Future/bison
1
0
Fork 0
mirror of https://git.savannah.gnu.org/git/bison.git synced 2026-03-09 12:23:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

* src/scan-gram.l: No longer "parse" things after `%union' until

Browse Source 
`{'.  Rather, return a single "%union" token.
No longer make symbols: return strings, and leave the conversion
to symbols to the parser.
(SC_PRE_CODE, token_type): Remove.
* src/parse-gram.y (%union): New field `character'.
Sort tokens.
(CHAR): New token.
(ID, ID_COLON): Now that the scanner no longer makes them
identifiers, adjust all uses to invoke symbol_get.
(id_colon): New, wraps the conversion from string to symbol.
(%union): Accept a possible union_name.
(symbol): Now can be a char.
* data/c.m4 (b4_union_name): Leave a default value.
* data/glr.c, data/yacc.c: Use it.
This commit is contained in:
Akim Demaille
2006-06-19 16:49:44 +00:00
parent 40637e8169
commit 58d7a1a1c7
5 changed files with 707 additions and 661 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
ChangeLog
View File

@@ -1,3 +1,21 @@
2006-06-19 Akim Demaille <akim@epita.fr>
* src/scan-gram.l: No longer "parse" things after `%union' until
`{'. Rather, return a single "%union" token.
No longer make symbols: return strings, and leave the conversion
to symbols to the parser.
(SC_PRE_CODE, token_type): Remove.
* src/parse-gram.y (%union): New field `character'.
Sort tokens.
(CHAR): New token.
(ID, ID_COLON): Now that the scanner no longer makes them
identifiers, adjust all uses to invoke symbol_get.
(id_colon): New, wraps the conversion from string to symbol.
(%union): Accept a possible union_name.
(symbol): Now can be a char.
* data/c.m4 (b4_union_name): Leave a default value.
* data/glr.c, data/yacc.c: Use it.
2006-06-11 Joel E. Denny <jdenny@ces.clemson.edu>
For associating token numbers with token names for "yacc.c", don't use

