Make our parsing of INTERVAL literals spec-compliant (or at least a heck of

a lot closer than it was before).  To do this, tweak coerce_type() to pass
through the typmod information when invoking interval_in() on an UNKNOWN
constant; then fix DecodeInterval to pay attention to the typmod when deciding
how to interpret a units-less integer value.  I changed one or two other
details as well.  I believe the code now reacts as expected by spec for all
the literal syntaxes that are specifically enumerated in the spec.  There
are corner cases involving strings that don't exactly match the set of fields
called out by the typmod, for which we might want to tweak the behavior some
more; but I think this is an area of user friendliness rather than spec
compliance.  There remain some non-compliant details about the SQL syntax
(as opposed to what's inside the literal string); but at least we'll throw
error rather than silently doing the wrong thing in those cases.

diff --git a/src/backend/parser/parse_coerce.c b/src/backend/parser/parse_coerce.c
index efe45974c35e9b03ec6c990df9bb2ad09cc21577..86e47661aa0888e8821752e395b02cb8fe595d89 100644 (file)
--- a/src/backend/parser/parse_coerce.c
+++ b/src/backend/parser/parse_coerce.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/parser/parse_coerce.c,v 2.166 2008/09/01 20:42:44 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/parser/parse_coerce.c,v 2.167 2008/09/10 18:29:40 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -179,6 +179,7 @@ coerce_type(ParseState *pstate, Node *node,
        Const      *newcon = makeNode(Const);
        Oid         baseTypeId;
        int32       baseTypeMod;
+       int32       inputTypeMod;
        Type        targetType;
        ParseCallbackState pcbstate;
 
@@ -190,13 +191,27 @@ coerce_type(ParseState *pstate, Node *node,
         * what we want here.  The needed check will be applied properly
         * inside coerce_to_domain().
         */
-       baseTypeMod = -1;
+       baseTypeMod = targetTypeMod;
        baseTypeId = getBaseTypeAndTypmod(targetTypeId, &baseTypeMod);
 
+       /*
+        * For most types we pass typmod -1 to the input routine, because
+        * existing input routines follow implicit-coercion semantics for
+        * length checks, which is not always what we want here.  Any length
+        * constraint will be applied later by our caller.  An exception
+        * however is the INTERVAL type, for which we *must* pass the typmod
+        * or it won't be able to obey the bizarre SQL-spec input rules.
+        * (Ugly as sin, but so is this part of the spec...)
+        */
+       if (baseTypeId == INTERVALOID)
+           inputTypeMod = baseTypeMod;
+       else
+           inputTypeMod = -1;
+
        targetType = typeidType(baseTypeId);
 
        newcon->consttype = baseTypeId;
-       newcon->consttypmod = -1;
+       newcon->consttypmod = inputTypeMod;
        newcon->constlen = typeLen(targetType);
        newcon->constbyval = typeByVal(targetType);
        newcon->constisnull = con->constisnull;
@@ -215,20 +230,17 @@ coerce_type(ParseState *pstate, Node *node,
        setup_parser_errposition_callback(&pcbstate, pstate, con->location);
 
        /*
-        * We pass typmod -1 to the input routine, primarily because existing
-        * input routines follow implicit-coercion semantics for length
-        * checks, which is not always what we want here. Any length
-        * constraint will be applied later by our caller.
-        *
         * We assume here that UNKNOWN's internal representation is the same
         * as CSTRING.
         */
        if (!con->constisnull)
            newcon->constvalue = stringTypeDatum(targetType,
                                            DatumGetCString(con->constvalue),
-                                                -1);
+                                                inputTypeMod);
        else
-           newcon->constvalue = stringTypeDatum(targetType, NULL, -1);
+           newcon->constvalue = stringTypeDatum(targetType,
+                                                NULL,
+                                                inputTypeMod);
 
        cancel_parser_errposition_callback(&pcbstate);
 

