"""纯正则 PDF 数据提取模块 — 不调用 LLM，零延迟。

从保险计划书 PDF 的原始文本中，用正则 + 启发式规则提取结构化 JSON。
提取率目标 > 80%（按保险演示表行数计算）。

用法：
    from insurance.ppt.regex_extractor import extract_insurance_regex
    data = extract_insurance_regex(pdf_text)
"""
import re
import logging

logger = logging.getLogger(__name__)


# ─── 金额解析 ──────────────────────────────────────────────

def _parse_money(s: str) -> float | None:
    """解析各种格式的金额字符串为 float。

    支持: "1,234,567.89" "1234567" "1,234,567" "US$1,234" "HK$1234"
    注意: 0 是合法值（如红利为 0 时），仅空字符串和无法解析返回 None。
    """
    if not s:
        return None
    # 去掉货币符号和空白
    s = re.sub(r'[Uu][Ss]\$|[Hh][Kk]\$|[Cc][Nn][Yy]?¥|¥|\$|\s', '', s.strip())
    # 去掉逗号
    s = s.replace(',', '')
    try:
        return float(s)
    except (ValueError, TypeError):
        return None


# ─── 产品信息提取 ──────────────────────────────────────────

def _extract_product_name(text: str) -> str | None:
    """提取产品名称。

    支持：带标签格式、计划书标题、繁体、英文缩写。
    """
    patterns = [
        # 带标签
        r'(?:产品名称|产品名|产品|保单名称)\s*[：:]\s*([^\n,，]+)',
        r'(?:Product(?:\s+Name)?|Plan(?:\s+Name)?)\s*[：:]\s*([^\n,，]+)',
        r'(?:建议书|建議書|計劃書|計劃名稱|保障計劃|保障计划)\s*[：:]\s*([^\n,，]+)',
        r'(?:Proposal)\s*[：:]\s*([^\n,，]+)',
        # 繁体
        r'(?:產品名稱|產品名)\s*[：:]\s*([^\n,，]+)',
        # "XXX 计划" 格式（无冒号标签）
        r'(?:^|\n)\s*([A-Z][\w\s]*(?:Plan|Scheme|Life|Assurance|Insurance|Protection))\s*(?:\n|$)',
        # 中文"XXX计划/保障"格式
        r'(?:^|\n)\s*([一-鿿]{2,10}(?:计划|計劃|保障|寿险|壽險|危疾|储蓄))\s*(?:\n|$)',
    ]
    for p in patterns:
        m = re.search(p, text, re.IGNORECASE)
        if m:
            name = m.group(1).strip()
            # 过滤掉太短或纯数字的结果
            if len(name) >= 2 and not name.isdigit():
                return name
    return None


def _extract_currency(text: str) -> str | None:
    """提取保单货币，支持多币种（优先匹配保费行中的币种符号）。

    未识别时返回 None（由用户或后续流程确认），不再默认 USD。
    """
    # 按优先级搜索
    patterns = [
        (r'(?:保单货币|保费货币|Currency)\s*[：:]\s*(USD|USB|HKD|CNY|RMB|SGD|GBP|EUR)', 'direct'),
        (r'\b(USD)\b', 'usd'),
        (r'\b(HKD)\b', 'hkd'),
        (r'\b(CNY|RMB)\b', 'cny'),
        (r'\b(SGD)\b', 'sgd'),
        (r'U\s*S\s*\$', 'us_symbol'),
        (r'H\s*K\s*\$', 'hk_symbol'),
    ]
    for pattern, tag in patterns:
        m = re.search(pattern, text, re.IGNORECASE)
        if m:
            if tag == 'us_symbol':
                return 'USD'
            if tag == 'hk_symbol':
                return 'HKD'
            value = m.group(1).upper()
            if value == "USB":
                return "USD"
            if value == "RMB":
                return "CNY"
            return value
    return None


def _extract_labeled_money(text: str, labels: list[str]) -> tuple[float | None, str | None]:
    """提取明确标签后的金额，同时保留原始命中标签。"""
    label_pattern = "|".join(re.escape(label) for label in labels)
    match = re.search(
        rf"({label_pattern})\s*[：:]\s*(?:[A-Z]{{2,3}}|[￥¥$£€]|US\$|HK\$)?\s*([\d,]+(?:\.\d+)?)",
        text,
        re.IGNORECASE,
    )
    if not match:
        return None, None
    return _parse_money(match.group(2)), match.group(1)


