refine code (#595)

### What problem does this PR solve?

### Type of change

- [x] Refactoring

rag/app/laws.py

@@ -19,7 +19,7 @@ from docx import Document
 from api.db import ParserType
 from rag.nlp import bullets_category, is_english, tokenize, remove_contents_table, hierarchical_merge, \
     make_colon_as_title, add_positions, tokenize_chunks, find_codec
-from rag.nlp import huqie
+from rag.nlp import rag_tokenizer
 from deepdoc.parser import PdfParser, DocxParser, PlainParser
 from rag.settings import cron_logger
 
@@ -89,9 +89,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     """
     doc = {
         "docnm_kwd": filename,
-        "title_tks": huqie.qie(re.sub(r"\.[a-zA-Z]+$", "", filename))
+        "title_tks": rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", filename))
     }
-    doc["title_sm_tks"] = huqie.qieqie(doc["title_tks"])
+    doc["title_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["title_tks"])
     pdf_parser = None
     sections = []
     if re.search(r"\.docx$", filename, re.IGNORECASE):