diff --git a/src/backend/utils/adt/datetime.c b/src/backend/utils/adt/datetime.c
index a92583ca19e947c64998ea4d3a22c488a06f8edf..6712d6d8d44397e1929db9e5b0660c957a2dd911 100644 (file)
--- a/src/backend/utils/adt/datetime.c
+++ b/src/backend/utils/adt/datetime.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/utils/adt/datetime.c,v 1.190 2008/06/09 19:34:02 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/utils/adt/datetime.c,v 1.191 2008/09/10 18:29:41 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -35,8 +35,8 @@ static int DecodeNumber(int flen, char *field, bool haveTextMonth,
 static int DecodeNumberField(int len, char *str,
                  int fmask, int *tmask,
                  struct pg_tm * tm, fsec_t *fsec, bool *is2digits);
-static int DecodeTime(char *str, int fmask, int *tmask,
-          struct pg_tm * tm, fsec_t *fsec);
+static int DecodeTime(char *str, int fmask, int range,
+          int *tmask, struct pg_tm * tm, fsec_t *fsec);
 static int DecodeTimezone(char *str, int *tzp);
 static const datetkn *datebsearch(const char *key, const datetkn *base, int nel);
 static int DecodeDate(char *str, int fmask, int *tmask, bool *is2digits,
@@ -832,7 +832,8 @@ DecodeDateTime(char **field, int *ftype, int nf,
                break;
 
            case DTK_TIME:
-               dterr = DecodeTime(field[i], fmask, &tmask, tm, fsec);
+               dterr = DecodeTime(field[i], fmask, INTERVAL_FULL_RANGE,
+                                  &tmask, tm, fsec);
                if (dterr)
                    return dterr;
 
@@ -1563,6 +1564,7 @@ DecodeTimeOnly(char **field, int *ftype, int nf,
 
            case DTK_TIME:
                dterr = DecodeTime(field[i], (fmask | DTK_DATE_M),
+                                  INTERVAL_FULL_RANGE,
                                   &tmask, tm, fsec);
                if (dterr)
                    return dterr;
@@ -2224,7 +2226,8 @@ ValidateDate(int fmask, bool is2digits, bool bc, struct pg_tm * tm)
  * used to represent time spans.
  */
 static int
-DecodeTime(char *str, int fmask, int *tmask, struct pg_tm * tm, fsec_t *fsec)
+DecodeTime(char *str, int fmask, int range,
+          int *tmask, struct pg_tm * tm, fsec_t *fsec)
 {
    char       *cp;
 
@@ -2245,6 +2248,13 @@ DecodeTime(char *str, int fmask, int *tmask, struct pg_tm * tm, fsec_t *fsec)
    {
        tm->tm_sec = 0;
        *fsec = 0;
+       /* If it's a MINUTE TO SECOND interval, take 2 fields as being mm:ss */
+       if (range == (INTERVAL_MASK(MINUTE) | INTERVAL_MASK(SECOND)))
+       {
+           tm->tm_sec = tm->tm_min;
+           tm->tm_min = tm->tm_hour;
+           tm->tm_hour = 0;
+       }
    }
    else if (*cp != ':')
        return DTERR_BAD_FORMAT;
@@ -2705,7 +2715,8 @@ DecodeSpecial(int field, char *lowtoken, int *val)
  * preceding an hh:mm:ss field. - thomas 1998-04-30
  */
 int
-DecodeInterval(char **field, int *ftype, int nf, int *dtype, struct pg_tm * tm, fsec_t *fsec)
+DecodeInterval(char **field, int *ftype, int nf, int range,
+              int *dtype, struct pg_tm * tm, fsec_t *fsec)
 {
    bool        is_before = FALSE;
    char       *cp;
@@ -2734,7 +2745,8 @@ DecodeInterval(char **field, int *ftype, int nf, int *dtype, struct pg_tm * tm,
        switch (ftype[i])
        {
            case DTK_TIME:
-               dterr = DecodeTime(field[i], fmask, &tmask, tm, fsec);
+               dterr = DecodeTime(field[i], fmask, range,
+                                  &tmask, tm, fsec);
                if (dterr)
                    return dterr;
                type = DTK_DAY;
@@ -2757,7 +2769,8 @@ DecodeInterval(char **field, int *ftype, int nf, int *dtype, struct pg_tm * tm,
                while (*cp != '\0' && *cp != ':' && *cp != '.')
                    cp++;
                if (*cp == ':' &&
-                   DecodeTime(field[i] + 1, fmask, &tmask, tm, fsec) == 0)
+                   DecodeTime(field[i] + 1, fmask, INTERVAL_FULL_RANGE,
+                              &tmask, tm, fsec) == 0)
                {
                    if (*field[i] == '-')
                    {
@@ -2796,19 +2809,66 @@ DecodeInterval(char **field, int *ftype, int nf, int *dtype, struct pg_tm * tm,
                        type = DTK_HOUR;
                    }
                }
-               /* DROP THROUGH */
+               /* FALL THROUGH */
 