def _extract_smoker(text: str) -> str | None:
    patterns = [
        r"(?:吸烟状态|是否吸烟|吸煙狀態|是否吸煙|Smoking\s*Status|Smoker)\s*[：:]\s*(是|否|吸烟|不吸烟|吸煙|不吸煙|Yes|No|Y|N)",
        r"(?:Non[-\s]?Smoker|Non[-\s]?Smoking)",
    ]
    for pattern in patterns:
        match = re.search(pattern, text, re.IGNORECASE)
        if not match:
            continue
        value = match.group(1) if match.lastindex else match.group(0)
        if str(value).strip().lower() in ("是", "吸烟", "吸煙", "yes", "y"):
            return "yes"
        return "no"
    return None


def _extract_annual_premium(text: str) -> float | None:
    """提取年缴保费。"""
    patterns = [
        r'(?:每年(?:缴付)?保费|年缴保费|年保费|每年(?:繳付)?保費|年繳保費)\s*[：:]\s*[\$UuSsHhKk]*\s*([\d,]+(?:\.\d+)?)',
        r'(?:Annual\s+Premium|每年(?:缴付)?保费|年缴保费)\s*[:：]?\s*(?:[A-Z]{2,3}\$?\s*)?([\d,]+(?:\.\d+)?)',
    ]
    for p in patterns:
        m = re.search(p, text, re.IGNORECASE)
        if m:
            val = _parse_money(m.group(1))
            if val and val >= 100:  # 排除太小的数字（可能是年期等）
                return val
    return None


def _extract_insured_info(text: str) -> dict:
    """提取被保人信息（年龄、性别）。

    支持：简体/繁体、英文、出生日期推算。
    使用"受保人上下文窗口"避免误取利益表中的年龄数字。
    """
    info = {'age': None, 'gender': None, 'age_source': None}

    # ── 年龄：优先匹配带标签的明确年龄 ──
    age_patterns = [
        # 简体
        r'(?:受保人|被保人|投保时|投保人)?\s*年龄\s*[：:]\s*(\d{1,3})\s*岁?',
        r'(?:受保人|被保人)\s*[：:]?\s*(?:[^\n,，]{0,10})?(\d{1,3})\s*岁',
        # 繁体
        r'(?:受保人|被保人|投保時|投保人)?\s*年齡\s*[：:]\s*(\d{1,3})\s*歲?',
        r'(?:受保人|被保人)\s*[：:]?\s*(?:[^\n,，]{0,10})?(\d{1,3})\s*歲',
        # 英文
        r'(?:Issue\s+Age|Age\s+at\s+Entry|Age\s+at\s+Issue|Insured\s+Age)\s*[：:]\s*(\d{1,3})',
        r'(?:Age)\s*[：:]\s*(\d{1,3})',
    ]
    for p in age_patterns:
        m = re.search(p, text, re.IGNORECASE)
        if m:
            age = int(m.group(1))
            if 0 <= age <= 120:
                info['age'] = age
                info['age_source'] = 'explicit'
                break

    # ── 年龄：出生日期推算 ──
    if info['age'] is None:
        dob_patterns = [
            r'(?:出生[日 destinationViewController]?[期日]|Date\s+of\s+Birth|DOB|Birth\s+Date)\s*[：:]\s*(\d{4})[/-](\d{1,2})[/-](\d{1,2})',
            r'(?:出生[日 destinationViewController]?[期日]|Date\s+of\s+Birth|DOB)\s*[：:]\s*(\d{1,2})[/-](\d{1,2})[/-](\d{4})',
        ]
        issue_date_patterns = [
            r'(?:保单[日 destinationViewController]?[期日]|Issue\s+Date|Policy\s+Date|投保[日 destinationViewController]?[期日])\s*[：:]\s*(\d{4})[/-](\d{1,2})[/-](\d{1,2})',
            r'(?:保单[日 destinationViewController]?[期日]|Issue\s+Date|Policy\s+Date)\s*[：:]\s*(\d{1,2})[/-](\d{1,2})[/-](\d{4})',
        ]
        import datetime
        today = datetime.date.today()
        for dp in dob_patterns:
            dm = re.search(dp, text, re.IGNORECASE)
            if dm:
                try:
                    groups = dm.groups()
                    if len(groups[0]) == 4:
                        dob = datetime.date(int(groups[0]), int(groups[1]), int(groups[2]))
                    else:
                        dob = datetime.date(int(groups[2]), int(groups[1]), int(groups[0]))
                    # 用保单日期或今天推算
                    issue_age = None
                    for ip in issue_date_patterns:
                        im = re.search(ip, text, re.IGNORECASE)
                        if im:
                            ig = im.groups()
                            if len(ig[0]) == 4:
                                issue_date = datetime.date(int(ig[0]), int(ig[1]), int(ig[2]))
                            else:
                                issue_date = datetime.date(int(ig[2]), int(ig[1]), int(ig[0]))
                            issue_age = issue_date.year - dob.year - (
                                (issue_date.month, issue_date.day) < (dob.month, dob.day)
                            )
                            break
                    if issue_age is None:
                        issue_age = today.year - dob.year - (
                            (today.month, today.day) < (dob.month, dob.day)
                        )
                    if 0 <= issue_age <= 120:
                        info['age'] = issue_age
                        info['age_source'] = 'inferred_from_dob'
                except (ValueError, TypeError):
                    pass
                break

