X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/d08290769c798befc27e9f8bbc3f1a3da12d1f08..6cf3716c3166d6d41cdbeea45d018b1760184421:/src/parse-gram.y?ds=sidebyside diff --git a/src/parse-gram.y b/src/parse-gram.y index dad4e8cf..c932ba54 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,12 +1,12 @@ -/* Bison Grammar Parser -*- C -*- +%{/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002, 2003 Free Software Foundation, Inc. + Copyright (C) 2002-2012 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. - This program is free software; you can redistribute it and/or modify + 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 2 of the License, or + 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, @@ -15,21 +15,9 @@ 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, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - 02111-1307 USA -*/ + along with this program. If not, see . */ - -%debug -%defines -%locations -%pure-parser -// %error-verbose -%defines -%name-prefix="gram_" - -%{ +#include #include "system.h" #include "complain.h" @@ -37,17 +25,23 @@ #include "files.h" #include "getargs.h" #include "gram.h" -#include "muscle_tab.h" -#include "output.h" +#include "muscle-tab.h" +#include "named-ref.h" +#include "quotearg.h" #include "reader.h" #include "symlist.h" - -/* Produce verbose syntax errors. */ -#define YYERROR_VERBOSE 1 +#include "scan-gram.h" +#include "scan-code.h" +#include "xmemdup0.h" #define YYLLOC_DEFAULT(Current, Rhs, N) (Current) = lloc_default (Rhs, N) static YYLTYPE lloc_default (YYLTYPE const *, int); +#define YY_LOCATION_PRINT(File, Loc) \ + location_print (File, Loc) + +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 @@ -55,30 +49,71 @@ static YYLTYPE lloc_default (YYLTYPE const *, int); 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 *, int, YYSTYPE const *); +static char const *char_name (char); +%} -static void add_param (char const *, char *, location); +%code +{ + static int current_prec = 0; + static location current_lhs_location; + static named_ref *current_lhs_named_ref; + static symbol *current_lhs_symbol; + static symbol_class current_class = unknown_sym; + static uniqstr current_type = NULL; + + /** Set the new current left-hand side symbol, possibly common + * to several right-hand side parts of rule. + */ + static + void + current_lhs(symbol *sym, location loc, named_ref *ref) + { + current_lhs_symbol = sym; + current_lhs_location = loc; + /* In order to simplify memory management, named references for lhs + are always assigned by deep copy into the current symbol_list + node. This is because a single named-ref in the grammar may + result in several uses when the user factors lhs between several + rules using "|". Therefore free the parser's original copy. */ + free (current_lhs_named_ref); + current_lhs_named_ref = ref; + } + + #define YYTYPE_INT16 int_fast16_t + #define YYTYPE_INT8 int_fast8_t + #define YYTYPE_UINT16 uint_fast16_t + #define YYTYPE_UINT8 uint_fast8_t +} -symbol_class current_class = unknown_sym; -uniqstr current_type = 0; -symbol *current_lhs; -location current_lhs_location; -assoc current_assoc; -int current_prec = 0; -%} +%debug +%verbose +%defines +%locations +%pure-parser +%define parse.error "verbose" +%define parse.lac full +%name-prefix="gram_" +%expect 0 +%initial-action +{ + /* Bison's grammar can initial empty locations, hence a default + location is needed. */ + boundary_set (&@$.start, current_file, 1, 1); + boundary_set (&@$.end, current_file, 1, 1); +} -/* Only NUMBERS have a value. */ %union { + assoc assoc; + char *code; + char const *chars; + int integer; + named_ref *named_ref; symbol *symbol; symbol_list *list; - int integer; - char *chars; - assoc assoc; uniqstr uniqstr; + unsigned char character; }; /* Define the tokens together with their human representation. */ @@ -90,114 +125,260 @@ int current_prec = 0; %token PERCENT_NTERM "%nterm" %token PERCENT_TYPE "%type" -%token PERCENT_DESTRUCTOR "%destructor {...