# Executing Actions. -*- Autotest -*- # Copyright (C) 2001-2012 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 # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . AT_BANNER([[User Actions.]]) ## ------------------ ## ## Mid-rule actions. ## ## ------------------ ## AT_SETUP([Mid-rule actions]) # Bison once forgot the mid-rule actions. It was because the action # was attached to the host rule (the one with the mid-rule action), # instead of being attached to the empty rule dedicated to this # action. AT_DATA_GRAMMAR([[input.y]], [[%define parse.error verbose %debug %{ # include # include static void yyerror (const char *msg); static int yylex (void); %} %% exp: { putchar ('0'); } '1' { putchar ('1'); } '2' { putchar ('2'); } '3' { putchar ('3'); } '4' { putchar ('4'); } '5' { putchar ('5'); } '6' { putchar ('6'); } '7' { putchar ('7'); } '8' { putchar ('8'); } '9' { putchar ('9'); } { putchar ('\n'); } ; %% static int yylex (void) { static char const input[] = "123456789"; static size_t toknum; if (! (toknum < sizeof input)) abort (); return input[toknum++]; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { return yyparse (); } ]]) AT_BISON_CHECK([-d -v -o input.c input.y]) AT_COMPILE([input]) AT_PARSER_CHECK([./input], 0, [[0123456789 ]]) AT_CLEANUP ## ---------------- ## ## Exotic Dollars. ## ## ---------------- ## AT_SETUP([Exotic Dollars]) AT_DATA_GRAMMAR([[input.y]], [[%define parse.error verbose %debug %{ # include # include static void yyerror (const char *msg); static int yylex (void); # define USE(Var) %} %union { int val; }; %type a_1 a_2 a_5 sum_of_the_five_previous_values %% exp: a_1 a_2 { $$ = 3; } { $$ = $3 + 1; } a_5 sum_of_the_five_previous_values { USE (($1, $2, $3, $4, $5)); printf ("%d\n", $6); } ; a_1: { $$ = 1; }; a_2: { $$ = 2; }; a_5: { $$ = 5; }; sum_of_the_five_previous_values: { $$ = $0 + $-1 + $-2 + $-3 + $-4; } ; %% static int yylex (void) { static int called; if (called++) abort (); return EOF; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { return yyparse (); } ]]) AT_BISON_CHECK([-d -v -o input.c input.y], 0) AT_COMPILE([input]) AT_PARSER_CHECK([./input], 0, [[15 ]]) # Make sure that fields after $n or $-n are parsed correctly. At one # point while implementing dashes in symbol names, we were dropping # fields after $-n. AT_DATA_GRAMMAR([[input.y]], [[ %{ # include static int yylex (void); static void yyerror (char const *msg); typedef struct { int val; } stype; # define YYSTYPE stype %} %% start: one two { $$.val = $1.val + $2.val; } sum ; one: { $$.val = 1; } ; two: { $$.val = 2; } ; sum: { printf ("%d\n", $0.val + $-1.val + $-2.val); } ; %% static int yylex (void) { return 0; } static void yyerror (char const *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { return yyparse (); } ]]) AT_BISON_CHECK([[-o input.c input.y]]) AT_COMPILE([[input]]) AT_PARSER_CHECK([[./input]], [[0]], [[6 ]]) AT_CLEANUP ## -------------------------- ## ## Printers and Destructors. ## ## -------------------------- ## # _AT_CHECK_PRINTER_AND_DESTRUCTOR($1, $2, $3, $4, BISON-DIRECTIVE, UNION-FLAG) # ----------------------------------------------------------------------------- m4_define([_AT_CHECK_PRINTER_AND_DESTRUCTOR], [# Make sure complex $n work. m4_if([$1$2$3], $[1]$[2]$[3], [], [m4_fatal([$0: Invalid arguments: $@])])dnl # Be sure to pass all the %directives to this macro to have correct # helping macros. So don't put any directly in the Bison file. AT_BISON_OPTION_PUSHDEFS([$5]) AT_DATA_GRAMMAR([[input.y]], [[%code requires { #include #include #include #include #define YYINITDEPTH 10 #define YYMAXDEPTH 10 ]AT_LALR1_CC_IF( [#define RANGE(Location) (Location).begin.line, (Location).end.line], [#define RANGE(Location) (Location).first_line, (Location).last_line]) [} $5] m4_ifval([$6], [%union { int ival; }]) AT_LALR1_CC_IF([%define global_tokens_and_yystype]) m4_ifval([$6], [[%code provides {]], [[%code {]]) AT_LALR1_CC_IF([typedef yy::location YYLTYPE;]) [static int yylex (]AT_LEX_FORMALS[); ]AT_LALR1_CC_IF([], [static void yyerror (const char *msg);]) [} ]m4_ifval([$6], [%type '(' 'x' 'y' ')' ';' thing line input END])[ /* FIXME: This %printer isn't actually tested. */ %printer { ]AT_LALR1_CC_IF([debug_stream () << $$;], [fprintf (yyoutput, "%d", $$)])[; } input line thing 'x' 'y' %destructor { printf ("Freeing nterm input (%d@%d-%d)\n", $$, RANGE (@$)); } input %destructor { printf ("Freeing nterm line (%d@%d-%d)\n", $$, RANGE (@$)); } line %destructor { printf ("Freeing nterm thing (%d@%d-%d)\n", $$, RANGE (@$)); } thing %destructor { printf ("Freeing token 'x' (%d@%d-%d)\n", $$, RANGE (@$)); } 'x' %destructor { printf ("Freeing token 'y' (%d@%d-%d)\n", $$, RANGE (@$)); } 'y' %token END 0 %destructor { printf ("Freeing token END (%d@%d-%d)\n", $$, RANGE (@$)); } END %% /* This grammar is made to exercise error recovery. "Lines" starting with `(' support error recovery, with ')' as synchronizing token. Lines starting with 'x' can never be recovered from if in error. */ input: /* Nothing. */ { $$ = 0; printf ("input (%d@%d-%d): /* Nothing */\n", $$, RANGE (@$)); } | line input /* Right recursive to load the stack so that popping at END can be exercised. */ { $$ = 2; printf ("input (%d@%d-%d): line (%d@%d-%d) input (%d@%d-%d)\n", $$, RANGE (@$), $1, RANGE (@1), $2, RANGE (@2)); } ; line: thing thing thing ';' { $$ = $1; printf ("line (%d@%d-%d): thing (%d@%d-%d) thing (%d@%d-%d) thing (%d@%d-%d) ';' (%d@%d-%d)\n", $$, RANGE (@$), $1, RANGE (@1), $2, RANGE (@2), $3, RANGE (@3), $4, RANGE (@4)); } | '(' thing thing ')' { $$ = $1; printf ("line (%d@%d-%d): '(' (%d@%d-%d) thing (%d@%d-%d) thing (%d@%d-%d) ')' (%d@%d-%d)\n", $$, RANGE (@$), $1, RANGE (@1), $2, RANGE (@2), $3, RANGE (@3), $4, RANGE (@4)); } | '(' thing ')' { $$ = $1; printf ("line (%d@%d-%d): '(' (%d@%d-%d) thing (%d@%d-%d) ')' (%d@%d-%d)\n", $$, RANGE (@$), $1, RANGE (@1), $2, RANGE (@2), $3, RANGE (@3)); } | '(' error ')' { $$ = -1; printf ("line (%d@%d-%d): '(' (%d@%d-%d) error (@%d-%d) ')' (%d@%d-%d)\n", $$, RANGE (@$), $1, RANGE (@1), RANGE (@2), $3, RANGE (@3)); } ; thing: 'x' { $$ = $1; printf ("thing (%d@%d-%d): 'x' (%d@%d-%d)\n", $$, RANGE (@$), $1, RANGE (@1)); } ; %% /* Alias to ARGV[1]. */ const char *source = YY_NULL; static int yylex (]AT_LEX_FORMALS[) { static unsigned int counter = 0; int c = ]AT_VAL[]m4_ifval([$6], [.ival])[ = counter++; /* As in BASIC, line numbers go from 10 to 10. */ ]AT_LALR1_CC_IF( [ AT_LOC.begin.line = AT_LOC.begin.column = 10 * c; AT_LOC.end.line = AT_LOC.end.column = AT_LOC.begin.line + 9; ], [ AT_LOC.first_line = AT_LOC.first_column = 10 * c; AT_LOC.last_line = AT_LOC.last_column = AT_LOC.first_line + 9; ])[ if (! (0 <= c && c <= strlen (source))) abort (); if (source[c]) printf ("sending: '%c'", source[c]); else printf ("sending: END"); printf (" (%d@%d-%d)\n", c, RANGE (]AT_LOC[)); return source[c]; } ]AT_LALR1_CC_IF( [/* A C++ error reporting function. */ void yy::parser::error (const location& l, const std::string& m) { printf ("%d-%d: %s\n", RANGE (l), m.c_str()); } static bool yydebug; int yyparse () { yy::parser parser; parser.set_debug_level (yydebug); return parser.parse (); } ], [static void yyerror (const char *msg) { printf ("%d-%d: %s\n", RANGE (yylloc), msg); }])[ int main (int argc, const char *argv[]) { int status; yydebug = !!getenv ("YYDEBUG"); assert (argc == 2); source = argv[1]; status = yyparse (); switch (status) { case 0: printf ("Successful parse.\n"); break; case 1: printf ("Parsing FAILED.\n"); break; default: printf ("Parsing FAILED (status %d).\n", status); break; } return status; } ]]) AT_FULL_COMPILE([input]) # Check the location of "empty" # ----------------------------- # I.e., epsilon-reductions, as in "(x)" which ends by reducing # an empty "line" nterm. # FIXME: This location is not satisfying. Depend on the lookahead? AT_PARSER_CHECK([./input '(x)'], 0, [[sending: '(' (0@0-9) sending: 'x' (1@10-19) thing (1@10-19): 'x' (1@10-19) sending: ')' (2@20-29) line (0@0-29): '(' (0@0-9) thing (1@10-19) ')' (2@20-29) sending: END (3@30-39) input (0@29-29): /* Nothing */ input (2@0-29): line (0@0-29) input (0@29-29) Freeing token END (3@30-39) Freeing nterm input (2@0-29) Successful parse. ]]) # Check locations in error recovery # --------------------------------- # '(y)' is an error, but can be recovered from. But what's the location # of the error itself ('y'), and of the resulting reduction ('(error)'). AT_PARSER_CHECK([./input '(y)'], 0, [[sending: '(' (0@0-9) sending: 'y' (1@10-19) 10-19: syntax error, unexpected 'y', expecting 'x' Freeing token 'y' (1@10-19) sending: ')' (2@20-29) line (-1@0-29): '(' (0@0-9) error (@10-19) ')' (2@20-29) sending: END (3@30-39) input (0@29-29): /* Nothing */ input (2@0-29): line (-1@0-29) input (0@29-29) Freeing token END (3@30-39) Freeing nterm input (2@0-29) Successful parse. ]]) # Syntax errors caught by the parser # ---------------------------------- # Exercise the discarding of stack top and input until `error' # can be reduced. # # '(', 