X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/2c5690250c9489f1ec3cd083ee754938bb47707f..a7ee59cfb466c53f7a9bed59df1bb2ee080146b3:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index d1ebbd67..f45b323c 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,5 +1,6 @@ -/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002 Free Software Foundation, Inc. +%{/* Bison Grammar Parser -*- C -*- + + Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -15,128 +16,186 @@ You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - 02111-1307 USA + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + 02110-1301 USA */ - -%debug -%defines -%locations -%pure-parser -// %error-verbose -%defines -%name-prefix="gram_" - -%{ +#include #include "system.h" -#include "muscle_tab.h" + +#include "complain.h" +#include "conflicts.h" #include "files.h" #include "getargs.h" -#include "output.h" #include "gram.h" +#include "muscle_tab.h" +#include "quotearg.h" #include "reader.h" -#include "conflicts.h" +#include "symlist.h" +#include "scan-gram.h" +#include "scan-code.h" +#include "strverscmp.h" -/* Produce verbose parse errors. */ -#define YYERROR_VERBOSE 1 +#define YYLLOC_DEFAULT(Current, Rhs, N) (Current) = lloc_default (Rhs, N) +static YYLTYPE lloc_default (YYLTYPE const *, int); -/* Pass the control structure to YYPARSE and YYLEX. */ -#define YYPARSE_PARAM gram_control -#define YYLEX_PARAM gram_control -/* YYPARSE receives GRAM_CONTROL as a void *. Provide a - correctly typed access to it. */ -#define yycontrol ((gram_control_t *) gram_control) +#define YY_LOCATION_PRINT(File, Loc) \ + location_print (File, Loc) -/* Request detailed parse error messages, and pass them to - GRAM_ERROR. */ +static void version_check (location const *loc, char const *version); + +/* Request detailed syntax error messages, and pass them to GRAM_ERROR. + FIXME: depends on the undocumented availability of YYLLOC. */ #undef yyerror #define yyerror(Msg) \ - gram_error (yycontrol, &yylloc, Msg) - -/* When debugging our pure parser, we want to see values and locations - of the tokens. */ -#define YYPRINT(File, Type, Value) \ - yyprint (File, &yylloc, Type, &Value) -static void yyprint (FILE *file, const location_t *loc, - int type, const yystype *value); - -symbol_class current_class = unknown_sym; -char *current_type = 0; -symbol_t *current_lhs; -associativity current_assoc; -int current_prec = 0; + gram_error (&yylloc, Msg) +static void gram_error (location const *, char const *); + +static char const *char_name (char); + +static void add_param (char const *, char *, location); + +static symbol_class current_class = unknown_sym; +static uniqstr current_type = 0; +static symbol *current_lhs; +static location current_lhs_location; +static int current_prec = 0; + +#ifdef UINT_FAST8_MAX +# define YYTYPE_UINT8 uint_fast8_t +#endif +#ifdef INT_FAST8_MAX +# define YYTYPE_INT8 int_fast8_t +#endif +#ifdef UINT_FAST16_MAX +# define YYTYPE_UINT16 uint_fast16_t +#endif +#ifdef INT_FAST16_MAX +# define YYTYPE_INT16 int_fast16_t +#endif %} +%debug +%verbose +%defines +%locations +%pure-parser +%error-verbose +%defines +%name-prefix="gram_" + +%initial-action +{ + /* Bison's grammar can initial empty locations, hence a default + location is needed. */ + boundary_set (&@$.start, current_file, 1, 0); + boundary_set (&@$.end, current_file, 1, 0); +} /* Only NUMBERS have a