Merge branch 'main' of https://github.com/biomedicalinformaticsgroup/cadmus into main

Author: jcampb14

cadmus/parsing/html_to_parsed_text.py

@@ -1,4 +1,6 @@
 from cadmus.parsing.get_attrs import get_attrs
+import re
+import unicodedata
 
 def html_to_parsed_text(soup):
     # i want to save the text portions to a holding list, adding new sections each time we think its useful or new.

setup.py

@@ -2,7 +2,7 @@
 
 setuptools.setup(
     name="cadmus",
-    version="0.2.1",
+    version="0.2.2",
     author="Jamie Campbell, Ian Simpson, Antoine Lain",
     author_email="Jamie.campbell@igmm.ed.ac.uk, Ian.Simpson@ed.ac.uk, Antoine.Lain@ed.ac.uk",
     description="This projects is to build full text retrieval system setup for generation of large biomedical corpora from published literature.",