Fix realfailN lexer rules to not make assumptions about input format.

tglsfdc · tglsfdc · commit 965a3d6be070 · 2018-11-13T14:54:41.000-05:00
The realfail1 and realfail2 backup-prevention rules always returned token type FCONST, ignoring the possibility that what we've scanned is more appropriately described as ICONST. I think that at the time that code was added, it might actually have been safe to not distinguish; but since we started allowing AS-less aliases in SELECT target lists, it's definitely legal to have a number immediately followed by an identifier. In the SELECT case, it seems there's no visible consequence because make_const() will change the type back to integer anyway. But I'm worried that there are other contexts, or will be in future, where it's more important to get the constant's type right. Hence, use process_integer_literal to correctly determine which token type to return. Arguably this is a bug fix, but given the lack of evidence of user-visible problems, I'll refrain from back-patching. Discussion: https://postgr.es/m/21364.1542136808@sss.pgh.pa.us
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
@@ -1005,22 +1005,18 @@ other			.
 				}
 {realfail1}		{
 					/*
-					 * throw back the [Ee], and treat as {decimal}.  Note
-					 * that it is possible the input is actually {integer},
-					 * but since this case will almost certainly lead to a
-					 * syntax error anyway, we don't bother to distinguish.
+					 * throw back the [Ee], and figure out whether what
+					 * remains is an {integer} or {decimal}.
 					 */
 					yyless(yyleng - 1);
 					SET_YYLLOC();
-					yylval->str = pstrdup(yytext);
-					return FCONST;
+					return process_integer_literal(yytext, yylval);
 				}
 {realfail2}		{
 					/* throw back the [Ee][+-], and proceed as above */
 					yyless(yyleng - 2);
 					SET_YYLLOC();
-					yylval->str = pstrdup(yytext);
-					return FCONST;
+					return process_integer_literal(yytext, yylval);
 				}
 
 
@@ -1255,6 +1251,10 @@ litbufdup(core_yyscan_t yyscanner)
 	return new;
 }
 
+/*
+ * Process {integer}.  Note this will also do the right thing with {decimal},
+ * ie digits and a decimal point.
+ */
 static int
 process_integer_literal(const char *token, YYSTYPE *lval)
 {
@@ -1265,7 +1265,7 @@ process_integer_literal(const char *token, YYSTYPE *lval)
 	val = strtoint(token, &endptr, 10);
 	if (*endptr != '\0' || errno == ERANGE)
 	{
-		/* integer too large, treat it as a float */
+		/* integer too large (or contains decimal pt), treat it as a float */
 		lval->str = pstrdup(token);
 		return FCONST;
 	}
diff --git a/src/fe_utils/psqlscan.l b/src/fe_utils/psqlscan.l
@@ -887,10 +887,9 @@ other			.
 				}
 {realfail1}		{
 					/*
-					 * throw back the [Ee], and treat as {decimal}.  Note
-					 * that it is possible the input is actually {integer},
-					 * but since this case will almost certainly lead to a
-					 * syntax error anyway, we don't bother to distinguish.
+					 * throw back the [Ee], and figure out whether what
+					 * remains is an {integer} or {decimal}.
+					 * (in psql, we don't actually care...)
 					 */
 					yyless(yyleng - 1);
 					ECHO;
diff --git a/src/interfaces/ecpg/preproc/pgc.l b/src/interfaces/ecpg/preproc/pgc.l
@@ -900,20 +900,16 @@ cppline			{space}*#([^i][A-Za-z]*|{if}|{ifdef}|{ifndef}|{import})((\/\*[^*/]*\*+
 				}
 {realfail1}		{
 					/*
-					 * throw back the [Ee], and treat as {decimal}.  Note
-					 * that it is possible the input is actually {integer},
-					 * but since this case will almost certainly lead to a
-					 * syntax error anyway, we don't bother to distinguish.
+					 * throw back the [Ee], and figure out whether what
+					 * remains is an {integer} or {decimal}.
 					 */
 					yyless(yyleng - 1);
-					base_yylval.str = mm_strdup(yytext);
-					return FCONST;
+					return process_integer_literal(yytext, &base_yylval);
 				}
 {realfail2}		{
 					/* throw back the [Ee][+-], and proceed as above */
 					yyless(yyleng - 2);
-					base_yylval.str = mm_strdup(yytext);
-					return FCONST;
+					return process_integer_literal(yytext, &base_yylval);
 				}
 } /* <C,SQL> */
 
@@ -1473,6 +1469,10 @@ addlitchar(unsigned char ychar)
 	literalbuf[literallen] = '\0';
 }
 
+/*
+ * Process {integer}.  Note this will also do the right thing with {decimal},
+ * ie digits and a decimal point.
+ */
 static int
 process_integer_literal(const char *token, YYSTYPE *lval)
 {
@@ -1483,7 +1483,7 @@ process_integer_literal(const char *token, YYSTYPE *lval)
 	val = strtoint(token, &endptr, 10);
 	if (*endptr != '\0' || errno == ERANGE)
 	{
-		/* integer too large, treat it as a float */
+		/* integer too large (or contains decimal pt), treat it as a float */
 		lval->str = mm_strdup(token);
 		return FCONST;
 	}
