#!/bin/bash
# build_site.sh — pull the images the docs reference from the artifact registry
# (if not already present locally), stage them under docs/assets/, then build
# the MkDocs site. The built site/ output is what gets pushed to gitea-pages —
# never the source images themselves (see scripts/artifacts/push_artifacts.sh).
set -euo pipefail

REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
cd "$REPO_ROOT"

ASSETS_DIR="docs/assets/images"
mkdir -p "$ASSETS_DIR"

# Frames referenced by docs/model-bakeoff.md. Pull the film's montage
# frames from the registry if this machine doesn't already have them locally.
FRAMES_ROOT="experiments/results/holdout/frames"
if [ ! -d "$FRAMES_ROOT/many_saints" ] || [ ! -d "$FRAMES_ROOT/downton_abbey" ]; then
    echo "==> pulling montage frames (not found locally)..."
    scripts/artifacts/pull_artifacts.sh montage-frames Many_Saints_of_Newark || true
    scripts/artifacts/pull_artifacts.sh montage-frames Downton_Abbey__A_New_Era || true
fi

echo "==> staging referenced frames into ${ASSETS_DIR}"
cp -v "${FRAMES_ROOT}/many_saints/fpi/fpi_t03543.jpg" \
      "${ASSETS_DIR}/many_saints_ghost_fpi.jpg"
cp -v "${FRAMES_ROOT}/downton_abbey/best/best_t00127.jpg" \
      "${ASSETS_DIR}/downton_wedding_19_correct.jpg"
if [ -f "${FRAMES_ROOT}/many_saints_intervals/w002_worst/w002_worst_t01382.jpg" ]; then
    cp -v "${FRAMES_ROOT}/many_saints_intervals/w002_worst/w002_worst_t01382.jpg" \
          "${ASSETS_DIR}/many_saints_ghosts_vs_unknowns.jpg"
else
    echo "WARN: many_saints_intervals frames not present; keeping existing" \
         "${ASSETS_DIR}/many_saints_ghosts_vs_unknowns.jpg (if any)"
fi

if [ ! -f "${ASSETS_DIR}/germar_beats_xray.jpg" ]; then
    echo "==> pulling report-highlights/germar_beats_xray.jpg..."
    scripts/artifacts/pull_artifacts.sh report-highlights germar_beats_xray.jpg
fi

if [ ! -f "${ASSETS_DIR}/readme_example.jpg" ]; then
    echo "==> pulling report-highlights/readme_example.jpg..."
    scripts/artifacts/pull_artifacts.sh report-highlights readme_example.jpg
fi

# pipeline_topology.svg is small and hand-authored (not pulled from anywhere) —
# committed directly at docs/assets/images/, not staged from the registry.

if [ ! -d experiments/galleries ] || [ -z "$(ls -A experiments/galleries 2>/dev/null)" ]; then
    echo "==> pulling galleries (not found locally)..."
    scripts/artifacts/pull_artifacts.sh galleries
fi

echo "==> generating calibration curve chart"
python3 scripts/docs/calibration_chart.py --out "${ASSETS_DIR}/calibration_curves.png"

echo "==> generating experiment charts (16-combo ranking, DE landscape, held-out F1, ghost timeline)"
python3 scripts/docs/experiment_charts.py --out-dir "${ASSETS_DIR}"

echo "==> building site"
mkdocs build

# -- commit-pinned repo links -------------------------------------------------
# Docs reference repo files via the placeholder hosts https://REPOLINK/<path>
# (this repo) and https://KPNLINK/<path> (the KPN++ submodule). Substitute them
# with raw URLs pinned to the exact commit being published, and fail the build
# if any linked path doesn't actually exist at that commit — no dead links.
HEAD_SHA="$(git rev-parse HEAD)"
KPN_SHA="$(git rev-parse HEAD:external/KPN)"
REPO_RAW="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/${HEAD_SHA}"
KPN_RAW="https://gitea.tourolle.paris/dtourolle/KPN/raw/commit/${KPN_SHA}"

if [ -n "$(git status --porcelain -- docs scripts src experiments)" ]; then
    echo "WARN: working tree is dirty — commit-pinned links will point at ${HEAD_SHA}," >&2
    echo "      which may not contain your latest changes. Commit before deploying." >&2
fi

echo "==> verifying repo-linked paths exist at ${HEAD_SHA}"
missing=0
for p in $(grep -rhoE 'https://REPOLINK/[A-Za-z0-9_./-]+' docs/*.md | sed 's|https://REPOLINK/||' | sort -u); do
    if ! git cat-file -e "HEAD:${p}" 2>/dev/null; then
        echo "error: docs link to '${p}', which does not exist at HEAD" >&2
        missing=1
    fi
done
[ "$missing" -eq 0 ] || exit 1

echo "==> pinning repo links to ${HEAD_SHA} (KPN: ${KPN_SHA})"
find site -name '*.html' -exec \
    sed -i "s|https://REPOLINK|${REPO_RAW}|g; s|https://KPNLINK|${KPN_RAW}|g" {} +

if grep -rq 'REPOLINK\|KPNLINK' site; then
    echo "error: unsubstituted REPOLINK/KPNLINK placeholder left in site/" >&2
    exit 1
fi

echo "==> done. site/ is ready to deploy to the gitea-pages branch."