oil-formula-calculator/backend/translate.py

"""Auto-translate Chinese recipe names to English using keyword dictionary."""

# Common keywords in essential oil recipe names
_KEYWORDS = {
    # Body parts
    '头': 'Head', '头疗': 'Scalp Therapy', '头皮': 'Scalp', '头发': 'Hair',
    '脸': 'Face', '面部': 'Face', '眼': 'Eye', '眼部': 'Eye',
    '鼻': 'Nose', '鼻腔': 'Nasal', '耳': 'Ear',
    '颈': 'Neck', '颈椎': 'Cervical', '肩': 'Shoulder', '肩颈': 'Neck & Shoulder',
    '背': 'Back', '腰': 'Lower Back', '腰椎': 'Lumbar',
    '胸': 'Chest', '腹': 'Abdomen', '腹部': 'Abdominal',
    '手': 'Hand', '脚': 'Foot', '足': 'Foot', '膝': 'Knee', '关节': 'Joint',
    '皮肤': 'Skin', '肌肤': 'Skin', '毛孔': 'Pore',
    '乳腺': 'Breast', '子宫': 'Uterine', '私密': 'Intimate',
    '淋巴': 'Lymph', '肝': 'Liver', '肾': 'Kidney', '脾': 'Spleen', '胃': 'Stomach',
    '肺': 'Lung', '心': 'Heart', '肠': 'Intestinal',
    '带脉': 'Belt Meridian', '经络': 'Meridian',

    # Symptoms & conditions
    '酸痛': 'Pain Relief', '疼痛': 'Pain Relief', '止痛': 'Pain Relief',
    '感冒': 'Cold', '发烧': 'Fever', '咳嗽': 'Cough', '咽喉': 'Throat',
    '过敏': 'Allergy', '鼻炎': 'Rhinitis', '哮喘': 'Asthma',
    '湿疹': 'Eczema', '痘痘': 'Acne', '粉刺': 'Acne',
    '炎症': 'Anti-Inflammatory', '消炎': 'Anti-Inflammatory',
    '便秘': 'Constipation', '腹泻': 'Diarrhea', '消化': 'Digestion',
    '失眠': 'Insomnia', '助眠': 'Sleep Aid', '好眠': 'Sleep Well', '安眠': 'Sleep',
    '焦虑': 'Anxiety', '抑郁': 'Depression', '情绪': 'Emotional',
    '压力': 'Stress', '放松': 'Relaxation', '舒缓': 'Soothing',
    '头痛': 'Headache', '偏头痛': 'Migraine',
    '水肿': 'Edema', '浮肿': 'Swelling',
    '痛经': 'Menstrual Pain', '月经': 'Menstrual', '经期': 'Menstrual',
    '更年期': 'Menopause', '荷尔蒙': 'Hormone',
    '结节': 'Nodule', '囊肿': 'Cyst',
    '灰指甲': 'Nail Fungus', '脚气': 'Athlete\'s Foot',
    '白发': 'Gray Hair', '脱发': 'Hair Loss', '生发': 'Hair Growth',
    '瘦身': 'Slimming', '减肥': 'Weight Loss', '纤体': 'Body Sculpting',
    '紫外线': 'UV', '晒伤': 'Sunburn', '防晒': 'Sun Protection',
    '抗衰': 'Anti-Aging', '抗皱': 'Anti-Wrinkle', '美白': 'Whitening',
    '补水': 'Hydrating', '保湿': 'Moisturizing',
    '排毒': 'Detox', '清洁': 'Cleansing', '净化': 'Purifying',
    '驱蚊': 'Mosquito Repellent', '驱虫': 'Insect Repellent',

    # Actions & methods
    '护理': 'Care', '调理': 'Therapy', '修复': 'Repair', '养护': 'Nourish',
    '按摩': 'Massage', '刮痧': 'Gua Sha', '拔罐': 'Cupping', '艾灸': 'Moxibustion',
    '泡脚': 'Foot Soak', '泡澡': 'Bath', '精油浴': 'Oil Bath',
    '热敷': 'Hot Compress', '冷敷': 'Cold Compress', '敷面': 'Face Mask',
    '喷雾': 'Spray', '滚珠': 'Roll-On', '扩香': 'Diffuser',
    '涂抹': 'Topical', '吸嗅': 'Inhalation',
    '疏通': 'Unblock', '提升': 'Boost', '增强': 'Enhance', '促进': 'Promote',
    '预防': 'Prevention', '改善': 'Improve',
    '祛湿': 'Dampness Relief', '驱寒': 'Warming',
    '化痰': 'Phlegm Relief', '健脾': 'Spleen Wellness',
    '化湿': 'Dampness Clear',

    # Beauty
    '美容': 'Beauty', '美发': 'Hair Care', '美体': 'Body Care',
    '面膜': 'Face Mask', '发膜': 'Hair Mask', '眼霜': 'Eye Cream',
    '精华': 'Serum', '乳液': 'Lotion', '洗发': 'Shampoo',

    # General
    '配方': 'Blend', '方': 'Blend', '包': 'Blend',
    '增强版': 'Enhanced', '高配版': 'Premium', '基础版': 'Basic',
    '男士': 'Men\'s', '女士': 'Women\'s', '儿童': 'Children\'s', '宝宝': 'Baby',
    '日常': 'Daily', '夜间': 'Night', '早晨': 'Morning',
    '呼吸': 'Respiratory', '呼吸系统': 'Respiratory System',
    '免疫': 'Immunity', '免疫力': 'Immunity',
    '细胞': 'Cellular', '律动': 'Rhythm',
}

# Longer keys first for greedy matching
_SORTED_KEYS = sorted(_KEYWORDS.keys(), key=len, reverse=True)


def auto_translate(name: str) -> str:
    """Translate a Chinese recipe name to English using keyword matching."""
    if not name:
        return ''
    remaining = name.strip()
    parts = []
    i = 0
    while i < len(remaining):
        matched = False
        for key in _SORTED_KEYS:
            if remaining[i:i+len(key)] == key:
                en = _KEYWORDS[key]
                if en not in parts:  # avoid duplicates
                    parts.append(en)
                i += len(key)
                matched = True
                break
        if not matched:
            # Skip numbers, punctuation, and unrecognized chars
            ch = remaining[i]
            if ch.isascii() and ch.isalpha():
                # Collect consecutive ASCII chars
                j = i
                while j < len(remaining) and remaining[j].isascii() and remaining[j].isalpha():
                    j += 1
                word = remaining[i:j]
                if word not in parts:
                    parts.append(word)
                i = j
            else:
                i += 1

    if parts:
        result = ' '.join(parts)
        # Title case each word but preserve apostrophes (Men's not Men'S)
        return ' '.join(w[0].upper() + w[1:] if w else w for w in result.split())
    # Fallback: return original name
    return name