r18560 - in /branches/upstream/libmime-encwords-perl/current: ./ EncWords/ t/ testin/
gregoa-guest at users.alioth.debian.org
gregoa-guest at users.alioth.debian.org
Sun Apr 13 12:06:17 UTC 2008
Author: gregoa-guest
Date: Sun Apr 13 12:06:16 2008
New Revision: 18560
URL: http://svn.debian.org/wsvn/?sc=1&rev=18560
Log:
[svn-upgrade] Integrating new upstream version, libmime-encwords-perl (1.010)
Added:
branches/upstream/libmime-encwords-perl/current/testin/decode-ascii.txt
branches/upstream/libmime-encwords-perl/current/testin/encode-ascii.txt
Modified:
branches/upstream/libmime-encwords-perl/current/Changes
branches/upstream/libmime-encwords-perl/current/EncWords.pm
branches/upstream/libmime-encwords-perl/current/EncWords/JA_JP.pod
branches/upstream/libmime-encwords-perl/current/META.yml
branches/upstream/libmime-encwords-perl/current/Makefile.PL
branches/upstream/libmime-encwords-perl/current/README
branches/upstream/libmime-encwords-perl/current/t/01decode.t
branches/upstream/libmime-encwords-perl/current/t/02encode.t
branches/upstream/libmime-encwords-perl/current/testin/encode-multibyte.txt
branches/upstream/libmime-encwords-perl/current/testin/encode-singlebyte.txt
Modified: branches/upstream/libmime-encwords-perl/current/Changes
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/Changes?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/Changes (original)
+++ branches/upstream/libmime-encwords-perl/current/Changes Sun Apr 13 12:06:16 2008
@@ -1,3 +1,21 @@
+2008-04-12 Hatuka*nezumi - IKEDA Soji <hatuka at nezumi.nu>
+
+ * Release 1.010.
+ * encode_mimeword(): Restrict characters in encoded-words
+ according to RFC 2047 section 5 (3).
+ Note: length(encode_mimeword()) may not be equal to
+ encoded_header_len() of MIME::Charset 1.004 or earlier.
+ * Bug Fix: Texts with ``US-ASCII transformation'' charsets,
+ HZ-GB-2312 (RFC 1842) and UTF-7 (RFC 2152), were treated
+ as US-ASCII.
+ * Fix: encoded-words exceeding line length can be generated.
+ * encode_mimewords(): Improved encoding of unsafe ASCII
+ sequences (words exceeding line length or including ``=?'').
+ * encode_mimeword(): can take charset object argument.
+ In this case RAW can be Unicode string.
+ * Modified / added tests for multibyte / singlebyte / unsafe
+ ASCII.
+
2008-03-30 Hatuka*nezumi - IKEDA Soji <hatuka at nezumi.nu>
* Release 1.009.
Modified: branches/upstream/libmime-encwords-perl/current/EncWords.pm
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/EncWords.pm?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/EncWords.pm (original)
+++ branches/upstream/libmime-encwords-perl/current/EncWords.pm Sun Apr 13 12:06:16 2008
@@ -120,7 +120,7 @@
#------------------------------
### The package version, both in 1.23 style *and* usable by MakeMaker:
-$VERSION = '1.009';
+$VERSION = '1.010';
### Public Configuration Attributes
$Config = {
@@ -142,6 +142,7 @@
my $NONPRINT = qr{[^$PRINTABLE]}; # Improvement: Unicode support.
my $UNSAFE = qr{[^\x01-\x20$PRINTABLE]};
my $WIDECHAR = qr{[^\x00-\xFF]};
+my $ASCIITRANS = qr{^(?:HZ-GB-2312|UTF-7)$}i;
#------------------------------
@@ -180,9 +181,9 @@
# Improvement by this module: Spaces are escaped by ``_''.
sub _encode_Q {
my $str = shift;
- # $str =~ s{([_\?\=$NONPRINT])}{sprintf("=%02X", ord($1))}eog;
- $str =~ s{(\x20)|([_?=]|$NONPRINT)}{
- defined $1? "_": sprintf("=%02X", ord($2))
+ # Restrict characters to those listed in RFC 2047 section 5 (3)
+ $str =~ s{[^-!*+/0-9A-Za-z]}{
+ $& eq "\x20"? "_": sprintf("=%02X", ord($&))
}eog;
$str;
}
@@ -483,9 +484,17 @@
sub encode_mimeword {
my $word = shift;
my $encoding = uc(shift || 'Q'); # not overridden.
- my $charset = uc(shift || 'ISO-8859-1'); # ditto.
+ my $charset = shift || 'ISO-8859-1'; # ditto.
my $language = uc(shift || ""); # ditto.
