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/book.py

@@ -15,6 +15,7 @@ from tika import parser
 import re
 from io import BytesIO
 
+from deepdoc.parser.utils import get_text
 from rag.nlp import bullets_category, is_english, tokenize, remove_contents_table, \
     hierarchical_merge, make_colon_as_title, naive_merge, random_choices, tokenize_table, add_positions, \
     tokenize_chunks, find_codec
@@ -88,17 +89,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
     elif re.search(r"\.txt$", 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)
         sections = txt.split("\n")
         sections = [(l, "") for l in sections if l]
         remove_contents_table(sections, eng=is_english(