from collections import defaultdict
from datetime import datetime
from pathlib import Path
from zipfile import ZipFile
from xml.etree import ElementTree as ET
import re

from openpyxl import Workbook, load_workbook
from openpyxl.styles import Alignment, Border, Font, PatternFill, Side
from openpyxl.utils import get_column_letter


BASE = Path("/Users/kkfluous/Downloads")
ASSESSMENT = BASE / "7月核算结果/租赁任务考核_2026年7月.xlsx"
PLATFORM_DIR = BASE / "广州新能源平台_纯氢纯电里程_2026年7月_按日"
GPS_FILES = [
    BASE / "里程统计[天][2026-07-01至2026-07-31].xlsx",
    BASE / "里程统计[天][2026-07-01至2026-07-31] (1).xlsx",
]
OUTPUT = BASE / "7月核算结果/7月考核车辆多源里程汇总.xlsx"
NS = "{http://schemas.openxmlformats.org/spreadsheetml/2006/main}"


def normalize_plate(value):
    return re.sub(r"\s+", "", str(value or "")).upper()


def parse_gps_file(path):
    result = {}
    with ZipFile(path) as zf:
        root = ET.fromstring(zf.read("xl/worksheets/sheet1.xml"))
        for row in root.findall(f".//{NS}row"):
            if int(row.get("r")) < 4:
                continue
            values = {}
            for cell in row.findall(f"{NS}c"):
                col = re.match(r"[A-Z]+", cell.get("r")).group()
                if cell.get("t") == "inlineStr":
                    values[col] = "".join(t.text or "" for t in cell.findall(f".//{NS}t"))
                else:
                    node = cell.find(f"{NS}v")
                    values[col] = node.text if node is not None else None
            plate = normalize_plate(values.get("H"))
            date_text = str(values.get("O") or "").strip()
            if not plate or plate == "合计" or not re.fullmatch(r"2026-07-\d{2}", date_text):
                continue
            result[(plate, datetime.strptime(date_text, "%Y-%m-%d").date())] = float(values.get("P") or 0)
    return result


platform = defaultdict(lambda: [0.0, 0.0])
platform_presence = set()
for path in sorted(PLATFORM_DIR.glob("2026-07-??_纯氢纯电里程.xlsx")):
    wb = load_workbook(path, read_only=True, data_only=True)
    ws = wb.active
    for row in ws.iter_rows(min_row=2, values_only=True):
        plate = normalize_plate(row[5])
        date_match = re.search(r"2026-07-\d{2}", str(row[6] or ""))
        if not plate or not date_match:
            continue
        date = datetime.strptime(date_match.group(), "%Y-%m-%d").date()
        electric = float(row[7] or 0)
        hydrogen = float(row[8] or 0)
        platform[(plate, date)][0] += hydrogen
        platform[(plate, date)][1] += electric
        platform_presence.add((plate, date))
    wb.close()

gps = {}
for path in GPS_FILES:
    incoming = parse_gps_file(path)
    overlap = set(gps) & set(incoming)
    if overlap:
        raise RuntimeError(f"GPS来源存在重复车辆日期：{sorted(overlap)[:5]}")
    gps.update(incoming)

source_wb = load_workbook(ASSESSMENT, read_only=True, data_only=True)
source_ws = source_wb["业务考核视图"]
headers = [c.value for c in source_ws[1]]
idx = {name: i for i, name in enumerate(headers)}

records = []
for row in source_ws.iter_rows(min_row=2, values_only=True):
    plate = normalize_plate(row[idx["车牌号"]])
    if not plate:
        continue
    start = row[idx["考核开始日期"]].date()
    end = row[idx["考核结束日期"]].date()
    dates = [(start.fromordinal(start.toordinal() + i)) for i in range((end - start).days + 1)]

    p_dates = [d for d in dates if (plate, d) in platform_presence]
    if p_dates:
        hydrogen = sum(platform[(plate, d)][0] for d in p_dates)
        electric = sum(platform[(plate, d)][1] for d in p_dates)
    else:
        hydrogen = electric = None

    test_mileage = row[idx["测试里程(km)"]]
    is_test = isinstance(test_mileage, (int, float)) and test_mileage > 0
    g_dates = [d for d in dates if (plate, d) in gps]
    gps_total = sum(gps[(plate, d)] for d in g_dates) if g_dates else None
    # 7月最终考核源表的“实际行驶里程”已按原处理链路写入测试车辆GPS里程：
    # 优先智能管车日报，缺失时用两份GPS日明细补充。补充明细未命中时，
    # 必须从最终源表回填，不能误标为“无来源”。
    if gps_total is None and is_test:
        gps_total = row[idx["实际行驶里程(km)"]]
    records.append({
        "plate": plate,
        "customer": row[idx["客户名称"]] or "",
        "start": start,
        "end": end,
        "days": (end - start).days + 1,
        "test": "是" if is_test else "否",
        "hydrogen": hydrogen,
        "electric": electric,
        "tbox": row[idx["原TBOX里程(km)"]] if row[idx["原TBOX里程(km)"]] is not None else None,
        "gps": gps_total,
    })
source_wb.close()

