# Exercising Bison on conflicts. -*- Autotest -*-
-# Copyright (C) 2002, 2003, 2004, 2005, 2007, 2008, 2009 Free Software
-# Foundation, Inc.
+# Copyright (C) 2002-2005, 2007-2011 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
}
]])
-# Specify the output files to avoid problems on different file systems.
-AT_BISON_CHECK([-o input.c input.y])
+m4_pushdef([AT_NONASSOC_AND_EOF_CHECK],
+[AT_BISON_CHECK([$1[ -o input.c input.y]])
AT_COMPILE([input])
+m4_pushdef([AT_EXPECTING], [m4_if($2, [correct], [[, expecting $end]])])
+
AT_PARSER_CHECK([./input '0<0'])
AT_PARSER_CHECK([./input '0<0<0'], [1], [],
- [syntax error, unexpected '<'
+ [syntax error, unexpected '<'AT_EXPECTING
])
AT_PARSER_CHECK([./input '0>0'])
AT_PARSER_CHECK([./input '0>0>0'], [1], [],
- [syntax error, unexpected '>'
+ [syntax error, unexpected '>'AT_EXPECTING
])
AT_PARSER_CHECK([./input '0<0>0'], [1], [],
- [syntax error, unexpected '>'
+ [syntax error, unexpected '>'AT_EXPECTING
])
+m4_popdef([AT_EXPECTING])])
+
+# Expected token list is missing.
+AT_NONASSOC_AND_EOF_CHECK([], [[incorrect]])
+
# 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.)
+# have an explicit list of all expected tokens.
+AT_NONASSOC_AND_EOF_CHECK([[-Dlr.default-reductions=consistent]],
+ [[correct]])
+
+# lr.default-reductions=consistent happens to work for this test case.
+# However, for other grammars, lookahead sets can be merged for
+# different left contexts, so it is still possible to have an incorrect
+# expected list. Canonical LR is almost a general solution (that is, it
+# can fail only when %nonassoc is used), so make sure it gives the same
+# result as above.
+AT_NONASSOC_AND_EOF_CHECK([[-Dlr.type=canonical-lr]], [[correct]])
+
+# parse.lac=full is a completely general solution that does not require
+# any of the above sacrifices. Of course, it does not extend the
+# language-recognition power of LALR to (IE)LR, but it does ensure that
+# the reported list of expected tokens matches what the given parser
+# would have accepted in place of the unexpected token.
+AT_NONASSOC_AND_EOF_CHECK([[-Dparse.lac=full]], [[correct]])
+
+m4_popdef([AT_NONASSOC_AND_EOF_CHECK])
-AT_BISON_CHECK([-Dlr.default-reductions=consistent -o input.c input.y])
-AT_COMPILE([input])
+AT_CLEANUP
-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
+## ------------------------------------------- ##
+## parse.error=verbose and consistent errors. ##
+## ------------------------------------------- ##
+
+AT_SETUP([[parse.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 <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[
+
+%define parse.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 (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],
+ [[$end]], [[ab]])
+
+# Only LAC gets it right.
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type canonical-lr
+ %define parse.lac full]],
+ [AT_PREVIOUS_STATE_GRAMMAR],
+ [AT_PREVIOUS_STATE_INPUT],
+ [[$end]], [[b]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type ielr
+ %define parse.lac full]],
+ [AT_PREVIOUS_STATE_GRAMMAR],
+ [AT_PREVIOUS_STATE_INPUT],
+ [[$end]], [[b]])
+
+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 == YYEMPTY);
+ yylval = 0;
+ yychar = 'b';
+} ;
+
+consistent-error:
+ 'a' { USE ($][1); }
+| /*empty*/ %prec 'a'
+;
+
+// Provide another context in which all rules are useful so that this
+// test case looks a little more realistic.
+start: 'b' consistent-error 'b' ;
+]])
+m4_pushdef([AT_USER_ACTION_INPUT], [[aa]])
+
+AT_CONSISTENT_ERRORS_CHECK([[]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [['b']], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%glr-parser]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [['b']], [[none]])
+# No C++ or Java test because yychar cannot be manipulated by users.
+
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.default-reductions consistent]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [['b']], [[none]])
+
+# Canonical LR doesn't foresee the error for 'a'!