            case DTK_DATE:
            case DTK_NUMBER:
+               if (type == IGNORE_DTF)
+               {
+                   /* use typmod to decide what rightmost integer field is */
+                   switch (range)
+                   {
+                       case INTERVAL_MASK(YEAR):
+                           type = DTK_YEAR;
+                           break;
+                       case INTERVAL_MASK(MONTH):
+                       case INTERVAL_MASK(YEAR) | INTERVAL_MASK(MONTH):
+                           type = DTK_MONTH;
+                           break;
+                       case INTERVAL_MASK(DAY):
+                           type = DTK_DAY;
+                           break;
+                       case INTERVAL_MASK(HOUR):
+                       case INTERVAL_MASK(DAY) | INTERVAL_MASK(HOUR):
+                       case INTERVAL_MASK(DAY) | INTERVAL_MASK(HOUR) | INTERVAL_MASK(MINUTE):
+                       case INTERVAL_MASK(DAY) | INTERVAL_MASK(HOUR) | INTERVAL_MASK(MINUTE) | INTERVAL_MASK(SECOND):
+                           type = DTK_HOUR;
+                           break;
+                       case INTERVAL_MASK(MINUTE):
+                       case INTERVAL_MASK(HOUR) | INTERVAL_MASK(MINUTE):
+                           type = DTK_MINUTE;
+                           break;
+                       case INTERVAL_MASK(SECOND):
+                       case INTERVAL_MASK(HOUR) | INTERVAL_MASK(MINUTE) | INTERVAL_MASK(SECOND):
+                       case INTERVAL_MASK(MINUTE) | INTERVAL_MASK(SECOND):
+                           type = DTK_SECOND;
+                           break;
+                       default:
+                           type = DTK_SECOND;
+                           break;
+                   }
+               }
+
                errno = 0;
                val = strtoi(field[i], &cp, 10);
                if (errno == ERANGE)
                    return DTERR_FIELD_OVERFLOW;
 
-               if (type == IGNORE_DTF)
-                   type = DTK_SECOND;
+               if (*cp == '-')
+               {
+                   /* SQL "years-months" syntax */
+                   int     val2;
 
-               if (*cp == '.')
+                   val2 = strtoi(cp + 1, &cp, 10);
+                   if (errno == ERANGE || val2 < 0 || val2 >= MONTHS_PER_YEAR)
+                       return DTERR_FIELD_OVERFLOW;
+                   if (*cp != '\0')
+                       return DTERR_BAD_FORMAT;
+                   type = DTK_MONTH;
+                   val = val * MONTHS_PER_YEAR + val2;
+                   fval = 0;
+               }
+               else if (*cp == '.')
                {
                    fval = strtod(cp, &cp);
                    if (*cp != '\0')
@@ -2896,6 +2956,7 @@ DecodeInterval(char **field, int *ftype, int nf, int *dtype, struct pg_tm * tm,
 #endif
                        }
                        tmask = DTK_M(HOUR);
+                       type = DTK_DAY;
                        break;
 
                    case DTK_DAY:

diff --git a/src/backend/utils/adt/nabstime.c b/src/backend/utils/adt/nabstime.c
index a40ca5edd05b485faba9ae9e8bb2b0df93243807..4a505c341e9f8f17898300ffd399e729a9b5c6d9 100644 (file)
--- a/src/backend/utils/adt/nabstime.c
+++ b/src/backend/utils/adt/nabstime.c
@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/utils/adt/nabstime.c,v 1.155 2008/03/25 22:42:44 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/utils/adt/nabstime.c,v 1.156 2008/09/10 18:29:41 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -632,7 +632,8 @@ reltimein(PG_FUNCTION_ARGS)
    dterr = ParseDateTime(str, workbuf, sizeof(workbuf),
                          field, ftype, MAXDATEFIELDS, &nf);
    if (dterr == 0)
-       dterr = DecodeInterval(field, ftype, nf, &dtype, tm, &fsec);
+       dterr = DecodeInterval(field, ftype, nf, INTERVAL_FULL_RANGE,
+                              &dtype, tm, &fsec);
    if (dterr != 0)
    {
        if (dterr == DTERR_FIELD_OVERFLOW)

diff --git a/src/backend/utils/adt/timestamp.c b/src/backend/utils/adt/timestamp.c
index d6a5dee08425b36f0d2d5d8b6948d77e29fc7be3..9060b989f9cd01e57d77e2d2c4368b02395b64cf 100644 (file)
--- 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 1.190 2008/07/07 18:09:46 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/utils/adt/timestamp.c,v 1.191 2008/09/10 18:29:41 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -604,6 +604,7 @@ interval_in(PG_FUNCTION_ARGS)
               *tm = &tt;
    int         dtype;
    int         nf;
+   int         range;
    int         dterr;
    char       *field[MAXDATEFIELDS];
    int         ftype[MAXDATEFIELDS];
@@ -617,10 +618,15 @@ interval_in(PG_FUNCTION_ARGS)
    tm->tm_sec = 0;
    fsec = 0;
 
