summaryrefslogtreecommitdiff
path: root/perl/FromCPAN/Mail/Address.pm
blob: 683d490b2b0b87f5d1e8459bea67c9ea90f477f1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
# Copyrights 1995-2018 by [Mark Overmeer].
#  For other contributors see ChangeLog.
# See the manual pages for details on the licensing terms.
# Pod stripped from pm file by OODoc 2.02.
# This code is part of the bundle MailTools.  Meta-POD processed with
# OODoc into POD and HTML manual-pages.  See README.md for Copyright.
# Licensed under the same terms as Perl itself.

package Mail::Address;
use vars '$VERSION';
$VERSION = '2.20';

use strict;

use Carp;

# use locale;   removed in version 1.78, because it causes taint problems

sub Version { our $VERSION }



# given a comment, attempt to extract a person's name
sub _extract_name
{   # This function can be called as method as well
    my $self = @_ && ref $_[0] ? shift : undef;

    local $_ = shift
        or return '';

    # Using encodings, too hard. See Mail::Message::Field::Full.
    return '' if m/\=\?.*?\?\=/;

    # trim whitespace
    s/^\s+//;
    s/\s+$//;
    s/\s+/ /;

    # Disregard numeric names (e.g. 123456.1234@compuserve.com)
    return "" if /^[\d ]+$/;

    s/^\((.*)\)$/$1/; # remove outermost parenthesis
    s/^"(.*)"$/$1/;   # remove outer quotation marks
    s/\(.*?\)//g;     # remove minimal embedded comments
    s/\\//g;          # remove all escapes
    s/^"(.*)"$/$1/;   # remove internal quotation marks
    s/^([^\s]+) ?, ?(.*)$/$2 $1/; # reverse "Last, First M." if applicable
    s/,.*//;

    # Change casing only when the name contains only upper or only
    # lower cased characters.
    unless( m/[A-Z]/ && m/[a-z]/ )
    {   # Set the case of the name to first char upper rest lower
        s/\b(\w+)/\L\u$1/igo;  # Upcase first letter on name
        s/\bMc(\w)/Mc\u$1/igo; # Scottish names such as 'McLeod'
        s/\bo'(\w)/O'\u$1/igo; # Irish names such as 'O'Malley, O'Reilly'
        s/\b(x*(ix)?v*(iv)?i*)\b/\U$1/igo; # Roman numerals, eg 'Level III Support'
    }

    # some cleanup
    s/\[[^\]]*\]//g;
    s/(^[\s'"]+|[\s'"]+$)//g;
    s/\s{2,}/ /g;

    $_;
}

sub _tokenise
{   local $_ = join ',', @_;
    my (@words,$snippet,$field);

    s/\A\s+//;
    s/[\r\n]+/ /g;

    while ($_ ne '')
    {   $field = '';
        if(s/^\s*\(/(/ )    # (...)
        {   my $depth = 0;

     PAREN: while(s/^(\(([^\(\)\\]|\\.)*)//)
            {   $field .= $1;
                $depth++;
                while(s/^(([^\(\)\\]|\\.)*\)\s*)//)
                {   $field .= $1;
                    last PAREN unless --$depth;
	            $field .= $1 if s/^(([^\(\)\\]|\\.)+)//;
                }
            }

            carp "Unmatched () '$field' '$_'"
                if $depth;

            $field =~ s/\s+\Z//;
            push @words, $field;

            next;
        }

        if( s/^("(?:[^"\\]+|\\.)*")\s*//       # "..."
         || s/^(\[(?:[^\]\\]+|\\.)*\])\s*//    # [...]
         || s/^([^\s()<>\@,;:\\".[\]]+)\s*//
         || s/^([()<>\@,;:\\".[\]])\s*//
          )
        {   push @words, $1;
            next;
        }

        croak "Unrecognised line: $_";
    }

    push @words, ",";
    \@words;
}

sub _find_next
{   my ($idx, $tokens, $len) = @_;

    while($idx < $len)
    {   my $c = $tokens->[$idx];
        return $c if $c eq ',' || $c eq ';' || $c eq '<';
        $idx++;
    }

    "";
}

sub _complete
{   my ($class, $phrase, $address, $comment) = @_;