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.default-reductions accepting]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [[$end]], [[a]])
+AT_CONSISTENT_ERRORS_CHECK([[%define lr.type canonical-lr]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [[$end]], [[a]])
+
+AT_CONSISTENT_ERRORS_CHECK([[%define parse.lac full]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [['b']], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%define parse.lac full
+ %define lr.default-reductions accepting]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [[$end]], [[none]])
+
+m4_popdef([AT_USER_ACTION_GRAMMAR])
+m4_popdef([AT_USER_ACTION_INPUT])
+
+m4_popdef([AT_CONSISTENT_ERRORS_CHECK])
+
AT_CLEANUP
+## ------------------------------------------------------- ##
+## LAC: %nonassoc requires splitting canonical LR states. ##
+## ------------------------------------------------------- ##
+
+# This test case demonstrates that, when %nonassoc is used, canonical
+# LR(1) parser table construction followed by conflict resolution
+# without further state splitting is not always sufficient to produce a
+# parser that can detect all syntax errors as soon as possible on one
+# token of lookahead. However, LAC solves the problem completely even
+# with minimal LR parser tables.
+
+AT_SETUP([[LAC: %nonassoc requires splitting canonical LR states]])
+
+AT_DATA_GRAMMAR([[input.y]],
+[[%code {
+ #include <stdio.h>
+ void yyerror (char const *);
+ int yylex (void);
+}
+
+%error-verbose
+%nonassoc 'a'
+
+%%
+
+start:
+ 'a' problem 'a' // First context.
+| 'b' problem 'b' // Second context.
+| 'c' reduce-nonassoc // Just makes reduce-nonassoc useful.
+;
+
+problem:
+ look reduce-nonassoc
+| look 'a'
+| look 'b'
+;
+
+// For the state reached after shifting the 'a' in these productions,
+// lookahead sets are the same in both the first and second contexts.
+// Thus, canonical LR reuses the same state for both contexts. However,
+// the lookahead 'a' for the reduction "look: 'a'" later becomes an
+// error action only in the first context. In order to immediately
+// detect the syntax error on 'a' here for only the first context, this
+// canonical LR state would have to be split into two states, and the
+// 'a' lookahead would have to be removed from only one of the states.
+look:
+ 'a' // Reduction lookahead set is always ['a', 'b'].
+| 'a' 'b'
+| 'a' 'c' // 'c' is forgotten as an expected token.
+;
+
+reduce-nonassoc: %prec 'a';
+
+%%
+
+void
+yyerror (char const *msg)
+{
+ fprintf (stderr, "%s\n", msg);
+}
+
+int
+yylex (void)
+{
+ char const *input = "aaa";
+ return *input++;
+}
+
+int
+main (void)
+{
+ return yyparse ();
+}
+]])
+
+# Show canonical LR's failure.
+AT_BISON_CHECK([[-Dlr.type=canonical-lr -o input.c input.y]],
+ [[0]], [[]],
+[[input.y: conflicts: 2 shift/reduce
+]])
+AT_COMPILE([[input]])
+AT_PARSER_CHECK([[./input]], [[1]], [[]],
+[[syntax error, unexpected 'a', expecting 'b'
+]])
+
+# It's corrected by LAC.
+AT_BISON_CHECK([[-Dlr.type=canonical-lr -Dparse.lac=full \
+ -o input.c input.y]], [[0]], [[]],
+[[input.y: conflicts: 2 shift/reduce
+]])
+AT_COMPILE([[input]])
+AT_PARSER_CHECK([[./input]], [[1]], [[]],
+[[syntax error, unexpected 'a', expecting 'b' or 'c'
+]])
+
+# IELR is sufficient when LAC is used.
+AT_BISON_CHECK([[-Dlr.type=ielr -Dparse.lac=full -o input.c input.y]],
+ [[0]], [[]],
+[[input.y: conflicts: 2 shift/reduce
+]])
+AT_COMPILE([[input]])
+AT_PARSER_CHECK([[./input]], [[1]], [[]],
+[[syntax error, unexpected 'a', expecting 'b' or 'c'
+]])
+
+AT_CLEANUP
+
## ------------------------- ##
## Unresolved SR Conflicts. ##
## ------------------------- ##
projects / bison.git / blobdiff