Changeset 29767

Timestamp:

02/09/09 18:50:51 (12 months ago)

Author:

drry

Message:

• fixed regexes.
  
• et cetera.
  

Location:

lang/perl/Encode/trunk

Files:

• Unicode/Unicode.pm (modified) (4 diffs)
• encoding.pm (modified) (8 diffs)
• lib/Encode/MIME/Header.pm (modified) (6 diffs)

lang/perl/Encode/trunk/Unicode/Unicode.pm

@@ -70 +70 @@
 =head1 SYNOPSIS
 
-    use Encode qw/encode decode/; 
+    use Encode qw/encode decode/;
     $ucs2 = encode("UCS-2BE", $utf8);
     $utf8 = decode("UCS-2BE", $ucs2);
@@ -231 +231 @@
 
 Note this move has made \x{D800}-\x{DFFF} into a forbidden zone but
-perl does not prohibit the use of characters within this range.  To perl, 
+perl does not prohibit the use of characters within this range.  To perl,
 every one of \x{0000_0000} up to \x{ffff_ffff} (*) is I<a character>.
 
@@ -242 +242 @@
 Unicode encodings simply croaks.
 
-  % perl -MEncode -e '$_ = "\xfe\xff\xd8\xd9\xda\xdb\0\n"' \
-         -e 'Encode::from_to($_, "utf16","shift_jis", 0); print'
+  % perl -MEncode -e'$_ = "\xfe\xff\xd8\xd9\xda\xdb\0\n"' \
+         -e'Encode::from_to($_, "utf16","shift_jis", 0); print'
   UTF-16:Malformed LO surrogate d8d9 at /path/to/Encode.pm line 184.
-  % perl -MEncode -e '$a = "BOM missing"' \
-         -e ' Encode::from_to($a, "utf16", "shift_jis", 0); print'
+  % perl -MEncode -e'$a = "BOM missing"' \
+         -e' Encode::from_to($a, "utf16", "shift_jis", 0); print'
   UTF-16:Unrecognised BOM 424f at /path/to/Encode.pm line 184.
 
@@ -265 +265 @@
 
 Ch. 15, pp. 403 of C<Programming Perl (3rd Edition)>
-by Larry Wall, Tom Christiansen, Jon Orwant; 
+by Larry Wall, Tom Christiansen, Jon Orwant;
 O'Reilly & Associates; ISBN 0-596-00027-8
 

lang/perl/Encode/trunk/encoding.pm

@@ -207 +207 @@
   # or you can even do this if your shell supports your native encoding
 
-  perl -Mencoding=latin2 -e '...' # Feeling centrally European?
-  perl -Mencoding=euc-kr -e '...' # Or Korean?
+  perl -Mencoding=latin2 -e'...' # Feeling centrally European?
+  perl -Mencoding=euc-kr -e'...' # Or Korean?
 
   # more control
@@ -332 +332 @@
 or later fixes this problem.
 
-=item tr// 
+=item tr//
 
 C<tr//> was overlooked by Perl 5 porters when they released perl 5.8.0
@@ -339 +339 @@
 =item DATA pseudo-filehandle
 
-Another feature that was overlooked was C<DATA>. 
+Another feature that was overlooked was C<DATA>.
 
 =back
@@ -349 +349 @@
 =item use encoding [I<ENCNAME>] ;
 
-Sets the script encoding to I<ENCNAME>.  And unless ${^UNICODE} 
+Sets the script encoding to I<ENCNAME>.  And unless ${^UNICODE}
 exists and non-zero, PerlIO layers of STDIN and STDOUT are set to
 ":encoding(I<ENCNAME>)".
@@ -427 +427 @@
 
 The pragma is a per script, not a per block lexical.  Only the last
-C<use encoding> or C<no encoding> matters, and it affects 
-B<the whole script>.  However, the <no encoding> pragma is supported and 
-B<use encoding> can appear as many times as you want in a given script. 
+C<use encoding> or C<no encoding> matters, and it affects
+B<the whole script>.  However, the <no encoding> pragma is supported and
+B<use encoding> can appear as many times as you want in a given script.
 The multiple use of this pragma is discouraged.
 
 By the same reason, the use this pragma inside modules is also
-discouraged (though not as strongly discouraged as the case above.  
+discouraged (though not as strongly discouraged as the case above.
 See below).
 
@@ -602 +602 @@
   $camel = "*non-ascii*";
   binmode(STDOUT=>':encoding(utf8)'); # bang!
-  write;              # funny 
+  write;              # funny
   print $camel, "\n"; # fine
 
@@ -635 +635 @@
 If 1. didn't work but we are under the locale pragma, the environment
 variables LC_ALL and LANG (in that order) are matched for encodings
-(the part after C<.>, if any), and if any found, that is used 
+(the part after C<.>, if any), and if any found, that is used
 as the default encoding for the open pragma.
 
