Compute confidence scores by char, word or line

Closes #33 (closed)

dan/predict/attention.py

 # -*- coding: utf-8 -*-
+import re
+
 import cv2
 import numpy as np
 from PIL import Image
@@ -18,17 +20,11 @@ def split_text(text, level, word_separators, line_separators):
         offset = 0
     # split into words
     elif level == "word":
-        main_sep = word_separators[0]
-        for other_sep in word_separators[1:]:
-            text = text.replace(other_sep, main_sep)
-        text_split = text.split(main_sep)
+        text_split = re.split(word_separators, text)
         offset = 1
     # split into lines
     elif level == "line":
-        main_sep = line_separators[0]
-        for other_sep in line_separators[1:]:
-            text = text.replace(other_sep, main_sep)
-        text_split = text.split(main_sep)
+        text_split = re.split(line_separators, text)
         offset = 1
     else:
         logger.error("Level should be either 'char', 'word', or 'line'")