905
src/parse-gram.c
View File

File diff suppressed because it is too large Load Diff

171
src/parse-gram.h
View File

@@ -47,48 +47,49 @@
PERCENT_TYPE = 262,
PERCENT_DESTRUCTOR = 263,
PERCENT_PRINTER = 264,
PERCENT_UNION = 265,
PERCENT_LEFT = 266,
PERCENT_RIGHT = 267,
PERCENT_NONASSOC = 268,
PERCENT_PREC = 269,
PERCENT_DPREC = 270,
PERCENT_MERGE = 271,
PERCENT_DEBUG = 272,
PERCENT_DEFAULT_PREC = 273,
PERCENT_DEFINE = 274,
PERCENT_DEFINES = 275,
PERCENT_ERROR_VERBOSE = 276,
PERCENT_EXPECT = 277,
PERCENT_EXPECT_RR = 278,
PERCENT_FILE_PREFIX = 279,
PERCENT_GLR_PARSER = 280,
PERCENT_INITIAL_ACTION = 281,
PERCENT_LEX_PARAM = 282,
PERCENT_LOCATIONS = 283,
PERCENT_NAME_PREFIX = 284,
PERCENT_NO_DEFAULT_PREC = 285,
PERCENT_NO_LINES = 286,
PERCENT_NONDETERMINISTIC_PARSER = 287,
PERCENT_OUTPUT = 288,
PERCENT_PARSE_PARAM = 289,
PERCENT_PURE_PARSER = 290,
PERCENT_REQUIRE = 291,
PERCENT_SKELETON = 292,
PERCENT_START = 293,
PERCENT_TOKEN_TABLE = 294,
PERCENT_VERBOSE = 295,
PERCENT_YACC = 296,
TYPE = 297,
EQUAL = 298,
SEMICOLON = 299,
PIPE = 300,
ID = 301,
ID_COLON = 302,
PERCENT_PERCENT = 303,
PERCENT_LEFT = 265,
PERCENT_RIGHT = 266,
PERCENT_NONASSOC = 267,
PERCENT_PREC = 268,
PERCENT_DPREC = 269,
PERCENT_MERGE = 270,
PERCENT_DEBUG = 271,
PERCENT_DEFAULT_PREC = 272,
PERCENT_DEFINE = 273,
PERCENT_DEFINES = 274,
PERCENT_ERROR_VERBOSE = 275,
PERCENT_EXPECT = 276,
PERCENT_EXPECT_RR = 277,
PERCENT_FILE_PREFIX = 278,
PERCENT_GLR_PARSER = 279,
PERCENT_INITIAL_ACTION = 280,
PERCENT_LEX_PARAM = 281,
PERCENT_LOCATIONS = 282,
PERCENT_NAME_PREFIX = 283,
PERCENT_NO_DEFAULT_PREC = 284,
PERCENT_NO_LINES = 285,
PERCENT_NONDETERMINISTIC_PARSER = 286,
PERCENT_OUTPUT = 287,
PERCENT_PARSE_PARAM = 288,
PERCENT_PURE_PARSER = 289,
PERCENT_REQUIRE = 290,
PERCENT_SKELETON = 291,
PERCENT_START = 292,
PERCENT_TOKEN_TABLE = 293,
PERCENT_VERBOSE = 294,
PERCENT_YACC = 295,
BRACED_CODE = 296,
CHAR = 297,
EPILOGUE = 298,
EQUAL = 299,
ID = 300,
ID_COLON = 301,
PERCENT_PERCENT = 302,
PIPE = 303,
PROLOGUE = 304,
EPILOGUE = 305,
BRACED_CODE = 306
SEMICOLON = 305,
TYPE = 306,
PERCENT_UNION = 307
};
#endif
/* Tokens. */
@@ -100,48 +101,49 @@
#define PERCENT_TYPE 262
#define PERCENT_DESTRUCTOR 263
#define PERCENT_PRINTER 264
#define PERCENT_UNION 265
#define PERCENT_LEFT 266
#define PERCENT_RIGHT 267
#define PERCENT_NONASSOC 268
#define PERCENT_PREC 269
#define PERCENT_DPREC 270
#define PERCENT_MERGE 271
#define PERCENT_DEBUG 272
#define PERCENT_DEFAULT_PREC 273
#define PERCENT_DEFINE 274
#define PERCENT_DEFINES 275
#define PERCENT_ERROR_VERBOSE 276
#define PERCENT_EXPECT 277
#define PERCENT_EXPECT_RR 278
#define PERCENT_FILE_PREFIX 279
#define PERCENT_GLR_PARSER 280
#define PERCENT_INITIAL_ACTION 281
#define PERCENT_LEX_PARAM 282
#define PERCENT_LOCATIONS 283
#define PERCENT_NAME_PREFIX 284
#define PERCENT_NO_DEFAULT_PREC 285
#define PERCENT_NO_LINES 286
#define PERCENT_NONDETERMINISTIC_PARSER 287
#define PERCENT_OUTPUT 288
#define PERCENT_PARSE_PARAM 289
#define PERCENT_PURE_PARSER 290
#define PERCENT_REQUIRE 291
#define PERCENT_SKELETON 292
#define PERCENT_START 293
#define PERCENT_TOKEN_TABLE 294
#define PERCENT_VERBOSE 295
#define PERCENT_YACC 296
#define TYPE 297
#define EQUAL 298
#define SEMICOLON 299
#define PIPE 300
#define ID 301
#define ID_COLON 302
#define PERCENT_PERCENT 303
#define PERCENT_LEFT 265
#define PERCENT_RIGHT 266
#define PERCENT_NONASSOC 267
#define PERCENT_PREC 268
#define PERCENT_DPREC 269
#define PERCENT_MERGE 270
#define PERCENT_DEBUG 271
#define PERCENT_DEFAULT_PREC 272
#define PERCENT_DEFINE 273
#define PERCENT_DEFINES 274
#define PERCENT_ERROR_VERBOSE 275
#define PERCENT_EXPECT 276
#define PERCENT_EXPECT_RR 277
#define PERCENT_FILE_PREFIX 278
#define PERCENT_GLR_PARSER 279
#define PERCENT_INITIAL_ACTION 280
#define PERCENT_LEX_PARAM 281
#define PERCENT_LOCATIONS 282
#define PERCENT_NAME_PREFIX 283
#define PERCENT_NO_DEFAULT_PREC 284
#define PERCENT_NO_LINES 285
#define PERCENT_NONDETERMINISTIC_PARSER 286
#define PERCENT_OUTPUT 287
#define PERCENT_PARSE_PARAM 288
#define PERCENT_PURE_PARSER 289
#define PERCENT_REQUIRE 290
#define PERCENT_SKELETON 291
#define PERCENT_START 292
#define PERCENT_TOKEN_TABLE 293
#define PERCENT_VERBOSE 294
#define PERCENT_YACC 295
#define BRACED_CODE 296
#define CHAR 297
#define EPILOGUE 298
#define EQUAL 299
#define ID 300
#define ID_COLON 301
#define PERCENT_PERCENT 302
#define PIPE 303
#define PROLOGUE 304
#define EPILOGUE 305
#define BRACED_CODE 306
#define SEMICOLON 305
#define TYPE 306
#define PERCENT_UNION 307
@@ -156,9 +158,10 @@ typedef union YYSTYPE
char *chars;
assoc assoc;
uniqstr uniqstr;
unsigned char character;
}
/* Line 1529 of yacc.c. */
#line 162 "../../src/parse-gram.h"
/* Line 1528 of yacc.c. */
#line 165 "../../src/parse-gram.h"
YYSTYPE;
# define yystype YYSTYPE /* obsolescent; will be withdrawn */
# define YYSTYPE_IS_DECLARED 1