+ if (ref $charset) {
+ if (is_utf8($word) or $word =~ /$WIDECHAR/) {
+ $word = $charset->undecode($word, 0);
+ }
+ $charset = $charset->as_string;
+ } else {
+ $charset = uc($charset);
+ }
my $encstr;
if ($encoding eq 'Q') {
$encstr = &_encode_Q($word);
@@ -639,17 +648,16 @@
my $words = shift;
my %params = @_;
my %Params = &_getparams(\%params,
- NoDefault => [qw(Charset)], # apply default later
YesNo => [qw(Detect7bit Minimal)],
- Others => [qw(Encoding Field Folding Mapping
- MaxLineLen Replacement)],
+ Others => [qw(Charset Encoding Field Folding
+ Mapping MaxLineLen Replacement)],
ToUpper => [qw(Charset Encoding Mapping
Replacement)],
);
- # checks
croak "unsupported encoding ``$Params{Encoding}''"
unless $Params{Encoding} =~ /^[ABQS]$/;
- my ($fwsbrk, $fwsspc); # Newline and following WSP
+ # newline and following WSP
+ my ($fwsbrk, $fwsspc);
if ($Params{Folding} =~ m/^([\r\n]*)([\t ]?)$/) {
$fwsbrk = $1;
$fwsspc = $2 || " ";
@@ -657,90 +665,115 @@
croak sprintf "illegal folding sequence ``\\x%*v02X''", '\\x',
$Params{Folding};
}
- # calculate some variables
+ # charset objects
my $charsetobj = MIME::Charset->new($Params{Charset},
Mapping => $Params{Mapping});
+ my $ascii = MIME::Charset->new("US-ASCII", Mapping => 'STANDARD');
+ $ascii->encoder($ascii);
+ # lengths
my $firstlinelen = $Params{MaxLineLen} -
($Params{Field}? length("$Params{Field}: "): 0);
my $maxrestlen = $Params{MaxLineLen} - length($fwsspc);
+ my $UNSAFEASCII = ($maxrestlen <= 1)?
+ qr{(?: =\? )}ox:
+ qr{(?: =\? | [$PRINTABLE]{$Params{MaxLineLen}} )}ox;
unless (ref($words) eq "ARRAY") {
+ my @words = ();
# unfolding: normalize linear-white-spaces and orphan newlines.
$words =~ s/(?:[\r\n]+[\t ])*[\r\n]+([\t ]|\Z)/$1? " ": ""/eg;
$words =~ s/[\r\n]+/ /g;
# split if required
if ($Params{Minimal} eq "YES") {
- my @words = map { [$_, $Params{Charset}] }
- split(/((?:\A|[\t ])[\t $PRINTABLE]+(?:[\t ]|\Z))/,
- $words);
- $words = \@words;
+ my ($spc, $unsafe_last) = ('', 0);
+ foreach my $w (split(/([\t ]+)/, $words)) {
+ next unless scalar(@words) or length($w); # skip garbage
+ if ($w =~ /[\t ]/) {
+ $spc = $w;
+ next;
+ }
+
+ # workaround for ``ASCII transformation'' charsets
+ my $u = $w;
+ if ($charsetobj->as_string =~ /$ASCIITRANS/ and $u =~ /[+~]/) {
+ if ($charsetobj->decoder) {
+ $u = $charsetobj->decode($u);
+ } elsif (!MIME::Charset::USE_ENCODE) { # for pre-Encode env.
+ $u = "X$u";
+ } else { # NOTREACHED
+ croak __PACKAGE__.": Bug in encode_mimewords";
+ }
+ }
+ if (scalar(@words)) {
+ if (($w =~ /$NONPRINT|$UNSAFEASCII/ or $u ne $w) xor
+ $unsafe_last) {
+ if ($unsafe_last) {
+ push @words, $spc.$w;
+ } else {
+ $words[-1] .= $spc;
+ push @words, $w;
+ }
+ $unsafe_last = not $unsafe_last;
+ } else {
+ $words[-1] .= $spc.$w;
+ }
+ } else {
+ push @words, $spc.$w;
+ $unsafe_last =
+ ($w =~ /$NONPRINT|$UNSAFEASCII/ or $u ne $w);
+ }
+ $spc = '';
+ }
+ if ($spc) {
+ if (scalar(@words)) {
+ $words[-1] .= $spc;
+ } else { # only WSPs
+ push @words, $spc;
+ }
+ }
} else {
- $words = [[$words, $Params{Charset}]];
- }
+ @words = ($words);
+ }
+ $words = [map { [$_, $Params{Charset}] } @words];
}
# Translate / concatenate words.
my @triplets;
foreach (@$words) {
my ($s, $cset) = @$_;
- my $csetobj = MIME::Charset->new($cset, Mapping => $Params{Mapping});
+ next unless length($s);
+ my $csetobj = MIME::Charset->new($cset || "",
+ Mapping => $Params{Mapping});
+ # determine charset and encoding
+ # try defaults only if 7-bit charset detection is not required
my $enc;
-
- next unless length($s);
-
- # Unicode string should be encoded by given charset.
