mail_to_db.pl

开启mysql的远程连接的方法 mysql-noinstall-5.1.6-alpha-win32.zip

      {
	$type = "in_reply_to";
	s/^\s*(<.*>)\s*/$1/;
	$values{$type} = $1;
      }
      elsif (/^Date: (.*)/i)
      {
	date_parser($1, \%values, $file_name);
	$type = "rubbish";
      }
      # Catch those fields that we don't or can't handle (yet)
      elsif (/^[\w\W-]+:/)
      {
	$type = "rubbish";
      }
      elsif ($_ eq "")
      { 
	$type = "message";
	$values{$type} = "";
      }
      else
      {
	s/^\s*/ /;
	if ($type eq 'message_id' || $type eq 'in_reply_to')
	{
	  s/^\s*(<.*>)\s*/$1/;
	}
	$values{$type} .= $_;
      }
    }
    elsif ($check != 0 && $_ ne "") # in case of forwarded messages
    {
      $values{$type} .= "\n" . $_;
      $check--;
    }
    elsif (/^From .* \d\d:\d\d:\d\d\s\d\d\d\d/ ||
           /^From .* \d\d\d\d\s\d\d:\d\d:\d\d/)
    {
      $values{'hash'} = checksum("$values{'message'}");
      update_table($dbh, $file_name, \%values);
      %values = ();
      $type = "";
      $check = 0;
    }
    elsif (/-* forwarded message .*-*/i) # in case of forwarded messages
    {
      $values{$type} .= "\n" . $_;
      $check++;
      $mail_forwarded++;
    }
    else
    {
      $values{$type} .= "\n" . $_;
    }
  }
  if (defined($values{'message'}))
  {
    $values{'hash'} = checksum("$values{'message'}");
    update_table($dbh, $file_name, \%values);
  }
}

####
#### get date and timezone
####

sub date_parser
{
  my ($date_raw, $values, $file_name, $tmp) = @_;

  # If you ever need to change this test, be especially careful with
  # the timezone; it may be just a number (-0600), or just a name (EET), or
  # both (-0600 (EET), or -0600 (EET GMT)), or without parenthesis: GMT.
  # You probably should use a 'greedy' regexp in the end
  $date_raw =~ /^\D*(\d{1,2})\s+(\w+)\s+(\d{2,4})\s+(\d+:\d+)(:\d+)?\s*(\S+.*)?/;

  if (!defined($1) || !defined($2) || !defined($3) || !defined($4) ||
      !defined($months{$2}))
  {
    if ($opt_debug || $opt_stop_on_error)
    {
      print "FAILED: date_parser: 1: $1 2: $2 3: $3 4: $4 5: $5\n";
      print "months{2}: $months{$2}\n";
      print "date_raw: $date_raw\n";
      print "Inbox filename: $file_name\n";
    }
    exit(1) if ($opt_stop_on_error);
    $values->{'date'} = "";
    $values->{'time_zone'} = "";
    return;
  }
  $tmp = $3 . "-" . $months{$2} . "-" . "$1 $4";
  $tmp.= defined($5) ? $5 : ":00";
  $values->{'date'} = $tmp;
  print "INSERTING DATE: $tmp\n" if ($opt_debug);
  $values->{'time_zone'} = $6;
}

####
#### Insert to table
#### 

sub update_table
{
  my($dbh, $file_name, $values) = @_;
  my($q, $tail, $message);

  if (!defined($values->{'subject'}) || !defined($values->{'to'}))
  {
    $mail_no_subject_f++;
    return;			# Ignore these
  }
  $message = $values->{'message'};
  $message =~ s/^\s*//; # removes whitespaces from the beginning 

 restart:
  $message =~ s/[\s\n>]*$//; # removes whitespaces and '>' from the end
  $values->{'message'} = $message;
  foreach $tail (@remove_tail)
  {
    $message =~ s/$tail//;
  }
  if ($message ne $values->{'message'})
  {
    $message =~ s/\s*$//; # removes whitespaces from the end
    $mail_fixed++;
    goto restart;	  # Some mails may have duplicated messages
  }

