X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/676385e29c4aedfc05d20daf1ef20cd4ccc84856..38a92d500a6c26a97e90256726241255f6f09d0a:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 2d00e035..4b7637e7 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -30,6 +30,7 @@ %{ #include "system.h" +#include "complain.h" #include "muscle_tab.h" #include "files.h" #include "getargs.h" @@ -39,7 +40,7 @@ #include "reader.h" #include "conflicts.h" -/* Produce verbose parse errors. */ +/* Produce verbose syntax errors. */ #define YYERROR_VERBOSE 1 #define YYLLOC_DEFAULT(Current, Rhs, N) \ do { \ @@ -56,28 +57,23 @@ do { \ } \ } while (0) -/* 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) - -/* 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) #define YYPRINT(File, Type, Value) \ - yyprint (File, Type, &Value) -static void yyprint (FILE *file, int type, const yystype *value); + print_token_value (File, Type, &Value) +static void print_token_value (FILE *file, int type, YYSTYPE const *value); + +static void add_param (char const *, char const *, location_t); symbol_class current_class = unknown_sym; -char *current_type = 0; +struniq_t current_type = 0; symbol_t *current_lhs; location_t current_lhs_location; -associativity current_assoc; +assoc_t current_assoc; int current_prec = 0; braced_code_t current_braced_code = action_braced_code; %} @@ -90,13 +86,14 @@ braced_code_t current_braced_code = action_braced_code; symbol_list_t *list; int integer; char *string; - associativity assoc; + assoc_t assoc; + struniq_t struniq; }; -/* Define the tokens together with there human representation. */ -%token GRAM_EOF 0 "end of string" -%token STRING CHARACTER -%token INT +/* 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" @@ -111,44 +108,53 @@ braced_code_t current_braced_code = action_braced_code; %token PERCENT_RIGHT "%right" %token PERCENT_NONASSOC "%nonassoc" -%token PERCENT_EXPECT "%expect" -%token PERCENT_START "%start" -%token PERCENT_PREC "%prec" -%token PERCENT_DPREC "%dprec" -%token PERCENT_MERGE "%merge" -%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_GLR_PARSER "%glr-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_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" +; + +%token TYPE "type" +%token EQUAL "=" +%token SEMICOLON ";" +%token COLON ":" +%token PIPE "|" +%token ID "identifier" %token PERCENT_PERCENT "%%" -%token PROLOGUE EPILOGUE -%token BRACED_CODE +%token PROLOGUE "%{...%}" +%token EPILOGUE "epilogue" +%token BRACED_CODE "{...}" + -%type CHARACTER TYPE STRING string_content - BRACED_CODE PROLOGUE EPILOGUE epilogue.opt action +%type STRING string_content + BRACED_CODE code_content action + PROLOGUE EPILOGUE +%type TYPE %type INT %type ID symbol string_as_id %type precedence_declarator @@ -157,10 +163,6 @@ braced_code_t current_braced_code = action_braced_code; input: declarations "%%" grammar epilogue.opt - { - yycontrol->errcode = 0; - epilogue_set ($4, @4); - } ; @@ -182,12 +184,14 @@ 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); } | "%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" code_content { add_param ("parse_param", $2, @2); } | "%pure-parser" { pure_parser = 1; } -| "%glr-parser" { glr_parser = 1; } | "%skeleton" string_content { skeleton = $2; } | "%token-table" { token_table_flag = 1; } | "%verbose" { report_flag = 1; } @@ -271,7 +275,7 @@ precedence_declarator: ; type.opt: - /* Nothing. */ { current_type = NULL;} + /* Nothing. */ { current_type = NULL; } | TYPE { current_type = $1; } ; @@ -303,14 +307,14 @@ symbol_def: { symbol_class_set ($1, current_class, @1); symbol_type_set ($1, current_type, @1); - symbol_make_alias ($1, $2); + symbol_make_alias ($1, $2, @$); } | ID INT string_as_id { 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); + symbol_make_alias ($1, $3, @$); } ; @@ -338,6 +342,14 @@ grammar: rules_or_grammar_declaration: rules | grammar_declaration ";" + { + if (yacc_flag) + complain_at (@$, _("POSIX forbids declarations in the grammar")); + } +| error ";" + { + yyerrok; + } ; rules: @@ -368,7 +380,6 @@ rhs: symbol: ID { $$ = $1; } | string_as_id { $$ = $1; } -| CHARACTER { $$ = getsym ($1, @1); } ; action: @@ -380,7 +391,7 @@ action: string_as_id: STRING { - $$ = getsym ($1, @1); + $$ = symbol_get ($1, @1); symbol_class_set ($$, token_sym, @1); } ; @@ -394,14 +405,21 @@ string_content: }; +/* A BRACED_CODE used for its contents. Strip the braces. */ +code_content: + BRACED_CODE + { + $$ = $1 + 1; + $$[strlen ($$) - 1] = '\0'; + }; + + epilogue.opt: /* Nothing. */ - { - $$ = xstrdup (""); - } | "%%" EPILOGUE { - $$ = $2; + epilogue_augment ($2, @2); + scanner_last_string_free (); } ; @@ -410,21 +428,54 @@ semi_colon.opt: | ";" ; %% +static void +add_param (char const *type, char const *decl, location_t loc) +{ + static char const alphanum[] = + "0123456789" + "abcdefghijklmnopqrstuvwxyz" + "ABCDEFGHIJKLMNOPQRSTUVWXYZ" + "_"; + char const *alpha = alphanum + 10; + char const *name_start = NULL; + char const *p; + + for (p = decl; *p; p++) + if ((p == decl || ! strchr (alphanum, p[-1])) && strchr (alpha, p[0])) + name_start = p; + + if (! name_start) + complain_at (loc, _("missing identifier in parameter declaration")); + else + { + 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' locations and values. | `------------------------------------------------------------------*/ static void -yyprint (FILE *file, - int type, const yystype *value) +print_token_value (FILE *file, int type, YYSTYPE const *value) { fputc (' ', file); switch (type) { - case CHARACTER: - fprintf (file, " = '%s'", value->string); - break; - case ID: fprintf (file, " = %s", value->symbol->tag); break; @@ -438,7 +489,7 @@ yyprint (FILE *file, break; case TYPE: - fprintf (file, " = <%s>", value->string); + fprintf (file, " = <%s>", value->struniq); break; case BRACED_CODE: @@ -446,13 +497,15 @@ yyprint (FILE *file, case EPILOGUE: fprintf (file, " = {{ %s }}", value->string); break; + + default: + fprintf (file, "unknown token type"); + break; } } void -gram_error (gram_control_t *control ATTRIBUTE_UNUSED, - location_t *yylloc, const char *msg) +gram_error (location_t const *loc, char const *msg) { - LOCATION_PRINT (stderr, *yylloc); - fprintf (stderr, ": %s\n", msg); + complain_at (*loc, "%s", msg); }