Solve the 'Turkish problem' with undesirable locale behavior for case

conversion of basic ASCII letters.  Remove all uses of strcasecmp and
strncasecmp in favor of new functions pg_strcasecmp and pg_strncasecmp;
remove most but not all direct uses of toupper and tolower in favor of
pg_toupper and pg_tolower.  These functions use the same notions of
case folding already developed for identifier case conversion.  I left
the straight locale-based folding in place for situations where we are
just manipulating user data and not trying to match it to built-in
strings --- for example, the SQL upper() function is still locale
dependent.  Perhaps this will prove not to be what's wanted, but at
the moment we can initdb and pass regression tests in Turkish locale.

1 files changed, 52 insertions, 141 deletions

diff --git a/src/backend/utils/adt/timestamp.c b/src/backend/utils/adt/timestamp.c
index b2628a3a6f6..cd59b7f34ad 100644
--- a/src/backend/utils/adt/timestamp.c
+++ b/src/backend/utils/adt/timestamp.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/timestamp.c,v 1.104 2004/04/10 18:02:59 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/timestamp.c,v 1.105 2004/05/07 00:24:58 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -26,6 +26,7 @@
 #include "catalog/pg_type.h"
 #include "libpq/pqformat.h"
 #include "miscadmin.h"
+#include "parser/scansup.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 
@@ -2699,32 +2700,20 @@ timestamp_trunc(PG_FUNCTION_ARGS)
 	Timestamp	result;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowunits[MAXDATELEN + 1];
+	char	   *lowunits;
 	fsec_t		fsec;
 	struct tm	tt,
 			   *tm = &tt;
 
-	if (VARSIZE(units) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("timestamp units \"%s\" not recognized",
-						DatumGetCString(DirectFunctionCall1(textout,
-											 PointerGetDatum(units))))));
+	if (TIMESTAMP_NOT_FINITE(timestamp))
+		PG_RETURN_TIMESTAMP(timestamp);
 
-	up = VARDATA(units);
-	lp = lowunits;
-	for (i = 0; i < (VARSIZE(units) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
+	lowunits = downcase_truncate_identifier(VARDATA(units),
+											VARSIZE(units) - VARHDRSZ,
+											false);
 
 	type = DecodeUnits(0, lowunits, &val);
 
-	if (TIMESTAMP_NOT_FINITE(timestamp))
-		PG_RETURN_TIMESTAMP(timestamp);
-
 	if (type == UNITS)
 	{
 		if (timestamp2tm(timestamp, NULL, tm, &fsec, NULL) != 0)
@@ -2814,32 +2803,21 @@ timestamptz_trunc(PG_FUNCTION_ARGS)
 	int			tz;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowunits[MAXDATELEN + 1];
+	char	   *lowunits;
 	fsec_t		fsec;
 	char	   *tzn;
 	struct tm	tt,
 			   *tm = &tt;
 
-	if (VARSIZE(units) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-		   errmsg("timestamp with time zone units \"%s\" not recognized",
-				  DatumGetCString(DirectFunctionCall1(textout,
-											 PointerGetDatum(units))))));
-	up = VARDATA(units);
-	lp = lowunits;
-	for (i = 0; i < (VARSIZE(units) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
-
-	type = DecodeUnits(0, lowunits, &val);
-
 	if (TIMESTAMP_NOT_FINITE(timestamp))
 		PG_RETURN_TIMESTAMPTZ(timestamp);
 
+	lowunits = downcase_truncate_identifier(VARDATA(units),
+											VARSIZE(units) - VARHDRSZ,
+											false);
+
+	type = DecodeUnits(0, lowunits, &val);
+
 	if (type == UNITS)
 	{
 		if (timestamp2tm(timestamp, &tz, tm, &fsec, &tzn) != 0)
@@ -2929,27 +2907,16 @@ interval_trunc(PG_FUNCTION_ARGS)
 	Interval   *result;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowunits[MAXDATELEN + 1];
+	char	   *lowunits;
 	fsec_t		fsec;
 	struct tm	tt,
 			   *tm = &tt;
 
 	result = (Interval *) palloc(sizeof(Interval));
 
-	if (VARSIZE(units) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("interval units \"%s\" not recognized",
-						DatumGetCString(DirectFunctionCall1(textout,
-											 PointerGetDatum(units))))));
-	up = VARDATA(units);
-	lp = lowunits;
-	for (i = 0; i < (VARSIZE(units) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
+	lowunits = downcase_truncate_identifier(VARDATA(units),
+											VARSIZE(units) - VARHDRSZ,
+											false);
 
 	type = DecodeUnits(0, lowunits, &val);
 
@@ -3173,36 +3140,25 @@ timestamp_part(PG_FUNCTION_ARGS)
 	float8		result;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowunits[MAXDATELEN + 1];
+	char	   *lowunits;
 	fsec_t		fsec;
 	struct tm	tt,
 			   *tm = &tt;
 
