Skip to content

Windows fixes #27

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

Open
wants to merge 6 commits into
base: master
Choose a base branch
from
Open

Windows fixes #27

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
581c968
get_hashed_filepath: use os.sep instead of : as method separator
laerreal Jan 6, 2019
234ecc6
get_cache: use `os.path.dirname` to get dir of cache_file
laerreal Jan 6, 2019
50f48e9
split_path: correct dirname path separators for Windows too
laerreal Jan 6, 2019
b7bffe7
split_path: use `os.path.join` instead of `os.sep.join`
laerreal Jan 9, 2019
f10996a
get_hashed_filepath: use MD5 hash for file path
laerreal Jan 9, 2019
f7fd182
CacheHandler: handle forbidden characters in directory name
laerreal Jan 9, 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
18 changes: 12 additions & 6 deletions cappy/cappy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry

from hashlib import md5
from re import compile

def log(*args):
message = "".join(args)
Expand Down Expand Up @@ -56,18 +58,17 @@ def split_path(path):
last_fragment = split_path[-1]
if '.' not in last_fragment:
filename = ''
dirname = path
dirname = os.path.join(*split_path)
else:
filename = last_fragment
dirname = '/'.join(split_path[:-1])
dirname = os.path.join(*split_path[:-1])
else:
filename = ''
dirname = path
return (dirname, filename)


def get_hashed_filepath(stub, method, parsed_url, params):
hash_template = '{method}:{stub}{param_str}'
param_str = ''
if not stub:
stub = 'index.html'
Expand All @@ -77,9 +78,11 @@ def get_hashed_filepath(stub, method, parsed_url, params):
param_str = parsed_url.query
if param_str:
param_str = '?'+param_str
return hash_template.format(method=method, stub=stub, param_str=param_str)
return md5(method + stub + param_str).hexdigest()


FORBIDDEN = compile('[<>:"|?*]')

class CacheHandler(SocketServer.ThreadingMixIn, BaseHTTPServer.BaseHTTPRequestHandler):
# Based on http://sharebear.co.uk/blog/2009/09/17/very-simple-python-caching-proxy/
def get_cache(self, parsed_url, url, params={}):
Expand All @@ -89,7 +92,10 @@ def get_cache(self, parsed_url, url, params={}):
data = None
filepath = get_hashed_filepath(stub=filepath_stub, method=method, parsed_url=parsed_url, params=params)

cache_file = os.path.join(get_cache_dir(CACHE_DIR), dirpath, filepath)
# replace characters forbidden by file system with `_`
clean_dirpath = FORBIDDEN.sub('_', dirpath)

cache_file = os.path.join(get_cache_dir(CACHE_DIR), clean_dirpath, filepath)
hit = False
if os.path.exists(cache_file):
if CACHE_TIMEOUT == 0:
Expand All @@ -113,7 +119,7 @@ def get_cache(self, parsed_url, url, params={}):
log("Cache miss")
data = self.make_request(url=url, params=params, method=method)
# make dirs before you write to file
dirname, _filename = split_path(cache_file)
dirname = os.path.dirname(cache_file)
make_dirs(dirname)
file_obj = fopen(cache_file, 'wb+')
file_obj.writelines(data)
Expand Down