cfc/cfc-langgraph/app/parsers/pdf_parser.py

"""
菌群报告 PDF 解析器
从 extract_full_report_v5.py 提取核心逻辑，封装为可调用函数
"""
import re
from PyPDF2 import PdfReader

# === 常量 ===
RADICAL_MAP = {
    '\u2f52': '\u6c0f', '\u2f51': '\u6bcd', '\u2f59': '\u6b6f',
    '\u2f04': '\u4e59', '\u2f20': '\u4e00', '\u2f21': '\u4e28',
    '\u2f22': '\u4e3f', '\u2f23': '\u4e39', '\u2f2b': '\u5c38',
    '\u2f2d': '\u5c71', '\u2f44': '\u4e59', '\u2f53': '\u6c14',
    '\u2f55': '\u6c34', '\u2f5c': '\u725b', '\u2f5f': '\u7389',
    '\u2f7a': '\u7f8a', '\u2f81': '\u8089', '\u2f83': '\u81ea',
    '\u2f8a': '\u8272', '\u2f8e': '\u8840', '\u2f95': '\u79be',
    '\u2f96': '\u8c46', '\u2faf': '\u9762', '\u2fb9': '\u9999',
    '\u2fca': '\u9ed1', '\u2ec9': '\u8d1d', '\u2edd': '\u98df',
    '\u2ee2': '\u9a6c', '\u2ee9': '\u9ec4',
}

KNOWN_MACRO = ['碳水化合物', '蛋白质', '脂肪', '纤维素', '乳制品']
KNOWN_AMINO = ['苏氨酸', '异亮氨酸', '亮氨酸', '赖氨酸', '蛋氨酸', '胱氨酸',
    '苯丙氨酸', '酪氨酸', '缬氨酸', '组氨酸', '丙氨酸', '丝氨酸', '甘氨酸',
    '脯氨酸', '谷氨酸', '天门冬氨酸', '天冬氨酸', '天冬酰胺', '谷氨酰胺',
    '精氨酸', '色氨酸']
KNOWN_VITAMINS = ['维生素A', '维生素B1', '维生素B2', '维生素B5', '维生素B6',
    '叶酸', '维生素B12', '维生素C', '维生素D', '维生素K2', '维生素E']
KNOWN_TRACE = ['铁', '锌']
KNOWN_DISEASE_RISKS = ['炎症性肠炎', '肠易激综合征', '感染性腹泻', '自闭症',
    '抑郁症', '甲状腺疾病', '肺部感染或疾病', '自体免疫病', '结直肠癌',
    '肥胖', '便秘', '过敏', '失眠', '肝病', '肾病', '胃病', '胆病',
    '心脑血管疾病', 'II型糖尿病']
KNOWN_BARRIER = ['肠道炎症水平', '肠道产气', '肠道屏障', '脂多糖LPS',
    '次级胆汁酸', '对甲酚（p-Cresol）', '吲哚', '苯酚', '腐胺', '硫化氢', '尸胺']
KNOWN_SCFA = ['丁酸盐（Butyrate）', '丙酸盐（Propionate）', '乙酸盐（Acetate）', '异戊酸盐（Isovaleric）']
KNOWN_NEURO = ['血清素（5-HT）', 'γ-氨基丁酸（GABA）', '谷氨酸（Glutamate）',
    '色氨酸（Tryptophan）', 'DOPAC', '多巴胺', '组胺（Histamine）', '一氧化氮',
    '喹啉（Quinolinic）', '维生素K2', '肌醇（Inositol）', '肾上腺素',
    '去甲肾上腺素', '乙酰胆碱', '皮质醇']
KNOWN_ANTIBIOTICS = ['β-内酰胺酶类', '氨基糖苷类', '大环内酯类', '呋喃类',
    '喹诺酮类', '磺胺类', '甲氧苄啶类', '氯霉素类', '四环素类']
KNOWN_PATHOGENS = ['幽门螺杆菌', '艰难梭菌', '沙门氏菌', '志贺氏菌', '弯曲杆菌']


def norm(s):
    return ''.join(RADICAL_MAP.get(c, c) for c in s)


def detect_format(lines):
    """检测 triplet / inline 格式"""
    text = '\n'.join(lines)
    has_triplet = '指标范围' in text and '疾病风险评估' in text
    for line in lines:
        if len(line) > 15 and re.search(r'[\u4e00-\u9fff]+[\d.]+[\u4e00-\u9fff/]+', line):
            for known in KNOWN_DISEASE_RISKS:
                if known in line:
                    return 'inline'
    return 'triplet' if has_triplet else 'inline'


