fn_registry/bash/functions/pipelines/init_paper.sh

#!/usr/bin/env bash
# init_paper
# ----------
# Scaffold de un paper académico reproducible en papers/<NNNN-slug>/.
#
# Calcula el siguiente número incremental escaneando papers/, crea el
# directorio con todas las subcarpetas (experiments data figures reviews out),
# copia las plantillas paper.md + preregistration.md rellenando el frontmatter
# (title, slug, date de hoy, phase=question, status=draft) y crea references.md.
#
# NO hace `git init`: el paper arranca en fase interna local (papers/ está
# gitignored en el repo padre, solo .gitkeep se versiona). La promoción a
# sub-repo Gitea (fase publishable) es un paso posterior MANUAL.
#
# Compone: next_numbered_dir (helper de numeración del registry) +
#          slugify_ascii (slug ASCII del registry).
#
# USO:
#   ./init_paper.sh <slug> [--title "..."] [--domain <d>] [--tags a,b,c]
#
# EJEMPLOS:
#   ./init_paper.sh mi-primer-paper --title "Mi primer paper"
#   ./init_paper.sh reactive-loop-calls --domain datascience --tags registry,telemetria

set -euo pipefail

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

# Funciones atómicas del registry
source "$REGISTRY_ROOT/bash/functions/io/next_numbered_dir.sh"

# ── Parsing de argumentos ────────────────────────────────────

SLUG_RAW=""
TITLE=""
DOMAIN="datascience"
TAGS=""

while [ $# -gt 0 ]; do
    case "$1" in
        --title)
            TITLE="$2"; shift 2 ;;
        --domain)
            DOMAIN="$2"; shift 2 ;;
        --tags)
            TAGS="$2"; shift 2 ;;
        -h|--help)
            grep "^#" "$0" | sed 's/^# \?//' ; exit 0 ;;
        -*)
            echo "Flag desconocido: $1" >&2 ; exit 1 ;;
        *)
            if [ -z "$SLUG_RAW" ]; then
                SLUG_RAW="$1"
            else
                echo "ERROR: argumento posicional inesperado: '$1' (solo se admite un <slug>)." >&2
                exit 1
            fi
            shift ;;
    esac
done

if [ -z "$SLUG_RAW" ]; then
    echo "ERROR: falta el argumento <slug>." >&2
    echo "Uso: $0 <slug> [--title \"...\"] [--domain <d>] [--tags a,b,c]" >&2
    echo "  Ejemplo: $0 mi-primer-paper --title \"Mi primer paper\"" >&2
    exit 1
fi

# ── Slugificar (reutiliza slugify_ascii del registry; solo stdlib) ──

PYBIN="$REGISTRY_ROOT/python/.venv/bin/python3"
[ -x "$PYBIN" ] || PYBIN="$(command -v python3 || true)"
if [ -z "$PYBIN" ]; then
    echo "ERROR: no se encontró python3 para slugificar el slug." >&2
    exit 1
fi

SLUG_CLEAN=$("$PYBIN" -c '
import sys, os
sys.path.insert(0, os.path.join(sys.argv[2], "python", "functions"))
from core.slugify_ascii import slugify_ascii
print(slugify_ascii(sys.argv[1], default="paper"))
' "$SLUG_RAW" "$REGISTRY_ROOT")

# ── Resolver número incremental y directorio destino ─────────

PAPERS_DIR="$REGISTRY_ROOT/papers"
mkdir -p "$PAPERS_DIR"

NUM=$(next_numbered_dir "$PAPERS_DIR")
SLUG_FULL="${NUM}-${SLUG_CLEAN}"
PAPER_DIR="$PAPERS_DIR/$SLUG_FULL"

if [ -d "$PAPER_DIR" ]; then
    echo "ERROR: el directorio del paper ya existe: $PAPER_DIR" >&2
    exit 1
fi

TODAY=$(date +%Y-%m-%d)
[ -n "$TITLE" ] || TITLE="$SLUG_CLEAN"

TAGS_YAML="[]"
if [ -n "$TAGS" ]; then
    TAGS_YAML="[$(echo "$TAGS" | sed 's/,/, /g')]"
fi

echo ""
echo "════════════════════════════════════════════════════════════"
echo "  INIT PAPER: ${SLUG_FULL}"
echo "  Título:     ${TITLE}"
echo "  Directorio: ${PAPER_DIR}"
echo "════════════════════════════════════════════════════════════"
echo ""

# ── Crear estructura ─────────────────────────────────────────

echo "[1/3] Creando estructura..."
mkdir -p "$PAPER_DIR"/experiments "$PAPER_DIR"/data "$PAPER_DIR"/figures \
         "$PAPER_DIR"/reviews "$PAPER_DIR"/out
echo "  experiments/ data/ figures/ reviews/ out/"

# ── Copiar plantillas + rellenar frontmatter ─────────────────

echo "[2/3] Escribiendo paper.md + preregistration.md..."

# Escapa caracteres especiales del RHS de sed (delimitador |)
sed_escape() { printf '%s' "$1" | sed -e 's/[\\&|]/\\&/g'; }
TITLE_ESC="$(sed_escape "$TITLE")"
DOMAIN_ESC="$(sed_escape "$DOMAIN")"

PAPER_MD="$PAPER_DIR/paper.md"
PREREG_MD="$PAPER_DIR/preregistration.md"

cp "$REGISTRY_ROOT/docs/templates/paper.md" "$PAPER_MD"
cp "$REGISTRY_ROOT/docs/templates/preregistration.md" "$PREREG_MD"

sed -i \
    -e "s|^title:.*|title: \"${TITLE_ESC}\"|" \
    -e "s|^slug:.*|slug: ${SLUG_FULL}|" \
    -e "s|^date:.*|date: ${TODAY}|" \
    -e "s|^domain:.*|domain: ${DOMAIN_ESC}|" \
    -e "s|^tags:.*|tags: ${TAGS_YAML}|" \
    "$PAPER_MD"

sed -i \
    -e "s|^paper_slug:.*|paper_slug: ${SLUG_FULL}|" \
    "$PREREG_MD"

echo "  $PAPER_MD"
echo "  $PREREG_MD"

# ── references.md ────────────────────────────────────────────

echo "[3/3] Escribiendo references.md..."
cat > "$PAPER_DIR/references.md" << EOF
# References — ${TITLE}

<!-- Una entrada por referencia. Formato libre (o BibTeX) hasta promocionar a publishable. -->
EOF
echo "  $PAPER_DIR/references.md"

# ── Resumen ──────────────────────────────────────────────────

echo ""
echo "════════════════════════════════════════════════════════════"
echo "  PAPER '${SLUG_FULL}' LISTO (fase: question, status: draft)"
echo "════════════════════════════════════════════════════════════"
echo ""
echo "  Pasos siguientes:"
echo "  1. Revisión de literatura (skill /deep-research) → Related work."
echo "  2. Pre-registro: congela H0/H1 + plan en preregistration.md (preregister_hypothesis)."
echo "  3. Experimentos en experiments/ → análisis (grupo eda) → escritura IMRaD en paper.md."
echo "  4. render_paper_pdf → out/paper.pdf. Peer review adversarial → reviews/."
echo ""
echo "  papers/ está gitignored: este paper vive local hasta promocionar a publishable."
echo ""