#!/bin/bash
#
# Copyright (c) 2007 Andy Parkins
#
# An example hook script to mail out commit update information.  This hook sends emails
# listing new revisions to the repository introduced by the change being reported.  The
# rule is that (for branch updates) each commit will appear on one email and one email
# only.
#
# This hook is stored in the contrib/hooks directory.  Your distribution will have put
# this somewhere standard.  You should make this script executable then link to it in
# the repository you would like to use it in.  For example, on debian the hook is stored
# in /usr/share/doc/git-core/contrib/hooks/post-receive-email:
#
#  chmod a+x post-receive-email
#  cd /path/to/your/repository.git
#  ln -sf /usr/share/doc/git-core/contrib/hooks/post-receive-email hooks/post-receive
#
# This hook script assumes it is enabled on the central repository of a project, with
# all users pushing only to it and not between each other.  It will still work if you
# don't operate in that style, but it would become possible for the email to be from
# someone other than the person doing the push.
#
# Config
# ------
# hooks.mailinglist
#   This is the list that all pushes will go to; leave it blank to not send
#   emails for every ref update.
# hooks.announcelist
#   This is the list that all pushes of annotated tags will go to.  Leave it
#   blank to default to the mailinglist field.  The announce emails lists the
#   short log summary of the changes since the last annotated tag.
# hook.envelopesender
#   If set then the -f option is passed to sendmail to allow the envelope sender
#   address to be set
#
# Notes
# -----
# All emails have their subjects prefixed with "[SCM]" to aid filtering.
# All emails include the headers "X-Git-Refname", "X-Git-Oldrev",
# "X-Git-Newrev", and "X-Git-Reftype" to enable fine tuned filtering and
# give information for debugging.
#

# ---------------------------- Functions

#
# Top level email generation function.  This decides what type of update
# this is and calls the appropriate body-generation routine after outputting
# the common header
#
# Note this function doesn't actually generate any email output, that is taken
# care of by the functions it calls:
#  - generate_email_header
#  - generate_create_XXXX_email
#  - generate_update_XXXX_email
#  - generate_delete_XXXX_email
#  - generate_email_footer
#
generate_email()
{
	# --- Arguments
	oldrev=$(git rev-parse $1)
	newrev=$(git rev-parse $2)
	refname="$3"

	# --- Interpret
	# 0000->1234 (create)
	# 1234->2345 (update)
	# 2345->0000 (delete)
	if expr "$oldrev" : '0*$' >/dev/null
	then
		change_type="create"
	else
		if expr "$newrev" : '0*$' >/dev/null
		then
			change_type="delete"
		else
			change_type="update"
		fi
	fi

	# --- Get the revision types
	newrev_type=$(git cat-file -t $newrev 2> /dev/null)
	oldrev_type=$(git cat-file -t "$oldrev" 2> /dev/null)
	case "$change_type" in
	create|update)
		rev="$newrev"
		rev_type="$newrev_type"
		;;
	delete)
		rev="$oldrev"
		rev_type="$oldrev_type"
		;;
	esac

	# The revision type tells us what type the commit is, combined with
	# the location of the ref we can decide between
	#  - working branch
	#  - tracking branch
	#  - unannoted tag
	#  - annotated tag
	case "$refname","$rev_type" in
		refs/tags/*,commit)
			# un-annotated tag
			refname_type="tag"
			short_refname=${refname##refs/tags/}
			;;
		refs/tags/*,tag)
			# annotated tag
			refname_type="annotated tag"
			short_refname=${refname##refs/tags/}
			# change recipients
			if [ -n "$announcerecipients" ]; then
				recipients="$announcerecipients"
			fi
			;;
		refs/heads/*,commit)
			# branch
			refname_type="branch"
			short_refname=${refname##refs/heads/}
			;;
		refs/remotes/*,commit)
			# tracking branch
			refname_type="tracking branch"
			short_refname=${refname##refs/remotes/}
			echo >&2 "*** Push-update of tracking branch, $refname"
			echo >&2 "***  - no email generated."
			exit 0
			;;
		*)
			# Anything else (is there anything else?)
			echo >&2 "*** Unknown type of update to $refname ($rev_type)"
			echo >&2 "***  - no email generated"
			exit 1
			;;
	esac

