Skip to content

fix(#163): manage indexing timeouts #164

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

Merged
merged 1 commit into from
Jun 19, 2025
Merged

fix(#163): manage indexing timeouts #164

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
7 changes: 7 additions & 0 deletions packages/stac-index/src/stac_index/indexer/stac_catalog_reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,6 +200,13 @@ async def fetch_and_ingest(
(item, dict_item) = self._stac_parser.parse_stac_item(dict_item)
except StacParserException as e:
item_errors.extend(e.indexing_errors)
except Exception as e:
item_errors.extend(
new_error(
type=IndexingErrorType.item_fetching,
description=str(e),
)
)
else:
if not _has_matching_self_link(item, uri):
_logger.debug(
Expand Down
56 changes: 30 additions & 26 deletions packages/stac-index/src/stac_index/io/readers/https/https_source_reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,34 +85,38 @@ async def get_item_uris_from_items_uri(
errors: List[str] = []
next_items_uri: str | None = uri
while next_items_uri is not None:
items_response: Dict[str, Any] = await self.load_json_from_uri(
next_items_uri
)
if not isinstance(items_response, dict):
errors.append(f"unexpected response from '{uri}'")
continue
for item in items_response.get("features", []):
for link in cast(Dict[str, Any], item).get("links", []):
link = cast(Dict[str, str], link)
if link.get("rel", "") == "self":
if "href" in link:
item_uris.append(link["href"])
break
if item_limit is not None and len(item_uris) == item_limit:
break
next_links = [
link
for link in items_response.get("links", [])
if link.get("rel", "") == "next"
and link.get("method", "GET").upper() == "GET"
]
if len(next_links) == 1:
if "href" in next_links[0]:
next_items_uri = next_links[0]["href"]
try:
items_response: Dict[str, Any] = await self.load_json_from_uri(
next_items_uri
)
if not isinstance(items_response, dict):
errors.append(f"unexpected response from '{uri}'")
continue
for item in items_response.get("features", []):
for link in cast(Dict[str, Any], item).get("links", []):
link = cast(Dict[str, str], link)
if link.get("rel", "") == "self":
if "href" in link:
item_uris.append(link["href"])
break
if item_limit is not None and len(item_uris) == item_limit:
break
next_links = [
link
for link in items_response.get("links", [])
if link.get("rel", "") == "next"
and link.get("method", "GET").upper() == "GET"
]
if len(next_links) == 1:
if "href" in next_links[0]:
next_items_uri = next_links[0]["href"]
else:
next_items_uri = None
else:
next_items_uri = None
else:
next_items_uri = None
except Exception as e:
errors.append(str(e))
break
return (item_uris, errors)

async def get_last_modified_epoch_for_uri(self: Self, uri: str) -> Optional[int]:
Expand Down