X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/203b9274149813e3ad763f1b800c83dcff07237f..ba061fa6f2fb7b144df75c1e052d61eeca392288:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 9933ecda..c7238dea 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,12 +1,13 @@ %{/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. + Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 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, @@ -15,10 +16,7 @@ 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., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301 USA -*/ + along with this program. If not, see . */ #include #include "system.h" @@ -34,7 +32,6 @@ #include "symlist.h" #include "scan-gram.h" #include "scan-code.h" -#include "strverscmp.h" #define YYLLOC_DEFAULT(Current, Rhs, N) (Current) = lloc_default (Rhs, N) static YYLTYPE lloc_default (YYLTYPE const *, int); @@ -53,26 +50,25 @@ static void gram_error (location const *, char const *); static char const *char_name (char); -static void add_param (char const *, char *, location); +/** Add a lex-param or a parse-param. + * + * \param type \a lex_param or \a parse_param + * \param decl the formal argument + * \param loc the location in the source. + */ +static void add_param (char const *type, char *decl, location loc); + static symbol_class current_class = unknown_sym; -static uniqstr current_type = 0; +static uniqstr current_type = NULL; 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 +#define YYTYPE_INT16 int_fast16_t +#define YYTYPE_INT8 int_fast8_t +#define YYTYPE_UINT16 uint_fast16_t +#define YYTYPE_UINT8 uint_fast8_t %} %debug @@ -81,24 +77,24 @@ static int current_prec = 0; %locations %pure-parser %error-verbose -%defines %name-prefix="gram_" +%expect 0 %initial-action { /* Bison's grammar can initial empty locations, hence a default location is needed. */ - boundary_set (&@$.start, current_file, 1, 0); - boundary_set (&@$.end, current_file, 1, 0); + boundary_set (&@$.start, current_file, 1, 1); + boundary_set (&@$.end, current_file, 1, 1); } -/* Only NUMBERS have a value. */ %union { symbol *symbol; symbol_list *list; int integer; - char *chars; + char const *chars; + char *code; assoc assoc; uniqstr uniqstr; unsigned char character; @@ -119,6 +115,7 @@ static int current_prec = 0; %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" %token PERCENT_NONASSOC "%nonassoc" +%token PERCENT_PRECEDENCE "%precedence" %token PERCENT_PREC "%prec" %token PERCENT_DPREC "%dprec" @@ -130,16 +127,18 @@ static int current_prec = 0; `----------------------*/ %token - PERCENT_DEBUG "%debug" + 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_LEX_PARAM "%lex-param" PERCENT_LOCATIONS "%locations" PERCENT_NAME_PREFIX "%name-prefix" @@ -168,34 +167,41 @@ static int current_prec = 0; %token PIPE "|" %token PROLOGUE "%{...%}" %token SEMICOLON ";" -%token TYPE "type" +%token TAG "" +%token TAG_ANY "<*>" +%token TAG_NONE "<>" %type CHAR %printer { fputs (char_name ($$), stderr); } CHAR -%type STRING string_content "{...}" PROLOGUE EPILOGUE +/* braceless is not to be used for rule or symbol actions, as it + calls code_props_plain_init. */ +%type STRING "%{...%}" EPILOGUE braceless content.opt +%type "{...}" %printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } - STRING string_content -%printer { fprintf (stderr, "{\n%s\n}", $$); } "{...}" PROLOGUE EPILOGUE + STRING +%printer { fprintf (stderr, "{\n%s\n}", $$); } + braceless content.opt "{...}" "%{...%}" EPILOGUE -%type TYPE ID ID_COLON -%printer { fprintf (stderr, "<%s>", $$); } TYPE -%printer { fputs ($$, stderr); } ID +%type TAG ID ID_COLON PERCENT_FLAG variable +%printer { fputs ($$, stderr); } ID variable %printer { fprintf (stderr, "%s:", $$); } ID_COLON +%printer { fprintf (stderr, "%%%s", $$); } PERCENT_FLAG +%printer { fprintf (stderr, "<%s>", $$); } TAG %type INT %printer { fprintf (stderr, "%d", $$); } INT -%type id id_colon symbol string_as_id +%type id id_colon symbol symbol.prec string_as_id %printer { fprintf (stderr, "%s", $$->tag); } id symbol string_as_id %printer { fprintf (stderr, "%s:", $$->tag); } id_colon %type precedence_declarator -%type symbols.1 +%type symbols.1 symbols.prec generic_symlist generic_symlist_item %% input: - declarations "%%" grammar epilogue.opt + prologue_declarations "%%" grammar epilogue.opt ; @@ -203,27 +209,41 @@ input: | Declarations: before the first %%. | `------------------------------------*/ -declarations: +prologue_declarations: /* Nothing */ -| declarations declaration +| prologue_declarations prologue_declaration ; -declaration: +prologue_declaration: grammar_declaration -| 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 = 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; } +| "%{...