X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/e9955c83734d0a545d7822a1feb9c4a8038a62cb..cce7a5f4230618ddc7e256e8b83b7f0d84ff5909:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 3cff05d1..c5d8024f 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -24,44 +24,47 @@ %defines %locations %pure-parser -%error-verbose +// %error-verbose %defines %name-prefix="gram_" %{ #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 "output.h" #include "reader.h" -#include "conflicts.h" +#include "symlist.h" + +/* Produce verbose syntax errors. */ +#define YYERROR_VERBOSE 1 -/* 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 YYLLOC_DEFAULT(Current, Rhs, N) (Current) = lloc_default (Rhs, N) +static YYLTYPE lloc_default (YYLTYPE const *, int); -/* Request detailed parse error messages, and pass them to - GRAM_ERROR. */ +/* 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) + gram_error (&yylloc, Msg) +static void gram_error (location const *, char const *); -/* 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 yyltype *loc, - int type, const yystype *value); + print_token_value (File, Type, &Value) +static void print_token_value (FILE *, int, YYSTYPE const *); + +static void add_param (char const *, char *, location); symbol_class current_class = unknown_sym; -char *current_type = 0; -symbol_t *current_lhs; -associativity current_assoc; +uniqstr current_type = 0; +symbol *current_lhs; +location current_lhs_location; +assoc current_assoc; int current_prec = 0; %} @@ -69,162 +72,210 @@ int current_prec = 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; }; -/* 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" -%token PERCENT_PERCENT "%%" -%token PROLOGUE EPILOGUE -%token BRACED_CODE +/* 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_UNION "%union {...}" + +%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_DEFINE "%define" + PERCENT_DEFINES "%defines" + PERCENT_ERROR_VERBOSE "%error-verbose" + PERCENT_EXPECT "%expect" + PERCENT_FILE_PREFIX "%file-prefix" + PERCENT_GLR_PARSER "%glr-parser" + PERCENT_LEX_PARAM "%lex-param {...}" + PERCENT_LOCATIONS "%locations" + PERCENT_NAME_PREFIX "%name-prefix" + PERCENT_NO_LINES "%no-lines" + PERCENT_OUTPUT "%output" + PERCENT_PARSE_PARAM "%parse-param {...}" + PERCENT_PURE_PARSER "%pure-parser" + PERCENT_SKELETON "%skeleton" + PERCENT_START "%start" + PERCENT_TOKEN_TABLE "%token-table" + PERCENT_VERBOSE "%verbose" + PERCENT_YACC "%yacc" +; -%type CHARACTER TYPE BRACED_CODE PROLOGUE EPILOGUE epilogue.opt action STRING string_content +%token TYPE "type" +%token EQUAL "=" +%token SEMICOLON ";" +%token PIPE "|" +%token ID "identifier" +%token ID_COLON "identifier:" +%token PERCENT_PERCENT "%%" +%token PROLOGUE "%{...%}" +%token EPILOGUE "epilogue" +%token BRACED_CODE "{...}" + + +%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 precedence_directive +%type ID ID_COLON symbol string_as_id +%type precedence_declarator +%type symbols.1 %% -input: { LOCATION_RESET (yylloc); } - directives "%%" gram epilogue.opt - { - yycontrol->errcode = 0; - epilogue_set ($5, @5.first_line); - } + +input: + declarations "%%" grammar epilogue.opt ; -directives: + + /*------------------------------------. + | Declarations: before the first %%. | + `------------------------------------*/ + +declarations: /* Nothing */ -| directives directive +| declarations declaration ; -directive: - grammar_directives -| PROLOGUE { prologue_augment ($1, @1.first_line); } +declaration: + grammar_declaration +| PROLOGUE { prologue_augment ($1, @1); } | "%debug" { debug_flag = 1; } | "%define" string_content string_content { muscle_insert ($2, $3); } | "%defines" { defines_flag = 1; } | "%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 {...}" { add_param ("lex_param", $1, @1); } | "%locations" { locations_flag = 1; } | "%name-prefix" "=" string_content { spec_name_prefix = $3; } | "%no-lines" { no_lines_flag = 1; } | "%output" "=" string_content { spec_outfile = $3; } +| "%parse-param {...}" { add_param ("parse_param", $1, @1); } | "%pure-parser" { pure_parser = 1; } | "%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_directives: - precedence_directives -| "%nterm" { current_class = nterm_sym; } symbol_defs.1 +grammar_declaration: + precedence_declaration +| symbol_declaration +| "%start" symbol { - current_class = unknown_sym; - current_type = NULL; + grammar_start_symbol_set ($2, @2); } -| "%start" symbol +| "%union {...}" { - grammar_start_symbol_set ($2); + typed = 1; + MUSCLE_INSERT_INT ("stype_line", @1.start.line); + muscle_insert ("stype", $1); } -| "%token" { current_class = token_sym; } symbol_defs.1 +| "%destructor {...}" symbols.1 + { + symbol_list *list; + for (list = $2; list; list = list->next) + symbol_destructor_set (list->sym, $1, @1); + symbol_list_free ($2); + } +| "%printer {...