Initial revision

This commit is contained in:
Paul Rodger 2002-03-26 03:53:09 +00:00
parent e7b0a0331f
commit 902a81b4bc
5 changed files with 1592 additions and 0 deletions

341
COPYING Normal file
View File

@ -0,0 +1,341 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.
59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Library General Public License instead.) You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
The precise terms and conditions for copying, distribution and
modification follow.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
1. You may copy and distribute verbatim copies of the Program's
source code as you receive it, in any medium, provided that you
conspicuously and appropriately publish on each copy an appropriate
copyright notice and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
2. You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
b) You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
c) If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
a) Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
b) Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
c) Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
4. You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
5. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
7. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
8. If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
9. The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
10. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
NO WARRANTY
11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) year name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, the commands you use may
be called something other than `show w' and `show c'; they could even be
mouse-clicks or menu items--whatever suits your program.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the program
`Gnomovision' (which makes passes at compilers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
This General Public License does not permit incorporating your program into
proprietary programs. If your program is a subroutine library, you may
consider it more useful to permit linking proprietary applications with the
library. If this is what you want to do, use the GNU Library General
Public License instead of this License.

21
README Normal file
View File

@ -0,0 +1,21 @@
archivemail - archive and compress old mail in your mailbox
'archivemail' is a tool written in Python for organising and storing old
email choking any of your mailboxes. It can move messages older than a
certain number of days to a separate 'archive' mailbox which can be
compressed with bzip2, gzip or compress.
For example, have you been subscribing to the 'linux-kernel' mailing list
for the last 6 years and ended up with an 160-meg mailbox that 'mutt' is
taking a long time to load? 'archivemail' can move all messages that are
older than 6 months to a separate compressed mailbox, and leave you with
just the most recent messages.
'archivemail' can save a lot of disk space and will significantly reduce
overhead on your mail reader. The number of days before mail is considered
'old' is up to you, but the default is 180 days.
'archivemail' currently works on mbox-format mailboxes, and requires python
v2.0 or greater. It also supports deleting old mail instead of archiving
it. It currently only works on Unix platforms.

26
TODO Normal file
View File

@ -0,0 +1,26 @@
add Maildir support
add MH support
start using private variables?
finish man page
add option to archive depending on mailbox size threshold
+ is this a good idea?
perserve atime of mailbox properly
lock any original .gz files (?)
check for symlink attacks for tempfiles (although we don't use /var/tmp)
test for write permission before doing anything
test for missing compression programs
+ is this a waste of time?
add option - do not compress (?)
Add Makefile with "make install" target ?

635
archivemail.1 Normal file
View File

@ -0,0 +1,635 @@
.\" archivemail man page
.if !\n(.g \{\
. if !\w|\*(lq| \{\
. ds lq ``
. if \w'\(lq' .ds lq "\(lq
. \}
. if !\w|\*(rq| \{\
. ds rq ''
. if \w'\(rq' .ds rq "\(rq
. \}
.\}
.de Id
.ds Dt \\$4
..
.TH archivemail 1 \*(Dt "GNU Project"
.SH NAME
archivemail \- archive and compress old email
.SH SYNOPSIS
.B archivemail
.RI [ options ]
.I FILE
.RI [ FILE .\|.\|.]
.br
.SH DESCRIPTION
.PP
.B archivemail
archives and compresses and
.IR FILE s
.IR PATTERN .
By default,
.B grep
prints the matching lines.
.PP
In addition, two variant programs
.B egrep
and
.B fgrep
are available.
.B Egrep
is the same as
.BR "grep\ \-E" .
.B Fgrep
is the same as
.BR "grep\ \-F" .
.SH OPTIONS
.TP
.BI \-A " NUM" "\fR,\fP \-\^\-after-context=" NUM
Print
.I NUM
lines of trailing context after matching lines.
.TP
.BR \-a ", " \-\^\-text
Process a binary file as if it were text; this is equivalent to the
.B \-\^\-binary-files=text
option.
.TP
.BI \-B " NUM" "\fR,\fP \-\^\-before-context=" NUM
Print
.I NUM
lines of leading context before matching lines.
.TP
\fB\-C\fP [\fINUM\fP], \fB\-\fP\fINUM\fP, \fB\-\^\-context\fP[\fB=\fP\fINUM\fP]
Print
.I NUM
lines (default 2) of output context.
.TP
.BR \-b ", " \-\^\-byte-offset
Print the byte offset within the input file before
each line of output.
