"""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|$)', ] for p in patterns: m = re.search(p, text, re.IGNORECASE) if m: name = m.group(1).strip() # 过滤掉太短或纯数字的结果 if len(name) >= 2 and not name.isdigit(): return name return None def _extract_currency(text: str) -> str | None: """提取保单货币，支持多币种（优先匹配保费行中的币种符号）。 未识别时返回 None（由用户或后续流程确认），不再默认 USD。 """ # 按优先级搜索 patterns = [ (r'(?:保单货币|保费货币|Currency)\s*[：:]\s*(USD|USB|HKD|CNY|RMB|SGD|GBP|EUR)', 'direct'), (r'\b(USD)\b', 'usd'), (r'\b(HKD)\b', 'hkd'), (r'\b(CNY|RMB)\b', 'cny'), (r'\b(SGD)\b', 'sgd'), (r'U\s*S\s*\$', 'us_symbol'), (r'H\s*K\s*\$', 'hk_symbol'), ] for pattern, tag in patterns: m = re.search(pattern, text, re.IGNORECASE) if m: if tag == 'us_symbol': return 'USD' if tag == 'hk_symbol': return 'HKD' value = m.group(1).upper() if value == "USB": return "USD" if value == "RMB": return "CNY" return value return None def _extract_labeled_money(text: str, labels: list[str]) -> tuple[float | None, str | None]: """提取明确标签后的金额，同时保留原始命中标签。""" label_pattern = "|".join( r"\s*".join(re.escape(char) for char in label if not char.isspace()) for label in labels ) match = re.search( rf"({label_pattern})\s*[：:]?\s*(?:[A-Z]{{2,3}}|[￥¥$£€]|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)", r"(?:非吸烟者|非吸煙者|不吸烟|不吸煙)", ] 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'(?:首期规划保费|首期規劃保費|偿还至形成基金所需保费|償還至形成基金所需保費)\s*[:：]?\s*(?:[A-Z]{2,3})?\$?\s*([\d,]+(?:\.\d+)?)', 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+)?)', r'(?:投保时|投保時)\s*(?:年缴保费|年繳保費)\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': 'age', '受保人年齡': 'age', '年龄': 'age', '年齡': 'age', 'insured age': 'age', 'age': 'age', # 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', '累计保费': 'total_premium_paid', '累計保費': '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', '非保证现金价值': 'non_guaranteed_cash_value', '非保證現金價值': 'non_guaranteed_cash_value', '非保证身故赔偿': 'non_guaranteed_death_benefit', '非保證身故賠償': 'non_guaranteed_death_benefit', 'non-guaranteed account value': 'non_guaranteed_account_value', 'guaranteed account value': 'guaranteed_account_value', 'non-guaranteed cash value': 'non_guaranteed_cash_value', 'non-guaranteed death benefit': 'non_guaranteed_death_benefit', '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]]: """检测表头槽位和字段名。返回 [(slot_index, field_name), ...]。""" columns = [] # 表头和数据行都按槽位解析，避免数据中的“—”被数字正则丢弃后整行左移。 parts = re.split(r'\t', header_line.strip()) if '\t' in header_line else re.split(r'\s{2,}', header_line.strip()) for slot_index, part in enumerate(parts): field = _normalize_column_name(part) if field: columns.append((slot_index, field)) # 如果没有检测到列，尝试逐个关键词搜索 if len(columns) < 2: matches = [] for alias, field in _COLUMN_ALIASES.items(): idx = header_line.lower().find(alias) if idx >= 0: matches.append((idx, field)) columns = [] for _, field in sorted(matches, key=lambda item: item[0]): if not any(existing == field for _, existing in columns): columns.append((len(columns), 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 or row.get('age') 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） has_policy_year_column = any(field == 'policy_year' for _, field in columns) year_match = re.match(r'^\s*(\d{1,3})\b', line) if has_policy_year_column else None if year_match: year_val = int(year_match.group(1)) if 0 < year_val <= 100: row['policy_year'] = year_val # 优先按表格槽位映射。制表符保留空槽；空格表格以两个以上空格分栏。 if columns: cells = line.strip().split('\t') if '\t' in line else re.split(r'\s{2,}', line.strip()) max_slot = max(slot for slot, _ in columns) if len(cells) == 1: compact_cells = re.findall( r'[\d,]+(?:\.\d+)?|[—–-]+|N/?A', line, re.IGNORECASE, ) if len(compact_cells) > max_slot: cells = compact_cells if len(cells) > 1 and len(cells) > max_slot: for slot, field in columns: val = _parse_money(cells[slot]) if val is not None: row[field] = val if row.get('policy_year') is not None: try: row['policy_year'] = int(row['policy_year']) except (TypeError, ValueError): pass else: # 无可靠分栏信息时保留旧的顺序回退，供紧凑纯数字表使用。 