seg: pure parser and reentrant scanner

petere · petere · commit 1f0de66ea2a5 · 2024-12-18T08:47:53.000+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. 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/seg/seg.c b/contrib/seg/seg.c
@@ -105,13 +105,14 @@ seg_in(PG_FUNCTION_ARGS)
 {
 	char	   *str = PG_GETARG_CSTRING(0);
 	SEG		   *result = palloc(sizeof(SEG));
+	yyscan_t	scanner;
 
-	seg_scanner_init(str);
+	seg_scanner_init(str, &scanner);
 
-	if (seg_yyparse(result, fcinfo->context) != 0)
-		seg_yyerror(result, fcinfo->context, "bogus input");
+	if (seg_yyparse(result, fcinfo->context, scanner) != 0)
+		seg_yyerror(result, fcinfo->context, scanner, "bogus input");
 
-	seg_scanner_finish();
+	seg_scanner_finish(scanner);
 
 	PG_RETURN_POINTER(result);
 }
diff --git a/contrib/seg/segdata.h b/contrib/seg/segdata.h
@@ -14,12 +14,17 @@ typedef struct SEG
 /* in seg.c */
 extern int	significant_digits(const char *s);
 
+/* for segscan.l and segparse.y */
+union YYSTYPE;
+typedef void *yyscan_t;
+
 /* in segscan.l */
-extern int	seg_yylex(void);
+extern int	seg_yylex(union YYSTYPE *yylval_param, yyscan_t yyscanner);
 extern void seg_yyerror(SEG *result, struct Node *escontext,
+						yyscan_t yyscanner,
 						const char *message);
-extern void seg_scanner_init(const char *str);
-extern void seg_scanner_finish(void);
+extern void seg_scanner_init(const char *str, yyscan_t *yyscannerp);
+extern void seg_scanner_finish(yyscan_t yyscanner);
 
 /* in segparse.y */
-extern int	seg_yyparse(SEG *result, struct Node *escontext);
+extern int	seg_yyparse(SEG *result, struct Node *escontext, yyscan_t yyscanner);
diff --git a/contrib/seg/segparse.y b/contrib/seg/segparse.y
@@ -14,10 +14,6 @@
 #include "segdata.h"
 #include "segparse.h"
 
-/* silence -Wmissing-variable-declarations */
-extern int seg_yychar;
-extern int seg_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
@@ -35,6 +31,9 @@ static int sig_digits(const char *value);
 /* BISON Declarations */
 %parse-param {SEG *result}
 %parse-param {struct Node *escontext}
+%parse-param {yyscan_t yyscanner}
+%lex-param   {yyscan_t yyscanner}
+%pure-parser
 %expect 0
 %name-prefix="seg_yy"
 
@@ -72,6 +71,8 @@ range: boundary PLUMIN deviation
 		result->u_sigd = Max(sig_digits(strbuf), Max($1.sigd, $3.sigd));
 		result->l_ext = '\0';
 		result->u_ext = '\0';
+
+		(void) yynerrs; /* suppress compiler warning */
 	}
 
 	| boundary RANGE boundary
diff --git a/contrib/seg/segscan.l b/contrib/seg/segscan.l
@@ -6,12 +6,8 @@
 
 #include "nodes/miscnodes.h"
 
-/*
- * NB: include segparse.h only AFTER including segdata.h, because segdata.h
- * contains the definition for SEG.
- */
 #include "segdata.h"
-#include "segparse.h"
+#include "segparse.h"	/* must be after segdata.h for SEG */
 }
 
 %{
@@ -29,18 +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="seg_yy"
 
@@ -53,12 +50,12 @@ float        ({integer}|{real})([eE]{integer})?
 
 %%
 
-{range}      seg_yylval.text = yytext; return RANGE;
-{plumin}     seg_yylval.text = yytext; return PLUMIN;
-{float}      seg_yylval.text = yytext; return SEGFLOAT;
-\<           seg_yylval.text = "<"; return EXTENSION;
-\>           seg_yylval.text = ">"; return EXTENSION;
-\~           seg_yylval.text = "~"; return EXTENSION;
+{range}      yylval->text = yytext; return RANGE;
+{plumin}     yylval->text = yytext; return PLUMIN;
+{float}      yylval->text = yytext; return SEGFLOAT;
+\<           yylval->text = "<"; return EXTENSION;
+\>           yylval->text = ">"; return EXTENSION;
+\~           yylval->text = "~"; return EXTENSION;
 [ \t\n\r\f\v]+ /* discard spaces */
 .            return yytext[0]; /* alert parser of the garbage */
 
@@ -67,8 +64,10 @@ float        ({integer}|{real})([eE]{integer})?
 /* LCOV_EXCL_STOP */
 
 void
-seg_yyerror(SEG *result, struct Node *escontext, const char *message)
+seg_yyerror(SEG *result, struct Node *escontext, yyscan_t yyscanner, const char *message)
 {
+	struct yyguts_t * yyg = (struct yyguts_t *) yyscanner;	/* needed for yytext macro */
+
 	/* if we already reported an error, don't overwrite it */
 	if (SOFT_ERROR_OCCURRED(escontext))
 		return;
@@ -96,34 +95,51 @@ seg_yyerror(SEG *result, struct Node *escontext, const char *message)
  * Called before any actual parsing is done
  */
 void
-seg_scanner_init(const char *str)
+seg_scanner_init(const char *str, yyscan_t *yyscannerp)
 {
-	Size	slen = strlen(str);
-
-	/*
-	 * Might be left over after ereport()
-	 */
-	if (YY_CURRENT_BUFFER)
-		yy_delete_buffer(YY_CURRENT_BUFFER);
-
-	/*
-	 * Make a scan buffer with special termination needed by flex.
-	 */
-	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);
-
-	BEGIN(INITIAL);
+	yyscan_t yyscanner;
+
+	if (yylex_init(yyscannerp) != 0)
+		elog(ERROR, "yylex_init() failed: %m");
+
+	yyscanner = *yyscannerp;
+
+	yy_scan_string(str, yyscanner);
 }
 
 
 /*
  * Called after parsing is done to clean up after seg_scanner_init()
  */
 void
-seg_scanner_finish(void)
+seg_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);
 }
