199 lines
7.1 KiB
Python
199 lines
7.1 KiB
Python
"""
|
|
检查特定模板的关联关系
|
|
"""
|
|
import pymysql
|
|
import os
|
|
import re
|
|
from pathlib import Path
|
|
from docx import Document
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
DB_CONFIG = {
|
|
'host': os.getenv('DB_HOST', '152.136.177.240'),
|
|
'port': int(os.getenv('DB_PORT', 5012)),
|
|
'user': os.getenv('DB_USER', 'finyx'),
|
|
'password': os.getenv('DB_PASSWORD', '6QsGK6MpePZDE57Z'),
|
|
'database': os.getenv('DB_NAME', 'finyx'),
|
|
'charset': 'utf8mb4'
|
|
}
|
|
|
|
TENANT_ID = 615873064429507639
|
|
TEMPLATE_NAME = "1.请示报告卡（初核谈话）"
|
|
TEMPLATE_FILE = "template_finish/2-初核模版/2.谈话审批/走读式谈话审批/1.请示报告卡（初核谈话）.docx"
|
|
|
|
def extract_placeholders_from_docx(file_path: str):
|
|
"""从docx文件中提取所有占位符"""
|
|
placeholders = set()
|
|
pattern = r'\{\{([^}]+)\}\}'
|
|
|
|
try:
|
|
doc = Document(file_path)
|
|
|
|
# 从段落中提取占位符
|
|
for paragraph in doc.paragraphs:
|
|
text = paragraph.text
|
|
matches = re.findall(pattern, text)
|
|
for match in matches:
|
|
cleaned = match.strip()
|
|
if cleaned and '{' not in cleaned and '}' not in cleaned:
|
|
placeholders.add(cleaned)
|
|
|
|
# 从表格中提取占位符
|
|
for table in doc.tables:
|
|
for row in table.rows:
|
|
for cell in row.cells:
|
|
for paragraph in cell.paragraphs:
|
|
text = paragraph.text
|
|
matches = re.findall(pattern, text)
|
|
for match in matches:
|
|
cleaned = match.strip()
|
|
if cleaned and '{' not in cleaned and '}' not in cleaned:
|
|
placeholders.add(cleaned)
|
|
|
|
except Exception as e:
|
|
print(f"错误: 读取文件失败 - {str(e)}")
|
|
return []
|
|
|
|
return sorted(list(placeholders))
|
|
|
|
def check_template():
|
|
"""检查模板的关联关系"""
|
|
conn = pymysql.connect(**DB_CONFIG)
|
|
cursor = conn.cursor(pymysql.cursors.DictCursor)
|
|
|
|
try:
|
|
print(f"检查模板: {TEMPLATE_NAME}")
|
|
print("=" * 80)
|
|
|
|
# 1. 从文档提取占位符
|
|
print("\n1. 从文档提取占位符:")
|
|
if not Path(TEMPLATE_FILE).exists():
|
|
print(f" 文件不存在: {TEMPLATE_FILE}")
|
|
return
|
|
|
|
placeholders = extract_placeholders_from_docx(TEMPLATE_FILE)
|
|
print(f" 占位符数量: {len(placeholders)}")
|
|
print(f" 占位符列表: {placeholders}")
|
|
|
|
# 2. 查询模板ID
|
|
print(f"\n2. 查询模板ID:")
|
|
cursor.execute("""
|
|
SELECT id, name
|
|
FROM f_polic_file_config
|
|
WHERE tenant_id = %s AND name = %s
|
|
""", (TENANT_ID, TEMPLATE_NAME))
|
|
template = cursor.fetchone()
|
|
if not template:
|
|
print(f" 模板不存在")
|
|
return
|
|
|
|
template_id = template['id']
|
|
print(f" 模板ID: {template_id}")
|
|
|
|
# 3. 查询字段映射
|
|
print(f"\n3. 查询字段映射:")
|
|
cursor.execute("""
|
|
SELECT id, name, filed_code, field_type, state
|
|
FROM f_polic_field
|
|
WHERE tenant_id = %s
|
|
""", (TENANT_ID,))
|
|
fields = cursor.fetchall()
|
|
|
|
field_map = {}
|
|
for field in fields:
|
|
state = field['state']
|
|
if isinstance(state, bytes):
|
|
state = int.from_bytes(state, byteorder='big') if len(state) == 1 else 1
|
|
field_map[field['filed_code']] = {
|
|
'id': field['id'],
|
|
'name': field['name'],
|
|
'field_type': field['field_type'],
|
|
'state': state
|
|
}
|
|
|
|
print(f" 字段总数: {len(field_map)}")
|
|
|
|
# 4. 匹配占位符到字段
|
|
print(f"\n4. 匹配占位符到字段:")
|
|
input_field_ids = []
|
|
output_field_ids = []
|
|
not_found = []
|
|
|
|
for placeholder in placeholders:
|
|
if placeholder in field_map:
|
|
field_info = field_map[placeholder]
|
|
if field_info['state'] == 1:
|
|
if field_info['field_type'] == 1:
|
|
input_field_ids.append(field_info['id'])
|
|
elif field_info['field_type'] == 2:
|
|
output_field_ids.append(field_info['id'])
|
|
else:
|
|
not_found.append(placeholder)
|
|
|
|
# 添加必需的输入字段
|
|
required_input_fields = ['clue_info', 'target_basic_info_clue']
|
|
for req_field in required_input_fields:
|
|
if req_field in field_map:
|
|
field_info = field_map[req_field]
|
|
if field_info['state'] == 1 and field_info['id'] not in input_field_ids:
|
|
input_field_ids.append(field_info['id'])
|
|
|
|
print(f" 输入字段ID: {input_field_ids}")
|
|
print(f" 输出字段ID: {output_field_ids}")
|
|
if not_found:
|
|
print(f" 未找到的占位符: {not_found}")
|
|
|
|
# 5. 查询数据库中的关联关系
|
|
print(f"\n5. 查询数据库中的关联关系:")
|
|
cursor.execute("""
|
|
SELECT fff.filed_id, fff.state, f.name, f.field_type
|
|
FROM f_polic_file_field fff
|
|
INNER JOIN f_polic_field f ON fff.filed_id = f.id AND fff.tenant_id = f.tenant_id
|
|
WHERE fff.tenant_id = %s AND fff.file_id = %s
|
|
""", (TENANT_ID, template_id))
|
|
db_relations = cursor.fetchall()
|
|
|
|
db_input_ids = []
|
|
db_output_ids = []
|
|
for rel in db_relations:
|
|
state = rel['state']
|
|
if isinstance(state, bytes):
|
|
state = int.from_bytes(state, byteorder='big') if len(state) == 1 else 1
|
|
|
|
if state == 1:
|
|
if rel['field_type'] == 1:
|
|
db_input_ids.append(rel['filed_id'])
|
|
elif rel['field_type'] == 2:
|
|
db_output_ids.append(rel['filed_id'])
|
|
|
|
print(f" 数据库中的输入字段ID: {sorted(db_input_ids)}")
|
|
print(f" 数据库中的输出字段ID: {sorted(db_output_ids)}")
|
|
|
|
# 6. 对比
|
|
print(f"\n6. 对比结果:")
|
|
expected_input = set(input_field_ids)
|
|
expected_output = set(output_field_ids)
|
|
actual_input = set(db_input_ids)
|
|
actual_output = set(db_output_ids)
|
|
|
|
print(f" 输入字段 - 期望: {sorted(expected_input)}, 实际: {sorted(actual_input)}")
|
|
print(f" 输入字段匹配: {expected_input == actual_input}")
|
|
|
|
print(f" 输出字段 - 期望: {sorted(expected_output)}, 实际: {sorted(actual_output)}")
|
|
print(f" 输出字段匹配: {expected_output == actual_output}")
|
|
|
|
if expected_output != actual_output:
|
|
missing = expected_output - actual_output
|
|
extra = actual_output - expected_output
|
|
print(f" 缺少的输出字段: {sorted(missing)}")
|
|
print(f" 多余的输出字段: {sorted(extra)}")
|
|
|
|
finally:
|
|
cursor.close()
|
|
conn.close()
|
|
|
|
if __name__ == '__main__':
|
|
check_template()
|