Re: [PATCH] Adding more information to "Unrecognized character" error in toke.c

Message-Id: <57CEC660-0020-48DF-A72A-931BCADC2AEE@surfar.nu>

p4raw-id: //depot/perl@31699

diff --git a/pod/perldiag.pod b/pod/perldiag.pod
index 42fcabc..6ebcb64 100644 (file)
--- a/pod/perldiag.pod
+++ b/pod/perldiag.pod
@@ -4410,11 +4410,11 @@ reserved word.  It's best to put such a word in quotes, or capitalize it
 somehow, or insert an underbar into it.  You might also declare it as a
 subroutine.
 
-=item Unrecognized character %s
+=item Unrecognized character %s in column %d
 
 (F) The Perl parser has no idea what to do with the specified character
-in your Perl script (or eval).  Perhaps you tried to run a compressed
-script, a binary program, or a directory as a Perl program.
+in your Perl script (or eval) at the specified column.  Perhaps you tried 
+to run a compressed script, a binary program, or a directory as a Perl program.
 
 =item Unrecognized escape \\%c in character class passed through in regex; marked by <-- HERE in m/%s/
 

diff --git a/t/base/lex.t b/t/base/lex.t
index 464e68b..f45e56c 100755 (executable)
--- a/t/base/lex.t
+++ b/t/base/lex.t
@@ -1,6 +1,6 @@
 #!./perl
 
-print "1..55\n";
+print "1..56\n";
 
 $x = 'x';
 
@@ -263,3 +263,7 @@ print ((exists $str{xyz::bar} ? "" : "not ")."ok $test\n"); ++$test;
 
 sub foo::::::bar { print "ok $test\n"; $test++ }
 foo::::::bar;
+
+eval "\$x =\xE2foo";
+if ($@ =~ /Unrecognized character \\xE2 in column 5/) { print "ok $test\n"; } else { print "not ok $test\n"; }
+$test++;

diff --git a/toke.c b/toke.c
index ead6806..889e7ec 100644 (file)
--- a/toke.c
+++ b/toke.c
@@ -3561,7 +3561,8 @@ Perl_yylex(pTHX)
     default:
        if (isIDFIRST_lazy_if(s,UTF))
            goto keylookup;
-       Perl_croak(aTHX_ "Unrecognized character \\x%02X", *s & 255);
+       len = UTF ? Perl_utf8_length((U8 *) PL_linestart, (U8 *) s) : (STRLEN) (s - PL_linestart);
+       Perl_croak(aTHX_ "Unrecognized character \\x%02X in column %d", *s & 255, (int) len + 1);
     case 4:
     case 26:
        goto fake_eof;                  /* emulate EOF on ^D or ^Z */