'x', 'x', 'x', 'x', 'x', ')', # # Load the stack and provoke an error that cannot be caught by the # grammar, to check that the stack is cleared. And make sure the # lookahead is freed. # # '(', 'x', ')', # '(', 'x', ')', # 'y' AT_PARSER_CHECK([./input '(xxxxx)(x)(x)y'], 1, [[sending: '(' (0@0-9) sending: 'x' (1@10-19) thing (1@10-19): 'x' (1@10-19) sending: 'x' (2@20-29) thing (2@20-29): 'x' (2@20-29) sending: 'x' (3@30-39) 30-39: syntax error, unexpected 'x', expecting ')' Freeing nterm thing (2@20-29) Freeing nterm thing (1@10-19) Freeing token 'x' (3@30-39) sending: 'x' (4@40-49) Freeing token 'x' (4@40-49) sending: 'x' (5@50-59) Freeing token 'x' (5@50-59) sending: ')' (6@60-69) line (-1@0-69): '(' (0@0-9) error (@10-59) ')' (6@60-69) sending: '(' (7@70-79) sending: 'x' (8@80-89) thing (8@80-89): 'x' (8@80-89) sending: ')' (9@90-99) line (7@70-99): '(' (7@70-79) thing (8@80-89) ')' (9@90-99) sending: '(' (10@100-109) sending: 'x' (11@110-119) thing (11@110-119): 'x' (11@110-119) sending: ')' (12@120-129) line (10@100-129): '(' (10@100-109) thing (11@110-119) ')' (12@120-129) sending: 'y' (13@130-139) input (0@129-129): /* Nothing */ input (2@100-129): line (10@100-129) input (0@129-129) input (2@70-129): line (7@70-99) input (2@100-129) input (2@0-129): line (-1@0-69) input (2@70-129) 130-139: syntax error, unexpected 'y', expecting END Freeing nterm input (2@0-129) Freeing token 'y' (13@130-139) Parsing FAILED. ]]) # Syntax error caught by the parser where lookahead = END # -------------------------------------------------------- # Load the stack and provoke an error that cannot be caught by the # grammar, to check that the stack is cleared. And make sure the # lookahead is freed. # # '(', 'x', ')', # '(', 'x', ')', # 'x' AT_PARSER_CHECK([./input '(x)(x)x'], 1, [[sending: '(' (0@0-9) sending: 'x' (1@10-19) thing (1@10-19): 'x' (1@10-19) sending: ')' (2@20-29) line (0@0-29): '(' (0@0-9) thing (1@10-19) ')' (2@20-29) sending: '(' (3@30-39) sending: 'x' (4@40-49) thing (4@40-49): 'x' (4@40-49) sending: ')' (5@50-59) line (3@30-59): '(' (3@30-39) thing (4@40-49) ')' (5@50-59) sending: 'x' (6@60-69) thing (6@60-69): 'x' (6@60-69) sending: END (7@70-79) 70-79: syntax error, unexpected END, expecting 'x' Freeing nterm thing (6@60-69) Freeing nterm line (3@30-59) Freeing nterm line (0@0-29) Freeing token END (7@70-79) Parsing FAILED. ]]) # Check destruction upon stack overflow # ------------------------------------- # Upon stack overflow, all symbols on the stack should be destroyed. # Only check for yacc.c. AT_YACC_IF([ AT_PARSER_CHECK([./input '(x)(x)(x)(x)(x)(x)(x)'], 2, [[sending: '(' (0@0-9) sending: 'x' (1@10-19) thing (1@10-19): 'x' (1@10-19) sending: ')' (2@20-29) line (0@0-29): '(' (0@0-9) thing (1@10-19) ')' (2@20-29) sending: '(' (3@30-39) sending: 'x' (4@40-49) thing (4@40-49): 'x' (4@40-49) sending: ')' (5@50-59) line (3@30-59): '(' (3@30-39) thing (4@40-49) ')' (5@50-59) sending: '(' (6@60-69) sending: 'x' (7@70-79) thing (7@70-79): 'x' (7@70-79) sending: ')' (8@80-89) line (6@60-89): '(' (6@60-69) thing (7@70-79) ')' (8@80-89) sending: '(' (9@90-99) sending: 'x' (10@100-109) thing (10@100-109): 'x' (10@100-109) sending: ')' (11@110-119) line (9@90-119): '(' (9@90-99) thing (10@100-109) ')' (11@110-119) sending: '(' (12@120-129) sending: 'x' (13@130-139) thing (13@130-139): 'x' (13@130-139) sending: ')' (14@140-149) line (12@120-149): '(' (12@120-129) thing (13@130-139) ')' (14@140-149) sending: '(' (15@150-159) sending: 'x' (16@160-169) thing (16@160-169): 'x' (16@160-169) sending: ')' (17@170-179) line (15@150-179): '(' (15@150-159) thing (16@160-169) ')' (17@170-179) sending: '(' (18@180-189) sending: 'x' (19@190-199) thing (19@190-199): 'x' (19@190-199) sending: ')' (20@200-209) 200-209: memory exhausted Freeing nterm thing (19@190-199) Freeing nterm line (15@150-179) Freeing nterm line (12@120-149) Freeing nterm line (9@90-119) Freeing nterm line (6@60-89) Freeing nterm line (3@30-59) Freeing nterm line (0@0-29) Parsing FAILED (status 2). ]]) ]) ]) # AT_CHECK_PRINTER_AND_DESTRUCTOR([BISON-OPTIONS], [UNION-FLAG], [SKIP_FLAG]) # --------------------------------------------------------------------------- m4_define([AT_CHECK_PRINTER_AND_DESTRUCTOR], [AT_SETUP([Printers and Destructors $2: $1]) $3 _AT_CHECK_PRINTER_AND_DESTRUCTOR($[1], $[2], $[3], $[4], [%define parse.error verbose %debug %verbose %locations $1], [$2]) AT_CLEANUP ]) AT_CHECK_PRINTER_AND_DESTRUCTOR([]) AT_CHECK_PRINTER_AND_DESTRUCTOR([], [with