X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/8e0a5e9e735620ef5196a155eed1f8cf4d3aab5f..a1d1ab50a00a4d28d6ba7b227ddc6628d5734ce3:/src/scan-gram.l
diff --git a/src/scan-gram.l b/src/scan-gram.l
index fb22e588..ad061cc6 100644
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -1,13 +1,12 @@
/* Bison Grammar Scanner -*- C -*-
- Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007 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,
@@ -16,12 +15,9 @@
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 . */
-%option debug nodefault nounput noyywrap never-interactive
+%option debug nodefault noinput nounput noyywrap never-interactive
%option prefix="gram_" outfile="lex.yy.c"
%{
@@ -40,6 +36,7 @@
#include "reader.h"
#include "uniqstr.h"
+#include
#include
#include
@@ -58,9 +55,21 @@ static boundary scanner_cursor;
static size_t no_cr_read (FILE *, char *, size_t);
#define YY_INPUT(buf, result, size) ((result) = no_cr_read (yyin, buf, size))
+#define ROLLBACK_CURRENT_TOKEN \
+ do { \
+ scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0); \
+ yyless (0); \
+ } while (0)
+
/* A string representing the most recently saved token. */
static char *last_string;
+/* Bracketed identifier. */
+static uniqstr bracketed_id_str = 0;
+static location bracketed_id_loc;
+static boundary bracketed_id_start;
+static int bracketed_id_context_state = 0;
+
void
gram_scanner_last_string_free (void)
{
@@ -79,11 +88,11 @@ static void unexpected_newline (boundary, char const *);
/* Strings and characters in directives/rules. */
%x SC_ESCAPED_STRING SC_ESCAPED_CHARACTER
/* A identifier was just read in directives/rules. Special state
- to capture the sequence `identifier :'. */
+ to capture the sequence 'identifier :'. */
%x SC_AFTER_IDENTIFIER
/* Three types of user code:
- - prologue (code between `%{' `%}' in the first section, before %%);
+ - prologue (code between '%{' '%}' in the first section, before %%);
- actions, printers, union, etc, (between braced in the middle section);
- epilogue (everything after the second %%). */
%x SC_PROLOGUE SC_BRACED_CODE SC_EPILOGUE
@@ -91,10 +100,12 @@ static void unexpected_newline (boundary, char const *);
%x SC_COMMENT SC_LINE_COMMENT
/* Strings and characters in code. */
%x SC_STRING SC_CHARACTER
+ /* Bracketed identifiers support. */
+%x SC_BRACKETED_ID SC_RETURN_BRACKETED_ID
letter [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
-id {letter}({letter}|[0-9])*
-directive %{letter}({letter}|[0-9]|-)*
+id {letter}({letter}|[-0-9])*
+directive %{id}
int [0-9]+
/* POSIX says that a tag must be both an id and a C union member, but
@@ -109,13 +120,13 @@ splice (\\[ \f\t\v]*\n)*
%%
%{
/* Nesting level of the current code in braces. */
- int braces_level IF_LINT (= 0);
+ int braces_level PACIFY_CC (= 0);
/* Parent context state, when applicable. */
- int context_state IF_LINT (= 0);
+ int context_state PACIFY_CC (= 0);
/* Location of most recent identifier, when applicable. */
- location id_loc IF_LINT (= empty_location);
+ location id_loc PACIFY_CC (= empty_location);
/* Where containing code started, when applicable. Its initial
value is relevant only when yylex is invoked in the SC_EPILOGUE
@@ -124,7 +135,7 @@ splice (\\[ \f\t\v]*\n)*
/* Where containing comment or string or character literal started,
when applicable. */
- boundary token_start IF_LINT (= scanner_cursor);
+ boundary token_start PACIFY_CC (= scanner_cursor);
%}
@@ -132,10 +143,10 @@ splice (\\[ \f\t\v]*\n)*
| Scanning white space. |
`-----------------------*/
-
+
{
/* Comments and white space. */
- "," warn_at (*loc, _("stray `,' treated as white space"));
+ "," warn_at (*loc, _("stray ',' treated as white space"));
[ \f\n\t\v] |
"//".* ;
"/*" {
@@ -155,52 +166,57 @@ splice (\\[ \f\t\v]*\n)*
/*----------------------------.
| Scanning Bison directives. |
`----------------------------*/
+
+ /* For directives that are also command line options, the regex must be
+ "%..."