-	if (VARSIZE(units) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("timestamp units \"%s\" not recognized",
-						DatumGetCString(DirectFunctionCall1(textout,
-											 PointerGetDatum(units))))));
-	up = VARDATA(units);
-	lp = lowunits;
-	for (i = 0; i < (VARSIZE(units) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
-
-	type = DecodeUnits(0, lowunits, &val);
-	if (type == UNKNOWN_FIELD)
-		type = DecodeSpecial(0, lowunits, &val);
-
 	if (TIMESTAMP_NOT_FINITE(timestamp))
 	{
 		result = 0;
 		PG_RETURN_FLOAT8(result);
 	}
 
+	lowunits = downcase_truncate_identifier(VARDATA(units),
+											VARSIZE(units) - VARHDRSZ,
+											false);
+
+	type = DecodeUnits(0, lowunits, &val);
+	if (type == UNKNOWN_FIELD)
+		type = DecodeSpecial(0, lowunits, &val);
+
 	if (type == UNITS)
 	{
 		if (timestamp2tm(timestamp, NULL, tm, &fsec, NULL) != 0)
@@ -3395,38 +3351,27 @@ timestamptz_part(PG_FUNCTION_ARGS)
 	int			tz;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowunits[MAXDATELEN + 1];
+	char	   *lowunits;
 	double		dummy;
 	fsec_t		fsec;
 	char	   *tzn;
 	struct tm	tt,
 			   *tm = &tt;
 
-	if (VARSIZE(units) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-		   errmsg("timestamp with time zone units \"%s\" not recognized",
-				  DatumGetCString(DirectFunctionCall1(textout,
-											 PointerGetDatum(units))))));
-	up = VARDATA(units);
-	lp = lowunits;
-	for (i = 0; i < (VARSIZE(units) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
-
-	type = DecodeUnits(0, lowunits, &val);
-	if (type == UNKNOWN_FIELD)
-		type = DecodeSpecial(0, lowunits, &val);
-
 	if (TIMESTAMP_NOT_FINITE(timestamp))
 	{
 		result = 0;
 		PG_RETURN_FLOAT8(result);
 	}
 
+	lowunits = downcase_truncate_identifier(VARDATA(units),
+											VARSIZE(units) - VARHDRSZ,
+											false);
+
+	type = DecodeUnits(0, lowunits, &val);
+	if (type == UNKNOWN_FIELD)
+		type = DecodeSpecial(0, lowunits, &val);
+
 	if (type == UNITS)
 	{
 		if (timestamp2tm(timestamp, &tz, tm, &fsec, &tzn) != 0)
@@ -3597,25 +3542,14 @@ interval_part(PG_FUNCTION_ARGS)
 	float8		result;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowunits[MAXDATELEN + 1];
+	char	   *lowunits;
 	fsec_t		fsec;
 	struct tm	tt,
 			   *tm = &tt;
 
-	if (VARSIZE(units) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("interval units \"%s\" not recognized",
-						DatumGetCString(DirectFunctionCall1(textout,
-											 PointerGetDatum(units))))));
-	up = VARDATA(units);
-	lp = lowunits;
-	for (i = 0; i < (VARSIZE(units) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
+	lowunits = downcase_truncate_identifier(VARDATA(units),
+											VARSIZE(units) - VARHDRSZ,
+											false);
 
 	type = DecodeUnits(0, lowunits, &val);
 	if (type == UNKNOWN_FIELD)
@@ -3744,26 +3678,14 @@ timestamp_zone(PG_FUNCTION_ARGS)
 	int			tz;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowzone[MAXDATELEN + 1];
-
-	if (VARSIZE(zone) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("time zone \"%s\" not recognized",
-						DatumGetCString(DirectFunctionCall1(textout,
-											  PointerGetDatum(zone))))));
+	char	   *lowzone;
 
 	if (TIMESTAMP_NOT_FINITE(timestamp))
 		PG_RETURN_TIMESTAMPTZ(timestamp);
 
-	up = VARDATA(zone);
-	lp = lowzone;
-	for (i = 0; i < (VARSIZE(zone) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
+	lowzone = downcase_truncate_identifier(VARDATA(zone),
+										   VARSIZE(zone) - VARHDRSZ,
+										   false);
 
 	type = DecodeSpecial(0, lowzone, &val);
 
@@ -3903,28 +3825,17 @@ timestamptz_zone(PG_FUNCTION_ARGS)
 	int			tz;
 	int			type,
 				val;
-	int			i;
-	char	   *up,
-			   *lp,
-				lowzone[MAXDATELEN + 1];
-
-	if (VARSIZE(zone) - VARHDRSZ > MAXDATELEN)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("time zone \"%s\" not recognized",
-						DatumGetCString(DirectFunctionCall1(textout,
-											  PointerGetDatum(zone))))));
-	up = VARDATA(zone);
-	lp = lowzone;
-	for (i = 0; i < (VARSIZE(zone) - VARHDRSZ); i++)
-		*lp++ = tolower((unsigned char) *up++);
-	*lp = '\0';
-
-	type = DecodeSpecial(0, lowzone, &val);
+	char	   *lowzone;
 
 	if (TIMESTAMP_NOT_FINITE(timestamp))
 		PG_RETURN_NULL();
 
+	lowzone = downcase_truncate_identifier(VARDATA(zone),
+										   VARSIZE(zone) - VARHDRSZ,
+										   false);
+
+	type = DecodeSpecial(0, lowzone, &val);
+
 	if ((type == TZ) || (type == DTZ))
 	{
 		tz = val * 60;