.TP
.BI \-\^\-binary-files= TYPE
If the first few bytes of a file indicate that the file contains binary
data, assume that the file is of type
.IR TYPE .
By default,
.I TYPE
is
.BR binary ,
and
.B grep
normally outputs either
a one-line message saying that a binary file matches, or no message if
there is no match.
If
.I TYPE
is
.BR without-match ,
.B grep
assumes that a binary file does not match; this is equivalent to the
.B \-I
option.
If
.I TYPE
is
.BR text ,
.B grep
processes a binary file as if it were text; this is equivalent to the
.B \-a
option.
.I Warning:
.B "grep \-\^\-binary-files=text"
might output binary garbage,
which can have nasty side effects if the output is a terminal and if the
terminal driver interprets some of it as commands.
.TP
.BR \-c ", " \-\^\-count
Suppress normal output; instead print a count of
matching lines for each input file.
With the
.BR \-v ", " \-\^\-invert-match
option (see below), count non-matching lines.
.TP
.BI \-d " ACTION" "\fR,\fP \-\^\-directories=" ACTION
If an input file is a directory, use
.I ACTION
to process it. By default,
.I ACTION
is
.BR read ,
which means that directories are read just as if they were ordinary files.
If
.I ACTION
is
.BR skip ,
directories are silently skipped.
If
.I ACTION
is
.BR recurse ,
.B grep
reads all files under each directory, recursively;
this is equivalent to the
.B \-r
option.
.TP
.BR \-E ", " \-\^\-extended-regexp
Interpret
.I PATTERN
as an extended regular expression (see below).
.TP
.BI \-e " PATTERN" "\fR,\fP \-\^\-regexp=" PATTERN
Use
.I PATTERN
as the pattern; useful to protect patterns beginning with
.BR \- .
.TP
.BR \-F ", " \-\^\-fixed-strings
Interpret
.I PATTERN
as a list of fixed strings, separated by newlines,
any of which is to be matched.
.TP
.BI \-f " FILE" "\fR,\fP \-\^\-file=" FILE
Obtain patterns from
.IR FILE ,
one per line.
The empty file contains zero patterns, and therefore matches nothing.
.TP
.BR \-G ", " \-\^\-basic-regexp
Interpret
.I PATTERN
as a basic regular expression (see below). This is the default.
.TP
.BR \-H ", " \-\^\-with-filename
Print the filename for each match.
.TP
.BR \-h ", " \-\^\-no-filename
Suppress the prefixing of filenames on output
when multiple files are searched.
.TP
.B \-\^\-help
Output a brief help message.
.TP
.BR \-I
Process a binary file as if it did not contain matching data; this is
equivalent to the
.B \-\^\-binary-files=without-match
option.
.TP
.BR \-i ", " \-\^\-ignore-case
Ignore case distinctions in both the
.I PATTERN
and the input files.
.TP
.BR \-L ", " \-\^\-files-without-match
Suppress normal output; instead print the name
of each input file from which no output would
normally have been printed. The scanning will stop
on the first match.
.TP
.BR \-l ", " \-\^\-files-with-matches
Suppress normal output; instead print
the name of each input file from which output
would normally have been printed. The scanning will
stop on the first match.
.TP
.B \-\^\-mmap
If possible, use the
.BR mmap (2)
system call to read input, instead of
the default
.BR read (2)
system call. In some situations,
.B \-\^\-mmap
yields better performance. However,
.B \-\^\-mmap
can cause undefined behavior (including core dumps)
if an input file shrinks while
.B grep
is operating, or if an I/O error occurs.
.TP
.BR \-n ", " \-\^\-line-number
Prefix each line of output with the line number
within its input file.
.TP
.BR \-q ", " \-\^\-quiet ", " \-\^\-silent
Quiet; suppress normal output. The scanning will stop
on the first match.
Also see the
.B \-s
or
.B \-\^\-no-messages
option below.
.TP
.BR \-r ", " \-\^\-recursive
Read all files under each directory, recursively;
this is equivalent to the
.B "\-d recurse"
option.
.TP
.BR \-s ", " \-\^\-no-messages
Suppress error messages about nonexistent or unreadable files.
Portability note: unlike \s-1GNU\s0
.BR grep ,
traditional
.B grep
did not conform to \s-1POSIX.2\s0, because traditional
.B grep
lacked a
.B \-q
option and its
.B \-s
option behaved like \s-1GNU\s0
.BR grep 's
.B \-q
option.