    # ── 性别 ──
    gender_patterns = [
        r'(?:受保人|被保人|投保人)?\s*性[别別]?\s*[：:]\s*(男|女|Male|Female|M|F)',
        r'(?:Gender|Sex)\s*[：:]\s*(Male|Female|M|F)',
        r'(男|女)\s*(?:性|士|仕)',
    ]
    for p in gender_patterns:
        m = re.search(p, text, re.IGNORECASE)
        if m:
            raw = m.group(1).strip().upper()
            if raw in ('男', 'M', 'MALE'):
                info['gender'] = 'male'
            elif raw in ('女', 'F', 'FEMALE'):
                info['gender'] = 'female'
            break

    return info


def _extract_premium_payment_period(text: str) -> int | str | None:
    """提取保费缴付年期。返回 int（年数）或 '整付'，不再返回 '5年' 等字符串。"""
    patterns = [
        r'(?:保费缴付年期|缴费年期|缴付年期|保費繳付年期|繳費年期|繳付年期)\s*[：:]\s*(\d+)\s*(?:年|years?|yrs?)?',
        r'(?:Premium\s+Payment\s+(?:Period|Term|Years?))\s*[：:]\s*(\d+)\s*(?:years?|yrs?)?',
        r'(?:整付|趸缴|趸繳|Single\s+Premium)',
        r'(?:缴费|缴付|繳費|繳付)\s*(?:期限|年期)\s*[：:]\s*(\d+)\s*年',
    ]
    for p in patterns:
        m = re.search(p, text, re.IGNORECASE)
        if m:
            if '整付' in m.group(0) or '趸缴' in m.group(0) or 'Single' in m.group(0).title():
                return '整付'
            year_str = m.group(1)
            try:
                years = int(year_str)
                if 1 <= years <= 100:
                    return years
            except ValueError:
                pass
    return None


def _extract_coverage_period(text: str) -> str | None:
    """提取保障年期。"""
    patterns = [
        r'(?:保障年期|保障期|保障年期|Coverage\s+(?:Period|Term))\s*[：:]\s*([^\n,，]+)',
        r'(?:终身保障|保障至终身|终身|Whole\s+Life|終身)',
        r'(?:保障至|保至)\s*(\d+)\s*岁',
        r'(?:保障至|保至)\s*(\d+)\s*歲',
    ]
    for p in patterns:
        m = re.search(p, text, re.IGNORECASE)
        if m:
            if '终身' in m.group(0) or 'Whole' in m.group(0).title():
                return '终身'
            return m.group(1).strip() if m.lastindex else None
    return None