- # Unsupported charset will be fallbacked to UTF-8.
- if (is_utf8($s) or $s =~ $WIDECHAR) {
- unless ($csetobj->decoder) {
- if ($s !~ $UNSAFE) {
- $cset = "US-ASCII";
- } elsif ($Params{Replacement} =~ /^(CROAK|STRICT)$/) {
- croak "unsupported charset ``$cset''";
- } else {
- $cset = "UTF-8";
- }
- }
- $csetobj = MIME::Charset->new($cset, Mapping => $Params{Mapping});
- if ($Params{Replacement} =~ /^(CROAK|STRICT)$/) {
- $s = $csetobj->undecode($s, FB_CROAK());
- } else {
- $s = $csetobj->undecode($s, 0);
- }
- }
-
- # Determine charset and encoding.
- if ($Params{Encoding} eq "A") {
- my $obj = $cset? $csetobj: $charsetobj;
- ($s, $cset, $enc) =
- $obj->header_encode($s,
- Detect7bit => $Params{Detect7bit},
- Replacement => $Params{Replacement});
- if ($cset eq "8BIT") {
- $cset = $Config->{Charset};
- $csetobj = MIME::Charset->new($cset,
- Mapping => $Params{Mapping});
- $enc = $csetobj->header_encoding;
- } else {
- $csetobj = MIME::Charset->new($cset,
- Mapping => $Params{Mapping});
- }
- } elsif (!$cset or $cset ne "US-ASCII") {
- $cset ||= $Params{Charset} || $Config->{Charset};
- $csetobj = MIME::Charset->new($cset, Mapping => $Params{Mapping});
- my $u = $s;
- $@ = '';
- eval {
- $u = $csetobj->decode($u, 0);
- } if MIME::Charset::USE_ENCODE;
- if ($@ or $u =~ $UNSAFE) {
- $enc = $Params{Encoding};
- } else {
- ($cset, $enc) = ("US-ASCII", undef);
- $csetobj = MIME::Charset->new($cset, Mapping => "STANDARD");
- }
- }
-
- # Now no charset transformations are needed.
+ my $obj = $csetobj;
+ unless ($obj->as_string) {
+ if ($Params{Encoding} ne "A" or $Params{Detect7bit} eq "NO" or
+ $s =~ /$UNSAFE/) {
+ $obj = $charsetobj;
+ }
+ }
+ ($s, $cset, $enc) =
+ $obj->header_encode($s,
+ Detect7bit => $Params{Detect7bit},
+ Replacement => $Params{Replacement},
+ Encoding => $Params{Encoding});
+ # pure ASCII
+ if ($cset eq "US-ASCII" and !$enc and $s =~ /$UNSAFEASCII/) {
+ # pure ASCII with unsafe sequences should be encoded
+ $cset = $csetobj->output_charset ||
+ $charsetobj->output_charset ||
+ $ascii->output_charset;
+ $csetobj = MIME::Charset->new($cset,
+ Mapping => $Params{Mapping});
+ $enc = $csetobj->header_encoding || 'Q';
+ } else {
+ $csetobj = MIME::Charset->new($cset,
+ Mapping => $Params{Mapping});
+ }
+
+ # Now no charset translations are needed.
$csetobj->encoder($csetobj);
# Concatenate adjacent ``words'' so that multibyte sequences will
@@ -754,8 +787,8 @@
($lastenc || "") eq ($enc || "")) {
$triplets[-1]->[0] .= $s;
next;
- } elsif (!$lastenc and $enc and $last !~ /[\t ]$/) {
- if ($last =~ /^(.*)([\t ])([$PRINTABLE]+)$/s) {
+ } elsif (!$lastenc and $enc and $last !~ /[\r\n\t ]$/) {
+ if ($last =~ /^(.*)([\r\n\t ])([$PRINTABLE]+)$/s) {
$triplets[-1]->[0] = $1.$2;
$s = $3.$s;
} elsif ($lastcsetobj->as_string eq "US-ASCII") {
@@ -764,8 +797,8 @@
$triplets[-1]->[2] = $csetobj;
next;
}
- } elsif ($lastenc and !$enc and $s !~ /^[\t ]/) {
- if ($s =~ /^([$PRINTABLE]+)([\t ])(.*)$/s) {
+ } elsif ($lastenc and !$enc and $s !~ /^[\r\n\t ]/) {
+ if ($s =~ /^([$PRINTABLE]+)([\r\n\t ])(.*)$/s) {
$triplets[-1]->[0] .= $1;
$s = $2.$3;
} elsif ($csetobj->as_string eq "US-ASCII") {
@@ -778,8 +811,8 @@
}
# chop leading FWS
- while ($triplets[0]->[0] =~ s/^[\r\n\t ]+//) {
- shift @triplets unless $triplets[0]->[0];
+ while (scalar(@triplets) and $triplets[0]->[0] =~ s/^[\r\n\t ]+//) {
+ shift @triplets unless length($triplets[0]->[0]);