Shell scripts intended to be portable to traditional
.B grep
should avoid both
.B \-q
and
.B \-s
and should redirect output to /dev/null instead.
.TP
.BR \-U ", " \-\^\-binary
Treat the file(s) as binary. By default, under MS-DOS and MS-Windows,
.BR grep
guesses the file type by looking at the contents of the first 32KB
read from the file. If
.BR grep
decides the file is a text file, it strips the CR characters from the
original file contents (to make regular expressions with
.B ^
and
.B $
work correctly). Specifying
.B \-U
overrules this guesswork, causing all files to be read and passed to the
matching mechanism verbatim; if the file is a text file with CR/LF
pairs at the end of each line, this will cause some regular
expressions to fail.
This option has no effect on platforms other than MS-DOS and
MS-Windows.
.TP
.BR \-u ", " \-\^\-unix-byte-offsets
Report Unix-style byte offsets. This switch causes
.B grep
to report byte offsets as if the file were Unix-style text file, i.e. with
CR characters stripped off. This will produce results identical to running
.B grep
on a Unix machine. This option has no effect unless
.B \-b
option is also used;
it has no effect on platforms other than MS-DOS and MS-Windows.
.TP
.BR \-V ", " \-\^\-version
Print the version number of
.B grep
to standard error. This version number should
be included in all bug reports (see below).
.TP
.BR \-v ", " \-\^\-invert-match
Invert the sense of matching, to select non-matching lines.
.TP
.BR \-w ", " \-\^\-word-regexp
Select only those lines containing matches that form whole words.
The test is that the matching substring must either be at the
beginning of the line, or preceded by a non-word constituent
character. Similarly, it must be either at the end of the line
or followed by a non-word constituent character. Word-constituent
characters are letters, digits, and the underscore.
.TP
.BR \-x ", " \-\^\-line-regexp
Select only those matches that exactly match the whole line.
.TP
.B \-y
Obsolete synonym for
.BR \-i .
.TP
.BR \-Z ", " \-\^\-null
Output a zero byte (the \s-1ASCII\s0
.B NUL
character) instead of the character that normally follows a file name.
For example,
.B "grep \-lZ"
outputs a zero byte after each file name instead of the usual newline.
This option makes the output unambiguous, even in the presence of file
names containing unusual characters like newlines. This option can be
used with commands like
.BR "find \-print0" ,
.BR "perl \-0" ,
.BR "sort \-z" ,
and
.B "xargs \-0"
to process arbitrary file names,
even those that contain newline characters.
.SH "REGULAR EXPRESSIONS"
.PP
A regular expression is a pattern that describes a set of strings.
Regular expressions are constructed analogously to arithmetic
expressions, by using various operators to combine smaller expressions.
.PP
.B Grep
understands two different versions of regular expression syntax:
\*(lqbasic\*(rq and \*(lqextended.\*(rq In
.RB "\s-1GNU\s0\ " grep ,
there is no difference in available functionality using either syntax.
In other implementations, basic regular expressions are less powerful.
The following description applies to extended regular expressions;
differences for basic regular expressions are summarized afterwards.
.PP
The fundamental building blocks are the regular expressions that match
a single character. Most characters, including all letters and digits,
are regular expressions that match themselves. Any metacharacter with
special meaning may be quoted by preceding it with a backslash.
.PP
A list of characters enclosed by
.B [
and
.B ]
matches any single
character in that list; if the first character of the list
is the caret
.B ^
then it matches any character
.I not
in the list.
For example, the regular expression
.B [0123456789]
matches any single digit. A range of characters
may be specified by giving the first and last characters, separated
by a hyphen.
Finally, certain named classes of characters are predefined.
Their names are self explanatory, and they are
.BR [:alnum:] ,
.BR [:alpha:] ,
.BR [:cntrl:] ,
.BR [:digit:] ,
.BR [:graph:] ,
.BR [:lower:] ,
.BR [:print:] ,
.BR [:punct:] ,
.BR [:space:] ,
.BR [:upper:] ,
and
.BR [:xdigit:].
For example,
.B [[:alnum:]]
means
.BR [0-9A-Za-z] ,
except the latter form depends upon the \s-1POSIX\s0 locale and the
\s-1ASCII\s0 character encoding, whereas the former is independent
of locale and character set.
