X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/cff03fb2b92a05f61c142783dd3b2e0103782869..dcd39f1d4ab0d2efa467406682175643c7c0ca1d:/tests/conflicts.at

diff --git a/tests/conflicts.at b/tests/conflicts.at
index 8032256e..f455d1f5 100644
--- a/tests/conflicts.at
+++ b/tests/conflicts.at
@@ -1,6 +1,7 @@
 # Exercising Bison on conflicts.                         -*- Autotest -*-
 
-# Copyright (C) 2002, 2003, 2004, 2005, 2007 Free Software Foundation, Inc.
+# Copyright (C) 2002, 2003, 2004, 2005, 2007, 2009, 2010 Free
+# Software Foundation, Inc.
 
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -36,7 +37,7 @@ exp: e 'e';
 e: 'e' | /* Nothing. */;
 ]])
 
-AT_CHECK([bison -o input.c input.y], 0, [],
+AT_BISON_CHECK([-o input.c input.y], 0, [],
 [[input.y:4.9: warning: rule useless in parser due to conflicts: e: /* empty */
 ]])
 
@@ -94,26 +95,338 @@ main (int argc, const char *argv[])
 ]])
 
 # Specify the output files to avoid problems on different file systems.
-AT_CHECK([bison -o input.c input.y])
+AT_BISON_CHECK([-o input.c input.y])
 AT_COMPILE([input])
 
 AT_PARSER_CHECK([./input '0<0'])
-# FIXME: This is an actual bug, but a new one, in the sense that
-# no one has ever spotted it!  The messages are *wrong*: there should
-# be nothing there, it should be expected eof.
 AT_PARSER_CHECK([./input '0<0<0'], [1], [],
-         [syntax error, unexpected '<', expecting '<' or '>'
+         [syntax error, unexpected '<'
 ])
 
 AT_PARSER_CHECK([./input '0>0'])
 AT_PARSER_CHECK([./input '0>0>0'], [1], [],
-         [syntax error, unexpected '>', expecting '<' or '>'
+         [syntax error, unexpected '>'
 ])
 
 AT_PARSER_CHECK([./input '0<0>0'], [1], [],
-         [syntax error, unexpected '>', expecting '<' or '>'
+         [syntax error, unexpected '>'
 ])
 
