# The "checkoutlist" file is used to support additional version controlled
# administrative files in $CVSROOT/CVSROOT, such as template files.
#
# The first entry on a line is a filename which will be checked out from
# the corresponding RCS file in the $CVSROOT/CVSROOT directory.
# The remainder of the line is an error message to use if the file cannot
# be checked out.
#
# File format:
#
#	[<whitespace>]<filename><whitespace><error message><end-of-line>
#
# comment lines begin with '#'
syncmail

# The "commitinfo" file is used to control pre-commit checks.
# The filter on the right is invoked with the repository and a list 
# of files to check.  A non-zero exit of the filter program will 
# cause the commit to be aborted.
#
# The first entry on a line is a regular expression which is tested
# against the directory that the change is being committed to, relative
# to the $CVSROOT.  For the first match that is found, then the remainder
# of the line is the name of the filter to run.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name "ALL" appears as a regular expression it is always used
# in addition to the first matching regex or "DEFAULT".

# Set this to "no" if pserver shouldn't check system users/passwords
#SystemAuth=no

# Set `PreservePermissions' to `yes' to save file status information
# in the repository.
#PreservePermissions=no

# Set `TopLevelAdmin' to `yes' to create a CVS directory at the top
# level of the new working directory when using the `cvs checkout'
# command.
#TopLevelAdmin=no

# This file affects handling of files based on their names.
#
# The -t/-f options allow one to treat directories of files
# as a single file, or to transform a file in other ways on
# its way in and out of CVS.
#
# The -m option specifies whether CVS attempts to merge files.
#
# The -k option specifies keyword expansion (e.g. -kb for binary).
#
# Format of wrapper file ($CVSROOT/CVSROOT/cvswrappers or .cvswrappers)
#
#  wildcard	[option value][option value]...
#
#  where option is one of
#  -f		from cvs filter		value: path to filter
#  -t		to cvs filter		value: path to filter
#  -m		update methodology	value: MERGE or COPY
#  -k		expansion mode		value: b, o, kkv, &c
#
#  and value is a single-quote delimited value.
# For example:
#*.gif -k 'b'

# The "editinfo" file is used to allow verification of logging
# information.  It works best when a template (as specified in the
# rcsinfo file) is provided for the logging procedure.  Given a
# template with locations for, a bug-id number, a list of people who
# reviewed the code before it can be checked in, and an external
# process to catalog the differences that were code reviewed, the
# following test can be applied to the code:
#
#   Making sure that the entered bug-id number is correct.
#   Validating that the code that was reviewed is indeed the code being
#       checked in (using the bug-id number or a seperate review
#       number to identify this particular code set.).
#
# If any of the above test failed, then the commit would be aborted.
#
# Actions such as mailing a copy of the report to each reviewer are
# better handled by an entry in the loginfo file.
#
# One thing that should be noted is the the ALL keyword is not
# supported.  There can be only one entry that matches a given
# repository.

# The "loginfo" file controls where "cvs commit" log information
# is sent.  The first entry on a line is a regular expression which must match
# the directory that the change is being made to, relative to the
# $CVSROOT.  If a match is found, then the remainder of the line is a filter
# program that should expect log information on its standard input.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name ALL appears as a regular expression it is always used
# in addition to the first matching regex or DEFAULT.
#
# You may specify a format string as part of the
# filter.  The string is composed of a `%' followed
# by a single format character, or followed by a set of format
# characters surrounded by `{' and `}' as separators.  The format
# characters are:
#
#   s = file name
#   V = old version number (pre-checkin)
#   v = new version number (post-checkin)
#
# For example:
#DEFAULT (echo ""; id; echo %s; date; cat) >> $CVSROOT/CVSROOT/commitlog
# or
#DEFAULT (echo ""; id; echo %{sVv}; date; cat) >> $CVSROOT/CVSROOT/commitlog

# Lines to mail changes
CVSROOT $CVSROOT/CVSROOT/syncmail %{sVv} gawthrop@users.sourceforge.net
DEFAULT $CVSROOT/CVSROOT/syncmail %{sVv} mtt-checkins@lists.sourceforge.net

# Three different line formats are valid:
#	key	-a    aliases...
#	key [options] directory
#	key [options] directory files...
#
# Where "options" are composed of:
#	-i prog		Run "prog" on "cvs commit" from top-level of module.
#	-o prog		Run "prog" on "cvs checkout" of module.
#	-e prog		Run "prog" on "cvs export" of module.
#	-t prog		Run "prog" on "cvs rtag" of module.
#	-u prog		Run "prog" on "cvs update" of module.
#	-d dir		Place module in directory "dir" instead of module name.
#	-l		Top-level directory only -- do not recurse.
#
# NOTE:  If you change any of the "Run" options above, you'll have to
# release and re-checkout any working directories of these modules.
#
# And "directory" is a path to a directory relative to $CVSROOT.
#
# The "-a" option specifies an alias.  An alias is interpreted as if
# everything on the right of the "-a" had been typed on the command line.
#
# You can encode a module within a module by using the special '&'
# character to interpose another module into the current module.  This
# can be useful for creating a module that consists of many directories
# spread out over the entire source repository.

