"""MP1 · paso 42: compara cada caso de la muestra del cotejo (paso 41) con su entrada ATOM original (paso 40). Imagen etl:v2
(solo biblioteca estándar y csv). Escribe /w/interno/cotejo/comparacion.csv (campo a campo: nuestro valor, el del ATOM,
coincide) para la revisión caso a caso; el veredicto final lo pone la revisión (cotejo_resultado.csv).
"""
import csv, json, re
import xml.etree.ElementTree as ET
from pathlib import Path

D = Path("/w/interno/cotejo")
NS = {"cbc": "urn:dgpe:names:draft:codice:schema:xsd:CommonBasicComponents-2",
      "cac": "urn:dgpe:names:draft:codice:schema:xsd:CommonAggregateComponents-2",
      "cacx": "urn:dgpe:names:draft:codice-place-ext:schema:xsd:CommonAggregateComponents-2",
      "cbcx": "urn:dgpe:names:draft:codice-place-ext:schema:xsd:CommonBasicComponents-2", "a": "http://www.w3.org/2005/Atom"}
CAB = ('<entry xmlns="http://www.w3.org/2005/Atom" xmlns:cbc="%s" xmlns:cac="%s" xmlns:cac-place-ext="%s" xmlns:cbc-place-ext="%s">'
       % (NS["cbc"], NS["cac"], NS["cacx"], NS["cbcx"]))
TIPO = {"1": "Suministros", "2": "Servicios", "3": "Obras", "21": "Gestion_servicios_publicos", "22": "Concesion_servicios",
        "31": "Concesion_obras", "32": "Concesion_obras", "7": "Administrativo_especial", "8": "Privado", "50": "Patrimonial"}
PROC = {"1": "Abierto", "2": "Restringido", "3": "Negociado_sin_publicidad", "4": "Negociado_publicidad", "5": "Dialogo_competitivo",
        "6": "Contrato_menor", "7": "Derivado_acuerdo_marco", "8": "Concurso_proyectos", "9": "Abierto_simplificado",
        "10": "Asociacion_innovacion", "11": "Derivado_asociacion_innovacion", "12": "Basado_sistema_dinamico", "13": "Licitacion_con_negociacion",
        "100": "Normas_internas", "999": "Otros"}

def norm(s):
    s = (s or "").lower()
    for a, b in zip("áéíóúüñàèìòùç", "aeiouunaeiouc"):
        s = s.replace(a, b)
    return re.sub(r"[^a-z0-9]+", " ", s).strip()

def parse(xml):
    e = ET.fromstring(xml.replace("<entry>", CAB, 1))
    cfs = e.find("cacx:ContractFolderStatus", NS)
    g = lambda path: (cfs.find(path, NS).text if cfs is not None and cfs.find(path, NS) is not None else None)
    party = cfs.find("cacx:LocatedContractingParty/cac:Party", NS)
    ids = {i.get("schemeName"): i.text for i in party.findall("cac:PartyIdentification/cbc:ID", NS)} if party is not None else {}
    out = {"organo": party.find("cac:PartyName/cbc:Name", NS).text if party is not None else None, "nif": ids.get("NIF"), "dir3": ids.get("DIR3"),
           "expediente": g("cbc:ContractFolderID"), "estado": g("cbcx:ContractFolderStatusCode"),
           "tipo": TIPO.get(g("cac:ProcurementProject/cbc:TypeCode") or "", g("cac:ProcurementProject/cbc:TypeCode")),
           "cpv": g("cac:ProcurementProject/cac:RequiredCommodityClassification/cbc:ItemClassificationCode"),
           "pbl_exp": g("cac:ProcurementProject/cac:BudgetAmount/cbc:TaxExclusiveAmount"),
           "ve": g("cac:ProcurementProject/cac:BudgetAmount/cbc:EstimatedOverallContractAmount"),
           "procedimiento": PROC.get(g("cac:TenderingProcess/cbc:ProcedureCode") or "", g("cac:TenderingProcess/cbc:ProcedureCode")),
           "fin_ofertas": g("cac:TenderingProcess/cac:TenderSubmissionDeadlinePeriod/cbc:EndDate"),
           "updated": e.find("a:updated", NS).text}
    lotes = {}
    for lt in cfs.findall("cac:ProcurementProjectLot", NS):
        lid = lt.find("cbc:ID", NS).text
        lotes[lid] = {"cpv": (lt.find("cac:ProcurementProject/cac:RequiredCommodityClassification/cbc:ItemClassificationCode", NS).text
                              if lt.find("cac:ProcurementProject/cac:RequiredCommodityClassification/cbc:ItemClassificationCode", NS) is not None else None),
                      "pbl": (lt.find("cac:ProcurementProject/cac:BudgetAmount/cbc:TaxExclusiveAmount", NS).text
                              if lt.find("cac:ProcurementProject/cac:BudgetAmount/cbc:TaxExclusiveAmount", NS) is not None else None)}
    out["n_lotes"] = len(lotes)
    res = []
    for tr in cfs.findall("cac:TenderResult", NS):
        lot = tr.find("cac:AwardedTenderedProject/cbc:ProcurementProjectLotID", NS)
        res.append({"lote": lot.text if lot is not None else None, "codigo": (tr.find("cbc:ResultCode", NS).text if tr.find("cbc:ResultCode", NS) is not None else None),
                    "ofertas": (tr.find("cbc:ReceivedTenderQuantity", NS).text if tr.find("cbc:ReceivedTenderQuantity", NS) is not None else None),
                    "fecha": (tr.find("cbc:AwardDate", NS).text if tr.find("cbc:AwardDate", NS) is not None else None)})
    out["resultados"] = res
    pubs = []
    for v in cfs.findall("cacx:ValidNoticeInfo", NS):
        tipo = v.find("cbcx:NoticeTypeCode", NS)
        for d in v.findall(".//cbc:IssueDate", NS):
            pubs.append(((tipo.text if tipo is not None else None), d.text))
    out["publicaciones"] = pubs
    mods = []
    for m in cfs.iter():
        if m.tag.endswith("ContractModification"):
            txt = {c.tag.split("}")[-1]: (c.text or "").strip() for c in m.iter() if c.text and c.text.strip()}
            mods.append(txt)
    out["modificaciones"] = mods
    out["lotes"] = lotes
    return out