+# We must disable default reductions in inconsistent states in order to
+# have an explicit list of all expected tokens.  (However, unless we use
+# canonical LR, lookahead sets are merged for different left contexts,
+# so it is still possible to have extra incorrect tokens in the expected
+# list.  That just doesn't happen to be a problem for this test case.)
+
+AT_BISON_CHECK([-Dlr.default-reductions=consistent -o input.c input.y])
+AT_COMPILE([input])
+
+AT_PARSER_CHECK([./input '0<0'])
+AT_PARSER_CHECK([./input '0<0<0'], [1], [],
+         [syntax error, unexpected '<', expecting $end
+])
+
+AT_PARSER_CHECK([./input '0>0'])
+AT_PARSER_CHECK([./input '0>0>0'], [1], [],
+         [syntax error, unexpected '>', expecting $end
+])
+
+AT_PARSER_CHECK([./input '0<0>0'], [1], [],
+         [syntax error, unexpected '>', expecting $end
+])
+
+AT_CLEANUP
+
+
+
+## -------------------------------------- ##
+## %error-verbose and consistent errors.  ##
+## -------------------------------------- ##
+
+AT_SETUP([[%error-verbose and consistent errors]])
+
+m4_pushdef([AT_CONSISTENT_ERRORS_CHECK], [
+
+AT_BISON_OPTION_PUSHDEFS([$1])
+
+m4_pushdef([AT_YYLEX_PROTOTYPE],
+[AT_SKEL_CC_IF([[int yylex (yy::parser::semantic_type *lvalp)]],
+               [[int yylex (YYSTYPE *lvalp)]])])
+
+AT_SKEL_JAVA_IF([AT_DATA], [AT_DATA_GRAMMAR])([input.y],
+[AT_SKEL_JAVA_IF([[
+
+%code imports {
+  import java.io.IOException;
+}]], [[
+
+%code {]AT_SKEL_CC_IF([[
+  #include <cassert>
+  #include <string>]], [[
+  #include <assert.h>
+  #include <stdio.h>
+  void yyerror (char const *msg);]])[
+  ]AT_YYLEX_PROTOTYPE[;
+  #define USE(Var)
+}
+
+]AT_SKEL_CC_IF([[%defines]], [[%define api.pure]])])[
+
+]$1[
+
+%error-verbose
+
+%%
+
+]$2[
+
+]AT_SKEL_JAVA_IF([[%code lexer {]], [[%%]])[
+
+/*--------.
+| yylex.  |
+`--------*/]AT_SKEL_JAVA_IF([[
+
+public String input = "]$3[";
+public int index = 0;
+public int yylex ()
+{
+  if (index < input.length ())
+    return input.charAt (index++);
+  else
+    return 0;
+}
+public Object getLVal ()
+{
+  return new Integer(1);
+}]], [[
+
+]AT_YYLEX_PROTOTYPE[
+{
+  static char const *input = "]$3[";
+  *lvalp = 1;
+  return *input++;
+}]])[
+
+/*----------.
+| yyerror.  |
+`----------*/]AT_SKEL_JAVA_IF([[
+
+public void yyerror (String msg)
+{
+  System.err.println (msg);
+}
+
+};
+
+%%]], [AT_SKEL_CC_IF([[
+
+void
+yy::parser::error (const yy::location &, std::string const &msg)
+{
+  std::cerr << msg << std::endl;
+}]], [[
+
+void
+yyerror (char const *msg)
+{
+  fprintf (stderr, "%s\n", msg);
+}]])])[
+
+/*-------.
+| main.  |
+`-------*/]AT_SKEL_JAVA_IF([[
+
+class input
+{
+  public static void main (String args[]) throws IOException
+  {
+    YYParser p = new YYParser ();
+    p.parse ();
+  }
+}]], [AT_SKEL_CC_IF([[
+
+int
+main (void)
+{
+  yy::parser parser;
+  return parser.parse ();
+}]], [[
+
+int
+main (void)
+{
+  return yyparse ();
+}]])])[
+]])
+
+AT_FULL_COMPILE([[input]])
+
+m4_pushdef([AT_EXPECTING], [m4_if($5, [ab], [[, expecting 'a' or 'b']],
+                                  $5, [a],  [[, expecting 'a']],
+                                  $5, [b],  [[, expecting 'b']])])
+
+AT_SKEL_JAVA_IF([AT_JAVA_PARSER_CHECK([[input]], [[0]]],
+                [AT_PARSER_CHECK([[./input]], [[1]]]),
+[[]],
+[[syntax error, unexpected ]$4[]AT_EXPECTING[
+]])
+
+m4_popdef([AT_EXPECTING])
+m4_popdef([AT_YYLEX_PROTOTYPE])
+AT_BISON_OPTION_POPDEFS
+
+])
+
+m4_pushdef([AT_PREVIOUS_STATE_GRAMMAR],
+[[%nonassoc 'a';
+
+start: consistent-error-on-a-a 'a' ;
+
+consistent-error-on-a-a:
+    'a' default-reduction
+  | 'a' default-reduction 'a'
+  | 'a' shift
+  ;
+
+default-reduction: /*empty*/ ;
+shift: 'b' ;
+
+// Provide another context in which all rules are useful so that this
+// test case looks a little more realistic.
+start: 'b' consistent-error-on-a-a 'c' ;
+]])
+
+m4_pushdef([AT_PREVIOUS_STATE_INPUT], [[a]])
+
+# Unfortunately, no expected tokens are reported even though 'b' can be
+# accepted.  Nevertheless, the main point of this test is to make sure
+# that at least the unexpected token is reported.  In a previous version
+# of Bison, it wasn't reported because the error is detected in a
+# consistent state with an error action, and that case always triggered
+# the simple "syntax error" message.
+#
+# The point isn't to test IELR here, but state merging happens to
+# complicate this example.
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type ielr]],
+                           [AT_PREVIOUS_STATE_GRAMMAR],
+                           [AT_PREVIOUS_STATE_INPUT],
+                           [[$end]], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type ielr
+                             %glr-parser]],
+                           [AT_PREVIOUS_STATE_GRAMMAR],
