* data/glr.c (yyuserAction): Add "default: break;" case to pacify

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

diff --git a/src/scan-gram.l b/src/scan-gram.l
index a327501560b2b2737722294ed62154bf75bd3e21..7541bf9f640aa45f35024201c5b818a85991fdb4 100644 (file)
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -1,6 +1,6 @@
 /* Bison Grammar Scanner                             -*- C -*-
 
 /* 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.
 
 
    This file is part of Bison, the GNU Compiler Compiler.
 


@@ -101,8 +101,10 @@ 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 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_eof (boundary, char const *);
 static int convert_ucn_to_byte (char const *hex_text);
 static void unexpected_eof (boundary, char const *);

+static void unexpected_newline (boundary, char const *);

 
 %}
 %x SC_COMMENT SC_LINE_COMMENT SC_YACC_COMMENT
 
 %}
 %x SC_COMMENT SC_LINE_COMMENT SC_YACC_COMMENT


@@ -156,10 +158,9 @@ splice      (\\[ \f\t\v]*\n)*
 
 <INITIAL,SC_AFTER_IDENTIFIER,SC_PRE_CODE>
 {
 
 <INITIAL,SC_AFTER_IDENTIFIER,SC_PRE_CODE>
 {

-  [ \f\n\t\v]  ;
+  /* Comments and white space.  */

   ","         warn_at (*loc, _("stray `,' treated as white space"));
   ","         warn_at (*loc, _("stray `,' treated as white space"));

-
-  /* Comments. */
+  [ \f\n\t\v]  |

   "//".*       ;
   "/*" {
     token_start = loc->start;
   "//".*       ;
   "/*" {
     token_start = loc->start;


@@ -189,6 +190,7 @@ splice       (\\[ \f\t\v]*\n)*
   "%dprec"               return PERCENT_DPREC;
   "%error"[-_]"verbose"   return PERCENT_ERROR_VERBOSE;
   "%expect"               return PERCENT_EXPECT;
   "%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"       token_type = PERCENT_INITIAL_ACTION; BEGIN SC_PRE_CODE;
   "%file-prefix"          return PERCENT_FILE_PREFIX;
   "%fixed"[-_]"output"[-_]"files"   return PERCENT_YACC;
   "%initial-action"       token_type = PERCENT_INITIAL_ACTION; BEGIN SC_PRE_CODE;


@@ -198,6 +200,7 @@ splice       (\\[ \f\t\v]*\n)*
   "%locations"            return PERCENT_LOCATIONS;
   "%merge"               return PERCENT_MERGE;
   "%name"[-_]"prefix"     return PERCENT_NAME_PREFIX;
   "%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;
   "%no"[-_]"lines"        return PERCENT_NO_LINES;
   "%nonassoc"             return PERCENT_NONASSOC;
   "%nondeterministic-parser"   return PERCENT_NONDETERMINISTIC_PARSER;


@@ -234,15 +237,11 @@ splice     (\\[ \f\t\v]*\n)*
   }
 
   {int} {
   }
 
   {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;
   }
 
     return INT;
   }
 


@@ -353,10 +352,10 @@ splice     (\\[ \f\t\v]*\n)*
 }
 
 
 }
 
 

-  /*----------------------------------------------------------------.
-  | Scanning a C string, including its escapes.  The initial `"' is |
-  | already eaten.                                                  |
-  `----------------------------------------------------------------*/
+  /*------------------------------------------------.
+  | Scanning a Bison string, including its escapes. |
+  | The initial quote is already eaten.             |
+  `------------------------------------------------*/

 
 <SC_ESCAPED_STRING>
 {
 
 <SC_ESCAPED_STRING>
 {


@@ -369,15 +368,14 @@ splice     (\\[ \f\t\v]*\n)*
     BEGIN INITIAL;
     return STRING;
   }
     BEGIN INITIAL;
     return STRING;
   }

-
-  .|\n     STRING_GROW;
-  <<EOF>>   unexpected_eof (token_start, "\""); BEGIN INITIAL;
+  \n           unexpected_newline (token_start, "\""); BEGIN INITIAL;
+  <<EOF>>      unexpected_eof (token_start, "\"");     BEGIN INITIAL;

 }
 
 }
 

-  /*---------------------------------------------------------------.
-  | Scanning a C character, decoding its escapes.  The initial "'" |
-  | is already eaten.                                              |
-  `---------------------------------------------------------------*/
+  /*----------------------------------------------------------.
+  | Scanning a Bison character literal, decoding its escapes. |
+  | The initial quote is already eaten.                              |
+  `----------------------------------------------------------*/

