X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/cb48f1919ce8ccbd8587556c165a8b8b0d78d80f..a68b1f237e63c96ee905916424013f79d01908ba:/src/parse-gram.y?ds=sidebyside
diff --git a/src/parse-gram.y b/src/parse-gram.y
index 16ae62b8..5f77a5bd 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,
@@ -15,27 +15,25 @@
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 "c-ctype.h"
#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"
#include "scan-gram.h"
#include "scan-code.h"
+#include "xmemdup0.h"
#define YYLLOC_DEFAULT(Current, Rhs, N) (Current) = lloc_default (Rhs, N)
static YYLTYPE lloc_default (YYLTYPE const *, int);
@@ -54,14 +52,41 @@ 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 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
@@ -69,13 +94,14 @@ static int current_prec = 0;
%}
%debug
-%verbose
+%define api.prefix "gram_"
+%define api.pure
+%define parse.lac full
%defines
-%locations
-%pure-parser
%error-verbose
-%defines
-%name-prefix="gram_"
+%expect 0
+%locations
+%verbose
%initial-action
{
@@ -85,16 +111,17 @@ 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;
+ named_ref *named_ref;
};
/* Define the tokens together with their human representation. */
@@ -123,19 +150,18 @@ static int current_prec = 0;
`----------------------*/
%token
- PERCENT_AFTER_HEADER "%after-header"
- PERCENT_BEFORE_HEADER "%before-header"
+ PERCENT_CODE "%code"
PERCENT_DEBUG "%debug"
PERCENT_DEFAULT_PREC "%default-prec"
PERCENT_DEFINE "%define"
PERCENT_DEFINES "%defines"
- PERCENT_END_HEADER "%end-header"
PERCENT_ERROR_VERBOSE "%error-verbose"
PERCENT_EXPECT "%expect"
PERCENT_EXPECT_RR "%expect-rr"
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"
@@ -149,13 +175,13 @@ static int current_prec = 0;
PERCENT_REQUIRE "%require"
PERCENT_SKELETON "%skeleton"
PERCENT_START "%start"
- PERCENT_START_HEADER "%start-header"
PERCENT_TOKEN_TABLE "%token-table"
PERCENT_VERBOSE "%verbose"
PERCENT_YACC "%yacc"
;
%token BRACED_CODE "{...}"
+%token BRACKETED_ID "[identifier]"
%token CHAR "char"
%token EPILOGUE "epilogue"
%token EQUAL "="
@@ -166,33 +192,42 @@ static int current_prec = 0;
%token PROLOGUE "%{...%}"
%token SEMICOLON ";"
%token TYPE "type"
+%token TYPE_TAG_ANY "<*>"
+%token TYPE_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 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
+%type symbols.1 symbols.prec generic_symlist generic_symlist_item
+%type named_ref.opt
+
%%
input:
- declarations "%%" grammar epilogue.opt
+ prologue_declarations "%%" grammar epilogue.opt
;
@@ -200,47 +235,40 @@ 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, typed);
- }
-| "%after-header" "{...}"
- {
- /* Remove the '{', and replace the '}' with '\n'. */
- $2[strlen ($2) - 1] = '\n';
- prologue_augment (translate_code ($2+1, @2), @2, true);
- }
-| "%before-header" "{...}"
+| "%{...%}"
{
- /* Remove the '{', and replace the '}' with '\n'. */
- $2[strlen ($2) - 1] = '\n';
- prologue_augment (translate_code ($2+1, @2), @2, false);
+ 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
+| "%debug" { debug = true; }
+| "%define" variable content.opt
{
- static char one[] = "1";
- muscle_insert ($2, one);
+ muscle_percent_define_insert ($2, @2, $3,
+ MUSCLE_PERCENT_DEFINE_GRAMMAR_FILE);
}
-| "%define" string_content string_content { muscle_insert ($2, $3); }
-| "%defines" { defines_flag = true; }
-| "%end-header" "{...}"
+| "%defines" { defines_flag = true; }
+| "%defines" STRING
{
- /* Remove the '{', and replace the '}' with '\n'. */
- $2[strlen ($2) - 1] = '\n';
- muscle_code_grow ("end_header", translate_code ($2+1, @2), @2);
+ 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_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;
@@ -248,27 +276,66 @@ 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 ();
}
-| "%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; }
-| "%start-header" "{...}"
+| "%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"
{
- /* Remove the '{', and replace the '}' with '\n'. */
- $2[strlen ($2) - 1] = '\n';
- muscle_code_grow ("start_header", translate_code ($2+1, @2), @2);
+ /* %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);
}
-| "%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 (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)