(Note that the brackets in these class names are part of the symbolic
names, and must be included in addition to the brackets delimiting
the bracket list.) Most metacharacters lose their special meaning
inside lists. To include a literal
.B ]
place it first in the list. Similarly, to include a literal
.B ^
place it anywhere but first. Finally, to include a literal
.B \-
place it last.
.PP
The period
.B .
matches any single character.
The symbol
.B \ew
is a synonym for
.B [[:alnum:]]
and
.B \eW
is a synonym for
.BR [^[:alnum]] .
.PP
The caret
.B ^
and the dollar sign
.B $
are metacharacters that respectively match the empty string at the
beginning and end of a line.
The symbols
.B \e<
and
.B \e>
respectively match the empty string at the beginning and end of a word.
The symbol
.B \eb
matches the empty string at the edge of a word,
and
.B \eB
matches the empty string provided it's
.I not
at the edge of a word.
.PP
A regular expression may be followed by one of several repetition operators:
.PD 0
.TP
.B ?
The preceding item is optional and matched at most once.
.TP
.B *
The preceding item will be matched zero or more times.
.TP
.B +
The preceding item will be matched one or more times.
.TP
.BI { n }
The preceding item is matched exactly
.I n
times.
.TP
.BI { n ,}
The preceding item is matched
.I n
or more times.
.TP
.BI { n , m }
The preceding item is matched at least
.I n
times, but not more than
.I m
times.
.PD
.PP
Two regular expressions may be concatenated; the resulting
regular expression matches any string formed by concatenating
two substrings that respectively match the concatenated
subexpressions.
.PP
Two regular expressions may be joined by the infix operator
.BR | ;
the resulting regular expression matches any string matching
either subexpression.
.PP
Repetition takes precedence over concatenation, which in turn
takes precedence over alternation. A whole subexpression may be
enclosed in parentheses to override these precedence rules.
.PP
The backreference
.BI \e n\c
\&, where
.I n
is a single digit, matches the substring
previously matched by the
.IR n th
parenthesized subexpression of the regular expression.
.PP
In basic regular expressions the metacharacters
.BR ? ,
.BR + ,
.BR { ,
.BR | ,
.BR ( ,
and
.BR )
lose their special meaning; instead use the backslashed
versions
.BR \e? ,
.BR \e+ ,
.BR \e{ ,
.BR \e| ,
.BR \e( ,
and
.BR \e) .
.PP
Traditional
.B egrep
did not support the
.B {
metacharacter, and some
.B egrep
implementations support
.B \e{
instead, so portable scripts should avoid
.B {
in
.B egrep
patterns and should use
.B [{]
to match a literal
.BR { .
.PP
\s-1GNU\s0
.B egrep
attempts to support traditional usage by assuming that
.B {
is not special if it would be the start of an invalid interval
specification. For example, the shell command
.B "egrep '{1'"
searches for the two-character string
.B {1
instead of reporting a syntax error in the regular expression.
\s-1POSIX.2\s0 allows this behavior as an extension, but portable scripts
should avoid it.
.SH "ENVIRONMENT VARIABLES"
.TP
.B GREP_OPTIONS
This variable specifies default options to be placed in front of any
explicit options. For example, if
.B GREP_OPTIONS
is
.BR "'\-\^\-binary-files=without-match \-\^\-directories=skip'" ,
.B grep
behaves as if the two options
.B \-\^\-binary-files=without-match
and
.B \-\^\-directories=skip
had been specified before any explicit options.
Option specifications are separated by whitespace.
A backslash escapes the next character,
so it can be used to specify an option containing whitespace or a backslash.
.TP
\fBLC_ALL\fP, \fBLC_MESSAGES\fP, \fBLANG\fP
These variables specify the
.B LC_MESSAGES
locale, which determines the language that
.B grep
uses for messages.
The locale is determined by the first of these variables that is set.
American English is used if none of these environment variables are set,
or if the message catalog is not installed, or if
.B grep
was not compiled with national language support (\s-1NLS\s0).
.TP
\fBLC_ALL\fP, \fBLC_CTYPE\fP, \fBLANG\fP
These variables specify the
.B LC_CTYPE
locale, which determines the type of characters, e.g., which
characters are whitespace.
The locale is determined by the first of these variables that is set.
The \s-1POSIX\s0 locale is used if none of these environment variables
are set, or if the locale catalog is not installed, or if
.B grep
was not compiled with national language support (\s-1NLS\s0).
.TP
.B POSIXLY_CORRECT
If set,
.B grep
behaves as \s-1POSIX.2\s0 requires; otherwise,
.B grep
behaves more like other \s-1GNU\s0 programs.