# The "notify" file controls where notifications from watches set by
# "cvs watch add" or "cvs edit" are sent.  The first entry on a line is
# a regular expression which is tested against the directory that the
# change is being made to, relative to the $CVSROOT.  If it matches,
# then the remainder of the line is a filter program that should contain
# one occurrence of %s for the user to notify, and information on its
# standard input.
#
# "ALL" or "DEFAULT" can be used in place of the regular expression.
#
# For example:
#ALL mail %s -s "CVS notification"

# The "rcsinfo" file is used to control templates with which the editor
# is invoked on commit and import.
#
# The first entry on a line is a regular expression which is tested
# against the directory that the change is being made to, relative to the
# $CVSROOT.  For the first match that is found, then the remainder of the
# line is the name of the file that contains the template.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name "ALL" appears as a regular expression it is always used
# in addition to the first matching regex or "DEFAULT".

#! /usr/bin/python

# Copyright (c) 2002, 2003, Barry Warsaw, Fred Drake, and contributors
# All rights reserved.
# See the accompanying LICENSE file for details.

# Compatibility: Python 2.2.3, tied to the version of Python on SourceForge's
# authenticated CVS server.

"""Complicated notification for CVS checkins.

This script is used to provide email notifications of changes to the CVS
repository.  These email changes will include context diffs of the changes.
Really big diffs will be trimmed.

This script is run from a CVS loginfo file (see $CVSROOT/CVSROOT/loginfo).  To
set this up, create a loginfo entry that looks something like this:

    mymodule /path/to/this/script %%s some-email-addr@your.domain

In this example, whenever a checkin that matches `mymodule' is made, this
script is invoked, which will generate the diff containing email, and send it
to some-email-addr@your.domain.

    Note: This module used to also do repository synchronizations via
    rsync-over-ssh, but since the repository has been moved to SourceForge,
    this is no longer necessary.  The syncing functionality has been ripped
    out in the 3.0, which simplifies it considerably.  Access the 2.x versions
    to refer to this functionality.  Because of this, the script is misnamed.

It no longer makes sense to run this script from the command line.  Doing so
will only print out this usage information.

Usage:

    %(PROGRAM)s [options] <%%S> email-addr [email-addr ...]

Where options are:

    --cvsroot=<path>
        Use <path> as the environment variable CVSROOT.  Otherwise this
        variable must exist in the environment.

    --context=#
    -C #
        Include # lines of context around lines that differ (default: 2).

    -c
        Produce a context diff (default).

    -m hostname
    --mailhost hostname
        The hostname of an available SMTP server.  The default is
        'localhost'.

    -u
        Produce a unified diff (smaller).

    -S TEXT
    --subject-prefix=TEXT
        Prepend TEXT to the email subject line.

    -R ADDR
    --reply-to=ADDR
      Add a "Reply-To: ADDR" header to the email message.

    --quiet / -q
        Don't print as much status to stdout.

    --fromhost=hostname
    -f hostname
        The hostname that email messages appear to be coming from.  The From:
        header of the outgoing message will look like user@hostname.  By
        default, hostname is the machine's fully qualified domain name.

    --help / -h
        Print this text.

The rest of the command line arguments are:

    <%%S>
        CVS %%s loginfo expansion.  When invoked by CVS, this will be a single
        string containing the directory the checkin is being made in, relative
        to $CVSROOT, followed by the list of files that are changing.  If the
        %%s in the loginfo file is %%{sVv}, context diffs for each of the
        modified files are included in any email messages that are generated.

    email-addrs
        At least one email address.
"""
__version__ = '1.2'

import os
import sys
import re
import time
import string
import getopt
import smtplib
import pwd
import socket

try:
    from socket import getfqdn
except ImportError:
    def getfqdn():
        # Python 1.5.2 :(
        hostname = socket.gethostname()
        byaddr = socket.gethostbyaddr(socket.gethostbyname(hostname))
        aliases = byaddr[1]
        aliases.insert(0, byaddr[0])
        aliases.insert(0, hostname)
        for fqdn in aliases:
            if '.' in fqdn:
                break
        else:
            fqdn = 'localhost.localdomain'
        return fqdn


from cStringIO import StringIO

# Which SMTP server to do we connect to?
MAILHOST = 'localhost'
MAILPORT = 25

# Diff trimming stuff
DIFF_HEAD_LINES = 20
DIFF_TAIL_LINES = 20
DIFF_TRUNCATE_IF_LARGER = 1000

COMMASPACE = ', '

PROGRAM = sys.argv[0]

BINARY_EXPLANATION_LINES = [
    "(This appears to be a binary file; contents omitted.)\n"
    ]

NOVERSION = "Couldn't generate diff; no version number found for file: %s"
BACKSLASH = "Couldn't generate diff: backslash in filespec's filename: %s"



def usage(code, msg=''):
    print __doc__ % globals()
    if msg:
        print msg
    sys.exit(code)



def calculate_diff(entry, contextlines):
    file = entry.name
    oldrev = entry.revision
    newrev = entry.new_revision