	# Check if we've got anyone to send to
	if [ -z "$recipients" ]; then
		echo >&2 "*** hooks.recipients is not set so no email will be sent"
		echo >&2 "*** for $refname update $oldrev->$newrev"
		exit 0
	fi

	# Call the correct body generation function
	fn_name=general
	case "$refname_type" in
	"tracking branch"|branch)
		fn_name=branch
		;;
	"annotated tag")
		fn_name=atag
		;;
	esac

	generate_email_header
	generate_${change_type}_${fn_name}_email
	generate_email_footer
}

generate_email_reply()
{
	rev="$1"
	revtype=$(git cat-file -t "$rev")

	subject=$revtype\ $(git show -s --pretty=format:'%h: %s' $rev)
	committer=$(git show -s --pretty=format:'%cn <%ce>' $rev)
	committeraddy=$(echo $committer | sed -ne 's/\(.*\) </"\1" </p')
	commitdate=$(git show -s --pretty=format:%aD $rev) # author date

	cat <<-EOF
	From: $committeraddy
	To: $recipients
	Subject: $EMAILPREFIX$subject
	X-Git-Refname: $refname
	X-Git-Newrev: $rev
	In-Reply-To: $parentid
	Date: $commitdate

	EOF

	git_diff_count()
	{
		git diff-tree --no-color --shortstat --find-copies-harder -l500 $@ |
			tail -1 | awk '{print $4+$6}'  # number of changed lines sum
	}
	lines=$(git_diff_count $rev)
	if [ -n "$lines" ] && [ "$lines" -gt 10 ]; then
		linesw=$(git_diff_count -w $rev)
	fi

	diffargs='--find-copies-harder --no-color --stat -l500'
	diffshow='-p'  # show full diff by default
	if [ -n "$linesw" ]; then
		if [ "$linesw" -gt 2000 ]; then
			# huge either way
			diffshow=  # no diff
		elif (( 100 * $linesw / $lines < ($lines > 100 ? 95 : 75) )); then
			# at least 25% size decrease (5% for larger changes)
			diffshow='-p -w'  # ignore whitespace
		fi
	fi

	git show $diffargs $diffshow $rev
	case "$diffshow" in
		'')
			echo
			echo "($lines lines were changed)";;
		'-p -w')
			linesw=$(($lines - $linesw))
			echo
			echo "(ignoring $linesw lines of whitespace changes)";;
	esac

	generate_email_footer
}

generate_email_header()
{
	# Capitalized var (the ugly way because I don't particularly care)
	case "$change_type" in
		update) change="update of";;
		*)      change=$change_type;;
	esac
	Change=$(perl -e 'print ucfirst for @ARGV' "$change")

	case "$fn_name" in
		branch)
			# Email parameters
			# The committer will be obtained from the latest existing rev; so
			# for a deletion it will be the oldrev, for the others, then newrev
			committer=$(git show --pretty=full -s $rev | sed -ne "s/^Commit: //p")
			# total statistics over everything
			stats=($(
				git diff-tree --no-color --numstat --find-copies-harder -l500 $oldrev..$newrev |
				awk '$3 {files++; add+=$1; del+=$2} END {print files, add, del}'
			))
			# Put additional details on the subject line if possible
			subject="$change $short_refname"
			if [ ${#stats[@]} -eq 3 ]; then
				stats0="${stats[0]} file"
				((${stats[0]} != 1)) && stats0=${stats0}s  # plural
				subject="$subject ($stats0 +${stats[1]}-${stats[2]})"
			fi
			;;
		atag)
			# Use git-for-each-ref to pull out the individual fields from the tag
			committer=$(git for-each-ref --format='%(taggername) %(taggeremail)' $refname)
			subject="$change tag $short_refname"
			;;
		*)
			subject="$change $refname_type $short_refname"
			;;
	esac

	committeraddy=$(echo $committer | sed -ne 's/\(.*\) </"\1" </p')
	committername=${committer/ <*}

