Fixes piskvorky#1869 , Mmcorpus file-like object behaviour fixed

gensim/matutils.py

@@ -25,7 +25,7 @@
 
 from six import iteritems, itervalues, string_types
 from six.moves import xrange, zip as izip
-
+from contextlib import contextmanager
 
 logger = logging.getLogger(__name__)
 
@@ -1328,10 +1328,23 @@ class MmReader(object):
     This allows us to process corpora which are larger than the available RAM.
 
     """
+    @contextmanager
+    def open_file(self, input):
+        #Generates 'with' like behaviour excepting closing the file object
+        mgr = utils.file_or_filename(self.input)
+        exc = False
+        try:
+            yield mgr
+        except StandardError:
+            exc = True
+            if not exit(mgr, *sys.exc_info()):
+                raise
+        finally:
+            if not exc and isinstance(self.input, string_types):
+                exit(mgr, None, None, None)
 
     def __init__(self, input, transposed=True):
         """
-
         Parameters
         ----------
         input : {str, file-like object}
@@ -1344,39 +1357,25 @@ def __init__(self, input, transposed=True):
         logger.info("initializing corpus reader from %s", input)
         self.input, self.transposed = input, transposed
 
-        # 'with' statement behaviour without closing the file object
-        mgr = (utils.file_or_filename(self.input))
-        exit = type(mgr).__exit__
-        value = type(mgr).__enter__(mgr)
-        exc = True
-        try:
+        with self.open_file(self.input) as lines:
             try:
-                lines = value
-                try:
-                    header = utils.to_unicode(next(lines)).strip()
-                    if not header.lower().startswith('%%matrixmarket matrix coordinate real general'):
-                        raise ValueError(
-                            "File %s not in Matrix Market format with coordinate real general; instead found: \n%s" %
-                            (self.input, header)
-                        )
-                except StopIteration:
-                    pass
-
-                self.num_docs = self.num_terms = self.num_nnz = 0
-                for lineno, line in enumerate(lines):
-                    line = utils.to_unicode(line)
-                    if not line.startswith('%'):
-                        self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split())
-                        if not self.transposed:
-                            self.num_docs, self.num_terms = self.num_terms, self.num_docs
-                        break
-            except RuntimeError:
-                exc = False
-                if not exit(mgr, *sys.exc_info()):
-                    raise
-        finally:
-            if exc and isinstance(self.input, string_types):
-                exit(mgr, None, None, None)
+                header = utils.to_unicode(next(lines)).strip()
+                if not header.lower().startswith('%%matrixmarket matrix coordinate real general'):
+                    raise ValueError(
+                        "File %s not in Matrix Market format with coordinate real general; instead found: \n%s" %
+                        (self.input, header)
+                    )
+            except StopIteration:
+                pass
+
+            self.num_docs = self.num_terms = self.num_nnz = 0
+            for lineno, line in enumerate(lines):
+                line = utils.to_unicode(line)
+                if not line.startswith('%'):
+                    self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split())
+                    if not self.transposed:
+                        self.num_docs, self.num_terms = self.num_terms, self.num_docs
+                    break
 
         logger.info(
             "accepted corpus with %i documents, %i features, %i non-zero entries",