\s-1POSIX.2\s0 requires that options that follow file names must be
treated as file names; by default, such options are permuted to the
front of the operand list and are treated as options.
Also, \s-1POSIX.2\s0 requires that unrecognized options be diagnosed as
\*(lqillegal\*(rq, but since they are not really against the law the default
is to diagnose them as \*(lqinvalid\*(rq.
.B POSIXLY_CORRECT
also disables \fB_\fP\fIN\fP\fB_GNU_nonoption_argv_flags_\fP,
described below.
.TP
\fB_\fP\fIN\fP\fB_GNU_nonoption_argv_flags_\fP
(Here
.I N
is
.BR grep 's
numeric process ID.) If the
.IR i th
character of this environment variable's value is
.BR 1 ,
do not consider the
.IR i th
operand of
.B grep
to be an option, even if it appears to be one.
A shell can put this variable in the environment for each command it runs,
specifying which operands are the results of file name wildcard
expansion and therefore should not be treated as options.
This behavior is available only with the \s-1GNU\s0 C library, and only
when
.B POSIXLY_CORRECT
is not set.
.SH DIAGNOSTICS
.PP
Normally, exit status is 0 if matches were found,
and 1 if no matches were found. (The
.B \-v
option inverts the sense of the exit status.)
Exit status is 2 if there were syntax errors
in the pattern, inaccessible input files, or
other system errors.
.SH BUGS
.PP
Email bug reports to
.BR bug-gnu-utils@gnu.org .
Be sure to include the word \*(lqgrep\*(rq somewhere in the
\*(lqSubject:\*(rq field.
.PP
Large repetition counts in the
.BI { m , n }
construct may cause grep to use lots of memory.
In addition,
certain other obscure regular expressions require exponential time
and space, and may cause
.B grep
to run out of memory.
.PP
Backreferences are very slow, and may require exponential time.
.\" Work around problems with some troff -man implementations.
.br

569
archivemail.py Executable file
View File

@ -0,0 +1,569 @@
#!/usr/bin/python -tt
############################################################################
# Copyright (C) 2002 Paul Rodger <paul@paulrodger.com>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
############################################################################
"""Archive and compress old mail in mbox-format mailboxes"""
import atexit
import fcntl
import getopt
import mailbox
import os
import re
import rfc822
import string
import sys
import tempfile
import time
# globals
VERSION = "archivemail v0.1.0"
COPYRIGHT = """Copyright (C) 2002 Paul Rodger <paul@paulrodger.com>
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE."""
options = None # global instance of the run-time options class
stale = None # list of files to delete on abnormal exit
############## class definitions ###############
class Stats:
"""collect and print statistics per mailbox"""
archived = 0
mailbox_name = None
archive_name = None
start_time = 0
total = 0
def __init__(self, mailbox_name, final_archive_name):
"""constructor for a new set of statistics - the mailbox names are
only used for printing a friendly message"""
self.start_time = time.time()
self.mailbox_name = mailbox_name
self.archive_name = final_archive_name + options.compressor_extension
def another_message(self):
self.total = self.total + 1
def another_archived(self):
self.archived = self.archived + 1
def display(self):
"""Display one line of archive statistics for the mailbox"""
end_time = time.time()
time_seconds = end_time - self.start_time
action = "archived"
if options.delete_old_mail:
action = "deleted"
print "%s: %s %d of %d message(s) in %.1f seconds" % \
(self.mailbox_name, action, self.archived, self.total,
time_seconds)
class StaleFiles:
"""container for remembering stale files to delete on abnormal exit"""
archive = None # tempfile for messages to be archived
compressed_archive = None # compressed version of the above
procmail_lock = None # original_mailbox.lock
retain = None # tempfile for messages to be retained
class Options:
"""container for storing and setting our runtime options"""
archive_suffix = "_archive"
compressor = None
