Fit a lot of encodings for text file. (#458)

### What problem does this PR solve?

#384

### Type of change

- [x] Performance Improvement

rag/app/book.py

@@ -15,7 +15,8 @@ import re
 from io import BytesIO
 
 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
+    hierarchical_merge, make_colon_as_title, naive_merge, random_choices, tokenize_table, add_positions, \
+    tokenize_chunks, find_codec
 from rag.nlp import huqie
 from deepdoc.parser import PdfParser, DocxParser, PlainParser
 
@@ -87,7 +88,8 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         callback(0.1, "Start to parse.")
         txt = ""
         if binary:
-            txt = binary.decode("utf-8")
+            encoding = find_codec(binary)
+            txt = binary.decode(encoding)
         else:
             with open(filename, "r") as f:
                 while True: