[tor-commits] [stem/master] Adding a broken get_microdescriptors() method

[atagar at torproject.org]

commit 749c8d37fd54ea6e41dfca04495c35b47a755f6a
Author: Damian Johnson <atagar at torproject.org>
Date:   Sat Jul 20 09:52:07 2013 -0700

    Adding a broken get_microdescriptors() method
    
    Huh. Not really sure why this isn't working. Adding a get_microdescriptors()
    for how the spec seems to indicate that the method works but tor gives an empty
    reply.
    
    % curl http://217.13.197.5:9030/tor/micro/d/6dCl6ab8CLo0LeMjxi/MZgVJiZgWN8WKTesWPBMtyTo
    
    Checking with karsten on irc t see if he knows what's up, and moving on to
    another part.
---
 stem/descriptor/remote.py       |   40 +++++++++++++++++++++++++++++++++------
 test/integ/descriptor/remote.py |   35 ++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+), 6 deletions(-)

diff --git a/stem/descriptor/remote.py b/stem/descriptor/remote.py
index 9df09f4..e0ca612 100644
--- a/stem/descriptor/remote.py
+++ b/stem/descriptor/remote.py
@@ -52,9 +52,10 @@ from stem import Flag
 from stem.util import log
 
 # Tor has a limit on the number of descriptors we can fetch explicitly by their
-# fingerprint.
+# fingerprint or hashes due to the url lenght of squid proxies.
 
-MAX_BATCH_SIZE = 96
+MAX_DESCRIPTOR_BATCH_SIZE = 96
+MAX_MICRODESCRIPTOR_BATCH_SIZE = 92
 
 # Tor directory authorities as of commit f631b73 (7/4/13). This should only
 # include authorities with 'v3ident':
@@ -318,8 +319,8 @@ class DescriptorDownloader(object):
       fingerprints = [fingerprints]
 
     if fingerprints:
-      if len(fingerprints) > MAX_BATCH_SIZE:
-        raise ValueError("Unable to request more than %i descriptors at a time by their fingerprints" % MAX_BATCH_SIZE)
+      if len(fingerprints) > MAX_DESCRIPTOR_BATCH_SIZE:
+        raise ValueError("Unable to request more than %i descriptors at a time by their fingerprints" % MAX_DESCRIPTOR_BATCH_SIZE)
 
       resource = '/tor/server/fp/%s' % '+'.join(fingerprints)
 
@@ -346,13 +347,40 @@ class DescriptorDownloader(object):
       fingerprints = [fingerprints]
 
     if fingerprints:
-      if len(fingerprints) > MAX_BATCH_SIZE:
-        raise ValueError("Unable to request more than %i descriptors at a time by their fingerprints" % MAX_BATCH_SIZE)
+      if len(fingerprints) > MAX_DESCRIPTOR_BATCH_SIZE:
+        raise ValueError("Unable to request more than %i descriptors at a time by their fingerprints" % MAX_DESCRIPTOR_BATCH_SIZE)
 
       resource = '/tor/extra/fp/%s' % '+'.join(fingerprints)
 
     return self._query(resource, 'extra-info 1.0')
 
+  def get_microdescriptors(self, hashes):
+    """
+    Provides the microdescriptors with the given hashes. To get these see the
+    'microdescriptor_hashes' attribute of
+    :class:`~stem.descriptor.router_status_entry.RouterStatusEntryV3`. Note
+    that these are only provided via a microdescriptor consensus (such as
+    'cached-microdesc-consensus' in your data directory).
+
+    :param str,list hashes: microdescriptor hash or list of hashes to be
+      retrieved
+
+    :returns: :class:`~stem.descriptor.remote.Query` for the microdescriptors
+
+    :raises: **ValueError** if we request more than 92 microdescriptors by their
+      hashes (this is due to a limit on the url length by squid proxies).
+    """
+
+    if isinstance(hashes, str):
+      hashes = [hashes]
+
+    if len(hashes) > MAX_MICRODESCRIPTOR_BATCH_SIZE:
+      raise ValueError("Unable to request more than %i microdescriptors at a time by their hashes" % MAX_MICRODESCRIPTOR_BATCH_SIZE)
+
+    resource = '/tor/micro/d/%s' % '-'.join(hashes)
+
+    return self._query(resource, 'microdescriptor 1.0')
+
   def get_consensus(self, document_handler = stem.descriptor.DocumentHandler.ENTRIES, authority_v3ident = None):
     """
     Provides the present router status entries.
diff --git a/test/integ/descriptor/remote.py b/test/integ/descriptor/remote.py
index a705486..e9d4e8a 100644
--- a/test/integ/descriptor/remote.py
+++ b/test/integ/descriptor/remote.py
@@ -5,6 +5,7 @@ Integration tests for stem.descriptor.remote.
 import unittest
 
 import stem.descriptor.extrainfo_descriptor
+import stem.descriptor.microdescriptor
 import stem.descriptor.remote
 import stem.descriptor.router_status_entry
 import stem.descriptor.server_descriptor
@@ -128,6 +129,40 @@ class TestDescriptorReader(unittest.TestCase):
 
     self.assertEqual(2, len(list(multiple_query)))
 
+  def test_get_microdescriptors(self):
+    """
+    Exercises the downloader's get_microdescriptors() method.
+    """
+
+    # TODO: method needs to be fixed - not quite sure what's going wrong...
+
+    test.runner.skip(self, '(test presently broken)')
+    return
+
+    if test.runner.require_online(self):
+      return
+    elif test.runner.only_run_once(self, "test_get_microdescriptors"):
+      return
+
+    downloader = stem.descriptor.remote.DescriptorDownloader()
+
+    single_query = downloader.get_microdescriptors('6dCl6ab8CLo0LeMjxi/MZgVJiZgWN8WKTesWPBMtyTo')
+
+    multiple_query = downloader.get_microdescriptors([
+      '6dCl6ab8CLo0LeMjxi/MZgVJiZgWN8WKTesWPBMtyTo',  # moria1
+      'oXBV80OwMACBJpqNeZrYSXF18l9EJCi4/mB8UOl9sME',  # tor26
+    ])
+
+    single_query.run()
+    multiple_query.run()
+
+    single_query_results = list(single_query)
+    self.assertEqual(1, len(single_query_results))
+    self.assertEqual('moria1', single_query_results[0].digest)
+    self.assertTrue(isinstance(single_query_results[0], stem.descriptor.microdescriptor.Microdescriptor))
+
+    self.assertEqual(2, len(list(multiple_query)))
+
   def test_get_consensus(self):
     """
     Exercises the downloader's get_consensus() method.