# ─── 演示表提取 ──────────────────────────────────────────

# 列名映射：各种 PDF 表头 → 标准字段名
_COLUMN_ALIASES = {
    # 保单年度
    '保单年度': 'policy_year', '保單年度': 'policy_year',
    'policy year': 'policy_year', 'policyyear': 'policy_year',
    'year': 'policy_year', '年度': 'policy_year',
    '保单': 'policy_year',  # 简称
    '受保人年龄': 'policy_year',  # 有些表用年龄代替年度
    '受保人年齡': 'policy_year',
    'age': 'policy_year',
    # 已缴总保费
    '缴付保费总额': 'total_premium_paid', '已缴保费': 'total_premium_paid',
    '已付保费总额': 'total_premium_paid', '已缴付保费': 'total_premium_paid',
    'total premium paid': 'total_premium_paid', 'premium paid': 'total_premium_paid',
    '累积已付保费': 'total_premium_paid', '累计已缴': 'total_premium_paid',
    '已缴保费总额': 'total_premium_paid', '缴付保费': 'total_premium_paid',
    '繳付保費總額': 'total_premium_paid', '已繳保費': 'total_premium_paid',
    '累積已付保費': 'total_premium_paid', '已付保費總額': 'total_premium_paid',
    # 保证现金价值
    '保证现金价值': 'guaranteed_cash_value', '保證現金價值': 'guaranteed_cash_value',
    'guaranteed cash value': 'guaranteed_cash_value', 'gcv': 'guaranteed_cash_value',
    '保证退保价值': 'guaranteed_cash_value', '保证价值': 'guaranteed_cash_value',
    '保证现金': 'guaranteed_cash_value',
    # 归原红利
    '归原红利': 'reversionary_bonus', '歸原紅利': 'reversionary_bonus',
    'reversionary bonus': 'reversionary_bonus', '累积归原红利': 'reversionary_bonus',
    '累计归原红利': 'reversionary_bonus', '周年红利': 'reversionary_bonus',
    '复归红利': 'reversionary_bonus', '歸原紅利/復歸紅利': 'reversionary_bonus',
    # 终期分红
    '终期分红': 'terminal_dividend', '終期分紅': 'terminal_dividend',
    'terminal dividend': 'terminal_dividend', '终期红利': 'terminal_dividend',
    '特别红利': 'terminal_dividend',
    # 退保发还总额
    '退保发还总额': 'total_surrender_value', '退保發還總額': 'total_surrender_value',
    'total surrender value': 'total_surrender_value', 'cash surrender value': 'total_surrender_value',
    '退保价值': 'total_surrender_value', '退保总值': 'total_surrender_value',
    '退保金额': 'total_surrender_value', '退保总额': 'total_surrender_value',
    '保证利益总额': 'total_surrender_value',
    # 身故赔偿
    '身故赔偿': 'death_benefit', '身故賠償': 'death_benefit',
    'death benefit': 'death_benefit', 'death': 'death_benefit',
    '身故保障': 'death_benefit', '身故保险金': 'death_benefit',
    # IUL 特有
    '账户价值': 'account_value', '非保证账户价值': 'non_guaranteed_account_value',
    '保证账户价值': 'guaranteed_account_value',
    'non-guaranteed account value': 'non_guaranteed_account_value',
    'guaranteed account value': 'guaranteed_account_value',
    '保险成本': 'cost_of_insurance', 'cost of insurance': 'cost_of_insurance', 'coi': 'cost_of_insurance',
    # 繁体中文别名
    '保單': 'policy_year', '保證現金': 'guaranteed_cash_value',
    '歸原紅利': 'reversionary_bonus', '復歸紅利': 'reversionary_bonus',
    '週年紅利': 'reversionary_bonus', '終期分紅': 'terminal_dividend',
    '特別紅利': 'terminal_dividend', '退保發還總額': 'total_surrender_value',
    '退保總值': 'total_surrender_value', '退保價值': 'total_surrender_value',
    '身故賠償': 'death_benefit',
    '已付保費總額': 'total_premium_paid', '已繳保費總額': 'total_premium_paid',
    '累積已付保費': 'total_premium_paid',
    '保證價值': 'guaranteed_cash_value', '保證現金價值': 'guaranteed_cash_value',
    # ─── 提领表列名 ────────────────────────────────────────
    # 年度提取金额
    '提取金额': 'annual_withdrawal', '提取金額': 'annual_withdrawal',
    '提款金额': 'annual_withdrawal', '提款金額': 'annual_withdrawal',
    '现金提取': 'annual_withdrawal', '現金提取': 'annual_withdrawal',
    '款项提取': 'annual_withdrawal', '款項提取': 'annual_withdrawal',
    '每年提取': 'annual_withdrawal', '每年提款': 'annual_withdrawal',
    'annual withdrawal': 'annual_withdrawal', 'withdrawal': 'annual_withdrawal',
    'cash withdrawal': 'annual_withdrawal',
    # 累计提取
    '累计提取': 'total_withdrawn', '累計提取': 'total_withdrawn',
    '累计提款': 'total_withdrawn', '累計提款': 'total_withdrawn',
    '累积提取': 'total_withdrawn', '累積提取': 'total_withdrawn',
    'total withdrawn': 'total_withdrawn', 'cumulative withdrawal': 'total_withdrawn',
    # 提取前退保价值
    '提取前退保金额': 'surrender_value_before', '提取前退保價值': 'surrender_value_before',
    '提款前退保金额': 'surrender_value_before', '提款前退保價值': 'surrender_value_before',
    'surrender value before': 'surrender_value_before',
    # 提取后退保价值
    '提取后退保金额': 'surrender_value_after', '提取後退保金額': 'surrender_value_after',
    '提款后退保金额': 'surrender_value_after', '提款後退保金額': 'surrender_value_after',
    '退保金额（提取后）': 'surrender_value_after',
    'surrender value after': 'surrender_value_after',
}


def _normalize_column_name(name: str) -> str | None:
    """将 PDF 表头规范化为标准字段名。"""
    normalized = name.strip().lower()
    # 去掉括号内容和多余空格
    normalized = re.sub(r'\(.*?\)|（.*?）', '', normalized).strip()
    normalized = re.sub(r'\s+', ' ', normalized)
    if normalized in _COLUMN_ALIASES:
        return _COLUMN_ALIASES[normalized]
    # 模糊匹配：检查是否包含关键词
    for alias, field in _COLUMN_ALIASES.items():
        if alias in normalized or normalized in alias:
            return field
    return None


def _detect_columns(header_line: str) -> list[tuple[int, str]]:
    """检测表头行的列位置和字段名。返回 [(start_pos, field_name), ...]。"""
    columns = []