compressor_extension = None
days_old_max = 180
delete_old_mail = 0
lockfile_attempts = 5 # 5 seconds of waiting
lockfile_extension = ".lock"
quiet = 0
script_name = os.path.basename(sys.argv[0])
verbose = 0
def parse_args(self, args, usage):
"""set our runtime options from the command-line arguments"""
try:
opts, args = getopt.getopt(args, '?IVZd:hqs:vz',
["bzip2", "compress", "days=", "delete", "gzip",
"help", "quiet", "suffix", "verbose",
"version"])
except getopt.error, msg:
user_error(msg)
for o, a in opts:
if o == '--delete':
self.delete_old_mail = 1
if o in ('-d', '--days'):
self.days_old_max = string.atoi(a)
if (self.days_old_max < 1):
user_error("argument to -d must be greater than zero")
if (self.days_old_max >= 10000):
user_error("argument to -d must be less than 10000")
if o in ('-h', '-?', '--help'):
print usage
sys.exit(0)
if o in ('-q', '--quiet'):
self.quiet = 1
if o in ('-v', '--verbose'):
self.verbose = 1
if o in ('-s', '--suffix'):
self.archive_suffix = a
if o in ('-V', '--version'):
print VERSION + "\n\n" + COPYRIGHT
sys.exit(0)
if o in ('-z', '--gzip'):
if (self.compressor):
user_error("conflicting compression options")
self.compressor = "gzip"
if o in ('-Z', '--compress'):
if (self.compressor):
user_error("conflicting compression options")
self.compressor = "compress"
if o in ('-I', '--bzip2'):
if (self.compressor):
user_error("conflicting compression options")
self.compressor = "bzip2"
if not self.compressor:
self.compressor = "gzip"
extensions = {
"compress" : ".Z",
"gzip" : ".gz",
"bzip2" : ".bz2",
}
self.compressor_extension = extensions[self.compressor]
return args
class Mailbox:
""" generic read/writable 'mbox' format mailbox file"""
count = 0
file = None
mbox = None
def __init__(self):
"""constructor: doesn't do much"""
pass
def store(self, msg):
"""write one message to the mbox file"""
vprint("saving message to file '%s'" % self.file.name)
assert(msg.unixfrom)
self.file.write(msg.unixfrom)
assert(msg.headers)
self.file.writelines(msg.headers)
self.file.write("\n")
# The following while loop is about twice as fast in
# practice to 'self.file.writelines(msg.fp.readlines())'
while 1:
body = msg.fp.read(8192)
if not body:
break
self.file.write(body)
self.count = self.count + 1
def unlink(self):
"""destroy the whole thing"""
if self.file:
file_name = self.file.name
self.close()
vprint("unlinking file '%s'" % self.file.name)
os.unlink(file_name)
def get_size(self):
"""determine file size of this mbox file"""
assert(self.file.name)
return os.path.getsize(self.file.name)
def close(self):
"""close the mbox file"""
if not self.file.closed:
vprint("closing file '%s'" % self.file.name)
self.file.close()
def read_message(self):
"""read one rfc822 message object from the mbox file"""
if not self.mbox:
self.file.seek(0)
self.mbox = mailbox.UnixMailbox(self.file)
assert(self.mbox)
message = self.mbox.next()
return message
def exclusive_lock(self):
"""set an advisory lock on the whole mbox file"""
vprint("obtaining exclusive lock on file '%s'" % self.file.name)
fcntl.flock(self.file, fcntl.LOCK_EX)
def exclusive_unlock(self):
"""unset any advisory lock on the mbox file"""
vprint("dropping exclusive lock on file '%s'" % self.file.name)
fcntl.flock(self.file, fcntl.LOCK_UN)
def procmail_lock(self):
"""create a procmail-style .lock file to prevent clashes"""
lock_name = self.file.name + options.lockfile_extension
attempt = 0
while os.path.isfile(lock_name):
vprint("lockfile '%s' exists - sleeping..." % lock_name)
time.sleep(1)
attempt = attempt + 1
if (attempt >= options.lockfile_attempts):
user_error("Giving up waiting for procmail lock '%s'" % lock_name)
vprint("writing lockfile '%s'" % lock_name)
lock = open(lock_name, "w")
stale.procmail_lock = lock_name
lock.close()
def procmail_unlock(self):
"""delete our procmail-style .lock file"""
lock_name = self.file.name + options.lockfile_extension
vprint("removing lockfile '%s'" % lock_name)
os.unlink(lock_name)
stale.procmail_lock = None
def leave_empty(self):
"""This should be the same as 'cp /dev/null mailbox'.