value_columns = [(slot, f) for slot, 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: 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 elif first_num is not None and first_num > 100: start_idx = 0 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 if row.get('age') is not None and not 0 <= row['age'] <= 150: row['age'] = None # 无明确年龄列时，保留带“岁”的年龄供上层结合投保年龄推算。 if 'policy_year' not in row and row.get('age') is None: age_match = re.search(r'(\d{1,3})\s*岁', line) if age_match: row['age'] = int(age_match.group(1)) return row if row else None def _derive_policy_years(rows: list[dict], insured_age: int | float | None) -> list[dict]: """仅在表格只有年龄列时，使用明确投保年龄推算保单年度。""" if insured_age is None: return rows try: issue_age = int(insured_age) except (TypeError, ValueError): return rows ages = [] for row in rows: try: if row.get('policy_year') is None and row.get('age') is not None: ages.append(int(row['age'])) except (TypeError, ValueError): continue if not ages: return rows first_table_age = min(ages) if first_table_age not in (issue_age, issue_age + 1): return rows for row in rows: if row.get('policy_year') is not None or row.get('age') is None: continue try: derived = int(row['age']) - first_table_age + 1 except (TypeError, ValueError): continue if 1 <= derived <= 100: row['policy_year'] = derived row['policy_year_source'] = 'derived_from_age' return rows def _ensure_required_fields(row: dict) -> dict: """确保每行有所有必需字段。""" required = { 'policy_year': None, 'age': None, 'total_premium_paid': None, 'guaranteed_cash_value': None, 'reversionary_bonus': None, 'terminal_dividend': None, 'total_surrender_value': None, 'death_benefit': None, 'guaranteed_account_value': None, 'non_guaranteed_account_value': None, 'non_guaranteed_cash_value': None, 'non_guaranteed_death_benefit': None, 'cost_of_insurance': None, } result = dict(required) result.update(row) return result # ─── 提领表提取 ────────────────────────────────────────── _WITHDRAWAL_HEADER_KEYWORDS = [ '提取', '提款', '提领', '提領', '领取', '領取', '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 pending_header_lines = 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: pending_header_lines = 2 if (has_header or pending_header_lines > 0) and has_value: candidate_columns = _detect_columns(stripped) columns = candidate_columns 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]}") pending_header_lines = 0 continue if pending_header_lines > 0 and not has_header: pending_header_lines -= 1 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', '指數型萬用', '万用寿险', '萬用壽險', 'index account', 'indexed account', '指数账户', '指數賬戶', '指數戶口', '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) savings_score = 0 # 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('total_surrender_value') is not None and ( row.get('terminal_dividend') is not None or row.get('reversionary_bonus') is not None or row.get('guaranteed_cash_value') is not None ): savings_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 savings_score > ci_score and savings_score > 0: return 'savings' if ci_score > 0: return 'ci' return 'savings' def _extract_summary_fields_from_words(words: list[tuple]) -> dict: """按保单摘要表的横纵坐标提取明确金额列。""" headers = [] values = [] for word in words: if len(word) < 5: continue x0, y0, x1, y1, raw_text = word[:5] text = re.sub(r"\s+|[（(]\d+[）)]", "", str(raw_text)) field = None label = None if "基本金额" in text or "基本金額" in text: field, label = "basic_sum_insured", "投保时基本金额" elif "投保时保额" in text or "投保時保額" in text: field, label = "sum_insured", "投保时保额" elif "年缴保费" in text or "年繳保費" in text: field, label = "annual_premium", "投保时年缴保费" if field: headers.append((field, label, float(x0), float(y0), float(x1), float(y1))) value = _parse_money(str(raw_text)) if value is not None and re.fullmatch(r"[\d,]+(?:\.