value. */ %union { - symbol_t *symbol; + symbol *symbol; + symbol_list *list; int integer; - char *string; - associativity assoc; + char *chars; + assoc assoc; + uniqstr uniqstr; + unsigned char character; }; -/* Define the tokens together with there human representation. */ -%token GRAM_EOF 0 "end of string" -%token STRING CHARACTER -%token INT - -%token PERCENT_TOKEN "%token" -%token PERCENT_NTERM "%nterm" -%token PERCENT_TYPE "%type" -%token PERCENT_UNION "%union" -%token PERCENT_EXPECT "%expect" -%token PERCENT_START "%start" -%token PERCENT_LEFT "%left" -%token PERCENT_RIGHT "%right" -%token PERCENT_NONASSOC "%nonassoc" -%token PERCENT_PREC "%prec" -%token PERCENT_VERBOSE "%verbose" -%token PERCENT_ERROR_VERBOSE "%error-verbose" - -%token PERCENT_OUTPUT "%output" -%token PERCENT_FILE_PREFIX "%file-prefix" -%token PERCENT_NAME_PREFIX "%name-prefix" - -%token PERCENT_DEFINE "%define" -%token PERCENT_PURE_PARSER "%pure-parser" - -%token PERCENT_DEFINES "%defines" - -%token PERCENT_YACC "%yacc" - -%token PERCENT_DEBUG "%debug" -%token PERCENT_LOCATIONS "%locations" -%token PERCENT_NO_LINES "%no-lines" -%token PERCENT_SKELETON "%skeleton" -%token PERCENT_TOKEN_TABLE "%token-table" - -%token TYPE -%token EQUAL "=" -%token SEMICOLON ";" -%token COLON ":" -%token PIPE "|" -%token ID "identifier" +/* Define the tokens together with their human representation. */ +%token GRAM_EOF 0 "end of file" +%token STRING "string" +%token INT "integer" + +%token PERCENT_TOKEN "%token" +%token PERCENT_NTERM "%nterm" + +%token PERCENT_TYPE "%type" +%token PERCENT_DESTRUCTOR "%destructor" +%token PERCENT_PRINTER "%printer" + +%token PERCENT_LEFT "%left" +%token PERCENT_RIGHT "%right" +%token PERCENT_NONASSOC "%nonassoc" + +%token PERCENT_PREC "%prec" +%token PERCENT_DPREC "%dprec" +%token PERCENT_MERGE "%merge" + + +/*----------------------. +| Global Declarations. | +`----------------------*/ + +%token + PERCENT_DEBUG "%debug" + PERCENT_DEFAULT_PREC "%default-prec" + PERCENT_DEFINE "%define" + PERCENT_DEFINES "%defines" + PERCENT_ERROR_VERBOSE "%error-verbose" + PERCENT_EXPECT "%expect" + PERCENT_EXPECT_RR "%expect-rr" + PERCENT_FILE_PREFIX "%file-prefix" + PERCENT_GLR_PARSER "%glr-parser" + PERCENT_INITIAL_ACTION "%initial-action" + PERCENT_LEX_PARAM "%lex-param" + PERCENT_LOCATIONS "%locations" + PERCENT_NAME_PREFIX "%name-prefix" + PERCENT_NO_DEFAULT_PREC "%no-default-prec" + PERCENT_NO_LINES "%no-lines" + PERCENT_NONDETERMINISTIC_PARSER + "%nondeterministic-parser" + PERCENT_OUTPUT "%output" + PERCENT_PARSE_PARAM "%parse-param" + PERCENT_PURE_PARSER "%pure-parser" + PERCENT_REQUIRE "%require" + PERCENT_SKELETON "%skeleton" + PERCENT_START "%start" + PERCENT_TOKEN_TABLE "%token-table" + PERCENT_VERBOSE "%verbose" + PERCENT_YACC "%yacc" +; + +%token BRACED_CODE "{...}" +%token CHAR "char" +%token EPILOGUE "epilogue" +%token EQUAL "=" +%token ID "identifier" +%token ID_COLON "identifier:" %token PERCENT_PERCENT "%%" -%token PROLOGUE EPILOGUE -%token BRACED_CODE +%token PIPE "|" +%token PROLOGUE "%{...%}" +%token SEMICOLON ";" +%token TYPE "type" + +%type CHAR +%printer { fputs (char_name ($$), stderr); } CHAR + +%type STRING string_content "{...}" PROLOGUE EPILOGUE +%printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } + STRING string_content +%printer { fprintf (stderr, "{\n%s\n}", $$); } "{...