+ after "[-_]"s are removed, and the directive must match the --long
+ option name, with a single string argument. Otherwise, add exceptions
+ to ../build-aux/cross-options.pl. */
+
{
- "%binary" return PERCENT_NONASSOC;
+ "%binary" return PERCENT_NONASSOC;
"%code" return PERCENT_CODE;
- "%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;
+ "%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" return PERCENT_INITIAL_ACTION;
- "%glr-parser" return PERCENT_GLR_PARSER;
- "%language" return PERCENT_LANGUAGE;
- "%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;
- "%push-parser" return PERCENT_PUSH_PARSER;
- "%push-pull-parser" return PERCENT_PUSH_PULL_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;
+ "%initial-action" return PERCENT_INITIAL_ACTION;
+ "%glr-parser" return PERCENT_GLR_PARSER;
+ "%language" return PERCENT_LANGUAGE;
+ "%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));
@@ -215,6 +231,7 @@ splice (\\[ \f\t\v]*\n)*
{id} {
val->uniqstr = uniqstr_new (yytext);
id_loc = *loc;
+ bracketed_id_str = NULL;
BEGIN SC_AFTER_IDENTIFIER;
}
@@ -227,8 +244,14 @@ splice (\\[ \f\t\v]*\n)*
return INT;
}
- /* Characters. We don't check there is only one. */
- "'" STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;
+ /* Identifiers may not start with a digit. Yet, don't silently
+ accept "1FOO" as "1 FOO". */
+ {int}{id} {
+ complain_at (*loc, _("invalid identifier: %s"), quote (yytext));
+ }
+
+ /* Characters. */
+ "'" token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;
/* Strings. */
"\"" token_start = loc->start; BEGIN SC_ESCAPED_STRING;
@@ -260,8 +283,15 @@ splice (\\[ \f\t\v]*\n)*
return PERCENT_PERCENT;
}
+ "[" {
+ bracketed_id_str = NULL;
+ bracketed_id_start = loc->start;
+ bracketed_id_context_state = YY_START;
+ BEGIN SC_BRACKETED_ID;
+ }
+
. {
- complain_at (*loc, _("invalid character: %s"), quote (yytext));
+ complain_at (*loc, _("invalid character: %s"), quote_mem (yytext, yyleng));
}
<> {
@@ -277,28 +307,97 @@ splice (\\[ \f\t\v]*\n)*
{
+ "[" {
+ if (bracketed_id_str)
+ {
+ ROLLBACK_CURRENT_TOKEN;
+ BEGIN SC_RETURN_BRACKETED_ID;
+ *loc = id_loc;
+ return ID;
+ }
+ else
+ {
+ bracketed_id_start = loc->start;
+ bracketed_id_context_state = YY_START;
+ BEGIN SC_BRACKETED_ID;
+ }
+ }
":" {
+ BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL);
*loc = id_loc;
- BEGIN INITIAL;
return ID_COLON;
}
. {
- scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0);
- yyless (0);
+ ROLLBACK_CURRENT_TOKEN;
+ BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL);
*loc = id_loc;
- BEGIN INITIAL;
return ID;
}
<> {
+ BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL);
*loc = id_loc;
- BEGIN INITIAL;
return ID;
}
}
+ /*--------------------------------.
