Clean up handling of %destructor for the end token (token 0).

Discussed starting at <http://lists.gnu.org/archive/html/bison-patches/2006-07/msg00019.html> and <http://lists.gnu.org/archive/html/help-bison/2006-07/msg00013.html>. Make the skeletons consistent in how they pop the end token and invoke its %destructor. * data/glr.c (yyrecoverSyntaxError, yyparse): Don't pop the start state, which has token number 0, since this would invoke the %destructor for the end token. * data/lalr1.cc (yy::parser::parse): Don't check for the final state until after shifting the end token, or else it won't be popped. * data/yacc.c (yyparse): Likewise. * data/glr.c (yyparse): Clear the lookahead after shifting it even when it's the end token. Upon termination, destroy an unshifted lookahead even when it's the end token. * data/lalr1.cc (yy::parser::parse): Likewise. * data/yacc.c (yyparse): Likewise. * src/reader.c (packgram): Don't check rule 0. This suppresses unused value warnings for the end token when the user gives the end token a %destructor. * tests/actions.at (Printers and Destructors): Test all the above.
2026-03-09 20:33:03 +00:00 · 2006-07-29 04:11:33 +00:00
parent 62a9592d3d
commit 868d2d9638
6 changed files with 101 additions and 33 deletions
--- a/29
+++ b/29
@@ -1,3 +1,32 @@
+2006-07-29  Joel E. Denny  <jdenny@ces.clemson.edu>
+
+	Clean up handling of %destructor for the end token (token 0).
+	Discussed starting at
+	<http://lists.gnu.org/archive/html/bison-patches/2006-07/msg00019.html>
+	and
+	<http://lists.gnu.org/archive/html/help-bison/2006-07/msg00013.html>.
+
+	Make the skeletons consistent in how they pop the end token and invoke
+	its %destructor.
+	* data/glr.c (yyrecoverSyntaxError, yyparse): Don't pop the start
+	state, which has token number 0, since this would invoke the
+	%destructor for the end token.
+	* data/lalr1.cc (yy::parser::parse): Don't check for the final state
+	until after shifting the end token, or else it won't be popped.
+	* data/yacc.c (yyparse): Likewise.
+
+	* data/glr.c (yyparse): Clear the lookahead after shifting it even when
+	it's the end token.  Upon termination, destroy an unshifted lookahead
+	even when it's the end token.
+	* data/lalr1.cc (yy::parser::parse): Likewise.
+	* data/yacc.c (yyparse): Likewise.
+
+	* src/reader.c (packgram): Don't check rule 0.  This suppresses unused
+	value warnings for the end token when the user gives the end token a
+	%destructor.
+
+	* tests/actions.at (Printers and Destructors): Test all the above.
+
 2006-07-24  Paul Eggert  <eggert@cs.ucla.edu>

 	Update to latest gnulib and gettext versions.
--- a/data/glr.c
+++ b/data/glr.c
@@ -2261,7 +2261,8 @@ yyrecoverSyntaxError (yyGLRStack* yystackp]b4_user_formals[)
 	    }
 	}
 ]b4_locations_if([[      yystackp->yyerror_range[1].yystate.yyloc = yys->yyloc;]])[
-      yydestroyGLRState ("Error: popping", yys]b4_user_args[);
+      if (yys->yypred != NULL)
+	yydestroyGLRState ("Error: popping", yys]b4_user_args[);
      yystackp->yytops.yystates[0] = yys->yypred;
      yystackp->yynextFree -= 1;
      yystackp->yyspaceLeft += 1;
@@ -2373,8 +2374,7 @@ m4_popdef([b4_at_dollar])])dnl
 	      if (yyisShiftAction (yyaction))
 		{
 		  YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);
-		  if (yychar != YYEOF)
-		    yychar = YYEMPTY;
+		  yychar = YYEMPTY;
 		  yyposn += 1;
 		  yyglrShift (&yystack, 0, yyaction, yyposn, &yylval, &yylloc);
 		  if (0 < yystack.yyerrState)
@@ -2490,7 +2490,7 @@ m4_popdef([b4_at_dollar])])dnl
  goto yyreturn;

