Add get_txt function (#2639)

### What problem does this PR solve?

Add get_txt function to reduce duplicate code

### Type of change

- [x] Refactoring

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

rag/app/table.py

@@ -20,6 +20,7 @@ from openpyxl import load_workbook
 from dateutil.parser import parse as datetime_parse
 
 from api.db.services.knowledgebase_service import KnowledgebaseService
+from deepdoc.parser.utils import get_text
 from rag.nlp import rag_tokenizer, is_english, tokenize, find_codec
 from deepdoc.parser import ExcelParser
 
@@ -146,17 +147,7 @@ def chunk(filename, binary=None, from_page=0, to_page=10000000000,
             callback=callback)
     elif re.search(r"\.(txt|csv)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        txt = ""
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(filename, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
+        txt = get_text(filename, binary)
         lines = txt.split("\n")
         fails = []
         headers = lines[0].split(kwargs.get("delimiter", "\t"))