Allow DateTimeParseError to handle bad-timezone error messages.

Pay down some ancient technical debt (dating to commit 022fd9966):
fix a couple of places in datetime parsing that were throwing
ereport's immediately instead of returning a DTERR code that could be
interpreted by DateTimeParseError.  The reason for that was that there
was no mechanism for passing any auxiliary data (such as a zone name)
to DateTimeParseError, and these errors seemed to really need it.
Up to now it didn't matter that much just where the error got thrown,
but now we'd like to have a hard policy that datetime parse errors
get thrown from just the one place.

Hence, invent a "DateTimeErrorExtra" struct that can be used to
carry any extra values needed for specific DTERR codes.  Perhaps
in the future somebody will be motivated to use this to improve
the specificity of other DateTimeParseError messages, but for now
just deal with the timezone-error cases.

This is on the way to making the datetime input functions report
parse errors softly; but it's really an independent change, so
commit separately.

Discussion: https://postgr.es/m/3bbbb0df-7382-bf87-9737-340ba096e034@postgrespro.ru

1 files changed, 77 insertions, 47 deletions

diff --git a/src/backend/utils/adt/datetime.c b/src/backend/utils/adt/datetime.c
index 6893c1ce09c..84bba97abc8 100644
--- a/src/backend/utils/adt/datetime.c
+++ b/src/backend/utils/adt/datetime.c
@@ -69,7 +69,8 @@ static int	DetermineTimeZoneOffsetInternal(struct pg_tm *tm, pg_tz *tzp,
 static bool DetermineTimeZoneAbbrevOffsetInternal(pg_time_t t,
 												  const char *abbr, pg_tz *tzp,
 												  int *offset, int *isdst);
-static pg_tz *FetchDynamicTimeZone(TimeZoneAbbrevTable *tbl, const datetkn *tp);
+static pg_tz *FetchDynamicTimeZone(TimeZoneAbbrevTable *tbl, const datetkn *tp,
+								   DateTimeErrorExtra *extra);
 