    # Make sure we can find a CVS version number
    if oldrev is None and newrev is None:
        return NOVERSION % file

    if string.find(file, "'") <> -1:
        # Those crazy users put single-quotes in their file names!  Now we
        # have to escape everything that is meaningful inside double-quotes.
        filestr = string.replace(file, '\\', '\\\\')
        filestr = string.replace(filestr, '`', '\`')
        filestr = string.replace(filestr, '"', '\"')
        filestr = string.replace(filestr, '$', '\$')
        # and quote it with double-quotes.
        filestr = '"' + filestr + '"'
    else:
        # quote it with single-quotes.
        filestr = "'" + file + "'"
    if oldrev is None:
        # File is being added.
        try:
            if os.path.exists(file):
                fp = open(file)
            else:
                update_cmd = "cvs -fn update -r %s -p %s" % (newrev, filestr)
                fp = os.popen(update_cmd)
            lines = fp.readlines()
            fp.close()
            # Is this a binary file?  Let's look at the first few
            # lines to figure it out:
            for line in lines[:5]:
                for c in string.rstrip(line):
                    if c in string.whitespace:
                        continue
                    if c < ' ' or c > chr(127):
                        lines = BINARY_EXPLANATION_LINES[:]
                        break
            lines.insert(0, '--- NEW FILE: %s ---\n' % file)
        except IOError, e:
            lines = ['***** Error reading new file: ',
                     str(e), '\n***** file: ', file, ' cwd: ', os.getcwd()]
    elif newrev is None:
        lines = ['--- %s DELETED ---\n' % file]
    else:
        # File has been changed.
        # This /has/ to happen in the background, otherwise we'll run into CVS
        # lock contention.  What a crock.
        if contextlines > 0:
            difftype = "-C " + str(contextlines)
        else:
            difftype = "-u"
        diffcmd = "/usr/bin/cvs -f diff -kk %s --minimal -r %s -r %s %s" \
                  % (difftype, oldrev, newrev, filestr)
        fp = os.popen(diffcmd)
        lines = fp.readlines()
        # ignore the error code, it always seems to be 1 :(
        fp.close()
    if len(lines) > DIFF_TRUNCATE_IF_LARGER:
        removedlines = len(lines) - DIFF_HEAD_LINES - DIFF_TAIL_LINES
        del lines[DIFF_HEAD_LINES:-DIFF_TAIL_LINES]
        lines.insert(DIFF_HEAD_LINES,
                     '[...%d lines suppressed...]\n' % removedlines)
    return string.join(lines, '')



rfc822_specials_re = re.compile(r'[\(\)\<\>\@\,\;\:\\\"\.\[\]]')

def quotename(name):
    if name and rfc822_specials_re.search(name):
        return '"%s"' % string.replace(name, '"', '\\"')
    else:
        return name



def blast_mail(subject, people, entries, contextlines, fromhost, replyto):
    # cannot wait for child process or that will cause parent to retain cvs
    # lock for too long.  Urg!
    if not os.fork():
        # in the child
        # give up the lock you cvs thang!
        time.sleep(2)
        # Create the smtp connection to the localhost
        conn = smtplib.SMTP()
        conn.connect(MAILHOST, MAILPORT)
        user = pwd.getpwuid(os.getuid())[0]
        name = string.split(pwd.getpwuid(os.getuid())[4], ',')[0]
        domain = fromhost or getfqdn()
        address = '%s@%s' % (user, domain)
        s = StringIO()
        sys.stdout = s
        datestamp = time.strftime('%a, %d %b %Y %H:%M:%S +0000',
                                  time.gmtime(time.time()))
        try:
            vars = {'address' : address,
                    'name'    : quotename(name),
                    'people'  : string.join(people, COMMASPACE),
                    'subject' : subject,
                    'version' : __version__,
                    'date'    : datestamp,
                    }
            print '''\
From: %(name)s <%(address)s>
To: %(people)s''' % vars
            if replyto:
                print 'Reply-To: %s' % replyto
            print '''\
Subject: %(subject)s
Date: %(date)s
X-Mailer: Python syncmail %(version)s <http://sf.net/projects/cvs-syncmail>
''' % vars
            s.write(sys.stdin.read())
            # append the diffs if available
            print
            for entry in entries:
                print calculate_diff(entry, contextlines)
        finally:
            sys.stdout = sys.__stdout__
        resp = conn.sendmail(address, people, s.getvalue())
        conn.close()
        os._exit(0)



class CVSEntry:
    def __init__(self, name, revision, timestamp, conflict, options, tagdate):
        self.name = name
        self.revision = revision
        self.timestamp = timestamp
        self.conflict = conflict
        self.options = options
        self.tagdate = tagdate

def get_entry(prefix, mapping, line, filename):
    line = string.strip(line)
    parts = string.split(line, "/")
    _, name, revision, timestamp, options, tagdate = parts
    key = namekey(prefix, name)
    try:
        entry = mapping[key]
    except KeyError:
        if revision == "0":
            revision = None
        if string.find(timestamp, "+") != -1:
            timestamp, conflict = tuple(string.split(timestamp, "+"))
        else:
            conflict = None
        entry = CVSEntry(key, revision, timestamp, conflict,
                         options, tagdate)
        mapping[key] = entry
    return entry

def namekey(prefix, name):
    if prefix:
        return os.path.join(prefix, name)
    else:
        return name