    @$phrase || @$comment || @$address
       or return undef;

    my $o = $class->new(join(" ",@$phrase), join("",@$address), join(" ",@$comment));
    @$phrase = @$address = @$comment = ();
    $o;
}

#------------

sub new(@)
{   my $class = shift;
    bless [@_], $class;
}


sub parse(@)
{   my $class = shift;
    my @line  = grep {defined} @_;
    my $line  = join '', @line;

    my (@phrase, @comment, @address, @objs);
    my ($depth, $idx) = (0, 0);

    my $tokens  = _tokenise @line;
    my $len     = @$tokens;
    my $next    = _find_next $idx, $tokens, $len;

    local $_;
    for(my $idx = 0; $idx < $len; $idx++)
    {   $_ = $tokens->[$idx];

        if(substr($_,0,1) eq '(') { push @comment, $_ }
        elsif($_ eq '<')    { $depth++ }
        elsif($_ eq '>')    { $depth-- if $depth }
        elsif($_ eq ',' || $_ eq ';')
        {   warn "Unmatched '<>' in $line" if $depth;
            my $o = $class->_complete(\@phrase, \@address, \@comment);
            push @objs, $o if defined $o;
            $depth = 0;
            $next = _find_next $idx+1, $tokens, $len;
        }
        elsif($depth)       { push @address, $_ }
        elsif($next eq '<') { push @phrase,  $_ }
        elsif( /^[.\@:;]$/ || !@address || $address[-1] =~ /^[.\@:;]$/ )
        {   push @address, $_ }
        else
        {   warn "Unmatched '<>' in $line" if $depth;
            my $o = $class->_complete(\@phrase, \@address, \@comment);
            push @objs, $o if defined $o;
            $depth = 0;
            push @address, $_;
        }
    }
    @objs;
}

#------------

sub phrase  { shift->set_or_get(0, @_) }
sub address { shift->set_or_get(1, @_) }
sub comment { shift->set_or_get(2, @_) }

sub set_or_get($)
{   my ($self, $i) = (shift, shift);
    @_ or return $self->[$i];

    my $val = $self->[$i];
    $self->[$i] = shift if @_;
    $val;
}


my $atext = '[\-\w !#$%&\'*+/=?^`{|}~]';
sub format
{   my @addrs;

    foreach (@_)
    {   my ($phrase, $email, $comment) = @$_;
        my @addr;

        if(defined $phrase && length $phrase)
        {   push @addr
              , $phrase =~ /^(?:\s*$atext\s*)+$/o ? $phrase
              : $phrase =~ /(?<!\\)"/             ? $phrase
              :                                    qq("$phrase");

            push @addr, "<$email>"
                if defined $email && length $email;
        }
        elsif(defined $email && length $email)
        {   push @addr, $email;
        }

        if(defined $comment && $comment =~ /\S/)
        {   $comment =~ s/^\s*\(?/(/;
            $comment =~ s/\)?\s*$/)/;
        }

        push @addr, $comment
            if defined $comment && length $comment;

        push @addrs, join(" ", @addr)
            if @addr;
    }

    join ", ", @addrs;
}

#------------

sub name
{   my $self   = shift;
    my $phrase = $self->phrase;
    my $addr   = $self->address;

    $phrase    = $self->comment
        unless defined $phrase && length $phrase;

    my $name   = $self->_extract_name($phrase);

    # first.last@domain address
    if($name eq '' && $addr =~ /([^\%\.\@_]+([\._][^\%\.\@_]+)+)[\@\%]/)
    {   ($name  = $1) =~ s/[\._]+/ /g;
	$name   = _extract_name $name;
    }

    if($name eq '' && $addr =~ m#/g=#i)    # X400 style address
    {   my ($f) = $addr =~ m#g=([^/]*)#i;
	my ($l) = $addr =~ m#s=([^/]*)#i;
	$name   = _extract_name "$f $l";
    }

    length $name ? $name : undef;
}


sub host
{   my $addr = shift->address || '';
    my $i    = rindex $addr, '@';
    $i >= 0 ? substr($addr, $i+1) : undef;
}


sub user
{   my $addr = shift->address || '';
    my $i    = rindex $addr, '@';
    $i >= 0 ? substr($addr,0,$i) : $addr;
}

1;