Warn about character literals not of length one.

* NEWS (2.5): Document.
* src/scan-gram.l (INITIAL): Remove comment that we don't check
the length.
(SC_ESCAPED_CHARACTER): Warn if length is wrong.
* tests/input.at (Bad character literals): New test group.
(cherry picked from commit ac9b0e954b1d3aed514a3bbd363da1514202af0f)

diff --git a/ChangeLog b/ChangeLog
index 7e2844a3352c5b17333ca5997ad2104eaeee7319..a67b8ca2c345d200ec65e0293df87678a15107df 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2009-07-24  Joel E. Denny  <jdenny@ces.clemson.edu>
+
+       Warn about character literals not of length one.
+       * NEWS (2.5): Document.
+       * src/scan-gram.l (INITIAL): Remove comment that we don't check
+       the length.
+       (SC_ESCAPED_CHARACTER): Warn if length is wrong.
+       * tests/input.at (Bad character literals): New test group.
+
 2009-07-24  Alex Rozenman  <rozenmam@gmail.com>
 
        Fix some memory leaks.

diff --git a/NEWS b/NEWS
index aa8c7ea27e903ee44c84807543d51339f3136494..b4887427cc2b37393fbc08f57dcc6c5f7bf3e8e5 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -133,6 +133,19 @@ Bison News
   about a missing semicolon where it did not before.  Future releases of
   Bison will cease to append semicolons entirely.
 
+** Character literals not of length one.
+
+  Previously, Bison quietly converted all character literals to length
+  one.  For example, without warning, Bison interpreted the operators in
+  the following grammar to be the same token:
+
+    exp: exp '++'
+       | exp '+' exp
+       ;
+
+  Bison now warns when a character literal is not of length one.  In
+  some future release, Bison will report an error instead.
+
 * Changes in version 2.4.2 (????-??-??):
 
 ** %code is now a permanent feature.

diff --git a/src/scan-gram.l b/src/scan-gram.l
index 6813e6053868adeee5b89c4eed925464b38df499..5c0418c630479b65c62445cacc0164aa6a76dfdc 100644 (file)
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -260,7 +260,7 @@ splice       (\\[ \f\t\v]*\n)*
     complain_at (*loc, _("invalid identifier: %s"), quote (yytext));
   }
 
-  /* Characters.  We don't check there is only one.  */
+  /* Characters.  */
   "'"        STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;
 
   /* Strings. */
@@ -493,24 +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;

diff --git a/tests/input.at b/tests/input.at
index 51b8819f5348c28068ddddf4763a05f32b44bd61..9c62f9ef6acf1fdf651946e6fd4472de29a653e7 100644 (file)
--- a/tests/input.at
+++ b/tests/input.at
@@ -1157,3 +1157,65 @@ AT_CHECK_NAMESPACE_ERROR([[::]],
                          [[namespace reference has a trailing "::"]])
 
 AT_CLEANUP
+
+## ------------------------ ##
+## Bad character literals.  ##
+## ------------------------ ##
+
+# Bison used to accept character literals that were empty or contained
+# too many characters.
+
+# FIXME: $ECHO_N and $ECHO_C are not very portable according to the
+# Autoconf manual.  Switch to AS_ECHO_N when Autoconf 2.64 is released?
+# Even better, AT_DATA or some variant of AT_DATA may eventually permit
+# a trailing newline.  See the threads starting at
+# <http://lists.gnu.org/archive/html/bison-patches/2009-07/msg00019.html>.
+
+AT_SETUP([[Bad character literals]])
+
+AT_DATA([empty.y],
+[[%%
+start: '';
+start: '
+]])
+echo $ECHO_N "start: '$ECHO_C" >> empty.y
+
+AT_BISON_CHECK([empty.y], [1], [],
+[[empty.y:2.8-9: warning: empty character literal
+empty.y:3.8-4.0: warning: empty character literal
+empty.y:3.8-4.0: missing `'' at end of line
+empty.y:4.8: warning: empty character literal
+empty.y:4.8: missing `'' at end of file
+]])
+
+AT_DATA([two.y],
+[[%%
+start: 'ab';
+start: 'ab
+]])
+echo $ECHO_N "start: 'ab$ECHO_C" >> two.y
+
+AT_BISON_CHECK([two.y], [1], [],
+[[two.y:2.8-11: warning: extra characters in character literal
+two.y:3.8-4.0: warning: extra characters in character literal
+two.y:3.8-4.0: missing `'' at end of line
+two.y:4.8-10: warning: extra characters in character literal
+two.y:4.8-10: missing `'' at end of file
+]])
+
+AT_DATA([three.y],
+[[%%
+start: 'abc';
+start: 'abc
+]])
+echo $ECHO_N "start: 'abc$ECHO_C" >> three.y
+
+AT_BISON_CHECK([three.y], [1], [],
+[[three.y:2.8-12: warning: extra characters in character literal
+three.y:3.8-4.0: warning: extra characters in character literal
+three.y:3.8-4.0: missing `'' at end of line
+three.y:4.8-11: warning: extra characters in character literal
+three.y:4.8-11: missing `'' at end of file
+]])
+
+AT_CLEANUP