#include <config.h>
#include "system.h"
+#include <strverscmp.h>
+
#include "complain.h"
#include "conflicts.h"
#include "files.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);
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
%error-verbose
%defines
%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;
};
/* Define the tokens together with their human representation. */
%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"
`----------------------*/
%token
+ PERCENT_CODE "%code"
+ PERCENT_CODE_TOP "%code-top"
PERCENT_DEBUG "%debug"
PERCENT_DEFAULT_PREC "%default-prec"
PERCENT_DEFINE "%define"
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_LEX_PARAM "%lex-param"
PERCENT_LOCATIONS "%locations"
PERCENT_NAME_PREFIX "%name-prefix"
PERCENT_NO_DEFAULT_PREC "%no-default-prec"
PERCENT_NONDETERMINISTIC_PARSER
"%nondeterministic-parser"
PERCENT_OUTPUT "%output"
- PERCENT_PARSE_PARAM "%parse-param {...}"
+ 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"
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 <chars> STRING string_content
- "%destructor {...}"
- "%initial-action {...}"
- "%lex-param {...}"
- "%parse-param {...}"
- "%printer {...}"
- "%union {...}"
- PROLOGUE EPILOGUE
-%printer { fprintf (stderr, "\"%s\"", $$); }
- STRING string_content
+%token SEMICOLON ";"
+%token TYPE "type"
+%token TYPE_TAG_ANY "<*>"
+%token TYPE_TAG_NONE "<!>"
+
+%type <character> CHAR
+%printer { fputs (char_name ($$), stderr); } CHAR
+
+/* braceless is not to be used for rule or symbol actions, as it
+ calls translate_code. */
+%type <chars> STRING "%{...%}" EPILOGUE braceless content content.opt
+%type <code> "{...}"
+%printer { fputs (quotearg_style (c_quoting_style, $$), stderr); }
+ STRING
%printer { fprintf (stderr, "{\n%s\n}", $$); }
- "%destructor {...}"
- "%initial-action {...}"
- "%lex-param {...}"
- "%parse-param {...}"
- "%printer {...}"
- "%union {...}"
- PROLOGUE EPILOGUE
-%type <uniqstr> TYPE
+ braceless content content.opt "{...}" "%{...%}" EPILOGUE
+
+%type <uniqstr> TYPE ID ID_COLON
%printer { fprintf (stderr, "<%s>", $$); } TYPE
+%printer { fputs ($$, stderr); } ID
+%printer { fprintf (stderr, "%s:", $$); } ID_COLON
+
%type <integer> INT
%printer { fprintf (stderr, "%d", $$); } INT
-%type <symbol> ID symbol string_as_id
-%printer { fprintf (stderr, "%s", $$->tag); } ID symbol string_as_id
-%type <symbol> ID_COLON
-%printer { fprintf (stderr, "%s:", $$->tag); } ID_COLON
+
+%type <symbol> id id_colon symbol string_as_id
+%printer { fprintf (stderr, "%s", $$->tag); } id symbol string_as_id
+%printer { fprintf (stderr, "%s:", $$->tag); } id_colon
+
%type <assoc> precedence_declarator
-%type <list> symbols.1
+%type <list> symbols.1 generic_symlist generic_symlist_item
%%
input:
- declarations "%%" grammar epilogue.opt
+ prologue_declarations "%%" grammar epilogue.opt
;
| 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
- {
- static char one[] = "1";
- muscle_insert ($2, one);
- }
-| "%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; }
+| "%{...%}" { prologue_augment (translate_code ($1, @1), @1, union_seen); }
+| "%debug" { debug_flag = true; }
+| "%define" STRING content.opt { 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 { spec_file_prefix = $3; }
| "%glr-parser"
{
nondeterministic_parser = true;
glr_parser = true;
}
-| "%initial-action {...}"
+| "%initial-action" "{...}"
{
- muscle_code_grow ("initial_action", $1, @1);
+ muscle_code_grow ("initial_action", translate_symbol_action ($2, @2), @2);
}
-| "%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; }
+| "%lex-param" "{...}" { add_param ("lex_param", $2, @2); }
+| "%locations" { locations_flag = true; }
+| "%name-prefix" "=" STRING { spec_name_prefix = $3; }
+| "%no-lines" { no_lines_flag = true; }
+| "%nondeterministic-parser" { nondeterministic_parser = true; }
+| "%output" "=" STRING { spec_outfile = $3; }
+| "%parse-param" "{...}" { add_param ("parse_param", $2, @2); }
+| "%pure-parser" { pure_parser = true; }
