(code_start): Initialize it to scanner_cursor,

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

diff --git a/src/scan-gram.l b/src/scan-gram.l
index fd384061e28bf220b66dfe839d5bad74f10502df..a31cd02e83e26d5c78a7ac8a42a3c5db6aded7f6 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 Free Software Foundation, Inc.
+   Copyright (C) 2002, 2003 Free Software Foundation, Inc.

 
    This file is part of Bison, the GNU Compiler Compiler.
 
 
    This file is part of Bison, the GNU Compiler Compiler.
 


@@ -97,8 +97,8 @@ scanner_last_string_free (void)
    Outside of well-formed rules, RULE_LENGTH has an undefined value.  */
 static int rule_length;
 
    Outside of well-formed rules, RULE_LENGTH has an undefined value.  */
 static int rule_length;
 

-static void handle_dollar (braced_code code_kind, char *cp, location loc);
-static void handle_at (braced_code code_kind, char *cp, location loc);
+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 int convert_ucn_to_byte (char const *hex_text);
 static void unexpected_end_of_file (boundary, char const *);
 static void handle_syncline (char *args);
 static int convert_ucn_to_byte (char const *hex_text);
 static void unexpected_end_of_file (boundary, char const *);


@@ -108,12 +108,12 @@ static void unexpected_end_of_file (boundary, char const *);
 %x SC_STRING SC_CHARACTER
 %x SC_AFTER_IDENTIFIER
 %x SC_ESCAPED_STRING SC_ESCAPED_CHARACTER
 %x SC_STRING SC_CHARACTER
 %x SC_AFTER_IDENTIFIER
 %x SC_ESCAPED_STRING SC_ESCAPED_CHARACTER

-%x SC_BRACED_CODE SC_PROLOGUE SC_EPILOGUE
+%x SC_PRE_CODE SC_BRACED_CODE SC_PROLOGUE SC_EPILOGUE

 
 letter   [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
 id       {letter}({letter}|[0-9])*
 directive %{letter}({letter}|[0-9]|-)*
 
 letter   [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
 id       {letter}({letter}|[0-9])*
 directive %{letter}({letter}|[0-9]|-)*

-int      [0-9]+
+int      [0-9]+

 
 /* POSIX says that a tag must be both an id and a C union member, but
    historically almost any character is allowed in a tag.  We disallow
 
 /* POSIX says that a tag must be both an id and a C union member, but
    historically almost any character is allowed in a tag.  We disallow


@@ -132,15 +132,20 @@ splice     (\\[ \f\t\v]*\n)*
   /* Parent context state, when applicable.  */
   int context_state IF_LINT (= 0);
 
   /* Parent context state, when applicable.  */
   int context_state IF_LINT (= 0);
 

+  /* Token type to return, when applicable.  */
+  int token_type IF_LINT (= 0);
+

   /* Location of most recent identifier, when applicable.  */
   /* Location of most recent identifier, when applicable.  */

-  location id_loc IF_LINT (= *loc);
+  location id_loc IF_LINT (= empty_location);

 
 

-  /* Where containing code started, when applicable.  */
-  boundary code_start IF_LINT (= loc->start);
+  /* Where containing code started, when applicable.  Its initial
+     value is relevant only when yylex is invoked in the SC_EPILOGUE
+     start condition.  */
+  boundary code_start = scanner_cursor;

 
   /* Where containing comment or string or character literal started,
      when applicable.  */
 
   /* Where containing comment or string or character literal started,
      when applicable.  */

-  boundary token_start IF_LINT (= loc->start);
+  boundary token_start IF_LINT (= scanner_cursor);

 %}
 
 
 %}
 
 


@@ -148,13 +153,18 @@ splice     (\\[ \f\t\v]*\n)*
   | Scanning white space.  |
   `-----------------------*/
 
   | Scanning white space.  |
   `-----------------------*/
 

-<INITIAL,SC_AFTER_IDENTIFIER>
+<INITIAL,SC_AFTER_IDENTIFIER,SC_PRE_CODE>

 {
   [ \f\n\t\v]  ;
 {
   [ \f\n\t\v]  ;

