refactor: reorganize file handling imports into a structured directory

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

@@ -9,12 +9,12 @@
 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
@@ -22,7 +22,6 @@ 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 @@ class CsvSplitHandle(BaseParseTableHandle):
             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 @@ class CsvSplitHandle(BaseParseTableHandle):
             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 @@ class XlsxSplitHandle(BaseParseTableHandle):
             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/doc_split_handle.py

@@ -10,10 +10,10 @@ import io
 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 docx.text.paragraph import Paragraph
 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)(?<!#)## (?!#).*|(?<=^)(?<!#)## (?!#).*'),

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

@@ -70,4 +70,4 @@ class HTMLSplitHandle(BaseSplitHandle):
             return html2text(content)
         except BaseException as e:
             traceback.print_exception(e)
-            return f'{e}'
+            return f'{e}'

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

@@ -15,11 +15,11 @@ import traceback
 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 @@ class PdfSplitHandle(BaseSplitHandle):
                 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 @@ class PdfSplitHandle(BaseSplitHandle):
             return self.handle_pdf_content(file, pdf_document)
         except BaseException as e:
             traceback.print_exception(e)
-            return f'{e}'
+            return f'{e}'

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

@@ -54,7 +54,7 @@ class TextSplitHandle(BaseSplitHandle):
     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}'

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

@@ -18,13 +18,13 @@ from charset_normalizer import detect
 from django.utils.translation import gettext_lazy as _
 
 from common.handle.base_split_handle import BaseSplitHandle
-from common.handle.impl.csv_split_handle import CsvSplitHandle
+from common.handle.impl.text.csv_split_handle import CsvSplitHandle
-from common.handle.impl.doc_split_handle import DocSplitHandle
+from common.handle.impl.text.doc_split_handle import DocSplitHandle
-from common.handle.impl.html_split_handle import HTMLSplitHandle
+from common.handle.impl.text.html_split_handle import HTMLSplitHandle
-from common.handle.impl.pdf_split_handle import PdfSplitHandle
+from common.handle.impl.text.pdf_split_handle import PdfSplitHandle
-from common.handle.impl.text_split_handle import TextSplitHandle
+from common.handle.impl.text.text_split_handle import TextSplitHandle
-from common.handle.impl.xls_split_handle import XlsSplitHandle
+from common.handle.impl.text.xls_split_handle import XlsSplitHandle
-from common.handle.impl.xlsx_split_handle import XlsxSplitHandle
+from common.handle.impl.text.xlsx_split_handle import XlsxSplitHandle
 from common.utils.common import parse_md_image
 from knowledge.models import File
 

apps/knowledge/serializers/document.py

@@ -13,14 +13,14 @@ from rest_framework import serializers
 from common.db.search import native_search
 from common.event import ListenerManagement
 from common.exception.app_exception import AppApiException
-from common.handle.impl.csv_split_handle import CsvSplitHandle
+from common.handle.impl.text.csv_split_handle import CsvSplitHandle
-from common.handle.impl.doc_split_handle import DocSplitHandle
+from common.handle.impl.text.doc_split_handle import DocSplitHandle
-from common.handle.impl.html_split_handle import HTMLSplitHandle
+from common.handle.impl.text.html_split_handle import HTMLSplitHandle
-from common.handle.impl.pdf_split_handle import PdfSplitHandle
+from common.handle.impl.text.pdf_split_handle import PdfSplitHandle
-from common.handle.impl.text_split_handle import TextSplitHandle
+from common.handle.impl.text.text_split_handle import TextSplitHandle
-from common.handle.impl.xls_split_handle import XlsSplitHandle
+from common.handle.impl.text.xls_split_handle import XlsSplitHandle
-from common.handle.impl.xlsx_split_handle import XlsxSplitHandle
+from common.handle.impl.text.xlsx_split_handle import XlsxSplitHandle
-from common.handle.impl.zip_split_handle import ZipSplitHandle
+from common.handle.impl.text.zip_split_handle import ZipSplitHandle
 from common.utils.common import post, get_file_content
 from knowledge.models import Knowledge, Paragraph, Problem, Document, KnowledgeType, ProblemParagraphMapping, State, \
     TaskType, File