#!/bin/bash

# Stalwart install hooks.
#
# Installing a mail server is not like installing any other app: the container
# starting successfully means almost nothing. Mail only works once DNS, reverse
# DNS and outbound port 25 are right, and every one of those lives OUTSIDE the
# box — at the registrar and the VPS provider. So the job of these hooks is to
# say plainly what still has to be done, with the actual values to enter, rather
# than reporting "installed" and leaving the admin to discover weeks later that
# their mail is landing in spam.

# Echo the admin credentials for the standard final-message block (word-split
# by the caller into positional args: user pass).
stalwart_install_message_data()
{
    printf '%s %s' "${CFG_STALWART_ADMIN_USER:-admin}" "${CFG_STALWART_ADMIN_PASSWORD_1:-}"
}

# Run the Stalwart CLI against our own container.
#
# The CLI is deliberately NOT in the server image — upstream split it into its
# own repository so it ships and versions separately. It does publish a
# multi-arch container, which suits us better than a host binary: nothing to
# install, nothing to clean up on uninstall, and arm64 works for Pi installs.
#
# `--network container:stalwart-service` borrows the server's network namespace,
# so the CLI reaches it on localhost:8080 without us having to resolve the
# LibrePortal network name or expose the admin port to get at it.
stalwart_cli()
{
    runFileOp docker run --rm -i --network "container:stalwart-service" \
        -e STALWART_URL="http://localhost:8080" \
        -e STALWART_USER="${CFG_STALWART_ADMIN_USER:-admin}" \
        -e STALWART_PASSWORD="${CFG_STALWART_ADMIN_PASSWORD_1:-}" \
        "ghcr.io/stalwartlabs/cli:${CFG_STALWART_CLI_VERSION:-1.0.12}" --no-color "$@"
}

# Resolve CFG_STALWART_MODE, turning 'auto' into a real answer.
#
# Traefik is the tell: LibrePortal only installs it once there is a domain
# pointed at this box, so its presence is a decent proxy for "this machine is
# meant to be reachable from the internet". Absent it, the safe reading is that
# nobody outside can reach this host anyway, and a public mail server would only
# produce mail that silently fails to deliver.
stalwart_mode()
{
    local mode="${CFG_STALWART_MODE:-auto}"
    if [[ "$mode" == "auto" ]]; then
        if [[ -d "${containers_dir}traefik" ]]; then mode="public"; else mode="private"; fi
    fi
    [[ "$mode" == "public" || "$mode" == "private" ]] || mode="private"
    printf '%s' "$mode"
}

# Rewrite the `access` field (4th, pipe-separated) of one port line, in BOTH
# places it has to change.
#
# sed rather than updateConfigOption because these values are themselves
# pipe-delimited, and the config-update path encodes `|` as %7C — round-tripping
# a port spec through it would mangle the very field we are editing.
#
# The second half is the part that is easy to miss: initializeAppVariables reads
# CFG_<APP>_PORT_n out of the SHELL, not off disk, and the compose file is built
# from what it parses. Editing only the file leaves the config claiming one thing
# while the running container does another.
stalwart_set_port_access()
{
    local cfg="$1" key="$2" access="$3"

    runFileOp sed -i -E "s#^(${key}=\"([^|\"]*\|){3})[^|\"]*#\1${access}#" "$cfg" 2>/dev/null

    local cur="${!key}"
    [[ -z "$cur" ]] && return 0
    printf -v "$key" '%s' "$(printf '%s' "$cur" | sed -E "s#^(([^|]*\|){3})[^|]*#\1${access}#")"
}

# Put the mail ports where the chosen mode says they belong.
#
# Private does NOT simply firewall everything off: port 25 is dropped entirely
# (nothing should be delivering mail here from outside), while the client ports
# stay bound to the host under `private`, so a mail client on the LAN — or over
# the tailnet, if Headscale is in play — still reaches its mailbox. That
# distinction is the whole point: private means "not on the internet", not
# "switched off".
stalwart_apply_port_access()
{
    local cfg="$1" mode="$2"
    local smtp client
    if [[ "$mode" == "private" ]]; then
        smtp="disabled"; client="private"
    else
        smtp="public";   client="public"
    fi

    stalwart_set_port_access "$cfg" "CFG_STALWART_PORT_2" "$smtp"     # 25   inbound mail
    stalwart_set_port_access "$cfg" "CFG_STALWART_PORT_3" "$client"   # 465  submissions
    stalwart_set_port_access "$cfg" "CFG_STALWART_PORT_4" "$client"   # 587  submission
    stalwart_set_port_access "$cfg" "CFG_STALWART_PORT_5" "$client"   # 993  imaps
}