}" symbols.1 + { + symbol_list *list; + for (list = $2; list; list = list->next) + symbol_printer_set (list->sym, $1, list->location); + symbol_list_free ($2); + } +; + +symbol_declaration: + "%nterm" { current_class = nterm_sym; } symbol_defs.1 { current_class = unknown_sym; current_type = NULL; } -| "%type" TYPE {current_type = $2; } nterms_to_type.1 +| "%token" { current_class = token_sym; } symbol_defs.1 { + current_class = unknown_sym; current_type = NULL; } -| "%union" BRACED_CODE semi_colon_opt +| "%type" TYPE symbols.1 { - typed = 1; - MUSCLE_INSERT_INT ("stype_line", @2.first_line); - muscle_insert ("stype", $2); + symbol_list *list; + for (list = $3; list; list = list->next) + symbol_type_set (list->sym, $2, @2); + symbol_list_free ($3); } ; -precedence_directives: - precedence_directive type.opt - { current_assoc = $1; ++current_prec; } - terms_to_prec.1 - { current_assoc = non_assoc; current_type = NULL; } +precedence_declaration: + 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_directive: +precedence_declarator: "%left" { $$ = left_assoc; } | "%right" { $$ = right_assoc; } | "%nonassoc" { $$ = non_assoc; } ; type.opt: - /* Nothing. */ { current_type = NULL;} + /* Nothing. */ { current_type = NULL; } | TYPE { current_type = $1; } ; /* One or more nonterminals to be %typed. */ -nterms_to_type.1: - ID { symbol_type_set ($1, current_type); } -| nterms_to_type.1 ID { symbol_type_set ($2, current_type); } -; -/* One or more symbols to be given a precedence/associativity. */ -terms_to_prec.1: - symbol - { - symbol_type_set ($1, current_type); - symbol_precedence_set ($1, current_prec, current_assoc); - } -| terms_to_prec.1 symbol - { - symbol_type_set ($2, current_type); - symbol_precedence_set ($2, current_prec, current_assoc); - } +symbols.1: + symbol { $$ = symbol_list_new ($1, @1); } +| symbols.1 symbol { $$ = symbol_list_prepend ($1, $2, @2); } ; - /* One token definition. */ symbol_def: TYPE @@ -233,68 +284,89 @@ symbol_def: } | ID { - symbol_class_set ($1, current_class); - symbol_type_set ($1, current_type); + symbol_class_set ($1, current_class, @1); + symbol_type_set ($1, current_type, @1); } | 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); + symbol_type_set ($1, current_type, @1); + symbol_user_token_number_set ($1, $2, @2); } | 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); + symbol_type_set ($1, current_type, @1); + symbol_make_alias ($1, $2, @$); } | 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); + 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 - {;} ; -gram: + + /*------------------------------------------. + | The grammar section: between the two %%. | + `------------------------------------------*/ + +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 -| gram rules +| grammar_declaration + { + if (yacc_flag) + complain_at (@$, _("POSIX forbids declarations in the grammar")); + } +| 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_rule_end (@1); } +| rhses.1 "|" rhs { grammar_rule_end (@3); } ; rhs: /* Nothing. */ - { grammar_rule_begin (current_lhs); } + { grammar_rule_begin (current_lhs, current_lhs_location); } | rhs symbol - { grammar_current_rule_symbol_append ($2); } + { grammar_current_rule_symbol_append ($2, @2); } | rhs action - { grammar_current_rule_action_append ($2, @2.first_line); } + { grammar_current_rule_action_append ($2, @2); } | 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); } ; action: @@ -306,8 +378,8 @@ action: string_as_id: STRING { - $$ = getsym ($1); - symbol_class_set ($$, token_sym); + $$ = symbol_get ($1, @1); + symbol_class_set ($$, token_sym, @1); } ; @@ -322,37 +394,97 @@ string_content: epilogue.opt: /* Nothing. */ - { - $$ = xstrdup (""); - } | "%%" EPILOGUE { - $$ = $2; + epilogue_augment ($2, @2); + 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 r; + r.start = r.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)) + { + r.start = rhs[i].start; + break; + } + + return r; +} + + +/* Add a lex-param or a parse-param (depending on TYPE) with + declaration DECL and location LOC. */ static void -yyprint (FILE *file, - const yyltype *loc, int type, const yystype *value) +add_param (char const *type, char *decl, location loc) { - fputs (" (", file); - LOCATION_PRINT (file, *loc); - fputs (")", file); - switch (type) + static char const alphanum[] = + "0123456789" + "abcdefghijklmnopqrstuvwxyz" + "ABCDEFGHIJKLMNOPQRSTUVWXYZ" + "_"; + char const *alpha = alphanum + 10; + char const *name_start = NULL; + 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 { - case CHARACTER: - fprintf (file, " = '%s'", value->string); - break; + char *name; + size_t name_len; + + for (name_len = 1; + name_start[name_len] && strchr (alphanum, name_start[name_len]); + 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); + } + + scanner_last_string_free (); +} +/*----------------------------------------------------. +| When debugging the parser, display tokens' values. | +`----------------------------------------------------*/ + +static void +print_token_value (FILE *file, int type, YYSTYPE const *value) +{ + fputc (' ', file); + switch (type) + { case ID: fprintf (file, " = %s", value->symbol->tag); break; @@ -362,25 +494,38 @@ yyprint (FILE *file, break; case STRING: - fprintf (file, " = \"%s\"", value->string); + fprintf (file, " = \"%s\"", value->chars); break; case TYPE: - fprintf (file, " = <%s>", value->string); + 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: + fprintf (file, "unknown token type"); break; } } -void -gram_error (gram_control_t *control ATTRIBUTE_UNUSED, - yyltype *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[type]; }