docs: remove deprecated extract_food_csv.py

docs/参考资料/extract_food_csv.py

@@ -1,355 +0,0 @@
-import sys, os, csv, re
-sys.stdout.reconfigure(encoding='utf-8')
-sys.stderr.reconfigure(encoding='utf-8')
-from PyPDF2 import PdfReader
-
-path = r'D:\workspace\cfc\docs\参考资料'
-outdir = path
-columns = ['名称', '分类', '推荐指数', '能量KJ', '蛋白g', '脂肪g', '碳水化合物g', '淀粉g', '总膳食纤维g', '胆固醇mg']
-known_cats = ['主食', '乳制品', '干果', '坚果', '快餐', '水产品', '水果', '汤', '肉类', '蔬菜', '豆类及豆制品', '蛋类', '饮料']
-
-# CJK Radical -> Standard Hanzi mapping (observed in these PDFs)
-_RADICAL_MAP = {
-    '\u2f24': '大',  # ⼤ -> 大
-    '\u2f29': '小',  # ⼩ -> 小
-    '\u2f2d': '山',  # ⼭ -> 山
-    '\u2f32': '干',  # ⼲ -> 干
-    '\u2f46': '无',  # ⽆ -> 无
-    '\u2f4a': '木',  # ⽊ -> 木
-    '\u2f50': '比',  # ⽐ -> 比
-    '\u2f54': '水',  # ⽔ -> 水
-    '\u2f55': '火',  # ⽕ -> 火
-    '\u2f5c': '牛',  # ⽜ -> 牛
-    '\u2f5f': '玉',  # ⽟ -> 玉
-    '\u2f62': '甘',  # ⽢ -> 甘
-    '\u2f63': '生',  # ⽣ -> 生
-    '\u2f64': '用',  # ⽤ -> 用
-    '\u2f69': '白',  # ⽩ -> 白
-    '\u2f6f': '石',  # ⽯ -> 石
-    '\u2f75': '竹',  # ⽵ -> 竹
-    '\u2f76': '米',  # ⽶ -> 米
-    '\u2f7b': '羽',  # ⽻ -> 羽
-    '\u2f7c': '老',  # ⽼ -> 老
-    '\u2f81': '肉',  # ⾁ -> 肉
-    '\u2f96': '豆',  # ⾖ -> 豆
-    '\u2f9d': '身',  # ⾝ -> 身
-    '\u2faf': '面',  # ⾯ -> 面
-    '\u2fb2': '韭',  # ⾲ -> 韭
-    '\u2fb9': '香',  # ⾹ -> 香
-    '\u2fca': '黑',  # ⿊ -> 黑
-    '\u2ee5': '鱼',  # ⻥ -> 鱼
-    '\u2ee8': '麦',  # ⻨ -> 麦
-    '\u2ee9': '黄',  # ⻩ -> 黄
-    '\u2ec9': '贝',  # ⻉ -> 贝
-    '\u2ee2': '马',  # ⻢ -> 马
-    '\u2edd': '食',  # ⻝ -> 食
-    '\u2ef0': '龙',  # ⻰ -> 龙
-    '\u2f18': '卜',  # ⼘ -> 卜
-    '\u2f1f': '土',  # ⼟ -> 土
-    '\u2f26': '子',  # ⼦ -> 子
-    '\u2f3c': '心',  # ⼼ -> 心
-    '\u2f42': '文',  # ⽂ -> 文
-    '\u2f60': '瓜',  # ⽠ -> 瓜
-    '\u2f6a': '皮',  # ⽪ -> 皮
-    '\u2f6c': '目',  # ⽬ -> 目
-    '\u2f7a': '羊',  # ⽺ -> 羊
-    '\u2f7f': '耳',  # ⽿ -> 耳
-    '\u2f90': '衣',  # ⾐ -> 衣
-    '\u2f95': '谷',  # ⾕ -> 谷
-    '\u2fa6': '金',  # ⾦ -> 金
-}
-
-def normalize_text(text):
-    """Replace CJK radical characters with standard Hanzi."""
