Debian Codegraph @

anonymize_mailbox

raw
1 #!/usr/bin/perl -w
2
3 $VERSION = '1.00';
4
5 use strict;
6 use FileHandle;
7
8 #-------------------------------------------------------------------------------
9
10 my $LINE = 0;
11 my $FILE_HANDLE = undef;
12 my $START = 0;
13 my $END = 0;
14 my $READ_BUFFER = '';
15
16 sub reset_file
17 {
18 my $file_handle = shift;
19
20 $FILE_HANDLE = $file_handle;
21 $LINE = 1;
22 $START = 0;
23 $END = 0;
24 $READ_BUFFER = '';
25 }
26
27 #-------------------------------------------------------------------------------
28
29 # Need this for a lookahead.
30 my $READ_CHUNK_SIZE = 0;
31
32 sub read_email
33 {
34 # Undefined read buffer means we hit eof on the last read.
35 return 0 unless defined $READ_BUFFER;
36
37 my $line = $LINE;
38
39 $START = $END;
40
41 # Look for the start of the next email
42 LOOK_FOR_NEXT_HEADER:
43 while($READ_BUFFER =~ m/^(From\s.*\d:\d+:\d.* \d{4})/mg)
44 {
45 $END = pos($READ_BUFFER) - length($1);
46
47 # Don't stop on email header for the first email in the buffer
48 next if $END == 0;
49
50 # Keep looking if the header we found is part of a "Begin Included
51 # Message".
52 my $end_of_string = substr($READ_BUFFER, $END-200, 200);
53 if ($end_of_string =~
54 /\n-----( Begin Included Message |Original Message)-----\n[^\n]*\n*$/i)
55 {
56 next;
57 }
58
59 # Found the next email!
60 my $email = substr($READ_BUFFER, $START, $END-$START);
61 $LINE += ($email =~ tr/\n//);
62
63 return (1, $email, $line);
64 }
65
66 # Didn't find next email in current buffer. Most likely we need to read some
67 # more of the mailbox. Shift the current email to the front of the buffer
68 # unless we've already done so.
69 $READ_BUFFER = substr($READ_BUFFER,$START) unless $START == 0;
70 $START = 0;
71
72 # Start looking at the end of the buffer, but back up some in case the edge
73 # of the newly read buffer contains the start of a new header. I believe the
74 # RFC says header lines can be at most 90 characters long.
75 my $search_position = length($READ_BUFFER) - 90;
76 $search_position = 0 if $search_position < 0;
77
78 # Can't use sysread because it doesn't work with ungetc
79 if ($READ_CHUNK_SIZE == 0)
80 {
81 local $/ = undef;
82
83 if (eof $FILE_HANDLE)
84 {
85 my $email = $READ_BUFFER;
86 undef $READ_BUFFER;
87 return (1, $email, $line);
88 }
89 else
90 {
91 $READ_BUFFER = <$FILE_HANDLE>;
92 pos($READ_BUFFER) = $search_position;
93 goto LOOK_FOR_NEXT_HEADER;
94 }
95 }
96 else
97 {
98 if (read($FILE_HANDLE, $READ_BUFFER, $READ_CHUNK_SIZE, length($READ_BUFFER)))
99 {
100 pos($READ_BUFFER) = $search_position;
101 goto LOOK_FOR_NEXT_HEADER;
102 }
103 else
104 {
105 my $email = $READ_BUFFER;
106 undef $READ_BUFFER;
107 return (1, $email, $line);
108 }
109 }
110 }
111
112 sub Read_Chunk_Of_Body
113 {
114 my $email = shift;
115
116 local $/ = "\nFrom ";
117 my $chunk = <$FILE_HANDLE>;
118 local $/ = "From ";
119 chomp $chunk;
120
121 $LINE += ($chunk =~ tr/\n//);
122
123 $$email .= $chunk;
124 }
125
126 die unless @ARGV;
127
128 $FILE_HANDLE = new FileHandle($ARGV[0]);
129
130 while(1)
131 {
132 my ($status,$email,$line) = read_email();
133 exit unless $status;
134
135 my ($header,$body) = $email =~ /(.*?\n\n)(.*)/s;
136
137
138 $body =~ s/\w/X/g;
139
140
141 {
142 my ($header_to) = $header =~ /^To: (.*)$/m;
143 my ($header_subject) = $header =~ /^Subject: (.*)$/m;
144
145 if (defined $header_to)
146 {
147 my $modified_header_to = $header_to;
148 $modified_header_to =~ s/\w/X/g;
149
150 $header =~ s/To: \Q$header_to\E/To: $modified_header_to/g;
151 }
152
153 if (defined $header_subject)
154 {
155 my $modified_header_subject = $header_subject;
156 $modified_header_subject =~ s/\w/X/g;
157
158 $header =~ s/Subject: \Q$header_subject\E/Subject: $modified_header_subject/g;
159 }
160 }
161
162
163 print $header,$body;
164 }