Files
bison/src/scan-gram.l
Akim Demaille e9955c8373 Have Bison grammars parsed by a Bison grammar.
* src/reader.c, src/reader.h (prologue_augment): New.
* src/reader.c (copy_definition): Remove.
* src/reader.h, src/reader.c (gram_start_symbol_set, prologue_augment)
(grammar_symbol_append, grammar_rule_begin, grammar_midrule_action)
(grammar_current_rule_prec_set, grammar_current_rule_check)
(grammar_current_rule_symbol_append)
(grammar_current_rule_action_append): Export.
* src/parse-gram.y (symbol_list_new, symbol_list_symbol_append_
(symbol_list_action_append): Remove.
Hook the routines from reader.
* src/scan-gram.l: In INITIAL, characters and strings are tokens.
* src/system.h (ATTRIBUTE_NORETURN, ATTRIBUTE_UNUSED): Now.
* src/reader.c (read_declarations): Remove, unused.
* src/parse-gram.y: Handle the epilogue.
* src/reader.h, src/reader.c (gram_start_symbol_set): Rename as...
(grammar_start_symbol_set): this.
* src/scan-gram.l: Be sure to ``use'' yycontrol to keep GCC quiet.
* src/reader.c (readgram): Remove, unused.
(reader): Adjust to insert eoftoken and axiom where appropriate.
* src/reader.c (copy_dollar): Replace with...
* src/scan-gram.h (handle_dollar): this.
* src/parse-gram.y: Remove `%thong'.
* src/reader.c (copy_at): Replace with...
* src/scan-gram.h (handle_at): this.
* src/complain.h, src/complain.c (warn_at, complain_at, fatal_at):
New.
* src/scan-gram.l (YY_LINES): Keep lineno synchronized for the
time being.
* src/reader.h, src/reader.c (grammar_rule_end): New.
* src/parse.y (current_type, current_class): New.
Implement `%nterm', `%token' support.
Merge `%term' into `%token'.
(string_as_id): New.
* src/symtab.h, src/symtab.c (symbol_make_alias): Don't pass the
type name.
* src/parse-gram.y: Be sure to handle properly the beginning of
rules.
* src/parse-gram.y: Handle %type.
* src/reader.c (grammar_rule_end): Call grammar_current_rule_check.
* src/parse-gram.y: More directives support.
* src/options.c: No longer handle source directives.
* src/parse-gram.y: Fix %output.
* src/parse-gram.y: Handle %union.
Use the prologue locations.
* src/reader.c (parse_union_decl): Remove.
* src/reader.h, src/reader.c (epilogue_set): New.
* src/parse-gram.y: Use it.
* data/bison.simple, data/bison.c++: b4_stype is now either not
defined, then default to int, or to the contents of %union,
without `union' itself.
Adjust.
* src/muscle_tab.c (muscle_init): Don't predefine `stype'.
* src/output.c (actions_output): Don't output braces, as they are
already handled by the scanner.
* src/scan-gram.l (SC_CHARACTER): Set the user_token_number of
characters to themselves.
* tests/reduce.at (Reduced Automaton): End the grammars with %% so
that the epilogue has a proper #line.
* src/parse-gram.y: Handle precedence/associativity.
* src/symtab.c (symbol_precedence_set): Requires the symbol to be
a terminal.
* src/scan-gram.l (SC_BRACED_CODE): Catch strings and characters.
* tests/calc.at: Do not use `%token "foo"' as it makes not sense
at all to define terminals that cannot be emitted.
* src/scan-gram.l: Escape M4 characters.
* src/scan-gram.l: Working properly with escapes in user
strings/characters.
* tests/torture.at (AT_DATA_TRIANGULAR_GRAMMAR)
(AT_DATA_HORIZONTAL_GRAMMAR): Respect the `%token ID NUM STRING'
grammar.
Use more modest sizes, as for the time being the parser does not
release memory, and therefore the process swallows a huge amount
of memory.
* tests/torture.at (AT_DATA_LOOKAHEADS_GRAMMAR): Adjust to the
stricter %token grammar.
