519 lines
23 KiB
Python
519 lines
23 KiB
Python
import os
|
||
import json
|
||
from typing import List, Tuple, Dict, Any, Optional
|
||
import re
|
||
from kg_build.extract_compose_table import get_compose_node_relation
|
||
from kg_build.extract_compose_tujie_table import get_tujiecompose_node_relation
|
||
from kg_build.extract_guzhang_table import get_guzhang_node_relation
|
||
from kg_build.extract_operation_table import get_operation_node_relation
|
||
from kg_build.extract_repair_table import get_repair_node_relation
|
||
from kg_build.extract_wxanli_table import get_wxanli_node_relation
|
||
from kg_build.get_text_node_reala import extract_text_node_relationship
|
||
from kg_build.extract_beipinbeijian_table import get_beipinbeijian_node_relation
|
||
from kg_build.extract_filtertext import get_filtertext_node_relation
|
||
import requests
|
||
from doc2pdf import Doc2PDF
|
||
import traceback
|
||
from extract_excel_node_relation import get_excel_node_relation
|
||
|
||
import logging
|
||
import asyncio # ← 新增导入
|
||
import time
|
||
# --- 日志配置 ---
|
||
logger = logging.getLogger(__name__)
|
||
if not logger.handlers:
|
||
handler = logging.StreamHandler()
|
||
fmt = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||
handler.setFormatter(fmt)
|
||
logger.addHandler(handler)
|
||
logger.setLevel(logging.INFO)
|
||
|
||
converter = Doc2PDF()
|
||
|
||
def build_repair_relationships(entities: List[Dict]) -> Tuple[List[Dict], List[Dict]]:
|
||
"""
|
||
根据维修项目编号 OR 名称在故障维修方案中的出现情况，建立“修理”关系。
|
||
匹配规则：只要编号或名称任意一个出现在维修方案文本中，即视为匹配。
|
||
"""
|
||
# 1. 数据分类：分离故障模式和维修项目
|
||
faults = [e for e in entities if e.get("type") == "故障模式"]
|
||
maintenances = [e for e in entities if e.get("type") == "维修项目"]
|
||
devices = [e for e in entities if e.get("type") == "设备"]
|
||
|
||
|
||
relationships = []
|
||
entitys = []
|
||
# 2. 遍历每一个维修项目
|
||
for mt in maintenances:
|
||
props = mt.get("properties", {})
|
||
mt_code = props.get("编号")
|
||
mt_name = props.get("名称")
|
||
|
||
# 如果连名称和编号都没有，无法进行任何匹配，直接跳过
|
||
if not mt_code and not mt_name:
|
||
continue
|
||
|
||
# 3. 遍历每一个故障模式
|
||
for fault in faults:
|
||
f_props = fault.get("properties", {})
|
||
fault_name = f_props.get("名称")
|
||
repair_text = f_props.get("维修方案", "")
|
||
|
||
if not fault_name or not repair_text:
|
||
continue
|
||
|
||
# 4. 核心匹配逻辑修改 (OR 关系)
|
||
match_by_code = mt_code in repair_text if mt_code else False
|
||
match_by_name = mt_name in repair_text if mt_name else False
|
||
|
||
# 只要满足任一条件，即建立关系
|
||
if match_by_code or match_by_name:
|
||
relationships.append({
|
||
"type": "修理",
|
||
"from_entity": mt_name, # 关系起点：维修项目名称
|
||
"to_entity": fault_name # 关系终点：故障名称
|
||
})
|
||
for mt in devices:
|
||
props = mt.get("properties", {})
|
||
mt_code = props.get("维修项目名称")
|
||
mt_name = props.get("维修项目编号")
|
||
devicename = props.get("名称")
|
||
# 如果连名称和编号都没有，无法进行任何匹配，直接跳过
|
||
if not mt_code and not mt_name:
|
||
continue
|
||
|
||
# 3. 遍历每一个故障模式
|
||
for fault in faults:
|
||
f_props = fault.get("properties", {})
|
||
fault_name = f_props.get("名称")
|
||
repair_text = f_props.get("维修方案", "")
|
||
|
||
if not fault_name or not repair_text:
|
||
continue
|
||
|
||
# 4. 核心匹配逻辑修改 (OR 关系)
|
||
match_by_code = mt_code in repair_text if mt_code else False
