Fix to_char() to use ASCII-only case-folding rules where appropriate.

formatting.c used locale-dependent case folding rules in some code paths
where the result isn't supposed to be locale-dependent, for example
to_char(timestamp, 'DAY').  Since the source data is always just ASCII
in these cases, that usually didn't matter ... but it does matter in
Turkish locales, which have unusual treatment of "i" and "I".  To confuse
matters even more, the misbehavior was only visible in UTF8 encoding,
because in single-byte encodings we used pg_toupper/pg_tolower which
don't have locale-specific behavior for ASCII characters.  Fix by providing
intentionally ASCII-only case-folding functions and using these where
appropriate.  Per bug #7913 from Adnan Dursun.  Back-patch to all active
branches, since it's been like this for a long time.

diff --git a/src/backend/utils/adt/formatting.c b/src/backend/utils/adt/formatting.c
index cb99b86b23e378d32b2675c389393df9f4205072..3b823fa78fb8a9ea6a4f1641c27d8a6bfb92334b 100644 (file)
--- a/src/backend/utils/adt/formatting.c
+++ b/src/backend/utils/adt/formatting.c
@@ -1646,6 +1646,87 @@ str_initcap(const char *buff, size_t nbytes)
        return result;
 }
 
+/*
+ * ASCII-only lower function
+ *
+ * We pass the number of bytes so we can pass varlena and char*
+ * to this function.  The result is a palloc'd, null-terminated string.
+ */
+char *
+asc_tolower(const char *buff, size_t nbytes)
+{
+       char       *result;
+       char       *p;
+
+       if (!buff)
+               return NULL;
+
+       result = pnstrdup(buff, nbytes);
+
+       for (p = result; *p; p++)
+               *p = pg_tolower((unsigned char) *p);
+
+       return result;
+}
+
+/*
+ * ASCII-only upper function
+ *
+ * We pass the number of bytes so we can pass varlena and char*
+ * to this function.  The result is a palloc'd, null-terminated string.
+ */
+char *
+asc_toupper(const char *buff, size_t nbytes)
+{
+       char       *result;
+       char       *p;
+
+       if (!buff)
+               return NULL;
+
+       result = pnstrdup(buff, nbytes);
+
+       for (p = result; *p; p++)
+               *p = pg_toupper((unsigned char) *p);
+
+       return result;
+}
+
+/*
+ * ASCII-only initcap function
+ *
+ * We pass the number of bytes so we can pass varlena and char*
+ * to this function.  The result is a palloc'd, null-terminated string.
+ */
+char *
+asc_initcap(const char *buff, size_t nbytes)
+{
+       char       *result;
+       char       *p;
+       int                     wasalnum = false;
+
+       if (!buff)
+               return NULL;
+
+       result = pnstrdup(buff, nbytes);
+
+       for (p = result; *p; p++)
+       {
+               char            c;
+
+               if (wasalnum)
+                       *p = c = pg_tolower((unsigned char) *p);
+               else
+                       *p = c = pg_toupper((unsigned char) *p);
+               /* we don't trust isalnum() here */
+               wasalnum = ((c >= 'A' && c <= 'Z') ||
+                                       (c >= 'a' && c <= 'z') ||
+                                       (c >= '0' && c <= '9'));
+       }
+
+       return result;
+}
+
 /* convenience routines for when the input is null-terminated */
 
 static char *
@@ -1666,6 +1747,20 @@ str_initcap_z(const char *buff)
        return str_initcap(buff, strlen(buff));
 }
 
+static char *
+asc_tolower_z(const char *buff)
+{
+       return asc_tolower(buff, strlen(buff));
+}
+
+static char *
+asc_toupper_z(const char *buff)
+{
+       return asc_toupper(buff, strlen(buff));
+}
+
+/* asc_initcap_z is not currently needed */
+
 
 /* ----------
  * Skip TM / th in FROM_CHAR
@@ -2149,7 +2244,8 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                INVALID_FOR_INTERVAL;
                                if (tmtcTzn(in))
                                {
-                                       char       *p = str_tolower_z(tmtcTzn(in));
+                                       /* We assume here that timezone names aren't localized */
+                                       char       *p = asc_tolower_z(tmtcTzn(in));
 
