Let 'One' applicable for tables in docx

rag/app/one.py

@@ -16,7 +16,7 @@
 import re
 
 from deepdoc.parser.utils import get_text
-from rag.app import laws
+from rag.app import naive
 from rag.nlp import rag_tokenizer, tokenize
 from deepdoc.parser import PdfParser, ExcelParser, PlainParser, HtmlParser
 
@@ -67,7 +67,10 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
     if re.search(r"\.docx$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        sections = [txt for txt in laws.Docx()(filename, binary) if txt]
+        sections, tbls = naive.Docx()(filename, binary)
+        sections = [s for s, _ in sections if s]
+        for (_, html), _ in tbls:
+            sections.append(html)
         callback(0.8, "Finish parsing.")
 
     elif re.search(r"\.pdf$", filename, re.IGNORECASE):