cube: pure parser and reentrant scanner

petere · petere · commit 802fe923e3cd · 2024-12-18T08:47:34.000+01:00
Use the flex %option reentrant and the bison option %pure-parser to make the generated scanner and parser pure, reentrant, and thread-safe. Make the generated scanner use palloc() etc. instead of malloc() etc. Previously, we only used palloc() for the buffer, but flex would still use malloc() for its internal structures. As a result, there could be some small memory leaks in case of uncaught errors. (We do catch normal syntax errors as soft errors.) Now, all the memory is under palloc() control, so there are no more such issues. Simplify flex scan buffer management: Instead of constructing the buffer from pieces and then using yy_scan_buffer(), we can just use yy_scan_string(), which does the same thing internally. (Actually, we use yy_scan_bytes() here because we already have the length.) The previous code was necessary because we allocated the buffer with palloc() and the rest of the state was handled by malloc(). But this is no longer the case; everything is under palloc() now. (We could even get rid of the yylex_destroy() call and just let the memory context cleanup handle everything. But for now, we preserve the existing behavior.) Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi> Reviewed-by: Andreas Karlsson <andreas@proxel.se> Discussion: https://www.postgresql.org/message-id/flat/eb6faeac-2a8a-4b69-9189-c33c520e5b7b@eisentraut.org
diff --git a/contrib/cube/cube.c b/contrib/cube/cube.c
@@ -120,13 +120,14 @@ cube_in(PG_FUNCTION_ARGS)
 	char	   *str = PG_GETARG_CSTRING(0);
 	NDBOX	   *result;
 	Size		scanbuflen;
+	yyscan_t	scanner;
 
-	cube_scanner_init(str, &scanbuflen);
+	cube_scanner_init(str, &scanbuflen, &scanner);
 
-	cube_yyparse(&result, scanbuflen, fcinfo->context);
+	cube_yyparse(&result, scanbuflen, fcinfo->context, scanner);
 
 	/* We might as well run this even on failure. */
-	cube_scanner_finish();
+	cube_scanner_finish(scanner);
 
 	PG_RETURN_NDBOX_P(result);
 }
diff --git a/contrib/cube/cubedata.h b/contrib/cube/cubedata.h
@@ -59,14 +59,21 @@ typedef struct NDBOX
 #define CubeKNNDistanceEuclid			17	/* <-> */
 #define CubeKNNDistanceChebyshev		18	/* <=> */
 
+/* for cubescan.l and cubeparse.y */
+/* All grammar constructs return strings */
+#define YYSTYPE char *
+typedef void *yyscan_t;
+
 /* in cubescan.l */
-extern int	cube_yylex(void);
+extern int	cube_yylex(YYSTYPE *yylval_param, yyscan_t yyscanner);
 extern void cube_yyerror(NDBOX **result, Size scanbuflen,
 						 struct Node *escontext,
+						 yyscan_t yyscanner,
 						 const char *message);
-extern void cube_scanner_init(const char *str, Size *scanbuflen);
-extern void cube_scanner_finish(void);
+extern void cube_scanner_init(const char *str, Size *scanbuflen, yyscan_t *yyscannerp);
+extern void cube_scanner_finish(yyscan_t yyscanner);
 
 /* in cubeparse.y */
 extern int	cube_yyparse(NDBOX **result, Size scanbuflen,
-						 struct Node *escontext);
+						 struct Node *escontext,
+						 yyscan_t yyscanner);
diff --git a/contrib/cube/cubeparse.y b/contrib/cube/cubeparse.y
@@ -7,19 +7,11 @@
 #include "postgres.h"
 
 #include "cubedata.h"
+#include "cubeparse.h"	/* must be after cubedata.h for YYSTYPE and NDBOX */
 #include "nodes/miscnodes.h"
 #include "utils/float.h"
 #include "varatt.h"
 
-/* All grammar constructs return strings */
-#define YYSTYPE char *
-
-#include "cubeparse.h"
-
-/* silence -Wmissing-variable-declarations */
-extern int cube_yychar;
-extern int cube_yynerrs;
-
 /*
  * Bison doesn't allocate anything that needs to live across parser calls,
  * so we can easily have it use palloc instead of malloc.  This prevents
@@ -40,6 +32,9 @@ static bool write_point_as_box(int dim, char *str,
 %parse-param {NDBOX **result}
 %parse-param {Size scanbuflen}
 %parse-param {struct Node *escontext}
+%parse-param {yyscan_t yyscanner}
+%lex-param   {yyscan_t yyscanner}
+%pure-parser
 %expect 0
 %name-prefix="cube_yy"
 
@@ -75,6 +70,8 @@ box: O_BRACKET paren_list COMMA paren_list C_BRACKET
 
 		if (!write_box(dim, $2, $4, result, escontext))
 			YYABORT;
+
+		(void) yynerrs;	/* suppress compiler warning */
 	}
 
 	| paren_list COMMA paren_list
diff --git a/contrib/cube/cubescan.l b/contrib/cube/cubescan.l
@@ -6,13 +6,8 @@
 