	# --- Email (all stdout will be the email)
	# Generate header
	cat <<-EOF
	From: $committeraddy
	To: $recipients
	Subject: ${EMAILPREFIX}$subject
	X-Git-Refname: $refname
	X-Git-Reftype: $refname_type
	X-Git-Oldrev: $oldrev
	X-Git-Newrev: $newrev
	Message-ID: $parentid

	$Change $refname_type $short_refname by $committer:

	EOF
}

generate_email_footer()
{
	cat <<-EOF
	-- 
	$projectdesc hooks/post-receive
	EOF
}

# --------------- Branches

#
# Called for the creation of a branch
#
generate_create_branch_email()
{
	# This is a new branch and so oldrev is not valid
	echo "        at  $newrev ($newrev_type)"
	echo ""

	# This shows all log entries that are not already covered by
	# another ref - i.e. commits that are now accessible from this
	# ref that were previously not accessible (see generate_update_branch_email
	# for the explanation of this command)
	git rev-parse --not --branches | grep -v $(git rev-parse $refname) |
	git rev-list --pretty --stdin $newrev
}

#
# Called for the change of a pre-existing branch
#
generate_update_branch_email()
{
	# Consider this:
	#   1 --- 2 --- O --- X --- 3 --- 4 --- N
	#
	# O is $oldrev for $refname
	# N is $newrev for $refname
	# X is a revision pointed to by some other ref, for which we may
	#   assume that an email has already been generated.
	# In this case we want to issue an email containing only revisions
	# 3, 4, and N.  Given (almost) by
	#
	#  git-rev-list N ^O --not --all
	#
	# The reason for the "almost", is that the "--not --all" will take
	# precedence over the "N", and effectively will translate to
	#
	#  git-rev-list N ^O ^X ^N
	#
	# So, we need to build up the list more carefully.  git-rev-parse will
	# generate a list of revs that may be fed into git-rev-list.  We can get
	# it to make the "--not --all" part and then filter out the "^N" with:
	#
	#  git-rev-parse --not --all | grep -v N
	#
	# Then, using the --stdin switch to git-rev-list we have effectively
	# manufactured
	#
	#  git-rev-list N ^O ^X
	#
	# This leaves a problem when someone else updates the repository
	# while this script is running.  Their new value of the ref we're working
	# on would be included in the "--not --all" output; and as our $newrev
	# would be an ancestor of that commit, it would exclude all of our
	# commits.  What we really want is to exclude the current value of
	# $refname from the --not list, rather than N itself.  So:
	#
	#  git-rev-parse --not --all | grep -v $(git-rev-parse $refname)
	#
	# Get's us to something pretty safe (apart from the small time between
	# refname being read, and git-rev-parse running - for that, I give up)
	#
	#
	# Next problem, consider this:
	#   * --- B --- * --- O ($oldrev)
	#          \
	#           * --- X --- * --- N ($newrev)
	#
	# That is to say, there is no guarantee that oldrev is a strict subset of
	# newrev (it would have required a --force, but that's allowed).  So, we
	# can't simply say rev-list $oldrev..$newrev.  Instead we find the common
	# base of the two revs and list from there.
	#
	# As above, we need to take into account the presence of X; if another
	# branch is already in the repository and points at some of the revisions
	# that we are about to output - we don't want them.  The solution is as
	# before: git-rev-parse output filtered.
	#
	# Finally, tags:
	#   1 --- 2 --- O --- T --- 3 --- 4 --- N
	#
	# Tags pushed into the repository generate nice shortlog emails that
	# summarise the commits between them and the previous tag.  However,
	# those emails don't include the full commit messages that we output
	# for a branch update.  Therefore we still want to output revisions
	# that have been output on a tag email.
	#
	# Luckily, git-rev-parse includes just the tool.  Instead of using "--all"
	# we use "--branches"; this has the added benefit that "remotes/" will
	# be ignored as well.

