mirror of
https://git.savannah.gnu.org/git/bison.git
synced 2026-03-14 14:53:03 +00:00
parse.lac: implement as %define variable.
LAC = lookahead correction. See discussion at <http://lists.gnu.org/archive/html/bison-patches/2009-09/msg00034.html>. However, one point there must be corrected: because of %nonassoc, LAC is *not* always redundant for lr.type=canonical-lr. * data/yacc.c: Accept values of "none" (default) or "full" for parse.lac. Accept %define parse.lac.es-capacity to specify capacity of LAC's temporary exploratory stack. It defaults to 20 and, for now, will not grow dynamically. (b4_lac_flag, b4_lac_if): New m4 macros. Evaluate as true for parse.lac!=none. (YYBACKUP): Invoke YY_LAC_DISCARD. (YY_LAC_ESTABLISH, YY_LAC_DISCARD): New cpp macros that invoke yy_lac and track when it needs to be invoked (yy_lac): New function that, given the current stack, determines whether a token can eventually be shifted. Return status mimics yyparse return status. (yysyntax_error): Change yystate argument to yyssp so stack top can be passed to yy_lac. If LAC is requested, build expected token list by invoking yy_lac for every token instead of just checking the current state for lookaheads. Return 2 if yy_lac exhausts memory. (yyparse, yypush_parse): Use local variable yy_lac_established and cpp macros YY_LAC_ESTABLISH and YY_LAC_DISCARD to implement LAC. Update yysyntax_error invocation. Add yyexhaustedlab code if LAC is requested. * tests/conflicts.at (%nonassoc and eof): Extend to check the effect of each of -Dlr.type=canonical-lr and -Dparse.lac=full. (parse.error=verbose and consistent errors): Likewise. (LAC: %nonassoc requires splitting canonical LR states): New test group demonstrating how LAC can fix canonical LR. * tests/input.at (LAC: Errors for %define): New test group. * tests/regression.at (LAC: Exploratory stack): New test group. (LAC: Memory exhaustion): New test group.
This commit is contained in:
@@ -1469,3 +1469,186 @@ memory exhausted
|
||||
]])
|
||||
|
||||
AT_CLEANUP
|
||||
|
||||
|
||||
|
||||
## ------------------------ ##
|
||||
## LAC: Exploratory stack. ##
|
||||
## ------------------------ ##
|
||||
|
||||
AT_SETUP([[LAC: Exploratory stack]])
|
||||
|
||||
m4_pushdef([AT_LAC_CHECK], [
|
||||
|
||||
AT_BISON_OPTION_PUSHDEFS([$1])
|
||||
|
||||
AT_DATA_GRAMMAR([input.y],
|
||||
[[%code {
|
||||
#include <stdio.h>
|
||||
void yyerror (char const *);
|
||||
int yylex (]AT_PURE_IF([[YYSTYPE *]], [[void]])[);
|
||||
}
|
||||
|
||||
]$1[
|
||||
%define parse.error verbose
|
||||
%token 'c'
|
||||
|
||||
%%
|
||||
|
||||
// default reductions in inconsistent states
|
||||
// v v v v v v v v v v v v v v
|
||||
S: A B A A B A A A A B A A A A A A A B C C A A A A A A A A A A A A B ;
|
||||
|
||||
A: 'a' | /*empty*/ { printf ("inconsistent default reduction\n"); } ;
|
||||
B: 'b' ;
|
||||
C: /*empty*/ { printf ("consistent default reduction\n"); } ;
|
||||
|
||||
%%
|
||||
|
||||
void
|
||||
yyerror (char const *msg)
|
||||
{
|
||||
fprintf (stderr, "%s\n", msg);
|
||||
}
|
||||
|
||||
int
|
||||
yylex (]AT_PURE_IF([[YYSTYPE *v]], [[void]])[)
|
||||
{
|
||||
static char const *input = "bbbbc";]AT_PURE_IF([[
|
||||
*v = 0;]])[
|
||||
return *input++;
|
||||
}
|
||||
|
||||
int
|
||||
main (void)
|
||||
{
|
||||
yydebug = 1;
|
||||
return yyparse ();
|
||||
}
|
||||
]])
|
||||
|
||||
# Give exactly the right amount of memory to be sure there's no
|
||||
# off-by-one error, for example.
|
||||
AT_BISON_CHECK([[-Dparse.lac=full -Dparse.lac.es-capacity=12 \
|
||||
-t -o input.c input.y]], [[0]], [],
|
||||
[[input.y: conflicts: 21 shift/reduce
|
||||
]])
|
||||
AT_COMPILE([[input]])
|
||||
AT_PARSER_CHECK([[./input > stdout.txt 2> stderr.txt]], [[1]])