+                           [AT_PREVIOUS_STATE_INPUT],
+                           [[$end]], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type ielr
+                             %language "c++"]],
+                           [AT_PREVIOUS_STATE_GRAMMAR],
+                           [AT_PREVIOUS_STATE_INPUT],
+                           [[$end]], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type ielr
+                             %language "java"]],
+                           [AT_PREVIOUS_STATE_GRAMMAR],
+                           [AT_PREVIOUS_STATE_INPUT],
+                           [[end of input]], [[none]])
+
+# Even canonical LR doesn't foresee the error for 'a'!
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type ielr
+                             %define lr.default-reductions consistent]],
+                           [AT_PREVIOUS_STATE_GRAMMAR],
+                           [AT_PREVIOUS_STATE_INPUT],
+                           [[$end]], [[ab]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type ielr
+                             %define lr.default-reductions accepting]],
+                           [AT_PREVIOUS_STATE_GRAMMAR],
+                           [AT_PREVIOUS_STATE_INPUT],
+                           [[$end]], [[ab]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type canonical-lr]],
+                           [AT_PREVIOUS_STATE_GRAMMAR],
+                           [AT_PREVIOUS_STATE_INPUT],
+                           [[$end]], [[ab]])
+
+m4_popdef([AT_PREVIOUS_STATE_GRAMMAR])
+m4_popdef([AT_PREVIOUS_STATE_INPUT])
+
+m4_pushdef([AT_USER_ACTION_GRAMMAR],
+[[%nonassoc 'a';
+
+// If $$ = 0 here, then we know that the 'a' destructor is being invoked
+// incorrectly for the 'b' set in the semantic action below.  All 'a'
+// tokens are returned by yylex, which sets $$ = 1.
+%destructor {
+  if (!$$)
+    fprintf (stderr, "Wrong destructor.\n");
+} 'a';
+
+// Rather than depend on an inconsistent state to induce reading a
+// lookahead as in the previous grammar, just assign the lookahead in a
+// semantic action.  That lookahead isn't needed before either error
+// action is encountered.  In a previous version of Bison, this was a
+// problem as it meant yychar was not translated into yytoken before
+// either error action.  The second error action thus invoked a
+// destructor that it selected according to the incorrect yytoken.  The
+// first error action would have reported an incorrect unexpected token
+// except that, due to the bug described in the previous grammar, the
+// unexpected token was not reported at all.
+start: error-reduce consistent-error 'a' { USE ($][3); } ;
+
+error-reduce:
+  'a' 'a' consistent-reduction consistent-error 'a'
+  { USE (($][1, $][2, $][5)); }
+| 'a' error
+  { USE ($][1); }
+;
+
+consistent-reduction: /*empty*/ {
+  assert (yychar == ]AT_SKEL_CC_IF([[yyempty_]], [[YYEMPTY]])[);
+  yylval = 0;
+  yychar = 'b';
+} ;
+
+consistent-error:
+  'a' { USE ($][1); }
+| /*empty*/ %prec 'a'
+;
+
+// Provide another context in which all rules are useful so that this
+// test case looks a little more realistic.
+start: 'b' consistent-error 'b' ;
+]])
+m4_pushdef([AT_USER_ACTION_INPUT], [[aa]])
+
+AT_CONSISTENT_ERRORS_CHECK([[]],
+                           [AT_USER_ACTION_GRAMMAR],
+                           [AT_USER_ACTION_INPUT],
+                           [['b']], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%glr-parser]],
+                           [AT_USER_ACTION_GRAMMAR],
+                           [AT_USER_ACTION_INPUT],
+                           [['b']], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%language "c++"]],
+                           [AT_USER_ACTION_GRAMMAR],
+                           [AT_USER_ACTION_INPUT],
+                           [['b']], [[none]])
+# No Java test because yychar cannot be manipulated by users.
+
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.default-reductions consistent]],
+                           [AT_USER_ACTION_GRAMMAR],
+                           [AT_USER_ACTION_INPUT],
+                           [['b']], [[none]])
+
+# Canonical LR doesn't foresee the error for 'a'!
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.default-reductions accepting]],
+                           [AT_USER_ACTION_GRAMMAR],
+                           [AT_USER_ACTION_INPUT],
+                           [[$end]], [[a]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type canonical-lr]],
+                           [AT_USER_ACTION_GRAMMAR],
+                           [AT_USER_ACTION_INPUT],
+                           [[$end]], [[a]])
+
+m4_popdef([AT_USER_ACTION_GRAMMAR])
+m4_popdef([AT_USER_ACTION_INPUT])
+
+m4_popdef([AT_CONSISTENT_ERRORS_CHECK])
+
 AT_CLEANUP
 
