sisvietnamvn_01/sisvietnamvn_main/generate_merged_doctors.py

import csv
import xml.etree.ElementTree as ET
import sys
import os

csv_file = '/home/x79/sisvietnamvn_01/sisvietnamvn_Trang chính thức hiện tại/DS_BacSi/DANH SÁCH BÁC SĨ NGỒI PHÒNG KHÁM_THÔNG TIN CHI TIẾT_FULL.csv'
xml_file = '/home/x79/sisvietnamvn_01/sisvietnamvn_Trang chính thức hiện tại/DS_BacSi/bnhvinakhoaquctsiscnth.WordPress.2026-07-28 (5).xml'

# Read CSV
csv_doctors = {}
with open(csv_file, 'r', encoding='utf-8-sig') as f:
    reader = csv.DictReader(f)
    for row in reader:
        name = row.get('Họ và tên', '').strip()
        if not name:
            continue
        msnv = row.get('MSNV', '').strip()
        title = row.get('Chức danh', '').strip()
        degree = row.get('Trình độ chuyên môn', '').strip()
        specialty = row.get('Khoa/ Phòng', '').strip()
        education = row.get('Quá trình đào tạo', '').strip()
        experience = row.get('Quá trình công tác', '').strip()
        achievements = row.get('Hiệp hội chuyên môn', '').strip() + '\n' + row.get('Ghi chú', '').strip()
        
        csv_doctors[name.lower()] = {
            'name': name,
            'doctor_code': msnv,
            'title': degree,
            'position': title,
            'specialty': specialty,
            'education': education,
            'experience': experience,
            'achievements': achievements,
            'active': 1 if msnv else 0
        }

# Read XML
xml_doctors = {}
tree = ET.parse(xml_file)
root = tree.getroot()
ns = {
    'wp': 'http://wordpress.org/export/1.2/',
    'content': 'http://purl.org/rss/1.0/modules/content/'
}

for channel in root.findall('channel'):
    for item in channel.findall('item'):
        post_type = item.find('wp:post_type', ns)
        if post_type is None or post_type.text != 'doctor':
            continue
            
        title_elem = item.find('title')
        if title_elem is None or not title_elem.text:
            continue
            
        name = title_elem.text.strip()
        if not name:
            continue
            
        doc = {'name': name}
        
        # Extract department category
        for cat in item.findall('category'):
            if cat.get('domain') == 'department':
                doc['specialty'] = cat.text.strip()
                break
                
        for meta in item.findall('wp:postmeta', ns):
            key = meta.find('wp:meta_key', ns)
            val = meta.find('wp:meta_value', ns)
            if key is not None and val is not None and val.text:
                k = key.text
                v = val.text.strip()
                if k == 'doctor_information_position':
                    doc['position'] = v
                elif k == 'doctor_information_specialty':
                    doc['specialty'] = v
                elif k == 'doctor_information_experience':
                    doc['experience'] = v
                elif k == 'doctor_information_education':
                    doc['education'] = v
                elif k == 'doctor_information_achievements':
                    doc['achievements'] = v
                elif k == 'doctor_information_gender':
                    doc['gender'] = v
                elif k == 'doctor_information_phone':
                    doc['phone_number'] = v
                elif k == 'doctor_information_email':
                    doc['email'] = v
                elif k == 'doctor_information_avatar':
                    doc['avatar_url'] = v
                elif k == 'doctor_information_booking':
                    doc['booking_url'] = v
                elif k == 'doctor_information_title':
                    doc['title'] = v
        
        xml_doctors[name.lower()] = doc

# Merge
merged_doctors = {}
for name_key, xml_doc in xml_doctors.items():
    merged_doctors[name_key] = xml_doc

# Priorities: CSV overwrites XML
for name_key, csv_doc in csv_doctors.items():
    # Find matching XML doctor by checking if CSV name is substring of XML name
    matched_xml_key = None
    for xml_key in merged_doctors.keys():
        # Remove spaces and dashes for comparison
        clean_csv = name_key.replace(' ', '').replace('-', '')
        clean_xml = xml_key.replace(' ', '').replace('-', '')
        if clean_csv in clean_xml or clean_xml in clean_csv:
            matched_xml_key = xml_key
            break
            
    if matched_xml_key:
        existing = merged_doctors[matched_xml_key]
        for k, v in csv_doc.items():
            if v and str(v).strip():
                existing[k] = v
        # Ensure we use the clean plain name from CSV, not the long XML title
        existing['name'] = csv_doc['name']
    else:
        merged_doctors[name_key] = csv_doc

# Write SQL
plsql = "BEGIN\n"
plsql += "    DELETE FROM sis_doctor_schedule;\n"
plsql += "    DELETE FROM sis_doctor;\n"

for doc in merged_doctors.values():
    name = doc.get('name', '').replace("'", "''")
    code = doc.get('doctor_code', '').replace("'", "''")
    title = doc.get('title', '').replace("'", "''")
    pos = doc.get('position', '').replace("'", "''")
    gender = doc.get('gender', '').replace("'", "''")
    phone = doc.get('phone_number', '').replace("'", "''")
    email = doc.get('email', '').replace("'", "''")
    spec = doc.get('specialty', '').replace("'", "''")
    edu = doc.get('education', '').replace("'", "''")
    exp = doc.get('experience', '').replace("'", "''")
    ach = doc.get('achievements', '').replace("'", "''")
    avt = doc.get('avatar_url', '').replace("'", "''")
    bk = doc.get('booking_url', '').replace("'", "''")
    active = doc.get('active', 0)
    
    plsql += f"""
    DECLARE
        v_count NUMBER;
        v_spec_id NUMBER := NULL;
    BEGIN
        IF '{spec}' IS NOT NULL THEN
            SELECT COUNT(*) INTO v_count FROM sis_specialty WHERE name = '{spec}';
            IF v_count = 0 THEN
                INSERT INTO sis_specialty (id, name, slug, created_by, created_date, last_modified_by, last_modified_date) 
                VALUES (sequence_generator.NEXTVAL, '{spec}', '{spec}', 'system', sysdate, 'system', sysdate);
            END IF;
            SELECT id INTO v_spec_id FROM sis_specialty WHERE name = '{spec}' FETCH FIRST 1 ROWS ONLY;
        END IF;
        
        INSERT INTO sis_doctor (
            id, name, doctor_code, title, position, gender, phone_number, email,
            specialty_id, education, work_experience, achievements, avatar_url, booking_url,
            active, display_order, created_by, created_date, last_modified_by, last_modified_date
        ) VALUES (
            sequence_generator.NEXTVAL, '{name}', '{code}', '{title}', '{pos}', '{gender}', '{phone}', '{email}',
            v_spec_id, '{edu}', '{exp}', '{ach}', '{avt}', '{bk}',
            {active}, 0, 'system', sysdate, 'system', sysdate
        );
    END;
    """

plsql += "COMMIT;\nEND;\n/"

with open('/home/x79/sisvietnamvn_01/sisvietnamvn_main/src/main/resources/config/liquibase/data/merge_doctors.sql', 'w', encoding='utf-8') as f:
    f.write(plsql)

print("Generated merge_doctors.sql")