132
src/parse-gram.y
View File

@@ -99,6 +99,7 @@ static int current_prec = 0;
char *chars;
assoc assoc;
uniqstr uniqstr;
unsigned char character;
};
/* Define the tokens together with their human representation. */
@@ -113,8 +114,6 @@ 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"
@@ -157,35 +156,37 @@ 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 "{...}"
%token SEMICOLON ";"
%token TYPE "type"
%type <chars> STRING string_content
"{...}"
"%union {...}"
PROLOGUE EPILOGUE
%printer { fprintf (stderr, "\"%s\"", $$); }
STRING string_content
%printer { fprintf (stderr, "{\n%s\n}", $$); }
"{...}"
"%union {...}"
PROLOGUE EPILOGUE
%type <uniqstr> TYPE
%type <character> CHAR
%printer { fprintf (stderr, "'%c' (%d)", $$, $$); } CHAR
%type <chars> STRING string_content "{...}" PROLOGUE EPILOGUE
%printer { fprintf (stderr, "\"%s\"", $$); } STRING string_content
%printer { fprintf (stderr, "{\n%s\n}", $$); } "{...}" PROLOGUE EPILOGUE
%type <uniqstr> TYPE ID ID_COLON
%printer { fprintf (stderr, "<%s>", $$); } TYPE
%printer { fprintf (stderr, "%s", $$); } 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
%%
@@ -252,22 +253,6 @@ 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
{
symbol_list *list;
@@ -294,6 +279,40 @@ grammar_declaration:
}
;
/*----------*
| %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;
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);
}
;
symbol_declaration:
"%nterm" { current_class = nterm_sym; } symbol_defs.1
{
@@ -352,24 +371,24 @@ symbol_def:
{
current_type = $1;
}
| 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 +425,7 @@ 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:
@@ -431,9 +450,32 @@ rhs:
{ grammar_current_rule_merge_set ($3, @3); }
;
/*---------------*
| Identifiers. |
*---------------*/
/* Identifiers are return as uniqstr by the scanner. Depending on
their use, we may need to make them genuine symbols. */
id:
ID { $$ = symbol_get ($1, @1); }
| CHAR { char cp[4] = { '\'', $1, '\'', 0 };
$$ = symbol_get (quotearg_style (escape_quoting_style, cp),
@1);
symbol_class_set ($$, token_sym, @1, false);
symbol_user_token_number_set ($$, $1, @1);
}
;
id_colon:
ID_COLON { $$ = symbol_get ($1, @1); }
;
symbol:
ID { $$ = $1; }
| string_as_id { $$ = $1; }
id
| string_as_id
;
/* A string used as an ID: quote it. */

142
src/scan-gram.l
View File

@@ -88,9 +88,6 @@ static void unexpected_newline (boundary, char const *);
/* A identifier was just read in directives/rules. Special state
to capture the sequence `identifier :'. */
%x SC_AFTER_IDENTIFIER
/* A keyword that should be followed by some code was read (e.g.
%printer). */
%x SC_PRE_CODE
/* Three types of user code:
- prologue (code between `%{' `%}' in the first section, before %%);
@@ -124,9 +121,6 @@ splice (\\[ \f\t\v]*\n)*
/* Parent context state, when applicable. */
int context_state IF_LINT (= 0);
/* Token type to return, when applicable. */
int token_type IF_LINT (= 0);
/* Location of most recent identifier, when applicable. */
location id_loc IF_LINT (= empty_location);
@@ -145,7 +139,7 @@ splice (\\[ \f\t\v]*\n)*
| Scanning white space. |
`-----------------------*/
<INITIAL,SC_AFTER_IDENTIFIER,SC_PRE_CODE>
<INITIAL,SC_AFTER_IDENTIFIER>
{
/* Comments and white space. */
"," warn_at (*loc, _("stray `,' treated as white space"));
@@ -170,46 +164,46 @@ splice (\\[ \f\t\v]*\n)*
`----------------------------*/
<INITIAL>
{
"%binary" return PERCENT_NONASSOC;
"%debug" return PERCENT_DEBUG;
"%default"[-_]"prec" return PERCENT_DEFAULT_PREC;
"%define" return PERCENT_DEFINE;
"%defines" return PERCENT_DEFINES;
"%destructor" /* FIXME: Remove once %union handled differently. */ token_type = BRACED_CODE; return PERCENT_DESTRUCTOR;
"%dprec" return PERCENT_DPREC;
"%error"[-_]"verbose" return PERCENT_ERROR_VERBOSE;
"%expect" return PERCENT_EXPECT;
"%expect"[-_]"rr" return PERCENT_EXPECT_RR;
"%file-prefix" return PERCENT_FILE_PREFIX;
"%binary" return PERCENT_NONASSOC;
"%debug" return PERCENT_DEBUG;
"%default"[-_]"prec" return PERCENT_DEFAULT_PREC;
"%define" return PERCENT_DEFINE;
"%defines" return PERCENT_DEFINES;
"%destructor" return PERCENT_DESTRUCTOR;
"%dprec" return PERCENT_DPREC;
"%error"[-_]"verbose" return PERCENT_ERROR_VERBOSE;
"%expect" return PERCENT_EXPECT;
"%expect"[-_]"rr" return PERCENT_EXPECT_RR;
"%file-prefix" return PERCENT_FILE_PREFIX;
"%fixed"[-_]"output"[-_]"files" return PERCENT_YACC;
"%initial-action" /* FIXME: Remove once %union handled differently. */ token_type = BRACED_CODE; return PERCENT_INITIAL_ACTION;
"%glr-parser" return PERCENT_GLR_PARSER;
"%left" return PERCENT_LEFT;
"%lex-param" /* FIXME: Remove once %union handled differently. */ token_type = BRACED_CODE; return PERCENT_LEX_PARAM;
"%locations" return PERCENT_LOCATIONS;
"%merge" return PERCENT_MERGE;
"%name"[-_]"prefix" return PERCENT_NAME_PREFIX;
"%no"[-_]"default"[-_]"prec" return PERCENT_NO_DEFAULT_PREC;
"%no"[-_]"lines" return PERCENT_NO_LINES;
"%nonassoc" return PERCENT_NONASSOC;
"%nondeterministic-parser" return PERCENT_NONDETERMINISTIC_PARSER;
"%nterm" return PERCENT_NTERM;
"%output" return PERCENT_OUTPUT;
"%parse-param" /* FIXME: Remove once %union handled differently. */ token_type = BRACED_CODE; return PERCENT_PARSE_PARAM;
"%prec" return PERCENT_PREC;
"%printer" /* FIXME: Remove once %union handled differently. */ token_type = BRACED_CODE; return PERCENT_PRINTER;
"%pure"[-_]"parser" return PERCENT_PURE_PARSER;
"%require" return PERCENT_REQUIRE;
"%right" return PERCENT_RIGHT;
"%skeleton" return PERCENT_SKELETON;
"%start" return PERCENT_START;
"%term" return PERCENT_TOKEN;
"%token" return PERCENT_TOKEN;
"%token"[-_]"table" return PERCENT_TOKEN_TABLE;
"%type" return PERCENT_TYPE;
"%union" token_type = PERCENT_UNION; BEGIN SC_PRE_CODE;
"%verbose" return PERCENT_VERBOSE;
"%yacc" return PERCENT_YACC;
"%initial-action" return PERCENT_INITIAL_ACTION;
"%glr-parser" return PERCENT_GLR_PARSER;
"%left" return PERCENT_LEFT;
"%lex-param" return PERCENT_LEX_PARAM;
"%locations" return PERCENT_LOCATIONS;
"%merge" return PERCENT_MERGE;
"%name"[-_]"prefix" return PERCENT_NAME_PREFIX;
"%no"[-_]"default"[-_]"prec" return PERCENT_NO_DEFAULT_PREC;
"%no"[-_]"lines" return PERCENT_NO_LINES;
"%nonassoc" return PERCENT_NONASSOC;
"%nondeterministic-parser" return PERCENT_NONDETERMINISTIC_PARSER;
"%nterm" return PERCENT_NTERM;
"%output" return PERCENT_OUTPUT;
"%parse-param" return PERCENT_PARSE_PARAM;
"%prec" return PERCENT_PREC;
"%printer" return PERCENT_PRINTER;
"%pure"[-_]"parser" return PERCENT_PURE_PARSER;
"%require" return PERCENT_REQUIRE;
"%right" return PERCENT_RIGHT;
"%skeleton" return PERCENT_SKELETON;
"%start" return PERCENT_START;
"%term" return PERCENT_TOKEN;
"%token" return PERCENT_TOKEN;
"%token"[-_]"table" return PERCENT_TOKEN_TABLE;
"%type" return PERCENT_TYPE;
"%union" return PERCENT_UNION;
"%verbose" return PERCENT_VERBOSE;
"%yacc" return PERCENT_YACC;
{directive} {
complain_at (*loc, _("invalid directive: %s"), quote (yytext));
@@ -220,7 +214,7 @@ splice (\\[ \f\t\v]*\n)*
";" return SEMICOLON;
{id} {
val->symbol = symbol_get (yytext, *loc);
val->uniqstr = uniqstr_new (yytext);
id_loc = *loc;
BEGIN SC_AFTER_IDENTIFIER;
}
@@ -248,7 +242,6 @@ splice (\\[ \f\t\v]*\n)*
if (current_rule && current_rule->action)
grammar_midrule_action ();
STRING_GROW;
token_type = BRACED_CODE;
braces_level = 0;
code_start = loc->start;
BEGIN SC_BRACED_CODE;
@@ -372,15 +365,10 @@ splice (\\[ \f\t\v]*\n)*
STRING_GROW;
STRING_FINISH;
loc->start = token_start;
val->symbol = symbol_get (quotearg_style (escape_quoting_style,
last_string),
*loc);
symbol_class_set (val->symbol, token_sym, *loc, false);
last_string_1 = last_string[1];
symbol_user_token_number_set (val->symbol, last_string_1, *loc);
val->character = last_string[1];
STRING_FREE;
BEGIN INITIAL;
return ID;
return CHAR;
}
\n unexpected_newline (token_start, "'"); BEGIN INITIAL;
<<EOF>> unexpected_eof (token_start, "'"); BEGIN INITIAL;
@@ -501,45 +489,11 @@ splice (\\[ \f\t\v]*\n)*
}
/*---------------------------------------------------------------.
| Scanning after %union etc., possibly followed by white space. |
| For %union only, allow arbitrary C code to appear before the |
| following brace, as an extension to POSIX. |
`---------------------------------------------------------------*/
<SC_PRE_CODE>
{
. {
bool valid = yytext[0] == '{' || token_type == PERCENT_UNION;
scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0);
yyless (0);
if (valid)
{
braces_level = -1;
code_start = loc->start;
BEGIN SC_BRACED_CODE;
}
else
{
complain_at (*loc, _("missing `{' in %s"),
token_name (token_type));
obstack_sgrow (&obstack_for_string, "{}");
STRING_FINISH;
val->chars = last_string;
BEGIN INITIAL;
return token_type;
}
}
<<EOF>> unexpected_eof (scanner_cursor, "{}"); BEGIN INITIAL;
}
/*---------------------------------------------------------------.
| Scanning some code in braces (%union and actions). The initial |
| "{" is already eaten. |
`---------------------------------------------------------------*/
/*-----------------------------------------------------------.
| Scanning some code in braces (actions). The initial "{" is |
| already eaten. |
`-----------------------------------------------------------*/
<SC_BRACED_CODE>
{
@@ -556,7 +510,7 @@ splice (\\[ \f\t\v]*\n)*
val->chars = last_string;
gram_last_braced_code_loc = *loc;
BEGIN INITIAL;
return token_type;
return BRACED_CODE;
}
}