def load_change_info(prefix=None):
    if prefix is not None:
        entries_fn = os.path.join(prefix, "CVS", "Entries")
    else:
        entries_fn = os.path.join("CVS", "Entries")
    entries_log_fn = entries_fn + ".Log"
    mapping = {}
    f = open(entries_fn)
    while 1:
        line = f.readline()
        if not line:
            break
##        if string.strip(line) == "D":
##            continue
        # we could recurse down subdirs, except the Entries.Log files
        # we need haven't been written to the subdirs yet, so it
        # doesn't do us any good
##        if line[0] == "D":
##            name = string.split(line, "/")[1]
##            dirname = namekey(prefix, name)
##            if os.path.isdir(dirname):
##                m = load_change_info(dirname)
##                mapping.update(m)
        if line[0] == "/":
            # normal file
            get_entry(prefix, mapping, line, entries_fn)
        # else: bogus Entries line
    f.close()
    if os.path.isfile(entries_log_fn):
        f = open(entries_log_fn)
        while 1:
            line = f.readline()
            if not line:
                break
            if line[1:2] != ' ':
                # really old version of CVS
                break
            entry = get_entry(prefix, mapping, line[2:], entries_log_fn)
            parts = string.split(line, "/")[1:]
            if line[0] == "A":
                # adding a file
                entry.new_revision = parts[1]
            elif line[0] == "R":
                # removing a file
                entry.new_revision = None
        f.close()
    for entry in mapping.values():
        if not hasattr(entry, "new_revision"):
            print 'confused about file', entry.name, '-- ignoring'
            del mapping[entry.name]
    return mapping

def load_branch_name():
    tag_fn = os.path.join("CVS", "Tag")
    if os.path.isfile(tag_fn):
        f = open(tag_fn)
        line = string.strip(f.readline())
        f.close()
        if line[:1] == "T":
            return line[1:]
    return None

# scan args for options
def main():
    # XXX Should really move all the options to an object, just to
    # avoid threading so many positional args through everything.
    try:
        opts, args = getopt.getopt(
            sys.argv[1:], 'hC:cuS:R:qf:m:',
            ['fromhost=', 'context=', 'cvsroot=', 'mailhost=',
             'subject-prefix=', 'reply-to=',
             'help', 'quiet'])
    except getopt.error, msg:
        usage(1, msg)

    # parse the options
    contextlines = 2
    verbose = 1
    subject_prefix = ""
    replyto = None
    fromhost = None
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt == '--cvsroot':
            os.environ['CVSROOT'] = arg
        elif opt in ('-C', '--context'):
            contextlines = int(arg)
        elif opt == '-c':
            if contextlines <= 0:
                contextlines = 2
        elif opt == '-u':
            contextlines = 0
        elif opt in ('-S', '--subject-prefix'):
            subject_prefix = arg
        elif opt in ('-R', '--reply-to'):
            replyto = arg
        elif opt in ('-q', '--quiet'):
            verbose = 0
        elif opt in ('-f', '--fromhost'):
            fromhost = arg
        elif opt in ('-m', '--mailhost'):
            global MAILHOST
            MAILHOST = arg

    # What follows is the specification containing the files that were
    # modified.  The argument actually must be split, with the first component
    # containing the directory the checkin is being made in, relative to
    # $CVSROOT, followed by the list of files that are changing.
    if not args:
        usage(1, 'No CVS module specified')
    changes = load_change_info()
    branch = load_branch_name()
    subject = subject_prefix + args[0]
    specs = string.split(args[0])
    del args[0]

    # The remaining args should be the email addresses
    if not args:
        usage(1, 'No recipients specified')

    # Now do the mail command
    people = args

    if specs[-3:] == ['-', 'Imported', 'sources']:
        print 'Not sending email for imported sources.'
        return

    if verbose:
##        print 'Python version', sys.version
##        os.system("type python1.6; type python2;"
##                  " type python2.0; type python2.1; type python2.2;"
##                  " type rcsdiff; type rlog")
        print 'Mailing %s...' % string.join(people, COMMASPACE)
        print 'Generating notification message...'
    blast_mail(subject, people, changes.values(),
               contextlines, fromhost, replyto)
    if verbose:
        print 'Generating notification message... done.'



if __name__ == '__main__':
    main()
    sys.exit(0)

# The "taginfo" file is used to control pre-tag checks.
# The filter on the right is invoked with the following arguments:
#
# $1 -- tagname
# $2 -- operation "add" for tag, "mov" for tag -F, and "del" for tag -d
# $3 -- repository
# $4->  file revision [file revision ...]
#
# A non-zero exit of the filter program will cause the tag to be aborted.
#
# The first entry on a line is a regular expression which is tested
# against the directory that the change is being committed to, relative
# to the $CVSROOT.  For the first match that is found, then the remainder
# of the line is the name of the filter to run.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name "ALL" appears as a regular expression it is always used
# in addition to the first matching regex or "DEFAULT".

# The "verifymsg" file is used to allow verification of logging
# information.  It works best when a template (as specified in the
# rcsinfo file) is provided for the logging procedure.  Given a
# template with locations for, a bug-id number, a list of people who
# reviewed the code before it can be checked in, and an external
# process to catalog the differences that were code reviewed, the
# following test can be applied to the code:
#
#   Making sure that the entered bug-id number is correct.
#   Validating that the code that was reviewed is indeed the code being
#       checked in (using the bug-id number or a seperate review
#       number to identify this particular code set.).
#
# If any of the above test failed, then the commit would be aborted.
#
# Actions such as mailing a copy of the report to each reviewer are
# better handled by an entry in the loginfo file.
#
# One thing that should be noted is the the ALL keyword is not
# supported.  There can be only one entry that matches a given
# repository.