|
||
match_by_name = mt_name in repair_text if mt_name else False
|
||
|
||
# 只要满足任一条件，即建立关系
|
||
if match_by_code or match_by_name:
|
||
entitys.append({
|
||
"type": "维修工作",
|
||
"properties": {"名称": f"{devicename}的维修工作"}
|
||
})
|
||
relationships.append({
|
||
"type": "发生故障使用维修工作",
|
||
"from_entity": devicename,
|
||
"to_entity": f"{devicename}的维修工作"
|
||
})
|
||
relationships.append({
|
||
"type": "包含故障",
|
||
"from_entity": f"{devicename}的维修工作",
|
||
"to_entity": fault_name
|
||
})
|
||
relationships.append({
|
||
"type": "修理",
|
||
"from_entity": mt_name, # 关系起点：维修项目名称
|
||
"to_entity": fault_name
|
||
})
|
||
|
||
|
||
|
||
return entitys,relationships
|
||
|
||
async def get_md_node_relation(
|
||
content_list: str,
|
||
input_pdf_path:str,
|
||
Ontology: List[str],
|
||
Ontology_DESCRIPTION: Dict[str, List[str]],
|
||
Relationships: List[str],
|
||
RELATIONSHIP_TYPES: Dict[str, List[str]],
|
||
NODE_TYPES: Dict[str, List[str]],
|
||
PREFIX_URL : str = "http://192.168.0.111:9085",
|
||
device : str = "",
|
||
device_type : str = ""
|
||
) -> Tuple[List[Dict], List[Dict]]:
|
||
"""
|
||
核心函数：协调各模块完成知识抽取、清洗、向量化。
|
||
"""
|
||
start_time = time.time()
|
||
final_all_entity = []
|
||
final_all_relation = []
|
||
|
||
if not content_list:
|
||
logger.error("输入的 Markdown 内容为空")
|
||
return [], []
|
||
if "维修手册" in input_pdf_path or "维修说明书" in input_pdf_path or "培训手册" in input_pdf_path:
|
||
t = time.time()
|
||
all_entity_results_guzhang ,all_relation_results_guzhang =await get_guzhang_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL,device=device)
|
||
length_entity_guzhang = len(all_entity_results_guzhang)
|
||
length_relation_guzhang = len(all_relation_results_guzhang)
|
||
logger.info(f"故障抽取 - 实体: {length_entity_guzhang}, 关系: {length_relation_guzhang}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_guzhang > 0 :
|
||
final_all_entity.extend(all_entity_results_guzhang)
|
||
if length_relation_guzhang > 0:
|
||
final_all_relation.extend(all_relation_results_guzhang)
|
||
|
||
t = time.time()
|
||
all_entity_results_repair ,all_relation_results_repair =await get_repair_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL)
|
||
length_entity_repair = len(all_entity_results_repair)
|
||
length_relation_repair = len(all_relation_results_repair)
|
||
logger.info(f"维修项目表抽取 - 实体: {length_entity_repair}, 关系: {length_relation_repair}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_repair > 0 :
|
||
final_all_entity.extend(all_entity_results_repair)
|
||
if length_relation_repair > 0:
|
||
final_all_relation.extend(all_relation_results_repair)
|
||
|
||
t = time.time()
|
||
all_entity_results_text ,all_relation_results_text =await get_filtertext_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL,device= device)
|
||
length_entity_text= len(all_entity_results_text)
|
||
length_relation_text = len(all_relation_results_text)
|
||
logger.info(f"文本抽取 - 实体: {length_entity_text}, 关系: {length_relation_text}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_text > 0 :
|
||
final_all_entity.extend(all_entity_results_text)
|
||
if length_relation_text > 0:
|
||
final_all_relation.extend(all_relation_results_text)
|
||
elif "图解目录" in input_pdf_path:
|
||
# 2. 处理图解组成表
|
||
t = time.time()
|
||
