what

dataset.py

@@ -128,8 +128,11 @@ def get_crisis_dataset():
             date_path = topic_path / 'public' / 'content' / pub_date
             for article_filename in util.files(date_path, extension='.cont'):
                 article_file_path = date_path / article_filename
-                if '2429.htm.cont' not in str(article_file_path):
+
+                # nah
+                if '2429.htm.cont' in str(article_file_path):
                     continue
+
                 print(article_file_path)
                 article = {'pub_date': pub_date, 'sentences': []}
 

heideltime_util.py

@@ -17,7 +17,7 @@ def mentioned_dates_by_sentence(filename, pub_date):
     # create a temporary copy of the file with interfering characters escaped
     escaped_filename = str(filename) + '.escaped'
     with util.detect_encoding_and_open(filename) as f, open(escaped_filename, 'w', encoding='utf-8') as g:
-        for line in f:
+        for line in f.readlines():
             g.write(escape(line))
 
     # change to heideltime directory (and keep track of the path back to the root)