This will leave a zero-length mailbox file so that mail
reading programs don't get upset that the mailbox has been
completely deleted."""
vprint("turning '%s' into a zero-length file" % self.file.name)
atime = os.path.getatime(self.file.name)
mtime = os.path.getmtime(self.file.name)
blank_file = open(self.file.name, "w")
blank_file.close()
os.utime(self.file.name, (atime, mtime)) # reset to original timestamps
class RetainMailbox(Mailbox):
"""a temporary mailbox for holding messages that will be retained in the
original mailbox"""
def __init__(self):
"""constructor - create the temporary file"""
temp_name = tempfile.mktemp("archivemail_retain")
self.file = open(temp_name, "w")
stale.retain = temp_name
vprint("opened temporary retain file '%s'" % self.file.name)
def finalise(self, final_name):
"""constructor - create the temporary file"""
self.close()
atime = os.path.getatime(final_name)
mtime = os.path.getmtime(final_name)
vprint("renaming '%s' to '%s'" % (self.file.name, final_name))
os.rename(self.file.name, final_name)
os.utime(final_name, (atime, mtime)) # reset to original timestamps
stale.retain = None
def unlink(self):
"""Override the base-class version, removing from stalefiles"""
Mailbox.unlink(self)
stale.retain = None
class ArchiveMailbox(Mailbox):
"""all messages that are too old go here"""
final_name = None # this is
def __init__(self, final_name):
"""copy any pre-existing compressed archive to a temp file which we
use as the new soon-to-be compressed archive"""
assert(final_name)
compressor = options.compressor
compressedfilename = final_name + options.compressor_extension
if os.path.isfile(final_name):
user_error("There is already a file named '%s'!" % (final_name))
temp_name = tempfile.mktemp("archivemail_archive")
if os.path.isfile(compressedfilename):
vprint("file already exists that is named: %s" % compressedfilename)
uncompress = "%s -d -c %s > %s" % (compressor,
compressedfilename, temp_name)
vprint("running uncompressor: %s" % uncompress)
stale.archive = temp_name
system_or_die(uncompress)
stale.archive = temp_name
self.file = open(temp_name, "a")
self.final_name = final_name
def finalise(self):
"""rename the temp file back to the original compressed archive
file"""
self.close()
compressor = options.compressor
compressed_archive_name = self.file.name + options.compressor_extension
compress = compressor + " " + self.file.name
vprint("running compressor: '%s'" % compress)
stale.compressed_archive = compressed_archive_name
system_or_die(compress)
stale.archive = None
compressed_final_name = self.final_name + options.compressor_extension
vprint("renaming '%s' to '%s'" % (compressed_archive_name,
compressed_final_name))
os.rename(compressed_archive_name, compressed_final_name)
stale.compressed_archive = None
class OriginalMailbox(Mailbox):
"""This is the mailbox that we read messages from to determine if they are
too old. We will never write to this file directly except at the end
where we override the whole file with the RetainMailbox."""
file = None
def __init__(self, mailbox_name):
"""open the mailbox, ready for reading"""
try:
self.file = open(mailbox_name, "r")
except IOError, msg:
user_error(msg)
def main(args = sys.argv[1:]):
global options
global stale
options = Options()
usage = """Usage: %s [options] mailbox [mailbox...]
Moves old mail messages in mbox-format mailboxes to compressed mailbox
archives. This is useful for saving space and keeping your mailbox manageable.
Options are as follows:
-d, --days=<days> archive messages older than <days> days (default: %d)
-s, --suffix=<name> suffix for archive filename (default: '%s')
-z, --gzip compress the archive using gzip (default)
-I, --bzip2 compress the archive using bzip2
-Z, --compress compress the archive using compress
--delete delete rather than archive old mail (use with caution!)
-v, --verbose report lots of extra debugging information
-q, --quiet quiet mode - print no statistics (suitable for crontab)
-V, --version display version information
-h, --help display this message
Example: %s linux-devel
This will move all messages older than %s days to a file called
'linux-devel_archive.gz', deleting them from the original 'linux-devel'
mailbox. If the 'linux-devel_archive.gz' mailbox already exists, the
newly archived messages are appended.