@@ -654 +654 @@
 =head1 HISTORY
 
-This pragma first appeared in Perl 5.8.0.  For features that require 
+This pragma first appeared in Perl 5.8.0.  For features that require
 5.8.1 and better, see above.
 

lang/perl/Encode/trunk/lib/Encode/MIME/Header.pm

@@ -45 +45 @@
 
     # multi-line header to single line
-    $str =~ s/(?:\r|\n|\r\n)[ \t]+//gos;
+    $str =~ s/(?:\r\n|[\r\n)[ \t]+//gos;
 
     1 while ( $str =~
-        s/(\=\?[0-9A-Za-z\-_]+\?[Qq]\?)(.*?)\?\=\1(.*?)\?\=/$1$2$3\?\=/ )
+        s/(=\?[-0-9A-Za-z_]+\?[Qq]\?)(.*?)\?=\1(.*?\?=)/$1$2$3/ )
       ;    # Concat consecutive QP encoded mime headers
            # Fixes breaking inside multi-byte characters
 
     $str =~ s{
-        =\?                  # begin encoded word
-        ([0-9A-Za-z\-_]+) # charset (encoding)
-                (?:\*[A-Za-z]{1,8}(?:-[A-Za-z]{1,8})*)? # language (RFC 2231)
+        =\?              # begin encoded word
+        ([-0-9A-Za-z_]+) # charset (encoding)
+        (?:\*[A-Za-z]{1,8}(?:-[A-Za-z]{1,8})*)? # language (RFC 2231)
         \?([QqBb])\?     # delimiter
         (.*?)            # Base64-encodede contents
-        \?=              # end encoded word      
-        }{
-        if    (uc($2) eq 'B'){
+        \?=              # end encoded word
+    }{
+        if      (uc($2) eq 'B'){
             $obj->{decode_b} or croak qq(MIME "B" unsupported);
             decode_b($1, $3);
-        }elsif(uc($2) eq 'Q'){
+        } elsif (uc($2) eq 'Q'){
             $obj->{decode_q} or croak qq(MIME "Q" unsupported);
             decode_q($1, $3);
-        }else{
+        } else {
             croak qq(MIME "$2" encoding is nonexistent!);
         }
-        }egox;
+    }egox;
     $_[1] = '' if $chk;
     return $str;
@@ -95 +95 @@
 my $especials =
   join( '|' => map { quotemeta( chr($_) ) }
-      unpack( "C*", qq{()<>@,;:\"\'/[]?.=} ) );
+      unpack( "C*", qq{()<>@,;:"'/[]?.=} ) );
 
 my $re_encoded_word = qr{
-       (?:
-    =\?               # begin encoded word
-    (?:[0-9A-Za-z\-_]+) # charset (encoding)
-        (?:\*\w+(?:-\w+)*)? # language (RFC 2231)
-    \?(?:[QqBb])\?      # delimiter
-    (?:.*?)             # Base64-encodede contents
-    \?=                 # end encoded word
-       )
-      }xo;
+    =\?                # begin encoded word
+    (?:[-0-9A-Za-z_]+) # charset (encoding)
+    (?:\*[A-Za-z]{1,8}+(?:-[A-Za-z]{1,8})*)? # language (RFC 2231)
+    \?(?:[QqBb])\?     # delimiter
+    (?:.*?)            # Base64-encodede contents
+    \?=                # end encoded word
+}xo;
 
 my $re_especials = qr{$re_encoded_word|$especials}xo;
@@ -113 +111 @@
     my ( $obj, $str, $chk ) = @_;
     my @line = ();
-    for my $line ( split /\r|\n|\r\n/o, $str ) {
+    for my $line ( split /\r\n|[\r\n]/o, $str ) {
         my ( @word, @subline );
         for my $word ( split /($re_especials)/o, $line ) {
@@ -177 +175 @@
     $chunk = encode_utf8($chunk);
     $chunk =~ s{
-        ([^0-9A-Za-z])
-           }{
-           join("" => map {sprintf "=%02X", $_} unpack("C*", $1))
-           }egox;
+            [^0-9A-Za-z]
+       }{
+            join("" => map {sprintf "=%02X", $_} unpack("C*", $&))
+       }egox;
     return HEAD . 'Q?' . $chunk . TAIL;
 }
@@ -193 +191 @@
 =head1 SYNOPSIS
 
-    use Encode qw/encode decode/; 
+    use Encode qw/encode decode/;
     $utf8   = decode('MIME-Header', $header);
     $header = encode('MIME-Header', $utf8);
@@ -238 +236 @@
 
 RFC 2047, L<http://www.faqs.org/rfcs/rfc2047.html> and many other
-locations. 
+locations.
 
 =cut