* src/symtab.h (associativity): Add `undef_assoc'.
(symbol_precedence_set): Do nothing when passed an undef_assoc.
* src/symtab.c (symbol_check_alias_consistence): Adjust.
* tests/regression.at (Invalid %directive): Remove, as it is now
meaningless.
(Invalid inputs): Adjust to the new error messages.
(Token definitions): The new grammar doesn't allow too many
eccentricities.
* src/lex.h, src/lex.c: Remove.
* src/reader.c (lastprec, skip_to_char, read_signed_integer)
(copy_character, copy_string2, copy_string, copy_identifier)
(copy_comment, parse_token_decl, parse_type_decl, parse_assoc_decl)
(parse_muscle_decl, parse_dquoted_param, parse_skel_decl)
(parse_action): Remove.
* po/POTFILES.in: Adjust.
2002-06-11 20:16:05 +00:00

583 lines
16 KiB
C

/* Bison Grammar Scanner -*- C -*-
Copyright (C) 2002 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
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
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., 59 Temple Place, Suite 330, Boston, MA
02111-1307 USA
*/
%option debug nodefault noyywrap nounput never-interactive stack
%option prefix="gram_" outfile="lex.yy.c"
%{
#include "system.h"
#include "complain.h"
#include "quote.h"
#include "getargs.h"
#include "gram.h"
#include "reader.h"
/* Each time we match a string, move the end cursor to its end. */
#define YY_USER_ACTION LOCATION_COLUMNS (*yylloc, yyleng)
#define YY_LINES LOCATION_LINES (*yylloc, yyleng); lineno += yyleng;
#define YY_STEP LOCATION_STEP (*yylloc)
/* Appending to the STRING_OBSTACK. */
#define YY_INIT obstack_init (&string_obstack)
#define YY_GROW obstack_grow (&string_obstack, yytext, yyleng)
#define YY_FINISH obstack_1grow (&string_obstack, '\0'); yylval->string = obstack_finish (&string_obstack);
/* This is only to avoid GCC warnings. */
#define YY_USER_INIT if (yycontrol) {;};
static struct obstack string_obstack;
static int braces_level = 0;
static int percent_percent_count = 0;
static void handle_dollar PARAMS ((char *cp));
static void handle_at PARAMS ((char *cp));
%}
%x SC_COMMENT
%x SC_STRING SC_CHARACTER
%x SC_ESCAPED_STRING SC_ESCAPED_CHARACTER
%x SC_BRACED_CODE SC_PROLOGUE SC_EPILOGUE
id [.a-zA-Z][.a-zA-Z_0-9]*
int [0-9]+
eols (\n|\r|\n\r|\r\n)+
blanks [ \t\f]+
%%
%{
/* At each yylex invocation, mark the current position as the
start of the next token. */
#define TR_POS 0
#if TR_POS
fprintf (stderr, "FOO1: ");
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, "\n");
#endif
YY_STEP;
#if TR_POS
fprintf (stderr, "BAR1: ");
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, "\n");
#endif
%}
/*----------------------------.
| Scanning Bison directives. |
`----------------------------*/
<INITIAL>
{
"%binary" return PERCENT_NONASSOC;
"%debug" return PERCENT_DEBUG;
"%define" return PERCENT_DEFINE;
"%defines" return PERCENT_DEFINES;
"%error"[-_]"verbose" return PERCENT_ERROR_VERBOSE;
"%expect" return PERCENT_EXPECT;
"%file-prefix" return PERCENT_FILE_PREFIX;
"%fixed"[-_]"output"[-_]"files" return PERCENT_YACC;
"%left" return PERCENT_LEFT;
"%locations" return PERCENT_LOCATIONS;
"%name"[-_]"prefix" return PERCENT_NAME_PREFIX;
"%no"[-_]"lines" return PERCENT_NO_LINES;
"%nonassoc" return PERCENT_NONASSOC;
"%nterm" return PERCENT_NTERM;
"%output" return PERCENT_OUTPUT;
"%prec" return PERCENT_PREC;
"%pure"[-_]"parser" return PERCENT_PURE_PARSER;
"%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;
"=" return EQUAL;
":" return COLON;
"|" return PIPE;
";" return SEMICOLON;
{eols} YY_LINES; YY_STEP;
{blanks} YY_STEP;
{id} {
YY_INIT; YY_GROW; YY_FINISH;
yylval->symbol = getsym (yylval->string);
return ID;
}
{int} yylval->integer = strtol (yytext, 0, 10); return INT;
/* Characters. We don't check there is only one. */
\' YY_INIT; YY_GROW; yy_push_state (SC_ESCAPED_CHARACTER);
/* Strings. */
\" YY_INIT; YY_GROW; yy_push_state (SC_ESCAPED_STRING);
/* Comments. */
"/*" yy_push_state (SC_COMMENT);
"//".* YY_STEP;
/* Prologue. */
"%{" YY_INIT; yy_push_state (SC_PROLOGUE);
/* Code in between braces. */
"{" YY_INIT; YY_GROW; ++braces_level; yy_push_state (SC_BRACED_CODE);
/* A type. */
"<"[^>]+">" YY_INIT; obstack_grow (&string_obstack, yytext + 1, yyleng - 2); YY_FINISH; return TYPE;
"%%" {
if (++percent_percent_count == 2)
yy_push_state (SC_EPILOGUE);
return PERCENT_PERCENT;
}
. {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": invalid character: `%c'\n", *yytext);
YY_STEP;
}
}
/*------------------------------------------------------------.
| Whatever the start condition (but those which correspond to |
| entity `swallowed' by Bison: SC_ESCAPED_STRING and |
| SC_ESCAPED_CHARACTER), no M4 character must escape as is. |
`------------------------------------------------------------*/
<SC_COMMENT,SC_STRING,SC_CHARACTER,SC_BRACED_CODE,SC_PROLOGUE,SC_EPILOGUE>
{
\[ obstack_sgrow (&string_obstack, "@<:@");
\] obstack_sgrow (&string_obstack, "@:>@");
}
/*-----------------------------------------------------------.
| Scanning a C comment. The initial `/ *' is already eaten. |
`-----------------------------------------------------------*/
<SC_COMMENT>
{
"*/" { /* End of the comment. */
if (yy_top_state () == INITIAL)
{
YY_STEP;
}
else
{
YY_GROW;
}
yy_pop_state ();
}
[^\[\]*\n\r]+ if (yy_top_state () != INITIAL) YY_GROW;
{eols} if (yy_top_state () != INITIAL) YY_GROW; YY_LINES;
. /* Stray `*'. */if (yy_top_state () != INITIAL) YY_GROW;
<<EOF>> {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unexpected end of file in a comment\n");
yy_pop_state ();
}
}
/*----------------------------------------------------------------.
| Scanning a C string, including its escapes. The initial `"' is |
| already eaten. |
`----------------------------------------------------------------*/
<SC_ESCAPED_STRING>
{
\" {
assert (yy_top_state () == INITIAL);
YY_GROW;
YY_FINISH;
yy_pop_state ();
return STRING;
}
[^\"\n\r\\]+ YY_GROW;
{eols} obstack_1grow (&string_obstack, '\n'); YY_LINES;
<<EOF>> {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unexpected end of file in a string\n");
assert (yy_top_state () == INITIAL);
YY_FINISH;
yy_pop_state ();
return STRING;
}
}
/*---------------------------------------------------------------.
| Scanning a C character, decoding its escapes. The initial "'" |
| is already eaten. |
`---------------------------------------------------------------*/
<SC_ESCAPED_CHARACTER>
{
\' {
YY_GROW;
assert (yy_top_state () == INITIAL);
{
char c;
YY_FINISH;
c = yylval->string[1];
yylval->symbol = getsym (yylval->string);
symbol_class_set (yylval->symbol, token_sym);
symbol_user_token_number_set (yylval->symbol, (unsigned int) c);
yy_pop_state ();
return ID;
}
}
[^\'\n\r\\] YY_GROW;
{eols} obstack_1grow (&string_obstack, '\n'); YY_LINES;
<<EOF>> {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unexpected end of file in a character\n");
assert (yy_top_state () == INITIAL);
YY_FINISH;
yy_pop_state ();
return CHARACTER;
}
}
/*----------------------------.