 
 const int	day_tab[2][13] =
@@ -951,6 +952,9 @@ ParseDateTime(const char *timestr, char *workbuf, size_t buflen,
  * Return 0 if full date, 1 if only time, and negative DTERR code if problems.
  * (Currently, all callers treat 1 as an error return too.)
  *
+ * Inputs are field[] and ftype[] arrays, of length nf.
+ * Other arguments are outputs.
+ *
  *		External format(s):
  *				"<weekday> <month>-<day>-<year> <hour>:<minute>:<second>"
  *				"Fri Feb-7-1997 15:23:27"
@@ -972,7 +976,8 @@ ParseDateTime(const char *timestr, char *workbuf, size_t buflen,
  */
 int
 DecodeDateTime(char **field, int *ftype, int nf,
-			   int *dtype, struct pg_tm *tm, fsec_t *fsec, int *tzp)
+			   int *dtype, struct pg_tm *tm, fsec_t *fsec, int *tzp,
+			   DateTimeErrorExtra *extra)
 {
 	int			fmask = 0,
 				tmask,
@@ -1112,15 +1117,8 @@ DecodeDateTime(char **field, int *ftype, int nf,
 						namedTz = pg_tzset(field[i]);
 						if (!namedTz)
 						{
-							/*
-							 * We should return an error code instead of
-							 * ereport'ing directly, but then there is no way
-							 * to report the bad time zone name.
-							 */
-							ereport(ERROR,
-									(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-									 errmsg("time zone \"%s\" not recognized",
-											field[i])));
+							extra->dtee_timezone = field[i];
+							return DTERR_BAD_TIMEZONE;
 						}
 						/* we'll apply the zone setting below */
 						tmask = DTK_M(TZ);
@@ -1376,7 +1374,10 @@ DecodeDateTime(char **field, int *ftype, int nf,
 			case DTK_STRING:
 			case DTK_SPECIAL:
 				/* timezone abbrevs take precedence over built-in tokens */
-				type = DecodeTimezoneAbbrev(i, field[i], &val, &valtz);
+				dterr = DecodeTimezoneAbbrev(i, field[i],
+											 &type, &val, &valtz, extra);
+				if (dterr)
+					return dterr;
 				if (type == UNKNOWN_FIELD)
 					type = DecodeSpecial(i, field[i], &val);
 				if (type == IGNORE_DTF)
@@ -1912,6 +1913,9 @@ DetermineTimeZoneAbbrevOffsetInternal(pg_time_t t, const char *abbr, pg_tz *tzp,
  * Interpret parsed string as time fields only.
  * Returns 0 if successful, DTERR code if bogus input detected.
  *
+ * Inputs are field[] and ftype[] arrays, of length nf.
+ * Other arguments are outputs.
+ *
  * Note that support for time zone is here for
  * SQL TIME WITH TIME ZONE, but it reveals
  * bogosity with SQL date/time standards, since
@@ -1922,7 +1926,8 @@ DetermineTimeZoneAbbrevOffsetInternal(pg_time_t t, const char *abbr, pg_tz *tzp,
  */
 int
 DecodeTimeOnly(char **field, int *ftype, int nf,
-			   int *dtype, struct pg_tm *tm, fsec_t *fsec, int *tzp)
+			   int *dtype, struct pg_tm *tm, fsec_t *fsec, int *tzp,
+			   DateTimeErrorExtra *extra)
 {
 	int			fmask = 0,
 				tmask,
@@ -2018,15 +2023,8 @@ DecodeTimeOnly(char **field, int *ftype, int nf,
 						namedTz = pg_tzset(field[i]);
 						if (!namedTz)
 						{
-							/*
-							 * We should return an error code instead of
-							 * ereport'ing directly, but then there is no way
-							 * to report the bad time zone name.
-							 */
-							ereport(ERROR,
-									(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-									 errmsg("time zone \"%s\" not recognized",
-											field[i])));
+							extra->dtee_timezone = field[i];
+							return DTERR_BAD_TIMEZONE;
 						}
 						/* we'll apply the zone setting below */
 						ftype[i] = DTK_TZ;
@@ -2278,7 +2276,10 @@ DecodeTimeOnly(char **field, int *ftype, int nf,
 			case DTK_STRING:
 			case DTK_SPECIAL:
 				/* timezone abbrevs take precedence over built-in tokens */
-				type = DecodeTimezoneAbbrev(i, field[i], &val, &valtz);
+				dterr = DecodeTimezoneAbbrev(i, field[i],
+											 &type, &val, &valtz, extra);
+				if (dterr)
+					return dterr;
 				if (type == UNKNOWN_FIELD)
 					type = DecodeSpecial(i, field[i], &val);
 				if (type == IGNORE_DTF)
@@ -3211,12 +3212,18 @@ DecodeTimezone(const char *str, int *tzp)
 /* DecodeTimezoneAbbrev()
  * Interpret string as a timezone abbreviation, if possible.
  *
- * Returns an abbreviation type (TZ, DTZ, or DYNTZ), or UNKNOWN_FIELD if
+ * Sets *ftype to an abbreviation type (TZ, DTZ, or DYNTZ), or UNKNOWN_FIELD if
  * string is not any known abbreviation.  On success, set *offset and *tz to
  * represent the UTC offset (for TZ or DTZ) or underlying zone (for DYNTZ).
  * Note that full timezone names (such as America/New_York) are not handled
  * here, mostly for historical reasons.
  *
+ * The function result is 0 or a DTERR code; in the latter case, *extra
+ * is filled as needed.  Note that unknown-abbreviation is not considered
+ * an error case.  Also note that many callers assume that the DTERR code
+ * is one that DateTimeParseError does not require "str" or "datatype"
+ * strings for.
+ *
  * Given string must be lowercased already.
  *
  * Implement a cache lookup since it is likely that dates
@@ -3224,9 +3231,9 @@ DecodeTimezone(const char *str, int *tzp)
  */
 int
 DecodeTimezoneAbbrev(int field, const char *lowtoken,
-					 int *offset, pg_tz **tz)
+					 int *ftype, int *offset, pg_tz **tz,
+					 DateTimeErrorExtra *extra)
 {
-	int			type;
 	const datetkn *tp;
 
 	tp = abbrevcache[field];
@@ -3241,18 +3248,20 @@ DecodeTimezoneAbbrev(int field, const char *lowtoken,
 	}
 	if (tp == NULL)
 	{
-		type = UNKNOWN_FIELD;
+		*ftype = UNKNOWN_FIELD;
 		*offset = 0;
 		*tz = NULL;
 	}
 	else
 	{
 		abbrevcache[field] = tp;
-		type = tp->type;
-		if (type == DYNTZ)
+		*ftype = tp->type;
+		if (tp->type == DYNTZ)
 		{
 			*offset = 0;
-			*tz = FetchDynamicTimeZone(zoneabbrevtbl, tp);
+			*tz = FetchDynamicTimeZone(zoneabbrevtbl, tp, extra);
+			if (*tz == NULL)
+				return DTERR_BAD_ZONE_ABBREV;
 		}
 		else
 		{
@@ -3261,7 +3270,7 @@ DecodeTimezoneAbbrev(int field, const char *lowtoken,
 		}
 	}
 