+ | Scanning bracketed identifiers. |
+ `--------------------------------*/
+
+
+{
+ {id} {
+ if (bracketed_id_str)
+ {
+ complain_at (*loc, _("unexpected identifier in bracketed name: %s"),
+ quote (yytext));
+ }
+ else
+ {
+ bracketed_id_str = uniqstr_new (yytext);
+ bracketed_id_loc = *loc;
+ }
+ }
+ "]" {
+ BEGIN bracketed_id_context_state;
+ if (bracketed_id_str)
+ {
+ if (INITIAL == bracketed_id_context_state)
+ {
+ val->uniqstr = bracketed_id_str;
+ bracketed_id_str = 0;
+ *loc = bracketed_id_loc;
+ return BRACKETED_ID;
+ }
+ }
+ else
+ complain_at (*loc, _("an identifier expected"));
+ }
+ . {
+ complain_at (*loc, _("invalid character in bracketed name: %s"),
+ quote_mem (yytext, yyleng));
+ }
+ <> {
+ BEGIN bracketed_id_context_state;
+ unexpected_eof (bracketed_id_start, "]");
+ }
+}
+
+
+{
+ . {
+ ROLLBACK_CURRENT_TOKEN;
+ val->uniqstr = bracketed_id_str;
+ bracketed_id_str = 0;
+ *loc = bracketed_id_loc;
+ BEGIN INITIAL;
+ return BRACKETED_ID;
+ }
+}
+
/*---------------------------------------------------------------.
- | Scanning a Yacc comment. The initial `/ *' is already eaten. |
+ | Scanning a Yacc comment. The initial '/ *' is already eaten. |
`---------------------------------------------------------------*/
@@ -310,7 +409,7 @@ splice (\\[ \f\t\v]*\n)*
/*------------------------------------------------------------.
- | Scanning a C comment. The initial `/ *' is already eaten. |
+ | Scanning a C comment. The initial '/ *' is already eaten. |
`------------------------------------------------------------*/
@@ -321,7 +420,7 @@ splice (\\[ \f\t\v]*\n)*
/*--------------------------------------------------------------.
- | Scanning a line comment. The initial `//' is already eaten. |
+ | Scanning a line comment. The initial '//' is already eaten. |
`--------------------------------------------------------------*/
@@ -366,24 +465,42 @@ splice (\\[ \f\t\v]*\n)*
{
"'"|"\n" {
- if (yytext[0] == '\n')
- unexpected_newline (token_start, "'");
- STRING_GROW;
STRING_FINISH;
loc->start = token_start;
- val->character = last_string[1];
+ val->character = last_string[0];
+ {
+ /* FIXME: Eventually, make these errors. */
+ if (last_string[0] == '\0')
+ {
+ warn_at (*loc, _("empty character literal"));
+ /* '\0' seems dangerous even if we are about to complain. */
+ val->character = '\'';
+ }
+ else if (last_string[1] != '\0')
+ warn_at (*loc, _("extra characters in character literal"));
+ }
+ if (yytext[0] == '\n')
+ unexpected_newline (token_start, "'");
STRING_FREE;
BEGIN INITIAL;
return CHAR;
}
<> {
- unexpected_eof (token_start, "'");
STRING_FINISH;
loc->start = token_start;
- if (strlen(last_string) > 1)
- val->character = last_string[1];
- else
- val->character = last_string[0];
+ val->character = last_string[0];
+ {
+ /* FIXME: Eventually, make these errors. */
+ if (last_string[0] == '\0')
+ {
+ warn_at (*loc, _("empty character literal"));
+ /* '\0' seems dangerous even if we are about to complain. */
+ val->character = '\'';
+ }
+ else if (last_string[1] != '\0')
+ warn_at (*loc, _("extra characters in character literal"));
+ }
+ unexpected_eof (token_start, "'");
STRING_FREE;
BEGIN INITIAL;
return CHAR;
@@ -404,10 +521,9 @@ splice (\\[ \f\t\v]*\n)*
{