    # 尝试按多个空格或制表符分割
    parts = re.split(r'\s{2,}|\t', header_line)
    pos = 0
    for part in parts:
        field = _normalize_column_name(part)
        if field:
            columns.append((pos, field))
        pos += len(part) + 2  # 近似位置

    # 如果没有检测到列，尝试逐个关键词搜索
    if len(columns) < 2:
        for alias, field in _COLUMN_ALIASES.items():
            idx = header_line.lower().find(alias)
            if idx >= 0:
                # 避免重复
                if not any(f == field for _, f in columns):
                    columns.append((idx, field))

    columns.sort(key=lambda x: x[0])
    return columns


def _extract_benefit_rows(text: str) -> list[dict]:
    """从 PDF 文本中提取利益演示表数据行。

    策略：
    1. 找到包含"保单年度"等关键词的表头行
    2. 解析表头列位置
    3. 提取后续数字行
    """
    rows = []
    lines = text.split('\n')
    in_table = False
    columns: list[tuple[int, str]] = []
    consecutive_non_data = 0
    MAX_NON_DATA_LINES = 5  # 允许的最大连续非数据行数

    for line in lines:
        stripped = line.strip()
        if not stripped:
            continue

        # 检测表头行
        if not in_table:
            header_fields = ['保单年度', '保單年度', 'policy year', '年度', '受保人年龄', '受保人年齡']
            has_header = any(f in stripped.lower() for f in header_fields)
            # 需要至少有两个数值相关列名
            value_cols = ['价值', '價值', '保费', '保費', '红利', '紅利', '分红', '分紅',
                          '赔偿', '賠償', 'surrender', 'premium', 'cash', 'bonus',
                          'benefit', 'value', '退保', '保证', '保證']
            has_value = sum(1 for v in value_cols if v in stripped.lower()) >= 1

            if has_header and has_value:
                columns = _detect_columns(stripped)
                if len(columns) >= 2:
                    in_table = True
                    consecutive_non_data = 0
                    logger.debug(f"检测到演示表头: {[(c[1], c[0]) for c in columns]}")
            continue

        # 跳过子表头行（如"保证 非保证 总额"等）
        subheader_patterns = ['保证', '非保证', '总额', 'guaranteed', 'non-guaranteed', 'total']
        if sum(1 for p in subheader_patterns if p in stripped.lower()) >= 2:
            continue

        # 尝试解析数据行
        numbers = re.findall(r'[\d,]+(?:\.\d+)?', stripped)
        if not numbers:
            consecutive_non_data += 1
            if consecutive_non_data >= MAX_NON_DATA_LINES:
                break  # 表格结束
            continue

        consecutive_non_data = 0
        row = _parse_data_row(stripped, columns, numbers)
        if row and row.get('policy_year') is not None:
            rows.append(row)

    return rows


def _parse_data_row(
    line: str, columns: list[tuple[int, str]], numbers: list[str]
) -> dict | None:
    """解析单行数据。"""
    row = {}

    # 提取第一个数字作为保单年度（通常是行首的小数字）
    year_match = re.match(r'^\s*(\d{1,3})\b', line)
    if year_match:
        year_val = int(year_match.group(1))
        if 0 < year_val <= 100:
            row['policy_year'] = year_val

    # 用列位置映射数值
    if columns:
        # 获取非 policy_year 的列（按原始顺序）
        value_columns = [(pos, f) for pos, f in columns if f != 'policy_year']