# Runs after the deployed config exists but before the compose file is built
# from it — the only window where changing port exposure still reaches the
# running container.
stalwart_install_post_setup()
{
    local app_name="$1"
    local cfg="$containers_dir$app_name/$app_name.config"
    [[ -f "$cfg" ]] || return 0

    local mode; mode=$(stalwart_mode)

    # Write the resolved answer back, so the WebUI shows what this install
    # actually is instead of leaving the user to work out what 'auto' became.
    if [[ "${CFG_STALWART_MODE:-auto}" == "auto" ]]; then
        runFileOp sed -i -E "s#^CFG_STALWART_MODE=.*#CFG_STALWART_MODE=${mode}#" "$cfg" 2>/dev/null
        isNotice "Mail exposure not set explicitly — using '${mode}' (Traefik $([[ "$mode" == public ]] && echo present || echo absent))."
    fi

    stalwart_apply_port_access "$cfg" "$mode"

    # The port arrays were parsed from this config before this hook ran, and the
    # compose file is filled in from those arrays, not from the file we just
    # edited. Without re-reading, the access changes above are written to disk
    # and then quietly ignored — the config says port 25 is disabled while the
    # container publishes it anyway, which is the worst of both worlds.
    if declare -F initializeAppVariables >/dev/null 2>&1; then
        initializeAppVariables "$app_name" >/dev/null 2>&1
    fi

    if [[ "$mode" == "private" ]]; then
        isNotice "Private mail server: port 25 stays closed, mail clients reach it on the local network only."
    fi
}

# Status code for one path on the admin listener, empty if the container did
# not answer at all. Empty and a code are different answers — "no reply" is a
# container/exec problem, while a code means the server replied and said no.
#
# curl runs INSIDE the container so this works whatever the port mapping does:
# private mode unbinds ports from the host, and a probe aimed at the host would
# then fail for reasons that have nothing to do with the server's health.
stalwart_http_code()
{
    local path="$1" max_time="${2:-5}"
    runFileOp docker exec stalwart-service curl -fsS -o /dev/null -w '%{http_code}' \
        --max-time "$max_time" "http://localhost:8080${path}" 2>/dev/null | tr -d '\r'
}

# Wait for the admin HTTP listener. Used twice: once for the bootstrap listener
# before we configure anything, once for the real one after the restart.
#
# Takes a healthz probe NAME (live/ready), not a path — the two callers are both
# waiting on a health probe, and only a 200 ends the wait. Anything that needs a
# different path, or the code rather than a yes/no, wants stalwart_http_code.
stalwart_wait_http()
{
    local probe="$1" tries="${2:-40}" i code
    for ((i = 0; i < tries; i++)); do
        code=$(stalwart_http_code "/healthz/$probe" 3)
        [[ "$code" == "200" ]] && return 0
        sleep 2
    done
    return 1
}

# Fill in the first-run setup wizard instead of making the user do it.
#
# Out of the box Stalwart boots into "bootstrap mode" and waits for a human to
# answer five screens of questions in the WebUI: hostname, domain, which storage
# backend, which directory, where to log, how to handle DNS. LibrePortal already
# knows the answers to the ones that matter and the rest have sane defaults, so
# making the user answer them is asking a question we can answer ourselves.
#
# `Bootstrap` is a singleton object holding exactly those wizard fields, so the
# whole wizard is one `update`. Once it is set the server writes its config.json,
# provisions the domain, generates DKIM keys and leaves bootstrap mode — and the
# user's first sight of Stalwart is a configured mail server, not a form.
stalwart_install_provision()
{
    # config.json only exists once setup has completed, which makes it the
    # honest "is this already configured?" test. Re-running the installer over a
    # working server must not re-answer its setup questions.
    if runFileOp docker exec stalwart-service test -f /etc/stalwart/config.json 2>/dev/null; then
        isNotice "Stalwart is already configured — leaving its existing settings alone."
        return 0
    fi