\d+)?", str(raw_text).strip()): values.append((value, float(x0), float(y0), float(x1), float(y1))) result = {} for field, label, hx0, _, hx1, hy1 in headers: candidates = [] header_center = (hx0 + hx1) / 2 for value, vx0, vy0, vx1, _ in values: dy = vy0 - hy1 value_center = (vx0 + vx1) / 2 if 0 <= dy <= 80 and hx0 - 25 <= value_center <= hx1 + 25: candidates.append((dy, abs(value_center - header_center), value)) if candidates and field not in result: _, _, value = min(candidates) result[field] = value result[f"{field}_source_label"] = label return result def extract_policy_summary_layout(pdf_path: str, max_pages: int = 3) -> dict: """从 PDF 单词坐标提取摘要金额；解析失败时返回空字典。""" try: try: import fitz except ImportError: import pymupdf as fitz result = {} with fitz.open(pdf_path) as doc: for page_index in range(min(len(doc), max_pages)): page_result = _extract_summary_fields_from_words( doc[page_index].get_text("words") ) for key, value in page_result.items(): result.setdefault(key, value) if all(key in result for key in ( "basic_sum_insured", "sum_insured", "annual_premium" )): break return result except Exception as exc: logger.debug("保单摘要坐标提取失败: %s", exc) return {} def _expand_multiline_table_rows(matrix: list[list]) -> list[list]: """展开 PyMuPDF 把整列数据压进单个单元格的表格。""" expanded = [] for row in matrix: parts = [str(cell or "").splitlines() for cell in row] row_count = max((len(items) for items in parts), default=0) aligned_columns = sum(1 for items in parts if len(items) == row_count) if row_count >= 3 and aligned_columns >= 5: for index in range(row_count): expanded.append([ items[index] if len(items) == row_count else "" for items in parts ]) else: expanded.append(row) return expanded def _parse_iul_year_age(cells: list) -> tuple[int, int | None, set[int]] | None: """识别 `1/49`、`1 49` 或分列的年度/年龄。""" for index, cell in enumerate(cells): text = str(cell or "").strip() match = re.fullmatch(r"[#|]?\s*(\d{1,3})\s*[/\s]\s*(\d{1,3})\s*", text) if match: year, age = int(match.group(1)), int(match.group(2)) if 1 <= year <= 100 and 1 <= age <= 130: return year, age, {index} small_values = [] for index, cell in enumerate(cells[:5]): match = re.fullmatch(r"[#|]?\s*(\d{1,3})\s*", str(cell or "").strip()) if match: small_values.append((index, int(match.group(1)))) for position in range(len(small_values) - 1): year_index, year = small_values[position] age_index, age = small_values[position + 1] if 1 <= year <= 100 and year <= age <= 130: return year, age, {year_index, age_index} return None def _iul_header_columns(header_rows: list[list], column_count: int) -> list[str]: headers = [] for column in range(column_count): headers.append(" ".join( str(row[column] or "").strip() for row in header_rows if column < len(row) and str(row[column] or "").strip() ).lower()) return headers def _find_iul_column(headers: list[str], patterns: tuple[str, ...], *, rightmost=False) -> int | None: matches = [] for index, header in enumerate(headers): compact = re.sub(r"\s+", "", header) if any(pattern in compact for pattern in patterns): matches.append(index) if not matches: return None return matches[-1] if rightmost else matches[0] def _find_iul_account_column(headers: list[str]) -> int | None: candidates = [] patterns = ("accountvalue", "accumulationvalue", "账户价值", "賬戶價值", "户口价值", "戶口價值") for index, header in enumerate(headers): compact = re.sub(r"\s+", "", header) if not any(pattern in compact for pattern in patterns): continue polluted = any(value in compact for value in ( "退保", "保证", "保證", "guaranteed", "lesssurrender" )) candidates.append((0 if polluted else 10, index)) return max(candidates)[1] if candidates else None def _parse_iul_table_matrix(matrix: list[list], source_page: int = 1) -> list[dict]: """把保险公司 IUL 说明表转换为统一利益行。""" matrix = _expand_multiline_table_rows(matrix or []) parsed_rows = [] first_data_index = None for row_index, cells in enumerate(matrix): year_age = _parse_iul_year_age(cells) if year_age: first_data_index = row_index break if first_data_index is None: return [] column_count = max((len(row) for row in matrix), default=0) headers = _iul_header_columns(matrix[:first_data_index], column_count) death_col = _find_iul_column( headers, ("deathbenefit", "身故利益", "身故權益", "身故赔偿", "身故賠償", "身故保险金", "身故保險金"), rightmost=True, ) surrender_col = _find_iul_column( headers, ("surrendervalue", "退保价值", "退保價值", "现金价值", "現金價值"), rightmost=True, ) account_col = _find_iul_account_column(headers) total_premium_col = _find_iul_column( headers, ("totalpremium", "总年度保费(累计)", "總年度保費(累計)", "缴付保费总额", "繳付保費總額", "累计保费", "累計保費"), ) annual_premium_col = _find_iul_column( headers, ("premiumschedule", "basicpremium", "保费计划", "保費計劃", "保费进度", "保費進度"), ) if annual_premium_col is None: annual_premium_col = next(( index for index, header in enumerate(headers) if ("保单年度" in header or "保單年度" in header) and ("保费" in header or "保費" in header) ), None) sum_insured_col = _find_iul_column( headers, ("suminsured", "保单面值", "保單面值", "保障金额", "保障金額", "投保金额", "投保金額"), rightmost=True, ) # 利益表必须同时有退保价值和身故利益，避免误把收费表识别成利益表。 if death_col is None or surrender_col is None: return [] for cells in matrix[first_data_index:]: year_age = _parse_iul_year_age(cells) if not year_age: continue year, age, identity_columns = year_age def value_at(column: int | None) -> float | None: if column is None or column >= len(cells) or column in identity_columns: return None return _parse_money(str(cells[column] or "")) surrender = value_at(surrender_col) death = value_at(death_col) if surrender is None and death is None: continue parsed_rows.append({ "policy_year": year, "age": age, "total_premium_paid": value_at(total_premium_col), "_annual_premium_paid": value_at(annual_premium_col), "non_guaranteed_account_value": value_at(account_col), "non_guaranteed_cash_value": surrender, "total_surrender_value": surrender, "non_guaranteed_death_benefit": death, "death_benefit": death, "_sum_insured": value_at(sum_insured_col), "source_page": source_page, }) return parsed_rows def _has_iul_text(text: str) -> bool: compact = re.sub(r"\s+", "", (text or "").lower()) return any(value in compact for value in ( "iul", "universallife", "indexaccount", "indexedaccount", "指数账户", "指數賬戶", "指數戶口", "指数型万用", "指數型萬用", "萬用壽險", )) def _extract_iul_slash_rows(text: str, issue_age: int | None = None) -> list[dict]: """解析 OCR 后形如 `1/49 80,060 ...` 的 IUL 行。""" if not _has_iul_text(text): return [] selected = {} scenario_score = 0 source_page = 1 cumulative_premium = 0.0 for line in text.splitlines(): stripped = line.strip().strip("|") page_match = re.search(r"(?:\[PAGE|--- Page)\s+(\d+)", stripped, re.IGNORECASE) if page_match: source_page = int(page_match.group(1)) scenario_score = 0 compact = re.sub(r"\s+", "", stripped).lower() if any(value in compact for value in ("当前假设", "當前假設", "现时假设", "現時假設", "currentassumed")): scenario_score = 20 elif any(value in compact for value in ("保证派息率", "保證派息率", "guaranteedbasis")): scenario_score = min(scenario_score, -10) match = re.match(r"[#|]?\s*(\d{1,3})\s*/\s*(\d{1,3})\s+(.+)$", stripped) if not match: continue year, age = int(match.group(1)), int(match.group(2)) values = [_parse_money(value) for value in re.findall(r"[\d,]+(?:\.\d+)?", match.group(3))] values = [value for value in values if value is not None] if len(values) < 7 or values[-1] < 10_000 or values[-2] < 10_000: continue if issue_age and 1 <= age - int(issue_age) <= 100: year = age - int(issue_age) if not 1 <= year <= 100: continue annual_premium, account_value = values[0], values[1] surrender_value, sum_insured, death_benefit = values[-3:] candidate = { "policy_year": year, "age": age, "_annual_premium_paid": annual_premium, "non_guaranteed_account_value": account_value, "non_guaranteed_cash_value": surrender_value, "total_surrender_value": surrender_value, "non_guaranteed_death_benefit": death_benefit, "death_benefit": death_benefit, "_sum_insured": sum_insured, "source_page": source_page, } existing = selected.get(year) if existing is None or scenario_score >= existing[0]: selected[year] = (scenario_score, candidate) result = [] for year in sorted(selected): row = selected[year][1] cumulative_premium += row.get("_annual_premium_paid") or 0 