X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/136a0f766b38072ec6ac6c386b230e04d4146151..e0c653e7e660c353c59b054de571474450aa4c92:/src/parse-gram.y?ds=sidebyside diff --git a/src/parse-gram.y b/src/parse-gram.y index 80fe01f0..cada04f7 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 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, @@ -15,16 +16,11 @@ 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" @@ -81,7 +77,6 @@ static int current_prec = 0; %locations %pure-parser %error-verbose -%defines %name-prefix="gram_" %expect 0 @@ -93,13 +88,13 @@ static int current_prec = 0; 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; @@ -116,12 +111,11 @@ static int current_prec = 0; %token PERCENT_TYPE "%type" %token PERCENT_DESTRUCTOR "%destructor" %token PERCENT_PRINTER "%printer" -%token PERCENT_SYMBOL_DEFAULT - "%symbol-default" %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" %token PERCENT_NONASSOC "%nonassoc" +%token PERCENT_PRECEDENCE "%precedence" %token PERCENT_PREC "%prec" %token PERCENT_DPREC "%dprec" @@ -144,6 +138,7 @@ 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" @@ -153,11 +148,8 @@ 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" @@ -175,33 +167,36 @@ 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 ($$), stderr); } CHAR /* braceless is not to be used for rule or symbol actions, as it - calls translate_code. */ -%type STRING "{...}" "%{...%}" EPILOGUE braceless content content.opt + calls code_props_plain_init. */ +%type STRING "%{...%}" EPILOGUE braceless content.opt +%type "{...}" %printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } - STRING + 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 ($$, stderr); } ID +%type TAG ID ID_COLON variable +%printer { fprintf (stderr, "<%s>", $$); } TAG +%printer { fputs ($$, stderr); } ID variable %printer { fprintf (stderr, "%s:", $$); } ID_COLON %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 generic_symlist generic_symlist_item +%type symbols.1 symbols.prec generic_symlist generic_symlist_item %% input: @@ -220,15 +215,32 @@ prologue_declarations: prologue_declaration: grammar_declaration -| "%{...%}" { prologue_augment (translate_code ($1, @1), @1, union_seen); } -| "%code" braceless { prologue_augment ($2, @2, 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 (); + } | "%debug" { debug_flag = true; } -| "%define" STRING content.opt { muscle_insert ($2, $3); } +| "%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); + } | "%error-verbose" { error_verbose = true; } | "%expect" INT { expected_sr_conflicts = $2; } | "%expect-rr" INT { expected_rr_conflicts = $2; } -| "%file-prefix" "=" STRING { spec_file_prefix = $3; } +| "%file-prefix" STRING { spec_file_prefix = $2; } +| "%file-prefix" "=" STRING { spec_file_prefix = $3; } /* deprecated */ | "%glr-parser" { nondeterministic_parser = true; @@ -236,23 +248,63 @@ 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 = $3; } +| "%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 = $3; } +| "%output" STRING { spec_outfile = $2; } +| "%output" "=" STRING { spec_outfile = $3; } /* deprecated */ | "%parse-param" "{...}" { add_param ("parse_param", $2, @2); } -| "%provides" braceless { muscle_code_grow ("provides", $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, ""); + /* 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); } -| "%requires" braceless { muscle_code_grow ("requires", $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? */ ";" ; @@ -267,17 +319,15 @@ 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" @@ -288,12 +338,24 @@ 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"; @@ -303,27 +365,11 @@ 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 (); } ; @@ -341,7 +387,7 @@ symbol_declaration: current_class = unknown_sym; current_type = NULL; } -| "%type" TYPE symbols.1 +| "%type" TAG symbols.1 { symbol_list *list; tag_seen = true; @@ -352,7 +398,7 @@ symbol_declaration: ; precedence_declaration: - precedence_declarator type.opt symbols.1 + precedence_declarator tag.opt symbols.prec { symbol_list *list; ++current_prec; @@ -367,16 +413,30 @@ 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_seen = true; } +| 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)); } ; +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 @@ -391,14 +451,15 @@ generic_symlist: ; generic_symlist_item: - symbol { $$ = symbol_list_sym_new ($1, @1); } -| TYPE { $$ = symbol_list_type_new ($1, @1); } -| "%symbol-default" { $$ = symbol_list_default_new (@1); } + symbol { $$ = symbol_list_sym_new ($1, @1); } +| TAG { $$ = symbol_list_type_new ($1, @1); } +| "<*>" { $$ = symbol_list_default_tagged_new (@1); } +| "<>" { $$ = symbol_list_default_tagless_new (@1); } ; /* One token definition. */ symbol_def: - TYPE + TAG { current_type = $1; tag_seen = true; @@ -477,43 +538,50 @@ rhs: { grammar_current_rule_prec_set ($3, @3); } | rhs "%dprec" INT { grammar_current_rule_dprec_set ($3, @3); } -| rhs "%merge" TYPE +| rhs "%merge" TAG { grammar_current_rule_merge_set ($3, @3); } ; -/*-----------* - | content. | - *-----------*/ +/*---------------------------. +| variable and content.opt. | +`---------------------------*/ -content: - STRING -| braceless +variable: + ID +| STRING { $$ = uniqstr_new ($1); } /* deprecated and not M4-friendly */ ; -/* Some content or "1" by default. */ +/* Some content or empty by default. */ content.opt: /* Nothing. */ { - static char one[] = "1"; - $$ = one; + $$ = ""; } -| content +| 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; } ; -/*---------------* - | Identifiers. | - *---------------*/ +/*--------------. +| Identifiers. | +`--------------*/ /* Identifiers are returned as uniqstr values by the scanner. Depending on their use, we may need to make them genuine symbols. */ @@ -552,8 +620,12 @@ 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 (); } ;