+| "%push-parser" { push_parser = true; }
+| "%require" STRING { version_check (&@2, $2); }
+| "%skeleton" STRING { skeleton = $2; }
+| "%token-table" { token_table_flag = true; }
+| "%verbose" { report_flag = report_states; }
+| "%yacc" { yacc_flag = true; }
| /*FIXME: Err? What is this horror doing here? */ ";"
;
{
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);
+ const char *action = translate_symbol_action ($2, @2);
+ for (list = $3; list; list = list->next)
+ symbol_list_destructor_set (list, action, @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, @1);
- symbol_list_free ($2);
+ const char *action = translate_symbol_action ($2, @2);
+ for (list = $3; list; list = list->next)
+ symbol_list_printer_set (list, action, @2);
+ symbol_list_free ($3);
}
| "%default-prec"
{
{
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); }
+;
+
+
+/*----------*
+ | %union. |
+ *----------*/
+
+%token PERCENT_UNION "%union";
+
+union_name:
+ /* Nothing. */ {}
+| ID { muscle_code_grow ("union_name", $1, @1); }
+;
+
+grammar_declaration:
+ "%union" union_name "{...}"
+ {
+ 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);
+ }
;
+
+
+
symbol_declaration:
"%nterm" { current_class = nterm_sym; } symbol_defs.1
{
| "%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);
}
;
++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;
type.opt:
/* Nothing. */ { current_type = NULL; }
-| TYPE { current_type = $1; }
+| TYPE { current_type = $1; tag_seen = true; }
;
-/* One or more nonterminals to be %typed. */
-
+/* 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. */
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);
;
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:
{ grammar_current_rule_begin (current_lhs, current_lhs_location); }
| rhs symbol
{ grammar_current_rule_symbol_append ($2, @2); }
-| rhs action
+| rhs "{...}"
+ { grammar_current_rule_action_append ($2, @2); }
| rhs "%prec" symbol
{ grammar_current_rule_prec_set ($3, @3); }
| rhs "%dprec" INT
{ grammar_current_rule_merge_set ($3, @3); }
;
-symbol:
- ID { $$ = $1; }
-| string_as_id { $$ = $1; }
+
+/*-----------*
+ | content. |
+ *-----------*/
+
+content:
+ STRING
+| braceless
+;
+
+/* Some content or "1" by default. */
+content.opt:
+ /* Nothing. */
+ {
+ static char one[] = "1";
+ $$ = one;
+ }
+| content
;
-/* Handle the semantics of an action specially, with a mid-rule
- action, so that grammar_current_rule_action_append is invoked
- immediately after the braced code is read by the scanner.
-
- This implementation relies on the LALR(1) parsing algorithm.
- If grammar_current_rule_action_append were executed in a normal
- action for this rule, then when the input grammar contains two
- successive actions, the scanner would have to read both actions
- before reducing this rule. That wouldn't work, since the scanner
- relies on all preceding input actions being processed by
- grammar_current_rule_action_append before it scans the next
- action. */
-action:
- { grammar_current_rule_action_append (last_string, last_braced_code_loc); }
- BRACED_CODE
+
+braceless:
+ "{...}"
+ {
+ $1[strlen ($1) - 1] = '\n';
+ $$ = translate_code ($1 + 1, @1);
+ }
+;
+
+
+/*---------------*
+ | 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 { $$ = symbol_from_uniqstr ($1, @1); }
+;
+
+
+symbol:
+ id
+| string_as_id
;
/* A string used as an ID: quote it. */
}
;
-/* A string used for its contents. Don't quote it. */
-string_content:
- STRING
- { $$ = $1; }
-;
-
-
epilogue.opt:
/* Nothing. */
| "%%" EPILOGUE
{
- muscle_code_grow ("epilogue", $2, @2);
- scanner_last_string_free ();
+ muscle_code_grow ("epilogue", translate_code ($2, @2), @2);
+ gram_scanner_last_string_free ();
}
;
free (name);
}
- scanner_last_string_free ();
+ gram_scanner_last_string_free ();
}
+
static void
version_check (location const *loc, char const *version)
{
{
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);
+ }
+}
projects / bison.git / blobdiff