Page MenuHomeSoftware Heritage
Files F7066693

D2324.id8688.diff
No OneTemporary
Actions

D2324.id8688.diff
View Options

diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py
--- a/swh/storage/in_memory.py
+++ b/swh/storage/in_memory.py
@@ -1157,6 +1157,37 @@
self._origins[self._origins_by_id[idx]])
yield {'id': idx+1, **origin}
+ def origin_list(self, page_token=None, limit=100):
+ """Returns the list of origins
+
+ Args:
+ page_token (Optional[str]): opaque token used for pagination.
+ limit (int): the maximum number of results to return
+
+ Returns:
+ dict: dict with the following keys:
+ - **next_page_token** (str, optional): opaque token to be used as
+ `page_token` for retrieveing the next page. if absent, there is
+ no more pages to gather.
+ - **origins** (List[dict]): list of origins, as returned by
+ `origin_get`.
+ """
+ origin_urls = sorted(self._origins)
+ if page_token:
+ from_ = bisect.bisect_left(origin_urls, page_token)
+ else:
+ from_ = 0
+
+ result = {
+ 'origins': [{'url': origin_url}
+ for origin_url in origin_urls[from_:from_+limit]]
+ }
+
+ if from_+limit < len(origin_urls):
+ result['next_page_token'] = origin_urls[from_+limit]
+
+ return result
+
def origin_search(self, url_pattern, offset=0, limit=50,
regexp=False, with_visit=False, db=None, cur=None):
"""Search for origins whose urls contain a provided string pattern
diff --git a/swh/storage/storage.py b/swh/storage/storage.py
--- a/swh/storage/storage.py
+++ b/swh/storage/storage.py
@@ -1690,6 +1690,44 @@
for origin in db.origin_get_range(origin_from, origin_count, cur):
yield dict(zip(db.origin_get_range_cols, origin))
+ @remote_api_endpoint('origin/list')
+ @timed
+ @db_transaction()
+ def origin_list(self, page_token=None, limit=100, *, db, cur):
+ """Returns the list of origins
+
+ Args:
+ page_token (Optional[str]): opaque token used for pagination.
+ limit (int): the maximum number of results to return
+
+ Returns:
+ dict: dict with the following keys:
+ - **next_page_token** (str, optional): opaque token to be used as
+ `page_token` for retrieveing the next page. if absent, there is
+ no more pages to gather.
+ - **origins** (List[dict]): list of origins, as returned by
+ `origin_get`.
+ """
+ page_token = page_token or '0'
+ if not isinstance(page_token, str):
+ raise TypeError('page_token must be a string.')
+ origin_from = int(page_token)
+ result = {
+ 'origins': [
+ dict(zip(db.origin_get_range_cols, origin))
+ for origin in db.origin_get_range(origin_from, limit, cur)
+ ],
+ }
+
+ assert len(result['origins']) <= limit
+ if len(result['origins']) == limit:
+ result['next_page_token'] = str(result['origins'][limit-1]['id']+1)
+
+ for origin in result['origins']:
+ del origin['id']
+
+ return result
+
@remote_api_endpoint('origin/search')
@timed
@db_transaction_generator()
diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py
--- a/swh/storage/tests/test_storage.py
+++ b/swh/storage/tests/test_storage.py
@@ -3242,6 +3242,32 @@
assert actual_origins == expected_origins
+ @pytest.mark.parametrize('limit', [1, 7, 10, 100, 1000])
+ def test_origin_list(self, swh_storage, swh_origins, limit):
+ returned_origins = []
+
+ page_token = None
+ i = 0
+ while True:
+ result = swh_storage.origin_list(
+ page_token=page_token, limit=limit)
+ assert len(result['origins']) <= limit
+
+ returned_origins.extend(
+ origin['url'] for origin in result['origins'])
+
+ i += 1
+ page_token = result.get('next_page_token')
+
+ if page_token is None:
+ assert i*limit >= len(swh_origins)
+ break
+ else:
+ assert len(result['origins']) == limit
+
+ expected_origins = [origin['url'] for origin in swh_origins]
+ assert sorted(returned_origins) == sorted(expected_origins)
+
ORIGINS = [
'https://github.com/user1/repo1',
'https://github.com/user2/repo1',

File Metadata

Mime Type
text/plain
Expires
Nov 5 2024, 6:30 PM (11 w, 17 h ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3230375

Event Timeline

About · Developer information · Legal