def not_replay_duplicate(
replay: sc2reader.resources.Replay,
collection_: pymongo.collection.Collection = replays_info) -> bool:
'''
Verify that the replay does not exist in a collection.
*Args:*
- replay (sc2reader.resources.Replay):
The replay being cheked
- collection_ (pymongo.collection.Collection):
The collection where the existance check is being performed.
*Returns:*
- bool:
True if the replay is not in the collection, False if it is.
'''
if not collection_.count_documents({'replay_name': replay.filename},
limit=1):
print(
f'New replay found: {Path(replay.filename).name} \n adding to replay_info collection.'
)
return True
else:
print(
f'{replay.filename} already exists in the replay_info collection.')
return False
def count_items(collection: pymongo.collection.Collection,
*,
query: dict = None) -> int:
"""
Returns the number of items in a collection matching the query
:param collection: Collection to query
:param query: Only match objects that contain the query (or all if None)
:return:
"""
query = {} if query is None else query
return collection.count_documents(query)
def do_skip(coll_tables: pymongo.collection.Collection, raw_pdf_name: str,
page_num: str, coords: str) -> bool:
"""
Check if document is already scanned or not. If yes, skip it
"""
return coll_tables.count_documents(
{
'pdf_name': raw_pdf_name,
'page_num': page_num,
'coords': coords
},
limit=1) != 0
def count(collection: pymongo.collection.Collection, query: Dict[Text,
Any]) -> int:
return collection.count_documents(query)
def exploreChunks(self,
ilon_chunk: int,
ilat_chunk: int,
delta: int,
mask_query: Union[dict, None],
retrn: str,
col_grid: pymongo.collection.Collection)\
-> Union[dict, pymongo.cursor.Cursor]:
'''
Explore an xarray chunk and returns either the number
of grid cells or the grid ids.
Parameters
----------
ilon_chunk : int
Longitude of the upper-left bounding box corner.
ilon_chunk : int
Latitude of the upper-left bounding box corner.
delta : int
Width and height of the bounding box (in degrees).
mask_query : Union[dict, None]
If all grid cells needs to be considered, set mask_query=None.
If only certain grid cells needs to be considered, filter
with this query. Example: for only land grid cells
(i.e., excluding oceans) mask_query = {'lsm': {'gt': 0.6}}.
Land-sea mask (lsm) has fractional values in the range
0 (sea) to 1 (land).
retrn : str
What to return:
* either 'ndocs' for the number or grid cells inside the chunk
* or 'docs' for the ids of the grid cells inside the chunk.
col_grid : pymongo.collection.Collection
Mongo connection to the grid collection.
Returns
-------
Union[dict, pymongo.cursor.Cursor]
'''
ilon_orig = int(ilon_chunk)
ilon_chunk = int(self._shiftlon(x=ilon_chunk))
ilon_plus = int(self._shiftlon(x=ilon_chunk + delta))
ilat_chunk = int(ilat_chunk)
geoqry = {
'loc': {
'$geoWithin': {
'$geometry': {
'type':
'Polygon',
'coordinates': [[[ilon_chunk, ilat_chunk],
[ilon_plus, ilat_chunk],
[ilon_plus, ilat_chunk + delta],
[ilon_chunk, ilat_chunk + delta],
[ilon_chunk, ilat_chunk]]]
}
}
}
}
if mask_query is not None:
geoqry.update(mask_query)
if retrn == 'ndocs':
# How many grid cells in this chunk ?
res = {
'ilon_chunk': ilon_orig,
'ilat_chunk': ilat_chunk,
'n': col_grid.count_documents(filter=geoqry)
}
elif retrn == 'docs':
res = col_grid.find(geoqry, {'id_grid': 1, 'loc': 1, '_id': 0})
return (res)