}
# Split long ``words''.
@@ -788,23 +821,21 @@
foreach (@triplets) {
my ($s, $enc, $csetobj) = @$_;
- if ($enc and $restlen < $csetobj->encoded_header_len("\a", $enc) or
- !$enc and $restlen < length($s) - ($s =~ /^[\t ]/? 1: 0)) {
- $restlen = $maxrestlen;
- }
-
push @splitted, &_split($s, $enc, $csetobj, $restlen, $maxrestlen);
my ($last, $lastenc, $lastcsetobj) = @{$splitted[-1]};
+ my $lastlen;
if ($lastenc) {
- $restlen -= $lastcsetobj->encoded_header_len($last, $lastenc);
+ $lastlen = $lastcsetobj->encoded_header_len($last, $lastenc);
} else {
- $restlen -= length($last); # FIXME: Sometimes estimated longer
- }
+ $lastlen = length($last);
+ }
+ $restlen -= $lastlen; # FIXME: Sometimes estimated longer
+ $restlen = $maxrestlen if $restlen <= 1;
}
# Do encoding.
my @lines;
- my $linelen = $firstlinelen;
+ $restlen = $firstlinelen;
foreach (@splitted) {
my ($str, $encoding, $charsetobj) = @$_;
next unless length($str);
@@ -813,22 +844,22 @@
if (!$encoding) {
$s = $str;
} else {
- $s = &encode_mimeword($str, $encoding, $charsetobj->as_string);
- }
-
- my $spc = (scalar(@lines) and $lines[-1] =~ /[\t ]$/ or
- $s =~ /^[\t ]/)? '': ' ';
+ $s = encode_mimeword($str, $encoding, $charsetobj);
+ }
+
+ my $spc = (scalar(@lines) and $lines[-1] =~ /[\r\n\t ]$/ or
+ $s =~ /^[\r\n\t ]/)? '': ' ';
if (!scalar(@lines)) {
push @lines, $s;
- } elsif (length($lines[-1].$spc.$s) <= $linelen) {
+ } elsif (length($lines[-1].$spc.$s) <= $restlen) {
$lines[-1] .= $spc.$s;
} else {
if ($lines[-1] =~ s/([\r\n\t ]+)$//) {
$s = $1.$s;
}
- $s =~ s/^[\t ]//; # strip only one WSP replaced by that of FWS
+ $s =~ s/^[\r\n]*[\t ]//; # strip only one WSP replaced by FWS
push @lines, $s;
- $linelen = $maxrestlen;
+ $restlen = $maxrestlen;
}
}
@@ -866,10 +897,17 @@
last;
}
$ustr = $str;
- if (MIME::Charset::USE_ENCODE) {
+ if (!(is_utf8($ustr) or $ustr =~ /$WIDECHAR/) and
+ MIME::Charset::USE_ENCODE) {
$ustr = $charset->decode($ustr);
}
($first, $str) = &_clip_unsafe($ustr, $encoding, $charset, $restlen);
+ # retry splitting if failed
+ if ($first and !$str and
+ $maxrestlen < $charset->encoded_header_len($first, $encoding)) {
+ ($first, $str) = &_clip_unsafe($ustr, $encoding, $charset,
+ $maxrestlen);
+ }
push @splitted, [$first, $encoding, $charset];
$restlen = $maxrestlen;
}
@@ -879,9 +917,7 @@
# _split_ascii RAW, ROOM_OF_FIRST_LINE, MAXRESTLEN
# Private: used by encode_mimewords() to split an US-ASCII string into
# (encoded or non-encoded) words.
-# Returns an array of arrayrefs [SUBSTRING, ENCODING, "US-ASCII"],
-# where ENCODING is either undef or (if any unsafe sequences are
-# included) "Q".
+# Returns an array of arrayrefs [SUBSTRING, undef, "US-ASCII"].
