X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/073f92889fed2bb511833920e841243a749223ca..c932d6135ca3e508f7136810b9b0bf79725290b9:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 71f4829e..fc648ea1 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,12 +1,12 @@ %{/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002, 2003, 2004, 2005, 2006 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, @@ -15,10 +15,7 @@ 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" @@ -28,18 +25,19 @@ #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" -#include "strverscmp.h" +#include "scan-gram.h" +#include "scan-code.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) + location_print (File, Loc) static void version_check (location const *loc, char const *version); @@ -47,16 +45,50 @@ static void version_check (location const *loc, char const *version); FIXME: depends on the undocumented availability of YYLLOC. */ #undef yyerror #define yyerror(Msg) \ - gram_error (&yylloc, Msg) + gram_error (&yylloc, Msg) static void gram_error (location const *, char const *); -static void add_param (char const *, char *, location); +static char const *char_name (char); + +/** 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 symbol *current_lhs; +static uniqstr current_type = NULL; +static symbol *current_lhs_symbol; static location current_lhs_location; +static named_ref *current_lhs_named_ref; static int current_prec = 0; + +/** 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 %} %debug @@ -65,27 +97,29 @@ static int current_prec = 0; %locations %pure-parser %error-verbose -%defines +%define parse.lac full %name-prefix="gram_" +%expect 0 %initial-action { /* Bison's grammar can initial empty locations, hence a default location is needed. */ - @$.start.file = @$.end.file = current_file; - @$.start.line = @$.end.line = 1; - @$.start.column = @$.end.column = 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; + named_ref *named_ref; }; /* Define the tokens together with their human representation. */ @@ -97,10 +131,8 @@ static 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" @@ -116,6 +148,7 @@ static int current_prec = 0; `----------------------*/ %token + PERCENT_CODE "%code" PERCENT_DEBUG "%debug" PERCENT_DEFAULT_PREC "%default-prec" PERCENT_DEFINE "%define" @@ -125,18 +158,19 @@ static int current_prec = 0; PERCENT_EXPECT_RR "%expect-rr" PERCENT_FILE_PREFIX "%file-prefix" PERCENT_GLR_PARSER "%glr-parser" - PERCENT_INITIAL_ACTION "%initial-action {...}" - PERCENT_LEX_PARAM "%lex-param {...}" + PERCENT_INITIAL_ACTION "%initial-action" + PERCENT_LANGUAGE "%language" + PERCENT_LEX_PARAM "%lex-param" PERCENT_LOCATIONS "%locations" PERCENT_NAME_PREFIX "%name-prefix" PERCENT_NO_DEFAULT_PREC "%no-default-prec" PERCENT_NO_LINES "%no-lines" PERCENT_NONDETERMINISTIC_PARSER - "%nondeterministic-parser" + "%nondeterministic-parser" PERCENT_OUTPUT "%output" - PERCENT_PARSE_PARAM "%parse-param {...}" + PERCENT_PARSE_PARAM "%parse-param" PERCENT_PURE_PARSER "%pure-parser" - PERCENT_REQUIRE "%require" + PERCENT_REQUIRE "%require" PERCENT_SKELETON "%skeleton" PERCENT_START "%start" PERCENT_TOKEN_TABLE "%token-table" @@ -144,52 +178,54 @@ static int current_prec = 0; PERCENT_YACC "%yacc" ; -%token TYPE "type" +%token BRACED_CODE "{...}" +%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 "{...}" - - -%type STRING string_content - "%destructor {...}" - "%initial-action {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%printer { fprintf (stderr, "\"%s\"", $$); } - STRING string_content +%token SEMICOLON ";" +%token TYPE "type" +%token TYPE_TAG_ANY "<*>" +%token TYPE_TAG_NONE "<>" + +%type CHAR +%printer { fputs (char_name ($$), 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, $$), stderr); } + STRING %printer { fprintf (stderr, "{\n%s\n}", $$); } - "%destructor {...}" - "%initial-action {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%type TYPE + braceless content.opt "{...}" "%{...%}" EPILOGUE + +%type BRACKETED_ID ID ID_COLON TYPE variable +%printer { fputs ($$, stderr); } +%printer { fprintf (stderr, "[%s]", $$); } BRACKETED_ID +%printer { fprintf (stderr, "%s:", $$); } ID_COLON %printer { fprintf (stderr, "<%s>", $$); } TYPE + %type INT -%printer { fprintf (stderr, "%d", $$); } INT -%type ID symbol string_as_id -%printer { fprintf (stderr, "%s", $$->tag); } ID symbol string_as_id -%type ID_COLON -%printer { fprintf (stderr, "%s:", $$->tag); } ID_COLON +%printer { fprintf (stderr, "%d", $$); } + +%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 + %% input: - declarations "%%" grammar epilogue.opt + prologue_declarations "%%" grammar epilogue.opt ; @@ -197,44 +233,107 @@ input: | 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 { muscle_insert ($2, "1"); } -| "%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 (); + } +| "%debug" { debug_flag = 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" { error_verbose = true; } +| "%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 {...