Remove flanker and replace PyML with scikit-learn

I never was actually able to successfully install PyML but the source-forge
distribution and lack of python3 support convinced me that scikit-learn would
be a fine substitute. Flanker was also difficult for me to install and seemed
only to be used in the tests, so I removed it as well to get into a position
where I could run the tests. As of this commit, only one is not passing
(test_standard_replies with android.eml) though I'm not familiar with the `email`
library yet.
This commit is contained in:
Alex Riina
2015-03-08 00:06:01 -05:00
committed by Alex Riina
parent b36287e573
commit f16760c466
12 changed files with 44 additions and 133 deletions

View File

@@ -5,8 +5,7 @@ from . fixtures import *
import os
from flanker import mime
import email.iterators
from talon import quotations
@@ -614,22 +613,21 @@ def test_preprocess_postprocess_2_links():
def test_standard_replies():
for filename in os.listdir(STANDARD_REPLIES):
filename = os.path.join(STANDARD_REPLIES, filename)
if os.path.isdir(filename):
if not filename.endswith('.eml') or os.path.isdir(filename):
continue
with open(filename) as f:
msg = f.read()
m = mime.from_string(msg)
for part in m.walk():
if part.content_type == 'text/plain':
text = part.body
stripped_text = quotations.extract_from_plain(text)
reply_text_fn = filename[:-4] + '_reply_text'
if os.path.isfile(reply_text_fn):
with open(reply_text_fn) as f:
reply_text = f.read()
else:
reply_text = 'Hello'
eq_(reply_text, stripped_text,
"'%(reply)s' != %(stripped)s for %(fn)s" %
{'reply': reply_text, 'stripped': stripped_text,
'fn': filename})
message = email.message_from_file(f)
body = email.iterators.typed_subpart_iterator(message, subtype='plain').next()
text = ''.join(email.iterators.body_line_iterator(body))
stripped_text = quotations.extract_from_plain(text)
reply_text_fn = filename[:-4] + '_reply_text'
if os.path.isfile(reply_text_fn):
with open(reply_text_fn) as f:
reply_text = f.read()
else:
reply_text = 'Hello'
yield eq_, reply_text, stripped_text, \
"'%(reply)s' != %(stripped)s for %(fn)s" % \
{'reply': reply_text, 'stripped': stripped_text,
'fn': filename}