commit 8ec17d804e7f6142fae0f14120bdf06e523e3982 Author: Damian Johnson <atagar@torproject.org> Date: Sat Aug 4 17:04:24 2018 -0700 Better error message if file objects aren't seekable As reported by teor, stem.descriptor's parse_file() function cannot accept stdin... https://trac.torproject.org/projects/tor/ticket/23859 The trouble is that not all file objects in python are seekable. I'd *like* to handle address this transparently by buffering the content... try: descriptor_file.tell() except IOError: # file's not seekable, wrapping in a buffer that is descriptor_file = io.BytesIO(descriptor_file.read()) This works great if our stream has content... % cat my_descriptors | python demo.py *But* hangs indefinitely if no EOF is present in the stream. % python demo.py <= hangs Turns out non-blocking, platform independent reading of streams like stdin is pretty tricky... http://eyalarubas.com/python-subproc-nonblock.html As such simply providing callers with a more descriptive exception. If they know their stream won't block *they* can add the above wrapper to provide us with a seekable file object. --- stem/descriptor/__init__.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/stem/descriptor/__init__.py b/stem/descriptor/__init__.py index 05255648..a9860140 100644 --- a/stem/descriptor/__init__.py +++ b/stem/descriptor/__init__.py @@ -93,6 +93,13 @@ __all__ = [ 'Descriptor', ] +UNSEEKABLE_MSG = """\ +File object isn't seekable. Try wrapping it with a BytesIO instead... + + content = my_file.read() + parsed_descriptors = stem.descriptor.parse_file(io.BytesIO(content)) +""" + KEYWORD_CHAR = 'a-zA-Z0-9-' WHITESPACE = ' \t' KEYWORD_LINE = re.compile('^([%s]+)(?:[%s]+(.*))?$' % (KEYWORD_CHAR, WHITESPACE)) @@ -218,6 +225,16 @@ def parse_file(descriptor_file, descriptor_type = None, validate = False, docume return + # Not all files are seekable. If unseekable then advising the user. + # + # Python 3.x adds an io.seekable() method, but not an option with python 2.x + # so using an experimental call to tell() to determine this. + + try: + descriptor_file.tell() + except IOError: + raise IOError(UNSEEKABLE_MSG) + # The tor descriptor specifications do not provide a reliable method for # identifying a descriptor file's type and version so we need to guess # based on its filename. Metrics descriptors, however, can be identified