commit ec335d1b5bf4368982bc9736a271f675a6a7c60d Author: Damian Johnson <atagar@torproject.org> Date: Thu Oct 11 19:54:05 2012 -0700 Supporting v2 documents in the descriptor reader The v2 descriptor's integ data broke the descriptor reader tests. Turned that I had forgotten to add v2 documents to the types that it recognizes. --- stem/descriptor/__init__.py | 6 +++- stem/descriptor/networkstatus.py | 25 ++++++++++++++++------- test/integ/descriptor/data/cached-consensus-v2 | 1 + test/integ/descriptor/networkstatus.py | 1 + 4 files changed, 23 insertions(+), 10 deletions(-) diff --git a/stem/descriptor/__init__.py b/stem/descriptor/__init__.py index f0ab82d..9d33ab7 100644 --- a/stem/descriptor/__init__.py +++ b/stem/descriptor/__init__.py @@ -25,7 +25,6 @@ __all__ = [ import os import re -import datetime import collections import stem.util.enum @@ -86,7 +85,7 @@ def parse_file(path, descriptor_file): elif filename == "cached-consensus": file_parser = stem.descriptor.networkstatus.parse_file elif filename == "cached-microdesc-consensus": - file_parser = lambda f: stem.descriptor.networkstatus.parse_file(f, True, True) + file_parser = lambda f: stem.descriptor.networkstatus.parse_file(f, is_microdescriptor = True) else: # Metrics descriptor handling first_line, desc = descriptor_file.readline().strip(), None @@ -128,6 +127,9 @@ def _parse_metrics_file(descriptor_type, major_version, minor_version, descripto elif descriptor_type in ("network-status-consensus-3", "network-status-vote-3") and major_version == 1: for desc in stem.descriptor.networkstatus.parse_file(descriptor_file): yield desc + elif descriptor_type == "network-status-2" and major_version == 1: + for desc in stem.descriptor.networkstatus.parse_file(descriptor_file, document_version = 2): + yield desc elif descriptor_type == "network-status-microdesc-consensus-3" and major_version == 1: for desc in stem.descriptor.networkstatus.parse_file(descriptor_file, is_microdescriptor = True): yield desc diff --git a/stem/descriptor/networkstatus.py b/stem/descriptor/networkstatus.py index a028572..21f7ee0 100644 --- a/stem/descriptor/networkstatus.py +++ b/stem/descriptor/networkstatus.py @@ -164,7 +164,7 @@ BANDWIDTH_WEIGHT_ENTRIES = ( "Wmb", "Wmd", "Wme", "Wmg", "Wmm", ) -def parse_file(document_file, validate = True, is_microdescriptor = False): +def parse_file(document_file, validate = True, is_microdescriptor = False, document_version = 3): """ Parses a network status and iterates over the RouterStatusEntry in it. The document that these instances reference have an empty 'rotuers' attribute to @@ -173,29 +173,38 @@ def parse_file(document_file, validate = True, is_microdescriptor = False): :param file document_file: file with network status document content :param bool validate: checks the validity of the document's contents if True, skips these checks otherwise :param bool is_microdescriptor: True if this is for a microdescriptor consensus, False otherwise + :param int document_version: network status document version - :returns: :class:`stem.descriptor.networkstatus.NetworkStatusDocumentV3` object + :returns: :class:`stem.descriptor.networkstatus.NetworkStatusDocument` object :raises: - * ValueError if the contents is malformed and validate is True + * ValueError if the document_version is unrecognized or the contents is malformed and validate is True * IOError if the file can't be read """ # getting the document without the routers section - header = stem.descriptor._read_until_keywords((ROUTERS_START, FOOTER_START), document_file) + header = stem.descriptor._read_until_keywords((ROUTERS_START, FOOTER_START, V2_FOOTER_START), document_file) routers_start = document_file.tell() - stem.descriptor._read_until_keywords(FOOTER_START, document_file, skip = True) + stem.descriptor._read_until_keywords((FOOTER_START, V2_FOOTER_START), document_file, skip = True) routers_end = document_file.tell() footer = document_file.readlines() document_content = "".join(header + footer) - if not is_microdescriptor: + if document_version == 2: + document_type = NetworkStatusDocumentV2 router_type = stem.descriptor.router_status_entry.RouterStatusEntryV3 + elif document_version == 3: + document_type = NetworkStatusDocumentV3 + + if not is_microdescriptor: + router_type = stem.descriptor.router_status_entry.RouterStatusEntryV3 + else: + router_type = stem.descriptor.router_status_entry.RouterStatusEntryMicroV3 else: - router_type = stem.descriptor.router_status_entry.RouterStatusEntryMicroV3 + raise ValueError("Document version %i isn't recognized (only able to parse v2 or v3)" % document_version) desc_iterator = _get_entries( document_file, @@ -204,7 +213,7 @@ def parse_file(document_file, validate = True, is_microdescriptor = False): entry_keyword = ROUTERS_START, start_position = routers_start, end_position = routers_end, - extra_args = (NetworkStatusDocumentV3(document_content, validate),), + extra_args = (document_type(document_content, validate),), ) for desc in desc_iterator: diff --git a/test/integ/descriptor/data/cached-consensus-v2 b/test/integ/descriptor/data/cached-consensus-v2 index 4f8cbce..ad64d40 100644 --- a/test/integ/descriptor/data/cached-consensus-v2 +++ b/test/integ/descriptor/data/cached-consensus-v2 @@ -1,3 +1,4 @@ +@type network-status-2 1.0 network-status-version 2 dir-source 18.244.0.114 18.244.0.114 80 fingerprint 719BE45DE224B607C53707D0E2143E2D423E74CF diff --git a/test/integ/descriptor/networkstatus.py b/test/integ/descriptor/networkstatus.py index e0ecd00..96ce12f 100644 --- a/test/integ/descriptor/networkstatus.py +++ b/test/integ/descriptor/networkstatus.py @@ -213,6 +213,7 @@ TpQQk3nNQF8z6UIvdlvP+DnJV4izWVkQEZgUZgIVM0E= consensus_path = test.integ.descriptor.get_resource("cached-consensus-v2") with open(consensus_path) as descriptor_file: + descriptor_file.readline() # strip header document = stem.descriptor.networkstatus.NetworkStatusDocumentV2(descriptor_file.read()) self.assertEquals(2, document.version)