Merge fca29fa into f2fdef0

danlp/datasets/dacoref.py

@@ -27,7 +27,7 @@ def load_as_conllu(self, predefined_splits: bool = False):
                 or a list of train, dev, test split parsed conllu list
                 depending on predefined_split
         """
-        with open('{}/CDT_coref.conllu'.format(self.dataset_dir)) as f:
+        with open('{}/CDT_coref.conllu'.format(self.dataset_dir), encoding='utf-8') as f:
             conlist = conllu.parse(f.read(), fields=["id", "form", "lemma", "upos", 'xpos', 'feats', 'head', 'deprel','deps', 'misc', 'coref_id', 'coref_rel', 'doc_id', 'qid'])
 
         if predefined_splits==False:

danlp/datasets/ddt.py

@@ -136,7 +136,7 @@ def load_with_spacy(self):
             json_path = os.path.join(self.dataset_dir, "ddt.{}.json".format(part))
 
             if not os.path.isfile(json_path):  # Convert the conllu files to json
-                with open(conll_path, 'r') as file:
+                with open(conll_path, 'r', encoding='utf-8') as file:
                     file_as_string = file.read()
                     file_as_string = file_as_string.replace("name=", "").replace("|SpaceAfter=No", "")
                     file_as_json = conllu2json(file_as_string)

danlp/utils.py

@@ -70,6 +70,7 @@ def extract_single_file_from_zip(cache_dir: str, file_in_zip: str, dest_full_pat
     tmp_path = os.path.join(cache_dir, ''.join(random_string()))
 
     outpath = zip_file.extract(file_in_zip, path=tmp_path)
-    os.rename(outpath, dest_full_path)
+    if not os.path.exists(dest_full_path):
+        os.rename(outpath, dest_full_path)
 
     shutil.rmtree(tmp_path)

docs/docs/datasets.md

@@ -263,7 +263,7 @@ dannet.meanings(word)
 # part-of-speech (returns a list comprised in 'Noun', 'Verb' or 'Adjective')
 dannet.pos(word)
 # wordnet relations (EUROWORDNET or WORDNETOWL)
-dannet.wordnet_relations(word, eurowordnet=True))
+dannet.wordnet_relations(word, eurowordnet=True)
 # word ids
 dannet._word_ids(word)
 # synset ids