X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/379f0ac840fa8b04eacbfdd7d19394f86574031e..1452af69b4f4d2aeabf50918e9b6039cc809b988:/src/scan-gram.l diff --git a/src/scan-gram.l b/src/scan-gram.l index 77fe5beb..849b72e1 100644 --- a/src/scan-gram.l +++ b/src/scan-gram.l @@ -1,6 +1,6 @@ /* Bison Grammar Scanner -*- C -*- - Copyright (C) 2002, 2003 Free Software Foundation, Inc. + Copyright (C) 2002, 2003, 2004 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -20,7 +20,7 @@ 02111-1307 USA */ -%option debug nodefault noyywrap never-interactive +%option debug nodefault nounput noyywrap never-interactive %option prefix="gram_" outfile="lex.yy.c" %{ @@ -101,8 +101,9 @@ static int rule_length; static void handle_dollar (int token_type, char *cp, location loc); static void handle_at (int token_type, char *cp, location loc); static void handle_syncline (char *args); +static unsigned long int scan_integer (char const *p, int base, location loc); static int convert_ucn_to_byte (char const *hex_text); -static void unexpected_end_of_file (boundary, char const *); +static void unexpected_eof (boundary, char const *); %} %x SC_COMMENT SC_LINE_COMMENT SC_YACC_COMMENT @@ -182,6 +183,7 @@ splice (\\[ \f\t\v]*\n)* { "%binary" return PERCENT_NONASSOC; "%debug" return PERCENT_DEBUG; + "%default"[-_]"prec" return PERCENT_DEFAULT_PREC; "%define" return PERCENT_DEFINE; "%defines" return PERCENT_DEFINES; "%destructor" token_type = PERCENT_DESTRUCTOR; BEGIN SC_PRE_CODE; @@ -190,14 +192,17 @@ splice (\\[ \f\t\v]*\n)* "%expect" return PERCENT_EXPECT; "%file-prefix" return PERCENT_FILE_PREFIX; "%fixed"[-_]"output"[-_]"files" return PERCENT_YACC; + "%initial-action" token_type = PERCENT_INITIAL_ACTION; BEGIN SC_PRE_CODE; "%glr-parser" return PERCENT_GLR_PARSER; "%left" return PERCENT_LEFT; "%lex-param" token_type = PERCENT_LEX_PARAM; BEGIN SC_PRE_CODE; "%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" token_type = PERCENT_PARSE_PARAM; BEGIN SC_PRE_CODE; @@ -231,15 +236,11 @@ splice (\\[ \f\t\v]*\n)* } {int} { - unsigned long num; - set_errno (0); - num = strtoul (yytext, 0, 10); - if (INT_MAX < num || get_errno ()) - { - complain_at (*loc, _("integer out of range: %s"), quote (yytext)); - num = INT_MAX; - } - val->integer = num; + val->integer = scan_integer (yytext, 10, *loc); + return INT; + } + 0[xX][0-9abcdefABCDEF]+ { + val->integer = scan_integer (yytext, 16, *loc); return INT; } @@ -323,7 +324,7 @@ splice (\\[ \f\t\v]*\n)* { "*/" BEGIN context_state; .|\n ; - <> unexpected_end_of_file (token_start, "*/"); + <> unexpected_eof (token_start, "*/"); BEGIN context_state; } @@ -334,7 +335,7 @@ splice (\\[ \f\t\v]*\n)* { "*"{splice}"/" STRING_GROW; BEGIN context_state; - <> unexpected_end_of_file (token_start, "*/"); + <> unexpected_eof (token_start, "*/"); BEGIN context_state; } @@ -367,8 +368,9 @@ splice (\\[ \f\t\v]*\n)* return STRING; } + \0 complain_at (*loc, _("invalid null character")); .|\n STRING_GROW; - <> unexpected_end_of_file (token_start, "\""); + <> unexpected_eof (token_start, "\""); BEGIN INITIAL; } /*---------------------------------------------------------------. @@ -393,8 +395,9 @@ splice (\\[ \f\t\v]*\n)* return ID; } + \0 complain_at (*loc, _("invalid null character")); .