database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-30 11:03:19 +03:00
Code Activity

Per-column collation support

Browse Source 
This adds collation support for columns and domains, a COLLATE clause
to override it per expression, and B-tree index support.

Peter Eisentraut
reviewed by Pavel Stehule, Itagaki Takahiro, Robert Haas, Noah Misch
This commit is contained in:
Peter Eisentraut
2011-02-08 23:04:18 +02:00
parent 1703f0e8da
commit 414c5a2ea6
156 changed files with 4519 additions and 582 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
src/backend/utils/adt/selfuncs.c
View File

@ -94,6 +94,7 @@
#include "access/gin.h"
#include "access/sysattr.h"
#include "catalog/index.h"
#include "catalog/pg_collation.h"
#include "catalog/pg_opfamily.h"
#include "catalog/pg_statistic.h"
#include "catalog/pg_type.h"
@ -144,7 +145,7 @@ static double eqjoinsel_inner(Oid operator,
static double eqjoinsel_semi(Oid operator,
VariableStatData *vardata1, VariableStatData *vardata2);
static bool convert_to_scalar(Datum value, Oid valuetypid, double *scaledvalue,
Datum lobound, Datum hibound, Oid boundstypid,
Datum lobound, Datum hibound, Oid boundstypid, Oid boundscollid,
double *scaledlobound, double *scaledhibound);
static double convert_numeric_to_scalar(Datum value, Oid typid);
static void convert_string_to_scalar(char *value,
@ -163,10 +164,10 @@ static double convert_one_string_to_scalar(char *value,
int rangelo, int rangehi);
static double convert_one_bytea_to_scalar(unsigned char *value, int valuelen,
int rangelo, int rangehi);
static char *convert_string_datum(Datum value, Oid typid);
static char *convert_string_datum(Datum value, Oid typid, Oid collid);
static double convert_timevalue_to_scalar(Datum value, Oid typid);
static bool get_variable_range(PlannerInfo *root, VariableStatData *vardata,
Oid sortop, Datum *min, Datum *max);
Oid sortop, Oid collation, Datum *min, Datum *max);
static bool get_actual_variable_range(PlannerInfo *root,
VariableStatData *vardata,
Oid sortop,
@ -513,6 +514,7 @@ scalarineqsel(PlannerInfo *root, Oid operator, bool isgt,
stats = (Form_pg_statistic) GETSTRUCT(vardata->statsTuple);
fmgr_info(get_opcode(operator), &opproc);
fmgr_info_collation(vardata->attcollation, &opproc);
/*
* If we have most-common-values info, add up the fractions of the MCV
@ -837,7 +839,7 @@ ineq_histogram_selectivity(PlannerInfo *root,
*/
if (convert_to_scalar(constval, consttype, &val,
values[i - 1], values[i],
vardata->vartype,
vardata->vartype, vardata->attcollation,
&low, &high))
{
if (high <= low)
@ -1249,6 +1251,7 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype, bool negate)
/* Try to use the histogram entries to get selectivity */
fmgr_info(get_opcode(operator), &opproc);
fmgr_info_collation(DEFAULT_COLLATION_OID, &opproc);
selec = histogram_selectivity(&vardata, &opproc, constval, true,
10, 1, &hist_size);
@ -2585,7 +2588,7 @@ icnlikejoinsel(PG_FUNCTION_ARGS)
*/
void
mergejoinscansel(PlannerInfo *root, Node *clause,
Oid opfamily, int strategy, bool nulls_first,
Oid opfamily, Oid collation, int strategy, bool nulls_first,
Selectivity *leftstart, Selectivity *leftend,
Selectivity *rightstart, Selectivity *rightend)
{
@ -2754,20 +2757,20 @@ mergejoinscansel(PlannerInfo *root, Node *clause,
/* Try to get ranges of both inputs */
if (!isgt)
{
if (!get_variable_range(root, &leftvar, lstatop,
if (!get_variable_range(root, &leftvar, lstatop, collation,
&leftmin, &leftmax))
goto fail; /* no range available from stats */
if (!get_variable_range(root, &rightvar, rstatop,
if (!get_variable_range(root, &rightvar, rstatop, collation,
&rightmin, &rightmax))
goto fail; /* no range available from stats */
}
else
{