sub _split_ascii {
my $s = shift;
my $restlen = shift;
@@ -891,12 +927,6 @@
my @splitted;
my $ascii = MIME::Charset->new("US-ASCII", Mapping => 'STANDARD');
foreach my $line (split(/(?:[\t ]*[\r\n]+)+/, $s)) {
- if (length($line) <= $restlen and $line !~ /=\?|$UNSAFE/) {
- push @splitted, [$line, undef, $ascii];
- $restlen = $maxrestlen;
- next;
- }
-
my $spc = '';
foreach my $word (split(/([\t ]+)/, $line)) {
next unless scalar(@splitted) or $word; # skip first garbage
@@ -905,44 +935,22 @@
next;
}
- my $enc = ($word =~ /=\?|$UNSAFE/)? "Q": undef;
+ my $cont = $spc.$word;
+ my $elen = length($cont);
+ next unless $elen;
if (scalar(@splitted)) {
- my ($last, $lastenc, $lastcsetobj) = @{$splitted[-1]};
- my ($elen, $cont, $appe);
-
# Concatenate adjacent words so that encoded-word and
# unencoded text will adjoin with separating whitespace.
- if (!$lastenc and !$enc) {
- $elen = length($spc.$word);
- ($cont, $appe) = ($spc.$word, "");
- } elsif (!$lastenc and $enc) {
- $elen = length($spc) +
- $ascii->encoded_header_len($word, "Q");
- ($cont, $appe) = ($spc, $word);
- } elsif ($lastenc and !$enc) {
- $elen = length($spc.$word);
- ($cont, $appe) = ("", $spc.$word);
- } else {
- $elen = $ascii->encoded_header_len($spc.$word, "Q") - 15;
- ($cont, $appe) = ($spc.$word, "");
- }
if ($elen <= $restlen) {
- $splitted[-1]->[0] .= $cont if $cont;
- push @splitted, [$appe, $enc, $ascii] if $appe;
+ $splitted[-1]->[0] .= $cont;
$restlen -= $elen;
} else {
- push @splitted, [$cont, $lastenc, $ascii] if $cont;
- push @splitted, [$appe, $enc, $ascii] if $appe;
+ push @splitted, [$cont, undef, $ascii];
$restlen = $maxrestlen - $elen;
- $restlen -= 15 if $lastenc and $enc;
}
} else {
- push @splitted, [$spc.$word, $enc, $ascii];
- if ($enc) {
- $restlen -= $ascii->encoded_header_len($spc.$word, "Q");
- } else {
- $restlen -= length($spc.$word);
- }
+ push @splitted, [$cont, undef, $ascii];
+ $restlen -= $elen;
}
$spc = '';
}
@@ -950,7 +958,7 @@
if (scalar(@splitted)) {
$splitted[-1]->[0] .= $spc;
$restlen -= length($spc);
- } else { # NOTREACHED
+ } else { # only WSPs
push @splitted, [$spc, undef, $ascii];
$restlen = $maxrestlen - length($spc);
}
Modified: branches/upstream/libmime-encwords-perl/current/EncWords/JA_JP.pod
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/EncWords/JA_JP.pod?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/EncWords/JA_JP.pod (original)
+++ branches/upstream/libmime-encwords-perl/current/EncWords/JA_JP.pod Sun Apr 13 12:06:16 2008
@@ -41,7 +41,7 @@
=head1 DESCRIPTION
åˆè¡†å›½ã®è«¸å›ã€‚ã“ã®ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«ã§ã„ã£ãŸã„何をやらã‹ãã†ã¨ã„ã†ã®ã‹ã€
-ã‚ã‹ã‚‰ãªã„ã‹ã‚‚ã—ã‚Œãªã„ã。欧州ã€ãƒã‚·ã‚¢ã®è«¸å›ãªã‚‰ã€ã‚ã‹ã‚‹ã ã‚ã†ã€‚C<(:-)>。
+ã‚ã‹ã‚‰ãªã„ã‹ã‚‚ã—ã‚Œãªã„ã。欧州ã€ãƒã‚·ã‚¢ç‰ã®è«¸å›ãªã‚‰ã€ã‚ã‹ã‚‹ã ã‚ã†ã€‚C<(:-)>。
ãŸã¨ãˆã°ã€ã“ã‚Œã¯æœ‰åŠ¹ãª MIME ヘッダã :
@@ -61,7 +61,7 @@
B<追補>: åˆè¡†å›½ã€æ¬§å·žã®è«¸å›ã€‚
ã“ã®ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«ã§ã„ã£ãŸã„ãªã«ã‚’やらã‹ãã†ã¨ã„ã†ã®ã‹ã€
-ã‚ã‹ã‚‰ãªã„ã‹ã‚‚ã—ã‚Œãªã„ã。æ±ã‚¢ã‚¸ã‚¢ã®è«¸å›ãªã‚‰ã€ã‚ã‹ã‚‹ã ã‚ã†ã€‚
+ã‚ã‹ã‚‰ãªã„ã‹ã‚‚ã—ã‚Œãªã„ã。æ±ã‚¢ã‚¸ã‚¢ç‰ã®è«¸å›ãªã‚‰ã€ã‚ã‹ã‚‹ã ã‚ã†ã€‚
C<(^_^)>.