\\[0-7]{1,3} {
unsigned long int c = strtoul (yytext + 1, NULL, 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));
+ if (!c || UCHAR_MAX < c)
+ complain_at (*loc, _("invalid number after \\-escape: %s"),
+ yytext+1);
else
obstack_1grow (&obstack_for_string, c);
}
@@ -415,10 +531,9 @@ splice (\\[ \f\t\v]*\n)*
\\x[0-9abcdefABCDEF]+ {
verify (UCHAR_MAX < ULONG_MAX);
unsigned long int c = strtoul (yytext + 2, NULL, 16);
- 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));
+ if (!c || UCHAR_MAX < c)
+ complain_at (*loc, _("invalid number after \\-escape: %s"),
+ yytext+1);
else
obstack_1grow (&obstack_for_string, c);
}
@@ -436,16 +551,20 @@ splice (\\[ \f\t\v]*\n)*
\\(u|U[0-9abcdefABCDEF]{4})[0-9abcdefABCDEF]{4} {
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));
+ if (c <= 0)
+ complain_at (*loc, _("invalid number after \\-escape: %s"),
+ yytext+1);
else
obstack_1grow (&obstack_for_string, c);
}
\\(.|\n) {
- complain_at (*loc, _("unrecognized escape sequence: %s"), quote (yytext));
- STRING_GROW;
+ char const *p = yytext + 1;
+ /* Quote only if escaping won't make the character visible. */
+ if (c_isspace ((unsigned char) *p) && c_isprint ((unsigned char) *p))
+ p = quote (p);
+ else
+ p = quotearg_style_mem (escape_quoting_style, p, 1);
+ complain_at (*loc, _("invalid character after \\-escape: %s"), p);
}
}
@@ -529,8 +648,8 @@ splice (\\[ \f\t\v]*\n)*
}
}
- /* Tokenize `<<%' correctly (as `<<' `%') rather than incorrrectly
- (as `<' `<%'). */
+ /* Tokenize '<<%' correctly (as '<<' '%') rather than incorrrectly
+ (as '<' '<%'). */
"<"{splice}"<" STRING_GROW;
<> {
@@ -721,7 +840,7 @@ convert_ucn_to_byte (char const *ucn)
/*----------------------------------------------------------------.
-| Handle `#line INT "FILE"'. ARGS has already skipped `#line '. |
+| Handle '#line INT "FILE"'. ARGS has already skipped '#line '. |
`----------------------------------------------------------------*/
static void
@@ -729,8 +848,8 @@ handle_syncline (char *args, location loc)
{
char *after_num;
unsigned long int lineno = strtoul (args, &after_num, 10);
- char *file = strchr (after_num, '"') + 1;
- *strchr (file, '"') = '\0';
+ char *file = mbschr (after_num, '"') + 1;
+ *mbschr (file, '"') = '\0';
if (INT_MAX <= lineno)
{
warn_at (loc, _("line number overflow"));
@@ -753,6 +872,10 @@ unexpected_end (boundary start, char const *msgid, char const *token_end)
location loc;
loc.start = start;
loc.end = scanner_cursor;
+ token_end = quote (token_end);
+ // Instead of '\'', display "'".
+ if (!strcmp (token_end, "'\\''"))
+ token_end = "\"'\"";
complain_at (loc, _(msgid), token_end);
}
@@ -765,7 +888,7 @@ unexpected_end (boundary start, char const *msgid, char const *token_end)
static void
unexpected_eof (boundary start, char const *token_end)
{
- unexpected_end (start, N_("missing `%s' at end of file"), token_end);
+ unexpected_end (start, N_("missing %s at end of file"), token_end);
}
@@ -776,7 +899,7 @@ unexpected_eof (boundary start, char const *token_end)
static void
unexpected_newline (boundary start, char const *token_end)
{
- unexpected_end (start, N_("missing `%s' at end of line"), token_end);
+ unexpected_end (start, N_("missing %s at end of line"), token_end);
}