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

 
   /* Comments. */
 
   /* Comments. */

-  "/*"         token_start = loc->start; context_state = YY_START; BEGIN SC_YACC_COMMENT;

   "//".*       ;
   "//".*       ;

+  "/*" {
+    token_start = loc->start;
+    context_state = YY_START;
+    BEGIN SC_YACC_COMMENT;
+  }

 
   /* #line directives are not documented, and may be withdrawn or
      modified in future versions of Bison.  */
 
   /* #line directives are not documented, and may be withdrawn or
      modified in future versions of Bison.  */


@@ -173,7 +183,7 @@ splice       (\\[ \f\t\v]*\n)*
   "%debug"                return PERCENT_DEBUG;
   "%define"               return PERCENT_DEFINE;
   "%defines"              return PERCENT_DEFINES;
   "%debug"                return PERCENT_DEBUG;
   "%define"               return PERCENT_DEFINE;
   "%defines"              return PERCENT_DEFINES;

-  "%destructor"           return PERCENT_DESTRUCTOR;
+  "%destructor"                  token_type = PERCENT_DESTRUCTOR; BEGIN SC_PRE_CODE;

   "%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;


@@ -181,6 +191,7 @@ splice       (\\[ \f\t\v]*\n)*
   "%fixed"[-_]"output"[-_]"files"   return PERCENT_YACC;
   "%glr-parser"           return PERCENT_GLR_PARSER;
   "%left"                 return PERCENT_LEFT;
   "%fixed"[-_]"output"[-_]"files"   return PERCENT_YACC;
   "%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;
   "%locations"            return PERCENT_LOCATIONS;
   "%merge"               return PERCENT_MERGE;
   "%name"[-_]"prefix"     return PERCENT_NAME_PREFIX;


@@ -188,19 +199,18 @@ splice     (\\[ \f\t\v]*\n)*
   "%nonassoc"             return PERCENT_NONASSOC;
   "%nterm"                return PERCENT_NTERM;
   "%output"               return PERCENT_OUTPUT;
   "%nonassoc"             return PERCENT_NONASSOC;
   "%nterm"                return PERCENT_NTERM;
   "%output"               return PERCENT_OUTPUT;

-  "%parse-param"          return PERCENT_PARSE_PARAM;
+  "%parse-param"         token_type = PERCENT_PARSE_PARAM; BEGIN SC_PRE_CODE;

   "%prec"                 rule_length--; return PERCENT_PREC;
   "%prec"                 rule_length--; return PERCENT_PREC;

-  "%printer"              return PERCENT_PRINTER;
+  "%printer"              token_type = PERCENT_PRINTER; BEGIN SC_PRE_CODE;

   "%pure"[-_]"parser"     return PERCENT_PURE_PARSER;
   "%right"                return PERCENT_RIGHT;
   "%pure"[-_]"parser"     return PERCENT_PURE_PARSER;
   "%right"                return PERCENT_RIGHT;

-  "%lex-param"            return PERCENT_LEX_PARAM;

   "%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;
   "%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;
+  "%union"               token_type = PERCENT_UNION; BEGIN SC_PRE_CODE;

   "%verbose"              return PERCENT_VERBOSE;
   "%yacc"                 return PERCENT_YACC;
 
   "%verbose"              return PERCENT_VERBOSE;
   "%yacc"                 return PERCENT_YACC;
 


@@ -212,10 +222,6 @@ splice      (\\[ \f\t\v]*\n)*
   "|"                     rule_length = 0; return PIPE;
   ";"                     return SEMICOLON;
 
   "|"                     rule_length = 0; return PIPE;
   ";"                     return SEMICOLON;
 

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

   {id} {
     val->symbol = symbol_get (yytext, *loc);
     id_loc = *loc;
   {id} {
     val->symbol = symbol_get (yytext, *loc);
     id_loc = *loc;