union]) AT_CHECK_PRINTER_AND_DESTRUCTOR([%defines %skeleton "lalr1.cc"]) AT_CHECK_PRINTER_AND_DESTRUCTOR([%defines %skeleton "lalr1.cc"], [with union]) AT_CHECK_PRINTER_AND_DESTRUCTOR([%glr-parser]) AT_CHECK_PRINTER_AND_DESTRUCTOR([%glr-parser], [with union]) ## ----------------------------------------- ## ## Default tagless %printer and %destructor. ## ## ----------------------------------------- ## # Check that the right %printer and %destructor are called, that they're not # called for $end, and that $$ and @$ work correctly. AT_SETUP([Default tagless %printer and %destructor]) AT_DATA_GRAMMAR([[input.y]], [[%define parse.error verbose %debug %locations %initial-action { @$.first_line = @$.last_line = 1; @$.first_column = @$.last_column = 1; } %{ # include # include static void yyerror (const char *msg); static int yylex (void); # define USE(SYM) %} %printer { fprintf (yyoutput, "<*> printer should not be called.\n"); } <*> %printer { fprintf (yyoutput, "<> printer for '%c' @ %d", $$, @$.first_column); } <> %destructor { fprintf (stdout, "<> destructor for '%c' @ %d.\n", $$, @$.first_column); } <> %printer { fprintf (yyoutput, "'b'/'c' printer for '%c' @ %d", $$, @$.first_column); } 'b' 'c' %destructor { fprintf (stdout, "'b'/'c' destructor for '%c' @ %d.\n", $$, @$.first_column); } 'b' 'c' %destructor { fprintf (yyoutput, "<*> destructor should not be called.\n"); } <*> %% start: 'a' 'b' 'c' 'd' 'e' { $$ = 'S'; USE(($1, $2, $3, $4, $5)); } ; %% static int yylex (void) { static char const input[] = "abcd"; static size_t toknum; if (! (toknum < sizeof input)) abort (); yylval = input[toknum++]; yylloc.first_line = yylloc.last_line = 1; yylloc.first_column = yylloc.last_column = toknum; return yylval; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { yydebug = 1; return yyparse (); } ]]) AT_BISON_CHECK([-o input.c input.y]) AT_COMPILE([input]) AT_PARSER_CHECK([./input], 1, [[<> destructor for 'd' @ 4. 'b'/'c' destructor for 'c' @ 3. 'b'/'c' destructor for 'b' @ 2. <> destructor for 'a' @ 1. ]], [[Starting parse Entering state 0 Reading a token: Next token is token 'a' (1.1-1.1: <> printer for 'a' @ 1) Shifting token 'a' (1.1-1.1: <> printer for 'a' @ 1) Entering state 1 Reading a token: Next token is token 'b' (1.2-1.2: 'b'/'c' printer for 'b' @ 2) Shifting token 'b' (1.2-1.2: 'b'/'c' printer for 'b' @ 2) Entering state 3 Reading a token: Next token is token 'c' (1.3-1.3: 'b'/'c' printer for 'c' @ 3) Shifting token 'c' (1.3-1.3: 'b'/'c' printer for 'c' @ 3) Entering state 5 Reading a token: Next token is token 'd' (1.4-1.4: <> printer for 'd' @ 4) Shifting token 'd' (1.4-1.4: <> printer for 'd' @ 4) Entering state 6 Reading a token: Now at end of input. syntax error, unexpected $end, expecting 'e' Error: popping token 'd' (1.4-1.4: <> printer for 'd' @ 4) Stack now 0 1 3 5 Error: popping token 'c' (1.3-1.3: 'b'/'c' printer for 'c' @ 3) Stack now 0 1 3 Error: popping token 'b' (1.2-1.2: 'b'/'c' printer for 'b' @ 2) Stack now 0 1 Error: popping token 'a' (1.1-1.1: <> printer for 'a' @ 1) Stack now 0 Cleanup: discarding lookahead token $end (1.5-1.5: ) Stack now 0 ]]) AT_CLEANUP ## ------------------------------------------------------ ## ## Default tagged and per-type %printer and %destructor. ## ## ------------------------------------------------------ ## AT_SETUP([Default tagged and per-type %printer and %destructor]) AT_DATA_GRAMMAR([[input.y]], [[%define parse.error verbose %debug %{ # include # include static void yyerror (const char *msg); static int yylex (void); # define USE(SYM) %} %printer { fprintf (yyoutput, "<> printer should not be called.\n"); } <> %union { int field0; int field1; int field2; } %type start 'a' 'g' %type 'e' %type 'f' %printer { fprintf (yyoutput, "<*>//e printer"); } <*> 'e' %destructor { fprintf (stdout, "<*>//e destructor.\n"); } <*> 'e' %type 'b' %printer { fprintf (yyoutput, " printer"); } %destructor { fprintf (stdout, " destructor.\n"); } %type 'c' %printer { fprintf (yyoutput, "'c' printer"); } 'c' %destructor { fprintf (stdout, "'c' destructor.\n"); } 'c' %type 'd' %printer { fprintf (yyoutput, "'d' printer"); } 'd' %destructor { fprintf (stdout, "'d' destructor.\n"); } 'd' %destructor { fprintf (yyoutput, "<> destructor should not be called.\n"); } <> %% start: 'a' 'b' 'c' 'd' 'e' 'f' 'g' { USE(($1, $2, $3, $4, $5, $6, $7)); $$ = 'S'; } ; %% static int yylex (void) { static char const input[] = "abcdef"; static size_t toknum; if (! (toknum < sizeof input)) abort (); return input[toknum++]; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { yydebug = 1; return yyparse (); } ]]) AT_BISON_CHECK([-o input.c input.y]) AT_COMPILE([input]) AT_PARSER_CHECK([./input], 1, [[<*>//e destructor. <*>//e destructor. 