	# List all of the revisions that were removed by this update, in a fast forward
	# update, this list will be empty, because rev-list O ^N is empty.  For a non
	# fast forward, O ^N is the list of removed revisions
	echo "from $oldrev_type $oldrev"

	rev=""
	for rev in $(git rev-list $newrev..$oldrev)
	do
		revtype=$(git cat-file -t "$rev")
		echo "discards $revtype $rev"
	done
	if [ -n "$rev" ]; then
		# This update added new revisions after undoing old revisions.  That is to"
		# say, the old revision is not a strict subset of the new revision.  This"
		# situation occurs when you --force push a change and generate a"
		# repository containing something like this:"
		#
		#  * -- * -- B -- O -- O -- O ($oldrev)"
		#             \\"
		#              N -- N -- N ($newrev)"
		#
		# When this happens we assume that you've already had alert emails for all"
		# of the O revisions, and so we here report only the revisions in the N"
		# branch from the common base, B."
		echo " (old revision is not a strict subset of $newrev)"
	fi

	# List all the revisions from baserev to newrev in a kind of
	# "table-of-contents"; note this list can include revisions that have
	# already had notification emails and is present to show the full detail
	# of the change from rolling back the old revision to the base revision and
	# then forward to the new revision
	git rev-list $oldrev..$newrev --reverse --pretty=format:'    %s'

	# XXX: Need a way of detecting whether git rev-list actually outputted
	# anything, so that we can issue a "no new revisions added by this
	# update" message

	# The diffstat is shown from the old revision to the new revision.  This
	# is to show the truth of what happened in this change.  There's no point
	# showing the stat from the base to the new revision because the base
	# is effectively a random revision at this point - the user will be
	# interested in what this revision changed - including the undoing of
	# previous revisions in the case of non-fast forward updates.
	echo
	echo "Summary of changes:"
	git diff-tree --no-color --stat --find-copies-harder -l500 $oldrev..$newrev
	echo
}

#
# Called for the deletion of a branch
#
generate_delete_branch_email()
{
	echo "       was  $oldrev"
	echo ""
	git show -s --pretty=oneline $oldrev
}

# --------------- Annotated tags

#
# Called for the creation of an annotated tag
#
generate_create_atag_email()
{
	echo "        at  $newrev ($newrev_type)"

	generate_atag_email
}

#
# Called for the update of an annotated tag (this is probably a rare event
# and may not even be allowed)
#
generate_update_atag_email()
{
	echo "        to  $newrev ($newrev_type)"
	echo "      from  $oldrev (which is now obsolete)"

	generate_atag_email
}

#
# Called when an annotated tag is created or changed
#
generate_atag_email()
{
	# Use git-for-each-ref to pull out the individual fields from the tag
	eval $(git for-each-ref --shell --format='
	tagobject=%(*objectname)
	tagtype=%(*objecttype)
	tagger=%(taggername)
	tagged=%(taggerdate)' $refname
	)

	echo "   tagging  $tagobject ($tagtype)"
	echo "        on  $tagged"
	case "$tagtype" in
	commit)
		# If the tagged object is a commit, then we assume this is a
		# release, and so we calculate which tag this tag is replacing
		prevtag=$(git describe --abbrev=0 $newrev^ 2>/dev/null)

		if [ -n "$prevtag" ]; then
			echo "  replaces  $prevtag"
		fi
		;;
	*)
		echo "    length  $(git cat-file -s $tagobject) bytes"
		;;
	esac

	echo ""

	# Show the content of the tag message; this might contain a change log
	# or release notes so is worth displaying.
	git cat-file tag $newrev | sed -e '1,/^$/d'

	echo ""
	case "$tagtype" in
	commit)
		# Only commit tags make sense to have rev-list operations performed
		# on them
		if [ -n "$prevtag" ]; then
			# Show changes since the previous release
			git rev-list --pretty=short "$prevtag..$newrev" | git shortlog
		else
			# No previous tag, show all the changes since time began
			git rev-list --pretty=short $newrev | git shortlog
		fi
		;;
	*)
		# XXX: Is there anything useful we can do for non-commit objects?
		;;
	esac
}

