#!/bin/bash
#
# capture-site-content.sh - Pull the content a PXE server needs but neither
# the repo nor the MCL image import provides, into the gitignored USB payload,
# so a freshly installed server can build every image from the USB alone.
#
# Run on the build PC (not the server), with the imaging LAN reachable:
#   scripts/capture-site-content.sh                 show what would change
#   scripts/capture-site-content.sh --apply         pull it
#
# What it pulls (live path -> payload dir):
#   winpeapps/_shared/Applications/extra/        -> site-content/shared/Applications/extra/
#       Office, Adobe, OpenText, Java, fonts, Wi-Fi profile, print drivers,
#       Zscaler: every unattend installs from C:\Deploy\Applications\extra.
#       pxe-status/ is left out (the playbook deploys Send-ImagingStage.ps1).
#   winpeapps/<image>/Deploy/Applications/ top-level files (GE CA and Zscaler
#       certificates) and real folders (extra_engineering)
#                                                -> site-content/images/<image>/Applications/
#       Install-EngineeringLayer.ps1 is left out (repo playbook/engineering/).
#   the links each image keeps in Deploy/Applications (extra, BPRT)
#                                                -> site-content/links.txt
#   winpeapps/_shared/BIOS/*.exe + models.txt    -> bios-staging/
#       models.txt pairs each model with its file; the webapp's Dell update
#       rewrites it, so the live copy, not the repo's, matches the binaries.
#   www/win11/sources/boot.wim                   -> boot-files/boot.wim
#   www/blancco/<the files already in boot-tools/blancco/>
#                                                -> boot-tools/blancco/
#       only that known set: kexec-initrd, kmod, preferences.xml and the rest
#       are built by the playbook on the server.
#
# Not pulled, on purpose: BPRT (the first MCL import seeds it, plus our
# overlay from the repo), Operating Systems / Packages / drivers (the MCL
# import and Upload-Image.ps1 -IncludeDrivers bring those), Blancco reports,
# Clonezilla backups and imaging logs (records, not setup).
#
# Then it writes site-content/SHA256SUMS (the playbook checks it before it
# restores anything), and refuses content a FAT32 USB cannot hold: a file of
# 4 GiB or more, a name Windows rejects, or two names that differ only in case.
#
# Needs SSH key login as pxe on the server (files there are world-readable).
# Folders are mirrored (--delete): what the server no longer has goes from
# the payload too. Nothing on the server is changed.

set -euo pipefail

REPO_ROOT="$(cd "$(dirname "$0")"/.. && pwd)"
SERVER="172.16.9.1"
USER_="pxe"
PAYLOAD_ROOT="$REPO_ROOT"
APPLY=0

usage() {
    echo "Usage: $0 [--apply] [--server IP] [--user NAME] [--payload-root DIR]"
    echo "  Without --apply it only shows what would change."
}

while [ $# -gt 0 ]; do
    case "$1" in
        --apply) APPLY=1; shift ;;
        --server) SERVER="${2:?}"; shift 2 ;;
        --user) USER_="${2:?}"; shift 2 ;;
        --payload-root) PAYLOAD_ROOT="$(cd "${2:?}" && pwd)"; shift 2 ;;
        -h|--help) usage; exit 0 ;;
        *) usage; exit 1 ;;
    esac
done

SHARE="${CAPTURE_SHARE:-/srv/samba/winpeapps}"   # overridable for tests only
WWW="${CAPTURE_WWW:-/var/www/html}"
SITE="$PAYLOAD_ROOT/site-content"
BIOS="$PAYLOAD_ROOT/bios-staging"
BOOT_FILES="$PAYLOAD_ROOT/boot-files"
BLANCCO="$PAYLOAD_ROOT/boot-tools/blancco"
SSH_OPTS=(-o BatchMode=yes -o ConnectTimeout=10)
REMOTE="$USER_@$SERVER"

DRY=(-n)
[ "$APPLY" -eq 1 ] && DRY=()

# rsync -a over ssh. --checksum: the same size and time is not proof of the
# same content (a Blancco config.img differed that way). -L: a symlink in a
# pulled folder becomes its file (FAT32 has no links). Itemized, so the dry
# run lists every change.
pull() {
    rsync -aL --checksum --mkpath --delete --itemize-changes --human-readable --stats \
        -e "ssh ${SSH_OPTS[*]}" "${DRY[@]}" "$@" | summarize
}

