# Exercising Bison on conflicts. -*- Autotest -*-
-# Copyright (C) 2002, 2003, 2004, 2005, 2007, 2009, 2010 Free
-# Software Foundation, Inc.
+# Copyright (C) 2002-2005, 2007, 2009-2012 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
])
-# 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.)
+m4_popdef([AT_EXPECTING])])
-AT_BISON_CHECK([-Dlr.default-reductions=consistent -o input.c input.y])
-AT_COMPILE([input])
+# Expected token list is missing.
+AT_NONASSOC_AND_EOF_CHECK([], [[incorrect]])
-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 $end
-])
+# We must disable default reductions in inconsistent states in order to
+# have an explicit list of all expected tokens.
+AT_NONASSOC_AND_EOF_CHECK([[-Dlr.default-reductions=consistent]],
+ [[correct]])
+
+# lr.default-reductions=consistent happens to work for this test case.
+# However, for other grammars, lookahead sets can be merged for
+# different left contexts, so it is still possible to have an incorrect
+# expected list. Canonical LR is almost a general solution (that is, it
+# can fail only when %nonassoc is used), so make sure it gives the same
+# result as above.
+AT_NONASSOC_AND_EOF_CHECK([[-Dlr.type=canonical-lr]], [[correct]])
+
+# parse.lac=full is a completely general solution that does not require
+# any of the above sacrifices. Of course, it does not extend the
+# language-recognition power of LALR to (IE)LR, but it does ensure that
+# the reported list of expected tokens matches what the given parser
+# would have accepted in place of the unexpected token.
+AT_NONASSOC_AND_EOF_CHECK([[-Dparse.lac=full]], [[correct]])
+
+m4_popdef([AT_NONASSOC_AND_EOF_CHECK])
AT_CLEANUP
}]], [[
%code {]AT_SKEL_CC_IF([[
+ #include <cassert>
#include <string>]], [[
#include <assert.h>
#include <stdio.h>
[AT_PREVIOUS_STATE_INPUT],
[[$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])
;
consistent-reduction: /*empty*/ {
- assert (yychar == YYEMPTY);
+ assert (yychar == ]AT_SKEL_CC_IF([[yyempty_]], [[YYEMPTY]])[);
yylval = 0;
yychar = 'b';
} ;
[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([[%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],
[[$end]], [[a]])
+AT_CONSISTENT_ERRORS_CHECK([[%define parse.lac full]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [['b']], [[none]])
+AT_CONSISTENT_ERRORS_CHECK([[%define parse.lac full
+ %define lr.default-reductions accepting]],
+ [AT_USER_ACTION_GRAMMAR],
+ [AT_USER_ACTION_INPUT],
+ [[$end]], [[none]])
+
m4_popdef([AT_USER_ACTION_GRAMMAR])
m4_popdef([AT_USER_ACTION_INPUT])
+## ------------------------------------------------------- ##
+## 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. ##
## ------------------------- ##
state 1
]])
AT_CLEANUP
+
+
+## --------------------------------- ##
+## -W versus %expect and %expect-rr ##
+## --------------------------------- ##
+
+AT_SETUP([[-W versus %expect and %expect-rr]])
+
+AT_DATA([[sr-rr.y]],
+[[%glr-parser
+%%
+start: 'a' | A 'a' | B 'a' ;
+A: ;
+B: ;
+]])
+AT_DATA([[sr.y]],
+[[%glr-parser
+%%
+start: 'a' | A 'a' ;
+A: ;
+]])
+AT_DATA([[rr.y]],
+[[%glr-parser
+%%
+start: A | B ;
+A: ;
+B: ;
+]])
+
+AT_BISON_CHECK([[sr-rr.y]], [[0]], [[]],
+[[sr-rr.y: conflicts: 1 shift/reduce, 1 reduce/reduce
+]])
+AT_BISON_CHECK([[-Wno-conflicts-sr sr-rr.y]], [[0]], [[]],
+[[sr-rr.y: conflicts: 1 reduce/reduce
+]])
+AT_BISON_CHECK([[-Wno-conflicts-rr sr-rr.y]], [[0]], [[]],
+[[sr-rr.y: conflicts: 1 shift/reduce
+]])
+
+[for gram in sr-rr sr rr; do
+ for sr_exp_i in '' 0 1 2; do
+ for rr_exp_i in '' 0 1 2; do
+ test -z "$sr_exp_i" && test -z "$rr_exp_i" && continue
+
+ # Build grammar file.
+ sr_exp=0
+ rr_exp=0
+ file=$gram
+ directives=
+ if test -n "$sr_exp_i"; then
+ sr_exp=$sr_exp_i
+ file=$file-expect-$sr_exp
+ directives="%expect $sr_exp"
+ fi
+ if test -n "$rr_exp_i"; then
+ rr_exp=$rr_exp_i
+ file=$file-expect-rr-$rr_exp
+ directives="$directives %expect-rr $rr_exp"
+ fi
+ file=$file.y
+ echo "$directives" > $file
+ cat $gram.y >> $file
+
+ # Count actual conflicts.
+ conflicts=
+ sr_count=0
+ rr_count=0
+ if test $gram = sr || test $gram = sr-rr; then
+ conflicts="1 shift/reduce"
+ sr_count=1
+ fi
+ if test $gram = rr || test $gram = sr-rr; then
+ if test -n "$conflicts"; then
+ conflicts="$conflicts, "
+ fi
+ conflicts="${conflicts}1 reduce/reduce"
+ rr_count=1
+ fi
+
+ # Run tests.
+ if test $sr_count -eq $sr_exp && test $rr_count -eq $rr_exp; then
+ ]AT_BISON_CHECK([[-Wnone $file]])[
+ ]AT_BISON_CHECK([[-Werror $file]])[
+ else
+ echo "$file: conflicts: $conflicts" > experr
+ if test $sr_count -ne $sr_exp; then
+ if test $sr_exp -ne 1; then s=s; else s= ; fi
+ echo "$file: expected $sr_exp shift/reduce conflict$s" >> experr
+ fi
+ if test $rr_count -ne $rr_exp; then
+ if test $rr_exp -ne 1; then s=s; else s= ; fi
+ echo "$file: expected $rr_exp reduce/reduce conflict$s" >> experr
+ fi
+ ]AT_BISON_CHECK([[-Wnone $file]], [[1]], [[]], [[experr]])[
+ ]AT_BISON_CHECK([[-Werror $file]], [[1]], [[]], [[experr]])[
+ fi
+ done
+ done
+done]
+
+AT_CLEANUP
projects / bison.git / blobdiff