# The "checkoutlist" file is used to support additional version controlled
# administrative files in $CVSROOT/CVSROOT, such as template files.
#
# The first entry on a line is a filename which will be checked out from
# the corresponding RCS file in the $CVSROOT/CVSROOT directory.
# The remainder of the line is an error message to use if the file cannot
# be checked out.
#
# File format:
#
#	[<whitespace>]<filename><whitespace><error message><end-of-line>
#
# comment lines begin with '#'
syncmail

# The "commitinfo" file is used to control pre-commit checks.
# The filter on the right is invoked with the repository and a list 
# of files to check.  A non-zero exit of the filter program will 
# cause the commit to be aborted.
#
# The first entry on a line is a regular expression which is tested
# against the directory that the change is being committed to, relative
# to the $CVSROOT.  For the first match that is found, then the remainder
# of the line is the name of the filter to run.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name "ALL" appears as a regular expression it is always used
# in addition to the first matching regex or "DEFAULT".

# Set this to "no" if pserver shouldn't check system users/passwords
#SystemAuth=no

# Set `PreservePermissions' to `yes' to save file status information
# in the repository.
#PreservePermissions=no

# Set `TopLevelAdmin' to `yes' to create a CVS directory at the top
# level of the new working directory when using the `cvs checkout'
# command.
#TopLevelAdmin=no

# This file affects handling of files based on their names.
#
# The -t/-f options allow one to treat directories of files
# as a single file, or to transform a file in other ways on
# its way in and out of CVS.
#
# The -m option specifies whether CVS attempts to merge files.
#
# The -k option specifies keyword expansion (e.g. -kb for binary).
#
# Format of wrapper file ($CVSROOT/CVSROOT/cvswrappers or .cvswrappers)
#
#  wildcard	[option value][option value]...
#
#  where option is one of
#  -f		from cvs filter		value: path to filter
#  -t		to cvs filter		value: path to filter
#  -m		update methodology	value: MERGE or COPY
#  -k		expansion mode		value: b, o, kkv, &c
#
#  and value is a single-quote delimited value.
# For example:
#*.gif -k 'b'

# The "editinfo" file is used to allow verification of logging
# information.  It works best when a template (as specified in the
# rcsinfo file) is provided for the logging procedure.  Given a
# template with locations for, a bug-id number, a list of people who
# reviewed the code before it can be checked in, and an external
# process to catalog the differences that were code reviewed, the
# following test can be applied to the code:
#
#   Making sure that the entered bug-id number is correct.
#   Validating that the code that was reviewed is indeed the code being
#       checked in (using the bug-id number or a seperate review
#       number to identify this particular code set.).
#
# If any of the above test failed, then the commit would be aborted.
#
# Actions such as mailing a copy of the report to each reviewer are
# better handled by an entry in the loginfo file.
#
# One thing that should be noted is the the ALL keyword is not
# supported.  There can be only one entry that matches a given
# repository.

# The "loginfo" file controls where "cvs commit" log information
# is sent.  The first entry on a line is a regular expression which must match
# the directory that the change is being made to, relative to the
# $CVSROOT.  If a match is found, then the remainder of the line is a filter
# program that should expect log information on its standard input.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name ALL appears as a regular expression it is always used
# in addition to the first matching regex or DEFAULT.
#
# You may specify a format string as part of the
# filter.  The string is composed of a `%' followed
# by a single format character, or followed by a set of format
# characters surrounded by `{' and `}' as separators.  The format
# characters are:
#
#   s = file name
#   V = old version number (pre-checkin)
#   v = new version number (post-checkin)
#
# For example:
#DEFAULT (echo ""; id; echo %s; date; cat) >> $CVSROOT/CVSROOT/commitlog
# or
#DEFAULT (echo ""; id; echo %{sVv}; date; cat) >> $CVSROOT/CVSROOT/commitlog

# Lines to mail changes
CVSROOT $CVSROOT/CVSROOT/syncmail %{sVv} mtt@gawthrop.net
DEFAULT $CVSROOT/CVSROOT/syncmail %{sVv} mtt-cvs@lists.sourceforge.net

# Three different line formats are valid:
#	key	-a    aliases...
#	key [options] directory
#	key [options] directory files...
#
# Where "options" are composed of:
#	-i prog		Run "prog" on "cvs commit" from top-level of module.
#	-o prog		Run "prog" on "cvs checkout" of module.
#	-e prog		Run "prog" on "cvs export" of module.
#	-t prog		Run "prog" on "cvs rtag" of module.
#	-u prog		Run "prog" on "cvs update" of module.
#	-d dir		Place module in directory "dir" instead of module name.
#	-l		Top-level directory only -- do not recurse.
#
# NOTE:  If you change any of the "Run" options above, you'll have to
# release and re-checkout any working directories of these modules.
#
# And "directory" is a path to a directory relative to $CVSROOT.
#
# The "-a" option specifies an alias.  An alias is interpreted as if
# everything on the right of the "-a" had been typed on the command line.
#
# You can encode a module within a module by using the special '&'
# character to interpose another module into the current module.  This
# can be useful for creating a module that consists of many directories
# spread out over the entire source repository.