+   if (typmod >= 0)
+       range = INTERVAL_RANGE(typmod);
+   else
+       range = INTERVAL_FULL_RANGE;
+
    dterr = ParseDateTime(str, workbuf, sizeof(workbuf), field,
                          ftype, MAXDATEFIELDS, &nf);
    if (dterr == 0)
-       dterr = DecodeInterval(field, ftype, nf, &dtype, tm, &fsec);
+       dterr = DecodeInterval(field, ftype, nf, range, &dtype, tm, &fsec);
    if (dterr != 0)
    {
        if (dterr == DTERR_FIELD_OVERFLOW)
@@ -945,7 +951,7 @@ AdjustIntervalForTypmod(Interval *interval, int32 typmod)
     * Unspecified range and precision? Then not necessary to adjust. Setting
     * typmod to -1 is the convention for all types.
     */
-   if (typmod != -1)
+   if (typmod >= 0)
    {
        int         range = INTERVAL_RANGE(typmod);
        int         precision = INTERVAL_PRECISION(typmod);

diff --git a/src/include/utils/datetime.h b/src/include/utils/datetime.h
index ffb4c45240f5cd374f480e8c0d3a891fd1773867..439e9779d203cc54e885ca08e6acb1c391730538 100644 (file)
--- a/src/include/utils/datetime.h
+++ b/src/include/utils/datetime.h
@@ -9,7 +9,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/datetime.h,v 1.69 2008/01/01 19:45:59 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/utils/datetime.h,v 1.70 2008/09/10 18:29:41 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -290,7 +290,7 @@ extern int DecodeTimeOnly(char **field, int *ftype,
               int nf, int *dtype,
               struct pg_tm * tm, fsec_t *fsec, int *tzp);
 extern int DecodeInterval(char **field, int *ftype,
-              int nf, int *dtype,
+              int nf, int range, int *dtype,
               struct pg_tm * tm, fsec_t *fsec);
 extern void DateTimeParseError(int dterr, const char *str,
                   const char *datatype);