ãŸã¨ãˆã°ã€ã“ã‚Œã¯æœ‰åŠ¹ãª MIME ヘッダã :
Modified: branches/upstream/libmime-encwords-perl/current/META.yml
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/META.yml?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/META.yml (original)
+++ branches/upstream/libmime-encwords-perl/current/META.yml Sun Apr 13 12:06:16 2008
@@ -1,13 +1,13 @@
# http://module-build.sourceforge.net/META-spec.html
#XXXXXXX This is a prototype!!! It will change in the future!!! XXXXX#
name: MIME-EncWords
-version: 1.009
+version: 1.010
version_from: EncWords.pm
installdirs: site
requires:
Encode: 1.98
MIME::Base64: 2.13
- MIME::Charset: 1.004
+ MIME::Charset: 1.006
Test: 0
distribution_type: module
Modified: branches/upstream/libmime-encwords-perl/current/Makefile.PL
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/Makefile.PL?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/Makefile.PL (original)
+++ branches/upstream/libmime-encwords-perl/current/Makefile.PL Sun Apr 13 12:06:16 2008
@@ -6,11 +6,11 @@
'VERSION_FROM' => 'EncWords.pm',
'PREREQ_PM' => ($] >= 5.008001)? {
'Encode' => 1.98,
- 'MIME::Charset' => 1.004,
+ 'MIME::Charset' => 1.006,
'MIME::Base64' => 2.13,
'Test' => 0,
}: {
- 'MIME::Charset' => 1.004,
+ 'MIME::Charset' => 1.006,
'MIME::Base64' => 2.13,
'Test' => 0,
},
Modified: branches/upstream/libmime-encwords-perl/current/README
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/README?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/README (original)
+++ branches/upstream/libmime-encwords-perl/current/README Sun Apr 13 12:06:16 2008
@@ -55,7 +55,8 @@
Subject: If you can read this you understand the example... cool!
Supplement: Fellow Americans, Europeans, you probably won't know what
- the hell this module is for. East Asians, et al, you probably do. ":-)".
+ the hell this module is for. East Asians, et al, you probably do.
+ "(^_^)".
For example, here's a valid MIME header you might get:
Modified: branches/upstream/libmime-encwords-perl/current/t/01decode.t
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/t/01decode.t?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/t/01decode.t (original)
+++ branches/upstream/libmime-encwords-perl/current/t/01decode.t Sun Apr 13 12:06:16 2008
@@ -1,7 +1,7 @@
use strict;
use Test;
-BEGIN { plan tests => ($] >= 5.008001)? 42: 10 }
+BEGIN { plan tests => ($] >= 5.008001)? 48: 16 }
use MIME::EncWords qw(decode_mimewords);
$MIME::EncWords::Config = {
@@ -16,9 +16,7 @@
Minimal => 'YES',
};
-my @testins = MIME::Charset::USE_ENCODE?
- qw(decode-singlebyte decode-multibyte):
- qw(decode-singlebyte);
+my @testins = qw(decode-singlebyte decode-multibyte decode-ascii);
{
local($/) = '';
@@ -32,7 +30,8 @@
$isgood = (uc($isgood) eq 'GOOD');
($expect, $charset, $ucharset) = eval $expect;
- my $dec = decode_mimewords($enc, Charset => $charset);
+ # Convert to raw data...
+ my $dec = decode_mimewords($enc);
ok((($isgood && !$@) or (!$isgood && $@)) and
($isgood ? ($dec eq $expect) : 1));
if (MIME::Charset::USE_ENCODE) {
Modified: branches/upstream/libmime-encwords-perl/current/t/02encode.t
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/t/02encode.t?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/t/02encode.t (original)
+++ branches/upstream/libmime-encwords-perl/current/t/02encode.t Sun Apr 13 12:06:16 2008
@@ -1,7 +1,7 @@
use strict;
use Test;
-BEGIN { plan tests => ($] >= 5.008001)? 17: 12 }
+BEGIN { plan tests => ($] >= 5.008001)? 26: 12 }
use MIME::EncWords qw(encode_mimewords);
$MIME::EncWords::Config = {
@@ -17,7 +17,7 @@
};
my @testins = MIME::Charset::USE_ENCODE?