muestra = list(csv.DictReader(open(D / "muestra.csv")))
filas = []
for r in muestra:
    x = D / "xml" / f"{r['clave']}.xml"
    a = parse(x.read_text(encoding="utf-8")) if x.exists() else None
    lote = None
    if r.get("lote_u") and r.get("licitacion_id") and r["lote_u"] != r["licitacion_id"]:
        lote = r["lote_u"].rsplit("|", 1)[-1] if "|" in r["lote_u"] else r["lote_u"].split("/")[-1]
    f = {"clave": r["clave"], "grupo": r["grupo"], "licitacion_id": r.get("licitacion_id"), "lote_u": r.get("lote_u"), "en_atom": a is not None}
    if a:
        f.update({"organo_nuestro": r.get("organo_nom") or "", "organo_atom": norm(a["organo"]), "nif_atom": a["nif"],
                  "cpv_nuestro": r.get("cpv_div"), "cpv_atom": (a["lotes"].get(lote, {}).get("cpv") if lote else a["cpv"]),
                  "tipo_nuestro": r.get("tipo_contrato"), "tipo_atom": a["tipo"], "proc_nuestro": r.get("proc_nat"), "proc_atom": a["procedimiento"],
                  "pbl_nuestro": r.get("pbl") or r.get("pbl_lote") or r.get("pbl_exp"), "pbl_atom": (a["lotes"].get(lote, {}).get("pbl") if lote else a["pbl_exp"]),
                  "fecha_pub_nuestra": r.get("fecha_pub"), "publicaciones_atom": json.dumps(a["publicaciones"]), "ffo_nuestro": r.get("ffo"),
                  "ffo_atom": a["fin_ofertas"], "nlotes_nuestro": r.get("n_lotes_an"), "nlotes_atom": a["n_lotes"],
                  "ofertas_nuestro": r.get("num_ofertas"), "desierto_nuestro": r.get("des") or r.get("y_des"),
                  "resultados_atom": json.dumps(a["resultados"], ensure_ascii=False), "y_mod": r.get("y_mod"), "fecha_adj_nuestra": r.get("fecha_adj"),
                  "modificaciones_atom": json.dumps(a["modificaciones"], ensure_ascii=False)[:1500], "estado_atom": a["estado"],
                  "updated_atom": a["updated"], "expediente_atom": a["expediente"], "y_rec": r.get("y_rec")})
    filas.append(f)
cols = sorted({k for f in filas for k in f}, key=lambda k: list(filas[0].keys()).index(k) if k in filas[0] else 99)
with open(D / "comparacion.csv", "w", newline="") as fh:
    w = csv.DictWriter(fh, fieldnames=cols); w.writeheader(); [w.writerow(f) for f in filas]
print(len(filas), sum(f["en_atom"] for f in filas))