@@ -248,6 +254,7 @@ splice       (\\[ \f\t\v]*\n)*
   /* Code in between braces.  */
   "{" {
     STRING_GROW;
   /* Code in between braces.  */
   "{" {
     STRING_GROW;

+    token_type = BRACED_CODE;

     braces_level = 0;
     code_start = loc->start;
     BEGIN SC_BRACED_CODE;
     braces_level = 0;
     code_start = loc->start;
     BEGIN SC_BRACED_CODE;


@@ -265,10 +272,7 @@ splice      (\\[ \f\t\v]*\n)*
   "%%" {
     static int percent_percent_count;
     if (++percent_percent_count == 2)
   "%%" {
     static int percent_percent_count;
     if (++percent_percent_count == 2)

-      {
-       code_start = loc->start;
-       BEGIN SC_EPILOGUE;
-      }
+      BEGIN SC_EPILOGUE;

     return PERCENT_PERCENT;
   }
 
     return PERCENT_PERCENT;
   }
 


@@ -495,6 +499,39 @@ splice      (\\[ \f\t\v]*\n)*
 }
 
 
 }
 
 

+  /*---------------------------------------------------------------.
+  | Scanning after %union etc., possibly followed by white space.  |
+  | For %union only, allow arbitrary C code to appear before the   |
+  | following brace, as an extension to POSIX.                    |
+  `---------------------------------------------------------------*/
+
+<SC_PRE_CODE>
+{
+  . {
+    bool valid = yytext[0] == '{' || token_type == PERCENT_UNION;
+    scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0);
+    yyless (0);
+
+    if (valid)
+      {
+       braces_level = -1;
+       code_start = loc->start;
+       BEGIN SC_BRACED_CODE;
+      }
+    else
+      {
+       complain_at (*loc, _("missing `{' in `%s'"),
+                    token_name (token_type));
+       obstack_sgrow (&obstack_for_string, "{}");
+       STRING_FINISH;
+       val->chars = last_string;
+       BEGIN INITIAL;
+       return token_type;
+      }
+  }
+}
+
+

   /*---------------------------------------------------------------.
   | Scanning some code in braces (%union and actions). The initial |
   | "{" is already eaten.                                          |
   /*---------------------------------------------------------------.
   | Scanning some code in braces (%union and actions). The initial |
   | "{" is already eaten.                                          |


@@ -505,16 +542,35 @@ splice     (\\[ \f\t\v]*\n)*
   "{"|"<"{splice}"%"  STRING_GROW; braces_level++;
   "%"{splice}">"      STRING_GROW; braces_level--;
   "}" {
   "{"|"<"{splice}"%"  STRING_GROW; braces_level++;
   "%"{splice}">"      STRING_GROW; braces_level--;
   "}" {

-    STRING_GROW;
-    braces_level--;
-    if (braces_level < 0)
+    bool outer_brace = --braces_level < 0;
+
+    /* As an undocumented Bison extension, append `;' before the last
+       brace in braced code, so that the user code can omit trailing
+       `;'.  But do not append `;' if emulating Yacc, since Yacc does
+       not append one.
+
+       FIXME: Bison should warn if a semicolon seems to be necessary
+       here, and should omit the semicolon if it seems unnecessary
+       (e.g., after ';', '{', or '}', each followed by comments or
+       white space).  Such a warning shouldn't depend on --yacc; it
+       should depend on a new --pedantic option, which would cause
+       Bison to warn if it detects an extension to POSIX.  --pedantic
+       should also diagnose other Bison extensions like %yacc.
+       Perhaps there should also be a GCC-style --pedantic-errors
+       option, so that such warnings are diagnosed as errors.  */
+    if (outer_brace && token_type == BRACED_CODE && ! yacc_flag)
+      obstack_1grow (&obstack_for_string, ';');
+
+    obstack_1grow (&obstack_for_string, '}');
+
+    if (outer_brace)

       {
        STRING_FINISH;
       {
        STRING_FINISH;

+       rule_length++;

        loc->start = code_start;
        val->chars = last_string;
        loc->start = code_start;
        val->chars = last_string;

