X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/1773ceee65c71da0db258fbc2039568c271a6341..916708d59e02812675ce2d85597b7e1f2d677213:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 4b7637e7..606ec569 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. + + Copyright (C) 2002, 2003 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -30,64 +31,54 @@ %{ #include "system.h" + #include "complain.h" -#include "muscle_tab.h" +#include "conflicts.h" #include "files.h" #include "getargs.h" -#include "output.h" -#include "symlist.h" #include "gram.h" +#include "muscle_tab.h" +#include "output.h" #include "reader.h" -#include "conflicts.h" +#include "symlist.h" /* Produce verbose syntax errors. */ #define YYERROR_VERBOSE 1 -#define YYLLOC_DEFAULT(Current, Rhs, N) \ -do { \ - if (N) \ - { \ - Current.first_column = Rhs[1].first_column; \ - Current.first_line = Rhs[1].first_line; \ - Current.last_column = Rhs[N].last_column; \ - Current.last_line = Rhs[N].last_line; \ - } \ - else \ - { \ - Current = Rhs[0]; \ - } \ -} while (0) + +#define YYLLOC_DEFAULT(Current, Rhs, N) (Current) = lloc_default (Rhs, N) +static YYLTYPE lloc_default (YYLTYPE const *, int); /* 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 (&yylloc, Msg) +static void gram_error (location const *, char const *); #define YYPRINT(File, Type, Value) \ print_token_value (File, Type, &Value) -static void print_token_value (FILE *file, int type, YYSTYPE const *value); +static void print_token_value (FILE *, int, YYSTYPE const *); -static void add_param (char const *, char const *, location_t); +static void add_param (char const *, char *, location); symbol_class current_class = unknown_sym; -struniq_t current_type = 0; -symbol_t *current_lhs; -location_t current_lhs_location; -assoc_t current_assoc; +uniqstr current_type = 0; +symbol *current_lhs; +location current_lhs_location; +assoc current_assoc; int current_prec = 0; -braced_code_t current_braced_code = action_braced_code; %} /* Only NUMBERS have a value. */ %union { - symbol_t *symbol; - symbol_list_t *list; + symbol *symbol; + symbol_list *list; int integer; - char *string; - assoc_t assoc; - struniq_t struniq; + char *chars; + assoc assoc; + uniqstr uniqstr; }; /* Define the tokens together with their human representation. */ @@ -99,10 +90,10 @@ braced_code_t current_braced_code = action_braced_code; %token PERCENT_NTERM "%nterm" %token PERCENT_TYPE "%type" -%token PERCENT_DESTRUCTOR "%destructor" -%token PERCENT_PRINTER "%printer" +%token PERCENT_DESTRUCTOR "%destructor {...}" +%token PERCENT_PRINTER "%printer {...}" -%token PERCENT_UNION "%union" +%token PERCENT_UNION "%union {...}" %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" @@ -125,12 +116,13 @@ braced_code_t current_braced_code = action_braced_code; PERCENT_EXPECT "%expect" PERCENT_FILE_PREFIX "%file-prefix" PERCENT_GLR_PARSER "%glr-parser" - PERCENT_LEX_PARAM "%lex-param" + PERCENT_LEX_PARAM "%lex-param {...}" PERCENT_LOCATIONS "%locations" PERCENT_NAME_PREFIX "%name-prefix" PERCENT_NO_LINES "%no-lines" + PERCENT_NONDETERMINISTIC_PARSER "%nondeterministic-parser" PERCENT_OUTPUT "%output" - PERCENT_PARSE_PARAM "%parse-param" + PERCENT_PARSE_PARAM "%parse-param {...}" PERCENT_PURE_PARSER "%pure-parser" PERCENT_SKELETON "%skeleton" PERCENT_START "%start" @@ -142,21 +134,26 @@ braced_code_t current_braced_code = action_braced_code; %token TYPE "type" %token EQUAL "=" %token SEMICOLON ";" -%token COLON ":" %token PIPE "|" %token ID "identifier" +%token ID_COLON "identifier:" %token PERCENT_PERCENT "%%" %token PROLOGUE "%{...%}" %token EPILOGUE "epilogue" %token BRACED_CODE "{...}" -%type STRING string_content - BRACED_CODE code_content action - PROLOGUE EPILOGUE -%type TYPE +%type STRING string_content + "%destructor {...}" + "%lex-param {...}" + "%parse-param {...}" + "%printer {...}" + "%union {...}" + BRACED_CODE action + PROLOGUE EPILOGUE +%type TYPE %type INT -%type ID symbol string_as_id +%type ID ID_COLON symbol string_as_id %type precedence_declarator %type symbols.1 %% @@ -172,7 +169,7 @@ input: declarations: /* Nothing */ -| declarations declaration semi_colon.opt +| declarations declaration ; declaration: @@ -184,18 +181,21 @@ declaration: | "%error-verbose" { error_verbose = 1; } | "%expect" INT { expected_conflicts = $2; } | "%file-prefix" "=" string_content { spec_file_prefix = $3; } -| "%glr-parser" { glr_parser = 1; } -| "%lex-param" code_content { add_param ("lex_param", $2, @2); } +| "%glr-parser" { nondeterministic_parser = true; + glr_parser = true; } +| "%lex-param {...}" { add_param ("lex_param", $1, @1); } | "%locations" { locations_flag = 1; } | "%name-prefix" "=" string_content { spec_name_prefix = $3; } | "%no-lines" { no_lines_flag = 1; } +| "%nondeterministic-parser" { nondeterministic_parser = true; } | "%output" "=" string_content { spec_outfile = $3; } -| "%parse-param" code_content { add_param ("parse_param", $2, @2); } -| "%pure-parser" { pure_parser = 1; } +| "%parse-param {...