'd' destructor. 'c' destructor. destructor. <*>//e destructor. ]], [[Starting parse Entering state 0 Reading a token: Next token is token 'a' (<*>//e printer) Shifting token 'a' (<*>//e printer) Entering state 1 Reading a token: Next token is token 'b' ( printer) Shifting token 'b' ( printer) Entering state 3 Reading a token: Next token is token 'c' ('c' printer) Shifting token 'c' ('c' printer) Entering state 5 Reading a token: Next token is token 'd' ('d' printer) Shifting token 'd' ('d' printer) Entering state 6 Reading a token: Next token is token 'e' (<*>//e printer) Shifting token 'e' (<*>//e printer) Entering state 7 Reading a token: Next token is token 'f' (<*>//e printer) Shifting token 'f' (<*>//e printer) Entering state 8 Reading a token: Now at end of input. syntax error, unexpected $end, expecting 'g' Error: popping token 'f' (<*>//e printer) Stack now 0 1 3 5 6 7 Error: popping token 'e' (<*>//e printer) Stack now 0 1 3 5 6 Error: popping token 'd' ('d' printer) Stack now 0 1 3 5 Error: popping token 'c' ('c' printer) Stack now 0 1 3 Error: popping token 'b' ( printer) Stack now 0 1 Error: popping token 'a' (<*>//e printer) Stack now 0 Cleanup: discarding lookahead token $end () Stack now 0 ]]) AT_CLEANUP ## ------------------------------------------------------------- ## ## Default %printer and %destructor for user-defined end token. ## ## ------------------------------------------------------------- ## AT_SETUP([Default %printer and %destructor for user-defined end token]) # _AT_CHECK_DEFAULT_PRINTER_AND_DESTRUCTOR_FOR_END_TOKEN(TYPED) # ----------------------------------------------------------------------------- m4_define([_AT_CHECK_DEFAULT_PRINTER_AND_DESTRUCTOR_FOR_END_TOKEN], [m4_if($1, 0, [m4_pushdef([kind], []) m4_pushdef([not_kind], [*])], [m4_pushdef([kind], [*]) m4_pushdef([not_kind], [])]) AT_DATA_GRAMMAR([[input]]$1[[.y]], [[%define parse.error verbose %debug %locations %initial-action { @$.first_line = @$.last_line = 1; @$.first_column = @$.last_column = 1; } %{ # include # include static void yyerror (const char *msg); static int yylex (void); # define USE(SYM) %} %destructor { fprintf (yyoutput, "<]]not_kind[[> destructor should not be called.\n"); } <]]not_kind[[> %token END 0 %printer { fprintf (yyoutput, "<]]kind[[> for '%c' @ %d", $$, @$.first_column); } <]]kind[[> %destructor { fprintf (stdout, "<]]kind[[> for '%c' @ %d.\n", $$, @$.first_column); } <]]kind[[> %printer { fprintf (yyoutput, "<]]not_kind[[> printer should not be called.\n"); } <]]not_kind[[> ]]m4_if($1, 0, [[[ ]]], [[[%union { char tag; } %type start END]]])[[ %% start: { $$ = 'S'; } ; %% static int yylex (void) { static int called; if (called++) abort (); yylval]]m4_if($1, 0,, [[[.tag]]])[[ = 'E'; yylloc.first_line = yylloc.last_line = 1; yylloc.first_column = yylloc.last_column = 1; return 0; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { yydebug = 1; return yyparse (); } ]]) AT_BISON_CHECK([-o input$1.c input$1.y]) AT_COMPILE([input$1]) AT_PARSER_CHECK([./input$1], 0, [[<]]kind[[> for 'E' @ 1. <]]kind[[> for 'S' @ 1. ]], [[Starting parse Entering state 0 Reducing stack by rule 1 (line 46): -> $$ = nterm start (1.1-1.1: <]]kind[[> for 'S' @ 1) Stack now 0 Entering state 1 Reading a token: Now at end of input. Shifting token END (1.1-1.1: <]]kind[[> for 'E' @ 1) Entering state 2 Stack now 0 1 2 Cleanup: popping token END (1.1-1.1: <]]kind[[> for 'E' @ 1) Cleanup: popping nterm start (1.1-1.1: <]]kind[[> for 'S' @ 1) ]]) m4_popdef([kind]) m4_popdef([not_kind]) ]) _AT_CHECK_DEFAULT_PRINTER_AND_DESTRUCTOR_FOR_END_TOKEN(0) _AT_CHECK_DEFAULT_PRINTER_AND_DESTRUCTOR_FOR_END_TOKEN(1) AT_CLEANUP ## ------------------------------------------------------------------ ## ## Default %printer and %destructor are not for error or $undefined. ## ## ------------------------------------------------------------------ ## AT_SETUP([Default %printer and %destructor are not for error or $undefined]) # If Bison were to apply the default %printer and %destructor to the error # token or to $undefined: # - For the error token: # - It would generate warnings for unused $n. # - It would invoke the %printer and %destructor on the error token's # semantic value, which would be initialized from the lookahead, which # would