    local mail_host="${host_setup:-}"
    local mail_domain="${mail_host#*.}"
    if [[ -z "$mail_host" || "$mail_host" != *.* ]]; then
        isError "No mail hostname is configured, so Stalwart cannot be set up automatically."
        isNotice "  Set a domain in the general config, then open the admin console to"
        isNotice "  complete setup by hand."
        return 1
    fi

    isNotice "Waiting for Stalwart's setup listener…"
    if ! stalwart_wait_http live; then
        isError "Stalwart did not open its setup listener — skipping automatic setup."
        return 1
    fi

    # requestTlsCertificate matters more than it looks. Traefik only fronts the
    # admin port; SMTP and IMAP (25/465/587/993) bypass it entirely, so Traefik's
    # certificate never reaches a mail client. Without this Stalwart serves a
    # self-signed cert on 993 and every mail client throws a warning.
    #
    # generateDkimKeys makes the server own DKIM: it creates an Ed25519 and an
    # RSA key, publishes both, and rotates them on a schedule. Hand-managed DKIM
    # keys are, in practice, keys that never get rotated.
    # A private server has no route to a publicly-trusted certificate — there is
    # no public name to validate — so asking for one only produces a failing
    # renewal loop. DKIM keys are generated either way: they cost nothing, and
    # having them already in place is what makes a later switch to public a
    # setting change rather than a key ceremony.
    local mode; mode=$(stalwart_mode)
    local want_cert=true
    [[ "$mode" == "private" ]] && want_cert=false

    # Public + Traefik + no DNS provider is a real dead end worth naming. Stalwart
    # validates over TLS-ALPN-01 (443) or HTTP-01 (80), and Traefik holds both, so
    # the only route left is DNS-01 — which needs the DNS provider integration.
    # Without it mail clients get a self-signed certificate on 993 and no amount
    # of waiting fixes it.
    if [[ "$mode" == "public" && -d "${containers_dir}traefik" \
          && ( "${CFG_STALWART_DNS_PROVIDER:-manual}" == "manual" || -z "${CFG_STALWART_DNS_API_TOKEN:-}" ) ]]; then
        isNotice "Traefik owns ports 80 and 443, so Stalwart cannot validate a certificate"
        isNotice "  for its mail ports on its own. Set CFG_STALWART_DNS_PROVIDER and a token"
        isNotice "  to validate over DNS instead, or mail clients will see a self-signed"
        isNotice "  certificate on port 993."
    fi

    isNotice "Configuring Stalwart for ${mail_domain} (${mode})…"
    local plan
    plan=$(printf '{"@type":"update","object":"Bootstrap","value":{"serverHostname":"%s","defaultDomain":"%s","generateDkimKeys":true,"requestTlsCertificate":%s}}' \
        "$mail_host" "$mail_domain" "$want_cert")

    # Keep the server's own error rather than swallowing it. The two that
    # actually happen say exactly what is wrong — a hostname under a TLD that
    # does not exist, or a data directory the server cannot write — and both are
    # unfixable guesswork without the message.
    local apply_out
    if ! apply_out=$(printf '%s\n' "$plan" | stalwart_cli apply --stdin 2>&1); then
        isError "Automatic setup failed — open the admin console to finish it by hand."
        local reason
        reason=$(printf '%s\n' "$apply_out" | grep -oE '(Invalid|Failed|Permission)[^|]*' | head -1)
        [[ -n "$reason" ]] && isNotice "  Stalwart said: ${reason% }"
        return 1
    fi

    # Leaving bootstrap mode needs a restart: the server swaps its temporary
    # setup listener for the real ones (SMTP, IMAP, submission) on the way back up.
    isNotice "Restarting Stalwart to bring up the mail services…"
    runFileOp docker restart stalwart-service >/dev/null 2>&1
    if ! stalwart_wait_http ready 60; then
        isError "Stalwart did not come back up after setup — check: docker logs stalwart-service"
        return 1
    fi

    isSuccessful "Stalwart configured: ${mail_domain} added, DKIM keys generated."

