopyReadAttributesCSV(CopyFromState cstate);
static Datum CopyReadBinaryAttribute(CopyFromState cstate, FmgrInfo *flinfo,
Oid typioparam, int32 typmod,
bool *isnull);
@@ -775,10 +773,7 @@ NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
{
int fldnum;
if (cstate->opts.csv_mode)
fldct = CopyReadAttributesCSV(cstate);
else
fldct = CopyReadAttributesText(cstate);
fldct = cstate->copy_read_attributes(cstate);
if (fldct != list_length(cstate->attnumlist))
ereport(ERROR,
@@ -830,10 +825,7 @@ NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
return false;
/* Parse the line into de-escaped field values */
if (cstate->opts.csv_mode)
fldct = CopyReadAttributesCSV(cstate);
else
fldct = CopyReadAttributesText(cstate);
fldct = cstate->copy_read_attributes(cstate);
*fields = cstate->raw_fields;
*nfields = fldct;
@@ -1502,7 +1494,7 @@ GetDecimalFromHex(char hex)
*
* The return value is the number of fields actually read.
*/
static int
int
CopyReadAttributesText(CopyFromState cstate)
{
char delimc = cstate->opts.delim[0];
@@ -1756,7 +1748,7 @@ CopyReadAttributesText(CopyFromState cstate)
* CopyReadAttributesText, except we parse the fields according to
* "standard" (i.e. common) CSV usage.
*/
static int
int
CopyReadAttributesCSV(CopyFromState cstate)
{
char delimc = cstate->opts.delim[0];