be destroyed separately. # - For $undefined, who knows what the semantic value would be. AT_DATA_GRAMMAR([[input.y]], [[%debug %{ # include # include static void yyerror (const char *msg); static int yylex (void); # define USE(SYM) %} %printer { fprintf (yyoutput, "'%c'", $$); } <> <*> %destructor { fprintf (stderr, "DESTROY '%c'\n", $$); } <> <*> %% start: { $$ = 'S'; } /* In order to reveal the problems that this bug caused during parsing, add * $2 to USE. */ | 'a' error 'b' 'c' { USE(($1, $3, $4)); $$ = 'S'; } ; %% static int yylex (void) { static char const input[] = "abd"; static size_t toknum; if (! (toknum < sizeof input)) abort (); yylval = input[toknum++]; return yylval; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { yydebug = 1; return yyparse (); } ]]) AT_BISON_CHECK([-o input.c input.y]) AT_COMPILE([input]) AT_PARSER_CHECK([./input], [1], [], [[Starting parse Entering state 0 Reading a token: Next token is token 'a' ('a') Shifting token 'a' ('a') Entering state 1 Reading a token: Next token is token 'b' ('b') syntax error Shifting token error () Entering state 3 Next token is token 'b' ('b') Shifting token 'b' ('b') Entering state 5 Reading a token: Next token is token $undefined () Error: popping token 'b' ('b') DESTROY 'b' Stack now 0 1 3 Error: popping token error () Stack now 0 1 Shifting token error () Entering state 3 Next token is token $undefined () Error: discarding token $undefined () Error: popping token error () Stack now 0 1 Shifting token error () Entering state 3 Reading a token: Now at end of input. Cleanup: discarding lookahead token $end () Stack now 0 1 3 Cleanup: popping token error () Cleanup: popping token 'a' ('a') DESTROY 'a' ]]) AT_CLEANUP ## ------------------------------------------------------ ## ## Default %printer and %destructor are not for $accept. ## ## ------------------------------------------------------ ## AT_SETUP([Default %printer and %destructor are not for $accept]) # If YYSTYPE is a union and Bison were to apply the default %printer and # %destructor to $accept: # - The %printer and %destructor code generated for $accept would always be # dead code because $accept is currently never shifted onto the stack. # - $$ for $accept would always be of type YYSTYPE because it's not possible # to declare `%type $accept'. (Also true for $undefined.) # - Thus, the compiler might complain that the user code assumes the wrong # type for $$ since the code might assume the type associated with a # specific union field, which is especially reasonable in C++ since that # type may be a base type. This test case checks for this problem. (Also # true for $undefined and the error token, so there are three warnings for # %printer and three for %destructor.) AT_DATA_GRAMMAR([[input.y]], [[%debug /* So that %printer is actually compiled. */ %{ # include # include static void yyerror (const char *msg); static int yylex (void); # define USE(SYM) %} %printer { char chr = $$; fprintf (yyoutput, "'%c'", chr); } <> <*> %destructor { char chr = $$; fprintf (stderr, "DESTROY '%c'\n", chr); } <> <*> %union { char chr; } %type start %% start: { USE($$); } ; %% static int yylex (void) { static int called; if (called++) abort (); return 0; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { return yyparse (); } ]]) AT_BISON_CHECK([-o input.c input.y]) AT_COMPILE([input]) AT_CLEANUP ## ------------------------------------------------------ ## ## Default %printer and %destructor for mid-rule values. ## ## ------------------------------------------------------ ## AT_SETUP([Default %printer and %destructor for mid-rule values]) AT_DATA_GRAMMAR([[input.y]], [[%debug /* So that %printer is actually compiled. */ %{ # include # include static void yyerror (const char *msg); static int yylex (void); # define USE(SYM) # define YYLTYPE int # define YYLLOC_DEFAULT(Current, Rhs, N) (void)(Rhs) # define YY_LOCATION_PRINT(File, Loc) %} %printer { fprintf (yyoutput, "%d", @$); } <> %destructor { fprintf (stderr, "DESTROY %d\n", @$); } <> %printer { fprintf (yyoutput, "<*> printer should not be called"); } <*> %destructor { fprintf (yyoutput, "<*> destructor should not be called"); } <*> %% start: { @$ = 1; } // Not set or used. { USE ($$); @$ = 2; } // Both set and used. { USE ($$); @$ = 3; } // Only set. { @$ = 4; } // Only used. 