commit 677272c11ea1a4b86fb143a12a76d03a6384b032 Author: aagbsn aagbsn@extc.org Date: Wed May 30 21:03:47 2012 -0700

5947 - Parse "a" lines from networkstatus

The "a" lines have been tested by the Bridge Authority. The or-addresses in the bridge descriptors have not.

This fix makes BridgeDB read or-addresses from the networkstatus instead of the bridge descriptors --- lib/bridgedb/Bridges.py | 46 +++++++++++++++++++++------------------------- lib/bridgedb/Main.py | 9 ++++++--- 2 files changed, 27 insertions(+), 28 deletions(-)

diff --git a/lib/bridgedb/Bridges.py b/lib/bridgedb/Bridges.py index 1e15157..9af5dfb 100644 --- a/lib/bridgedb/Bridges.py +++ b/lib/bridgedb/Bridges.py @@ -268,37 +268,14 @@ def parseDescFile(f, bridge_purpose='bridge'): orport = int(items[3]) elif line.startswith("fingerprint "): fingerprint = line[12:].replace(" ", "") - elif line.startswith("or-address "): - if num_or_address_lines < 8: - line = line[11:] - try: - address,portlist = parseORAddressLine(line) - except ParseORAddressError: - logging.warn("Invalid or-address line "\ - "from bridge with ID %r" %fingerprint) - continue - try: - # distinct ports only - portlist.add(or_addresses[address]) - except KeyError: - pass - finally: - or_addresses[address] = portlist - else: - logging.warn("Skipping extra or-address line "\ - "from Bridge with ID %r" % id) - num_or_address_lines += 1 elif line.startswith("router-signature"): purposeMatches = (purpose == bridge_purpose or bridge_purpose is None) if purposeMatches and nickname and ip and orport and fingerprint: - b = Bridge(nickname, ip, orport, fingerprint, - or_addresses=or_addresses) + b = Bridge(nickname, ip, orport, fingerprint) b.assertOK() yield b nickname = ip = orport = fingerprint = purpose = None - num_or_address_lines = 0 - or_addresses = {}

class PortList: """ container class for port ranges @@ -374,6 +351,8 @@ def parseORAddressLine(line): def parseStatusFile(f): """DOCDOC""" ID = None + num_or_address_lines = 0 + or_addresses = {} for line in f: line = line.strip() if line.startswith("opt "): @@ -384,9 +363,26 @@ def parseStatusFile(f): ID = binascii.a2b_base64(line.split()[2]+"=") except binascii.Error: logging.warn("Unparseable base64 ID %r", line.split()[2]) + + elif ID and line.startswith("a "): + if num_or_address_lines < 8: + line = line[2:] + address,portlist = parseORAddressLine(line) + try: + or_addresses[address].add(portlist) + except KeyError: + or_addresses[address] = portlist + else: + logging.warn("Skipping extra or-address line "\ + "from Bridge with ID %r" % id) + num_or_address_lines += 1 + elif ID and line.startswith("s "): flags = line.split() - yield ID, ("Running" in flags), ("Stable" in flags) + yield ID, ("Running" in flags), ("Stable" in flags), or_addresses + ID = None + num_or_address_lines = 0 + or_addresses = {}

def parseCountryBlockFile(f): """Generator. Parses a blocked-bridges file 'f', and yields a diff --git a/lib/bridgedb/Main.py b/lib/bridgedb/Main.py index fe34cb0..befb4ed 100644 --- a/lib/bridgedb/Main.py +++ b/lib/bridgedb/Main.py @@ -166,10 +166,12 @@ def load(cfg, splitter, clear=False): countryblock.clear() logging.info("Loading bridges") status = {} + addresses = {} if hasattr(cfg, "STATUS_FILE"): f = open(cfg.STATUS_FILE, 'r') - for ID, running, stable in Bridges.parseStatusFile(f): + for ID, running, stable, or_addresses in Bridges.parseStatusFile(f): status[ID] = running, stable + addresses[ID] = or_addresses f.close() if hasattr(cfg, "COUNTRY_BLOCK_FILE"): f = open(cfg.COUNTRY_BLOCK_FILE, 'r') @@ -183,6 +185,7 @@ def load(cfg, splitter, clear=False): if s is not None: running, stable = s bridge.setStatus(running=running, stable=stable) + bridge.or_addresses = addresses.get(bridge.getID()) bridge.setBlockingCountries( countryblock.getBlockingCountries(bridge.fingerprint)) splitter.insert(bridge) @@ -324,8 +327,8 @@ def startup(cfg): logging.info("%d for email", len(emailDistributor.splitter)) if ipDistributor: logging.info("%d for web:", len(ipDistributor.splitter)) - for (n,(f,r)) in ipDistributor.splitter.filterRings.items(): - logging.info(" by filter set %s, %d" % (n, len(r))) + for (n,(f,r)) in ipDistributor.splitter.filterRings.items(): + logging.info(" by filter set %s, %d" % (n, len(r))) #logging.info(" by location set: %s", # " ".join(str(len(r)) for r in ipDistributor.rings)) #logging.info(" by category set: %s",