Warn about character literals not of length one.

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

diff --git a/src/scan-gram.l b/src/scan-gram.l
index 2eb36664cd486f1295cddcbb281b7a57a8362f0e..5c0418c630479b65c62445cacc0164aa6a76dfdc 100644 (file)
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -61,10 +61,21 @@ static size_t no_cr_read (FILE *, char *, size_t);
     return PERCENT_FLAG;                        \
   } while (0)
 
+#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)
 {
@@ -97,9 +108,11 @@ 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]|-)*
+letter   [-.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
+id       {letter}({letter}|[0-9])*
 directive %{id}
 int      [0-9]+
 
@@ -141,7 +154,7 @@ splice       (\\[ \f\t\v]*\n)*
   | 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"));
@@ -181,7 +194,7 @@ splice       (\\[ \f\t\v]*\n)*
   "%defines"                        return PERCENT_DEFINES;
   "%destructor"                     return PERCENT_DESTRUCTOR;
   "%dprec"                          return PERCENT_DPREC;
-  "%error"[-_]"verbose"             RETURN_PERCENT_FLAG("error-verbose");
+  "%error"[-_]"verbose"             return PERCENT_ERROR_VERBOSE;
   "%expect"                         return PERCENT_EXPECT;
   "%expect"[-_]"rr"                 return PERCENT_EXPECT_RR;
   "%file-prefix"                    return PERCENT_FILE_PREFIX;
@@ -228,6 +241,7 @@ splice       (\\[ \f\t\v]*\n)*
   {id} {
     val->uniqstr = uniqstr_new (yytext);
     id_loc = *loc;
+    bracketed_id_str = NULL;
     BEGIN SC_AFTER_IDENTIFIER;
   }
 
@@ -240,7 +254,13 @@ splice      (\\[ \f\t\v]*\n)*
     return INT;
   }
 
-  /* Characters.  We don't check there is only one.  */
+  /* 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.  */
   "'"        STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;
 
   /* Strings. */
@@ -280,6 +300,13 @@ 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));
   }
@@ -308,25 +335,94 @@ splice     (\\[ \f\t\v]*\n)*
 
 <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;
-    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;
   }
   <<EOF>> {
+    BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL);
     *loc = id_loc;
-    BEGIN INITIAL;
     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.  |
@@ -397,24 +493,40 @@ splice     (\\[ \f\t\v]*\n)*
 <SC_ESCAPED_CHARACTER>
 {
   "'"|"\n" {
-    if (yytext[0] == '\n')
-      unexpected_newline (token_start, "'");
     STRING_GROW;
     STRING_FINISH;
     loc->start = token_start;
     val->character = last_string[1];
+    {
+      /* FIXME: Eventually, make these errors.  */
+      size_t length = strlen (last_string);
+      if (strlen (last_string) < 3)
+        warn_at (*loc, _("empty character literal"));
+      else if (strlen (last_string) > 3)
+        warn_at (*loc, _("extra characters in character literal"));
+    }
+    if (yytext[0] == '\n')
+      unexpected_newline (token_start, "'");
     STRING_FREE;
     BEGIN INITIAL;
     return CHAR;
   }
   <<EOF>> {
-    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];
+    {
+      size_t length = strlen (last_string);
+      /* FIXME: Eventually, make these errors.  */
+      if (length < 2)
+        warn_at (*loc, _("empty character literal"));
+      else if (length > 2)
+        warn_at (*loc, _("extra characters in character literal"));
+      if (length > 1)
+        val->character = last_string[1];
+      else
+        val->character = last_string[0];
+    }
+    unexpected_eof (token_start, "'");
     STRING_FREE;
     BEGIN INITIAL;
     return CHAR;