    stalwart_install_dns_provider
    stalwart_install_first_mailbox
    return 0
}

# Optionally hand DNS to the provider's API.
#
# This is the part that turns a page of records-to-paste into nothing at all:
# Stalwart writes MX, SPF, DKIM, DMARC, MTA-STS, TLS-RPT, SRV and CAA into the
# zone itself and keeps them in sync — including republishing DKIM records when
# it rotates the keys, which is the whole reason rotation is safe to automate.
#
# Off by default. It needs an API token with write access to the zone, stored in
# the mail server's database, which widens what a compromise of this box costs.
# Scope the token to the single zone if your provider supports it.
stalwart_install_dns_provider()
{
    local provider="${CFG_STALWART_DNS_PROVIDER:-manual}"
    [[ "$provider" == "manual" || -z "$provider" ]] && return 0
    # A private server publishes nothing: there is no public zone to keep in
    # sync, and handing a zone-write token to a box that never sends mail is
    # blast radius bought for nothing.
    [[ "$(stalwart_mode)" == "private" ]] && return 0

    if [[ -z "${CFG_STALWART_DNS_API_TOKEN:-}" ]]; then
        isError "CFG_STALWART_DNS_PROVIDER is set to '$provider' but no API token was given."
        isNotice "  Falling back to manual DNS — the records are printed below."
        return 0
    fi

    local mail_domain="${host_setup#*.}"
    # Verified against Cloudflare; DigitalOcean and DeSEC take the same
    # description+secret shape. Providers needing more than a token (Route 53,
    # Google Cloud DNS) are not wired up here — add them in the admin console.
    local plan
    plan=$(printf '{"@type":"upsert","object":"DnsServer","matchOn":["description"],"value":{"dns":{"@type":"%s","description":"LibrePortal managed DNS","secret":{"@type":"Value","secret":"%s"}}}}\n{"@type":"upsert","object":"Domain","matchOn":["name"],"value":{"dom":{"name":"%s","dnsManagement":{"@type":"Automatic","dnsServerId":"#dns"}}}}' \
        "$provider" "$CFG_STALWART_DNS_API_TOKEN" "$mail_domain")

    if printf '%s\n' "$plan" | stalwart_cli apply --stdin >/dev/null 2>&1; then
        isSuccessful "DNS records will be published and kept in sync via $provider."
    else
        isError "Could not enable automatic DNS via $provider — check the API token."
        isNotice "  Manual DNS is still in effect; the records are printed below."
    fi
}

# Create one real mailbox.
#
# Setup leaves you with admin@<domain>, which is an administrator account — using
# it as a day-to-day mailbox is the wrong habit to start someone on. More
# concretely: the generated zone file points DMARC and TLS-RPT reports at
# postmaster@<domain>, and nothing creates that address, so those reports would
# bounce. Creating it fixes a real gap and gives the user a mailbox to log into.
stalwart_install_first_mailbox()
{
    local mailbox="${CFG_STALWART_FIRST_MAILBOX:-postmaster}"
    [[ -z "$mailbox" ]] && return 0

    local mail_domain="${host_setup#*.}"
    local plan
    # The domain is upserted by name purely to get a reference to it — it already
    # exists, so this matches rather than creates. Credentials are a map keyed by
    # slot, not a list. Stalwart enforces password strength, so the password has
    # to be a generated one, not a short hand-picked string.
    plan=$(printf '{"@type":"upsert","object":"Domain","matchOn":["name"],"value":{"dom":{"name":"%s"}}}\n{"@type":"upsert","object":"Account","matchOn":["name"],"value":{"acc":{"@type":"User","name":"%s","domainId":"#dom","description":"First mailbox","credentials":{"0":{"@type":"Password","secret":"%s"}}}}}' \
        "$mail_domain" "$mailbox" "${CFG_STALWART_FIRST_MAILBOX_PASSWORD_1:-}")

    if printf '%s\n' "$plan" | stalwart_cli apply --stdin >/dev/null 2>&1; then
        isSuccessful "Created the first mailbox: ${mailbox}@${mail_domain}"
    else
        isError "Could not create ${mailbox}@${mail_domain} — add it in the admin console."
    fi
}

stalwart_install_post_start()
{
    local app_name="$1"

