...

src/calibre/ebooks/metadata/pdf.py

@@ -17,6 +17,7 @@ pdfreflow, pdfreflow_error = plugins['pdfreflow']
 def get_metadata(stream, cover=True):
     if pdfreflow is None:
         raise RuntimeError(pdfreflow_error)
+    stream.seek(0)
     raw = stream.read()
     #isbn = _isbn_pat.search(raw)
     #if isbn is not None:

src/calibre/utils/mem.py

@@ -5,6 +5,8 @@ __license__   = 'GPL v3'
 __copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
+import gc
+
 ## {{{ http://code.activestate.com/recipes/286222/ (r1)
 import os
 
@@ -52,4 +54,19 @@ def stacksize(since=0.0):
 ## end of http://code.activestate.com/recipes/286222/ }}}
 
 
+def gc_histogram():
+    """Returns per-class counts of existing objects."""
+    result = {}
+    for o in gc.get_objects():
+        t = type(o)
+        count = result.get(t, 0)
+        result[t] = count + 1
+    return result
+
+def diff_hists(h1, h2):
+    """Prints differences between two results of gc_histogram()."""
+    for k in h1:
+        if h1[k] != h2[k]:
+            print "%s: %d -> %d (%s%d)" % (
+                k, h1[k], h2[k], h2[k] > h1[k] and "+" or "", h2[k] - h1[k])