# The "notify" file controls where notifications from watches set by
# "cvs watch add" or "cvs edit" are sent.  The first entry on a line is
# a regular expression which is tested against the directory that the
# change is being made to, relative to the $CVSROOT.  If it matches,
# then the remainder of the line is a filter program that should contain
# one occurrence of %s for the user to notify, and information on its
# standard input.
#
# "ALL" or "DEFAULT" can be used in place of the regular expression.
#
# For example:
#ALL mail %s -s "CVS notification"

# The "rcsinfo" file is used to control templates with which the editor
# is invoked on commit and import.
#
# The first entry on a line is a regular expression which is tested
# against the directory that the change is being made to, relative to the
# $CVSROOT.  For the first match that is found, then the remainder of the
# line is the name of the file that contains the template.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name "ALL" appears as a regular expression it is always used
# in addition to the first matching regex or "DEFAULT".

#! /usr/bin/python

# Copyright (c) 2002, 2003, Barry Warsaw, Fred Drake, and contributors
# All rights reserved.
# See the accompanying LICENSE file for details.

# Compatibility: Python 2.2.3, tied to the version of Python on SourceForge's
# authenticated CVS server.

"""Complicated notification for CVS checkins.

This script is used to provide email notifications of changes to the CVS
repository.  These email changes will include context diffs of the changes.
Really big diffs will be trimmed.

This script is run from a CVS loginfo file (see $CVSROOT/CVSROOT/loginfo).  To
set this up, create a loginfo entry that looks something like this:

    mymodule /path/to/this/script %%s some-email-addr@your.domain

In this example, whenever a checkin that matches `mymodule' is made, this
script is invoked, which will generate the diff containing email, and send it
to some-email-addr@your.domain.

    Note: This module used to also do repository synchronizations via
    rsync-over-ssh, but since the repository has been moved to SourceForge,
    this is no longer necessary.  The syncing functionality has been ripped
    out in the 3.0, which simplifies it considerably.  Access the 2.x versions
    to refer to this functionality.  Because of this, the script is misnamed.

It no longer makes sense to run this script from the command line.  Doing so
will only print out this usage information.

Usage:

    %(PROGRAM)s [options] <%%S> email-addr [email-addr ...]

Where options are:

    --cvsroot=<path>
        Use <path> as the environment variable CVSROOT.  Otherwise this
        variable must exist in the environment.

    --context=#
    -C #
        Include # lines of context around lines that differ (default: 2).

    -c
        Produce a context diff (default).

    -m hostname
    --mailhost hostname
        The hostname of an available SMTP server.  The default is
        'localhost'.

    -u
        Produce a unified diff (smaller).

    -S TEXT
    --subject-prefix=TEXT
        Prepend TEXT to the email subject line.

    -R ADDR
    --reply-to=ADDR
      Add a "Reply-To: ADDR" header to the email message.

    --quiet / -q
        Don't print as much status to stdout.

    --fromhost=hostname
    -f hostname
        The hostname that email messages appear to be coming from.  The From:
        header of the outgoing message will look like user@hostname.  By
        default, hostname is the machine's fully qualified domain name.

    --help / -h
        Print this text.

The rest of the command line arguments are:

    <%%S>
        CVS %%s loginfo expansion.  When invoked by CVS, this will be a single
        string containing the directory the checkin is being made in, relative
        to $CVSROOT, followed by the list of files that are changing.  If the
        %%s in the loginfo file is %%{sVv}, context diffs for each of the
        modified files are included in any email messages that are generated.

    email-addrs
        At least one email address.
"""
__version__ = '1.2'

import os
import sys
import re
import time
import string
import getopt
import smtplib
import pwd
import socket

try:
    from socket import getfqdn
except ImportError:
    def getfqdn():
        # Python 1.5.2 :(
        hostname = socket.gethostname()
        byaddr = socket.gethostbyaddr(socket.gethostbyname(hostname))
        aliases = byaddr[1]
        aliases.insert(0, byaddr[0])
        aliases.insert(0, hostname)
        for fqdn in aliases:
            if '.' in fqdn:
                break
        else:
            fqdn = 'localhost.localdomain'
        return fqdn


from cStringIO import StringIO

# Which SMTP server to do we connect to?
MAILHOST = 'localhost'
MAILPORT = 25

# Diff trimming stuff
DIFF_HEAD_LINES = 20
DIFF_TAIL_LINES = 20
DIFF_TRUNCATE_IF_LARGER = 1000

COMMASPACE = ', '

PROGRAM = sys.argv[0]

BINARY_EXPLANATION_LINES = [
    "(This appears to be a binary file; contents omitted.)\n"
    ]

NOVERSION = "Couldn't generate diff; no version number found for file: %s"
BACKSLASH = "Couldn't generate diff: backslash in filespec's filename: %s"



def usage(code, msg=''):
    print __doc__ % globals()
    if msg:
        print msg
    sys.exit(code)



def calculate_diff(entry, contextlines):
    file = entry.name
    oldrev = entry.revision
    newrev = entry.new_revision