row["total_premium_paid"] = cumulative_premium result.append(row) return result def _extract_iul_spaced_rows(text: str, issue_age: int | None = None) -> list[dict]: """解析 OCR 后年度、年龄分列但仍位于同一文本行的 IUL 表格。""" if not _has_iul_text(text): return [] raw_candidates = [] scenario_score = 0 source_page = 1 for line in text.splitlines(): stripped = line.strip().strip("|") page_match = re.search(r"(?:\[PAGE|--- Page)\s+(\d+)", stripped, re.IGNORECASE) if page_match: source_page = int(page_match.group(1)) scenario_score = 0 compact = re.sub(r"\s+", "", stripped).lower() if any(value in compact for value in ( "当前假设", "當前假設", "现时假设", "現時假設", "currentassumed", "currentcharges", )): scenario_score = 20 elif any(value in compact for value in ( "保证派息率", "保證派息率", "guaranteedcrediting", "guaranteedbasis", )): scenario_score = min(scenario_score, -10) match = re.match(r"[#|]?\s*(\d{1,3})\s+(\d{1,3})\s+(.+)$", stripped) if not match: continue raw_year, age = int(match.group(1)), int(match.group(2)) values = [_parse_money(value) for value in re.findall(r"[\d,]+(?:\.\d+)?", match.group(3))] values = [value for value in values if value is not None] if len(values) < 7 or values[-1] < 10_000 or values[-2] < 10_000: continue raw_candidates.append((scenario_score, source_page, raw_year, age, values)) offsets = [age - year for _, _, year, age, _ in raw_candidates if 1 <= year <= 100] if issue_age: inferred_issue_age = int(issue_age) elif offsets: counts = {value: offsets.count(value) for value in set(offsets)} inferred_issue_age = max(counts, key=counts.get) else: inferred_issue_age = None selected = {} for score, page, raw_year, age, values in raw_candidates: year = age - inferred_issue_age if inferred_issue_age is not None else raw_year if not 1 <= year <= 100: continue annual_premium, account_value = values[0], values[1] surrender_value, sum_insured, death_benefit = values[-3:] row = { "policy_year": year, "age": age, "_annual_premium_paid": annual_premium, "non_guaranteed_account_value": account_value, "non_guaranteed_cash_value": surrender_value, "total_surrender_value": surrender_value, "non_guaranteed_death_benefit": death_benefit, "death_benefit": death_benefit, "_sum_insured": sum_insured, "source_page": page, } existing = selected.get(year) if existing is None or score >= existing[0]: selected[year] = (score, row) result = [] cumulative_premium = 0.0 for year in sorted(selected): row = selected[year][1] cumulative_premium += row.get("_annual_premium_paid") or 0 row["total_premium_paid"] = cumulative_premium result.append(row) return result def _extract_savings_scenario_rows(text: str, issue_age: int | None = None) -> list[dict]: """合并分开列示的身故利益表与退保价值表。""" raw_candidates = [] table_mode = None source_page = 1 for line in text.splitlines(): stripped = line.strip().strip("|") page_match = re.search(r"(?:\[PAGE|--- Page)\s+(\d+)", stripped, re.IGNORECASE) if page_match: source_page = int(page_match.group(1)) compact = re.sub(r"\s+", "", stripped).lower() if any(value in compact for value in ("deathbenefit", "死亡利益", "身故利益", "身故权益", "身故權益")): table_mode = "death" elif any(value in compact for value in ("surrendervalue", "退保价值", "退保價值")): table_mode = "surrender" elif any(value in compact for value in ( "survivalbenefit", "生存利益", "现金红利", "現金紅利", "cashbonus", )): # 后续通常是另一张利益表，不能继续沿用上一页的退保表列含义。 table_mode = None if not table_mode: continue match = re.match(r"[#|]?\s*(\d{1,3})\s*/\s*(\d{1,3})\s+(.+)$", stripped) if not match: # 部分英文计划书将保单年度和年龄渲染为两个独立列，OCR 后没有斜杠。 match = re.match(r"[#|]?\s*(\d{1,3})\s+(\d{1,3})\s+(.+)$", stripped) if not match: continue raw_year, age = int(match.group(1)), int(match.group(2)) values = [_parse_money(value) for value in re.findall(r"[\d,]+(?:\.