Fix ResourceWarnings in tests

gensim/matutils.py

@@ -789,7 +789,7 @@ def __init__(self, input, transposed=True):
         to be rows of the matrix (and document features are columns).
 
         `input` is either a string (file path) or a file-like object that supports
-        `seek()` (e.g. gzip.GzipFile, bz2.BZ2File).
+        `seek()` (e.g. gzip.GzipFile, bz2.BZ2File). File-like objects are not closed automatically.
         """
         logger.info("initializing corpus reader from %s", input)
         self.input, self.transposed = input, transposed
@@ -881,9 +881,9 @@ def docbyoffset(self, offset):
         if offset == -1:
             return []
         if isinstance(self.input, string_types):
-            fin = utils.smart_open(self.input)
+            fin, close_fin = utils.smart_open(self.input), True
         else:
-            fin = self.input
+            fin, close_fin = self.input, False
 
         fin.seek(offset)  # works for gzip/bz2 input, too
         previd, document = -1, []
@@ -895,8 +895,11 @@ def docbyoffset(self, offset):
             assert previd <= docid, "matrix columns must come in ascending order"
             if docid != previd:
                 if previd >= 0:
-                    return document
+                    break
                 previd = docid
 
             document.append((termid, val,))  # add another field to the current document
+
+        if close_fin:
+            fin.close()
         return document

gensim/test/test_glove2word2vec.py

@@ -9,6 +9,7 @@
 import logging
 import unittest
 import os
+import sys
 import tempfile
 
 import numpy
@@ -32,7 +33,7 @@ def setUp(self):
 
     def testConversion(self):
         check_output(args=[
-            'python', '-m', 'gensim.scripts.glove2word2vec',
+            sys.executable, '-m', 'gensim.scripts.glove2word2vec',
             '--input', self.datapath, '--output', self.output_file
         ])
         # test that the converted model loads successfully

gensim/utils.py

@@ -33,7 +33,6 @@
 import multiprocessing
 import shutil
 import sys
-from contextlib import contextmanager
 import subprocess
 
 import numpy as np
@@ -135,7 +134,6 @@ def __exit__(self, type, value, traceback):
 nocm = NoCM()
 
 
-@contextmanager
 def file_or_filename(input):
     """
     Return a file-like object ready to be read from the beginning. `input` is either
@@ -144,11 +142,11 @@ def file_or_filename(input):
     """
     if isinstance(input, string_types):
         # input was a filename: open as file
-        yield smart_open(input)
+        return smart_open(input)
     else:
         # input already a file-like object; just reset to the beginning
         input.seek(0)
-        yield input
+        return input
 
 
 def deaccent(text):