# Itemized lines are noisy for 7 GB of Office; print counts and the first few.
summarize() {
    awk '
        /^[<>ch.*]/ || /^\*deleting/ { n++; if (n <= 8) print "      " $0; next }
        /^Number of (regular )?files transferred|^Total transferred file size|^Total file size/ { s = s "      " $0 "\n" }
        END { if (n > 8) printf "      ... %d changes in all\n", n; else if (n == 0) print "      (no changes)"; printf "%s", s }'
}

echo "Server : $REMOTE"
echo "Payload: $PAYLOAD_ROOT"
[ "$APPLY" -eq 1 ] && echo "Mode   : APPLY" || echo "Mode   : dry run (add --apply to pull)"
echo

ssh "${SSH_OPTS[@]}" "$REMOTE" true || { echo "ERROR: cannot ssh to $REMOTE (key login needed)" >&2; exit 1; }

# --- what the server has ------------------------------------------------------
# One remote listing: images with Deploy/Applications, and per image its
# top-level entries as "image<TAB>kind<TAB>name<TAB>link target".
LISTING=$(ssh "${SSH_OPTS[@]}" "$REMOTE" "
    cd '$SHARE' || exit 1
    for apps in */Deploy/Applications; do
        img=\${apps%%/*}
        case \"\$img\" in _*) continue ;; esac
        [ -d \"\$apps\" ] || continue
        for e in \"\$apps\"/* \"\$apps\"/.[!.]*; do
            [ -e \"\$e\" ] || [ -L \"\$e\" ] || continue
            n=\${e##*/}
            if [ -L \"\$e\" ]; then printf '%s\tlink\t%s\t%s\n' \"\$img\" \"\$n\" \"\$(readlink \"\$e\")\"
            elif [ -d \"\$e\" ]; then printf '%s\tdir\t%s\t\n' \"\$img\" \"\$n\"
            else printf '%s\tfile\t%s\t\n' \"\$img\" \"\$n\"; fi
        done
    done")

IMAGES=$(printf '%s\n' "$LISTING" | cut -f1 | sort -u | grep -v '^$' || true)
[ -n "$IMAGES" ] || { echo "ERROR: no image on $SERVER has Deploy/Applications" >&2; exit 1; }

# Links into _shared are recreated by the playbook. Anything else is reported.
LINKS=""
while IFS=$'\t' read -r img kind name target; do
    [ "$kind" = link ] || continue
    case "$target" in
        "$SHARE"/_shared/*) LINKS+="$img	$name	${target#"$SHARE"/}"$'\n' ;;
        *) echo "WARNING: $img/Deploy/Applications/$name links outside _shared ($target); not captured" ;;
    esac
done <<< "$LISTING"

# --- 1. _shared/Applications/extra -------------------------------------------
echo "[1/5] _shared/Applications/extra -> site-content/shared/Applications/extra/"
pull --exclude=/pxe-status/ "$REMOTE:$SHARE/_shared/Applications/extra/" "$SITE/shared/Applications/extra/"

# --- 2. per-image Applications content ---------------------------------------
echo "[2/5] per-image Deploy/Applications files and folders -> site-content/images/"
for img in $IMAGES; do
    names=$(printf '%s\n' "$LISTING" | awk -F'\t' -v i="$img" '$1 == i && ($2 == "file" || $2 == "dir") { print $3 }')
    # BPRT as a real folder is an old import's copy of the vendor folder: not ours.
    names=$(printf '%s\n' "$names" | grep -vix 'bprt' || true)
    if [ -z "$names" ]; then
        echo "    $img: nothing (links only)"
        [ "$APPLY" -eq 1 ] && rm -rf "$SITE/images/$img"
        continue
    fi
    echo "    $img: $(printf '%s\n' "$names" | tr '\n' ' ')"
    filter=()
    while IFS= read -r n; do
        [ -n "$n" ] && filter+=(--include="/$n" --include="/$n/***")
    done <<< "$names"
    pull --exclude=Install-EngineeringLayer.ps1 "${filter[@]}" --exclude='*' \
        --delete-excluded "$REMOTE:$SHARE/$img/Deploy/Applications/" "$SITE/images/$img/Applications/"
done

# --- 3. BIOS --------------------------------------------------------------------
echo "[3/5] _shared/BIOS (*.exe, models.txt) -> bios-staging/"
pull --include='/*.exe' --include=/models.txt --exclude='*' --delete-excluded \
    "$REMOTE:$SHARE/_shared/BIOS/" "$BIOS/"