'c' { USE (($$, $2, $4, $5)); @$ = 0; } ; %% static int yylex (void) { static int called; if (called++) abort (); return 0; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { yydebug = 1; return yyparse (); } ]]) AT_BISON_CHECK([-o input.c input.y], 0,, [[input.y:33.3-23: warning: unset value: $$ input.y:30.3-35.37: warning: unused value: $3 ]]) AT_COMPILE([input]) AT_PARSER_CHECK([./input], 1,, [[Starting parse Entering state 0 Reducing stack by rule 1 (line 30): -> $$ = nterm $@1 (: ) Stack now 0 Entering state 2 Reducing stack by rule 2 (line 31): -> $$ = nterm @2 (: 2) Stack now 0 2 Entering state 4 Reducing stack by rule 3 (line 32): -> $$ = nterm @3 (: 3) Stack now 0 2 4 Entering state 5 Reducing stack by rule 4 (line 33): -> $$ = nterm @4 (: 4) Stack now 0 2 4 5 Entering state 6 Reading a token: Now at end of input. syntax error Error: popping nterm @4 (: 4) DESTROY 4 Stack now 0 2 4 5 Error: popping nterm @3 (: 3) DESTROY 3 Stack now 0 2 4 Error: popping nterm @2 (: 2) DESTROY 2 Stack now 0 2 Error: popping nterm $@1 (: ) Stack now 0 Cleanup: discarding lookahead token $end (: ) Stack now 0 ]]) AT_CLEANUP ## ----------------------- ## ## @$ implies %locations. ## ## ----------------------- ## # Bison once forgot to check for @$ in actions other than semantic actions. # AT_CHECK_ACTION_LOCATIONS(ACTION-DIRECTIVE) # ------------------------------------------------------- m4_define([AT_CHECK_ACTION_LOCATIONS], [AT_SETUP([[@$ in ]$1[ implies %locations]]) AT_DATA_GRAMMAR([[input.y]], [[%code { #include static int yylex (void); static void yyerror (char const *msg); } %debug ]$1[ { printf ("%d\n", @$.first_line); } ]m4_if($1, [%initial-action], [], [[start]])[ %% start: ; %% static int yylex (void) { return 0; } static void yyerror (char const *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { return yyparse (); } ]]) AT_BISON_CHECK([[-o input.c input.y]]) AT_COMPILE([[input]]) AT_CLEANUP]) AT_CHECK_ACTION_LOCATIONS([[%initial-action]]) AT_CHECK_ACTION_LOCATIONS([[%destructor]]) AT_CHECK_ACTION_LOCATIONS([[%printer]]) ## ----------------------------------------------- ## ## Fix user actions without a trailing semicolon. ## ## ----------------------------------------------- ## AT_SETUP([[Fix user actions without a trailing semicolon]]) # This feature is undocumented, but we accidentally broke it in 2.3a, # and there was a complaint at: # . AT_DATA([input.y], [[%% start: test2 test1 test0 testc; test2 : 'a' { semi; /* TEST:N:2 */ } | 'b' { if (0) {no_semi} /* TEST:N:2 */ } | 'c' { if (0) {semi;} /* TEST:N:2 */ } | 'd' { semi; no_semi /* TEST:Y:2 */ } | 'e' { semi(); no_semi() /* TEST:Y:2 */ } | 'f' { semi[]; no_semi[] /* TEST:Y:2 */ } | 'g' { semi++; no_semi++ /* TEST:Y:2 */ } | 'h' { {no_semi} no_semi /* TEST:Y:2 */ } | 'i' { {semi;} no_semi /* TEST:Y:2 */ } ; test1 : 'a' { semi; // TEST:N:1 ; } | 'b' { if (0) {no_semi} // TEST:N:1 ; } | 'c' { if (0) {semi;} // TEST:N:1 ; } | 'd' { semi; no_semi // TEST:Y:1 ; } | 'e' { semi(); no_semi() // TEST:Y:1 ; } | 'f' { semi[]; no_semi[] // TEST:Y:1 ; } | 'g' { semi++; no_semi++ // TEST:Y:1 ; } | 'h' { {no_semi} no_semi // TEST:Y:1 ; } | 'i' { {semi;} no_semi // TEST:Y:1 ; } ; test0 : 'a' { semi; // TEST:N:1 {} } | 'b' { if (0) {no_semi} // TEST:N:1 {} } | 'c' { if (0) {semi;} // TEST:N:1 {} } | 'd' { semi; no_semi // TEST:Y:1 {} } | 'e' { semi(); no_semi() // TEST:Y:1 {} } | 'f' { semi[]; no_semi[] // TEST:Y:1 {} } | 'g' { semi++; no_semi++ // TEST:Y:1 {} } | 'h' { {no_semi} no_semi // TEST:Y:1 {} } | 'i' { {semi;} no_semi // TEST:Y:1 {} } ; testc : 'a' { #define TEST_MACRO_N \ []"broken\" $ @ $$ @$ [];\ string;"} | 'b' { no_semi #define TEST_MACRO_N \ []"broken\" $ @ $$ @$ [];\ string;"} ]]) AT_BISON_CHECK([[-o input.c input.y]], [0], [], [[input.y:8.48: warning: a ';' might be needed at the end of action code input.y:8.48: warning: future versions of Bison will not add the ';' input.y:9.48: warning: a ';' might be needed at the end of action code input.y:9.48: warning: future versions of Bison will not add the ';' input.y:10.48: warning: a ';' might be needed at the end of action code input.y:10.48: warning: future versions of Bison will not add the ';' input.y:11.48: warning: a ';' might be needed at the end of action code input.y:11.48: warning: future versions of Bison will not add the ';' input.y:12.48: warning: a ';' might be needed at the end of action code input.y:12.48: warning: future versions of Bison will not add the ';' input.y:13.48: warning: a ';' might be needed at the end of action code input.y:13.48: warning: future versions of Bison will not add the ';' input.y:20.1: warning: a ';' might be needed at the end of action code input.y:20.1: warning: future versions of Bison will not add the ';' input.y:21.1: warning: a ';' might be needed at the end of action code input.y:21.1: warning: future versions of Bison will not add the ';' input.y:22.1: warning: a ';' might be needed at the end of action code input.y:22.1: warning: future versions of Bison will not add the ';' input.y:23.1: warning: a ';' might be needed at the end of action code input.y:23.1: warning: future versions of Bison will not add the ';' input.y:24.1: warning: a ';' might be needed at the end of action code input.y:24.1: warning: future versions of Bison will not add the ';' input.y:25.1: warning: a ';' might be needed at the end of action code input.y:25.1: warning: future versions of Bison will not add the ';' input.y:31.1: warning: a ';' might be needed at the end of action code input.y:31.1: warning: future versions of Bison will not add the ';' input.y:32.1: warning: a ';' might be needed at the end of action code input.y:32.1: warning: future versions of Bison will not add the ';' input.y:33.1: warning: a ';' might be needed at the end of action code input.y:33.1: warning: future versions of Bison will not add the ';' input.y:34.1: warning: a ';' might be needed at the end of action code input.y:34.1: warning: future versions of Bison will not add the ';' input.y:35.1: warning: a ';' might be needed at the end of action code input.y:35.1: warning: future versions of Bison will not add the ';' input.y:36.1: warning: a ';' might be needed at the end of action code input.y:36.1: warning: future versions of Bison will not add the ';' ]]) AT_MATCHES_CHECK([input.c], [[/\* TEST:N:2 \*/ \}$]], [[3]]) AT_MATCHES_CHECK([input.c], [[/\* TEST:Y:2 \*/ ;\}$]], [[6]]) AT_MATCHES_CHECK([input.c], [[// TEST:N:1 [;{}]*\n\}$]], [[6]]) AT_MATCHES_CHECK([input.c], [[// TEST:Y:1 [;{}]*\n;\}$]], [[12]]) AT_MATCHES_CHECK([input.c], [[#define TEST_MACRO_N \\\n\[\]"broken\\" \$ \@ \$\$ \@\$ \[\];\\\nstring;"\}]], [[2]]) AT_CLEANUP ## -------------------------------------------------- ## ## Destroying lookahead assigned by semantic action. ## ## -------------------------------------------------- ## AT_SETUP([[Destroying lookahead assigned by semantic action]]) AT_DATA_GRAMMAR([input.y], [[ %code { #include #include static void yyerror (char const *); static int yylex (void); #define USE(Var) } %destructor { fprintf (stderr, "'a' destructor\n"); } 'a' %destructor { fprintf (stderr, "'b' destructor\n"); } 'b' %% // In a previous version of Bison, yychar assigned by the semantic // action below was not translated into yytoken before the lookahead was // discarded and thus before its destructor (selected according to // yytoken) was called in order to return from yyparse. This would // happen even if YYACCEPT was performed in a later semantic action as // long as only consistent states with default reductions were visited // in between. However, we leave YYACCEPT in the same semantic action // for this test in order to show that skeletons cannot simply translate // immediately after every semantic action because a semantic action // that has set yychar might not always return normally. Instead, // skeletons must translate before every use of yytoken. start: 'a' accept { USE($1); } ; accept: /*empty*/ { assert (yychar == YYEMPTY); yychar = 'b'; YYACCEPT; } ; %% static void yyerror (char const *msg) { fprintf (stderr, "%s\n", msg); } static int yylex (void) { static char const *input = "a"; return *input++; } int main (void) { return yyparse (); } ]]) AT_BISON_CHECK([[-o input.c input.y]]) AT_COMPILE([[input]]) AT_PARSER_CHECK([[./input]], [[0]], [], [['b' destructor 'a' destructor ]]) AT_CLEANUP ## ---------- ## ## YYBACKUP. ## ## ---------- ## AT_SETUP([[YYBACKUP]]) AT_DATA_GRAMMAR([input.y], [[ %error-verbose %debug %pure-parser %code { # include # include # include static void yyerror (const char *msg); static int yylex (YYSTYPE *yylval); } %% input: exp exp {} ; exp: 'a' { printf ("a: %d\n", $1); } | 'b' { YYBACKUP('a', 123); } | 'c' 'd' { YYBACKUP('a', 456); } ; %% static int yylex (YYSTYPE *yylval) { static char const input[] = "bcd"; static size_t toknum; assert (toknum < sizeof input); *yylval = (toknum + 1) * 10; return input[toknum++]; } static void yyerror (const char *msg) { fprintf (stderr, "%s\n", msg); } int main (void) { yydebug = !!getenv("YYDEBUG"); return yyparse (); } ]]) AT_BISON_CHECK([[-o input.c input.y]]) AT_COMPILE([[input]]) AT_PARSER_CHECK([[./input]], [[0]], [[a: 123 a: 456 ]]) AT_CLEANUP