}" { add_param ("parse_param", $1, @1); } +| "%pure-parser" { pure_parser = true; } | "%skeleton" string_content { skeleton = $2; } | "%token-table" { token_table_flag = 1; } -| "%verbose" { report_flag = 1; } +| "%verbose" { report_flag = report_states; } | "%yacc" { yacc_flag = 1; } +| ";" ; grammar_declaration: @@ -205,31 +205,25 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%union" BRACED_CODE +| "%union {...}" { typed = 1; - MUSCLE_INSERT_INT ("stype_line", @2.first_line); - muscle_insert ("stype", $2); + MUSCLE_INSERT_INT ("stype_line", @1.start.line); + muscle_insert ("stype", $1); } -| "%destructor" - { current_braced_code = destructor_braced_code; } - BRACED_CODE symbols.1 +| "%destructor {...}" symbols.1 { - symbol_list_t *list; - for (list = $4; list; list = list->next) - symbol_destructor_set (list->sym, $3, @3); - symbol_list_free ($4); - current_braced_code = action_braced_code; + symbol_list *list; + for (list = $2; list; list = list->next) + symbol_destructor_set (list->sym, $1, @1); + symbol_list_free ($2); } -| "%printer" - { current_braced_code = printer_braced_code; } - BRACED_CODE symbols.1 +| "%printer {...}" symbols.1 { - symbol_list_t *list; - for (list = $4; list; list = list->next) - symbol_printer_set (list->sym, $3, list->location); - symbol_list_free ($4); - current_braced_code = action_braced_code; + symbol_list *list; + for (list = $2; list; list = list->next) + symbol_printer_set (list->sym, $1, list->location); + symbol_list_free ($2); } ; @@ -246,7 +240,7 @@ symbol_declaration: } | "%type" TYPE symbols.1 { - symbol_list_t *list; + symbol_list *list; for (list = $3; list; list = list->next) symbol_type_set (list->sym, $2, @2); symbol_list_free ($3); @@ -256,7 +250,7 @@ symbol_declaration: precedence_declaration: precedence_declarator type.opt symbols.1 { - symbol_list_t *list; + symbol_list *list; ++current_prec; for (list = $3; list; list = list->next) { @@ -321,9 +315,7 @@ symbol_def: /* One or more symbol definitions. */ symbol_defs.1: symbol_def - {;} | symbol_defs.1 symbol_def - {;} ; @@ -337,11 +329,10 @@ grammar: ; /* As a Bison extension, one can use the grammar declarations in the - body of the grammar. But to remain LALR(1), they must be ended - with a semi-colon. */ + body of the grammar. */ rules_or_grammar_declaration: rules -| grammar_declaration ";" +| grammar_declaration { if (yacc_flag) complain_at (@$, _("POSIX forbids declarations in the grammar")); @@ -350,11 +341,11 @@ rules_or_grammar_declaration: { yyerrok; } +| ";" ; rules: - ID ":" { current_lhs = $1; current_lhs_location = @1; } rhses.1 ";" - {;} + ID_COLON { current_lhs = $1; current_lhs_location = @1; } rhses.1 ; rhses.1: @@ -405,15 +396,6 @@ string_content: }; -/* A BRACED_CODE used for its contents. Strip the braces. */ -code_content: - BRACED_CODE - { - $$ = $1 + 1; - $$[strlen ($$) - 1] = '\0'; - }; - - epilogue.opt: /* Nothing. */ | "%%" EPILOGUE @@ -423,13 +405,40 @@ epilogue.opt: } ; -semi_colon.opt: - /* Nothing. */ -| ";" -; %% + + +/* 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; + loc.start = 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 const *decl, location_t loc) +add_param (char const *type, char *decl, location loc) { static char const alphanum[] = "0123456789" @@ -438,12 +447,16 @@ add_param (char const *type, char const *decl, location_t loc) "_"; char const *alpha = alphanum + 10; char const *name_start = NULL; - char const *p; + char *p; for (p = decl; *p; p++) if ((p == decl || ! strchr (alphanum, p[-1])) && strchr (alpha, p[0])) name_start = p; + /* Strip the surrounding '{' and '}'. */ + decl++; + p[-1] = '\0'; + if (! name_start) complain_at (loc, _("missing identifier in parameter declaration")); else @@ -466,9 +479,9 @@ add_param (char const *type, char const *decl, location_t loc) scanner_last_string_free (); } -/*------------------------------------------------------------------. -| When debugging the parser, display tokens' locations and values. | -`------------------------------------------------------------------*/ +/*----------------------------------------------------. +| When debugging the parser, display tokens' values. | +`----------------------------------------------------*/ static void print_token_value (FILE *file, int type, YYSTYPE const *value) @@ -485,17 +498,22 @@ print_token_value (FILE *file, int type, YYSTYPE const *value) break; case STRING: - fprintf (file, " = \"%s\"", value->string); + fprintf (file, " = \"%s\"", value->chars); break; case TYPE: - fprintf (file, " = <%s>", value->struniq); + fprintf (file, " = <%s>", value->uniqstr); break; case BRACED_CODE: + case PERCENT_DESTRUCTOR: + case PERCENT_LEX_PARAM: + case PERCENT_PARSE_PARAM: + case PERCENT_PRINTER: + case PERCENT_UNION: case PROLOGUE: case EPILOGUE: - fprintf (file, " = {{ %s }}", value->string); + fprintf (file, " = {{ %s }}", value->chars); break; default: @@ -504,8 +522,14 @@ print_token_value (FILE *file, int type, YYSTYPE const *value) } } -void -gram_error (location_t const *loc, char const *msg) +static void +gram_error (location const *loc, char const *msg) { complain_at (*loc, "%s", msg); } + +char const * +token_name (int type) +{ + return yytname[type]; +}