        # 确定从哪个数字开始分配（跳过已识别的年度）
        start_idx = 0
        if 'policy_year' in row:
            # 验证第一个数字确实是年度
            first_num = _parse_money(numbers[0]) if numbers else None
            if first_num is not None and first_num == row['policy_year']:
                start_idx = 1  # 跳过年度对应的数字
            # 如果第一个数字是大的金额（如50000），说明行首没有年度列
            elif first_num is not None and first_num > 100:
                start_idx = 0  # 从头开始分配给 value_columns

        for i, num_str in enumerate(numbers[start_idx:], start=start_idx):
            val = _parse_money(num_str)
            if val is None:
                continue
            col_idx = i - start_idx
            if col_idx < len(value_columns):
                _, field = value_columns[col_idx]
                row[field] = val
    else:
        # 没有列位置信息，按顺序猜测
        all_fields = ['policy_year', 'total_premium_paid', 'guaranteed_cash_value',
                       'reversionary_bonus', 'terminal_dividend', 'total_surrender_value',
                       'death_benefit']
        for i, num_str in enumerate(numbers):
            if i >= len(all_fields):
                break
            val = _parse_money(num_str)
            if val is not None:
                row[all_fields[i]] = val

    # 如果没有识别到保单年度，检查是否有"年龄"列推算
    if 'policy_year' not in row:
        age_match = re.search(r'(\d{1,3})\s*岁', line)
        if age_match:
            age = int(age_match.group(1))
            row['_age'] = age  # 留给上层推算

    return row if row else None


def _fill_missing_premiums(rows: list[dict], annual_premium: float | None) -> list[dict]:
    """填充缺失的 total_premium_paid。"""
    if not annual_premium or annual_premium <= 0:
        return rows
    for row in rows:
        if row.get('total_premium_paid') is None and row.get('policy_year') is not None:
            row['total_premium_paid'] = annual_premium * row['policy_year']
    return rows


def _ensure_required_fields(row: dict) -> dict:
    """确保每行有所有必需字段。"""
    required = {
        'policy_year': None,
        'total_premium_paid': None,
        'guaranteed_cash_value': None,
        'reversionary_bonus': None,
        'terminal_dividend': None,
        'total_surrender_value': None,
        'death_benefit': None,
    }
    result = dict(required)
    result.update(row)
    return result


# ─── 提领表提取 ──────────────────────────────────────────

_WITHDRAWAL_HEADER_KEYWORDS = [
    '提取', '提款', '现金提取', '現金提取', '款项提取', '款項提取',
    'withdrawal', 'cash withdrawal',
]

_WITHDRAWAL_REQUIRED_COLS = [
    '价值', '價值', 'surrender', 'cash', 'value', '退保',
]


def _extract_withdrawal_rows(text: str) -> list[dict]:
    """从 PDF 文本中提取提领/提款演示表。

    注意：只提取"总额"列，不取"保证"子列。
    """
    rows = []
    lines = text.split('\n')
    in_table = False
    columns: list[tuple[int, str]] = []
    consecutive_non_data = 0
    MAX_NON_DATA_LINES = 5

    for line in lines:
        stripped = line.strip()
        if not stripped:
            continue

        if not in_table:
            has_header = any(kw in stripped for kw in _WITHDRAWAL_HEADER_KEYWORDS)
            has_value = any(kw in stripped.lower() for kw in _WITHDRAWAL_REQUIRED_COLS)
            if has_header and has_value:
                columns = _detect_columns(stripped)
                if len(columns) >= 2:
                    in_table = True
                    consecutive_non_data = 0
                    logger.debug(f"检测到提领表头: {[(c[1], c[0]) for c in columns]}")
            continue

        # 跳过子表头（"保证 非保证 总额"等）
        subheader_pats = ['保证', '保證', '非保证', '非保證', '总额', '總額',
                          'guaranteed', 'non-guaranteed', 'total']
        if sum(1 for p in subheader_pats if p in stripped.lower()) >= 2:
            continue

        numbers = re.findall(r'[\d,]+(?:\.\d+)?', stripped)
        if not numbers:
            consecutive_non_data += 1
            if consecutive_non_data >= MAX_NON_DATA_LINES:
                break
            continue

        consecutive_non_data = 0
        row = _parse_withdrawal_row(stripped, columns, numbers)
        if row and row.get('policy_year') is not None:
            rows.append(row)

    return rows


def _parse_withdrawal_row(
    line: str, columns: list[tuple[int, str]], numbers: list[str]
) -> dict | None:
    """解析提领表单行。"""
    row = {}
    year_match = re.match(r'^\s*(\d{1,3})\b', line)
    if year_match:
        year_val = int(year_match.group(1))
        if 0 < year_val <= 100:
            row['policy_year'] = year_val

