X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/02975b9aade52df362645b82a81ac2134290e221..686e83e396696572171fad32f440cc279ab82a75:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index aabace13..8871f672 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) 2002-2011 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, @@ -15,22 +15,18 @@ 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" -#include - #include "complain.h" #include "conflicts.h" #include "files.h" #include "getargs.h" #include "gram.h" -#include "muscle_tab.h" +#include "muscle-tab.h" +#include "named-ref.h" #include "quotearg.h" #include "reader.h" #include "symlist.h" @@ -67,6 +63,7 @@ static symbol_class current_class = unknown_sym; static uniqstr current_type = NULL; static symbol *current_lhs; static location current_lhs_location; +static named_ref *current_lhs_named_ref; static int current_prec = 0; #define YYTYPE_INT16 int_fast16_t @@ -81,7 +78,7 @@ static int current_prec = 0; %locations %pure-parser %error-verbose -%defines +%define parse.lac full %name-prefix="gram_" %expect 0 @@ -103,6 +100,7 @@ static int current_prec = 0; assoc assoc; uniqstr uniqstr; unsigned char character; + named_ref *named_ref; }; /* Define the tokens together with their human representation. */ @@ -132,7 +130,6 @@ static int current_prec = 0; %token PERCENT_CODE "%code" - PERCENT_CODE_TOP "%code-top" PERCENT_DEBUG "%debug" PERCENT_DEFAULT_PREC "%default-prec" PERCENT_DEFINE "%define" @@ -143,6 +140,7 @@ static int current_prec = 0; 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" @@ -152,11 +150,8 @@ static int current_prec = 0; "%nondeterministic-parser" PERCENT_OUTPUT "%output" PERCENT_PARSE_PARAM "%parse-param" - PERCENT_PROVIDES "%provides" PERCENT_PURE_PARSER "%pure-parser" - PERCENT_PUSH_PARSER "%push-parser" PERCENT_REQUIRE "%require" - PERCENT_REQUIRES "%requires" PERCENT_SKELETON "%skeleton" PERCENT_START "%start" PERCENT_TOKEN_TABLE "%token-table" @@ -165,6 +160,7 @@ static int current_prec = 0; ; %token BRACED_CODE "{...}" +%token BRACKETED_ID "[identifier]" %token CHAR "char" %token EPILOGUE "epilogue" %token EQUAL "=" @@ -182,28 +178,31 @@ static int current_prec = 0; %printer { fputs (char_name ($$), stderr); } CHAR /* braceless is not to be used for rule or symbol actions, as it - calls translate_code. */ -%type STRING "%{...%}" EPILOGUE braceless content content.opt + calls code_props_plain_init. */ +%type STRING "%{...%}" EPILOGUE braceless content.opt %type "{...}" %printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } STRING %printer { fprintf (stderr, "{\n%s\n}", $$); } - braceless content content.opt "{...}" "%{...%}" EPILOGUE + braceless content.opt "{...}" "%{...%}" EPILOGUE -%type TYPE ID ID_COLON -%printer { fprintf (stderr, "<%s>", $$); } TYPE -%printer { fputs ($$, stderr); } ID +%type BRACKETED_ID ID ID_COLON TYPE variable +%printer { fputs ($$, 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 +%printer { fprintf (stderr, "%d", $$); } -%type id id_colon symbol string_as_id -%printer { fprintf (stderr, "%s", $$->tag); } id symbol string_as_id +%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 generic_symlist generic_symlist_item +%type symbols.1 symbols.prec generic_symlist generic_symlist_item +%type named_ref.opt + %% input: @@ -222,9 +221,22 @@ prologue_declarations: prologue_declaration: grammar_declaration -| "%{...%}" { prologue_augment (translate_code ($1, @1), @1, union_seen); } +| "%{...%}" + { + 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" STRING content.opt { muscle_insert ($2, $3); } +| "%define" variable content.opt + { + muscle_percent_define_insert ($2, @2, $3, + MUSCLE_PERCENT_DEFINE_GRAMMAR_FILE); + } | "%defines" { defines_flag = true; } | "%defines" STRING { @@ -243,8 +255,14 @@ prologue_declaration: } | "%initial-action" "{...}" { - muscle_code_grow ("initial_action", translate_symbol_action ($2, @2), @2); + 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; } @@ -254,12 +272,48 @@ prologue_declaration: | "%output" STRING { spec_outfile = $2; } | "%output" "=" STRING { spec_outfile = $3; } /* deprecated */ | "%parse-param" "{...