wb = Workbook()
ws = wb.active
ws.title = "7月考核车辆里程汇总"
columns = [
    "序号", "车牌", "客户", "考核开始日期", "考核结束日期", "考核天数", "是否存在测试",
    "纯氢里程(km)", "纯电里程(km)", "广州平台总里程(km)", "TBOX里程(km)", "GPS里程(km)",
]
ws.append(columns)

for n, rec in enumerate(records, 1):
    row_num = ws.max_row + 1
    ws.append([
        n, rec["plate"], rec["customer"], rec["start"], rec["end"], rec["days"], rec["test"],
        rec["hydrogen"] if rec["hydrogen"] is not None else "无来源",
        rec["electric"] if rec["electric"] is not None else "无来源",
        round(rec["hydrogen"] + rec["electric"], 3) if rec["hydrogen"] is not None else "无来源",
        rec["tbox"] if rec["tbox"] is not None else "无来源",
        rec["gps"] if rec["gps"] is not None else "无来源",
    ])

ws.insert_rows(1)
ws.merge_cells("A1:L1")
ws["A1"] = (
    "1. 纯氢里程(km)、纯电里程(km)来源于广州平台统计，TBOX里程来源于车机上报的仪表盘里程统计，"
    "GPS里程优先按两份7月GPS日明细汇总；测试车辆未命中时，回填7月最终考核源表中已确认的GPS实际里程\n"
    "2. 广州平台总里程(km)=纯氢里程(km)+纯电里程(km)\n"
    "3. 已确认广州平台暂未接入86辆普货车数据；无对应记录统一标记为“无来源”"
)

header_fill = PatternFill("solid", fgColor="1F4E78")
platform_fill = PatternFill("solid", fgColor="DDEBF7")
tbox_fill = PatternFill("solid", fgColor="E2F0D9")
gps_fill = PatternFill("solid", fgColor="E4DFEC")
test_fill = PatternFill("solid", fgColor="FFF2CC")
missing_fill = PatternFill("solid", fgColor="F2F2F2")
thin = Side(style="thin", color="B7B7B7")

for cell in ws[2]:
    cell.fill = header_fill
    cell.font = Font(color="FFFFFF", bold=True)
    cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=True)
    cell.border = Border(bottom=Side(style="medium", color="FFFFFF"))

for row in ws.iter_rows(min_row=3, max_row=ws.max_row):
    is_test = row[6].value == "是"
    for cell in row:
        cell.border = Border(left=thin, right=thin, top=thin, bottom=thin)
        cell.alignment = Alignment(horizontal="center", vertical="center")
    row[2].alignment = Alignment(horizontal="left", vertical="center")
    if is_test:
        for cell in row:
            cell.fill = test_fill
    else:
        for cell in row[7:10]:
            cell.fill = platform_fill
        row[10].fill = tbox_fill
        row[11].fill = gps_fill
        for cell in row[7:12]:
            if cell.value == "无来源":
                cell.fill = missing_fill
                cell.font = Font(color="7F7F7F", italic=True)

for row in range(3, ws.max_row + 1):
    ws.cell(row, 4).number_format = "yyyy-mm-dd"
    ws.cell(row, 5).number_format = "yyyy-mm-dd"
    for col in range(8, 13):
        ws.cell(row, col).number_format = "#,##0.0"

widths = [8, 14, 34, 15, 15, 11, 14, 17, 17, 23, 17, 17]
for col, width in enumerate(widths, 1):
    ws.column_dimensions[get_column_letter(col)].width = width
ws["A1"].fill = PatternFill("solid", fgColor="FFF2CC")
ws["A1"].font = Font(color="7F6000", italic=True)
ws["A1"].alignment = Alignment(horizontal="left", vertical="center", wrap_text=True)
ws.row_dimensions[1].height = 58
ws.row_dimensions[2].height = 36
ws.freeze_panes = "A3"
ws.auto_filter.ref = f"A2:L{ws.max_row}"
ws.sheet_view.showGridLines = False
ws.sheet_properties.pageSetUpPr.fitToPage = True
ws.page_setup.orientation = "landscape"
ws.page_setup.fitToWidth = 1
ws.page_setup.fitToHeight = 0
ws.print_title_rows = "1:2"

OUTPUT.parent.mkdir(parents=True, exist_ok=True)
wb.save(OUTPUT)

print({
    "output": str(OUTPUT),
    "records": len(records),
    "test_records": sum(r["test"] == "是" for r in records),
    "platform_missing": sum(r["hydrogen"] is None for r in records),
    "tbox_missing": sum(r["tbox"] is None for r in records),
    "gps_missing": sum(r["gps"] is None for r in records),
})