| 1 |
35 |
dpavlin |
#!/usr/bin/perl -w |
| 2 |
|
|
|
| 3 |
|
|
# Fix stupd html which is embedded in mailman mbox which you download |
| 4 |
|
|
# this is a filter. Use it like this: |
| 5 |
|
|
# |
| 6 |
|
|
# mailman2mbox.pl < mbox > mbox-new |
| 7 |
|
|
# |
| 8 |
|
|
# 2003-09-04 Dobrica Pavlinusic <dpavlin@rot13.org> |
| 9 |
|
|
# |
| 10 |
|
|
|
| 11 |
|
|
my $first = 1; |
| 12 |
|
|
|
| 13 |
|
|
while(<STDIN>) { |
| 14 |
|
|
if ($first) { |
| 15 |
|
|
chomp; |
| 16 |
|
|
$first = 0; |
| 17 |
|
|
next if ($_ eq ""); # skip first empty line |
| 18 |
|
|
$_ .= "\n"; |
| 19 |
|
|
} |
| 20 |
|
|
|
| 21 |
|
|
s,^</*PRE>,,g; |
| 22 |
|
|
s,<A HREF="[^"]*">(.+?)</A>,$1,g; |
| 23 |
|
|
|
| 24 |
|
|
# fix quoting |
| 25 |
|
|
s,^><i>,>,; |
| 26 |
|
|
s,^</I>(>[^<]*)<i>,$1,; |
| 27 |
|
|
s,^</I>,,; |
| 28 |
|
|
|
| 29 |
|
|
s/</</g; |
| 30 |
|
|
s/>/>/g; |
| 31 |
|
|
s/"/"/g; |
| 32 |
|
|
s/&/&/g; |
| 33 |
|
|
s/^(From.+?) at (.+)$/$1\@$2/g; |
| 34 |
|
|
print; |
| 35 |
|
|
} |