}" - { - muscle_code_grow ("initial_action", $1, @1); - } -| "%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; } -| "%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; } + { + 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); } +| "%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, "", + MUSCLE_PERCENT_DEFINE_GRAMMAR_FILE); + /* 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, "", + MUSCLE_PERCENT_DEFINE_GRAMMAR_FILE); + } +| "%require" STRING { version_check (&@2, $2); } +| "%skeleton" STRING + { + char const *skeleton_user = $2; + if (mbschr (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? */ ";" ; @@ -245,35 +344,19 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%union {...}" - { - char const *body = $1; - - 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, @1); - } -| "%destructor {...}" symbols.1 +| "%destructor" "{...}" 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_destructor_set (list, $2, @2); + symbol_list_free ($3); } -| "%printer {...}" symbols.1 +| "%printer" "{...}" generic_symlist { symbol_list *list; - for (list = $2; list; list = list->next) - symbol_printer_set (list->sym, $1, list->location); - symbol_list_free ($2); + for (list = $3; list; list = list->next) + symbol_list_printer_set (list, $2, @2); + symbol_list_free ($3); } | "%default-prec" { @@ -283,8 +366,44 @@ 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. | + *----------*/ + +%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 { @@ -299,21 +418,22 @@ symbol_declaration: | "%type" TYPE 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 type.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; @@ -328,14 +448,40 @@ precedence_declarator: type.opt: /* Nothing. */ { current_type = NULL; } -| TYPE { current_type = $1; } +| TYPE { current_type = $1; tag_seen = true; } ; -/* One or more nonterminals to be %typed. */ +/* 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)); } +; + +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 { $$ = symbol_list_sym_new ($1, @1); } +| TYPE { $$ = symbol_list_type_new ($1, @1); } +| "<*>" { $$ = symbol_list_default_tagged_new (@1); } +| "<>" { $$ = symbol_list_default_tagless_new (@1); } ; /* One token definition. */ @@ -343,25 +489,26 @@ symbol_def: TYPE { current_type = $1; + tag_seen = true; } -| ID +| id { 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, 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, 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, true); symbol_type_set ($1, current_type, @1); @@ -391,10 +538,6 @@ grammar: rules_or_grammar_declaration: rules | grammar_declaration ";" - { - if (yacc_flag) - complain_at (@$, _("POSIX forbids declarations in the grammar")); - } | error ";" { yyerrok; @@ -402,7 +545,11 @@ 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: @@ -413,11 +560,12 @@ rhses.1: rhs: /* Nothing. */ - { grammar_current_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); } | rhs "%prec" symbol { grammar_current_rule_prec_set ($3, @3); } | rhs "%dprec" INT @@ -426,14 +574,75 @@ rhs: { 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 { $$ = uniqstr_new ($1); } +; + +/* Some content or empty by default. */ +content.opt: + /* Nothing. */ { $$ = ""; } +| ID { $$ = $1; } +| STRING ; -action: - BRACED_CODE - { $$ = $1; } + +/*-------------* + | 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 (); + $$ = plain_code.code; + } +; + + +/*---------------* + | Identifiers. | + *---------------*/ + +/* Identifiers are returned as uniqstr values by the scanner. + Depending on their use, we may need to make them genuine symbols. */ + +id: + ID + { $$ = symbol_from_uniqstr ($1, @1); } +| CHAR + { + $$ = symbol_get (char_name ($1), @1); + symbol_class_set ($$, 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. */ @@ -445,19 +654,16 @@ 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", $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 (); } ; @@ -542,9 +748,10 @@ add_param (char const *type, char *decl, location loc) free (name); } - scanner_last_string_free (); + gram_scanner_last_string_free (); } + static void version_check (location const *loc, char const *version) { @@ -567,3 +774,16 @@ token_name (int 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); + } +}