Changeset 197 in lab

Timestamp:

Jan 26, 2013 1:38:41 AM (11 years ago)

Author:

mitty

Message:

• output string contains numeric character references

File:

• trunk/misc/findnonsjis.pl (modified) (2 diffs)

trunk/misc/findnonsjis.pl

@@ -19 +19 @@
     my $sjis = encode("cp932", $utf8->decode($str), Encode::FB_HTMLCREF);
     if ($sjis =~ /&#\d{4,};/) {
-        return 1;
+        Encode::from_to($sjis, "cp932", "utf8");
+        return $sjis;
     }
     
@@ -35 +36 @@
     my @dirs;
     while (my $entry = shift @entries) {
-        if (match($entry)) {
-            print "'$target/$entry' contains non Shift_JIS character\n";
+        if (my $convert = match($entry)) {
+            print "'$target/$entry' can be converted to '$convert'\n";
             next;
         }