Skip to content
Merged
Changes from all commits
Commits
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
48 changes: 32 additions & 16 deletions mp_api/client/contribs/client.py
Original file line number Diff line number Diff line change
Expand Up @@ -994,11 +994,14 @@ def get_contribution(
else MPCDict(contrib)
)

def get_table(self, tid_or_md5: str) -> Table:
def get_table(self, tid_or_md5: str, timeout: int = -1) -> Table:
"""Retrieve full Pandas DataFrame for a table.

Data pages beyond the first are fetched concurrently.

Args:
tid_or_md5 (str): ObjectId or MD5 hash digest for table
timeout (int): cancel remaining requests if timeout exceeded (in seconds)
"""
str_len = len(tid_or_md5)
if str_len not in {24, 32}:
Expand All @@ -1016,23 +1019,36 @@ def get_table(self, tid_or_md5: str) -> Table:

op = self.swagger_spec.resources["tables"].queryTables
per_page = op.params["data_per_page"].param_spec["maximum"]
table: dict[str, list[str]] = {"data": []}
page, pages = 1, None

while pages is None or page <= pages:
resp = self.tables.getTableById(
pk=tid, _fields=["_all"], data_page=page, data_per_page=per_page
).result()
table["data"].extend(resp["data"])
if pages is None:
pages = resp["total_data_pages"]
table["index"] = resp["index"]
table["columns"] = resp["columns"]
table_attrs: dict[str, str] = (resp.get("attrs") or {}) | {
field: resp.get(field) for field in {"id", "name", "md5"}
}
# fetch the first page to learn the total number of data pages + metadata
resp = self.tables.getTableById(
pk=tid, _fields=["_all"], data_page=1, data_per_page=per_page
).result()
pages = resp["total_data_pages"]
table: dict[str, Any] = {
"data": resp["data"],
"index": resp["index"],
"columns": resp["columns"],
}
table_attrs: dict[str, str] = (resp.get("attrs") or {}) | {
field: resp.get(field) for field in {"id", "name", "md5"}
}

page += 1
# fetch any remaining pages concurrently, then reassemble in page order
if pages > 1:
futures = [
self._get_future(
page,
{"_fields": "_all", "data_page": page, "data_per_page": per_page},
rel_url=f"tables/{tid}",
)
for page in range(2, pages + 1)
]
responses = _run_futures(
futures, timeout=timeout, disable=self.mute_progress_bars
)
for page in sorted(responses):
table["data"].extend(responses[page]["result"]["data"])

return Table.from_dict(table | {"attrs": table_attrs})

Expand Down
Loading