def extract_text(file_path):
    """读取 PDF 并提取文本"""
    reader = PdfReader(file_path)
    lines = []
    for page in reader.pages:
        text = norm(page.extract_text() or '')
        for line in text.split('\n'):
            ls = line.strip()
            if ls:
                lines.append(ls)
    return lines


def parse_overview(lines):
    """提取报告概述"""
    text = '\n'.join(lines)
    r = {}
    m = re.search(r'编号[：:\s]*(\d+)', text)
    if m: r['report_number'] = m.group(1)
    m = re.search(r'姓名[：:\s]*([\u4e00-\u9fff]{2,10})', text)
    if m: r['person_name'] = re.sub(r'(编号|年龄|性别|备注|肠道).*', '', m.group(1))[:4]
    m = re.search(r'年龄[：:\s]*(\d+)', text)
    if m: r['age'] = int(m.group(1))
    m = re.search(r'性别[：:\s]*([\u4e00-\u9fff])', text)
    if m: r['gender'] = 'male' if m.group(1) == '男' else 'female'
    for kw in ['健康总分', '菌群健康', '慢病控制', '营养均衡', '肠道菌群平衡',
               '菌群多样性', '有益菌', '有害菌', '核心菌属']:
        m = re.search(rf'{kw}\s*(\d+)', text)
        if m: r[kw] = int(m.group(1))
    m = re.search(r'肠道预测年龄[：:\s]*([\d.]+)', text)
    if m: r['gut_age'] = m.group(1)
    m = re.search(r'肠型[：:\s]*(\S+)', text)
    if m: r['gut_type'] = m.group(1)
    return r


def parse_triplet_until(lines, stop_markers):
    """三元组解析：3行一组 名称/数值/状态"""
    results = []
    i = 0
    while i < len(lines):
        if any(lines[i] == sm or lines[i].startswith(sm) for sm in stop_markers):
            break
        if lines[i] in ('指标范围', '名称', '丰度', '评估'):
            i += 1
            continue
        name = lines[i]
        if i + 2 >= len(lines): break
        val = lines[i + 1]
        status = lines[i + 2]
        if re.match(r'^-?\d+\.?\d*$', val):
            results.append({'name': name, 'value': val, 'status': status})
            i += 3
        else:
            i += 1
    return results


def parse_report_pdf(file_path: str) -> dict:
    """主函数：解析 PDF 返回结构化数据"""
    lines = extract_text(file_path)
    fmt = detect_format(lines)
    result = {'format': fmt, 'overview': parse_overview(lines)}

    # 疾病风险评估
    for i, line in enumerate(lines):
        if '疾病风险评估' in line and '注' not in line:
            risks = parse_triplet_until(lines[i+1:],
                ['主要营养评估', '氨基酸评估', '维生素评估', '微量元素评估', '抗生素风险评估'])
            result['disease_risks'] = [r for r in risks if '注' not in r['name']]
            break

    # 主要营养评估
    for i, line in enumerate(lines):
        if '主要营养评估' in line:
            nutrients = parse_triplet_until(lines[i+1:], ['氨基酸评估'])
            result['nutrition'] = nutrients[:5]
            break

    # 氨基酸评估
    for i, line in enumerate(lines):
        if '氨基酸评估' in line:
            aminos = parse_triplet_until(lines[i+1:], ['维生素评估', '微量元素评估'])
            result['amino_acids'] = aminos
            break

    # 维生素评估
    for i, line in enumerate(lines):
        if '维生素评估' in line:
            vits = parse_triplet_until(lines[i+1:], ['微量元素评估', '抗生素风险评估'])
            result['vitamins'] = [r for r in vits if '维生素' in r['name']]
            result['trace_elements'] = [r for r in vits if '维生素' not in r['name']]
            break

    return result


def parse_report_pdf_with_fallback(file_path: str) -> dict:
    """算法解析 + 简单校验，返回结构化数据"""
    result = parse_report_pdf(file_path)
    # 简单校验：如果关键字段缺失，标记为解析不完整
    if not result.get('overview', {}).get('overallScore') and \
       not result.get('overview', {}).get('健康总分'):
        result['_parse_incomplete'] = True
    return result