Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Brotli: Don't accept brotli if library can't be loaded. #444

Merged
merged 3 commits into from
Feb 20, 2019
Merged

Brotli: Don't accept brotli if library can't be loaded. #444

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0ea5bea
brotli: if the brotli module can not be loaded, print warning
ikreymer Feb 19, 2019
952d6d1
fix comment
ikreymer Feb 19, 2019
f2df7ed
style: add Exception
ikreymer Feb 20, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions pywb/rewrite/rewriteinputreq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,13 @@
from six.moves.urllib.parse import urlsplit
import re

try: # pragma: no cover
import brotli
has_brotli = True
except: # pragma: no cover
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it would be good practice to start using named exceptions when possible.

Here it would be except ImportError in order to be clearer about why we expect an exception and to be pythonic :)

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In general, yes, but here want to catch any Exception as that means brotli is not properly installed. Added Exception

has_brotli = False
print('Warning: brotli module could not be loaded, will not be able to replay brotli-encoded content')


#=============================================================================
class RewriteInputRequest(DirectWSGIInputRequest):
Expand Down Expand Up @@ -79,6 +86,12 @@ def get_req_headers(self):
if self.splits:
value = self.splits.scheme

elif not has_brotli and name == 'HTTP_ACCEPT_ENCODING' and 'br' in value:
# if brotli not available, remove 'br' from accept-encoding to avoid
# capture brotli encoded content
name = 'Accept-Encoding'
value = ','.join([enc for enc in value.split(',') if enc.strip() != 'br'])

elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')

Expand Down
25 changes: 22 additions & 3 deletions tests/test_record_replay.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,15 @@
from pywb.manager.autoindex import AutoIndexer
from pywb.warcserver.test.testutils import to_path, HttpBinLiveTests, TEST_WARC_PATH, TEST_CDX_PATH

from warcio import ArchiveIterator

import os
import time
import json

from mock import patch
import pytest


# ============================================================================
class TestRecordReplay(HttpBinLiveTests, CollsDirMixin, BaseConfigTest):
Expand Down Expand Up @@ -153,6 +158,20 @@ def test_init_and_rec(self):
assert names[0].startswith('pywb-rec-test-')
assert names[0].endswith('.warcgz')

TestRecordCustomConfig.warc_name = os.path.join(dir_name, names[0])

@patch('pywb.rewrite.rewriteinputreq.has_brotli', False)
def test_no_brotli(self):
res = self.testapp.get('/test-new/record/mp_/http://httpbin.org/get?C=D',
headers={'Accept-Encoding': 'gzip, deflate, br'})
assert '"C": "D"' in res.text

with open(self.warc_name, 'rb') as fh:
for record in ArchiveIterator(fh):
last_record = record

assert record.http_headers['Accept-Encoding'] == 'gzip, deflate'


# ============================================================================
class TestRecordFilter(HttpBinLiveTests, CollsDirMixin, BaseConfigTest):
Expand All @@ -174,17 +193,17 @@ def setup_class(cls):
}
super(TestRecordFilter, cls).setup_class('config_test_record.yaml', custom_config=rec_custom)
manager(['init', 'test-new'])

def test_skip_existing(self):
dir_name = os.path.join(self.root_dir, '_test_colls', 'test-new', 'archive')
assert os.path.isdir(dir_name)
res = self.testapp.get('/fallback/cdx?url=http://example.com/?example=1')
assert res.text != ''

res = self.testapp.get('/test-new/record/mp_/http://example.com/?example=1')
assert 'Example Domain' in res.text
assert os.listdir(dir_name) == []

def test_record_new(self):
dir_name = os.path.join(self.root_dir, '_test_colls', 'test-new', 'archive')
assert os.path.isdir(dir_name)
Expand Down