- qw(encode-singlebyte encode-multibyte):
+ qw(encode-singlebyte encode-multibyte encode-ascii):
qw(encode-singlebyte);
{
@@ -32,8 +32,8 @@
my @params = eval $dec;
my $enc = encode_mimewords(@params);
- ok((($isgood && !$@) or (!$isgood && $@)) and
- ($isgood ? ($enc eq $expect) : 1));
+ ok((($isgood && !$@) or (!$isgood && $@)) &&
+ ($isgood ? $enc : $expect), $expect, $enc);
}
close WORDS;
}
Added: branches/upstream/libmime-encwords-perl/current/testin/decode-ascii.txt
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/testin/decode-ascii.txt?rev=18560&op=file
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/testin/decode-ascii.txt (added)
+++ branches/upstream/libmime-encwords-perl/current/testin/decode-ascii.txt Sun Apr 13 12:06:16 2008
@@ -1,0 +1,10 @@
+GOOD
+("Subject: Notification d'+AOk-tat de remise (+AOk-chec)","utf-7","iso-8859-1")
+Subject: Notification =?utf-7?Q?d=27+AOk-tat?= de remise
+ =?utf-7?Q?(+AOk-chec)?=
+
+GOOD
+("The next sentence is in GB.~{<:Ky2;S{#,NpJ)l6HK!#~}Bye.", "hz")
+The next sentence is in
+ =?HZ-GB-2312?B?R0Iufns8Okt5MjtTeyMsTnBKKWw2SEshI359QnllLg==?=
+
Added: branches/upstream/libmime-encwords-perl/current/testin/encode-ascii.txt
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/testin/encode-ascii.txt?rev=18560&op=file
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/testin/encode-ascii.txt (added)
+++ branches/upstream/libmime-encwords-perl/current/testin/encode-ascii.txt Sun Apr 13 12:06:16 2008
@@ -1,0 +1,41 @@
+GOOD
+([["Perl=?: "], ["\x1B\x24BIBE*\x40^Co<g5AE*GQJ*=PNO4o\x1B(B", "ISO-2022-JP"], [" (Pathologically Eclectic Rubbish Lister)"]])
+=?ISO-8859-1?Q?Perl=3D=3F=3A_?= =?ISO-2022-JP?B?GyRCSUJFKkBeQ288ZzVBGyhC?=
+ =?ISO-2022-JP?B?GyRCRSpHUUoqPVBOTzRvGyhC?= (Pathologically
+ Eclectic Rubbish Lister)
+
+GOOD
+([["Perl=?: "], ["\x1B\x24BIBE*\x40^Co<g5AE*GQJ*=PNO4o\x1B(B", "ISO-2022-JP"], [" (Pathologically Eclectic Rubbish Lister)"]], Charset => "EUC-JP")
+=?ISO-2022-JP?B?UGVybD0/OiAbJEJJQkUqQF5DbzxnNUFFKkdRSio9UE5PNG8bKEI=?=
+ (Pathologically Eclectic Rubbish Lister)
+
+GOOD
+("Perl=?: \x1B\x24BIBE*\x40^Co<g5AE*GQJ*=PNO4o\x1B(B (Pathologically Eclectic Rubbish Lister)", Charset => "iso-2022-jp")
+=?ISO-2022-JP?B?UGVybD0/OiAbJEJJQkUqQF5DbzxnNUFFKkdRSio9UE5PNG8bKEI=?=
+ (Pathologically Eclectic Rubbish Lister)
+
+GOOD
+("Peeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeerl: \x1B\x24BIBE*\x40^Co<g5AE*GQJ*=PNO4o\x1B(B (Pathologically Eclectic Rubbish Lister)", Charset => "iso-2022-jp")
+=?ISO-2022-JP?B?UGVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVl?=
+ =?ISO-2022-JP?B?ZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZWVlZXJsOiA=?=
+ =?ISO-2022-JP?B?GyRCSUJFKkBeQ288ZzVBRSpHUUoqPVBOTzRvGyhC?= (Pathologically
+ Eclectic Rubbish Lister)
+
+GOOD
+("Perl: \x1B\x24BIBE*\x40^Co<g5AE*GQJ*=PNO4o\x1B(B (Pathologicalllllllllly-Ecleclecleclecleclectic-Rubbbbbbbbbbish-Listeeeeeer)", Charset => "iso-2022-jp")
+Perl: =?ISO-2022-JP?B?GyRCSUJFKkBeQ288ZzVBRSpHUUoqPVBOTzRvGyhCIChQYXRob2xv?=
+ =?ISO-2022-JP?B?Z2ljYWxsbGxsbGxsbGx5LUVjbGVjbGVjbGVjbGVjbGVjbGVjdGljLVJ1?=
+ =?ISO-2022-JP?B?YmJiYmJiYmJiYmlzaC1MaXN0ZWVlZWVlcik=?=
+
+GOOD
+("The next sentence is in GB.~{<:Ky2;S{#,NpJ)l6HK!#~}Bye.", MaxLineLen => 42, Charset => "HZ-GB-2312")
+The next sentence is in
+ =?HZ-GB-2312?B?R0Iufns8Okt5MjtTeyMsfn0=?=
+ =?HZ-GB-2312?B?fntOcEopbDZISyEjfn1CeWUu?=
+
+GOOD
+([["The next sentence is in GB. "], ["~{<:Ky2;S{#,NpJ)l6HK!#~}", "hzgb2312"], [" Bye."]], MaxLineLen => 42, Charset => "")
+The next sentence is in GB.
