scan-gram: avoid portability trap with ctype usage.

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

diff --git a/src/scan-gram.l b/src/scan-gram.l
index 279bba974b11922b773b88ce7b773cfce9353a23..bcb7209b5101aa5d4d16b36200f71d61f7e64343 100644 (file)
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -18,7 +18,7 @@
    You should have received a copy of the GNU General Public License
    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"
 
 %{
@@ -37,6 +37,7 @@
 #include <src/reader.h>
 #include <src/uniqstr.h>
 
+#include <ctype.h>
 #include <mbswidth.h>
 #include <quote.h>
 
@@ -70,7 +71,7 @@ static size_t no_cr_read (FILE *, char *, size_t);
 /* A string representing the most recently saved token.  */
 static char *last_string;
 
-/* Bracketed identifier */
+/* Bracketed identifier. */
 static uniqstr bracketed_id_str = 0;
 static location bracketed_id_loc;
 static boundary bracketed_id_start;
@@ -108,7 +109,7 @@ 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 */
+ /* Bracketed identifiers support. */
 %x SC_BRACKETED_ID SC_RETURN_BRACKETED_ID
 
 letter   [-.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
@@ -260,8 +261,8 @@ splice       (\\[ \f\t\v]*\n)*
     complain_at (*loc, _("invalid identifier: %s"), quote (yytext));
   }
 
-  /* Characters.  We don't check there is only one.  */
-  "'"        STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;
+  /* Characters.  */
+  "'"        token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;
 
   /* Strings. */
   "\""       token_start = loc->start; BEGIN SC_ESCAPED_STRING;
@@ -336,19 +337,19 @@ splice     (\\[ \f\t\v]*\n)*
 <SC_AFTER_IDENTIFIER>
 {
   "[" {
-    if (!bracketed_id_str)
-      {
-       bracketed_id_start = loc->start;
-       bracketed_id_context_state = YY_START;
-       BEGIN SC_BRACKETED_ID;
-      }
-    else
+    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);
@@ -375,15 +376,15 @@ splice     (\\[ \f\t\v]*\n)*
 <SC_BRACKETED_ID>
 {
   {id} {
-    if (!bracketed_id_str)
+    if (bracketed_id_str)
       {
-       bracketed_id_str = uniqstr_new (yytext);
-       bracketed_id_loc = *loc;
+       complain_at (*loc, _("unexpected identifier in bracketed name: %s"),
+                    quote (yytext));
       }
     else
       {
-       complain_at (*loc, _("redundant identifier in bracketed name: %s"),
-                    quote (yytext));
+       bracketed_id_str = uniqstr_new (yytext);
+       bracketed_id_loc = *loc;
       }
   }
   "]" {
@@ -399,7 +400,7 @@ splice       (\\[ \f\t\v]*\n)*
          }
       }
     else
-      complain_at (*loc, _("a non empty identifier expected"));
+      complain_at (*loc, _("an identifier expected"));
   }
   . {
     complain_at (*loc, _("invalid character in bracketed name: %s"),
@@ -493,24 +494,42 @@ 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];
+    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>> {
-    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;
@@ -560,10 +579,9 @@ 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);
   }
@@ -571,10 +589,9 @@ 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);
   }
@@ -592,16 +609,20 @@ 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 (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);
   }
 }