""" % (options.script_name, options.days_old_max, options.archive_suffix,
options.script_name, options.days_old_max)
check_python_version()
args = options.parse_args(args, usage)
if len(args) == 0:
print usage
sys.exit(1)
os.umask(077) # saves setting permissions on mailboxes/tempfiles
stale = StaleFiles()
atexit.register(clean_up)
for filename in args:
tempfile.tempdir = os.path.dirname(filename) # don't use /var/tmp
final_archive_name = filename + options.archive_suffix
archive_mailbox(mailbox_name = filename,
final_archive_name = final_archive_name)
######## errors and debug ##########
def vprint(string):
"""this saves putting 'if (verbose) print foo' everywhere"""
if options.verbose:
print string
def user_error(string):
"""fatal error, probably something the user did wrong"""
script_name = options.script_name
message = "%s: %s\n" % (script_name, string)
sys.stderr.write(message)
sys.exit(1)
########### operations on a message ############
def is_too_old(message):
"""return true if a message is too old (and should be archived),
false otherwise"""
date = message.getdate('Date')
delivery_date = message.getdate('Delivery-date')
use_date = None
time_message = None
if delivery_date:
try:
time_message = time.mktime(delivery_date)
use_date = delivery_date
vprint("using message 'Delivery-date' header")
except ValueError:
pass
if date and not use_date:
try:
time_message = time.mktime(date)
use_date = date
vprint("using message 'Date' header")
except ValueError:
pass
if not use_date:
print message
vprint("no valid dates found for message")
return 0
time_now = time.time()
if time_message > time_now:
time_string = time.asctime(use_date)
vprint("warning: message has date in the future: %s !" % time_string)
return 0
secs_old_max = (options.days_old_max * 24 * 60 * 60)
days_old = (time_now - time_message) / 24 / 60 / 60
vprint("message is %.2f days old" % days_old)
if ((time_message + secs_old_max) < time_now):
return 1
return 0
############### mailbox operations ###############
def archive_mailbox(mailbox_name, final_archive_name):
"""process and archive the given mailbox name"""
archive = None
retain = None
vprint("archiving '%s' to '%s' ..." % (mailbox_name, final_archive_name))
stats = Stats(mailbox_name, final_archive_name)
original = OriginalMailbox(mailbox_name)
if original.get_size() == 0:
original.close()
vprint("skipping '%s' because it is a zero-length file" %
original.file.name)
if not options.quiet:
stats.display()
return
original.procmail_lock()
original.exclusive_lock()
msg = original.read_message()
if not msg:
user_error("file '%s' is not in 'mbox' format" % mailbox.file.name)
while (msg):
stats.another_message()
message_id = msg.get('Message-ID')
vprint("processing message '%s'" % message_id)
if is_too_old(msg):
stats.another_archived()
if options.delete_old_mail:
vprint("decision: delete message")
else:
vprint("decision: archive message")
if (not archive):
archive = ArchiveMailbox(final_archive_name)
archive.store(msg)
else:
vprint("decision: retain message")
if (not retain):
retain = RetainMailbox()
retain.store(msg)
msg = original.read_message()
vprint("finished reading messages")
original.exclusive_unlock()
original.close()
if options.delete_old_mail:
# we will never have an archive file
if retain:
retain.finalise(mailbox_name)
else:
original.leave_empty()
elif archive:
archive.finalise()
if retain:
retain.finalise(mailbox_name)
else:
original.leave_empty()
else:
# There was nothing to archive
if retain:
# retain will be the same as original mailbox -- no point copying
retain.close()
retain.unlink()
original.procmail_unlock()
if not options.quiet:
stats.display()
############### misc functions ###############
def clean_up():
"""This is run on exit to make sure we haven't left any stale
files/lockfiles left on the system"""
vprint("cleaning up ...")
if stale.procmail_lock:
vprint("removing stale procmail lock '%s'" % stale.procmail_lock)
try: os.unlink(stale.procmail_lock)
except (IOError, OSError): pass
if stale.retain:
vprint("removing stale retain file '%s'" % stale.retain)
try: os.unlink(stale.retain)
except (IOError, OSError): pass
if stale.archive:
vprint("removing stale archive file '%s'" % stale.archive)
try: os.unlink(stale.archive)
except (IOError, OSError): pass
if stale.compressed_archive:
vprint("removing stale compressed archive file '%s'" %
stale.compressed_archive)
try: os.unlink(stale.compressed_archive)
except (IOError, OSError): pass
def check_python_version():
"""make sure we are running with the right version of python"""
build = sys.version
too_old_error = "requires python v2.0 or greater. Your version is: %s" % build
try:
version = sys.version_info # we might not even have this function! :)
if (version[0] < 2):
UserError(too_old_error)
except: # I should be catching more specific exceptions
UserError(too_old_error)
def system_or_die(command):
"""Give a user_error() if the command we ran returned a non-zero status"""
rv = os.system(command)
if (rv != 0):
status = os.WEXITSTATUS(rv)
user_error("command '%s' returned status %d" % (command, status))
# this is where it all happens, folks
if __name__ == '__main__':
main()