Skip to content

Try to avoid "...//state.txt" URLs for replication. #320

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
amandasaurus wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Try to avoid "...//state.txt" URLs for replication. #320

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 15 additions & 3 deletions src/osmium/replication/server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,15 @@ def __init__(self, url: str, diff_type: str = 'osc.gz') -> None:
than osc.gz files, set the `diff_type` to the given file suffix.
"""

# Canonicalize the baseurl to have exactle one trailing slash.
# Try to avoid calling `example.com/area-updates//state.txt`
# Don't turn `http://example.com/` into `http://example.com`
# Remove all trailing /'s then add one back
while url.endswith("/"):
url = url.rstrip("/")
# put a final / at the end
url = url + "/"

self.baseurl = url
self.diff_type = diff_type
self.extra_request_params: Dict[str, Any] = dict(timeout=60, stream=True)
Expand Down Expand Up @@ -483,16 +492,19 @@ def get_state_url(self, seq: Optional[int]) -> str:
i.e. the state file in the root directory of the replication
service.
"""

# baseurl is guaranteed to end with /, as per __init__
if seq is None:
return self.baseurl + '/state.txt'
return self.baseurl + 'state.txt'

return '%s/%03i/%03i/%03i.state.txt' % \
return '%s%03i/%03i/%03i.state.txt' % \
(self.baseurl, seq / 1000000, (seq % 1000000) / 1000, seq % 1000)

def get_diff_url(self, seq: int) -> str:
""" Returns the URL to the diff file for the given sequence id.
"""
return '%s/%03i/%03i/%03i.%s' % \
# baseurl is guaranteed to end with /, as per __init__
return '%s%03i/%03i/%03i.%s' % \
(self.baseurl,
seq / 1000000, (seq % 1000000) / 1000, seq % 1000,
self.diff_type)
47 changes: 31 additions & 16 deletions test/test_replication.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,28 +22,43 @@
pytestmark = [pytest.mark.thread_unsafe, pytest.mark.iterations(1)]


@pytest.mark.parametrize("inp,outp", [
(None, 'https://text.org/state.txt'),
(1, 'https://text.org/000/000/001.state.txt'),
(999, 'https://text.org/000/000/999.state.txt'),
(1000, 'https://text.org/000/001/000.state.txt'),
(573923, 'https://text.org/000/573/923.state.txt'),
(3290012, 'https://text.org/003/290/012.state.txt'),
@pytest.mark.parametrize("baseurl,inp,outp", [
("https://text.org", None, 'https://text.org/state.txt'),
("https://text.org", 1, 'https://text.org/000/000/001.state.txt'),
("https://text.org", 999, 'https://text.org/000/000/999.state.txt'),
("https://text.org", 1000, 'https://text.org/000/001/000.state.txt'),
("https://text.org", 573923, 'https://text.org/000/573/923.state.txt'),
("https://text.org", 3290012, 'https://text.org/003/290/012.state.txt'),

("https://text.org/", None, 'https://text.org/state.txt'),
("https://text.org/", 1, 'https://text.org/000/000/001.state.txt'),
("https://text.org//", None, 'https://text.org/state.txt'),
("https://text.org//", 1, 'https://text.org/000/000/001.state.txt'),

("https://text.org/area-updates", None, 'https://text.org/area-updates/state.txt'),
("https://text.org/area-updates", 3290012, 'https://text.org/area-updates/003/290/012.state.txt'),
("https://text.org/area-updates/", None, 'https://text.org/area-updates/state.txt'),
("https://text.org/area-updates/", 3290012, 'https://text.org/area-updates/003/290/012.state.txt'),
("https://text.org/area-updates//", None, 'https://text.org/area-updates/state.txt'),
("https://text.org/area-updates//", 3290012, 'https://text.org/area-updates/003/290/012.state.txt'),
("https://text.org/area-updates///", 3290012, 'https://text.org/area-updates/003/290/012.state.txt'),
])
def test_get_state_url(inp, outp):
svr = rserv.ReplicationServer("https://text.org")
def test_get_state_url(baseurl, inp, outp):
svr = rserv.ReplicationServer(baseurl)

assert outp == svr.get_state_url(inp)


@pytest.mark.parametrize("inp,outp", [
(1, 'https://who.is/me//000/000/001.osc.gz'),
(500, 'https://who.is/me//000/000/500.osc.gz'),
(83750, 'https://who.is/me//000/083/750.osc.gz'),
(999999999, 'https://who.is/me//999/999/999.osc.gz'),
@pytest.mark.parametrize("baseurl,inp,outp", [
("https://who.is/me/", 1, 'https://who.is/me//sdfsdf000/000/001.osc.gz'),
("https://who.is/me/", 500, 'https://who.is/me/000/000/500.osc.gz'),
("https://who.is/me/", 83750, 'https://who.is/me/000/083/750.osc.gz'),
("https://who.is/me/", 999999999, 'https://who.is/me/999/999/999.osc.gz'),

("https://who.is/me", 999999999, 'https://who.is/me/999/999/999.osc.gz'),
])
def test_get_diff_url(inp, outp):
svr = rserv.ReplicationServer("https://who.is/me/")
def test_get_diff_url(baseurl, inp, outp):
svr = rserv.ReplicationServer(baseurl)

assert outp, svr.get_diff_url(inp)

Expand Down
Loading