diff --git a/src/test/regress/expected/interval.out b/src/test/regress/expected/interval.out
index 049850af8eb764a97735ec81149aab2eb1274165..ede3c58708c1c321ddffd80d72be6dd380982c16 100644 (file)
--- a/src/test/regress/expected/interval.out
+++ b/src/test/regress/expected/interval.out
@@ -361,3 +361,160 @@ SELECT '1:20:05 5 microseconds'::interval;          -- error
 ERROR:  invalid input syntax for type interval: "1:20:05 5 microseconds"
 LINE 1: SELECT '1:20:05 5 microseconds'::interval;
                ^
+SELECT interval '1-2';  -- SQL year-month literal
+   interval    
+---------------
+ 1 year 2 mons
+(1 row)
+
+-- test SQL-spec syntaxes for restricted field sets
+SELECT interval '1' year;
+ interval 
+----------
+ 1 year
+(1 row)
+
+SELECT interval '2' month;
+ interval 
+----------
+ 2 mons
+(1 row)
+
+SELECT interval '3' day;
+ interval 
+----------
+ 3 days
+(1 row)
+
+SELECT interval '4' hour;
+ interval 
+----------
+ 04:00:00
+(1 row)
+
+SELECT interval '5' minute;
+ interval 
+----------
+ 00:05:00
+(1 row)
+
+SELECT interval '6' second;
+ interval 
+----------
+ 00:00:06
+(1 row)
+
+SELECT interval '1' year to month;
+ interval 
+----------
+ 1 mon
+(1 row)
+
+SELECT interval '1-2' year to month;
+   interval    
+---------------
+ 1 year 2 mons
+(1 row)
+
+SELECT interval '1 2' day to hour;
+    interval    
+----------------
+ 1 day 02:00:00
+(1 row)
+
+SELECT interval '1 2:03' day to hour;
+    interval    
+----------------
+ 1 day 02:00:00
+(1 row)
+
+SELECT interval '1 2:03:04' day to hour;
+    interval    
+----------------
+ 1 day 02:00:00
+(1 row)
+
+SELECT interval '1 2' day to minute;
+    interval    
+----------------
+ 1 day 02:00:00
+(1 row)
+
+SELECT interval '1 2:03' day to minute;
+    interval    
+----------------
+ 1 day 02:03:00
+(1 row)
+
+SELECT interval '1 2:03:04' day to minute;
+    interval    
+----------------
+ 1 day 02:03:00
+(1 row)
+
+SELECT interval '1 2' day to second;
+    interval    
+----------------
+ 1 day 02:00:00
+(1 row)
+
+SELECT interval '1 2:03' day to second;
+    interval    
+----------------
+ 1 day 02:03:00
+(1 row)
+
+SELECT interval '1 2:03:04' day to second;
+    interval    
+----------------
+ 1 day 02:03:04
+(1 row)
+
+SELECT interval '1 2' hour to minute;
+ERROR:  invalid input syntax for type interval: "1 2"
+LINE 1: SELECT interval '1 2' hour to minute;
+                        ^
+SELECT interval '1 2:03' hour to minute;
+ interval 
+----------
+ 02:03:00
+(1 row)
+
+SELECT interval '1 2:03:04' hour to minute;
+ interval 
+----------
+ 02:03:00
+(1 row)
+
+SELECT interval '1 2' hour to second;
+ERROR:  invalid input syntax for type interval: "1 2"
+LINE 1: SELECT interval '1 2' hour to second;
+                        ^
+SELECT interval '1 2:03' hour to second;
+ interval 
+----------
+ 02:03:00
+(1 row)
+
+SELECT interval '1 2:03:04' hour to second;
+ interval 
+----------
+ 02:03:04
+(1 row)
+
+SELECT interval '1 2' minute to second;
+ERROR:  invalid input syntax for type interval: "1 2"
+LINE 1: SELECT interval '1 2' minute to second;
+                        ^
+SELECT interval '1 2:03' minute to second;
+ interval 
+----------
+ 00:02:03
+(1 row)
+
+SELECT interval '1 2:03:04' minute to second;
+ interval 
+----------
+ 00:03:04
+(1 row)
+

diff --git a/src/test/regress/sql/interval.sql b/src/test/regress/sql/interval.sql
index d081bf1ffedf2d504f2c422e49abd9a2a6a48045..2c6aecaa5197d65afb1dda84414f669ab4096309 100644 (file)
--- a/src/test/regress/sql/interval.sql
+++ b/src/test/regress/sql/interval.sql
@@ -126,4 +126,33 @@ SELECT '3 days 5 milliseconds'::interval;
 SELECT '1 second 2 seconds'::interval;              -- error
 SELECT '10 milliseconds 20 milliseconds'::interval; -- error
 SELECT '5.5 seconds 3 milliseconds'::interval;      -- error
-SELECT '1:20:05 5 microseconds'::interval;          -- error
\ No newline at end of file
+SELECT '1:20:05 5 microseconds'::interval;          -- error
+SELECT interval '1-2';  -- SQL year-month literal
+
+-- test SQL-spec syntaxes for restricted field sets
+SELECT interval '1' year;
+SELECT interval '2' month;
+SELECT interval '3' day;
+SELECT interval '4' hour;
+SELECT interval '5' minute;
+SELECT interval '6' second;
+SELECT interval '1' year to month;
+SELECT interval '1-2' year to month;
+SELECT interval '1 2' day to hour;
+SELECT interval '1 2:03' day to hour;
+SELECT interval '1 2:03:04' day to hour;
+SELECT interval '1 2' day to minute;
+SELECT interval '1 2:03' day to minute;
+SELECT interval '1 2:03:04' day to minute;
+SELECT interval '1 2' day to second;
+SELECT interval '1 2:03' day to second;
+SELECT interval '1 2:03:04' day to second;
+SELECT interval '1 2' hour to minute;
+SELECT interval '1 2:03' hour to minute;
+SELECT interval '1 2:03:04' hour to minute;
+SELECT interval '1 2' hour to second;
+SELECT interval '1 2:03' hour to second;
+SELECT interval '1 2:03:04' hour to second;
+SELECT interval '1 2' minute to second;
+SELECT interval '1 2:03' minute to second;
+SELECT interval '1 2:03:04' minute to second;