Fix: chunk method error. (#11807)

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

rag/app/laws.py

@@ -201,12 +201,23 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
     elif re.search(r"\.doc$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        binary = BytesIO(binary)
-        doc_parsed = parser.from_buffer(binary)
-        sections = doc_parsed['content'].split('\n')
-        sections = [s for s in sections if s]
-        callback(0.8, "Finish parsing.")
+        try:
+            from tika import parser as tika_parser
+        except Exception as e:
+            callback(0.8, f"tika not available: {e}. Unsupported .doc parsing.")
+            logging.warning(f"tika not available: {e}. Unsupported .doc parsing for {filename}.")
+            return []
 
+        binary = BytesIO(binary)
+        doc_parsed = tika_parser.from_buffer(binary)
+        if doc_parsed.get('content', None) is not None:
+            sections = doc_parsed['content'].split('\n')
+            sections = [s for s in sections if s]
+            callback(0.8, "Finish parsing.")
+        else:
+            callback(0.8, f"tika.parser got empty content from {filename}.")
+            logging.warning(f"tika.parser got empty content from {filename}.")
+            return []
     else:
         raise NotImplementedError(
             "file type not supported yet(doc, docx, pdf, txt supported)")