#
# Called for the deletion of an annotated tag
#
generate_delete_atag_email()
{
	echo "       was  $oldrev"
	echo ""
	git show -s --pretty=oneline $oldrev
}

# --------------- General references

#
# Called when any other type of reference is created (most likely a
# non-annotated tag)
#
generate_create_general_email()
{
	echo "        at  $newrev ($newrev_type)"

	generate_general_email
}

#
# Called when any other type of reference is updated (most likely a
# non-annotated tag)
#
generate_update_general_email()
{
	echo "        to  $newrev ($newrev_type)"
	echo "      from  $oldrev"

	generate_general_email
}

#
# Called for creation or update of any other type of reference
#
generate_general_email()
{
	# Unannotated tags are more about marking a point than releasing a version;
	# therefore we don't do the shortlog summary that we do for annotated tags
	# above - we simply show that the point has been marked, and print the log
	# message for the marked point for reference purposes
	#
	# Note this section also catches any other reference type (although there
	# aren't any) and deals with them in the same way.

	echo ""
	if [ "$newrev_type" = "commit" ]; then
		git show --no-color --root -s $newrev
	else
		# What can we do here?  The tag marks an object that is not a commit,
		# so there is no log for us to display.  It's probably not wise to
		# output git-cat-file as it could be a binary blob.  We'll just say how
		# big it is
		echo "$newrev is a $newrev_type, and is $(git cat-file -s $newrev) bytes long."
		echo
	fi
}

#
# Called for the deletion of any other type of reference
#
generate_delete_general_email()
{
	echo "       was  $oldrev"
	echo ""
	git show -s --pretty=oneline $oldrev
}

# ---------------------------- main()

# --- Constants
EMAILPREFIX="[SCM] "

# --- Config
# Set GIT_DIR either from the working directory, or from the environment
# variable.
GIT_DIR=$(git rev-parse --git-dir 2>/dev/null)
if [ -z "$GIT_DIR" ]; then
	echo >&2 "fatal: post-receive: GIT_DIR not set"
	exit 1
fi

projectdesc=$(head -1 "$GIT_DIR/description")
# Check if the description is unchanged from it's default, and shorten it to a
# more manageable length if it is
if expr "$projectdesc" : "Unnamed repository.*$" >/dev/null
then
	projectdesc="UNNAMED PROJECT"
else
	EMAILPREFIX="[$projectdesc] "
fi

recipients=$(git repo-config hooks.mailinglist)
announcerecipients=$(git repo-config hooks.announcelist)
envelopesender=$(git-repo-config hooks.envelopesender)

# --- Main loop
# Abort at first error in pipeline (i.e. don't send mail if generation failed).
set -o pipefail 2>/dev/null
# Allow dual mode: run from the command line just like the update hook, or if
# no arguments are given then run as a hook script
if [ -n "$1" -a -n "$2" -a -n "$3" ]; then
	# Output to the terminal in command line mode - if someone wanted to
	# resend an email; they could redirect the output to sendmail themselves
	PAGER= generate_email $2 $3 $1
else
	if [ -n "$envelopesender" ]; then
		envelopesender="-f -- $envelopesender"
	fi

	while read oldrev newrev refname
	do
		parentid="<$newrev-$$@$(cat /etc/mailname 2>/dev/null || hostname)>"
		generate_email $oldrev $newrev $refname |
		/usr/sbin/sendmail -t $envelopesender

#		if [ "$refname_type" == "branch" ]; then
#			if [ "$change_type" == "update" ]; then  #TODO: support other types as well
		for rev in $(
			git rev-parse --not --branches | grep -v $(git rev-parse $refname) |
			git rev-list --stdin $oldrev..$newrev | tac
		); do
			generate_email_reply $rev |
			/usr/sbin/sendmail -t $envelopesender
		done
#			fi
#		fi
	done
fi