-       rule_length++;

        BEGIN INITIAL;
        BEGIN INITIAL;

-       return BRACED_CODE;
+       return token_type;

       }
   }
 
       }
   }
 


@@ -522,10 +578,8 @@ splice      (\\[ \f\t\v]*\n)*
      (as `<' `<%').  */
   "<"{splice}"<"  STRING_GROW;
 
      (as `<' `<%').  */
   "<"{splice}"<"  STRING_GROW;
 

-  "$"("<"{tag}">")?(-?[0-9]+|"$") { handle_dollar (current_braced_code,
-                                                  yytext, *loc); }
-  "@"(-?[0-9]+|"$")               { handle_at (current_braced_code,
-                                              yytext, *loc); }
+  "$"("<"{tag}">")?(-?[0-9]+|"$")  handle_dollar (token_type, yytext, *loc);
+  "@"(-?[0-9]+|"$")               handle_at (token_type, yytext, *loc);

 
   <<EOF>>  unexpected_end_of_file (code_start, "}");
 }
 
   <<EOF>>  unexpected_end_of_file (code_start, "}");
 }


@@ -627,14 +681,14 @@ adjust_location (location *loc, char const *token, size_t size)
 static size_t
 no_cr_read (FILE *fp, char *buf, size_t size)
 {
 static size_t
 no_cr_read (FILE *fp, char *buf, size_t size)
 {

-  size_t s = fread (buf, 1, size, fp);
-  if (s)
+  size_t bytes_read = fread (buf, 1, size, fp);
+  if (bytes_read)

     {
     {

-      char *w = memchr (buf, '\r', s);
+      char *w = memchr (buf, '\r', bytes_read);

       if (w)
        {
          char const *r = ++w;
       if (w)
        {
          char const *r = ++w;

-         char const *lim = buf + s;
+         char const *lim = buf + bytes_read;

 
          for (;;)
            {
 
          for (;;)
            {


@@ -663,7 +717,7 @@ no_cr_read (FILE *fp, char *buf, size_t size)
        }
     }
 
        }
     }
 

-  return s;
+  return bytes_read;

 }
 
 
 }
 
 


@@ -675,12 +729,15 @@ no_cr_read (FILE *fp, char *buf, size_t size)
 | Output to OBSTACK_FOR_STRING a reference to this semantic value.  |
 `------------------------------------------------------------------*/
 
 | Output to OBSTACK_FOR_STRING a reference to this semantic value.  |
 `------------------------------------------------------------------*/
 

-static inline void
+static inline bool

 handle_action_dollar (char *text, location loc)
 {
   const char *type_name = NULL;
   char *cp = text + 1;
 
 handle_action_dollar (char *text, location loc)
 {
   const char *type_name = NULL;
   char *cp = text + 1;
 

+  if (! current_rule)
+    return false;
+

   /* Get the type name if explicit. */
   if (*cp == '<')
     {
   /* Get the type name if explicit. */
   if (*cp == '<')
     {


@@ -726,44 +783,40 @@ handle_action_dollar (char *text, location loc)
       else
        complain_at (loc, _("integer out of range: %s"), quote (text));
     }
       else
        complain_at (loc, _("integer out of range: %s"), quote (text));
     }

-}
-

 
 

-/*---------------------------------------------------------------.
-| TEXT is expected to be $$ in some code associated to a symbol: |
-| destructor or printer.                                         |
-`---------------------------------------------------------------*/
-
-static inline void
-handle_symbol_code_dollar (char *text, location loc)
-{
-  char *cp = text + 1;
-  if (*cp == '$')
-    obstack_sgrow (&obstack_for_string, "]b4_dollar_dollar[");
-  else
-    complain_at (loc, _("invalid value: %s"), quote (text));
+  return true;

 }
 
 
 /*-----------------------------------------------------------------.
 | Dispatch onto handle_action_dollar, or handle_destructor_dollar, |
 }
 
 
 /*-----------------------------------------------------------------.
 | Dispatch onto handle_action_dollar, or handle_destructor_dollar, |