 yyreturn:
-  if (yychar != YYEOF && yychar != YYEMPTY)
+  if (yychar != YYEMPTY)
    yydestruct ("Cleanup: discarding lookahead",
 		YYTRANSLATE (yychar),
 		&yylval]b4_locations_if([, &yylloc])[]b4_user_args[);
@@ -2512,7 +2512,8 @@ m4_popdef([b4_at_dollar])])dnl
 		  {
 		    yyGLRState *yys = yystates[yyk];
 ]b4_locations_if([[		    yystack.yyerror_range[1].yystate.yyloc = yys->yyloc;]]
-)[		    yydestroyGLRState ("Cleanup: popping", yys]b4_user_args[);
+)[		    if (yys->yypred != NULL)
+		      yydestroyGLRState ("Cleanup: popping", yys]b4_user_args[);
 		    yystates[yyk] = yys->yypred;
 		    yystack.yynextFree -= 1;
 		    yystack.yyspaceLeft += 1;
--- a/data/lalr1.cc
+++ b/data/lalr1.cc
@@ -567,6 +567,11 @@ m4_popdef([b4_at_dollar])])dnl
  yynewstate:
    yystate_stack_.push (yystate);
    YYCDEBUG << "Entering state " << yystate << std::endl;
+
+    /* Accept?  */
+    if (yystate == yyfinal_)
+      goto yyacceptlab;
+
    goto yybackup;

    /* Backup.  */
@@ -616,16 +621,11 @@ m4_ifdef([b4_lex_param], [, ]b4_lex_param))[;
 	goto yyreduce;
      }

-    /* Accept?  */
-    if (yyn == yyfinal_)
-      goto yyacceptlab;
-
    /* Shift the lookahead token.  */
    YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);

-    /* Discard the token being shifted unless it is eof.  */
-    if (yychar != yyeof_)
-      yychar = yyempty_;
+    /* Discard the token being shifted.  */
+    yychar = yyempty_;

    yysemantic_stack_.push (yylval);
    yylocation_stack_.push (yylloc);
@@ -780,9 +780,6 @@ b4_error_verbose_if([, yytoken])[));
 	YY_STACK_PRINT ();
      }

-    if (yyn == yyfinal_)
-      goto yyacceptlab;
-
    yyerror_range[1] = yylloc;
    // Using YYLLOC is tempting, but would change the location of
    // the lookahead.  YYLOC is available though.
@@ -808,7 +805,7 @@ b4_error_verbose_if([, yytoken])[));
    goto yyreturn;

  yyreturn:
-    if (yychar != yyeof_ && yychar != yyempty_)
+    if (yychar != yyempty_)
      yydestruct_ ("Cleanup: discarding lookahead", yytoken, &yylval, &yylloc);

    /* Do not reclaim the symbols of the rule which action triggered
--- a/data/yacc.c
+++ b/data/yacc.c
@@ -1164,6 +1164,9 @@ m4_ifdef([b4_at_dollar_used], [[  yylsp[0] = yylloc;

  YYDPRINTF ((stderr, "Entering state %d\n", yystate));

+  if (yystate == YYFINAL)
+    YYACCEPT;
+
  goto yybackup;

 /*-----------.
@@ -1213,9 +1216,6 @@ yybackup:
      goto yyreduce;
    }

-  if (yyn == YYFINAL)
-    YYACCEPT;
-
  /* Count tokens shifted since error; after three, turn off error
     status.  */
  if (yyerrstatus)
@@ -1224,9 +1224,8 @@ yybackup:
  /* Shift the lookahead token.  */
  YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);

-  /* Discard the shifted token unless it is eof.  */
-  if (yychar != YYEOF)
-    yychar = YYEMPTY;
+  /* Discard the shifted token.  */
+  yychar = YYEMPTY;

  yystate = yyn;
  *++yyvsp = yylval;
@@ -1418,9 +1417,6 @@ yyerrlab1:
      YY_STACK_PRINT (yyss, yyssp);
    }

-  if (yyn == YYFINAL)
-    YYACCEPT;
-
  *++yyvsp = yylval;
 ]b4_locations_if([[
  yyerror_range[1] = yylloc;
@@ -1461,7 +1457,7 @@ yyexhaustedlab:
 #endif

 yyreturn:
-  if (yychar != YYEOF && yychar != YYEMPTY)
+  if (yychar != YYEMPTY)
     yydestruct ("Cleanup: discarding lookahead",
 		 yytoken, &yylval]b4_locations_if([, &yylloc])[]b4_user_args[);
  /* Do not reclaim the symbols of the rule which action triggered
--- a/src/reader.c
+++ b/src/reader.c
@@ -488,7 +488,11 @@ packgram (void)
 	 rule.  Thus, the midrule actions have already been scanned in order to
 	 set `used' flags for this rule's rhs, so grammar_rule_check will work
 	 properly.  */
-      grammar_rule_check (p);
+      /* Don't check the generated rule 0.  It has no action, so some rhs
+	 symbols may appear unused, but the parsing algorithm ensures that
+	 %destructor's are invoked appropriately.  */
+      if (p != grammar)
+	grammar_rule_check (p);

      for (p = p->next; p && p->sym; p = p->next)
 	{
--- a/tests/actions.at
+++ b/tests/actions.at
@@ -197,8 +197,9 @@ AT_LALR1_CC_IF([typedef yy::location YYLTYPE;
 ]AT_LALR1_CC_IF([], [static void yyerror (const char *msg);])
 [}

