mm3-hk-export/mm3-hk-export

#!/bin/sh
# mm3-hk-export: export a private HyperKitty (Mailman 3) list archive to an mbox.
#
# Usage:  mm3-hk-export [-z|--gzip] <list@domain> [output]
#
# Output is byte-for-byte what the web "Download" button produces (same
# Email.as_bytes() code path). With -z/--gzip the stream is gzip-compressed,
# matching the web download's .mbox.gz exactly (and ".gz" is appended to the
# output name if absent). If the list has no archived messages — including the
# case where HyperKitty never created a MailingList row for it — nothing is
# written and the script exits 0 with a notice.
#
# Runs the export through Debian's `mailman-web` wrapper, which executes the
# Django site as the correct web user. The mbox is created by that (privilege-
# dropped) user via tempfile.mkstemp (0600, race-free) and then moved into
# place by this script, which is expected to run as root.

set -eu

usage() {
    echo "usage: mm3-hk-export [-z|--gzip] <list@domain> [output]" >&2
}

GZIP=0
while [ $# -gt 0 ]; do
    case "$1" in
        -z|--gzip) GZIP=1; shift ;;
        -h|--help) usage; exit 0 ;;
        --)        shift; break ;;
        -*)        echo "mm3-hk-export: unknown option: $1" >&2; usage; exit 2 ;;
        *)         break ;;
    esac
done

if [ $# -lt 1 ]; then usage; exit 2; fi
addr="$1"
out="${2:-./${addr%@*}.mbox}"

if [ "$GZIP" -eq 1 ]; then
    gzip_py=True
    case "$out" in *.gz) ;; *) out="$out.gz" ;; esac
else
    gzip_py=False
fi

# Validate the address: this value is interpolated into a Python string
# literal below, so reject anything that isn't a plain localpart@domain.
if ! printf '%s' "$addr" | grep -Eq '^[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+$'; then
    echo "mm3-hk-export: invalid list address: $addr" >&2
    exit 2
fi

# Best-effort: ask Mailman *core* (via its REST API) for a list's archive_policy.
# Used only to explain why a list has no HyperKitty archive. Echoes the policy
# string (never|private|public) on success, nothing on any failure — it must
# never abort the export. REST root + credentials are read live from
# `mailman info` so no secrets are baked into this script.
core_archive_policy() {
    command -v curl            >/dev/null 2>&1 || return 0
    command -v mailman-wrapper >/dev/null 2>&1 || return 0
    info=$(mailman-wrapper info 2>/dev/null) || return 0
    root=$(printf '%s\n'  "$info" | sed -n 's/^REST root url: *//p')
    creds=$(printf '%s\n' "$info" | sed -n 's/^REST credentials: *//p')
    [ -n "$root" ] && [ -n "$creds" ] || return 0
    lid=$(printf '%s' "$1" | sed 's/@/./')
    curl -sf -u "$creds" "${root}lists/${lid}/config/archive_policy" 2>/dev/null \
        | sed -n 's/.*"archive_policy": *"\([^"]*\)".*/\1/p'
}

result=$(mailman-web shell <<EOF
import sys, os, tempfile, gzip
from hyperkitty.models import MailingList
addr = "$addr"
GZIP = $gzip_py
try:
    ml = MailingList.objects.get(name=addr)
except MailingList.DoesNotExist:
    # No HyperKitty row at all: list is not archived (archive_policy=never)
    # or no message has ever been archived for it.
    print("MM3HK|NONE|0")
    sys.exit(0)
n = ml.emails.count()
if n == 0:
    # Row exists but holds no messages.
    print("MM3HK|EMPTY|0")
    sys.exit(0)
fd, path = tempfile.mkstemp(prefix="mm3hk-", suffix=".mbox", dir="/var/tmp")
raw = os.fdopen(fd, "wb")
# mtime=0 keeps the gzip header deterministic (no timestamp), matching the
# web export, which uses a bare zlib gzip stream.
fh = gzip.GzipFile(fileobj=raw, mode="wb", mtime=0) if GZIP else raw
try:
    for e in ml.emails.order_by("archived_date").iterator():
        fh.write(e.as_bytes())
        fh.write(b"\n\n")
finally:
    if GZIP:
        fh.close()
    raw.close()
print("MM3HK|FILE|%d|%s" % (n, path))
EOF
)

line=$(printf '%s\n' "$result" | grep '^MM3HK|' | tail -n1 || true)
if [ -z "$line" ]; then
    echo "mm3-hk-export: unexpected output from mailman-web shell:" >&2
    printf '%s\n' "$result" >&2
    exit 1
fi

status=$(printf '%s' "$line" | cut -d'|' -f2)
count=$(printf '%s' "$line" | cut -d'|' -f3)

case "$status" in
    NONE)
        policy=$(core_archive_policy "$addr")
        case "$policy" in
            never)
                echo "mm3-hk-export: $addr is set not to archive (archive_policy=never); nothing to export." >&2
                ;;
            private|public)
                echo "mm3-hk-export: $addr archives (archive_policy=$policy) but nothing has been archived yet; nothing written." >&2
                ;;
            *)
                echo "mm3-hk-export: $addr has no HyperKitty archive (archiving disabled, or nothing ever archived); nothing written." >&2
                ;;
        esac
        ;;
    EMPTY)
        echo "mm3-hk-export: $addr has a HyperKitty archive but 0 messages — nothing written." >&2
        ;;
    FILE)
        path=$(printf '%s' "$line" | cut -d'|' -f4)
        mkdir -p "$(dirname "$out")"
        mv "$path" "$out"
        echo "mm3-hk-export: wrote $count messages to $out" >&2
        ;;
    *)
        echo "mm3-hk-export: unexpected status '$status'" >&2
        exit 1
        ;;
esac