}" { add_param ("parse_param", $2, @2); } -| "%pure-parser" { pure_parser = true; } -| "%push-parser" { push_parser = true; } +| "%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 { skeleton = $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; } +| "%verbose" { report_flag |= report_states; } | "%yacc" { yacc_flag = true; } | /*FIXME: Err? What is this horror doing here? */ ";" ; @@ -274,17 +328,15 @@ grammar_declaration: | "%destructor" "{...}" generic_symlist { symbol_list *list; - const char *action = translate_symbol_action ($2, @2); for (list = $3; list; list = list->next) - symbol_list_destructor_set (list, action, @2); + symbol_list_destructor_set (list, $2, @2); symbol_list_free ($3); } | "%printer" "{...}" generic_symlist { symbol_list *list; - const char *action = translate_symbol_action ($2, @2); for (list = $3; list; list = list->next) - symbol_list_printer_set (list, action, @2); + symbol_list_printer_set (list, $2, @2); symbol_list_free ($3); } | "%default-prec" @@ -295,10 +347,18 @@ grammar_declaration: { default_prec = false; } -| "%code" braceless { prologue_augment ($2, @2, true); } -| "%code-top" braceless { prologue_augment ($2, @2, false); } -| "%provides" braceless { muscle_code_grow ("provides", $2, @2); } -| "%requires" braceless { muscle_code_grow ("requires", $2, @2); } +| "%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 (); + } ; @@ -314,27 +374,11 @@ union_name: ; grammar_declaration: - "%union" union_name "{...}" + "%union" union_name braceless { - char const *body = $3; - - /* Concatenate the %union bodies. If this is the first %union, make sure - the synchronization line appears after the opening '{' so as not to - confuse Doxygen. Otherwise, turn the previous %union's trailing '}' - into '\n', and omit the new %union's leading '{'. */ - if (!union_seen) - { - muscle_grow ("stype", "{", ""); - } - else - { - char *code = muscle_find ("stype"); - code[strlen (code) - 1] = '\n'; - } - body++; - union_seen = true; - muscle_code_grow ("stype", body, @3); + muscle_code_grow ("stype", $3, @3); + code_scanner_last_string_free (); } ; @@ -363,7 +407,7 @@ symbol_declaration: ; precedence_declaration: - precedence_declarator type.opt symbols.1 + precedence_declarator type.opt symbols.prec { symbol_list *list; ++current_prec; @@ -388,6 +432,19 @@ type.opt: | TYPE { 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)); } +; + +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 @@ -469,7 +526,8 @@ rules_or_grammar_declaration: ; rules: - id_colon { current_lhs = $1; current_lhs_location = @1; } rhses.1 + id_colon named_ref.opt { current_lhs = $1; current_lhs_location = @1; + current_lhs_named_ref = $2; } rhses.1 ; rhses.1: @@ -480,11 +538,12 @@ rhses.1: rhs: /* Nothing. */ - { grammar_current_rule_begin (current_lhs, current_lhs_location); } -| rhs symbol - { grammar_current_rule_symbol_append ($2, @2); } -| rhs "{...}" - { grammar_current_rule_action_append ($2, @2); } + { grammar_current_rule_begin (current_lhs, 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 @@ -493,32 +552,45 @@ rhs: { grammar_current_rule_merge_set ($3, @3); } ; +named_ref.opt: + /* Nothing. */ { $$ = 0; } +| + BRACKETED_ID { $$ = named_ref_new($1, @1); } +; -/*-----------* - | content. | - *-----------*/ -content: - STRING -| braceless +/*----------------------------* + | 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 { $$ = uniqstr_new ($1); } ; -/* Some content or "1" by default. */ +/* Some content or empty by default. */ content.opt: - /* Nothing. */ - { - static char one[] = "1"; - $$ = one; - } -| content + /* Nothing. */ { $$ = ""; } +| ID { $$ = $1; } +| STRING ; +/*-------------* + | braceless. | + *-------------*/ + braceless: "{...}" { + code_props plain_code; $1[strlen ($1) - 1] = '\n'; - $$ = translate_code ($1 + 1, @1); + code_props_plain_init (&plain_code, $1+1, @1); + code_props_translate_code (&plain_code); + gram_scanner_last_string_free (); + $$ = plain_code.code; } ; @@ -564,8 +636,12 @@ 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 (); } ;