-    result = []
-    for ch in text:
-        result.append(_RADICAL_MAP.get(ch, ch))
-    return ''.join(result)
-
-# Load reference (侯 report) for nutritional values
-ref_path = os.path.join(path, '530010234-侯-个体化食物推荐表.csv')
-ref_nutrition = {}  # name -> {field: value}
-with open(ref_path, 'r', encoding='utf-8-sig') as f:
-    for row in csv.DictReader(f):
-        ref_nutrition[row['名称']] = {k: row[k] for k in ['能量KJ','蛋白g','脂肪g','碳水化合物g','淀粉g','总膳食纤维g','胆固醇mg']}
-
-def parse_compressed_v2(text):
-    """Parse compressed format (朱评估报告 style) using reference nutrition values."""
-    # Remove header
-    header = '名称分类推荐指数能量KJ蛋白g脂肪g碳水化合物g淀粉g总膳食纤维g胆固醇mg'
-    rest = text
-    if header in rest:
-        rest = rest.replace(header, '')
-    
-    # Remove known junk patterns
-    skip_kws = ['根据您的肠道菌群', '分值从-100', '食物推荐考虑', '食物推荐是综合',
-                '需要注意的是', '本饮食推荐', '该饮食推荐根据', '后续表格中的营养',
-                '肠道菌群健康检测报告说明', '检测方法及局限性', '数据分析及模型',
-                '本报告中的检测', '以上模型预测', '结果解读及使用', '正常范围的定义',
-                '影响因素说明', '建议将检测结果', '营养建议说明', '报告中的食物推荐',
-                '重要提示', '推荐食物清单', '实际食用时需结合', '如有特殊疾病',
-                '免责声明', '本检测报告仅供', '16S 高通量测序', '基于机器学习和']
-    for kw in skip_kws:
-        rest = rest.replace(kw, '')
-    
-    rows = []
-    
-    while rest:
-        # Find earliest category
-        best_cat, best_idx = None, len(rest)
-        for cat in known_cats:
-            idx = rest.find(cat)
-            if idx != -1 and idx < best_idx:
-                best_idx, best_cat = idx, cat
-        if best_cat is None:
-            break
-        
-        name = rest[:best_idx]
-        rest = rest[best_idx + len(best_cat):]
-        
-        # Extract digit string
-        num_str = ''
-        while rest and (rest[0].isdigit() or rest[0] in '-\u2212\u2014'):
-            c = rest[0]
-            if c in '\u2212\u2014':
-                c = '-'
-            num_str += c
-            rest = rest[1:]
-        
-        if not name or not num_str:
-            continue
-        
-        # Try to decode using reference
-        decoded = decode_num_str(name, num_str)
-        if decoded:
-            rows.append(dict(zip(columns, [name, best_cat] + [str(v) for v in decoded])))
-    
-    return rows
-
-def decode_num_str(name, s):
-    """Decode 8-field number string using reference nutrition values."""
-    # Expected 7 nutrition values from reference
-    ref_vals = ref_nutrition.get(name)
-    if ref_vals:
-        ref_nums = [int(ref_vals[k]) for k in ['能量KJ','蛋白g','脂肪g','碳水化合物g','淀粉g','总膳食纤维g','胆固醇mg']]
-    else:
-        ref_nums = None
-    
-    raw = s.lstrip('-')  # remove leading dash from 推荐指数
-    has_neg = s.startswith('-')
-    
-    results = []
-    
-    # Try all possible splits for 推荐指数 (1 or 2 digits) and 能量KJ (2-4 digits)
-    for rec_len in range(1, 3):
-        if rec_len > len(raw):
-            continue
-        rec_str = '-' + raw[:rec_len] if has_neg else raw[:rec_len]
-        rec_val = int(rec_str)
-        if not (-100 <= rec_val <= 100):
-            continue
-        
-        # Now try to split the remaining 7 fields
-        remain = raw[rec_len:]
-        candidates = split_7_fields(remain)
-        
-        for nums in candidates:
-            full = [rec_val] + nums
-            if len(full) == 8:
-                # If we have reference values, check match (allow 1-char shifts)
-                if ref_nums:
-                    matches = sum(1 for i in range(7) if ref_nums[i] == nums[i])
-                    if matches >= 6:
-                        results.append(full)
-                else:
-                    results.append(full)
-    
-    if not results:
-        return None
-    
-    # Pick best: max nutrition matches, then shortest rec_len
-    if ref_nums:
-        def score(r):
-            matches = sum(1 for i in range(7) if ref_nums[i] == r[1:][i])
-            # Penalize rec_len=2 slightly (prefer 1-digit rec)
-            return (matches, -len(str(abs(r[0]))))
-        results.sort(key=score, reverse=True)
-    
-    r = results[0]
-    if ref_nums:
-        matches = sum(1 for i in range(7) if ref_nums[i] == r[1:][i])
-        if matches < 6:
-            return None
-    
-    return r
-
-def split_7_fields(s):
-    """Split remaining string into 7 numeric fields using width heuristics."""