all_entity_results_tujiecompose ,all_relation_results_tujiecompose =await get_tujiecompose_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL,device=device,lower_entity_type=device_type)
|
||
length_entity_tujiecompose = len(all_entity_results_tujiecompose)
|
||
length_relation_tujiecompose = len(all_relation_results_tujiecompose)
|
||
logger.info(f"图解组成表抽取 - 实体: {length_entity_tujiecompose}, 关系: {length_relation_tujiecompose}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_tujiecompose > 0 :
|
||
final_all_entity.extend(all_entity_results_tujiecompose)
|
||
if length_relation_tujiecompose > 0:
|
||
final_all_relation.extend(all_relation_results_tujiecompose)
|
||
|
||
elif "操作使用手册" in input_pdf_path:
|
||
# 6. 处理操作项目表
|
||
t = time.time()
|
||
all_entity_results_operation ,all_relation_results_goperation =await get_operation_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL,device=device)
|
||
length_entity_operation= len(all_entity_results_operation)
|
||
length_relation_goperation = len(all_relation_results_goperation)
|
||
logger.info(f"操作项目表抽取 - 实体: {length_entity_operation}, 关系: {length_relation_goperation}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_operation > 0 :
|
||
final_all_entity.extend(all_entity_results_operation)
|
||
if length_relation_goperation > 0:
|
||
final_all_relation.extend(all_relation_results_goperation)
|
||
|
||
t = time.time()
|
||
all_entity_results_text ,all_relation_results_text =await get_filtertext_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL,device= device)
|
||
length_entity_text= len(all_entity_results_text)
|
||
length_relation_text = len(all_relation_results_text)
|
||
logger.info(f"文本抽取 - 实体: {length_entity_text}, 关系: {length_relation_text}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_text > 0 :
|
||
final_all_entity.extend(all_entity_results_text)
|
||
if length_relation_text > 0:
|
||
final_all_relation.extend(all_relation_results_text)
|
||
|
||
elif "备品备件" in input_pdf_path:
|
||
# 5. 处理备品备件表
|
||
t = time.time()
|
||
all_entity_results_beipinbeijian ,all_relation_results_beipinbeijian =await get_filtertext_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL,device=device)
|
||
length_entity_beipinbeijian= len(all_entity_results_beipinbeijian)
|
||
length_relation_beipinbeijian = len(all_relation_results_beipinbeijian)
|
||
logger.info(f"备品备件表抽取 - 实体: {length_entity_beipinbeijian}, 关系: {length_relation_beipinbeijian}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_beipinbeijian > 0 :
|
||
final_all_entity.extend(all_entity_results_beipinbeijian)
|
||
if length_relation_beipinbeijian > 0:
|
||
final_all_relation.extend(all_relation_results_beipinbeijian)
|
||
elif "故障案例" in input_pdf_path:
|
||
|
||
# 7. 处理维修案例
|
||
t = time.time()
|
||
all_entity_results_wxanli ,all_relation_results_wxanli =await get_wxanli_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL)
|
||
length_entity_wxanli= len(all_entity_results_wxanli)
|
||
length_relation_wxanli = len(all_relation_results_wxanli)
|
||
logger.info(f"维修案例抽取 - 实体: {length_entity_wxanli}, 关系: {length_relation_wxanli}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_wxanli > 0 :
|
||
final_all_entity.extend(all_entity_results_wxanli)
|
||
if length_relation_wxanli > 0:
|
||
final_all_relation.extend(all_relation_results_wxanli)
|
||
else:
|
||
logger.warning("未识别的文档类型，默认进行文本抽取")
|
||
t = time.time()
|
||
all_entity_results_text ,all_relation_results_text =await get_filtertext_node_relation(input_pdf_path=input_pdf_path,data=content_list,prefix_url=PREFIX_URL,device= device)
|
||
length_entity_text= len(all_entity_results_text)
|
||
length_relation_text = len(all_relation_results_text)
|
||
logger.info(f"文本抽取 - 实体: {length_entity_text}, 关系: {length_relation_text}, 耗时: {time.time()-t:.2f}s")
|
||
if length_entity_text > 0 :
|
||
final_all_entity.extend(all_entity_results_text)
|
||
if length_relation_text > 0:
|
||
final_all_relation.extend(all_relation_results_text)
|
||
|
||
|
||
# 8. 建立修复关系
|
||
reparientitys,repair_relations = build_repair_relationships(final_all_entity)
|
||
final_all_entity.extend(reparientitys)
|
||
final_all_relation.extend(repair_relations)
|
||
logger.info(f"构建故障修复实体数量: {len(reparientitys)}")
|
||
logger.info(f"构建故障修复关系数量: {len(repair_relations)}")
|
||
|
||
|
||
|
||
logger.info(f"总实体: {len(final_all_entity)}, 总关系: {len(final_all_relation)}")
|
||
result = {
|
||
"entities": final_all_entity,
|
||
"relations": final_all_relation
|
||
}
|
||
output_json_path= "/app/wxproject.json"
|
||
# 保存为 JSON 文件
|
||
try:
|
||
with open(output_json_path, 'w', encoding='utf-8') as f:
|
||
json.dump(result, f, ensure_ascii=False, indent=4)
|
||
print(f"结果已保存至：{output_json_path}")
|
||
except Exception as e:
|
||
print(f"保存 JSON 文件时出错：{e}")
|
||
end_time = time.time()
|
||
print(f"总耗时: {end_time - start_time:.2f} 秒")
|
||
return final_all_entity, final_all_relation
|
||
|
||
def get_content_list_json(filename, folder_path):
|
||
"""
|
||
根据传入的文件名，在指定文件夹下查找对应的 _content_list.json 文件并读取内容。
|
||
|
||
参数:
|
||
filename (str): 原始文件名，例如 "163-06A0015-B01001_发动机-操作使用手册.pdf"
|
||
folder_path (str): 目标文件夹路径
|
||
|
||
返回:
|
||
dict or None: 如果找到文件则返回 JSON 内容字典，否则返回 None
|
||
"""
|
||
# 提取文件名主体（去掉扩展名）
|
||
base_name = os.path.splitext(filename)[0]
|
||
|
||
# 构造目标 JSON 文件名
|
||
target_json_filename = f"{base_name}_content_list.json"
|
||
|
||
# 构造完整路径
|
||
target_path = os.path.join(folder_path, target_json_filename)
|
||
|
||
# 检查文件是否存在
|
||
if not os.path.exists(target_path):
|
||
print(f"未找到文件: {target_path}")
|
||
return None
|
||
|
||
# 读取并解析 JSON
|
||
try:
|
||
with open(target_path, 'r', encoding='utf-8') as f:
|
||
data = json.load(f)
|
||
return data
|
||
except json.JSONDecodeError as e:
|
||
print(f"JSON 解析错误: {e}")
|
||
return None
|
||
except Exception as e:
|
||
print(f"读取文件时发生错误: {e}")
|
||
return None
|
||
|
||
|
||
def process_file_content(
|
||
file_name: str,
|
||
file_path: str,
|
||
task_id: str,
|
||
data_dir: str,
|
||
ontology: Any,
|
||
ontology_desc: str,
|
||
relationships: List,
|
||
node_types: List,
|
||
relationship_types: List,
|
||
prefix_url: str,
|
||
api_url: str,
|
||
check_cancelled_callback: callable,
|
||
device : str,
|
||
device_type : str,
|
||
) -> Tuple[List[Dict], List[Dict]]:
|
||
"""
|
||
根据文件类型解析内容并抽取实体和关系。
|
||
|
||
Returns:
|
||
tuple: (entities, relationships)
|
||
"""
|
||
file_extension = os.path.splitext(file_name)[1].lower()
|
||
merged_output_data = {"entities": [], "relationships": []}
|
||
from fileparse_util import process_document
|
||
|
||
# --- 处理 PDF 和 MD ---
|
||
if file_extension in ['.pdf', '.md']:
|
||
async def _run_process_doc():
|
||
return await process_document(file_name)
|
||
doc_result = asyncio.run(_run_process_doc())
|
||
if doc_result is not None:
|
||
content_list, _ = doc_result
|
||
|
||
else:
|
||
if not os.path.exists(file_path):
|
||
raise FileNotFoundError(f"文件未找到: {file_path}")
|
||
|
||
with open(file_path, "rb") as f:
|
||
files = {"file": (os.path.basename(file_path), f, "application/pdf")}
|
||
logger.info(file_path)
|
||
response = requests.post(api_url, files=files, timeout=12000)
|
||
|
||
if response.status_code != 200:
|
||
logger.error(f"❌ API 请求失败，状态码: {response.status_code}, 响应: {response.text}")
|
||
raise Exception(f"PDF/MD 解析 API 失败: {response.status_code}")
|
||
|
||
result = response.json()
|
||
data = result.get("data", {})
|
||
content_list = data.get("content_list")
|
||
|
||
logger.info(f"[{task_id}] 开始文件 {file_name} 的实体和关系抽取")
|
||
if check_cancelled_callback():
|
||
raise InterruptedError("任务已取消")
|
||
|
||
async def run_extraction():
|
||
return await get_md_node_relation(
|
||
content_list=content_list,
|
||
input_pdf_path=file_path,
|
||
Ontology=ontology,
|
||
Ontology_DESCRIPTION=ontology_desc,
|
||
Relationships=relationships,
|
||
RELATIONSHIP_TYPES=relationship_types,
|
||
NODE_TYPES=node_types,
|
||
PREFIX_URL=prefix_url,
|
||
device = device,
|
||
device_type = device_type
|
||
)
|
||
|
||
final_all_entity, final_all_relation = asyncio.run(run_extraction())
|
||
merged_output_data = {"entities": final_all_entity, "relationships": final_all_relation}
|
||
|
||
# --- 处理 DOCX ---
|
||
elif file_extension in ['.docx']:
|
||
base_name = os.path.splitext(file_name)[0]
|
||
pdf_filename = f"{base_name}.pdf"
|
||
pdf_path = os.path.join(data_dir, pdf_filename)
|
||
|
||
logger.info(f"[{task_id}] 转换 DOCX -> PDF: {file_name}")
|
||
|
||
try:
|
||
converter.convert(file_path, output_dir=data_dir)
|
||
|
||
if not os.path.exists(pdf_path):
|
||
raise FileNotFoundError(f"PDF 转换失败: {pdf_path}")
|
||
|
||
# 与 PDF 分支保持一致：先尝试 process_document，失败则上传 API
|
||
async def _run_process_doc_docx():
|
||
return await process_document(pdf_filename)
|
||
doc_result = asyncio.run(_run_process_doc_docx())
|
||
if doc_result is not None:
|
||
content_list, _ = doc_result
|
||
else:
|
||
with open(pdf_path, "rb") as f:
|
||
files = {"file": (pdf_filename, f, "application/pdf")}
|
||
logger.info(pdf_path)
|
||
response = requests.post(api_url, files=files, timeout=12000)
|
||
|
||
if response.status_code != 200:
|
||
logger.error(f"❌ API 请求失败，状态码: {response.status_code}, 响应: {response.text}")
|
||
raise Exception(f"PDF 解析 API 失败: {response.status_code}")
|
||
|
||
result = response.json()
|
||
data = result.get("data", {})
|
||
content_list = data.get("content_list")
|
||
|
||
logger.info(f"[{task_id}] 开始文件 {file_name} 的实体和关系抽取")
|
||
if check_cancelled_callback():
|
||
raise InterruptedError("任务已取消")
|
||
|
||
async def run_extraction_docx():
|
||
return await get_md_node_relation(
|
||
content_list=content_list,
|
||
input_pdf_path=pdf_path,
|
||
Ontology=ontology,
|
||
Ontology_DESCRIPTION=ontology_desc,
|
||
Relationships=relationships,
|
||
RELATIONSHIP_TYPES=relationship_types,
|
||
NODE_TYPES=node_types,
|
||
PREFIX_URL=prefix_url,
|
||
device=device,
|
||
device_type=device_type,
|
||
)
|
||
|
||
final_all_entity, final_all_relation = asyncio.run(run_extraction_docx())
|
||
merged_output_data = {"entities": final_all_entity, "relationships": final_all_relation}
|
||
|
||
except Exception as e:
|
||
logger.error(f"[{task_id}] DOCX 处理失败: {str(e)}")
|
||
logger.error(traceback.format_exc())
|
||
raise
|
||
finally:
|
||
pass
|
||
|
||
# --- 处理 XLSX ---
|
||
elif file_extension in ['.xlsx']:
|
||
base_name = os.path.splitext(file_name)[0]
|
||
pdf_filename = f"{base_name}.pdf"
|
||
logger.info(f"[{task_id}] 转换 xlsx -> PDF (仅生成索引引用): {file_name}")
|
||
# 注意：原代码中这里也调用了 converter，但后续逻辑主要依赖 Excel 解析
|
||
try:
|
||
converter.convert(file_path, output_dir=os.path.join(data_dir, "uploads_v1"))
|
||
except Exception as e:
|
||
logger.warning(f"Excel 转 PDF 失败，但不影响数据提取: {e}")
|
||
|
||
all_entities, all_relationships = get_excel_node_relation(file_path, sheet_name="Sheet1")
|
||
|
||
# 补充知识源信息
|
||
for entity in all_entities:
|
||
knowledge_source = []
|
||
qiepian = entity["properties"].get("切片")
|
||
url = f"{prefix_url}/files/uploads/{pdf_filename}"
|
||
knowledge_source.append({
|
||
"filename": file_name,
|
||
"info": qiepian,
|
||
"url": url
|
||
})
|
||
entity["properties"]["knowledge_source"] = knowledge_source
|
||
|
||
merged_output_data = {"entities": all_entities, "relationships": all_relationships}
|
||
|
||
else:
|
||
raise ValueError(f"不支持的文件类型: {file_extension}")
|
||
|
||
# 统一取消检查
|
||
if check_cancelled_callback():
|
||
raise InterruptedError("任务已取消")
|
||
|
||
# 保存缓存 (可选，保持原有逻辑)
|
||
try:
|
||
safe_fname = file_name.replace(os.sep, "_").replace(" ", "_")
|
||
cache_dir = os.path.join(data_dir, "kg_cache")
|
||
os.makedirs(cache_dir, exist_ok=True)
|
||
cache_path = os.path.join(cache_dir, f"merged_output_{task_id}_{safe_fname}.json")
|
||
with open(cache_path, "w", encoding="utf-8") as cf:
|
||
json.dump(merged_output_data, cf, ensure_ascii=False, indent=2)
|
||
logger.info(f"[{task_id}] Saved merged_output_data cache: {cache_path}")
|
||
except Exception as e:
|
||
logger.warning(f"[{task_id}] Failed to save merged_output_data cache: {e}")
|
||
|
||
return merged_output_data["entities"], merged_output_data["relationships"]
|
||
|
||
def check_filename_ocr(filename: str) -> Optional[str]:
|
||
"""
|
||
根据文件名关键词判断是否需要 OCR。
|
||
|
||
Returns:
|
||
"ocr_true" — 文件名包含维修/操作类关键词
|
||
"ocr_false" — 文件名包含原理/接线/总图类关键词
|
||
None — 未命中任何关键词
|
||
"""
|
||
#ocr_true_keywords = ["维修手册", "维修说明书", "操作使用手册", "图解目录","培训手册",""]
|
||
# ocr_false_keywords = ["原理图", "接线图", "总图","随机文件目录","安装说明书","芯线表","链接图","备品备件及工具清单"]
|
||
ocr_false_keywords = ["原理图", "接线图", "总图","连接图","线图","布置图","安装图","曲线图","标志图","综合图","结构图","基座图","型线图","展开图","编号图","剖面图","吊装图","总装图","曲线图","代号图","视界图","射角图","管路图","周界图","外形图","关系图","装配图","覆盖图","尺寸图","完工图","芯线表","明细表","接线表","编制表","值表册","线路表","矩阵表","汇总表","信息表","连接表","随机文件目录", "随机文件","备品备件","图解目录","电流图","接线图和芯线表","外形图","外形图、外部接线图、安装图","设备总图", "线路图"]
|
||
|
||
# for kw in ocr_true_keywords:
|
||
# if kw in filename:
|
||
# return "ocr_true"
|
||
|
||
for kw in ocr_false_keywords:
|
||
if kw in filename:
|
||
return "ocr_false"
|
||
# else:
|
||
# return "ocr_true"
|
||
|
||
#return None
|
||
return "ocr_true"
|
||
|
||
|