| Decode escaped characters. |
`----------------------------*/
<SC_ESCAPED_STRING,SC_ESCAPED_CHARACTER>
{
\\[0-7]{3} {
long c = strtol (yytext + 1, 0, 8);
if (c > 255)
{
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": invalid escape: %s\n", yytext);
YY_STEP;
}
else
obstack_1grow (&string_obstack, c);
}
\\x[0-9a-fA-F]{2} {
obstack_1grow (&string_obstack, strtol (yytext + 2, 0, 16));
}
\\a obstack_1grow (&string_obstack, '\a');
\\b obstack_1grow (&string_obstack, '\b');
\\f obstack_1grow (&string_obstack, '\f');
\\n obstack_1grow (&string_obstack, '\n');
\\r obstack_1grow (&string_obstack, '\r');
\\t obstack_1grow (&string_obstack, '\t');
\\v obstack_1grow (&string_obstack, '\v');
\\[\\""] obstack_1grow (&string_obstack, yytext[1]);
\\. {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unrecognized escape: %s\n", yytext);
YY_GROW;
}
}
/*----------------------------------------------------------.
| Scanning a C character without decoding its escapes. The |
| initial "'" is already eaten. |
`----------------------------------------------------------*/
<SC_CHARACTER>
{
\' {
YY_GROW;
assert (yy_top_state () != INITIAL);
yy_pop_state ();
}
[^\[\]\'\n\r\\] YY_GROW;
\\. YY_GROW;
{eols} YY_GROW; YY_LINES;
<<EOF>> {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unexpected end of file in a character\n");
assert (yy_top_state () != INITIAL);
yy_pop_state ();
}
}
/*----------------------------------------------------------------.
| Scanning a C string, without decoding its escapes. The initial |
| `"' is already eaten. |
`----------------------------------------------------------------*/
<SC_STRING>
{
\" {
assert (yy_top_state () != INITIAL);
YY_GROW;
yy_pop_state ();
}
[^\[\]\"\n\r\\]+ YY_GROW;
\\. YY_GROW;
{eols} YY_GROW; YY_LINES;
<<EOF>> {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unexpected end of file in a string\n");
assert (yy_top_state () != INITIAL);
yy_pop_state ();
}
}
/*---------------------------------------------------.
| Strings, comments etc. can be found in user code. |
`---------------------------------------------------*/
<SC_BRACED_CODE,SC_PROLOGUE,SC_EPILOGUE>
{
/* Characters. We don't check there is only one. */
\' YY_GROW; yy_push_state (SC_CHARACTER);
/* Strings. */
\" YY_GROW; yy_push_state (SC_STRING);
/* Comments. */
"/*" YY_GROW; yy_push_state (SC_COMMENT);
"//".* YY_GROW;
}
/*---------------------------------------------------------------.
| Scanning some code in braces (%union and actions). The initial |
| "{" is already eaten. |
`---------------------------------------------------------------*/
<SC_BRACED_CODE>
{
"}" {
YY_GROW;
if (--braces_level == 0)
{
yy_pop_state ();
YY_FINISH;
return BRACED_CODE;
}
}
"{" YY_GROW; braces_level++;
"$"("<".*">")?(-?[0-9]+|"$") { handle_dollar (yytext); }
"@"(-?[0-9]+|"$") { handle_at (yytext); }
[^\[\]$/\'\"@\{\}\n\r]+ YY_GROW;
{eols} YY_GROW; YY_LINES;
/* A lose $, or /, or etc. */
. YY_GROW;
<<EOF>> {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unexpected end of file in a braced code\n");
yy_pop_state ();
YY_FINISH;
return PROLOGUE;
}
}
/*--------------------------------------------------------------.