-    results = []
-    # Expected widths (min, max) for each field after 能量KJ
-    # 能量KJ: 2-4, 蛋白: 1-2, 脂肪: 1-2, 碳水: 1-2, 淀粉: 1-2, 膳食纤维: 1-2, 胆固醇: 1-4
-    ranges = [(2,4), (1,2), (1,2), (1,2), (1,2), (1,2), (1,4)]
-    
-    def backtrack(pos, field_idx, nums):
-        if field_idx == 7:
-            if pos == len(s):
-                results.append(list(nums))
-            return
-        if pos >= len(s):
-            return
-        min_w, max_w = ranges[field_idx]
-        for w in range(min_w, min(max_w + 1, len(s) - pos + 1)):
-            chunk = s[pos:pos+w]
-            if chunk.isdigit():
-                val = int(chunk)
-                # 胆固醇 can be up to 4 digits (>999), allow common values
-                if field_idx == 0:  # 能量KJ - typically >= 100 for meaningful foods
-                    pass  # allow all
-                backtrack(pos+w, field_idx+1, nums+[val])
-    
-    backtrack(0, 0, [])
-    return results
-
-def parse_vertical(all_lines):
-    rows = []
-    i = 0
-    while i + 9 < len(all_lines):
-        name = all_lines[i].strip()
-        cat = all_lines[i+1].strip()
-        if cat not in known_cats:
-            i += 1
-            continue
-        nums = []
-        ok = True
-        for j in range(2, 10):
-            try:
-                v = all_lines[i+j].replace('\u2212', '-').replace('\u2014', '-').strip()
-                int(v)
-                nums.append(v)
-            except:
-                ok = False
-                break
-        if ok and len(nums) == 8:
-            rows.append(dict(zip(columns, [name, cat] + nums)))
-        i += 1
-    return rows
-
-def detect_format(text):
-    lines = [l.strip() for l in text.split('\n') if l.strip() and not re.match(r'^\d+/\d+$', l)]
-    if not lines:
-        return 'unknown'
-    long_line_count = sum(1 for l in lines[:10] if len(l) > 100)
-    cat_count = sum(1 for l in lines[:80] if l.strip() in known_cats)
-    
-    if len(lines) <= 3 and len(lines[0]) > 200:
-        return 'compressed'
-    if long_line_count >= 3:
-        return 'compressed'
-    if cat_count >= 5:
-        return 'vertical'
-    return 'unknown'
-
-for pdf_file in sorted(os.listdir(path)):
-    if not pdf_file.endswith('.pdf'):
-        continue
-    report_name = pdf_file.replace('.pdf', '')
-    pdf_path = os.path.join(path, pdf_file)
-    try:
-        reader = PdfReader(pdf_path)
-    except:
-        print(f'ERROR {report_name}')
-        continue
-
-    food_start = None
-    for i, page in enumerate(reader.pages):
-        if '个体化食物推荐表' in page.extract_text():
-            food_start = i
-            break
-    if food_start is None:
-        print(f'SKIP {report_name}')
-        continue
-
-    print(f'{report_name}...', end=' ')
-    first_data = normalize_text(reader.pages[food_start + 1].extract_text())
-    fmt = detect_format(first_data)
-    print(f'[{fmt}]', end=' ')
-
-    food_rows = []
-    if fmt == 'compressed':
-        for i in range(food_start + 1, len(reader.pages)):
-            text = normalize_text(reader.pages[i].extract_text())
-            # Remove page numbers
-            text = re.sub(r'\d+/\d+', '', text)