    ((menu_number++))
    echo ""
    local mode; mode=$(stalwart_mode)
    if [[ "$mode" == "private" ]]; then
        echo "---- $menu_number. Setting up your private mail + calendar server"
    else
        echo "---- $menu_number. Mail server checks + the DNS records you still need"
    fi
    echo ""

    # Resolved admin port comes from the compose tag (format `external:internal`),
    # the same source adguard's hook reads — the legacy $usedport1 isn't populated
    # by the current install pipeline.
    local compose_file="$containers_dir$app_name/docker-compose.yml"
    local admin_pair admin_port
    admin_pair=$(tagsManagerGetTagContent "$compose_file" "PORTS_TAG_1" 2>/dev/null)
    admin_port="${admin_pair%%:*}"

    # ---- 1. Answer the setup wizard on the user's behalf ------------------
    stalwart_install_provision

    # ---- 2 + 3. Internet-mail prerequisites ------------------------------
    # Both of these are about exchanging mail with the outside world, so both
    # are noise on a private server — worse than noise, since a red ERROR about
    # port 25 on a server that is deliberately not on the internet reads as a
    # broken install and sends people chasing a problem they do not have.
    if [[ "$mode" == "public" ]]; then
        # Most cheap VPS providers block outbound 25 by default (and several only
        # unblock on request). A blocked port 25 means no mail EVER leaves the box,
        # and nothing in the WebUI would otherwise reveal it.
        isNotice "Checking outbound port 25 (required to deliver mail to other servers)…"
        if command -v timeout >/dev/null 2>&1 \
           && timeout 8 bash -c 'exec 3<>/dev/tcp/gmail-smtp-in.l.google.com/25' 2>/dev/null; then
            isSuccessful "Outbound port 25 is open."
        else
            isError "Outbound port 25 appears BLOCKED or filtered on this host."
            isNotice "  Most VPS providers block it by default. Ask your provider to unblock"
            isNotice "  outbound 25, or mail will queue and never deliver."
            isNotice "  If you did not mean to run an internet mail server, switch this app"
            isNotice "  to private in its Tools tab — none of this applies there."
        fi

        # Receiving servers check that the sending IP resolves back to a name. A
        # generic provider PTR (e.g. static.1.2.3.4.provider.net) is a common reason
        # for mail being junked, and it can only be fixed in the provider's panel.
        if [[ -n "$public_ip_v4" ]] && command -v dig >/dev/null 2>&1; then
            local ptr; ptr=$(dig +short -x "$public_ip_v4" 2>/dev/null | head -1)
            if [[ -n "$ptr" ]]; then
                isNotice "Reverse DNS (PTR) for $public_ip_v4 is: ${ptr%.}"
                isNotice "  It should match your mail hostname. Set it in your VPS provider's panel."
            else
                isError "No reverse DNS (PTR) record for $public_ip_v4 — set one at your VPS provider."
            fi
        fi
    fi

    # ---- 4. Is the admin console actually there? -------------------------
    # Stalwart v0.16 does not ship the WebUI inside the Docker image: the admin
    # console is a single-page app the server fetches from GitHub on first
    # start. If this host had no outbound HTTPS at that moment the download
    # silently fails, the server still comes up healthy, and /admin and
    # /account answer 404 forever with nothing to explain why. Checking it here
    # turns "the panel is broken" into a one-line, fixable cause.
    isNotice "Checking the admin console (WebUI) responds…"
    local admin_code
    admin_code=$(stalwart_http_code /admin)
    if [[ "$admin_code" == "404" ]]; then
        isError "The admin console is missing (/admin returns 404)."
        isNotice "  Stalwart does not bundle the WebUI — it downloads it from"
        isNotice "  https://github.com/stalwartlabs/webui/releases/latest on first start."
        isNotice "  That download failed, so /admin and /account will 404 until it succeeds."
        isNotice "  Allow outbound HTTPS to github.com from this host, then restart the"
        isNotice "  container: docker restart stalwart-service"
        isNotice "  The mail server itself is unaffected — only the web interface is."
    elif [[ -z "$admin_code" ]]; then
        isError "Could not probe the admin console (no response from the container)."
    else
        isSuccessful "Admin console is being served (HTTP $admin_code)."
    fi