| Scanning some prologue: from "%{" (already scanned) to "%}". |
`--------------------------------------------------------------*/
<SC_PROLOGUE>
{
"%}" {
yy_pop_state ();
YY_FINISH;
return PROLOGUE;
}
[^\[\]%\n\r]+ YY_GROW;
"%"+[^%\}\n\r]+ YY_GROW;
{eols} YY_GROW; YY_LINES;
<<EOF>> {
LOCATION_PRINT (stderr, *yylloc);
fprintf (stderr, ": unexpected end of file in a prologue\n");
yy_pop_state ();
YY_FINISH;
return PROLOGUE;
}
}
/*---------------------------------------------------------------.
| Scanning the epilogue (everything after the second "%%", which |
| has already been eaten. |
`---------------------------------------------------------------*/
<SC_EPILOGUE>
{
([^\[\]]|{eols})+ YY_GROW;
<<EOF>> {
yy_pop_state ();
YY_FINISH;
return EPILOGUE;
}
}
%%
/*------------------------------------------------------------------.
| CP is pointing to a wannabee semantic value (i.e., a `$'). |
| |
| Possible inputs: $[<TYPENAME>]($|integer) |
| |
| Output to the STRING_OBSTACK a reference to this semantic value. |
`------------------------------------------------------------------*/
static void
handle_dollar (char *cp)
{
const char *type_name = NULL;
/* RULE_LENGTH is the number of values in the current rule so far,
which says where to find `$0' with respect to the top of the
stack. It is not the same as the rule->length in the case of mid
rule actions. */
int rule_length = 0;
symbol_list *rhs;
for (rhs = current_rule->next; rhs; rhs = rhs->next)
++rule_length;
++cp;
/* Get the type name if explicit. */
if (*cp == '<')
{
type_name = ++cp;
while (*cp != '>')
++cp;
*cp = '\0';
++cp;
}
if (*cp == '$')
{
if (!type_name)
type_name = get_type_name (0, current_rule);
if (!type_name && typed)
complain (_("$$ of `%s' has no declared type"),
current_rule->sym->tag);
if (!type_name)
type_name = "";
obstack_fgrow1 (&string_obstack,
"]b4_lhs_value([%s])[", type_name);
}
else if (isdigit (*cp) || *cp == '-')
{
int n = strtol (cp, &cp, 10);
if (n > rule_length)
complain (_("invalid value: %s%d"), "$", n);
else
{
if (!type_name && n > 0)
type_name = get_type_name (n, current_rule);
if (!type_name && typed)
complain (_("$%d of `%s' has no declared type"),
n, current_rule->sym->tag);
if (!type_name)
type_name = "";
obstack_fgrow3 (&string_obstack,
"]b4_rhs_value([%d], [%d], [%s])[",
rule_length, n, type_name);
}
}
else
{
char buf[] = "$c";
buf[1] = *cp;
complain (_("%s is invalid"), quote (buf));
}
}
/*-------------------------------------------------------.
| CP is pointing to a location (i.e., a `@'). Output to |
| STRING_OBSTACK a reference to this location. |
`-------------------------------------------------------*/
static void
handle_at (char *cp)
{
/* RULE_LENGTH is the number of values in the current rule so far,
which says where to find `$0' with respect to the top of the
stack. It is not the same as the rule->length in the case of mid
rule actions. */
int rule_length = 0;
symbol_list *rhs;
for (rhs = current_rule->next; rhs; rhs = rhs->next)
++rule_length;
locations_flag = 1;
++cp;
if (*cp == '$')
{
obstack_sgrow (&string_obstack, "]b4_lhs_location[");
}
else if (isdigit (*cp) || *cp == '-')
{
int n = strtol (cp, &cp, 10);
if (n > rule_length)
complain (_("invalid value: %s%d"), "@", n);
else
obstack_fgrow2 (&string_obstack, "]b4_rhs_location([%d], [%d])[",
rule_length, n);
}
else
{
char buf[] = "@c";
buf[1] = *cp;
complain (_("%s is invalid"), quote (buf));
}
}