%}" + { + 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_insert ($1, @1, ""); + } +| "%define" variable content.opt + { + muscle_percent_define_insert ($2, @2, $3); + } +| "%defines" { defines_flag = true; } +| "%defines" STRING + { + defines_flag = true; + spec_defines_file = xstrdup ($2); + } +| "%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; @@ -231,21 +251,64 @@ declaration: } | "%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 = true; } -| "%nondeterministic-parser" { nondeterministic_parser = true; } -| "%output" "=" string_content { spec_outfile = $3; } -| "%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 = true; } -| "%verbose" { report_flag = report_states; } -| "%yacc" { yacc_flag = true; } + 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); } +| "%lex-param" "{...}" { add_param ("lex_param", $2, @2); } +| "%locations" { locations_flag = true; } +| "%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 */ +| "%parse-param" "{...}" { add_param ("parse_param", $2, @2); } +| "%pure-parser" + { + /* %pure-parser is deprecated in favor of `%define api.pure', so use + `%define api.pure' in a backward-compatible manner here. First, don't + complain if %pure-parser is specified multiple times. */ + if (!muscle_find_const ("percent_define(api.pure)")) + muscle_percent_define_insert ("api.pure", @1, ""); + /* In all cases, use api.pure now so that the backend doesn't complain if + the skeleton ignores api.pure, but do warn now if there's a previous + conflicting definition from an actual %define. */ + if (!muscle_percent_define_flag_if ("api.pure")) + muscle_percent_define_insert ("api.pure", @1, ""); + } +| "%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) + { + strncpy (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? */ ";" ; @@ -256,20 +319,18 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%destructor" "{...}" symbols.1 +| "%destructor" "{...}" generic_symlist { 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_destructor_set (list, $2, @2); symbol_list_free ($3); } -| "%printer" "{...}" symbols.1 +| "%printer" "{...}" generic_symlist { 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_printer_set (list, $2, @2); symbol_list_free ($3); } | "%default-prec" @@ -280,12 +341,24 @@ grammar_declaration: { 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. | - *----------*/ +/*---------. +| %union. | +`---------*/ %token PERCENT_UNION "%union"; @@ -295,21 +368,11 @@ union_name: ; grammar_declaration: - "%union" union_name "{...}" + "%union" union_name braceless { - 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); + union_seen = true; + muscle_code_grow ("stype", $3, @3); + code_scanner_last_string_free (); } ; @@ -327,24 +390,25 @@ 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; @@ -352,27 +416,56 @@ precedence_declaration: ; 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 { @@ -443,20 +536,55 @@ rhs: | rhs symbol { grammar_current_rule_symbol_append ($2, @2); } | rhs "{...}" - { grammar_current_rule_action_append (gram_last_string, - gram_last_braced_code_loc); } + { grammar_current_rule_action_append ($2, @2); } | 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); } ; -/*---------------* - | Identifiers. | - *---------------*/ +/*---------------------------. +| variable and content.opt. | +`---------------------------*/ + +variable: + ID +| STRING { $$ = uniqstr_new ($1); } /* deprecated and not M4-friendly */ +; + +/* Some content or empty by default. */ +content.opt: + /* Nothing. */ + { + $$ = ""; + } +| STRING +; + + +/*------------. +| braceless. | +`------------*/ + +braceless: + "{...}" + { + 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 (); + $$ = plain_code.code; + } +; + + +/*--------------. +| Identifiers. | +`--------------*/ /* Identifiers are returned as uniqstr values by the scanner. Depending on their use, we may need to make them genuine symbols. */ @@ -491,19 +619,16 @@ string_as_id: } ; -/* A string used for its contents. Don't quote it. */ -string_content: - STRING - { $$ = $1; } -; - - epilogue.opt: /* Nothing. */ | "%%" EPILOGUE { - muscle_code_grow ("epilogue", translate_code ($2, @2), @2); + 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 (); } ; @@ -591,6 +716,7 @@ add_param (char const *type, char *decl, location loc) gram_scanner_last_string_free (); } + static void version_check (location const *loc, char const *version) {