    # 提领表标准字段（按优先级）
    withdrawal_fields = [
        'annual_withdrawal', 'total_withdrawn',
        'surrender_value_before', 'surrender_value_after',
    ]

    if columns:
        value_columns = [(pos, f) for pos, f in columns if f != 'policy_year']
        start_idx = 0
        if 'policy_year' in row:
            first_num = _parse_money(numbers[0]) if numbers else None
            if first_num is not None and first_num == row['policy_year']:
                start_idx = 1

        for i, num_str in enumerate(numbers[start_idx:], start=start_idx):
            val = _parse_money(num_str)
            if val is None:
                continue
            col_idx = i - start_idx
            if col_idx < len(value_columns):
                _, field = value_columns[col_idx]
                row[field] = val
    else:
        for i, num_str in enumerate(numbers):
            if i == 0 and 'policy_year' in row:
                continue
            field_idx = i - 1 if 'policy_year' in row else i
            if field_idx >= len(withdrawal_fields):
                break
            val = _parse_money(num_str)
            if val is not None:
                row[withdrawal_fields[field_idx]] = val

    return row if row else None


def _ensure_withdrawal_fields(row: dict) -> dict:
    """确保提领行有所有必需字段。"""
    required = {
        'policy_year': None,
        'annual_withdrawal': None,
        'total_withdrawn': None,
        'surrender_value_before': None,
        'surrender_value_after': None,
    }
    result = dict(required)
    result.update(row)
    return result


# ─── 产品类型识别 ─────────────────────────────────────────

def _detect_product_type(text: str, benefit_rows: list[dict]) -> str:
    """从文本和提取数据推断产品类型：savings / ci / iul。"""
    text_lower = text.lower()

    # 文本关键词判断
    ci_keywords = ['危疾', '重疾', '重大疾病', 'critical illness', 'ci plan',
                   '严重疾病', '危疾保障', 'dread disease']
    iul_keywords = ['iul', 'index universal', 'universal life', '指数型万用',
                    '万用寿险', '萬用壽險', 'index account', 'index_accounts']

    ci_score = sum(1 for kw in ci_keywords if kw in text_lower)
    iul_score = sum(1 for kw in iul_keywords if kw in text_lower)

    # 数据特征判断
    for row in benefit_rows:
        if row.get('account_value') or row.get('non_guaranteed_account_value'):
            iul_score += 3
        if row.get('death_benefit') and not row.get('guaranteed_cash_value'):
            ci_score += 1

    # policy 字段判断
    if re.search(r'(?:保额|投保额|sum\s*insured|保額)\s*[：:]\s*[\d,]+', text_lower):
        ci_score += 1

    if iul_score > ci_score and iul_score > 0:
        return 'iul'
    if ci_score > 0:
        return 'ci'
    return 'savings'


# ─── 主提取函数 ──────────────────────────────────────────

def extract_insurance_regex(pdf_text: str) -> dict:
    """从 PDF 原始文本中用纯正则提取结构化保险数据。

    Args:
        pdf_text: PDF 提取的原始文本

    Returns:
        符合 extraction schema 的 dict，字段缺失填 null
    """
    product_name = _extract_product_name(pdf_text) or 'unknown'
    currency = _extract_currency(pdf_text)
    annual_premium = _extract_annual_premium(pdf_text)
    insured_info = _extract_insured_info(pdf_text)
    smoker = _extract_smoker(pdf_text)
    premium_period = _extract_premium_payment_period(pdf_text)
    coverage_period = _extract_coverage_period(pdf_text)

    # 提取利益演示表
    benefit_rows = _extract_benefit_rows(pdf_text)

    # 提取提领表
    withdrawal_rows = _extract_withdrawal_rows(pdf_text)

    # 产品类型由上层 infer_plan_type() 推断（基于实际提取数据），此处不重复判断

    # 填充缺失保费
    benefit_rows = _fill_missing_premiums(benefit_rows, annual_premium)

    # 确保字段完整
    benefit_rows = [_ensure_required_fields(r) for r in benefit_rows]
    withdrawal_rows = [_ensure_withdrawal_fields(r) for r in withdrawal_rows]

    # 按年度排序并去重
    seen_years = set()
    deduped = []
    for row in sorted(benefit_rows, key=lambda r: r.get('policy_year') or 0):
        year = row.get('policy_year')
        if year is not None and year not in seen_years:
            seen_years.add(year)
            deduped.append(row)
    benefit_rows = deduped

    # 提领表去重
    seen_wd_years = set()
    deduped_wd = []
    for row in sorted(withdrawal_rows, key=lambda r: r.get('policy_year') or 0):
        year = row.get('policy_year')
        if year is not None and year not in seen_wd_years:
            seen_wd_years.add(year)
            deduped_wd.append(row)
    withdrawal_rows = deduped_wd

