[tor-commits] [stem/master] Skip universal newline translation in descriptor reader

[atagar at torproject.org]

commit 0288267be5a325aadd078a487751cf4ce83a2f73
Author: Damian Johnson <atagar at torproject.org>
Date:   Wed Jan 30 08:24:59 2013 -0800

    Skip universal newline translation in descriptor reader
    
    Python 3 introduces universal newline translation, converting '\n', '\r', and
    '\r\n' into the local system's newline style. This is a really neat feature and
    will solve many-a-headaches... but not for us. We conform to the tor spec which
    specifies when CRLF appears verses other newline types.
    
    Universal newline translation broke our ability to read the
    'cr_in_contact_line' example which has multiple '\r' within a contact line
    (https://trac.torproject.org/5637). Fixing the reader to disable newline
    translation and adding a warning to our parse_file() pydocs.
---
 stem/descriptor/__init__.py |   10 ++++++++++
 stem/descriptor/reader.py   |    8 +++++++-
 2 files changed, 17 insertions(+), 1 deletions(-)

diff --git a/stem/descriptor/__init__.py b/stem/descriptor/__init__.py
index fe6c03c..69d7db7 100644
--- a/stem/descriptor/__init__.py
+++ b/stem/descriptor/__init__.py
@@ -82,6 +82,16 @@ def parse_file(descriptor_file, descriptor_type = None, path = None, validate =
   tordnsel 1.0                          **unsupported**
   ===================================== =====
 
+  If you're using python 3 then beware of the open() function's universal
+  newline translation. By default open() converts all common line endings (NL,
+  CR, and CRNL) into NL. In some edge cases this can cause us to misparse
+  content. To disable newline translation set the **newline** to an empty
+  string. For example...
+
+  ::
+
+    my_descriptor_file = open(descrptor_path, newline='')
+
   :param file descriptor_file: opened file with the descriptor contents
   :param str descriptor_type: `descriptor type <https://metrics.torproject.org/formats.html#descriptortypes>`_, this is guessed if not provided
   :param str path: absolute path to the file's location on disk
diff --git a/stem/descriptor/reader.py b/stem/descriptor/reader.py
index 877d230..ef35fc0 100644
--- a/stem/descriptor/reader.py
+++ b/stem/descriptor/reader.py
@@ -512,7 +512,13 @@ class DescriptorReader(object):
   def _handle_descriptor_file(self, target, mime_type):
     try:
       self._notify_read_listeners(target)
-      with open(target) as target_file:
+
+      if stem.prereq.is_python_3():
+        target_file = open(target, newline = '')
+      else:
+        target_file = open(target)
+
+      with target_file as target_file:
         for desc in stem.descriptor.parse_file(target_file, validate = self._validate, path = target):
           if self._is_stopped.isSet():
             return