}" PROLOGUE EPILOGUE + +%type TYPE ID ID_COLON +%printer { fprintf (stderr, "<%s>", $$); } TYPE +%printer { fputs ($$, stderr); } ID +%printer { fprintf (stderr, "%s:", $$); } ID_COLON -%type CHARACTER TYPE STRING string_content - BRACED_CODE PROLOGUE EPILOGUE epilogue.opt action %type INT -%type ID symbol string_as_id -%type precedence_declarator +%printer { fprintf (stderr, "%d", $$); } INT +%type id id_colon symbol string_as_id +%printer { fprintf (stderr, "%s", $$->tag); } id symbol string_as_id +%printer { fprintf (stderr, "%s:", $$->tag); } id_colon + +%type precedence_declarator +%type symbols.1 %% -input: { LOCATION_RESET (yylloc); } +input: declarations "%%" grammar epilogue.opt - { - yycontrol->errcode = 0; - epilogue_set ($5, @5); - } ; @@ -151,22 +210,43 @@ declarations: declaration: grammar_declaration -| PROLOGUE { prologue_augment ($1, @1); } -| "%debug" { debug_flag = 1; } +| PROLOGUE { prologue_augment (translate_code ($1, @1), + @1); } +| "%debug" { debug_flag = true; } +| "%define" string_content + { + static char one[] = "1"; + muscle_insert ($2, one); + } | "%define" string_content string_content { muscle_insert ($2, $3); } -| "%defines" { defines_flag = 1; } -| "%error-verbose" { error_verbose = 1; } -| "%expect" INT { expected_conflicts = $2; } +| "%defines" { defines_flag = true; } +| "%error-verbose" { error_verbose = true; } +| "%expect" INT { expected_sr_conflicts = $2; } +| "%expect-rr" INT { expected_rr_conflicts = $2; } | "%file-prefix" "=" string_content { spec_file_prefix = $3; } -| "%locations" { locations_flag = 1; } +| "%glr-parser" + { + nondeterministic_parser = true; + glr_parser = true; + } +| "%initial-action" "{...}" + { + muscle_code_grow ("initial_action", translate_symbol_action ($2, @2), @2); + } +| "%lex-param" "{...}" { add_param ("lex_param", $2, @2); } +| "%locations" { locations_flag = true; } | "%name-prefix" "=" string_content { spec_name_prefix = $3; } -| "%no-lines" { no_lines_flag = 1; } +| "%no-lines" { no_lines_flag = true; } +| "%nondeterministic-parser" { nondeterministic_parser = true; } | "%output" "=" string_content { spec_outfile = $3; } -| "%pure-parser" { pure_parser = 1; } +| "%parse-param" "{...}" { add_param ("parse_param", $2, @2); } +| "%pure-parser" { pure_parser = true; } +| "%require" string_content { version_check (&@2, $2); } | "%skeleton" string_content { skeleton = $2; } -| "%token-table" { token_table_flag = 1; } -| "%verbose" { report_flag = 1; } -| "%yacc" { yacc_flag = 1; } +| "%token-table" { token_table_flag = true; } +| "%verbose" { report_flag = report_states; } +| "%yacc" { yacc_flag = true; } +| /*FIXME: Err? What is this horror doing here? */ ";" ; grammar_declaration: @@ -174,16 +254,68 @@ grammar_declaration: | symbol_declaration | "%start" symbol { - grammar_start_symbol_set ($2); + grammar_start_symbol_set ($2, @2); + } +| "%destructor" "{...}" symbols.1 + { + symbol_list *list; + const char *action = translate_symbol_action ($2, @2); + for (list = $3; list; list = list->next) + symbol_destructor_set (list->sym, action, @2); + symbol_list_free ($3); } -| "%union" BRACED_CODE semi_colon_opt +| "%printer" "{...