}" -%token PERCENT_PRINTER "%printer {...}" - -%token PERCENT_UNION "%union {...}" +%token PERCENT_DESTRUCTOR "%destructor" +%token PERCENT_PRINTER "%printer" %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" %token PERCENT_NONASSOC "%nonassoc" +%token PERCENT_PRECEDENCE "%precedence" %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_NONDETERMINISTIC_PARSER "%nondeterministic-parser" - 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" + PERCENT_CODE "%code" + 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_FLAG "%" + PERCENT_FILE_PREFIX "%file-prefix" + PERCENT_GLR_PARSER "%glr-parser" + PERCENT_INITIAL_ACTION "%initial-action" + PERCENT_LANGUAGE "%language" + 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_REQUIRE "%require" + PERCENT_SKELETON "%skeleton" + PERCENT_START "%start" + PERCENT_TOKEN_TABLE "%token-table" + PERCENT_VERBOSE "%verbose" + PERCENT_YACC "%yacc" +; + +%token BRACED_CODE "{...}" +%token BRACED_PREDICATE "%?{...}" +%token BRACKETED_ID "[identifier]" +%token CHAR "char" +%token EPILOGUE "epilogue" %token EQUAL "=" -%token SEMICOLON ";" -%token PIPE "|" %token ID "identifier" %token ID_COLON "identifier:" %token PERCENT_PERCENT "%%" +%token PIPE "|" %token PROLOGUE "%{...%}" -%token EPILOGUE "epilogue" -%token BRACED_CODE "{...}" - +%token SEMICOLON ";" +%token TAG "" +%token TAG_ANY "<*>" +%token TAG_NONE "<>" + +%type CHAR +%printer { fputs (char_name ($$), stderr); } CHAR + +/* braceless is not to be used for rule or symbol actions, as it + calls code_props_plain_init. */ +%type STRING "%{...%}" EPILOGUE braceless content.opt +%type "{...}" "%?{...}" +%printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } + STRING +%printer { fprintf (stderr, "{\n%s\n}", $$); } + braceless content.opt "{...}" "%{...%}" EPILOGUE + +%type BRACKETED_ID ID ID_COLON PERCENT_FLAG TAG variable +%printer { fputs ($$, stderr); } +%printer { fprintf (stderr, "[%s]", $$); } BRACKETED_ID +%printer { fprintf (stderr, "%s:", $$); } ID_COLON +%printer { fprintf (stderr, "%%%s", $$); } PERCENT_FLAG +%printer { fprintf (stderr, "<%s>", $$); } TAG -%type STRING string_content - "%destructor {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%type TYPE %type INT -%type ID ID_COLON symbol string_as_id +%printer { fprintf (stderr, "%d", $$); } + +%type id id_colon string_as_id symbol symbol.prec +%printer { fprintf (stderr, "%s", $$->tag); } +%printer { fprintf (stderr, "%s:", $$->tag); } id_colon + %type precedence_declarator -%type symbols.1 +%type symbols.1 symbols.prec generic_symlist generic_symlist_item +%type named_ref.opt + +/*---------. +| %param. | +`---------*/ +%code requires +{ +# ifndef PARAM_TYPE +# define PARAM_TYPE + typedef enum + { + param_none = 0, + param_lex = 1 << 0, + param_parse = 1 << 1, + param_both = param_lex | param_parse + } param_type; +# endif +}; +%code +{ + /** Add a lex-param and/or a parse-param. + * + * \param type where to push this formal argument. + * \param decl the formal argument. Destroyed. + * \param loc the location in the source. + */ + static void add_param (param_type type, char *decl, location loc); + static param_type current_param = param_none; +}; +%union +{ + param_type param; +} +%token PERCENT_PARAM "%param"; +%printer +{ + switch ($$) + { +#define CASE(In, Out) \ + case param_ ## In: fputs ("%" #Out, stderr); break + CASE(lex, lex-param); + CASE(parse, parse-param); + CASE(both, param); +#undef CASE + case param_none: aver (false); break; + } +} ; + + + /*==========\ + | Grammar. | + \==========*/ %% input: - declarations "%%" grammar epilogue.opt + prologue_declarations "%%" grammar epilogue.opt ; - /*------------------------------------. - | Declarations: before the first %%. | - `------------------------------------*/ + /*------------------------------------. + | Declarations: before the first %%. | + `------------------------------------*/ -declarations: +prologue_declarations: /* Nothing */ -| declarations declaration +| prologue_declarations prologue_declaration ; -declaration: +prologue_declaration: grammar_declaration -| PROLOGUE { prologue_augment ($1, @1); } -| "%debug" { debug_flag = true; } -| "%define" string_content string_content { muscle_insert ($2, $3); } -| "%defines" { defines_flag = true; } -| "%error-verbose" { error_verbose = true; } -| "%expect" INT { expected_conflicts = $2; } -| "%file-prefix" "=" string_content { spec_file_prefix = $3; } -| "%glr-parser" { nondeterministic_parser = true; - glr_parser = true; } -| "%lex-param {...}" { add_param ("lex_param", $1, @1); } -| "%locations" { locations_flag = true; } -| "%name-prefix" "=" string_content { spec_name_prefix = $3; } -| "%no-lines" { no_lines_flag = true; } -| "%nondeterministic-parser" { nondeterministic_parser = true; } -| "%output" "=" string_content { spec_outfile = $3; } -| "%parse-param {...}" { add_param ("parse_param", $1, @1); } -| "%pure-parser" { pure_parser = true; } -| "%skeleton" string_content { skeleton = $2; } -| "%token-table" { token_table_flag = true; } -| "%verbose" { report_flag = report_states; } -| "%yacc" { yacc_flag = true; } -| ";" +| "%{...%}" + { + code_props plain_code; + code_props_plain_init (&plain_code, $1, @1); + code_props_translate_code (&plain_code); + gram_scanner_last_string_free (); + muscle_code_grow (union_seen ? "post_prologue" : "pre_prologue", + plain_code.code, @1); + code_scanner_last_string_free (); + } +| "%" + { + muscle_percent_define_ensure ($1, @1, true); + } +| "%define" variable content.opt + { + muscle_percent_define_insert ($2, @2, $3, + MUSCLE_PERCENT_DEFINE_GRAMMAR_FILE); + } +| "%defines" { defines_flag = true; } +| "%defines" STRING + { + defines_flag = true; + spec_defines_file = xstrdup ($2); + } +| "%error-verbose" + { + muscle_percent_define_insert ("parse.error", @1, "verbose", + MUSCLE_PERCENT_DEFINE_GRAMMAR_FILE); + } +| "%expect" INT { expected_sr_conflicts = $2; } +| "%expect-rr" INT { expected_rr_conflicts = $2; } +| "%file-prefix" STRING { spec_file_prefix = $2; } +| "%file-prefix" "=" STRING { spec_file_prefix = $3; } /* deprecated */ +| "%glr-parser" + { + nondeterministic_parser = true; + glr_parser = true; + } +| "%initial-action" "{...}" + { + code_props action; + code_props_symbol_action_init (&action, $2, @2); + code_props_translate_code (&action); + gram_scanner_last_string_free (); + muscle_code_grow ("initial_action", action.code, @2); + code_scanner_last_string_free (); + } +| "%language" STRING { language_argmatch ($2, grammar_prio, @1); } +| "%name-prefix" STRING { spec_name_prefix = $2; } +| "%name-prefix" "=" STRING { spec_name_prefix = $3; } /* deprecated */ +| "%no-lines" { no_lines_flag = true; } +| "%nondeterministic-parser" { nondeterministic_parser = true; } +| "%output" STRING { spec_outfile = $2; } +| "%output" "=" STRING { spec_outfile = $3; } /* deprecated */ +| "%param" { current_param = $1; } params { current_param = param_none; } +| "%require" STRING { version_check (&@2, $2); } +| "%skeleton" STRING + { + char const *skeleton_user = $2; + if (strchr (skeleton_user, '/')) + { + size_t dir_length = strlen (current_file); + char *skeleton_build; + while (dir_length && current_file[dir_length - 1] != '/') + --dir_length; + while (dir_length && current_file[dir_length - 1] == '/') + --dir_length; + skeleton_build = + xmalloc (dir_length + 1 + strlen (skeleton_user) + 1); + if (dir_length > 0) + { + memcpy (skeleton_build, current_file, dir_length); + skeleton_build[dir_length++] = '/'; + } + strcpy (skeleton_build + dir_length, skeleton_user); + skeleton_user = uniqstr_new (skeleton_build); + free (skeleton_build); + } + skeleton_arg (skeleton_user, grammar_prio, @1); + } +| "%token-table" { token_table_flag = true; } +| "%verbose" { report_flag |= report_states; } +| "%yacc" { yacc_flag = true; } +| /*FIXME: Err? What is this horror doing here? */ ";" ; +params: + params "{...}" { add_param (current_param, $2, @2); } +| "{...}" { add_param (current_param, $1, @1); } +; + + +/*----------------------. +| grammar_declaration. | +`----------------------*/ + grammar_declaration: precedence_declaration | symbol_declaration @@ -205,28 +386,66 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%union {...}" +| "%destructor" "{...}" generic_symlist { - typed = true; - MUSCLE_INSERT_INT ("stype_line", @1.start.line); - muscle_insert ("stype", $1); + symbol_list *list; + for (list = $3; list; list = list->next) + symbol_list_code_props_set (list, destructor, @2, $2); + symbol_list_free ($3); } -| "%destructor {...}" symbols.1 +| "%printer" "{...}" generic_symlist { symbol_list *list; - for (list = $2; list; list = list->next) - symbol_destructor_set (list->sym, $1, @1); - symbol_list_free ($2); + for (list = $3; list; list = list->next) + symbol_list_code_props_set (list, printer, @2, $2); + symbol_list_free ($3); } -| "%printer {...}" symbols.1 +| "%default-prec" { - symbol_list *list; - for (list = $2; list; list = list->next) - symbol_printer_set (list->sym, $1, list->location); - symbol_list_free ($2); + default_prec = true; + } +| "%no-default-prec" + { + default_prec = false; } +| "%code" braceless + { + /* Do not invoke muscle_percent_code_grow here since it invokes + muscle_user_name_list_grow. */ + muscle_code_grow ("percent_code()", $2, @2); + code_scanner_last_string_free (); + } +| "%code" ID braceless + { + muscle_percent_code_grow ($2, @2, $3, @3); + code_scanner_last_string_free (); + } +; + + +/*---------. +| %union. | +`---------*/ + +%token PERCENT_UNION "%union"; + +union_name: + /* Nothing. */ {} +| ID { muscle_code_grow ("union_name", $1, @1); } ; +grammar_declaration: + "%union" union_name braceless + { + union_seen = true; + muscle_code_grow ("stype", $3, @3); + code_scanner_last_string_free (); + } +; + + + + symbol_declaration: "%nterm" { current_class = nterm_sym; } symbol_defs.1 { @@ -238,74 +457,103 @@ symbol_declaration: current_class = unknown_sym; current_type = NULL; } -| "%type" TYPE symbols.1 +| "%type" TAG symbols.1 { symbol_list *list; + tag_seen = true; for (list = $3; list; list = list->next) - symbol_type_set (list->sym, $2, @2); + symbol_type_set (list->content.sym, $2, @2); symbol_list_free ($3); } ; precedence_declaration: - precedence_declarator type.opt symbols.1 + precedence_declarator tag.opt symbols.prec { 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_type_set (list->content.sym, current_type, @2); + symbol_precedence_set (list->content.sym, current_prec, $1, @1); + } symbol_list_free ($3); current_type = NULL; } ; precedence_declarator: - "%left" { $$ = left_assoc; } -| "%right" { $$ = right_assoc; } -| "%nonassoc" { $$ = non_assoc; } + "%left" { $$ = left_assoc; } +| "%right" { $$ = right_assoc; } +| "%nonassoc" { $$ = non_assoc; } +| "%precedence" { $$ = precedence_assoc; } ; -type.opt: +tag.opt: /* Nothing. */ { current_type = NULL; } -| TYPE { current_type = $1; } +| TAG { current_type = $1; tag_seen = true; } +; + +/* Just like symbols.1 but accept INT for the sake of POSIX. */ +symbols.prec: + symbol.prec + { $$ = symbol_list_sym_new ($1, @1); } +| symbols.prec symbol.prec + { $$ = symbol_list_prepend ($1, symbol_list_sym_new ($2, @2)); } ; -/* One or more nonterminals to be %typed. */ +symbol.prec: + symbol { $$ = $1; } + | symbol INT { $$ = $1; symbol_user_token_number_set ($1, $2, @2); } + ; +/* One or more symbols to be %typed. */ symbols.1: - symbol { $$ = symbol_list_new ($1, @1); } -| symbols.1 symbol { $$ = symbol_list_prepend ($1, $2, @2); } + symbol + { $$ = symbol_list_sym_new ($1, @1); } +| symbols.1 symbol + { $$ = symbol_list_prepend ($1, symbol_list_sym_new ($2, @2)); } +; + +generic_symlist: + generic_symlist_item { $$ = $1; } +| generic_symlist generic_symlist_item { $$ = symbol_list_prepend ($1, $2); } +; + +generic_symlist_item: + symbol { $$ = symbol_list_sym_new ($1, @1); } +| TAG { $$ = symbol_list_type_new ($1, @1); } +| "<*>" { $$ = symbol_list_default_tagged_new (@1); } +| "<>" { $$ = symbol_list_default_tagless_new (@1); } ; /* One token definition. */ symbol_def: - TYPE + TAG { current_type = $1; + tag_seen = true; } -| ID +| id { - symbol_class_set ($1, current_class, @1); + 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, @1); + 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, @1); + 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, @1); + 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, @$); @@ -319,9 +567,9 @@ symbol_defs.1: ; - /*------------------------------------------. - | The grammar section: between the two %%. | - `------------------------------------------*/ + /*------------------------------------------. + | The grammar section: between the two %%. | + `------------------------------------------*/ grammar: rules_or_grammar_declaration @@ -333,10 +581,6 @@ grammar: rules_or_grammar_declaration: rules | grammar_declaration ";" - { - if (yacc_flag) - complain_at (@$, _("POSIX forbids declarations in the grammar")); - } | error ";" { yyerrok; @@ -344,64 +588,126 @@ rules_or_grammar_declaration: ; rules: - ID_COLON { current_lhs = $1; current_lhs_location = @1; } rhses.1 + id_colon named_ref.opt { current_lhs ($1, @1, $2); } rhses.1 + { + /* Free the current lhs. */ + current_lhs (0, @1, 0); + } ; rhses.1: - rhs { grammar_rule_end (@1); } -| rhses.1 "|" rhs { grammar_rule_end (@3); } + rhs { grammar_current_rule_end (@1); } +| rhses.1 "|" rhs { grammar_current_rule_end (@3); } | rhses.1 ";" ; rhs: /* Nothing. */ - { grammar_rule_begin (current_lhs, current_lhs_location); } -| rhs symbol - { grammar_current_rule_symbol_append ($2, @2); } -| rhs action - { grammar_current_rule_action_append ($2, @2); } + { grammar_current_rule_begin (current_lhs_symbol, current_lhs_location, + current_lhs_named_ref); } +| rhs symbol named_ref.opt + { grammar_current_rule_symbol_append ($2, @2, $3); } +| rhs "{...}" named_ref.opt + { grammar_current_rule_action_append ($2, @2, $3, false); } +| rhs "%?{...}" + { grammar_current_rule_action_append ($2, @2, NULL, true); } | rhs "%prec" symbol { grammar_current_rule_prec_set ($3, @3); } | rhs "%dprec" INT { grammar_current_rule_dprec_set ($3, @3); } -| rhs "%merge" TYPE +| rhs "%merge" TAG { grammar_current_rule_merge_set ($3, @3); } ; -symbol: - ID { $$ = $1; } -| string_as_id { $$ = $1; } +named_ref.opt: + /* Nothing. */ { $$ = 0; } +| + BRACKETED_ID { $$ = named_ref_new($1, @1); } +; + +/*---------------------------. +| variable and content.opt. | +`---------------------------*/ + +/* The STRING form of variable is deprecated and is not M4-friendly. + For example, M4 fails for `%define "[" "value"'. */ +variable: + ID +| STRING { $$ = uniqstr_new ($1); } ; -action: - BRACED_CODE - { $$ = $1; } +/* Some content or empty by default. */ +content.opt: + /* Nothing. */ { $$ = ""; } +| ID { $$ = $1; } +| STRING ; -/* A string used as an ID: we have to keep the quotes. */ -string_as_id: - STRING + +/*------------. +| braceless. | +`------------*/ + +braceless: + "{...