+ =?HZ-GB-2312?B?fns8Okt5MjtTeyMsTnBKKX59?=
+ =?HZ-GB-2312?B?fntsNkhLISN+fQ==?= Bye.
+
Modified: branches/upstream/libmime-encwords-perl/current/testin/encode-multibyte.txt
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/testin/encode-multibyte.txt?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/testin/encode-multibyte.txt (original)
+++ branches/upstream/libmime-encwords-perl/current/testin/encode-multibyte.txt Sun Apr 13 12:06:16 2008
@@ -23,3 +23,14 @@
Perl: =?ISO-2022-JP?B?GyRCSUJFKkBeQ288ZzVBRSpHUUoqPVBOTzRvGyhC?=
(Pathologically Eclectic Rubbish Lister)
+GOOD
+("Perl - Pathologically Eclectic Rubbish Lister \x1b\x24BIBE*\x40^Co<g5AE*GQJ*=PNO4o\x24r<B8=\x249\x24k8\x408l\x1b(B", Charset => "iso-2022-jp", Field => "")
+Perl - Pathologically Eclectic Rubbish Lister =?ISO-2022-JP?B?GyRCSUIbKEI=?=
+ =?ISO-2022-JP?B?GyRCRSpAXkNvPGc1QUUqR1FKKj1QTk80byRyPEI4PSQ5JGs4QDhsGyhC?=
+
+GOOD
+("Perl -- Pathologically Eclectic Rubbish Lister \x1b\x24BIBE*\x40^Co<g5AE*GQJ*=PNO4o\x24r<B8=\x249\x24k8\x408l\x1b(B", Charset => "iso-2022-jp", Field => "")
+Perl -- Pathologically Eclectic Rubbish Lister
+ =?ISO-2022-JP?B?GyRCSUJFKkBeQ288ZzVBRSpHUUoqPVBOTzRvJHI8Qjg9JDkkazhAGyhC?=
+ =?ISO-2022-JP?B?GyRCOGwbKEI=?=
+
Modified: branches/upstream/libmime-encwords-perl/current/testin/encode-singlebyte.txt
URL: http://svn.debian.org/wsvn/branches/upstream/libmime-encwords-perl/current/testin/encode-singlebyte.txt?rev=18560&op=diff
==============================================================================
--- branches/upstream/libmime-encwords-perl/current/testin/encode-singlebyte.txt (original)
+++ branches/upstream/libmime-encwords-perl/current/testin/encode-singlebyte.txt Sun Apr 13 12:06:16 2008
@@ -12,7 +12,7 @@
GOOD
([["Andr\xE9 "],["(<- one space) Pirard"],[" "],["<PIRARD\@vm1.ulg.ac.be>"]], Charset => "iso-8859-1")
-=?ISO-8859-1?Q?Andr=E9_(<-?= one space) Pirard <PIRARD at vm1.ulg.ac.be>
+=?ISO-8859-1?Q?Andr=E9_=28=3C-?= one space) Pirard <PIRARD at vm1.ulg.ac.be>
GOOD
([["Andr\xE9"],[" (<- one space) Pirard"],[" "],["<PIRARD\@vm1.ulg.ac.be>"]], Charset => "iso-8859-1")
@@ -20,7 +20,7 @@
GOOD
([["Andr\xE9 "],["(<- two spaces) Pirard"],[" "],["<PIRARD\@vm1.ulg.ac.be>"]], Charset => "iso-8859-1")
-=?ISO-8859-1?Q?Andr=E9__(<-?= two spaces) Pirard <PIRARD at vm1.ulg.ac.be>
+=?ISO-8859-1?Q?Andr=E9__=28=3C-?= two spaces) Pirard <PIRARD at vm1.ulg.ac.be>
GOOD
([["Andr\xE9 "],[" (<- two spaces) Pirard"],[" "],["<PIRARD\@vm1.ulg.ac.be>"]], Charset => "ISO-8859-1")
@@ -41,8 +41,8 @@
GOOD
("Th\xE8me tr\xE8s important\xA0: La r\xE9alisation du Syst\xE8me de R\xE9f\xE9rence C\xE9leste", Charset => "iso-8859-1")
-=?ISO-8859-1?Q?Th=E8me_tr=E8s_important=A0:?= La =?ISO-8859-1?Q?r=E9alisat?=
- =?ISO-8859-1?Q?ion?= du =?ISO-8859-1?Q?Syst=E8me?= de
+=?ISO-8859-1?Q?Th=E8me_tr=E8s_important=A0=3A?= La =?ISO-8859-1?Q?r=E9alis?=
+ =?ISO-8859-1?Q?ation?= du =?ISO-8859-1?Q?Syst=E8me?= de
=?ISO-8859-1?Q?R=E9f=E9rence_C=E9leste?=
GOOD
More information about the Pkg-perl-cvs-commits
mailing list