# --- 4. boot.wim -----------------------------------------------------------------
echo "[4/5] win11/sources/boot.wim -> boot-files/boot.wim"
pull "$REMOTE:$WWW/win11/sources/boot.wim" "$BOOT_FILES/boot.wim"

# --- 5. Blancco (the known set only) ---------------------------------------------
echo "[5/5] blancco (files already in boot-tools/blancco/) -> boot-tools/blancco/"
if [ -d "$BLANCCO" ] && [ -n "$(ls -A "$BLANCCO")" ]; then
    filter=()
    for e in "$BLANCCO"/*; do
        n=${e##*/}
        filter+=(--include="/$n")
        [ -d "$e" ] && filter+=(--include="/$n/***")
    done
    pull "${filter[@]}" --exclude='*' "$REMOTE:$WWW/blancco/" "$BLANCCO/"
else
    echo "    SKIP: boot-tools/blancco/ is empty (run scripts/prepare-boot-tools.sh first)"
fi

if [ "$APPLY" -ne 1 ]; then
    echo
    echo "Dry run: nothing written. Re-run with --apply to pull."
    exit 0
fi

# --- links, checks, checksums ---------------------------------------------------
printf '# image<TAB>name in Deploy/Applications<TAB>link target under winpeapps/\n%s' "$LINKS" > "$SITE/links.txt"

echo
echo "Checking what a FAT32 USB can hold..."
BAD=0
BIG=$(find "$SITE" "$BIOS" "$BOOT_FILES/boot.wim" -type f -size +4194303k 2>/dev/null || true)
if [ -n "$BIG" ]; then
    echo "ERROR: files of 4 GiB or more (FAT32 cannot hold them):"; printf '%s\n' "$BIG" | sed 's/^/    /'; BAD=1
fi
ILLEGAL=$(cd "$SITE" && find . -name '*[<>:"|?*\\]*' 2>/dev/null || true)
if [ -n "$ILLEGAL" ]; then
    echo "ERROR: names Windows/FAT32 rejects:"; printf '%s\n' "$ILLEGAL" | sed 's/^/    /'; BAD=1
fi
CASE=$(cd "$SITE" && find . | sort -f | uniq -di || true)
if [ -n "$CASE" ]; then
    echo "ERROR: names that differ only in case (one would overwrite the other):"
    printf '%s\n' "$CASE" | sed 's/^/    /'; BAD=1
fi
[ "$BAD" -eq 0 ] || exit 1
echo "    ok"

echo "Writing site-content/SHA256SUMS..."
# Written beside site-content, not in it, so the list never names itself.
( cd "$SITE" && find . -type f ! -name SHA256SUMS -print0 | sort -z | xargs -0 sha256sum ) > "$PAYLOAD_ROOT/.site-content.SHA256SUMS.tmp"
mv "$PAYLOAD_ROOT/.site-content.SHA256SUMS.tmp" "$SITE/SHA256SUMS"

echo
echo "Summary:"
printf '    site-content/  %s, %s files\n' "$(du -sh "$SITE" | cut -f1)" "$(grep -c . "$SITE/SHA256SUMS")"
printf '    links.txt      %s links\n' "$(grep -vc '^#' "$SITE/links.txt" || true)"
printf '    bios-staging/  %s, %s .exe\n' "$(du -sh "$BIOS" | cut -f1)" "$(find "$BIOS" -name '*.exe' | wc -l)"
printf '    boot.wim       %s\n' "$(du -h "$BOOT_FILES/boot.wim" | cut -f1)"

# Files the repo tracks that the server has a different copy of: review and
# commit (or revert) before building the USB.
cd "$REPO_ROOT"
if [ "$PAYLOAD_ROOT" = "$REPO_ROOT" ] && ! git diff --quiet -- boot-tools/blancco/grub-blancco.cfg 2>/dev/null; then
    echo
    echo "NOTE: boot-tools/blancco/grub-blancco.cfg (tracked) now holds the server's copy:"
    git --no-pager diff --stat -- boot-tools/blancco/grub-blancco.cfg
fi
for f in check-bios.cmd hardware-report.ps1; do
    if ssh "${SSH_OPTS[@]}" "$REMOTE" "cat '$SHARE/_shared/BIOS/$f'" 2>/dev/null \
            | cmp -s - "playbook/shopfloor-setup/BIOS/$f"; then :; else
        echo "NOTE: the server's _shared/BIOS/$f differs from playbook/shopfloor-setup/BIOS/$f (the repo copy is installed)"
    fi
done
echo
echo "Done. Build the USB next (scripts/build-usb.sh copies site-content/)."