}" symbols.1 + { + symbol_list *list; + const char *action = translate_symbol_action ($2, @2); + for (list = $3; list; list = list->next) + symbol_printer_set (list->sym, action, @2); + symbol_list_free ($3); + } +| "%default-prec" + { + default_prec = true; + } +| "%no-default-prec" + { + default_prec = false; + } +; + + +/*----------* + | %union. | + *----------*/ + +%token PERCENT_UNION "%union"; + +union_name: + /* Nothing. */ {} +| ID { muscle_code_grow ("union_name", $1, @1); } +; + +grammar_declaration: + "%union" union_name "{...}" { - typed = 1; - MUSCLE_INSERT_INT ("stype_line", @2.first_line); - muscle_insert ("stype", $2); + char const *body = $3; + + if (typed) + { + /* Concatenate the union bodies, turning the first one's + trailing '}' into '\n', and omitting the second one's '{'. */ + char *code = muscle_find ("stype"); + code[strlen (code) - 1] = '\n'; + body++; + } + + typed = true; + muscle_code_grow ("stype", body, @3); } ; + + + symbol_declaration: "%nterm" { current_class = nterm_sym; } symbol_defs.1 { @@ -195,17 +327,28 @@ symbol_declaration: current_class = unknown_sym; current_type = NULL; } -| "%type" TYPE {current_type = $2; } nterms_to_type.1 +| "%type" TYPE symbols.1 { - current_type = NULL; + symbol_list *list; + for (list = $3; list; list = list->next) + symbol_type_set (list->sym, $2, @2); + symbol_list_free ($3); } ; precedence_declaration: - precedence_declarator type.opt - { current_assoc = $1; ++current_prec; } - terms_to_prec.1 - { current_assoc = non_assoc; current_type = NULL; } + precedence_declarator type.opt symbols.1 + { + symbol_list *list; + ++current_prec; + for (list = $3; list; list = list->next) + { + symbol_type_set (list->sym, current_type, @2); + symbol_precedence_set (list->sym, current_prec, $1, @1); + } + symbol_list_free ($3); + current_type = NULL; + } ; precedence_declarator: @@ -215,28 +358,14 @@ precedence_declarator: ; type.opt: - /* Nothing. */ { current_type = NULL;} + /* Nothing. */ { current_type = NULL; } | TYPE { current_type = $1; } ; /* One or more nonterminals to be %typed. */ -nterms_to_type.1: - ID { symbol_type_set ($1, current_type); } -| nterms_to_type.1 ID { symbol_type_set ($2, current_type); } -; - -/* One or more symbols to be given a precedence/associativity. */ -terms_to_prec.1: - symbol - { - symbol_type_set ($1, current_type); - symbol_precedence_set ($1, current_prec, current_assoc); - } -| terms_to_prec.1 symbol - { - symbol_type_set ($2, current_type); - symbol_precedence_set ($2, current_prec, current_assoc); - } +symbols.1: + symbol { $$ = symbol_list_new ($1, @1); } +| symbols.1 symbol { $$ = symbol_list_prepend ($1, $2, @2); } ; /* One token definition. */ @@ -245,38 +374,36 @@ symbol_def: { current_type = $1; } -| ID +| id { - symbol_class_set ($1, current_class); - symbol_type_set ($1, current_type); + symbol_class_set ($1, current_class, @1, true); + symbol_type_set ($1, current_type, @1); } -| ID INT +| id INT { - symbol_class_set ($1, current_class); - symbol_type_set ($1, current_type); - symbol_user_token_number_set ($1, $2); + symbol_class_set ($1, current_class, @1, true); + symbol_type_set ($1, current_type, @1); + symbol_user_token_number_set ($1, $2, @2); } -| ID string_as_id +| id string_as_id { - symbol_class_set ($1, current_class); - symbol_type_set ($1, current_type); - symbol_make_alias ($1, $2); + symbol_class_set ($1, current_class, @1, true); + symbol_type_set ($1, current_type, @1); + symbol_make_alias ($1, $2, @$); } -| ID INT string_as_id +| id INT string_as_id { - symbol_class_set ($1, current_class); - symbol_type_set ($1, current_type); - symbol_user_token_number_set ($1, $2); - symbol_make_alias ($1, $3); + symbol_class_set ($1, current_class, @1, true); + symbol_type_set ($1, current_type, @1); + symbol_user_token_number_set ($1, $2, @2); + symbol_make_alias ($1, $3, @$); } ; /* One or more symbol definitions. */ symbol_defs.1: symbol_def - {;} | symbol_defs.1 symbol_def - {;} ; @@ -285,121 +412,217 @@ symbol_defs.1: `------------------------------------------*/ grammar: + rules_or_grammar_declaration +| grammar rules_or_grammar_declaration +; + +/* As a Bison extension, one can use the grammar declarations in the + body of the grammar. */ +rules_or_grammar_declaration: rules -| grammar rules +| grammar_declaration ";" +| error ";" + { + yyerrok; + } ; rules: - ID ":" { current_lhs = $1; } rhses.1 ";" - {;} + id_colon { current_lhs = $1; current_lhs_location = @1; } rhses.1 ; rhses.1: - rhs { grammar_rule_end (); } -| rhses.1 "|" rhs { grammar_rule_end (); } + rhs { grammar_current_rule_end (@1); } +| rhses.1 "|" rhs { grammar_current_rule_end (@3); } +| rhses.1 ";" ; rhs: /* Nothing. */ - { grammar_rule_begin (current_lhs); } + { grammar_current_rule_begin (current_lhs, current_lhs_location); } | rhs symbol - { grammar_current_rule_symbol_append ($2); } -| rhs action - { grammar_current_rule_action_append ($2, @2.first_line); } + { grammar_current_rule_symbol_append ($2, @2); } +| rhs "{...}" + { grammar_current_rule_action_append (gram_last_string, + gram_last_braced_code_loc); } | rhs "%prec" symbol - { grammar_current_rule_prec_set ($3); } + { grammar_current_rule_prec_set ($3, @3); } +| rhs "%dprec" INT + { grammar_current_rule_dprec_set ($3, @3); } +| rhs "%merge" TYPE + { grammar_current_rule_merge_set ($3, @3); } ; -symbol: - ID { $$ = $1; } -| string_as_id { $$ = $1; } -| CHARACTER { $$ = getsym ($1); } + +/*---------------* + | Identifiers. | + *---------------*/ + +/* Identifiers are returned as uniqstr values by the scanner. + Depending on their use, we may need to make them genuine symbols. */ + +id: + ID + { $$ = symbol_get ($1, @1); } +| CHAR + { + $$ = symbol_get (char_name ($1), @1); + symbol_class_set ($$, token_sym, @1, false); + symbol_user_token_number_set ($$, $1, @1); + } ; -action: - BRACED_CODE - { $$ = $1; } +id_colon: + ID_COLON { $$ = symbol_get ($1, @1); } ; -/* A string used as an ID: we have to keep the quotes. */ + +symbol: + id +| string_as_id +; + +/* A string used as an ID: quote it. */ string_as_id: STRING { - $$ = getsym ($1); - symbol_class_set ($$, token_sym); + $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1); + symbol_class_set ($$, token_sym, @1, false); } ; -/* A string used for its contents. Strip the quotes. */ +/* A string used for its contents. Don't quote it. */ string_content: STRING - { - $$ = $1 + 1; - $$[strlen ($$) - 1] = '\0'; - }; + { $$ = $1; } +; epilogue.opt: /* Nothing. */ - { - $$ = xstrdup (""); - } | "%%" EPILOGUE { - $$ = $2; + muscle_code_grow ("epilogue", translate_code ($2, @2), @2); + gram_scanner_last_string_free (); } ; -semi_colon_opt: - /* Nothing. */ -| ";" -; %% -/*------------------------------------------------------------------. -| When debugging the parser, display tokens' locations and values. | -`------------------------------------------------------------------*/ + + +/* Return the location of the left-hand side of a rule whose + right-hand side is RHS[1] ... RHS[N]. Ignore empty nonterminals in + the