                                        strcpy(s, p);
                                        pfree(p);
@@ -2196,7 +2292,7 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                        strcpy(s, str_toupper_z(localized_full_months[tm->tm_mon - 1]));
                                else
                                        sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9,
-                                                       str_toupper_z(months_full[tm->tm_mon - 1]));
+                                                       asc_toupper_z(months_full[tm->tm_mon - 1]));
                                s += strlen(s);
                                break;
                        case DCH_Month:
@@ -2206,7 +2302,8 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_initcap_z(localized_full_months[tm->tm_mon - 1]));
                                else
-                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9, months_full[tm->tm_mon - 1]);
+                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9,
+                                                       months_full[tm->tm_mon - 1]);
                                s += strlen(s);
                                break;
                        case DCH_month:
@@ -2216,10 +2313,8 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_tolower_z(localized_full_months[tm->tm_mon - 1]));
                                else
-                               {
-                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9, months_full[tm->tm_mon - 1]);
-                                       *s = pg_tolower((unsigned char) *s);
-                               }
+                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9,
+                                                       asc_tolower_z(months_full[tm->tm_mon - 1]));
                                s += strlen(s);
                                break;
                        case DCH_MON:
@@ -2229,7 +2324,7 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_toupper_z(localized_abbrev_months[tm->tm_mon - 1]));
                                else
-                                       strcpy(s, str_toupper_z(months[tm->tm_mon - 1]));
+                                       strcpy(s, asc_toupper_z(months[tm->tm_mon - 1]));
                                s += strlen(s);
                                break;
                        case DCH_Mon:
@@ -2249,10 +2344,7 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_tolower_z(localized_abbrev_months[tm->tm_mon - 1]));
                                else
-                               {
-                                       strcpy(s, months[tm->tm_mon - 1]);
-                                       *s = pg_tolower((unsigned char) *s);
-                               }
+                                       strcpy(s, asc_tolower_z(months[tm->tm_mon - 1]));
                                s += strlen(s);
                                break;
                        case DCH_MM:
@@ -2267,7 +2359,7 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                        strcpy(s, str_toupper_z(localized_full_days[tm->tm_wday]));
                                else
                                        sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9,
-                                                       str_toupper_z(days[tm->tm_wday]));
+                                                       asc_toupper_z(days[tm->tm_wday]));
                                s += strlen(s);
                                break;
                        case DCH_Day:
@@ -2275,7 +2367,8 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_initcap_z(localized_full_days[tm->tm_wday]));
                                else
-                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9, days[tm->tm_wday]);
+                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9,
+                                                       days[tm->tm_wday]);
                                s += strlen(s);
                                break;
                        case DCH_day:
@@ -2283,10 +2376,8 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_tolower_z(localized_full_days[tm->tm_wday]));
                                else
-                               {
-                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9, days[tm->tm_wday]);
-                                       *s = pg_tolower((unsigned char) *s);
-                               }
+                                       sprintf(s, "%*s", S_FM(n->suffix) ? 0 : -9,
+                                                       asc_tolower_z(days[tm->tm_wday]));
                                s += strlen(s);
                                break;
                        case DCH_DY:
@@ -2294,7 +2385,7 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_toupper_z(localized_abbrev_days[tm->tm_wday]));
                                else
-                                       strcpy(s, str_toupper_z(days_short[tm->tm_wday]));
+                                       strcpy(s, asc_toupper_z(days_short[tm->tm_wday]));
                                s += strlen(s);
                                break;
                        case DCH_Dy:
@@ -2310,10 +2401,7 @@ DCH_to_char(FormatNode *node, bool is_interval, TmToChar *in, char *out)
                                if (S_TM(n->suffix))
                                        strcpy(s, str_tolower_z(localized_abbrev_days[tm->tm_wday]));
                                else
-                               {
-                                       strcpy(s, days_short[tm->tm_wday]);
-                                       *s = pg_tolower((unsigned char) *s);
-                               }
+                                       strcpy(s, asc_tolower_z(days_short[tm->tm_wday]));
                                s += strlen(s);
                                break;
                        case DCH_DDD:
@@ -4414,12 +4502,12 @@ NUM_processor(FormatNode *node, NUMDesc *Num, char *inout, char *number,
                                case NUM_rn:
                                        if (IS_FILLMODE(Np->Num))
                                        {
-                                               strcpy(Np->inout_p, str_tolower_z(Np->number_p));
+                                               strcpy(Np->inout_p, asc_tolower_z(Np->number_p));
                                                Np->inout_p += strlen(Np->inout_p) - 1;
                                        }
                                        else
                                        {
-                                               sprintf(Np->inout_p, "%15s", str_tolower_z(Np->number_p));
+                                               sprintf(Np->inout_p, "%15s", asc_tolower_z(Np->number_p));
                                                Np->inout_p += strlen(Np->inout_p) - 1;
                                        }
                                        break;

diff --git a/src/include/utils/formatting.h b/src/include/utils/formatting.h
index 006dbc8a28d334f5c594a83c9caac0d8d3dd53b5..e0c9dda2a07705a17aaaa23c46492ca3043b918b 100644 (file)
--- a/src/include/utils/formatting.h
+++ b/src/include/utils/formatting.h
@@ -25,6 +25,10 @@ extern char *str_tolower(const char *buff, size_t nbytes);
 extern char *str_toupper(const char *buff, size_t nbytes);
 extern char *str_initcap(const char *buff, size_t nbytes);
 
+extern char *asc_tolower(const char *buff, size_t nbytes);
+extern char *asc_toupper(const char *buff, size_t nbytes);
+extern char *asc_initcap(const char *buff, size_t nbytes);
+
 extern Datum timestamp_to_char(PG_FUNCTION_ARGS);
 extern Datum timestamptz_to_char(PG_FUNCTION_ARGS);
 extern Datum interval_to_char(PG_FUNCTION_ARGS);