chore: normalize with_filter parameter to boolean in split handle files

--bug=1057879 --user=刘瑞斌 【知识库】高级分段中自动清洗功能未生效 https://www.tapd.cn/62980211/s/1727744

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

@@ -197,6 +197,8 @@ class DocSplitHandle(BaseSplitHandle):
         try:
             if type(limit) is str:
                 limit = int(limit)
+            if type(with_filter) is str:
+                with_filter = with_filter.lower() == 'true'
             image_list = []
             buffer = get_buffer(file)
             doc = Document(io.BytesIO(buffer))

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

@@ -48,6 +48,8 @@ class HTMLSplitHandle(BaseSplitHandle):
         buffer = get_buffer(file)
         if type(limit) is str:
             limit = int(limit)
+        if type(with_filter) is str:
+            with_filter = with_filter.lower() == 'true'
         if pattern_list is not None and len(pattern_list) > 0:
             split_model = SplitModel(pattern_list, with_filter, limit)
         else:

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

@@ -54,6 +54,8 @@ class PdfSplitHandle(BaseSplitHandle):
         try:
             if type(limit) is str:
                 limit = int(limit)
+            if type(with_filter) is str:
+                with_filter = with_filter.lower() == 'true'
             # 处理有目录的pdf
             result = self.handle_toc(pdf_document, limit)
             if result is not None:

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

@@ -43,6 +43,8 @@ class TextSplitHandle(BaseSplitHandle):
         buffer = get_buffer(file)
         if type(limit) is str:
             limit = int(limit)
+        if type(with_filter) is str:
+            with_filter = with_filter.lower() == 'true'
         if pattern_list is not None and len(pattern_list) > 0:
             split_model = SplitModel(pattern_list, with_filter, limit)
         else:

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

@@ -121,6 +121,8 @@ class ZipSplitHandle(BaseSplitHandle):
     def handle(self, file, pattern_list: List, with_filter: bool, limit: int, get_buffer, save_image):
         if type(limit) is str:
             limit = int(limit)
+        if type(with_filter) is str:
+            with_filter = with_filter.lower() == 'true'
         buffer = get_buffer(file)
         bytes_io = io.BytesIO(buffer)
         result = []