 
 <SC_ESCAPED_CHARACTER>
 {
 
 <SC_ESCAPED_CHARACTER>
 {


@@ -395,9 +393,13 @@ splice      (\\[ \f\t\v]*\n)*
     BEGIN INITIAL;
     return ID;
   }
     BEGIN INITIAL;
     return ID;
   }

+  \n           unexpected_newline (token_start, "'");  BEGIN INITIAL;
+  <<EOF>>      unexpected_eof (token_start, "'");      BEGIN INITIAL;
+}

 
 

-  .|\n     STRING_GROW;
-  <<EOF>>   unexpected_eof (token_start, "'"); BEGIN INITIAL;
+<SC_ESCAPED_CHARACTER,SC_ESCAPED_STRING>
+{
+  \0       complain_at (*loc, _("invalid null character"));

 }
 
 
 }
 
 


@@ -408,19 +410,23 @@ splice     (\\[ \f\t\v]*\n)*
 <SC_ESCAPED_STRING,SC_ESCAPED_CHARACTER>
 {
   \\[0-7]{1,3} {
 <SC_ESCAPED_STRING,SC_ESCAPED_CHARACTER>
 {
   \\[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));
     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]+ {
     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));
     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);
   }
     else
       obstack_1grow (&obstack_for_string, c);
   }


@@ -440,6 +446,8 @@ splice       (\\[ \f\t\v]*\n)*
     int c = convert_ucn_to_byte (yytext);
     if (c < 0)
       complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext));
     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);
   }
     else
       obstack_1grow (&obstack_for_string, c);
   }


@@ -449,33 +457,27 @@ splice     (\\[ \f\t\v]*\n)*
   }
 }
 
   }
 }
 

+  /*--------------------------------------------.
+  | Scanning user-code characters and strings.  |
+  `--------------------------------------------*/

 
 

-  /*----------------------------------------------------------.
-  | Scanning a C character without decoding its escapes.  The |
-  | initial "'" is already eaten.                             |
-  `----------------------------------------------------------*/
+<SC_CHARACTER,SC_STRING>
+{
+  {splice}|\\{splice}[^\n$@\[\]]       STRING_GROW;
+}

 
 <SC_CHARACTER>
 {
 
 <SC_CHARACTER>
 {

-  "'"                  STRING_GROW; BEGIN context_state;
-  \\{splice}[^$@\[\]]  STRING_GROW;
-  <<EOF>>              unexpected_eof (token_start, "'"); BEGIN context_state;
+  "'"          STRING_GROW; BEGIN context_state;
+  \n           unexpected_newline (token_start, "'"); BEGIN context_state;
+  <<EOF>>      unexpected_eof (token_start, "'"); BEGIN context_state;

 }
 
 }
 

-
-  /*----------------------------------------------------------------.
-  | Scanning a C string, without decoding its escapes.  The initial |
-  | `"' is already eaten.                                           |
-  `----------------------------------------------------------------*/
-

 <SC_STRING>
 {
 <SC_STRING>
 {

-  "\""                 STRING_GROW; BEGIN context_state;
-  \\{splice}[^$@\[\]]  STRING_GROW;
-  <<EOF>> {
-    unexpected_eof (token_start, "\"");
-    BEGIN context_state;
-  }
+  "\""         STRING_GROW; BEGIN context_state;
+  \n           unexpected_newline (token_start, "\""); BEGIN context_state;
+  <<EOF>>      unexpected_eof (token_start, "\""); BEGIN context_state;

 }
 
 
 }
 
 


@@ -634,10 +636,9 @@ splice      (\\[ \f\t\v]*\n)*
 }
 
 
 }
 
 

-  /*----------------------------------------------------------------.
-  | By default, grow the string obstack with the input, escaping M4 |
-  | quoting characters.                                                    |
-  `----------------------------------------------------------------*/
+  /*-----------------------------------------.
+  | Escape M4 quoting characters in C code.  |
+  `-----------------------------------------*/

 
 <SC_COMMENT,SC_LINE_COMMENT,SC_STRING,SC_CHARACTER,SC_BRACED_CODE,SC_PROLOGUE,SC_EPILOGUE>
 {
 
 <SC_COMMENT,SC_LINE_COMMENT,SC_STRING,SC_CHARACTER,SC_BRACED_CODE,SC_PROLOGUE,SC_EPILOGUE>
 {


@@ -645,10 +646,16 @@ splice     (\\[ \f\t\v]*\n)*
   \@   obstack_sgrow (&obstack_for_string, "@@");
   \[   obstack_sgrow (&obstack_for_string, "@{");
   \]   obstack_sgrow (&obstack_for_string, "@}");
   \@   obstack_sgrow (&obstack_for_string, "@@");
   \[   obstack_sgrow (&obstack_for_string, "@{");
   \]   obstack_sgrow (&obstack_for_string, "@}");