-| depending upon CODE_KIND.                                        |
+| depending upon TOKEN_TYPE.                                       |

 `-----------------------------------------------------------------*/
 
 static void
 `-----------------------------------------------------------------*/
 
 static void

-handle_dollar (braced_code braced_code_kind, char *text, location loc)
+handle_dollar (int token_type, char *text, location loc)

 {
 {

-  switch (braced_code_kind)
+  switch (token_type)

     {
     {

-    case action_braced_code:
-      handle_action_dollar (text, loc);
+    case BRACED_CODE:
+      if (handle_action_dollar (text, loc))
+       return;
+      break;
+
+    case PERCENT_DESTRUCTOR:
+    case PERCENT_PRINTER:
+      if (text[1] == '$')
+       {
+         obstack_sgrow (&obstack_for_string, "]b4_dollar_dollar[");
+         return;
+       }

       break;
 
       break;
 

-    case destructor_braced_code:
-    case printer_braced_code:
-      handle_symbol_code_dollar (text, loc);
+    default:

       break;
     }
       break;
     }

+
+  complain_at (loc, _("invalid value: %s"), quote (text));

 }
 
 
 }
 
 


@@ -772,16 +825,17 @@ handle_dollar (braced_code braced_code_kind, char *text, location loc)
 | OBSTACK_FOR_STRING a reference to this location.      |
 `------------------------------------------------------*/
 
 | OBSTACK_FOR_STRING a reference to this location.      |
 `------------------------------------------------------*/
 

-static inline void
+static inline bool

 handle_action_at (char *text, location loc)
 {
   char *cp = text + 1;
   locations_flag = 1;
 
 handle_action_at (char *text, location loc)
 {
   char *cp = text + 1;
   locations_flag = 1;
 

+  if (! current_rule)
+    return false;
+

   if (*cp == '$')
   if (*cp == '$')

-    {
-      obstack_sgrow (&obstack_for_string, "]b4_lhs_location[");
-    }
+    obstack_sgrow (&obstack_for_string, "]b4_lhs_location[");

   else
     {
       long num;
   else
     {
       long num;


@@ -797,22 +851,8 @@ handle_action_at (char *text, location loc)
       else
        complain_at (loc, _("integer out of range: %s"), quote (text));
     }
       else
        complain_at (loc, _("integer out of range: %s"), quote (text));
     }

-}
-

 
 

-/*---------------------------------------------------------------.
-| TEXT is expected to be @$ in some code associated to a symbol: |
-| destructor or printer.                                         |
-`---------------------------------------------------------------*/
-
-static inline void
-handle_symbol_code_at (char *text, location loc)
-{
-  char *cp = text + 1;
-  if (*cp == '$')
-    obstack_sgrow (&obstack_for_string, "]b4_at_dollar[");
-  else
-    complain_at (loc, _("invalid value: %s"), quote (text));
+  return true;

 }
 
 
 }
 
 


@@ -822,19 +862,28 @@ handle_symbol_code_at (char *text, location loc)
 `-------------------------------------------------------------------*/
 
 static void
 `-------------------------------------------------------------------*/
 
 static void

-handle_at (braced_code braced_code_kind, char *text, location loc)
+handle_at (int token_type, char *text, location loc)

 {
 {

-  switch (braced_code_kind)
+  switch (token_type)

     {
     {

-    case action_braced_code:
+    case BRACED_CODE:

       handle_action_at (text, loc);
       handle_action_at (text, loc);

+      return;
+
+    case PERCENT_DESTRUCTOR:
+    case PERCENT_PRINTER:
+      if (text[1] == '$')
+       {
+         obstack_sgrow (&obstack_for_string, "]b4_at_dollar[");
+         return;
+       }

       break;
 
       break;
 

-    case destructor_braced_code:
-    case printer_braced_code:
-      handle_symbol_code_at (text, loc);
+    default:

       break;
     }
       break;
     }

+
+  complain_at (loc, _("invalid value: %s"), quote (text));

 }
 
 
 }