Minor code cleanup.

[bison.git] / src / scan-gram.l

diff --git a/src/scan-gram.l b/src/scan-gram.l
index 88369ea6b50097b1d2d0f17f5d1cf6e250983646..f199ec38ef337fa5e72cf98bba483f21e62cbc06 100644 (file)
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -1,12 +1,13 @@
 /* Bison Grammar Scanner                             -*- C -*-
 
 /* Bison Grammar Scanner                             -*- C -*-
 

-   Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc.
+   Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 Free
+   Software Foundation, Inc.

 
    This file is part of Bison, the GNU Compiler Compiler.
 
 
    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
    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,
    (at your option) any later version.
 
    This program is distributed in the hope that it will be useful,


@@ -15,12 +16,9 @@
    GNU General Public License for more details.
 
    You should have received a copy of the GNU General Public License
    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 <http://www.gnu.org/licenses/>.  */

 
 

-%option debug nodefault nounput noyywrap never-interactive
+%option debug nodefault noinput nounput noyywrap never-interactive

 %option prefix="gram_" outfile="lex.yy.c"
 
 %{
 %option prefix="gram_" outfile="lex.yy.c"
 
 %{


@@ -39,6 +37,7 @@
 #include "reader.h"
 #include "uniqstr.h"
 
 #include "reader.h"
 #include "uniqstr.h"
 

+#include <ctype.h>

 #include <mbswidth.h>
 #include <quote.h>
 
 #include <mbswidth.h>
 #include <quote.h>
 


@@ -57,8 +56,20 @@ 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))
 
 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.  */
 /* A string representing the most recently saved token.  */

-char *last_string;
+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)
 
 void
 gram_scanner_last_string_free (void)


@@ -90,10 +101,12 @@ static void unexpected_newline (boundary, char const *);
 %x SC_COMMENT SC_LINE_COMMENT
  /* Strings and characters in code. */
 %x SC_STRING SC_CHARACTER
 %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_]
+letter   [-.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]

 id       {letter}({letter}|[0-9])*
 id       {letter}({letter}|[0-9])*

-directive %{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
 int      [0-9]+
 
 /* POSIX says that a tag must be both an id and a C union member, but


@@ -131,7 +144,7 @@ splice       (\\[ \f\t\v]*\n)*
   | Scanning white space.  |
   `-----------------------*/
 
   | Scanning white space.  |
   `-----------------------*/
 

-<INITIAL,SC_AFTER_IDENTIFIER>
+<INITIAL,SC_AFTER_IDENTIFIER,SC_BRACKETED_ID,SC_RETURN_BRACKETED_ID>

 {
   /* Comments and white space.  */
   ","         warn_at (*loc, _("stray `,' treated as white space"));
 {
   /* Comments and white space.  */
   ","         warn_at (*loc, _("stray `,' treated as white space"));


@@ -154,53 +167,57 @@ splice     (\\[ \f\t\v]*\n)*
   /*----------------------------.
   | Scanning Bison directives.  |
   `----------------------------*/
   /*----------------------------.
   | 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.  */
+

 <INITIAL>
 {
 <INITIAL>
 {

-  "%binary"                        return PERCENT_NONASSOC;
+  "%binary"                         return PERCENT_NONASSOC;

   "%code"                           return PERCENT_CODE;
   "%code"                           return PERCENT_CODE;

-  "%code-top"                       return PERCENT_CODE_TOP;
-  "%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;
   "%fixed"[-_]"output"[-_]"files"   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;
-  "%provides"                       return PERCENT_PROVIDES;
-  "%pure"[-_]"parser"              return PERCENT_PURE_PARSER;
-  "%push"[-_]"parser"              return PERCENT_PUSH_PARSER;
-  "%require"                       return PERCENT_REQUIRE;
-  "%requires"                       return PERCENT_REQUIRES;
-  "%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));
 
   {directive} {
     complain_at (*loc, _("invalid directive: %s"), quote (yytext));