right-hand side, and return an empty location equal to the end + boundary of RHS[0] if the right-hand side is empty. */ + +static YYLTYPE +lloc_default (YYLTYPE const *rhs, int n) +{ + int i; + YYLTYPE loc; + + /* SGI MIPSpro 7.4.1m miscompiles "loc.start = loc.end = rhs[n].end;". + The bug is fixed in 7.4.2m, but play it safe for now. */ + loc.start = rhs[n].end; + loc.end = rhs[n].end; + + /* Ignore empty nonterminals the start of the the right-hand side. + Do not bother to ignore them at the end of the right-hand side, + since empty nonterminals have the same end as their predecessors. */ + for (i = 1; i <= n; i++) + if (! equal_boundaries (rhs[i].start, rhs[i].end)) + { + loc.start = rhs[i].start; + break; + } + + return loc; +} + + +/* Add a lex-param or a parse-param (depending on TYPE) with + declaration DECL and location LOC. */ + +static void +add_param (char const *type, char *decl, location loc) +{ + static char const alphanum[26 + 26 + 1 + 10] = + "abcdefghijklmnopqrstuvwxyz" + "ABCDEFGHIJKLMNOPQRSTUVWXYZ" + "_" + "0123456789"; + char const *name_start = NULL; + char *p; + + /* Stop on last actual character. */ + for (p = decl; p[1]; p++) + if ((p == decl + || ! memchr (alphanum, p[-1], sizeof alphanum)) + && memchr (alphanum, p[0], sizeof alphanum - 10)) + name_start = p; + + /* Strip the surrounding '{' and '}', and any blanks just inside + the braces. */ + while (*--p == ' ' || *p == '\t') + continue; + p[1] = '\0'; + while (*++decl == ' ' || *decl == '\t') + continue; + + if (! name_start) + complain_at (loc, _("missing identifier in parameter declaration")); + else + { + char *name; + size_t name_len; + + for (name_len = 1; + memchr (alphanum, name_start[name_len], sizeof alphanum); + name_len++) + continue; + + name = xmalloc (name_len + 1); + memcpy (name, name_start, name_len); + name[name_len] = '\0'; + muscle_pair_list_grow (type, decl, name); + free (name); + } + + gram_scanner_last_string_free (); +} static void -yyprint (FILE *file, - const location_t *loc, int type, const yystype *value) +version_check (location const *loc, char const *version) { - fputs (" (", file); - LOCATION_PRINT (file, *loc); - fputs (")", file); - switch (type) + if (strverscmp (version, PACKAGE_VERSION) > 0) { - case CHARACTER: - fprintf (file, " = '%s'", value->string); - break; - - case ID: - fprintf (file, " = %s", value->symbol->tag); - break; - - case INT: - fprintf (file, " = %d", value->integer); - break; - - case STRING: - fprintf (file, " = \"%s\"", value->string); - break; - - case TYPE: - fprintf (file, " = <%s>", value->string); - break; - - case BRACED_CODE: - case PROLOGUE: - case EPILOGUE: - fprintf (file, " = {{ %s }}", value->string); - break; + complain_at (*loc, "require bison %s, but have %s", + version, PACKAGE_VERSION); + exit (63); } } -void -gram_error (gram_control_t *control ATTRIBUTE_UNUSED, - location_t *yylloc, const char *msg) +static void +gram_error (location const *loc, char const *msg) +{ + complain_at (*loc, "%s", msg); +} + +char const * +token_name (int type) { - LOCATION_PRINT (stderr, *yylloc); - fprintf (stderr, ": %s\n", msg); + return yytname[YYTRANSLATE (type)]; +} + +static char const * +char_name (char c) +{ + if (c == '\'') + return "'\\''"; + else + { + char buf[4]; + buf[0] = '\''; buf[1] = c; buf[2] = '\''; buf[3] = '\0'; + return quotearg_style (escape_quoting_style, buf); + } }