 
@@ -132,7 +445,7 @@ AT_DATA([input.y],
 exp: exp OP exp | NUM;
 ]])
 
-AT_CHECK([bison -o input.c --report=all input.y], 0, [],
+AT_BISON_CHECK([-o input.c --report=all input.y], 0, [],
 [input.y: conflicts: 1 shift/reduce
 ])
 
@@ -240,7 +553,7 @@ AT_DATA([input.y],
 exp: exp OP exp | NUM;
 ]])
 
-AT_CHECK([bison -o input.c --report=all input.y])
+AT_BISON_CHECK([-o input.c --report=all input.y])
 
 # Check the contents of the report.
 AT_CHECK([cat input.output], [],
@@ -362,7 +675,7 @@ id : '0';
 %%
 ]])
 
-AT_CHECK([bison -o input.c --report=all input.y], 0, [],
+AT_BISON_CHECK([-o input.c --report=all input.y], 0, [],
 [[input.y: conflicts: 1 reduce/reduce
 input.y:4.6-8: warning: rule useless in parser due to conflicts: id: '0'
 ]])
@@ -479,7 +792,7 @@ AT_DATA([input.y],
 exp: exp OP exp | NUM;
 ]])
 
-AT_CHECK([bison -o input.c input.y], 1, [],
+AT_BISON_CHECK([-o input.c input.y], 1, [],
 [input.y: conflicts: 1 shift/reduce
 input.y: expected 0 shift/reduce conflicts
 ])
@@ -499,7 +812,7 @@ AT_DATA([input.y],
 exp: exp OP exp | NUM;
 ]])
 
-AT_CHECK([bison -o input.c input.y])
+AT_BISON_CHECK([-o input.c input.y])
 AT_CLEANUP
 
 
@@ -516,16 +829,16 @@ AT_DATA([input.y],
 exp: exp OP exp | NUM;
 ]])
 
-AT_CHECK([bison -o input.c input.y], 1, [],
+AT_BISON_CHECK([-o input.c input.y], 1, [],
 [input.y: conflicts: 1 shift/reduce
 input.y: expected 2 shift/reduce conflicts
 ])
 AT_CLEANUP
 
 
-## ------------------------------ ##
-## %expect with reduce conflicts  ##
-## ------------------------------ ##
+## ------------------------------- ##
+## %expect with reduce conflicts.  ##
+## ------------------------------- ##
 
 AT_SETUP([%expect with reduce conflicts])
 
@@ -536,16 +849,33 @@ program: a 'a' | a a;
 a: 'a';
 ]])
 
-AT_CHECK([bison -o input.c input.y], 1, [],
+AT_BISON_CHECK([-o input.c input.y], 1, [],
 [input.y: conflicts: 1 reduce/reduce
 input.y: expected 0 reduce/reduce conflicts
 ])
 AT_CLEANUP
 