@@ -210,11 +227,12 @@ splice     (\\[ \f\t\v]*\n)*
   "|"                     return PIPE;
   ";"                     return SEMICOLON;
   "<*>"                   return TYPE_TAG_ANY;
   "|"                     return PIPE;
   ";"                     return SEMICOLON;
   "<*>"                   return TYPE_TAG_ANY;

-  "<!>"                   return TYPE_TAG_NONE;
+  "<>"                    return TYPE_TAG_NONE;

 
   {id} {
     val->uniqstr = uniqstr_new (yytext);
     id_loc = *loc;
 
   {id} {
     val->uniqstr = uniqstr_new (yytext);
     id_loc = *loc;

+    bracketed_id_str = NULL;

     BEGIN SC_AFTER_IDENTIFIER;
   }
 
     BEGIN SC_AFTER_IDENTIFIER;
   }
 


@@ -227,8 +245,14 @@ splice      (\\[ \f\t\v]*\n)*
     return INT;
   }
 
     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;
 
   /* Strings. */
   "\""       token_start = loc->start; BEGIN SC_ESCAPED_STRING;


@@ -260,6 +284,13 @@ splice      (\\[ \f\t\v]*\n)*
     return PERCENT_PERCENT;
   }
 
     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 (yytext));
   }


@@ -277,25 +308,94 @@ splice     (\\[ \f\t\v]*\n)*
 
 <SC_AFTER_IDENTIFIER>
 {
 
 <SC_AFTER_IDENTIFIER>
 {

+  "[" {
+    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;
     *loc = id_loc;

-    BEGIN INITIAL;

     return ID_COLON;
   }
   . {
     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;
     *loc = id_loc;

-    BEGIN INITIAL;

     return ID;
   }
   <<EOF>> {
     return ID;
   }
   <<EOF>> {

+    BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL);

     *loc = id_loc;
     *loc = id_loc;

-    BEGIN INITIAL;

     return ID;
   }
 }
 
     return ID;
   }
 }
 

+  /*--------------------------------.
+  | Scanning bracketed identifiers. |
+  `--------------------------------*/
+
+<SC_BRACKETED_ID>
+{
+  {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 (yytext));
+  }
+  <<EOF>> {
+    BEGIN bracketed_id_context_state;
+    unexpected_eof (bracketed_id_start, "]");
+  }
+}
+
+<SC_RETURN_BRACKETED_ID>
+{
+  . {
+    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.  |


@@ -366,24 +466,42 @@ splice     (\\[ \f\t\v]*\n)*
 <SC_ESCAPED_CHARACTER>
 {
   "'"|"\n" {
 <SC_ESCAPED_CHARACTER>
 {
   "'"|"\n" {

-    if (yytext[0] == '\n')
-      unexpected_newline (token_start, "'");
-    STRING_GROW;

     STRING_FINISH;
     loc->start = token_start;
     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;
   }
   <<EOF>> {
     STRING_FREE;
     BEGIN INITIAL;
     return CHAR;
   }
   <<EOF>> {

-    unexpected_eof (token_start, "'");

     STRING_FINISH;
     loc->start = 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;
     STRING_FREE;
     BEGIN INITIAL;
     return CHAR;


@@ -404,10 +522,9 @@ splice      (\\[ \f\t\v]*\n)*
 {
   \\[0-7]{1,3} {
     unsigned long int c = strtoul (yytext + 1, NULL, 8);
 {
   \\[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);
   }
     else
       obstack_1grow (&obstack_for_string, c);
   }


@@ -415,10 +532,9 @@ splice      (\\[ \f\t\v]*\n)*
   \\x[0-9abcdefABCDEF]+ {
     verify (UCHAR_MAX < ULONG_MAX);
     unsigned long int c = strtoul (yytext + 2, NULL, 16);
   \\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);
   }
     else
       obstack_1grow (&obstack_for_string, c);
   }


@@ -436,16 +552,20 @@ splice     (\\[ \f\t\v]*\n)*
 
   \\(u|U[0-9abcdefABCDEF]{4})[0-9abcdefABCDEF]{4} {
     int c = convert_ucn_to_byte (yytext);
 
   \\(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)     {
     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 (isspace ((unsigned char) *p) && 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);

   }
 }
 
   }
 }