-  .|\n  STRING_GROW;

 }
 
 
 }
 
 

+  /*-----------------------------------------------------.
+  | By default, grow the string obstack with the input.  |
+  `-----------------------------------------------------*/
+
+<SC_COMMENT,SC_LINE_COMMENT,SC_BRACED_CODE,SC_PROLOGUE,SC_EPILOGUE,SC_STRING,SC_CHARACTER,SC_ESCAPED_STRING,SC_ESCAPED_CHARACTER>.     |
+<SC_COMMENT,SC_LINE_COMMENT,SC_BRACED_CODE,SC_PROLOGUE,SC_EPILOGUE>\n  STRING_GROW;
+

 %%
 
 /* Keeps track of the maximum number of semantic values to the left of
 %%
 
 /* Keeps track of the maximum number of semantic values to the left of


@@ -781,7 +788,7 @@ handle_action_dollar (char *text, location loc)
     }
   else
     {
     }
   else
     {

-      long num;
+      long int num;

       set_errno (0);
       num = strtol (cp, 0, 10);
 
       set_errno (0);
       num = strtol (cp, 0, 10);
 


@@ -860,7 +867,7 @@ handle_action_at (char *text, location loc)
     obstack_sgrow (&obstack_for_string, "]b4_lhs_location[");
   else
     {
     obstack_sgrow (&obstack_for_string, "]b4_lhs_location[");
   else
     {

-      long num;
+      long int num;

       set_errno (0);
       num = strtol (cp, 0, 10);
 
       set_errno (0);
       num = strtol (cp, 0, 10);
 


@@ -910,6 +917,25 @@ 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  |
 /*------------------------------------------------------------------.
 | Convert universal character name UCN to a single-byte character,  |
 | and return that character.  Return -1 if UCN does not correspond  |


@@ -919,7 +945,7 @@ handle_at (int token_type, char *text, location loc)
 static int
 convert_ucn_to_byte (char const *ucn)
 {
 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
 
   /* FIXME: Currently we assume Unicode-compatible unibyte characters
      on ASCII hosts (i.e., Latin-1 on hosts with 8-bit bytes).  On


@@ -977,12 +1003,28 @@ handle_syncline (char *args)
   const char *file = NULL;
   file = strchr (args, '"') + 1;
   *strchr (file, '"') = 0;
   const char *file = NULL;
   file = strchr (args, '"') + 1;
   *strchr (file, '"') = 0;

-  scanner_cursor.file = current_file = xstrdup (file);
+  scanner_cursor.file = current_file = uniqstr_new (file);

   scanner_cursor.line = lineno;
   scanner_cursor.column = 1;
 }
 
 
   scanner_cursor.line = lineno;
   scanner_cursor.column = 1;
 }
 
 

+/*----------------------------------------------------------------.
+| For a token or comment starting at START, report message MSGID, |
+| which should say that an end marker was found before           |
+| the expected TOKEN_END.                                        |
+`----------------------------------------------------------------*/
+
+static void
+unexpected_end (boundary start, char const *msgid, char const *token_end)
+{
+  location loc;
+  loc.start = start;
+  loc.end = scanner_cursor;
+  complain_at (loc, _(msgid), token_end);
+}
+
+

 /*------------------------------------------------------------------------.
 | 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.  |
 /*------------------------------------------------------------------------.
 | 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.  |


@@ -991,10 +1033,18 @@ handle_syncline (char *args)
 static void
 unexpected_eof (boundary start, char const *token_end)
 {
 static void
 unexpected_eof (boundary start, char const *token_end)
 {

-  location loc;
-  loc.start = start;
-  loc.end = scanner_cursor;
-  complain_at (loc, _("missing `%s' at end of file"), token_end);
+  unexpected_end (start, N_("missing `%s' at end of file"), token_end);
+}
+
+
+/*----------------------------------------.
+| Likewise, but for unexpected newlines.  |
+`----------------------------------------*/
+
+static void
+unexpected_newline (boundary start, char const *token_end)
+{
+  unexpected_end (start, N_("missing `%s' at end of line"), token_end);

 }
 
 
 }