Merge branch 'testing' of https://github.com/DARIAH-DE/Topics into te…

…sting

test/integration_test.py

@@ -1,14 +1,22 @@
-from subprocess import check_call
+from subprocess import check_output, STDOUT, CalledProcessError
 from nose.plugins.skip import SkipTest
+from pathlib import Path
+import logging
+
+project_path = Path(__file__).absolute().parent.parent
 
 
 def jupyter_integration_test():
     """
     Tries to run the integration test notebook using jupyter.
     """
     try:
-        check_call(["jupyter-nbconvert", "--execute",
-                    "IntegrationTest_v01.ipynb"])
+        check_output(["jupyter-nbconvert", "--execute",
+                    str(Path(project_path, "IntegrationTest_v01.ipynb"))],
+                     stderr=STDOUT, universal_newlines=True)
     except FileNotFoundError as e:
         raise SkipTest("jupyter-nbconvert not found. Cannot run integration test. "
                    + str(e))
+    except CalledProcessError as e:
+        logging.error(e.output)
+        raise

test/preprocessing_test.py

@@ -1,11 +1,14 @@
 from dariah_topics import preprocessing as pre
+from pathlib import Path
+
+project_path = Path(__file__).absolute().parent.parent
 
 # Funktion muss irgendwie mit test heißen
 def test_document_list():
 
     # die Funktion under test aufrufen
 
-    doclist = pre.create_document_list('corpus_txt')
+    doclist = pre.create_document_list(str(Path(project_path, 'corpus_txt')))
 
     # Bedingungen auf dem Ergebnis prüfen:
     assert len(doclist) == 17

test/testing.py

@@ -1,9 +1,11 @@
-import preprocessing
+from dariah_topics import preprocessing
 import glob
 import os.path
+from pathlib import Path
+
+project_path = Path(__file__).absolute().parent.parent
+basepath =  str(project_path)
 
-basepath =  os.path.abspath(os.path.join(".", os.pardir))
-
 #path_txt = "grenzbote_plain/*/"
 
 path_txt = "corpus_txt"
@@ -16,11 +18,11 @@
 
 #doc_tokens = preprocessing.tokenizer(corpus_txt)
 
-with open(os.path.join(basepath, "tutorial_supplementals/stopwords/en"), 'r', encoding = 'utf-8') as f: 
+with open(os.path.join(basepath, "tutorial_supplementals/stopwords/en"), 'r', encoding = 'utf-8') as f:
     stopword_list = f.read().split('\n')
 
 stopword_list = set(stopword_list)
-    
+
 doc_tokens = [list(preprocessing.tokenize(txt)) for txt in list(corpus_txt)]
 
 #print(list(doc_tokens[0]))
@@ -34,7 +36,7 @@
 with open("gb_all.mm", 'a', encoding = "utf-8") as f:
     f.write("%%MatrixMarket matrix coordinate real general\n")
     sparse_df.to_csv( f, sep = ' ', header = None)
-    
+
 sparse_df_stopwords_removed = preprocessing.remove_features(sparse_df, id_types, stopword_list)
 
 with open("gb_all_features_removed.mm", 'a', encoding = "utf-8") as f: