refactor: reorganize file handling imports into a structured directory

Author: liuruibin

apps/common/handle/impl/qa/zip_parse_qa_handle.py

@@ -9,20 +9,19 @@
 import io
 import os
 import re
-import uuid_utils.compat as uuid
 import zipfile
 from typing import List
 from urllib.parse import urljoin
 
-from django.db.models import QuerySet
+import uuid_utils.compat as uuid
+from django.utils.translation import gettext_lazy as _
 
 from common.handle.base_parse_qa_handle import BaseParseQAHandle
 from common.handle.impl.qa.csv_parse_qa_handle import CsvParseQAHandle
 from common.handle.impl.qa.xls_parse_qa_handle import XlsParseQAHandle
 from common.handle.impl.qa.xlsx_parse_qa_handle import XlsxParseQAHandle
 from common.utils.common import parse_md_image
 from knowledge.models import File
-from django.utils.translation import gettext_lazy as _
 
 
 class FileBufferHandle:

apps/common/handle/impl/table/csv_parse_table_handle.py

@@ -15,7 +15,7 @@ def support(self, file, get_buffer):
             return True
         return False
 
-    def handle(self, file, get_buffer,save_image):
+    def handle(self, file, get_buffer, save_image):
         buffer = get_buffer(file)
         try:
             content = buffer.decode(detect(buffer)['encoding'])
@@ -41,4 +41,4 @@ def get_content(self, file, save_image):
             return buffer.decode(detect(buffer)['encoding'])
         except BaseException as e:
             max_kb.error(f'csv split handle error: {e}')
-            return f'error: {e}'
+            return f'error: {e}'

apps/common/handle/impl/table/xlsx_parse_table_handle.py

@@ -78,7 +78,6 @@ def handle(self, file, get_buffer, save_image):
             return [{'name': file.name, 'paragraphs': []}]
         return result
 
-
     def get_content(self, file, save_image):
         try:
             # 加载 Excel 文件

apps/common/handle/impl/text/__init__.py

@@ -10,10 +10,10 @@
 import os
 import re
 import traceback
-import uuid_utils.compat as uuid
 from functools import reduce
 from typing import List
 
+import uuid_utils.compat as uuid
 from docx import Document, ImagePart
 from docx.oxml import ns
 from docx.table import Table
@@ -22,7 +22,6 @@
 from common.handle.base_split_handle import BaseSplitHandle
 from common.utils.split_model import SplitModel
 from knowledge.models import File
-from django.utils.translation import gettext_lazy as _
 
 default_pattern_list = [re.compile('(?<=^)# .*|(?<=\\n)# .*'),
                         re.compile('(?<=\\n)(?<!#)## (?!#).*|(?<=^)(?<!#)## (?!#).*'),

…s/common/handle/impl/csv_split_handle.py …mon/handle/impl/text/csv_split_handle.pyapps/common/handle/impl/csv_split_handle.py renamed to apps/common/handle/impl/text/csv_split_handle.py apps/common/handle/impl/csv_split_handle.py renamed to apps/common/handle/impl/text/csv_split_handle.py

@@ -70,4 +70,4 @@ def get_content(self, file, save_image):
             return html2text(content)
         except BaseException as e:
             traceback.print_exception(e)
-            return f'{e}'
+            return f'{e}'

…s/common/handle/impl/doc_split_handle.py …mon/handle/impl/text/doc_split_handle.pyapps/common/handle/impl/doc_split_handle.py renamed to apps/common/handle/impl/text/doc_split_handle.py apps/common/handle/impl/doc_split_handle.py renamed to apps/common/handle/impl/text/doc_split_handle.py

@@ -15,11 +15,11 @@
 from typing import List
 
 import fitz
+from django.utils.translation import gettext_lazy as _
 from langchain_community.document_loaders import PyPDFLoader
 
 from common.handle.base_split_handle import BaseSplitHandle
 from common.utils.split_model import SplitModel
-from django.utils.translation import gettext_lazy as _
 
 default_pattern_list = [re.compile('(?<=^)# .*|(?<=\\n)# .*'),
                         re.compile('(?<=\\n)(?<!#)## (?!#).*|(?<=^)(?<!#)## (?!#).*'),
@@ -42,6 +42,7 @@ def check_links_in_pdf(doc):
                     return True
     return False
 
+
 class PdfSplitHandle(BaseSplitHandle):
     def handle(self, file, pattern_list: List, with_filter: bool, limit: int, get_buffer, save_image):
         with tempfile.NamedTemporaryFile(delete=False) as temp_file:
@@ -181,7 +182,8 @@ def handle_toc(doc, limit):
                 for text in split_text:
                     chapters.append({"title": real_chapter_title, "content": text})
             else:
-                chapters.append({"title": real_chapter_title, "content": chapter_text if chapter_text else real_chapter_title})
+                chapters.append(
+                    {"title": real_chapter_title, "content": chapter_text if chapter_text else real_chapter_title})
             # 保存章节内容和章节标题
         return chapters
 
@@ -336,4 +338,4 @@ def get_content(self, file, save_image):
             return self.handle_pdf_content(file, pdf_document)
         except BaseException as e:
             traceback.print_exception(e)
-            return f'{e}'
+            return f'{e}'

…/common/handle/impl/html_split_handle.py …on/handle/impl/text/html_split_handle.pyapps/common/handle/impl/html_split_handle.py renamed to apps/common/handle/impl/text/html_split_handle.py apps/common/handle/impl/html_split_handle.py renamed to apps/common/handle/impl/text/html_split_handle.py

@@ -54,7 +54,7 @@ def handle(self, file, pattern_list: List, with_filter: bool, limit: int, get_bu
     def get_content(self, file, save_image):
         buffer = file.read()
         try:
-           return buffer.decode(detect(buffer)['encoding'])
+            return buffer.decode(detect(buffer)['encoding'])
         except BaseException as e:
             traceback.print_exception(e)
-            return f'{e}'
+            return f'{e}'