    # 提取保额（如果有）
    sum_insured = None
    si_match = re.search(
        r'(?:保额|投保额|保額|sum\s*insured)\s*[：:]\s*[\$UuSsHhKk]*\s*([\d,]+(?:\.\d+)?)',
        pdf_text, re.IGNORECASE,
    )
    if si_match:
        sum_insured = _parse_money(si_match.group(1))

    basic_plan_annual_premium, basic_premium_label = _extract_labeled_money(
        pdf_text,
        ["基本计划年保费", "基本計劃年保費", "Basic Plan Annual Premium"],
    )
    basic_sum_insured, basic_sum_label = _extract_labeled_money(
        pdf_text,
        ["基本计划名义金额", "基本計劃名義金額", "Basic Sum Assured", "Basic Notional Amount"],
    )
    first_year_amount_due, first_year_label = _extract_labeled_money(
        pdf_text,
        ["首年应缴金额", "首年應繳金額", "First Year Amount Due"],
    )

    logger.info(
        f"[RegexExtractor] 提取完成: product={product_name}, "
        f"currency={currency}, premium={annual_premium}, "
        f"age={insured_info.get('age')}, benefit_rows={len(benefit_rows)}, "
        f"withdrawal_rows={len(withdrawal_rows)}"
    )

    data = {
        'product_name': product_name,
        'product_type': None,  # 由上层 infer_plan_type() 基于实际数据推断
        'insured': {
            'name': None,
            'age': insured_info.get('age'),
            'gender': insured_info.get('gender'),
            'relation': None,
            'smoker': smoker,
        },
        'policy': {
            'product_name': product_name,
            'currency': currency,
            'sum_insured': sum_insured,
            'basic_sum_insured': basic_sum_insured,
            'basic_sum_insured_source_label': basic_sum_label,
            'annual_premium': annual_premium,
            'basic_plan_annual_premium': basic_plan_annual_premium,
            'basic_plan_annual_premium_source_label': basic_premium_label,
            'first_year_amount_due': first_year_amount_due,
            'first_year_amount_due_source_label': first_year_label,
            'premium_payment_period': premium_period,
            'coverage_period': coverage_period,
        },
        'benefit_illustration': benefit_rows,
        'withdrawal_illustration': withdrawal_rows,
        'sales_insights': None,
    }

    # CI 产品：提取保障项目（如果文本包含 CI 关键词）
    coverage_items = _extract_coverage_items(pdf_text)
    if coverage_items:
        data['coverage_items'] = coverage_items

    # IUL 产品：提取指数账户（如果文本包含 IUL 关键词）
    index_accounts = _extract_index_accounts(pdf_text)
    if index_accounts:
        data['index_accounts'] = index_accounts

    return data


def _extract_coverage_items(text: str) -> list[dict]:
    """提取危疾保险的保障项目。"""
    items = []
    # 匹配 "保障项目  赔付金额" 格式的表
    lines = text.split('\n')
    in_section = False
    for line in lines:
        stripped = line.strip()
        if not stripped:
            continue
        if '保障项目' in stripped or '保障範圍' in stripped or 'coverage' in stripped.lower():
            in_section = True
            continue
        if in_section:
            # 尝试匹配 "项目名 金额" 格式
            m = re.match(r'^(.{2,20})\s+[\$UuSsHhKk]*\s*([\d,]+(?:\.\d+)?)', stripped)
            if m:
                label = m.group(1).strip()
                amount = _parse_money(m.group(2))
                if amount and label:
                    items.append({'label': label, 'amount': amount, 'percentage': None, 'description': None})
            elif not re.search(r'\d', stripped):
                break  # 非数字行，可能到了下一节
    return items


def _extract_index_accounts(text: str) -> list[dict]:
    """提取 IUL 指数账户信息。"""
    accounts = []
    # 匹配 "账户名 配置比例 利率" 格式
    patterns = [
        r'(S&P\s*500|Hang\s*Seng|恒生指数|Global\s*index|指数\d?)\s+([\d.]+)%?\s+([\d.]+)%?\s+([\d.]+)%?',
        r'(S&P\s*500|Hang\s*Seng|恒生指数|Global\s*index)\s+([\d.]+)%',
    ]
    for p in patterns:
        for m in re.finditer(p, text, re.IGNORECASE):
            account = {
                'name': m.group(1).strip(),
                'allocation': float(m.group(2)),
                'current_rate': float(m.group(3)) if m.lastindex >= 3 else None,
                'guaranteed_floor': float(m.group(4)) if m.lastindex >= 4 else None,
            }
            accounts.append(account)
    return accounts


def count_benefit_rows(data: dict) -> int:
    """统计提取到的利益演示行数。"""
    rows = data.get('benefit_illustration', [])
    if not isinstance(rows, list):
        return 0
    return len(rows)