|\n STRING_GROW; - <> unexpected_end_of_file (token_start, "'"); + <> unexpected_eof (token_start, "'"); BEGIN INITIAL; } @@ -405,19 +408,23 @@ splice (\\[ \f\t\v]*\n)* { \\[0-7]{1,3} { - unsigned long c = strtoul (yytext + 1, 0, 8); + unsigned long int c = strtoul (yytext + 1, 0, 8); if (UCHAR_MAX < c) complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext)); + else if (! c) + complain_at (*loc, _("invalid null character: %s"), quote (yytext)); else obstack_1grow (&obstack_for_string, c); } \\x[0-9abcdefABCDEF]+ { - unsigned long c; + unsigned long int c; set_errno (0); c = strtoul (yytext + 2, 0, 16); if (UCHAR_MAX < c || get_errno ()) complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext)); + else if (! c) + complain_at (*loc, _("invalid null character: %s"), quote (yytext)); else obstack_1grow (&obstack_for_string, c); } @@ -437,6 +444,8 @@ splice (\\[ \f\t\v]*\n)* int c = convert_ucn_to_byte (yytext); if (c < 0) complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext)); + else if (! c) + complain_at (*loc, _("invalid null character: %s"), quote (yytext)); else obstack_1grow (&obstack_for_string, c); } @@ -456,7 +465,7 @@ splice (\\[ \f\t\v]*\n)* { "'" STRING_GROW; BEGIN context_state; \\{splice}[^$@\[\]] STRING_GROW; - <> unexpected_end_of_file (token_start, "'"); + <> unexpected_eof (token_start, "'"); BEGIN context_state; } @@ -469,7 +478,10 @@ splice (\\[ \f\t\v]*\n)* { "\"" STRING_GROW; BEGIN context_state; \\{splice}[^$@\[\]] STRING_GROW; - <> unexpected_end_of_file (token_start, "\""); + <> { + unexpected_eof (token_start, "\""); + BEGIN context_state; + } } @@ -536,7 +548,7 @@ splice (\\[ \f\t\v]*\n)* } } - <> unexpected_end_of_file (scanner_cursor, "{}"); + <> unexpected_eof (scanner_cursor, "{}"); BEGIN INITIAL; } @@ -589,7 +601,7 @@ splice (\\[ \f\t\v]*\n)* "$"("<"{tag}">")?(-?[0-9]+|"$") handle_dollar (token_type, yytext, *loc); "@"(-?[0-9]+|"$") handle_at (token_type, yytext, *loc); - <> unexpected_end_of_file (code_start, "}"); + <> unexpected_eof (code_start, "}"); BEGIN INITIAL; } @@ -607,7 +619,7 @@ splice (\\[ \f\t\v]*\n)* return PROLOGUE; } - <> unexpected_end_of_file (code_start, "%}"); + <> unexpected_eof (code_start, "%}"); BEGIN INITIAL; } @@ -645,6 +657,11 @@ splice (\\[ \f\t\v]*\n)* %% +/* Keeps track of the maximum number of semantic values to the left of + a handle (those referenced by $0, $-1, etc.) are required by the + semantic actions of this grammar. */ +int max_left_semantic_context = 0; + /* Set *LOC and adjust scanner cursor to account for token TOKEN of size SIZE. */ @@ -770,13 +787,15 @@ handle_action_dollar (char *text, location loc) } else { - long num; + long int num; set_errno (0); num = strtol (cp, 0, 10); if (INT_MIN <= num && num <= rule_length && ! get_errno ()) { int n = num; + if (1-n > max_left_semantic_context) + max_left_semantic_context = 1-n; if (!type_name && n > 0) type_name = symbol_list_n_type_name_get (current_rule, loc, n); if (!type_name && typed) @@ -796,10 +815,10 @@ handle_action_dollar (char *text, location loc) } -/*-----------------------------------------------------------------. -| Dispatch onto handle_action_dollar, or handle_destructor_dollar, | -| depending upon TOKEN_TYPE. | -`-----------------------------------------------------------------*/ +/*----------------------------------------------------------------. +| Map `$?' onto the proper M4 symbol, depending on its TOKEN_TYPE | +| (are we in an action?). | +`----------------------------------------------------------------*/ static void handle_dollar (int token_type, char *text, location