+ {
+ memcpy (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? */ ";"
;
@@ -279,21 +346,29 @@ 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_free ($3);
+ code_props code;
+ code_props_symbol_action_init (&code, $2, @2);
+ code_props_translate_code (&code);
+ {
+ symbol_list *list;
+ for (list = $3; list; list = list->next)
+ symbol_list_destructor_set (list, &code);
+ 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_free ($3);
+ code_props code;
+ code_props_symbol_action_init (&code, $2, @2);
+ code_props_translate_code (&code);
+ {
+ symbol_list *list;
+ for (list = $3; list; list = list->next)
+ symbol_list_printer_set (list, &code);
+ symbol_list_free ($3);
+ }
}
| "%default-prec"
{
@@ -303,6 +378,18 @@ 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 ();
+ }
;
@@ -318,21 +405,11 @@ 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 ();
}
;
@@ -353,21 +430,22 @@ 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;
@@ -382,13 +460,40 @@ 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); }
+| "<>" { $$ = symbol_list_default_tagless_new (@1); }
;
/* One token definition. */
@@ -396,6 +501,7 @@ symbol_def:
TYPE
{
current_type = $1;
+ tag_seen = true;
}
| id
{
@@ -451,7 +557,11 @@ rules_or_grammar_declaration:
;
rules:
- id_colon { current_lhs = $1; current_lhs_location = @1; } rhses.1
+ id_colon named_ref.opt { current_lhs ($1, @1, $2); } rhses.1
+ {
+ /* Free the current lhs. */
+ current_lhs (0, @1, 0);
+ }
;
rhses.1:
@@ -462,11 +572,12 @@ rhses.1:
rhs:
/* Nothing. */
- { grammar_current_rule_begin (current_lhs, current_lhs_location); }
-| rhs symbol
- { grammar_current_rule_symbol_append ($2, @2); }
-| rhs "{...}"
- { grammar_current_rule_action_append ($2, @2); }
+ { grammar_current_rule_begin (current_lhs_symbol, current_lhs_location,
+ current_lhs_named_ref); }
+| rhs symbol named_ref.opt
+ { grammar_current_rule_symbol_append ($2, @2, $3); }
+| rhs "{...}" named_ref.opt
+ { grammar_current_rule_action_append ($2, @2, $3); }
| rhs "%prec" symbol
{ grammar_current_rule_prec_set ($3, @3); }
| rhs "%dprec" INT
@@ -475,6 +586,48 @@ rhs:
{ grammar_current_rule_merge_set ($3, @3); }
;
+named_ref.opt:
+ /* Nothing. */ { $$ = 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
+;
+
+
+/*-------------*
+ | 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 ();
+ $$ = plain_code.code;
+ }
+;
+
/*---------------*
| Identifiers. |
@@ -513,19 +666,16 @@ string_as_id:
}
;
-/* A string used for its contents. Don't quote it. */
-string_content:
- STRING
- { $$ = $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 ();
}
;
@@ -548,7 +698,7 @@ lloc_default (YYLTYPE const *rhs, int n)
loc.start = rhs[n].end;
loc.end = rhs[n].end;
- /* Ignore empty nonterminals the start of the the right-hand side.
+ /* Ignore empty nonterminals the start of the right-hand side.
Do not bother to ignore them at the end of the right-hand side,
since empty nonterminals have the same end as their predecessors. */
for (i = 1; i <= n; i++)
@@ -585,27 +735,19 @@ add_param (char const *type, char *decl, location loc)
/* Strip the surrounding '{' and '}', and any blanks just inside
the braces. */
- while (*--p == ' ' || *p == '\t')
- continue;
+ --p;
+ while (c_isspace ((unsigned char) *p))
+ --p;
p[1] = '\0';
- while (*++decl == ' ' || *decl == '\t')
- continue;
+ ++decl;
+ while (c_isspace ((unsigned char) *decl))
+ ++decl;
if (! name_start)
complain_at (loc, _("missing identifier in parameter declaration"));
else
{
- char *name;
- size_t name_len;
-
- for (name_len = 1;
- memchr (alphanum, name_start[name_len], sizeof alphanum);
- name_len++)
- continue;
-
- name = xmalloc (name_len + 1);
- memcpy (name, name_start, name_len);
- name[name_len] = '\0';
+ char *name = xmemdup0 (name_start, strspn (name_start, alphanum));
muscle_pair_list_grow (type, decl, name);
free (name);
}
@@ -613,14 +755,15 @@ add_param (char const *type, char *decl, location loc)
gram_scanner_last_string_free ();
}
+
static void
version_check (location const *loc, char const *version)
{
if (strverscmp (version, PACKAGE_VERSION) > 0)
{
complain_at (*loc, "require bison %s, but have %s",
- version, PACKAGE_VERSION);
- exit (63);
+ version, PACKAGE_VERSION);
+ exit (EX_MISMATCH);
}
}