-            food_rows.extend(parse_compressed_v2(text))
-    else:
-        all_lines = []
-        for i in range(food_start + 1, len(reader.pages)):
-            for line in normalize_text(reader.pages[i].extract_text()).split('\n'):
-                lt = line.strip()
-                if not lt or re.match(r'^\d+/\d+$', lt) or lt in columns:
-                    continue
-                if len(lt) > 60 and any(k in lt for k in ['根据您的', '分值从', '食物推荐', '需要注意', '本饮食推荐', '该饮食推荐', '后续表格']):
-                    continue
-                all_lines.append(lt)
-        food_rows = parse_vertical(all_lines)
-
-    print(f'{len(food_rows)} entries')
-
-    if food_rows:
-        csv_name = f'{report_name}-个体化食物推荐表.csv'
-        csv_path = os.path.join(outdir, csv_name)
-        with open(csv_path, 'w', newline='', encoding='utf-8-sig') as f:
-            writer = csv.DictWriter(f, fieldnames=columns)
-            writer.writeheader()
-            writer.writerows(food_rows)
-        print(f'  -> {csv_name}')
-
-# ── Step 2: 生成推荐指数汇总表（标准营养 + 每人推荐指数） ──
-print('\n--- 生成推荐指数汇总表 ---')
-
-# 用侯报告作为标准营养参考（224条最完整）
-ref_csv = os.path.join(outdir, '530010234-侯-个体化食物推荐表.csv')
-if os.path.exists(ref_csv):
-    with open(ref_csv, 'r', encoding='utf-8-sig') as f:
-        std_rows = list(csv.DictReader(f))
-    std_lookup = {}
-    for r in std_rows:
-        name = r['名称']
-        std_lookup[name] = {k: r[k] for k in ['分类','能量KJ','蛋白g','脂肪g','碳水化合物g','淀粉g','总膳食纤维g','胆固醇mg']}
-
-    # 收集每份报告的推荐指数
-    rec_lookups = {}
-    report_labels = {'501999942-某人-个体化食物推荐表.csv': '某人',
-                     '530010234-侯-个体化食物推荐表.csv': '侯',
-                     '547982403-个体化食物推荐表.csv': '547982403',
-                     '儿童示例-个体化食物推荐表.csv': '儿童示例',
-                     '朱评估报告-个体化食物推荐表.csv': '朱评估报告'}
-    for csv_name, label in report_labels.items():
-        p = os.path.join(outdir, csv_name)
-        if os.path.exists(p):
-            with open(p, 'r', encoding='utf-8-sig') as f:
-                for row in csv.DictReader(f):
-                    rec_lookups.setdefault(label, {})[row['名称']] = row['推荐指数']
-
-    sum_cols = ['名称','分类','能量KJ','蛋白g','脂肪g','碳水化合物g','淀粉g','总膳食纤维g','胆固醇mg',
-                '某人','侯','547982403','儿童示例','朱评估报告']
-    sum_path = os.path.join(outdir, '推荐指数汇总.csv')
-    with open(sum_path, 'w', newline='', encoding='utf-8-sig') as f:
-        w = csv.DictWriter(f, fieldnames=sum_cols)
-        w.writeheader()
-        for r in std_rows:
-            name = r['名称']
-            s = std_lookup[name]
-            row = {'名称': name, '分类': s['分类'],
-                   '能量KJ': s['能量KJ'], '蛋白g': s['蛋白g'], '脂肪g': s['脂肪g'],
-                   '碳水化合物g': s['碳水化合物g'], '淀粉g': s['淀粉g'],
-                   '总膳食纤维g': s['总膳食纤维g'], '胆固醇mg': s['胆固醇mg']}
-            for label in ['某人','侯','547982403','儿童示例','朱评估报告']:
-                row[label] = rec_lookups.get(label, {}).get(name, '')
-            w.writerow(row)
-    print(f'推荐指数汇总表: {len(std_rows)} 行 -> {sum_path}')
-    for label in ['某人','侯','547982403','儿童示例','朱评估报告']:
-        missing = sum(1 for r in std_rows if not rec_lookups.get(label, {}).get(r['名称'], ''))
-        print(f'  {label}: 缺失 {missing} 条')
-
-print('\nDone!')