-]m4_ifval([$6], [%type <ival> '(' 'x' 'y' ')' ';' thing line input])[
+]m4_ifval([$6], [%type <ival> '(' 'x' 'y' ')' ';' thing line input END])[

+/* FIXME: This %printer isn't actually tested.  */
 %printer
  {
    ]AT_LALR1_CC_IF([debug_stream () << $$;],
@@ -226,6 +227,11 @@ AT_LALR1_CC_IF([typedef yy::location YYLTYPE;
  { printf ("Freeing token 'y' (%d@%d-%d)\n", $$, RANGE (@$)); }
  'y'

+%token END 0
+%destructor
+  { printf ("Freeing token END (%d@%d-%d)\n", $$, RANGE (@$)); }
+  END
+
 %%
 /*
   This grammar is made to exercise error recovery.
@@ -241,7 +247,7 @@ input:
      printf ("input (%d@%d-%d): /* Nothing */\n", $$, RANGE (@$));
    }
 | line input /* Right recursive to load the stack so that popping at
-		EOF can	be exercised.  */
+		END can	be exercised.  */
    {
      $$ = 2;
      printf ("input (%d@%d-%d): line (%d@%d-%d) input (%d@%d-%d)\n",
@@ -308,7 +314,7 @@ yylex (]AT_LEX_FORMALS[)
  if (source[c])
    printf ("sending: '%c'", source[c]);
  else
-    printf ("sending: EOF");
+    printf ("sending: END");
  printf (" (%d@%d-%d)\n", c, RANGE (]AT_LOC[));
  return source[c];
 }
@@ -372,9 +378,10 @@ sending: 'x' (1@10-19)
 thing (1@10-19): 'x' (1@10-19)
 sending: ')' (2@20-29)
 line (0@0-29): '(' (0@0-9) thing (1@10-19) ')' (2@20-29)
-sending: EOF (3@30-39)
+sending: END (3@30-39)
 input (0@29-29): /* Nothing */
 input (2@0-29): line (0@0-29) input (0@29-29)
+Freeing token END (3@30-39)
 Freeing nterm input (2@0-29)
 Successful parse.
 ]])
@@ -391,9 +398,10 @@ sending: 'y' (1@10-19)
 Freeing token 'y' (1@10-19)
 sending: ')' (2@20-29)
 line (-1@0-29): '(' (0@0-9) error (@10-19) ')' (2@20-29)
-sending: EOF (3@30-39)
+sending: END (3@30-39)
 input (0@29-29): /* Nothing */
 input (2@0-29): line (-1@0-29) input (0@29-29)
+Freeing token END (3@30-39)
 Freeing nterm input (2@0-29)
 Successful parse.
 ]])
@@ -445,12 +453,45 @@ input (0@129-129): /* Nothing */
 input (2@100-129): line (10@100-129) input (0@129-129)
 input (2@70-129): line (7@70-99) input (2@100-129)
 input (2@0-129): line (-1@0-69) input (2@70-129)
-130-139: syntax error, unexpected 'y', expecting $end
+130-139: syntax error, unexpected 'y', expecting END
 Freeing nterm input (2@0-129)
 Freeing token 'y' (13@130-139)
 Parsing FAILED.
 ]])

+
+# Syntax error caught by the parser where lookahead = END
+# --------------------------------------------------------
+# Load the stack and provoke an error that cannot be caught by the
+# grammar, to check that the stack is cleared.  And make sure the
+# lookahead is freed.
+#
+#     '(', 'x', ')',
+#     '(', 'x', ')',
+#     'x'
+AT_PARSER_CHECK([./input '(x)(x)x'], 1,
+[[sending: '(' (0@0-9)
+sending: 'x' (1@10-19)
+thing (1@10-19): 'x' (1@10-19)
+sending: ')' (2@20-29)
+line (0@0-29): '(' (0@0-9) thing (1@10-19) ')' (2@20-29)
+sending: '(' (3@30-39)
+sending: 'x' (4@40-49)
+thing (4@40-49): 'x' (4@40-49)
+sending: ')' (5@50-59)
+line (3@30-59): '(' (3@30-39) thing (4@40-49) ')' (5@50-59)
+sending: 'x' (6@60-69)
+thing (6@60-69): 'x' (6@60-69)
+sending: END (7@70-79)
+70-79: syntax error, unexpected END, expecting 'x'
+Freeing nterm thing (6@60-69)
+Freeing nterm line (3@30-59)
+Freeing nterm line (0@0-29)
+Freeing token END (7@70-79)
+Parsing FAILED.
+]])
+
+
 # Check destruction upon stack overflow
 # -------------------------------------
 # Upon stack overflow, all symbols on the stack should be destroyed.