-	return type;
+	return 0;
 }
 
 
@@ -4014,15 +4023,21 @@ DecodeUnits(int field, const char *lowtoken, int *val)
 /*
  * Report an error detected by one of the datetime input processing routines.
  *
- * dterr is the error code, str is the original input string, datatype is
- * the name of the datatype we were trying to accept.
+ * dterr is the error code, and *extra contains any auxiliary info we need
+ * for the error report.  extra can be NULL if not needed for the particular
+ * dterr value.
+ *
+ * str is the original input string, and datatype is the name of the datatype
+ * we were trying to accept.  (For some DTERR codes, these are not used and
+ * can be NULL.)
  *
  * Note: it might seem useless to distinguish DTERR_INTERVAL_OVERFLOW and
  * DTERR_TZDISP_OVERFLOW from DTERR_FIELD_OVERFLOW, but SQL99 mandates three
  * separate SQLSTATE codes, so ...
  */
 void
-DateTimeParseError(int dterr, const char *str, const char *datatype)
+DateTimeParseError(int dterr, DateTimeErrorExtra *extra,
+				   const char *str, const char *datatype)
 {
 	switch (dterr)
 	{
@@ -4052,6 +4067,20 @@ DateTimeParseError(int dterr, const char *str, const char *datatype)
 					 errmsg("time zone displacement out of range: \"%s\"",
 							str)));
 			break;
+		case DTERR_BAD_TIMEZONE:
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("time zone \"%s\" not recognized",
+							extra->dtee_timezone)));
+			break;
+		case DTERR_BAD_ZONE_ABBREV:
+			ereport(ERROR,
+					(errcode(ERRCODE_CONFIG_FILE_ERROR),
+					 errmsg("time zone \"%s\" not recognized",
+							extra->dtee_timezone),
+					 errdetail("This time zone name appears in the configuration file for time zone abbreviation \"%s\".",
+							   extra->dtee_abbrev)));
+			break;
 		case DTERR_BAD_FORMAT:
 		default:
 			ereport(ERROR,
@@ -4880,9 +4909,12 @@ InstallTimeZoneAbbrevs(TimeZoneAbbrevTable *tbl)
 
 /*
  * Helper subroutine to locate pg_tz timezone for a dynamic abbreviation.
+ *
+ * On failure, returns NULL and fills *extra for a DTERR_BAD_ZONE_ABBREV error.
  */
 static pg_tz *
-FetchDynamicTimeZone(TimeZoneAbbrevTable *tbl, const datetkn *tp)
+FetchDynamicTimeZone(TimeZoneAbbrevTable *tbl, const datetkn *tp,
+					 DateTimeErrorExtra *extra)
 {
 	DynamicZoneAbbrev *dtza;
 
@@ -4896,18 +4928,12 @@ FetchDynamicTimeZone(TimeZoneAbbrevTable *tbl, const datetkn *tp)
 	if (dtza->tz == NULL)
 	{
 		dtza->tz = pg_tzset(dtza->zone);
-
-		/*
-		 * Ideally we'd let the caller ereport instead of doing it here, but
-		 * then there is no way to report the bad time zone name.
-		 */
 		if (dtza->tz == NULL)
-			ereport(ERROR,
-					(errcode(ERRCODE_CONFIG_FILE_ERROR),
-					 errmsg("time zone \"%s\" not recognized",
-							dtza->zone),
-					 errdetail("This time zone name appears in the configuration file for time zone abbreviation \"%s\".",
-							   tp->token)));
+		{
+			/* Ooops, bogus zone name in config file entry */
+			extra->dtee_timezone = dtza->zone;
+			extra->dtee_abbrev = tp->token;
+		}
 	}
 	return dtza->tz;
 }
@@ -4993,10 +5019,14 @@ pg_timezone_abbrevs(PG_FUNCTION_ARGS)
 			{
 				/* Determine the current meaning of the abbrev */
 				pg_tz	   *tzp;
+				DateTimeErrorExtra extra;
 				TimestampTz now;
 				int			isdst;
 
-				tzp = FetchDynamicTimeZone(zoneabbrevtbl, tp);
+				tzp = FetchDynamicTimeZone(zoneabbrevtbl, tp, &extra);
+				if (tzp == NULL)
+					DateTimeParseError(DTERR_BAD_ZONE_ABBREV, &extra,
+									   NULL, NULL);
 				now = GetCurrentTransactionStartTimestamp();
 				gmtoffset = -DetermineTimeZoneAbbrevOffsetTS(now,
 															 tp->token,