  $q = "INSERT INTO my_mail (";
  $q.= "mail_id,";
  $q.= "message_id,";
  $q.= "in_reply_to,";
  $q.= "date,";
  $q.= "time_zone,";
  $q.= "mail_from,";
  $q.= "reply,";
  $q.= "mail_to,";
  $q.= "cc,";
  $q.= "sbj,";
  $q.= "txt,";
  $q.= "file,";
  $q.= "hash";
  $q.= ") VALUES (";
  $q.= "NULL,";
  $q.= (defined($values->{'message_id'}) ?
	$dbh->quote($values->{'message_id'}) : "NULL");
  $q.= ",";
  $q.= (defined($values->{'in_reply_to'}) ?
	$dbh->quote($values->{'in_reply_to'}) : "NULL");
  $q.= ",";
  $q.= "'" . $values->{'date'} . "',";
  $q.= (defined($values->{'time_zone'}) ?
	$dbh->quote($values->{'time_zone'}) : "NULL");
  $q.= ",";
  $q.= defined($values->{'from'}) ? $dbh->quote($values->{'from'}) : "NULL";
  $q.= ",";
  $q.= defined($values->{'reply'}) ? $dbh->quote($values->{'reply'}) : "NULL";
  $q.= ",";
  $q.= defined($values->{'to'}) ? $dbh->quote($values->{'to'}) : "NULL";
  $q.= ",";
  $q.= defined($values->{'cc'}) ? $dbh->quote($values->{'cc'}) : "NULL"; 
  $q.= ","; 
  $q.= $dbh->quote($values->{'subject'});
  $q.= ",";
  $q.= $dbh->quote($message);
  $q.= ",";
  $q.= $dbh->quote($file_name);
  $q.= ",";
  $q.= "'" . $values->{'hash'} . "'";
  $q.= ")";

  # Don't insert mails bigger than $opt_max_mail_size
  if (length($message) > $opt_max_mail_size)
  {
    $mail_too_big++;
  }
  # Don't insert mails without 'From' field
  elsif (!defined($values->{'from'}) || $values->{'from'} eq "")
  {
    $mail_no_from_f++;
  }
  elsif ($opt_test)
  {
    print "$q\n";
    $mail_inserted++;
  }
  # Don't insert mails without the 'message'
  elsif ($message eq "") 
  {
    $mail_no_txt_f++;
  }
  elsif ($dbh->do($q))
  {
    $mail_inserted++;
  }
  # This should never happen. This means that the above q failed,
  # but it wasn't because of a duplicate mail entry
  elsif (!($DBI::errstr =~ /Duplicate entry /))
  {
    die "FATAL: Got error :$DBI::errstr\nAttempted query was: $q\n";
  }
  else
  {
    $mail_duplicates++;
    print "Duplicate mail: query: $q\n" if ($opt_debug);
  }
  $q = "";
}

####
#### In case you have two identical messages we wanted to identify them
#### and remove additionals;  We do this by calculating a hash number of the
#### message and ignoring messages with the same from, date and hash.
#### This function calculates a simple 32 bit hash value for the message.
####

sub checksum
{
  my ($txt)= @_;
  my ($crc, $i, $count);
  $count = length($txt);
  for ($crc = $i = 0; $i < $count ; $i++)
  {
    $crc = (($crc << 1) + (ord (substr ($txt, $i, 1)))) +
      (($crc & (1 << 30)) ? 1 : 0);
    $crc &= ((1 << 31) -1);
  }
  return $crc;
}

####
#### my_which is used, because we can't assume that every system has the
#### which -command. my_which can take only one argument at a time.
#### Return values: requested system command with the first found path,
#### or undefined, if not found.
####

sub my_which
{
  my ($command) = @_;
  my (@paths, $path);

  return $command if (-f $command && -x $command);
  @paths = split(':', $ENV{'PATH'});
  foreach $path (@paths)
  {
    $path = "." if ($path eq "");
    $path .= "/$command";
    return $path if (-f $path && -x $path);
  }
  return undef();
}

####
#### usage and version
####

sub usage
{  
  my ($VER)= @_;
  
  if ($opt_version)
  {
    print "$progname version $VER\n";
  } 
  else
  {
    print <<EOF;
$progname version $VER

Description: Insert mails from inbox file(s) into a table. This program 
can read group [mail_to_db] from the my.cnf file. You may want to have db
and table set there at least.

Usage: $progname [options] file1 [file2 file3 ...]
or:    $progname [options] --create [file1 file2...]
or:    cat inbox | $progname [options] --stdin

The last example can be used to read mails from standard input and can
useful when inserting mails to database via a program 'on-the-fly'.
The filename will be 'READ-FROM-STDIN' in this case.

Options:
--help             Show this help and exit.
--version          Show the version number and exit.
--debug            Print some extra information during the run.
--host=...         Hostname to be used.
--port=#           TCP/IP port to be used with connection.
--socket=...       MySQL UNIX socket to be used with connection.
--db=...           Database to be used.
--user=...         Username for connecting.
--password=...     Password for the user.
--stdin            Read mails from stdin.
--max_mail_size=#  Maximum size of a mail in bytes.
                   Beware of the downside letting this variable be too big;
                   you may easily end up inserting a lot of attached 
                   binary files (like MS Word documents etc), which take
                   space, make the database slower and are not really
                   searchable anyway. (Default $opt_max_mail_size)
--create           Create the mails table. This can be done with the first run.
--test		   Dry run. Print the queries and the result as it would be.
--no_path          When inserting the file name, leave out any paths of
                   the name.
--stop_on_error    Stop the run, if an unexpected, but not fatal error occurs
                   during the run. Without this option some fields may get
                   unwanted values. --debug will also report about these.
EOF
  }
  exit(0);
}