 
-## ------------------------------- ##
-## %no-default-prec without %prec  ##
-## ------------------------------- ##
+## ------------------------- ##
+## %prec with user strings.  ##
+## ------------------------- ##
+
+AT_SETUP([%prec with user string])
+
+AT_DATA([[input.y]],
+[[%%
+exp:
+  "foo" %prec "foo"
+;
+]])
+
+AT_BISON_CHECK([-o input.c input.y])
+AT_CLEANUP
+
+
+## -------------------------------- ##
+## %no-default-prec without %prec.  ##
+## -------------------------------- ##
 
 AT_SETUP([%no-default-prec without %prec])
 
@@ -563,15 +893,15 @@ e:   e '+' e
    ;
 ]])
 
-AT_CHECK([bison -o input.c input.y], 0, [],
+AT_BISON_CHECK([-o input.c input.y], 0, [],
 [[input.y: conflicts: 4 shift/reduce
 ]])
 AT_CLEANUP
 
 
-## ---------------------------- ##
-## %no-default-prec with %prec  ##
-## ---------------------------- ##
+## ----------------------------- ##
+## %no-default-prec with %prec.  ##
+## ----------------------------- ##
 
 AT_SETUP([%no-default-prec with %prec])
 
@@ -589,13 +919,13 @@ e:   e '+' e %prec '+'
    ;
 ]])
 
-AT_CHECK([bison -o input.c input.y])
+AT_BISON_CHECK([-o input.c input.y])
 AT_CLEANUP
 
 
-## ---------------- ##
-## %default-prec    ##
-## ---------------- ##
+## --------------- ##
+## %default-prec.  ##
+## --------------- ##
 
 AT_SETUP([%default-prec])
 
@@ -613,7 +943,7 @@ e:   e '+' e
    ;
 ]])
 
-AT_CHECK([bison -o input.c input.y])
+AT_BISON_CHECK([-o input.c input.y])
 AT_CLEANUP
 
 
@@ -665,7 +995,7 @@ reported_conflicts:
 
 ]])
 
-AT_CHECK([[bison --report=all input.y]], 0, [],
+AT_BISON_CHECK([[--report=all input.y]], 0, [],
 [[input.y: conflicts: 1 shift/reduce, 1 reduce/reduce
 input.y:12.5-20: warning: rule useless in parser due to conflicts: resolved_conflict: 'a' unreachable1
 input.y:20.5-20: warning: rule useless in parser due to conflicts: unreachable1: 'a' unreachable2
@@ -813,11 +1143,11 @@ state 7
 ]])
 
 AT_DATA([[input-keep.y]],
-[[%define lr.keep_unreachable_states
+[[%define lr.keep-unreachable-states
 ]])
 AT_CHECK([[cat input.y >> input-keep.y]])
 
-AT_CHECK([[bison input-keep.y]], 0, [],
+AT_BISON_CHECK([[input-keep.y]], 0, [],
 [[input-keep.y: conflicts: 2 shift/reduce, 2 reduce/reduce
 input-keep.y:22.4: warning: rule useless in parser due to conflicts: unreachable1: /* empty */
 input-keep.y:26.16: warning: rule useless in parser due to conflicts: unreachable2: /* empty */
@@ -858,7 +1188,7 @@ empty_c1: %prec 'c' ;
 empty_c2: %prec 'c' ;
 empty_c3: %prec 'd' ;
 ]])
-AT_CHECK([[bison --report=all -o input.c input.y]], 0, [], [ignore])
+AT_BISON_CHECK([[--report=all -o input.c input.y]], 0, [], [ignore])
 AT_CHECK([[cat input.output | sed -n '/^state 0$/,/^state 1$/p']], 0,
 [[state 0
 
@@ -934,7 +1264,7 @@ empty_c2: %prec 'c' ;
 empty_c3: %prec 'c' ;
 ]])
 
-AT_CHECK([[bison --report=all -o input.c input.y]], 0, [], [ignore])
+AT_BISON_CHECK([[--report=all -o input.c input.y]], 0, [], [ignore])
 AT_CHECK([[cat input.output | sed -n '/^state 0$/,/^state 1$/p']], 0,
 [[state 0