Ticket #26217: patch-isspace-utf8-fix.diff

src/backend/utils/adt/arrayfuncs.c

@@ -50 +50 @@
         ARRAY_LEVEL_DELIMITED
 } ArrayParseState;
 
+static bool array_isspace(char ch);
 static int      ArrayCount(const char *str, int *dim, char typdelim);
 static void ReadArrayStr(char *arrayStr, const char *origStr,
                          int nitems, int ndim, int *dim,
@@ -192 +193 @@
                  * Note: we currently allow whitespace between, but not within,
                  * dimension items.
                  */
-                while (isspace((unsigned char) *p))
+                while (array_isspace(*p))
                         p++;
                 if (*p != '[')
                         break;                          /* no more dimension items */
@@ -265 +266 @@
                                         (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
                                          errmsg("missing assignment operator")));
                 p += strlen(ASSGN);
-                while (isspace((unsigned char) *p))
+                while (array_isspace(*p))
                         p++;
 
                 /*
@@ -345 +346 @@
 }
 
 /*
+ * array_isspace() --- a non-locale-dependent isspace()
+ *
+ * We used to use isspace() for parsing array values, but that has
+ * undesirable results: an array value might be silently interpreted
+ * differently depending on the locale setting.  Now we just hard-wire
+ * the traditional ASCII definition of isspace().
+ */
+static bool
+array_isspace(char ch)
+{
+        if (ch == ' ' ||
+                ch == '\t' ||
+                ch == '\n' ||
+                ch == '\r' ||
+                ch == '\v' ||
+                ch == '\f')
+                return true;
+        return false;
+}
+
+/*
  * ArrayCount
  *       Determines the dimensions for an array string.
  *
@@ -528 +550 @@
                                                         itemdone = true;
                                                         nelems[nest_level - 1]++;
                                                 }
-                                                else if (!isspace((unsigned char) *ptr))
+                                                else if (!array_isspace(*ptr))
                                                 {
                                                         /*
                                                          * Other non-space characters must be after a
@@ -557 +579 @@
         /* only whitespace is allowed after the closing brace */
         while (*ptr)
         {
-                if (!isspace((unsigned char) *ptr++))
+                if (!array_isspace(*ptr++))
                         ereport(ERROR,
                                         (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
                                          errmsg("malformed array literal: \"%s\"", str)));
@@ -750 +772 @@
                                                 indx[ndim - 1]++;
                                                 srcptr++;
                                         }
-                                        else if (isspace((unsigned char) *srcptr))
+                                        else if (array_isspace(*srcptr))
                                         {
                                                 /*
                                                  * If leading space, drop it immediately.  Else, copy
@@ -1038 +1060 @@
                                         overall_length += 1;
                                 }
                                 else if (ch == '{' || ch == '}' || ch == typdelim ||
-                                                 isspace((unsigned char) ch))
+                                                 array_isspace(ch))
                                         needquote = true;
                         }
                 }