    # Make sure we can find a CVS version number
    if oldrev is None and newrev is None:
        return NOVERSION % file

    if string.find(file, "'") <> -1:
        # Those crazy users put single-quotes in their file names!  Now we
        # have to escape everything that is meaningful inside double-quotes.
        filestr = string.replace(file, '\\', '\\\\')
        filestr = string.replace(filestr, '`', '\`')
        filestr = string.replace(filestr, '"', '\"')
        filestr = string.replace(filestr, '$', '\$')
        # and quote it with double-quotes.
        filestr = '"' + filestr + '"'
    else:
        # quote it with single-quotes.
        filestr = "'" + file + "'"
    if oldrev is None:
        # File is being added.
        try:
            if os.path.exists(file):
                fp = open(file)
            else:
                update_cmd = "cvs -fn update -r %s -p %s" % (newrev, filestr)
                fp = os.popen(update_cmd)
            lines = fp.readlines()
            fp.close()
            # Is this a binary file?  Let's look at the first few
            # lines to figure it out:
            for line in lines[:5]:
                for c in string.rstrip(line):
                    if c in string.whitespace:
                        continue
                    if c < ' ' or c > chr(127):
                        lines = BINARY_EXPLANATION_LINES[:]
                        break
            lines.insert(0, '--- NEW FILE: %s ---\n' % file)
        except IOError, e:
            lines = ['***** Error reading new file: ',
                     str(e), '\n***** file: ', file, ' cwd: ', os.getcwd()]
    elif newrev is None:
        lines = ['--- %s DELETED ---\n' % file]
    else:
        # File has been changed.
        # This /has/ to happen in the background, otherwise we'll run into CVS
        # lock contention.  What a crock.
        if contextlines > 0:
            difftype = "-C " + str(contextlines)
        else:
            difftype = "-u"
        diffcmd = "/usr/bin/cvs -f diff -kk %s --minimal -r %s -r %s %s" \
                  % (difftype, oldrev, newrev, filestr)
        fp = os.popen(diffcmd)
        lines = fp.readlines()
        # ignore the error code, it always seems to be 1 :(
        fp.close()
    if len(lines) > DIFF_TRUNCATE_IF_LARGER:
        removedlines = len(lines) - DIFF_HEAD_LINES - DIFF_TAIL_LINES
        del lines[DIFF_HEAD_LINES:-DIFF_TAIL_LINES]
        lines.insert(DIFF_HEAD_LINES,
                     '[...%d lines suppressed...]\n' % removedlines)
    return string.join(lines, '')



rfc822_specials_re = re.compile(r'[\(\)\<\>\@\,\;\:\\\"\.\[\]]')

def quotename(name):
    if name and rfc822_specials_re.search(name):
        return '"%s"' % string.replace(name, '"', '\\"')
    else:
        return name



def blast_mail(subject, people, entries, contextlines, fromhost, replyto):
    # cannot wait for child process or that will cause parent to retain cvs
    # lock for too long.  Urg!
    if not os.fork():
        # in the child
        # give up the lock you cvs thang!
        time.sleep(2)
        # Create the smtp connection to the localhost
        conn = smtplib.SMTP()
        conn.connect(MAILHOST, MAILPORT)
        user = pwd.getpwuid(os.getuid())[0]
        name = string.split(pwd.getpwuid(os.getuid())[4], ',')[0]
        domain = fromhost or getfqdn()
        address = '%s@%s' % (user, domain)
        s = StringIO()
        sys.stdout = s
        datestamp = time.strftime('%a, %d %b %Y %H:%M:%S +0000',
                                  time.gmtime(time.time()))
        try:
            vars = {'address' : address,
                    'name'    : quotename(name),
                    'people'  : string.join(people, COMMASPACE),
                    'subject' : subject,
                    'version' : __version__,
                    'date'    : datestamp,
                    }
            print '''\
From: %(name)s <%(address)s>
To: %(people)s''' % vars
            if replyto:
                print 'Reply-To: %s' % replyto
            print '''\
Subject: %(subject)s
Date: %(date)s
X-Mailer: Python syncmail %(version)s <http://sf.net/projects/cvs-syncmail>
''' % vars
            s.write(sys.stdin.read())
            # append the diffs if available
            print
            for entry in entries:
                print calculate_diff(entry, contextlines)
        finally:
            sys.stdout = sys.__stdout__
        resp = conn.sendmail(address, people, s.getvalue())
        conn.close()
        os._exit(0)



class CVSEntry:
    def __init__(self, name, revision, timestamp, conflict, options, tagdate):
        self.name = name
        self.revision = revision
        self.timestamp = timestamp
        self.conflict = conflict
        self.options = options
        self.tagdate = tagdate

def get_entry(prefix, mapping, line, filename):
    line = string.strip(line)
    parts = string.split(line, "/")
    _, name, revision, timestamp, options, tagdate = parts
    key = namekey(prefix, name)
    try:
        entry = mapping[key]
    except KeyError:
        if revision == "0":
            revision = None
        if string.find(timestamp, "+") != -1:
            timestamp, conflict = tuple(string.split(timestamp, "+"))
        else:
            conflict = None
        entry = CVSEntry(key, revision, timestamp, conflict,
                         options, tagdate)
        mapping[key] = entry
    return entry

def namekey(prefix, name):
    if prefix:
        return os.path.join(prefix, name)
    else:
        return name