\d+)?", match.group(3))] values = [value for value in values if value is not None] if len(values) < 6: continue raw_candidates.append((source_page, table_mode, raw_year, age, values)) offsets = [age - year for _, _, year, age, _ in raw_candidates if 1 <= year <= 100] if issue_age and 1 <= int(issue_age) <= 120: inferred_issue_age = int(issue_age) elif offsets: counts = {value: offsets.count(value) for value in set(offsets)} inferred_issue_age = max(counts, key=counts.get) else: inferred_issue_age = None by_year = {} for page, mode, raw_year, age, values in raw_candidates: year = age - inferred_issue_age if inferred_issue_age is not None else raw_year if not 1 <= year <= 100: continue row = by_year.setdefault(year, { "policy_year": year, "age": age, "total_premium_paid": values[0], "source_page": page, }) row["total_premium_paid"] = values[0] if mode == "death": row["death_benefit"] = values[3] else: row["guaranteed_cash_value"] = values[1] row["terminal_dividend"] = values[2] row["total_surrender_value"] = values[3] row["source_page"] = page return [by_year[year] for year in sorted(by_year)] def extract_iul_layout(pdf_path: str, max_pages: int = 12) -> dict: """按 PDF 表格坐标提取 IUL 摘要与非保证利益表。""" try: try: import fitz except ImportError: import pymupdf as fitz candidates = [] with fitz.open(pdf_path) as document: for page_index in range(min(len(document), max_pages)): page = document[page_index] page_text = page.get_text().lower() compact_page_text = re.sub(r"\s+", "", page_text) scenario_score = 0 if any(value in compact_page_text for value in ( "当前假设", "當前假設", "现时假设", "現時假設", "non-guaranteed", "nonguaranteed", "currentassumed", "currentcharges", )): scenario_score = 20 elif any(value in compact_page_text for value in ( "保证基础", "保證基礎", "guaranteedbasis", "maximumcharges", )): scenario_score = -10 tables = list(page.find_tables().tables) if not tables: tables = list(page.find_tables(strategy="text").tables) parsed_on_page = [] for table in tables: parsed_on_page.extend(_parse_iul_table_matrix( table.extract(), source_page=page_index + 1 )) if not parsed_on_page and tables: for table in page.find_tables(strategy="text").tables: parsed_on_page.extend(_parse_iul_table_matrix( table.extract(), source_page=page_index + 1 )) for row in parsed_on_page: candidates.append((scenario_score, row)) selected = {} for scenario_score, row in candidates: year = row.get("policy_year") completeness = sum(value is not None for value in row.values()) existing = selected.get(year) rank = (scenario_score, completeness) if existing is None or rank > existing[0]: selected[year] = (rank, row) rows = [selected[year][1] for year in sorted(selected) if year] if len(rows) < 3: return {} previous_total = 0.0 cumulative_premium = 0.0 annual_contributions = [] issue_ages = [] sum_insured_values = [] pay_years = [] for row in rows: annual = row.get("_annual_premium_paid") total = row.get("total_premium_paid") if annual is None and total is not None: annual = max(0.0, total - previous_total) if total is not None: previous_total = total cumulative_premium = total else: cumulative_premium += annual or 0 row["total_premium_paid"] = cumulative_premium if annual and annual > 0: annual_contributions.append(annual) pay_years.append(row["policy_year"]) if row.get("age") is not None: issue_ages.append(int(row["age"]) - int(row["policy_year"])) if row.get("_sum_insured"): sum_insured_values.append(row["_sum_insured"]) row.pop("_annual_premium_paid", None) row.pop("_sum_insured", None) def most_common(values: list[float]) -> float | None: if not values: return None counts = {} for value in values: counts[value] = counts.get(value, 0) + 1 return max(counts, key=counts.get) annual_premium = most_common(annual_contributions) policy = {} if annual_premium: policy.update({ "annual_premium": annual_premium, "annual_premium_source_label": "IUL利益表保费列", "initial_premium": annual_contributions[0], "first_year_amount_due": annual_contributions[0], "first_year_amount_due_source_label": "IUL利益表首年保费", }) if pay_years: policy["premium_payment_period"] = max(pay_years) policy["premium_payment_period_source_label"] = "IUL利益表保费列" sum_insured = most_common(sum_insured_values) if sum_insured: policy["sum_insured"] = sum_insured policy["sum_insured_source_label"] = "IUL利益表保额列" insured = {} issue_age = most_common(issue_ages) if issue_age and 0 < issue_age <= 120: insured["age"] = int(issue_age) return { "insured": insured, "policy": policy, "benefit_illustration": rows, } except Exception as exc: logger.debug("IUL 表格坐标提取失败: %s", exc) return {} # ─── 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, annual_premium_label = _extract_labeled_money( pdf_text, ["投保时年缴保费", "投保時年繳保費", "年缴保费", "年繳保費", "Annual Premium"], ) if annual_premium is None: 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) iul_slash_rows = _extract_iul_slash_rows(pdf_text, insured_info.get('age')) iul_spaced_rows = _extract_iul_spaced_rows(pdf_text, insured_info.get('age')) iul_line_rows = max((iul_slash_rows, iul_spaced_rows), key=len) if len(iul_line_rows) >= 3: benefit_rows = iul_line_rows savings_scenario_rows = _extract_savings_scenario_rows(pdf_text, insured_info.get('age')) if not iul_line_rows and len(savings_scenario_rows) >= 3: benefit_rows = savings_scenario_rows benefit_rows = _derive_policy_years(benefit_rows, insured_info.get('age')) # 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 # 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, sum_insured_label = _extract_labeled_money( pdf_text, ["投保时保额", "投保時保額", "Sum Insured", "Sum Assured", "Face Amount"], ) if sum_insured is None: si_match = re.search( r'(?:保额|投保额|保額|sum\s*(?:insured|assured))\s*[：:]\s*[\$UuSsHhKk]*\s*([\d,]+(?:\.\d+)?)', pdf_text, re.IGNORECASE, ) if si_match: sum_insured = _parse_money(si_match.group(1)) sum_insured_label = si_match.group(0).split(":", 1)[0].split("：", 1)[0] 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, [ "投保时基本金额", "投保時基本金額", "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, [ "投保时年缴总保费", "投保時年繳總保費", "首年应缴金额", "首年應繳金額", "First Year Amount Due", ], ) if sum_insured is None and basic_sum_insured is not None: sum_insured = basic_sum_insured if iul_line_rows: annual_values = [ row.get("_annual_premium_paid") for row in iul_line_rows if (row.get("_annual_premium_paid") or 0) > 0 ] if annual_values: annual_counts = {value: annual_values.count(value) for value in set(annual_values)} annual_premium = max(annual_counts, key=annual_counts.get) annual_premium_label = "IUL利益表保费列" first_year_amount_due = annual_values[0] first_year_label = "IUL利益表首年保费" premium_period = max( row["policy_year"] for row in iul_line_rows if (row.get("_annual_premium_paid") or 0) > 0 ) sum_values = [ row.get("_sum_insured") for row in iul_line_rows if (row.get("_sum_insured") or 0) > 0 ] if sum_values: sum_counts = {value: sum_values.count(value) for value in set(sum_values)} sum_insured = max(sum_counts, key=sum_counts.get) sum_insured_label = "IUL利益表保额列" for row in iul_line_rows: row.pop("_annual_premium_paid", None) row.pop("_sum_insured", None) elif savings_scenario_rows: premiums_by_year = [ (row.get("policy_year"), row.get("total_premium_paid")) for row in savings_scenario_rows if (row.get("total_premium_paid") or 0) > 0 ] increasing_years = [] previous_total = 0.0 for year, total in premiums_by_year: if total > previous_total: increasing_years.append(year) previous_total = total if increasing_years: premium_period = max(increasing_years) total_at_period = next( total for year, total in premiums_by_year if year == premium_period ) annual_premium = total_at_period / premium_period annual_premium_label = "利益表累计保费列" first_year_amount_due = premiums_by_year[0][1] first_year_label = "利益表首年累计保费" for row in benefit_rows: row.pop("_annual_premium_paid", None) row.pop("_sum_insured", None) 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, # 保持底层提取器中立；险种由 infer_plan_type 或文件名先验在上层确定。 'product_type': None, '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, 'sum_insured_source_label': sum_insured_label, 'basic_sum_insured': basic_sum_insured, 'basic_sum_insured_source_label': basic_sum_label, 'annual_premium': annual_premium, 'annual_premium_source_label': annual_premium_label, '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)