X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/e9071366c3104e4e4a2490c16d53e7eeef670f45..fe1b448ada5e3a79ae3f523e08b5004396f30ca9:/src/parse-gram.y
diff --git a/src/parse-gram.y b/src/parse-gram.y
index a0c708b3..8e3b7320 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,
@@ -15,10 +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);
@@ -51,26 +48,27 @@ static void version_check (location const *loc, char const *version);
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 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
@@ -79,26 +77,27 @@ 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;
};
/* Define the tokens together with their human representation. */
@@ -113,11 +112,10 @@ static int current_prec = 0;
%token PERCENT_DESTRUCTOR "%destructor"
%token PERCENT_PRINTER "%printer"
-%token PERCENT_UNION "%union {...}"
-
%token PERCENT_LEFT "%left"
%token PERCENT_RIGHT "%right"
%token PERCENT_NONASSOC "%nonassoc"
+%token PERCENT_PRECEDENCE "%precedence"
%token PERCENT_PREC "%prec"
%token PERCENT_DPREC "%dprec"
@@ -129,6 +127,7 @@ static int current_prec = 0;
`----------------------*/
%token
+ PERCENT_CODE "%code"
PERCENT_DEBUG "%debug"
PERCENT_DEFAULT_PREC "%default-prec"
PERCENT_DEFINE "%define"
@@ -139,6 +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"
@@ -157,41 +157,50 @@ static int current_prec = 0;
PERCENT_YACC "%yacc"
;
-%token TYPE "type"
+%token BRACED_CODE "{...}"
+%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
- "{...}"
- "%union {...}"
- 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, $$), stderr); }
+ STRING
%printer { fprintf (stderr, "{\n%s\n}", $$); }
- "{...}"
- "%union {...}"
- PROLOGUE EPILOGUE
-%type TYPE
+ braceless content.opt "{...}" "%{...%}" EPILOGUE
+
+%type TYPE ID ID_COLON variable
%printer { fprintf (stderr, "<%s>", $$); } TYPE
+%printer { fputs ($$, stderr); } ID variable
+%printer { fprintf (stderr, "%s:", $$); } ID_COLON
+
%type INT
%printer { fprintf (stderr, "%d", $$); } 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
+
+%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
;
@@ -199,27 +208,39 @@ 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
+| "%{...%}"
+ {
+ 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);
+ }
+| "%defines" { defines_flag = true; }
+| "%defines" STRING
{
- static char one[] = "1";
- muscle_insert ($2, one);
+ defines_flag = true;
+ spec_defines_file = xstrdup ($2);
}
-| "%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; }
+| "%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;
@@ -227,21 +248,64 @@ 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; }
+| "%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, "");
}
-| "%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; }
+| "%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? */ ";"
;
@@ -252,36 +316,18 @@ 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;
- 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"
@@ -292,8 +338,44 @@ 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
{
@@ -308,21 +390,22 @@ 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;
@@ -330,20 +413,48 @@ precedence_declaration:
;
precedence_declarator:
- "%left" { $$ = left_assoc; }
-| "%right" { $$ = right_assoc; }
-| "%nonassoc" { $$ = non_assoc; }
+ "%left" { $$ = left_assoc; }
+| "%right" { $$ = right_assoc; }
+| "%nonassoc" { $$ = non_assoc; }
+| "%precedence" { $$ = precedence_assoc; }
;
type.opt:
/* Nothing. */ { current_type = NULL; }
-| TYPE { current_type = $1; }
+| TYPE { current_type = $1; tag_seen = true; }
+;
+
+/* Just like symbols.1 but accept INT for the sake of POSIX. */
+symbols.prec:
+ symbol.prec
+ { $$ = symbol_list_sym_new ($1, @1); }
+| symbols.prec symbol.prec
+ { $$ = symbol_list_prepend ($1, symbol_list_sym_new ($2, @2)); }
;
-/* One or more nonterminals to be %typed. */
+symbol.prec:
+ symbol { $$ = $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); }
+| TYPE { $$ = symbol_list_type_new ($1, @1); }
+| "<*>" { $$ = symbol_list_default_tagged_new (@1); }
+| "<>" { $$ = symbol_list_default_tagless_new (@1); }
;
/* One token definition. */
@@ -351,25 +462,26 @@ symbol_def:
TYPE
{
current_type = $1;
+ tag_seen = true;
}
-| ID
+| id
{
symbol_class_set ($1, current_class, @1, true);
symbol_type_set ($1, current_type, @1);
}
-| ID INT
+| id INT
{
symbol_class_set ($1, current_class, @1, true);
symbol_type_set ($1, current_type, @1);
symbol_user_token_number_set ($1, $2, @2);
}
-| ID string_as_id
+| id string_as_id
{
symbol_class_set ($1, current_class, @1, true);
symbol_type_set ($1, current_type, @1);
symbol_make_alias ($1, $2, @$);
}
-| ID INT string_as_id
+| id INT string_as_id
{
symbol_class_set ($1, current_class, @1, true);
symbol_type_set ($1, current_type, @1);
@@ -406,7 +518,7 @@ rules_or_grammar_declaration:
;
rules:
- ID_COLON { current_lhs = $1; current_lhs_location = @1; } rhses.1
+ id_colon { current_lhs = $1; current_lhs_location = @1; } rhses.1
;
rhses.1:
@@ -421,8 +533,7 @@ rhs:
| rhs symbol
{ grammar_current_rule_symbol_append ($2, @2); }
| rhs "{...}"
- { grammar_current_rule_action_append (gram_last_string,
- gram_last_braced_code_loc); }
+ { grammar_current_rule_action_append ($2, @2); }
| rhs "%prec" symbol
{ grammar_current_rule_prec_set ($3, @3); }
| rhs "%dprec" INT
@@ -431,9 +542,69 @@ rhs:
{ grammar_current_rule_merge_set ($3, @3); }
;
+
+/*---------------------------.
+| variable and content.opt. |
+`---------------------------*/
+
+variable:
+ ID
+| STRING { $$ = 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. */
+
+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 { $$ = symbol_from_uniqstr ($1, @1); }
+;
+
+
symbol:
- ID { $$ = $1; }
-| string_as_id { $$ = $1; }
+ id
+| string_as_id
;
/* A string used as an ID: quote it. */
@@ -445,19 +616,16 @@ string_as_id:
}
;
-/* A string used for its contents. Don't quote it. */
-string_content:
- STRING
- { $$ = $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 ();
}
;
@@ -545,6 +713,7 @@ add_param (char const *type, char *decl, location loc)
gram_scanner_last_string_free ();
}
+
static void
version_check (location const *loc, char const *version)
{
@@ -567,3 +736,16 @@ 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);
+ }
+}