/* need to swap the max and min */
if (!get_variable_range(root, &leftvar, lstatop,
if (!get_variable_range(root, &leftvar, lstatop, collation,
&leftmax, &leftmin))
goto fail; /* no range available from stats */
if (!get_variable_range(root, &rightvar, rstatop,
if (!get_variable_range(root, &rightvar, rstatop, collation,
&rightmax, &rightmin))
goto fail; /* no range available from stats */
}
@ -3368,7 +3371,7 @@ estimate_hash_bucketsize(PlannerInfo *root, Node *hashkey, double nbuckets)
*/
static bool
convert_to_scalar(Datum value, Oid valuetypid, double *scaledvalue,
Datum lobound, Datum hibound, Oid boundstypid,
Datum lobound, Datum hibound, Oid boundstypid, Oid boundscollid,
double *scaledlobound, double *scaledhibound)
{
/*
@ -3421,9 +3424,9 @@ convert_to_scalar(Datum value, Oid valuetypid, double *scaledvalue,
case TEXTOID:
case NAMEOID:
{
char *valstr = convert_string_datum(value, valuetypid);
char *lostr = convert_string_datum(lobound, boundstypid);
char *histr = convert_string_datum(hibound, boundstypid);
char *valstr = convert_string_datum(value, valuetypid, boundscollid);
char *lostr = convert_string_datum(lobound, boundstypid, boundscollid);
char *histr = convert_string_datum(hibound, boundstypid, boundscollid);
convert_string_to_scalar(valstr, scaledvalue,
lostr, scaledlobound,
@ -3667,7 +3670,7 @@ convert_one_string_to_scalar(char *value, int rangelo, int rangehi)
* before continuing, so as to generate correct locale-specific results.
*/
static char *
convert_string_datum(Datum value, Oid typid)
convert_string_datum(Datum value, Oid typid, Oid collid)
{
char *val;
@ -3700,7 +3703,7 @@ convert_string_datum(Datum value, Oid typid)
return NULL;
}
if (!lc_collate_is_c())
if (!lc_collate_is_c(collid))
{
char *xfrmstr;
size_t xfrmlen;
@ -4099,6 +4102,7 @@ examine_variable(PlannerInfo *root, Node *node, int varRelid,
vardata->rel = find_base_rel(root, var->varno);
vardata->atttype = var->vartype;
vardata->atttypmod = var->vartypmod;
vardata->attcollation = var->varcollid;
vardata->isunique = has_unique_index(vardata->rel, var->varattno);
rte = root->simple_rte_array[var->varno];
@ -4184,6 +4188,7 @@ examine_variable(PlannerInfo *root, Node *node, int varRelid,
vardata->var = node;
vardata->atttype = exprType(node);
vardata->atttypmod = exprTypmod(node);
vardata->attcollation = exprCollation(node);
if (onerel)
{
@ -4392,7 +4397,7 @@ get_variable_numdistinct(VariableStatData *vardata)
* be "<" not ">", as only the former is likely to be found in pg_statistic.
*/
static bool
get_variable_range(PlannerInfo *root, VariableStatData *vardata, Oid sortop,
get_variable_range(PlannerInfo *root, VariableStatData *vardata, Oid sortop, Oid collation,
Datum *min, Datum *max)
{
Datum tmin = 0;
@ -4477,6 +4482,7 @@ get_variable_range(PlannerInfo *root, VariableStatData *vardata, Oid sortop,
FmgrInfo opproc;
fmgr_info(get_opcode(sortop), &opproc);
fmgr_info_collation(collation, &opproc);
for (i = 0; i < nvalues; i++)
{
@ -5482,7 +5488,7 @@ make_greater_string(const Const *str_const, FmgrInfo *ltproc)
{
workstr = TextDatumGetCString(str_const->constvalue);
len = strlen(workstr);
if (lc_collate_is_c() || len == 0)
if (lc_collate_is_c(ltproc->fn_collation) || len == 0)
cmpstr = str_const->constvalue;
else
{
@ -5494,11 +5500,11 @@ make_greater_string(const Const *str_const, FmgrInfo *ltproc)
char *best;
best = "Z";
if (varstr_cmp(best, 1, "z", 1) < 0)
if (varstr_cmp(best, 1, "z", 1, DEFAULT_COLLATION_OID) < 0)
best = "z";
if (varstr_cmp(best, 1, "y", 1) < 0)
if (varstr_cmp(best, 1, "y", 1, DEFAULT_COLLATION_OID) < 0)
best = "y";
if (varstr_cmp(best, 1, "9", 1) < 0)
if (varstr_cmp(best, 1, "9", 1, DEFAULT_COLLATION_OID) < 0)
best = "9";
suffixchar = *best;
}