}" { - $$ = symbol_get ($1, @1); - symbol_class_set ($$, token_sym, @1); + code_props plain_code; + $1[strlen ($1) - 1] = '\n'; + code_props_plain_init (&plain_code, $1+1, @1); + code_props_translate_code (&plain_code); + gram_scanner_last_string_free (); + $$ = plain_code.code; } ; -/* A string used for its contents. Strip the quotes. */ -string_content: - STRING + +/*--------------. +| Identifiers. | +`--------------*/ + +/* Identifiers are returned as uniqstr values by the scanner. + Depending on their use, we may need to make them genuine symbols. */ + +id: + ID + { $$ = symbol_from_uniqstr ($1, @1); } +| CHAR { - $$ = $1 + 1; - $$[strlen ($$) - 1] = '\0'; - }; + $$ = symbol_get (char_name ($1), @1); + symbol_class_set ($$, token_sym, @1, false); + symbol_user_token_number_set ($$, $1, @1); + } +; +id_colon: + ID_COLON { $$ = symbol_from_uniqstr ($1, @1); } +; + + +symbol: + id +| string_as_id +; + +/* A string used as an ID: quote it. */ +string_as_id: + STRING + { + $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1); + symbol_class_set ($$, token_sym, @1, false); + } +; epilogue.opt: /* Nothing. */ | "%%" EPILOGUE { - epilogue_augment ($2, @2); - scanner_last_string_free (); + code_props plain_code; + code_props_plain_init (&plain_code, $2, @2); + code_props_translate_code (&plain_code); + gram_scanner_last_string_free (); + muscle_code_grow ("epilogue", plain_code.code, @2); + code_scanner_last_string_free (); } ; @@ -418,107 +724,78 @@ 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. + /* 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 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; + 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) +add_param (param_type type, char *decl, location loc) { - static char const alphanum[] = - "0123456789" + static char const alphanum[26 + 26 + 1 + 10] = "abcdefghijklmnopqrstuvwxyz" "ABCDEFGHIJKLMNOPQRSTUVWXYZ" - "_"; - char const *alpha = alphanum + 10; - char const *name_start = NULL; - char *p; + "_" + "0123456789"; - 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'; + 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; - 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); + char *name = xmemdup0 (name_start, strspn (name_start, alphanum)); + if (type & param_lex) + muscle_pair_list_grow ("lex_param", decl, name); + if (type & param_parse) + muscle_pair_list_grow ("parse_param", decl, name); free (name); } - scanner_last_string_free (); + gram_scanner_last_string_free (); } -/*----------------------------------------------------. -| When debugging the parser, display tokens' values. | -`----------------------------------------------------*/ static void -print_token_value (FILE *file, int type, YYSTYPE const *value) +version_check (location const *loc, char const *version) { - fputc (' ', file); - switch (type) - { - case ID: - fprintf (file, " = %s", value->symbol->tag); - break; - - case INT: - fprintf (file, " = %d", value->integer); - break; - - case STRING: - fprintf (file, " = \"%s\"", value->chars); - break; - - case TYPE: - 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->chars); - break; - - default: - fprintf (file, "unknown token type"); - break; + if (strverscmp (version, PACKAGE_VERSION) > 0) + { + complain_at (*loc, "require bison %s, but have %s", + version, PACKAGE_VERSION); + exit (EX_MISMATCH); } } @@ -531,5 +808,18 @@ gram_error (location const *loc, char const *msg) char const * token_name (int type) { - return yytname[type]; + 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); + } }