loc) @@ -812,6 +831,7 @@ handle_dollar (int token_type, char *text, location loc) break; case PERCENT_DESTRUCTOR: + case PERCENT_INITIAL_ACTION: case PERCENT_PRINTER: if (text[1] == '$') { @@ -837,7 +857,7 @@ static inline bool handle_action_at (char *text, location loc) { char *cp = text + 1; - locations_flag = 1; + locations_flag = true; if (! current_rule) return false; @@ -846,7 +866,7 @@ handle_action_at (char *text, location loc) obstack_sgrow (&obstack_for_string, "]b4_lhs_location["); else { - long num; + long int num; set_errno (0); num = strtol (cp, 0, 10); @@ -864,10 +884,10 @@ handle_action_at (char *text, location loc) } -/*-------------------------------------------------------------------. -| Dispatch onto handle_action_at, or handle_destructor_at, depending | -| upon CODE_KIND. | -`-------------------------------------------------------------------*/ +/*----------------------------------------------------------------. +| Map `@?' onto the proper M4 symbol, depending on its TOKEN_TYPE | +| (are we in an action?). | +`----------------------------------------------------------------*/ static void handle_at (int token_type, char *text, location loc) @@ -878,6 +898,7 @@ handle_at (int token_type, char *text, location loc) handle_action_at (text, loc); return; + case PERCENT_INITIAL_ACTION: case PERCENT_DESTRUCTOR: case PERCENT_PRINTER: if (text[1] == '$') @@ -895,6 +916,25 @@ handle_at (int token_type, char *text, location loc) } +/*------------------------------------------------------. +| Scan NUMBER for a base-BASE integer at location LOC. | +`------------------------------------------------------*/ + +static unsigned long int +scan_integer (char const *number, int base, location loc) +{ + unsigned long int num; + set_errno (0); + num = strtoul (number, 0, base); + if (INT_MAX < num || get_errno ()) + { + complain_at (loc, _("integer out of range: %s"), quote (number)); + num = INT_MAX; + } + return num; +} + + /*------------------------------------------------------------------. | Convert universal character name UCN to a single-byte character, | | and return that character. Return -1 if UCN does not correspond | @@ -904,7 +944,7 @@ handle_at (int token_type, char *text, location loc) static int convert_ucn_to_byte (char const *ucn) { - unsigned long code = strtoul (ucn + 2, 0, 16); + unsigned long int code = strtoul (ucn + 2, 0, 16); /* FIXME: Currently we assume Unicode-compatible unibyte characters on ASCII hosts (i.e., Latin-1 on hosts with 8-bit bytes). On @@ -971,25 +1011,15 @@ handle_syncline (char *args) /*------------------------------------------------------------------------. | Report an unexpected EOF in a token or comment starting at START. | | An end of file was encountered and the expected TOKEN_END was missing. | -| After reporting the problem, pretend that TOKEN_END was found. | `------------------------------------------------------------------------*/ static void -unexpected_end_of_file (boundary start, char const *token_end) +unexpected_eof (boundary start, char const *token_end) { - size_t i = strlen (token_end); - location loc; loc.start = start; loc.end = scanner_cursor; complain_at (loc, _("missing `%s' at end of file"), token_end); - - /* Adjust scanner cursor so that any later message does not count - the characters about to be inserted. */ - scanner_cursor.column -= i; - - while (i != 0) - unput (token_end[--i]); }