zhuchaowe/maxkb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: 修复上传文档中后缀为PDF 不识别

Browse Source
This commit is contained in:
shaohuzhang1 2024-08-27 14:14:51 +08:00 committed by shaohuzhang1
parent 3dfcb0ff9a
commit a9443a638c
4 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
apps/common/handle/impl/doc_split_handle.py
View File

@ -149,6 +149,7 @@ class DocSplitHandle(BaseSplitHandle):
def support(self, file, get_buffer):
file_name: str = file.name.lower()
if file_name.endswith(".docx") or file_name.endswith(".doc"):
if file_name.endswith(".docx") or file_name.endswith(".doc") or file_name.endswith(
".DOC") or file_name.endswith(".DOCX"):
return True
return False

2
apps/common/handle/impl/html_split_handle.py
View File

@ -38,7 +38,7 @@ def get_encoding(buffer):
class HTMLSplitHandle(BaseSplitHandle):
def support(self, file, get_buffer):
file_name: str = file.name.lower()
if file_name.endswith(".html"):
if file_name.endswith(".html") or file_name.endswith(".HTML"):
return True
return False

5
apps/common/handle/impl/pdf_split_handle.py
View File

@ -74,7 +74,8 @@ class PdfSplitHandle(BaseSplitHandle):
elapsed_time = time.time() - start_time
# todo 实现进度条代替下面的普通输出
max_kb.debug(f"File: {file.name}, Page: {page_num + 1}, Time : {elapsed_time: .3f}s, content-length: {len(page_content)}")
max_kb.debug(
f"File: {file.name}, Page: {page_num + 1}, Time : {elapsed_time: .3f}s, content-length: {len(page_content)}")
if pattern_list is not None and len(pattern_list) > 0:
split_model = SplitModel(pattern_list, with_filter, limit)
else:
@ -96,6 +97,6 @@ class PdfSplitHandle(BaseSplitHandle):
def support(self, file, get_buffer):
file_name: str = file.name.lower()
if file_name.endswith(".pdf"):
if file_name.endswith(".pdf") or file_name.endswith(".PDF"):
return True
return False

3
apps/common/handle/impl/text_split_handle.py
View File

@ -26,7 +26,8 @@ class TextSplitHandle(BaseSplitHandle):
def support(self, file, get_buffer):
buffer = get_buffer(file)
file_name: str = file.name.lower()
if file_name.endswith(".md") or file_name.endswith('.txt'):
if file_name.endswith(".md") or file_name.endswith('.txt') or file_name.endswith('.TXT') or file_name.endswith(
'.MD'):
return True
result = detect(buffer)
if result['encoding'] is not None and result['confidence'] is not None and result['encoding'] != 'ascii' and \