def load_change_info(prefix=None):
    if prefix is not None:
        entries_fn = os.path.join(prefix, "CVS", "Entries")
    else:
        entries_fn = os.path.join("CVS", "Entries")
    entries_log_fn = entries_fn + ".Log"
    mapping = {}
    f = open(entries_fn)
    while 1:
        line = f.readline()
        if not line:
            break
##        if string.strip(line) == "D":
##            continue
        # we could recurse down subdirs, except the Entries.Log files
        # we need haven't been written to the subdirs yet, so it
        # doesn't do us any good
##        if line[0] == "D":
##            name = string.split(line, "/")[1]
##            dirname = namekey(prefix, name)
##            if os.path.isdir(dirname):
##                m = load_change_info(dirname)
##                mapping.update(m)
        if line[0] == "/":
            # normal file
            get_entry(prefix, mapping, line, entries_fn)
        # else: bogus Entries line
    f.close()
    if os.path.isfile(entries_log_fn):
        f = open(entries_log_fn)
        while 1:
            line = f.readline()
            if not line:
                break
            if line[1:2] != ' ':
                # really old version of CVS
                break
            entry = get_entry(prefix, mapping, line[2:], entries_log_fn)
            parts = string.split(line, "/")[1:]
            if line[0] == "A":
                # adding a file
                entry.new_revision = parts[1]
            elif line[0] == "R":
                # removing a file
                entry.new_revision = None
        f.close()
    for entry in mapping.values():
        if not hasattr(entry, "new_revision"):
            print 'confused about file', entry.name, '-- ignoring'
            del mapping[entry.name]
    return mapping

def load_branch_name():
    tag_fn = os.path.join("CVS", "Tag")
    if os.path.isfile(tag_fn):
        f = open(tag_fn)
        line = string.strip(f.readline())
        f.close()
        if line[:1] == "T":
            return line[1:]
    return None

# scan args for options
def main():
    # XXX Should really move all the options to an object, just to
    # avoid threading so many positional args through everything.
    try:
        opts, args = getopt.getopt(
            sys.argv[1:], 'hC:cuS:R:qf:m:',
            ['fromhost=', 'context=', 'cvsroot=', 'mailhost=',
             'subject-prefix=', 'reply-to=',
             'help', 'quiet'])
    except getopt.error, msg:
        usage(1, msg)

    # parse the options
    contextlines = 2
    verbose = 1
    subject_prefix = ""
    replyto = None
    fromhost = None
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt == '--cvsroot':
            os.environ['CVSROOT'] = arg
        elif opt in ('-C', '--context'):
            contextlines = int(arg)
        elif opt == '-c':
            if contextlines <= 0:
                contextlines = 2
        elif opt == '-u':
            contextlines = 0
        elif opt in ('-S', '--subject-prefix'):
            subject_prefix = arg
        elif opt in ('-R', '--reply-to'):
            replyto = arg
        elif opt in ('-q', '--quiet'):
            verbose = 0
        elif opt in ('-f', '--fromhost'):
            fromhost = arg
        elif opt in ('-m', '--mailhost'):
            global MAILHOST
            MAILHOST = arg

    # What follows is the specification containing the files that were
    # modified.  The argument actually must be split, with the first component
    # containing the directory the checkin is being made in, relative to
    # $CVSROOT, followed by the list of files that are changing.
    if not args:
        usage(1, 'No CVS module specified')
    changes = load_change_info()
    branch = load_branch_name()
    subject = subject_prefix + args[0]
    specs = string.split(args[0])
    del args[0]

    # The remaining args should be the email addresses
    if not args:
        usage(1, 'No recipients specified')

    # Now do the mail command
    people = args

    if specs[-3:] == ['-', 'Imported', 'sources']:
        print 'Not sending email for imported sources.'
        return

    if verbose:
##        print 'Python version', sys.version
##        os.system("type python1.6; type python2;"
##                  " type python2.0; type python2.1; type python2.2;"
##                  " type rcsdiff; type rlog")
        print 'Mailing %s...' % string.join(people, COMMASPACE)
        print 'Generating notification message...'
    blast_mail(subject, people, changes.values(),
               contextlines, fromhost, replyto)
    if verbose:
        print 'Generating notification message... done.'



if __name__ == '__main__':
    main()
    sys.exit(0)

# The "taginfo" file is used to control pre-tag checks.
# The filter on the right is invoked with the following arguments:
#
# $1 -- tagname
# $2 -- operation "add" for tag, "mov" for tag -F, and "del" for tag -d
# $3 -- repository
# $4->  file revision [file revision ...]
#
# A non-zero exit of the filter program will cause the tag to be aborted.
#
# The first entry on a line is a regular expression which is tested
# against the directory that the change is being committed to, relative
# to the $CVSROOT.  For the first match that is found, then the remainder
# of the line is the name of the filter to run.
#
# If the repository name does not match any of the regular expressions in this
# file, the "DEFAULT" line is used, if it is specified.
#
# If the name "ALL" appears as a regular expression it is always used
# in addition to the first matching regex or "DEFAULT".

# The "verifymsg" file is used to allow verification of logging
# information.  It works best when a template (as specified in the
# rcsinfo file) is provided for the logging procedure.  Given a
# template with locations for, a bug-id number, a list of people who
# reviewed the code before it can be checked in, and an external
# process to catalog the differences that were code reviewed, the
# following test can be applied to the code:
#
#   Making sure that the entered bug-id number is correct.
#   Validating that the code that was reviewed is indeed the code being
#       checked in (using the bug-id number or a seperate review
#       number to identify this particular code set.).
#
# If any of the above test failed, then the commit would be aborted.
#
# Actions such as mailing a copy of the report to each reviewer are
# better handled by an entry in the loginfo file.
#
# One thing that should be noted is the the ALL keyword is not
# supported.  There can be only one entry that matches a given
# repository.