Don't allow an undeclared string literal, but allow a string literal to

[bison.git] / tests / regression.at

diff --git a/tests/regression.at b/tests/regression.at
index bbd007615a189285efbbb4a34587cef3c5ec8033..1c5ccbbf370766306713828ff23c5d6d2f1ee7dd 100644 (file)
--- a/tests/regression.at
+++ b/tests/regression.at
@@ -49,6 +49,33 @@ AT_CLEANUP
 
 
 
+## ----------------- ##
+## YYSTYPE typedef.  ##
+## ----------------- ##
+
+AT_SETUP([YYSTYPE typedef])
+
+AT_DATA_GRAMMAR([input.y],
+[[%{
+void yyerror (char const *);
+int yylex (void);
+typedef union { char const *val; } YYSTYPE;
+%}
+
+%type <val> program
+
+%%
+
+program: { $$ = ""; };
+]])
+
+AT_CHECK([bison -o input.c input.y])
+AT_COMPILE([input.o], [-c input.c])
+
+AT_CLEANUP
+
+
+
 ## ------------------------------------- ##
 ## Early token definitions with --yacc.  ##
 ## ------------------------------------- ##
@@ -63,15 +90,17 @@ AT_DATA_GRAMMAR([input.y],
 [[%{
 void yyerror (const char *s);
 int yylex (void);
-#ifndef MY_TOKEN
-# error "MY_TOKEN not defined."
-#endif
 %}
 
 %union
 {
   int val;
 };
+%{
+#ifndef MY_TOKEN
+# error "MY_TOKEN not defined."
+#endif
+%}
 %token MY_TOKEN
 %%
 exp: MY_TOKEN;
@@ -101,6 +130,13 @@ AT_DATA_GRAMMAR([input.y],
 void yyerror (const char *s);
 int yylex (void);
 void print_my_token (void);
+%}
+
+%union
+{
+  int val;
+};
+%{
 void
 print_my_token (void)
 {
@@ -108,11 +144,6 @@ print_my_token (void)
   printf ("%d\n", my_token);
 }
 %}
-
-%union
-{
-  int val;
-};
 %token MY_TOKEN
 %%
 exp: MY_TOKEN;
@@ -367,6 +398,7 @@ input.y:5.1-17: invalid directive: `%a-does-not-exist'
 input.y:6.1: invalid character: `%'
 input.y:6.2: invalid character: `-'
 input.y:7.1-8.0: missing `%}' at end of file
+input.y:7.1-8.0: syntax error, unexpected %{...%}
 ]])
 
 AT_CLEANUP
@@ -457,7 +489,9 @@ AT_DATA_GRAMMAR([input.y],
 void yyerror (const char *s);
 int yylex (void);
 %}
-[%%
+[%token QUOTES "\""
+%token TICK "'"
+%%
 exp:
   '\'' "\'"
 | '\"' "\""
@@ -668,6 +702,10 @@ statement:  struct_stat;
 struct_stat:  /* empty. */ | if else;
 if: "if" "const" "then" statement;
 else: "else" statement;
+%token IF "if";
+%token CONST "const";
+%token THEN "then";
+%token ELSE "else";
 %%
 ]])
 
@@ -1000,3 +1038,124 @@ AT_CLEANUP
 AT_CHECK_EXPECT2()
 AT_CHECK_EXPECT2([%glr-parser])
 AT_CHECK_EXPECT2([%skeleton "lalr1.cc"])
+
+
+
+## --------------------------------------------- ##
+## Braced code in declaration in rules section.  ##
+## --------------------------------------------- ##
+
+AT_SETUP([Braced code in declaration in rules section])
+
+# Bison once mistook braced code in a declaration in the rules section to be a
+# rule action.
+
+AT_DATA_GRAMMAR([input.y],
+[[%{
+#include <stdio.h>
+static void yyerror (char const *msg);
+static int yylex (void);
+%}
+
+%error-verbose
+
+%%
+
+start:
+  {
+    printf ("Bison would once convert this action to a midrule because of the"
+           " subsequent braced code.\n");
+  }
+  ;
+
+%destructor { fprintf (stderr, "DESTRUCTOR\n"); } 'a';
+%printer { fprintf (yyoutput, "PRINTER"); } 'a';
+
+%%
+
+static void
+yyerror (char const *msg)
+{
+  fprintf (stderr, "%s\n", msg);
+}
+
+static int
+yylex (void)
+{
+  return 'a';
+}
+
+int
+main (void)
+{
+  yydebug = 1;
+  return !yyparse ();
+}
+]])
+
+AT_CHECK([bison -t -o input.c input.y])
+AT_COMPILE([input])
+AT_PARSER_CHECK([./input], 0,
+[[Bison would once convert this action to a midrule because of the subsequent braced code.
+]],
+[[Starting parse
+Entering state 0
+Reducing stack by rule 1 (line 22):
+-> $$ = nterm start ()
+Stack now 0
+Entering state 1
+Reading a token: Next token is token 'a' (PRINTER)
+syntax error, unexpected 'a', expecting $end
+Error: popping nterm start ()
+Stack now 0
+Cleanup: discarding lookahead token 'a' (PRINTER)
+DESTRUCTOR
+Stack now 0
+]])
+
+AT_CLEANUP
+
+
+
+## --------------------------------- ##
+## String alias declared after use.  ##
+## --------------------------------- ##
+
+AT_SETUP([String alias declared after use])
+
+# Bison once incorrectly asserted that the symbol number for either a token or
+# its alias was the highest symbol number so far at the point of the alias
+# declaration.  That was true unless the declaration appeared after their first
+# uses.
+
+AT_DATA([input.y],
+[[%%
+start: 'a' "A" 'b';
+%token 'a' "A";
+]])
+
+AT_CHECK([bison -t -o input.c input.y])
+
+AT_CLEANUP
+
+
+
+## --------------------------- ##
+## Undeclared string literal.  ##
+## --------------------------- ##
+
+AT_SETUP([Undeclared string literal])
+
+# Bison once allowed a string literal to be used in the grammar without any
+# declaration assigning it as an alias of another token.
+
+AT_DATA([input.y],
+[[%%
+start: "abc";
+]])
+
+AT_CHECK([bison -t -o input.c input.y], [1], [],
+[[input.y:2.8-12: "abc" undeclared
+]])
+
+AT_CLEANUP