descarga_xml_sunat/reporte_fallas.py

import sqlite3
from pathlib import Path
from datetime import datetime
from collections import Counter

# ============================================================================
try:
    import matplotlib
    matplotlib.use("Agg")
    import matplotlib.pyplot as plt
    import matplotlib.ticker as mticker
    HAS_MPL = True
except ImportError:
    HAS_MPL = False

DB_PATH = Path(__file__).parent / "fallas_descarga.db"
REPORTES_DIR = Path(__file__).parent / "reportes"
REPORTES_DIR.mkdir(exist_ok=True)

COLORS = {
    "Error HTTP 500": "#e74c3c",
    "falló: PDF": "#e67e22",
    "falló: XML": "#3498db",
    "falló: PDF, XML": "#9b59b6",
}
CMAP = list(COLORS.values())

# ============================================================================
def _query(sql, params=()):
    with sqlite3.connect(str(DB_PATH)) as conn:
        conn.row_factory = sqlite3.Row
        rows = conn.execute(sql, params).fetchall()
        return [dict(r) for r in rows]

# ============================================================================
def reporte_texto():
    print("\n" + "=" * 60)
    print("📊 REPORTE DE FALLAS - SUNAT")
    print("=" * 60)

    total = _query("SELECT COUNT(*) AS c FROM fallas")[0]["c"]
    print(f"\n📄 Total fallas registradas: {total}")

    if total == 0:
        print("\n✅ No hay fallas registradas.")
        return

    print("\n── Distribución por tipo de error ──")
    for r in _query("SELECT COUNT(*) AS c, error FROM fallas GROUP BY error ORDER BY c DESC"):
        pct = r["c"] / total * 100
        print(f"   {r['error']:25s} {r['c']:>5d}  ({pct:5.1f}%)")

    print("\n── Top 10 RUC con más fallas ──")
    for i, r in enumerate(_query("SELECT COUNT(*) AS c, ruc FROM fallas GROUP BY ruc ORDER BY c DESC LIMIT 10"), 1):
        print(f"   {i:2d}. {r['ruc']}  ({r['c']} fallas)")

    print("\n── Distribución por intentos ──")
    for r in _query("SELECT intentos, COUNT(*) AS c FROM fallas GROUP BY intentos ORDER BY intentos"):
        print(f"   {r['intentos']:2d} intento(s)  →  {r['c']:>5d} documento(s)")

    print("\n── Fallas por día ──")
    for r in _query("SELECT DATE(fecha_ultimo) AS dia, COUNT(*) AS c FROM fallas GROUP BY dia ORDER BY dia"):
        print(f"   {r['dia']}  →  {r['c']} falla(s)")

# ============================================================================
def _color_error(error):
    return COLORS.get(error, "#95a5a6")

# ============================================================================
def grafico_barras_errores():
    data = _query("SELECT COUNT(*) AS c, error FROM fallas GROUP BY error ORDER BY c DESC")
    if not data:
        return None

    labels = [r["error"] for r in data]
    values = [r["c"] for r in data]
    colors = [_color_error(l) for l in labels]

    fig, ax = plt.subplots(figsize=(10, 5))
    bars = ax.barh(labels, values, color=colors, edgecolor="white", height=0.6)
    for b, v in zip(bars, values):
        ax.text(b.get_width() + max(values) * 0.01, b.get_y() + b.get_height() / 2,
                str(v), va="center", fontsize=11, fontweight="bold")
    ax.set_xlabel("Cantidad de fallas")
    ax.set_title("Distribución de fallas por tipo de error", fontsize=14, fontweight="bold")
    ax.margins(x=0.15)
    ax.spines[["top", "right"]].set_visible(False)
    fig.tight_layout()
    path = REPORTES_DIR / "barras_errores.png"
    fig.savefig(path, dpi=150)
    plt.close(fig)
    return path

# ============================================================================
def grafico_barras_ruc():
    data = _query("SELECT COUNT(*) AS c, ruc FROM fallas GROUP BY ruc ORDER BY c DESC LIMIT 10")
    if not data:
        return None

    data.reverse()
    labels = [r["ruc"] for r in data]
    values = [r["c"] for r in data]

    fig, ax = plt.subplots(figsize=(10, 5))
    bars = ax.barh(labels, values, color="#e67e22", edgecolor="white", height=0.6)
    for b, v in zip(bars, values):
        ax.text(b.get_width() + 0.3, b.get_y() + b.get_height() / 2,
                str(v), va="center", fontsize=10, fontweight="bold")
    ax.set_xlabel("Cantidad de fallas")
    ax.set_title("Top 10 RUC con más fallas", fontsize=14, fontweight="bold")
    ax.margins(x=0.15)
    ax.spines[["top", "right"]].set_visible(False)
    fig.tight_layout()
    path = REPORTES_DIR / "barras_ruc.png"
    fig.savefig(path, dpi=150)
    plt.close(fig)
    return path

# ============================================================================
def grafico_torta():
    data = _query("SELECT COUNT(*) AS c, error FROM fallas GROUP BY error ORDER BY c DESC")
    if not data:
        return None

    labels = [r["error"] for r in data]
    values = [r["c"] for r in data]
    colors = [_color_error(l) for l in labels]

    fig, ax = plt.subplots(figsize=(7, 7))
    wedges, texts, autotexts = ax.pie(
        values, labels=labels, autopct="%1.1f%%",
        colors=colors, startangle=90, textprops={"fontsize": 11}
    )
    for at in autotexts:
        at.set_fontweight("bold")
    ax.set_title("Proporción de fallas por tipo", fontsize=14, fontweight="bold")
    fig.tight_layout()
    path = REPORTES_DIR / "torta_errores.png"
    fig.savefig(path, dpi=150)
    plt.close(fig)
    return path

# ============================================================================
def main():
    reporte_texto()

    if not HAS_MPL:
        print("\n⚠️  matplotlib no instalado. Ejecuta: pip3 install matplotlib")
        return

    paths = []
    for name, fn in [("barras_errores", grafico_barras_errores),
                     ("barras_ruc", grafico_barras_ruc),
                     ("torta_errores", grafico_torta)]:
        p = fn()
        if p:
            paths.append(p)

    if paths:
        print(f"\n📁 Gráficos guardados en: {REPORTES_DIR}")
        for p in paths:
            print(f"   {p.name}")
        print(f"\n💡 Abre con: open {REPORTES_DIR}")

# ============================================================================
if __name__ == "__main__":
    main()
# ============================================================================