 #include "postgres.h"
 
-/*
- * NB: include cubeparse.h only AFTER defining YYSTYPE (to match cubeparse.y)
- * and cubedata.h for NDBOX.
- */
 #include "cubedata.h"
-#define YYSTYPE char *
-#include "cubeparse.h"
+#include "cubeparse.h"	/* must be after cubedata.h for YYSTYPE and NDBOX */
 }
 
 %{
@@ -30,18 +25,19 @@ fprintf_to_ereport(const char *fmt, const char *msg)
 {
 	ereport(ERROR, (errmsg_internal("%s", msg)));
 }
-
-/* Handles to the buffer that the lexer uses internally */
-static YY_BUFFER_STATE scanbufhandle;
-static char *scanbuf;
 %}
 
+%option reentrant
+%option bison-bridge
 %option 8bit
 %option never-interactive
 %option nodefault
 %option noinput
 %option nounput
 %option noyywrap
+%option noyyalloc
+%option noyyrealloc
+%option noyyfree
 %option warn
 %option prefix="cube_yy"
 
@@ -55,14 +51,14 @@ NaN          [nN][aA][nN]
 
 %%
 
-{float}      cube_yylval = yytext; return CUBEFLOAT;
-{infinity}   cube_yylval = yytext; return CUBEFLOAT;
-{NaN}        cube_yylval = yytext; return CUBEFLOAT;
-\[           cube_yylval = "("; return O_BRACKET;
-\]           cube_yylval = ")"; return C_BRACKET;
-\(           cube_yylval = "("; return O_PAREN;
-\)           cube_yylval = ")"; return C_PAREN;
-\,           cube_yylval = ","; return COMMA;
+{float}      *yylval = yytext; return CUBEFLOAT;
+{infinity}   *yylval = yytext; return CUBEFLOAT;
+{NaN}        *yylval = yytext; return CUBEFLOAT;
+\[           *yylval = "("; return O_BRACKET;
+\]           *yylval = ")"; return C_BRACKET;
+\(           *yylval = "("; return O_PAREN;
+\)           *yylval = ")"; return C_PAREN;
+\,           *yylval = ","; return COMMA;
 [ \t\n\r\f\v]+ /* discard spaces */
 .            return yytext[0]; /* alert parser of the garbage */
 
@@ -74,8 +70,11 @@ NaN          [nN][aA][nN]
 void
 cube_yyerror(NDBOX **result, Size scanbuflen,
 			 struct Node *escontext,
+			 yyscan_t yyscanner,
 			 const char *message)
 {
+	struct yyguts_t * yyg = (struct yyguts_t *) yyscanner;	/* needed for yytext macro */
+
 	if (*yytext == YY_END_OF_BUFFER_CHAR)
 	{
 		errsave(escontext,
@@ -99,35 +98,53 @@ cube_yyerror(NDBOX **result, Size scanbuflen,
  * Called before any actual parsing is done
  */
 void
-cube_scanner_init(const char *str, Size *scanbuflen)
+cube_scanner_init(const char *str, Size *scanbuflen, yyscan_t *yyscannerp)
 {
 	Size		slen = strlen(str);
+	yyscan_t	yyscanner;
 
-	/*
-	 * Might be left over after ereport()
-	 */
-	if (YY_CURRENT_BUFFER)
-		yy_delete_buffer(YY_CURRENT_BUFFER);
+	if (yylex_init(yyscannerp) != 0)
+		elog(ERROR, "yylex_init() failed: %m");
 
-	/*
-	 * Make a scan buffer with special termination needed by flex.
-	 */
-	*scanbuflen = slen;
-	scanbuf = palloc(slen + 2);
-	memcpy(scanbuf, str, slen);
-	scanbuf[slen] = scanbuf[slen + 1] = YY_END_OF_BUFFER_CHAR;
-	scanbufhandle = yy_scan_buffer(scanbuf, slen + 2);
+	yyscanner = *yyscannerp;
 
-	BEGIN(INITIAL);
+	yy_scan_bytes(str, slen, yyscanner);
+	*scanbuflen = slen;
 }
 
 
 /*
  * Called after parsing is done to clean up after cube_scanner_init()
  */
 void
-cube_scanner_finish(void)
+cube_scanner_finish(yyscan_t yyscanner)
+{
+	yylex_destroy(yyscanner);
+}
+
+/*
+ * Interface functions to make flex use palloc() instead of malloc().
+ * It'd be better to make these static, but flex insists otherwise.
+ */
+
+void *
+yyalloc(yy_size_t size, yyscan_t yyscanner)
+{
+	return palloc(size);
+}
+
+void *
+yyrealloc(void *ptr, yy_size_t size, yyscan_t yyscanner)
+{
+	if (ptr)
+		return repalloc(ptr, size);
+	else
+		return palloc(size);
+}
+
+void
+yyfree(void *ptr, yyscan_t yyscanner)
 {
-	yy_delete_buffer(scanbufhandle);
-	pfree(scanbuf);
+	if (ptr)
+		pfree(ptr);
 }