    # ---- 5. The records that still have to be published -------------------
    # Read back from the server rather than composed here. Stalwart keeps the
    # domain's full record set in `dnsZoneFile`, so this prints what it actually
    # expects — MX, SPF, DMARC, MTA-STS, TLS-RPT, the SRV records clients use to
    # autoconfigure, and crucially the real DKIM public keys. The old version of
    # this hook had to tell the user to go and fetch DKIM themselves; by this
    # point the keys exist, so there is nothing left to look up.
    local mail_host="${host_setup:-your-mail-hostname}"
    local mail_domain="${mail_host#*.}"

    if [[ "$mode" == "private" ]]; then
        # Nothing to publish, so say what the user actually has instead — the
        # honest headline is that everything below works today, with no DNS,
        # no registrar and no waiting.
        echo ""
        isNotice "Nothing to add at a registrar — this server is not on the internet."
        isNotice "What you have, working now, on your local network:"
        echo "    Mail between local accounts, IMAP on 993, submission on 465/587"
        echo "    Calendars (CalDAV) and contacts (CardDAV)"
        echo ""
        isNotice "Point mail and calendar clients at:  ${mail_host}"
        isNotice "  Certificates are self-signed, so clients will ask you to trust it once."
        [[ -d "${containers_dir}headscale" ]] && \
            isNotice "  Headscale is installed, so this also reaches you from anywhere on your tailnet."
        echo ""
        isNotice "To exchange mail with the internet later, switch this app to public"
        isNotice "  in its Tools tab. DKIM keys are already generated, so nothing is lost."
        echo ""
    elif [[ "${CFG_STALWART_DNS_PROVIDER:-manual}" != "manual" && -n "${CFG_STALWART_DNS_API_TOKEN:-}" ]]; then
        isNotice "DNS is managed automatically — no records to add by hand."
        isNotice "  Still set at your provider, because they are not in the zone:"
        echo "    A      ${mail_host}   ${public_ip_v4:-<the IP of this server>}"
        echo "    PTR    ${public_ip_v4:-<the IP of this server>}   ${mail_host}"
    else
        local domain_id zone
        domain_id=$(stalwart_cli query Domain 2>/dev/null | awk 'NR==2{print $1}')
        if [[ -n "$domain_id" ]]; then
            zone=$(stalwart_cli get Domain "$domain_id" 2>/dev/null \
                | sed -n '/DNS Zone File:/,$p' | sed 's/^ *DNS Zone File: *//')
        fi

        echo ""
        if [[ -n "$zone" ]]; then
            isNotice "DNS records to add at your domain registrar:"
            echo "    A    ${mail_host}    ${public_ip_v4:-<the IP of this server>}"
            echo ""
            printf '%s\n' "$zone" | sed 's/^/    /'
        else
            # Setup did not complete, so there is no zone to read. Say what is
            # needed rather than printing nothing.
            isNotice "DNS records to add at your domain registrar:"
            echo "    MX     @              10 ${mail_host}"
            echo "    A      ${mail_host}   ${public_ip_v4:-<the IP of this server>}"
            echo "    TXT    @              \"v=spf1 mx -all\""
            echo "    TXT    _dmarc         \"v=DMARC1; p=quarantine; rua=mailto:postmaster@${mail_domain}\""
            isNotice "  DKIM records are shown in the admin console under your domain."
        fi
        echo ""
    fi

    # ---- 6. Where to go next ---------------------------------------------
    if [[ -n "$admin_port" ]]; then
        isNotice "Admin console (server settings, domains, queue, reports):"
        [[ -n "$public_ip_v4" ]] && echo "    http://$public_ip_v4:$admin_port/admin"
        isNotice "Mailbox settings for everyday users (password, filters, autoresponder):"
        [[ -n "$public_ip_v4" ]] && echo "    http://$public_ip_v4:$admin_port/account"
        echo ""
        isNotice "Sign in as '${CFG_STALWART_ADMIN_USER:-admin}' with the password shown below."
    fi

    if [[ "$mode" == "public" ]]; then
        isNotice "Until MX, PTR, SPF, DKIM and DMARC are all in place, expect delivery"
        isNotice "problems — that is normal for a new mail server, not a fault in the app."
        isNotice "Even once they are, large providers distrust a brand-new sending IP for"
        isNotice "a while. That part is reputation, not configuration, and it takes time."
    fi
}