|
||||
|
||||
# Make sure syntax error doesn't forget that 'a' is expected. It would
|
||||
# be forgotten without lookahead correction.
|
||||
AT_CHECK([[grep 'syntax error,' stderr.txt]], [[0]],
|
||||
[[syntax error, unexpected 'c', expecting 'a' or 'b'
|
||||
]])
|
||||
|
||||
# Check number of default reductions in inconsistent states to be sure
|
||||
# syntax error is detected before unnecessary reductions are performed.
|
||||
AT_CHECK([[perl -0777 -ne 'print s/inconsistent default reduction//g;' \
|
||||
< stdout.txt || exit 77]], [[0]], [[14]])
|
||||
|
||||
# Check number of default reductions in consistent states to be sure
|
||||
# it is performed before the syntax error is detected.
|
||||
AT_CHECK([[perl -0777 -ne 'print s/\bconsistent default reduction//g;' \
|
||||
< stdout.txt || exit 77]], [[0]], [[2]])
|
||||
|
||||
AT_BISON_OPTION_POPDEFS
|
||||
])
|
||||
|
||||
AT_LAC_CHECK([[%define api.push-pull pull]])
|
||||
AT_LAC_CHECK([[%define api.push-pull pull %define api.pure]])
|
||||
AT_LAC_CHECK([[%define api.push-pull both]])
|
||||
AT_LAC_CHECK([[%define api.push-pull both %define api.pure]])
|
||||
|
||||
m4_popdef([AT_LAC_CHECK])
|
||||
|
||||
AT_CLEANUP
|
||||
|
||||
|
||||
|
||||
## ------------------------ ##
|
||||
## LAC: Memory exhaustion. ##
|
||||
## ------------------------ ##
|
||||
|
||||
AT_SETUP([[LAC: Memory exhaustion]])
|
||||
|
||||
m4_pushdef([AT_LAC_CHECK], [
|
||||
|
||||
AT_DATA_GRAMMAR([input.y],
|
||||
[[%code {
|
||||
#include <stdio.h>
|
||||
void yyerror (char const *);
|
||||
int yylex (void);
|
||||
}
|
||||
|
||||
%error-verbose
|
||||
|
||||
%%
|
||||
|
||||
S: A A A A A A A A A ;
|
||||
A: /*empty*/ | 'a' ;
|
||||
|
||||
%%
|
||||
|
||||
void
|
||||
yyerror (char const *msg)
|
||||
{
|
||||
fprintf (stderr, "%s\n", msg);
|
||||
}
|
||||
|
||||
int
|
||||
yylex (void)
|
||||
{
|
||||
static char const *input = "]$1[";
|
||||
return *input++;
|
||||
}
|
||||
|
||||
int
|
||||
main (void)
|
||||
{
|
||||
yydebug = 1;
|
||||
return yyparse ();
|
||||
}
|
||||
]])
|
||||
|
||||
AT_BISON_CHECK([[-Dparse.lac=full -Dparse.lac.es-capacity=8 \
|
||||
-t -o input.c input.y]], [[0]], [],
|
||||
[[input.y: conflicts: 8 shift/reduce
|
||||
]])
|
||||
AT_COMPILE([[input]])
|
||||
|
||||
])
|
||||
|
||||
# Check for memory exhaustion during parsing.
|
||||
AT_LAC_CHECK([[]])
|
||||
AT_PARSER_CHECK([[./input]], [[2]], [[]],
|
||||
[[Starting parse
|
||||
Entering state 0
|
||||
Reading a token: Now at end of input.
|
||||
LAC: initial context established for $end
|
||||
LAC: checking lookahead $end: R2 G3 R2 G5 R2 G6 R2 G7 R2 G8 R2 G9 R2 G10 R2 G11 R2 (max stack size exceeded)
|
||||
memory exhausted
|
||||
Cleanup: discarding lookahead token $end ()
|
||||
Stack now 0
|
||||
]])
|
||||
|
||||
# Induce an immediate syntax error with an undefined token, and check
|
||||
# for memory exhaustion while building syntax error message.
|
||||
AT_LAC_CHECK([[z]], [[0]])
|
||||
AT_PARSER_CHECK([[./input]], [[2]], [[]],
|
||||
[[Starting parse
|
||||
Entering state 0
|
||||
Reading a token: Next token is token $undefined ()
|
||||
LAC: initial context established for $undefined
|
||||
LAC: checking lookahead $undefined: Always Err
|
||||
Constructing syntax error message
|
||||
LAC: checking lookahead $end: R2 G3 R2 G5 R2 G6 R2 G7 R2 G8 R2 G9 R2 G10 R2 G11 R2 (max stack size exceeded)
|
||||
syntax error
|
||||
memory exhausted
|
||||
Cleanup: discarding lookahead token $undefined ()
|
||||
Stack now 0
|
||||
]])
|
||||
|
||||
m4_popdef([AT_LAC_CHECK])
|
||||
|
||||
AT_CLEANUP
|
||||
|
||||
Reference in New Issue
Block a user