datamule 1.6.4__py3-none-any.whl → 1.6.5__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- datamule/sec/submissions/monitor.py +9 -1
- {datamule-1.6.4.dist-info → datamule-1.6.5.dist-info}/METADATA +1 -1
- {datamule-1.6.4.dist-info → datamule-1.6.5.dist-info}/RECORD +5 -5
- {datamule-1.6.4.dist-info → datamule-1.6.5.dist-info}/WHEEL +0 -0
- {datamule-1.6.4.dist-info → datamule-1.6.5.dist-info}/top_level.txt +0 -0
@@ -65,6 +65,7 @@ def clean_efts_hits(hits):
|
|
65
65
|
class Monitor():
|
66
66
|
def __init__(self):
|
67
67
|
self.accessions = deque(maxlen=50000)
|
68
|
+
self.accessions_set = set()
|
68
69
|
self.ratelimiters = {'sec.gov': PreciseRateLimiter(rate=5)}
|
69
70
|
self.efts_query = EFTSQuery(quiet=True)
|
70
71
|
self.efts_query.limiter = self.ratelimiters['sec.gov']
|
@@ -250,7 +251,14 @@ class Monitor():
|
|
250
251
|
new_items = []
|
251
252
|
for item in items:
|
252
253
|
accession = item['accession']
|
253
|
-
if accession not in self.
|
254
|
+
if accession not in self.accessions_set: # O(1) lookup instead of O(n)
|
255
|
+
# Check if deque is at capacity and will evict an item
|
256
|
+
if len(self.accessions) == self.accessions.maxlen:
|
257
|
+
evicted_accession = self.accessions[0] # Get leftmost item that will be evicted
|
258
|
+
self.accessions_set.discard(evicted_accession) # Remove from set
|
259
|
+
|
260
|
+
# Add to both structures
|
254
261
|
self.accessions.append(accession)
|
262
|
+
self.accessions_set.add(accession)
|
255
263
|
new_items.append(item)
|
256
264
|
return new_items
|
@@ -52,7 +52,7 @@ datamule/sec/infrastructure/submissions_metadata.py,sha256=f1KarzFSryKm0EV8DCDNs
|
|
52
52
|
datamule/sec/submissions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
53
53
|
datamule/sec/submissions/downloader.py,sha256=zGS0oJJI8tVF_GnVpZm20MymdYxnjrEjQioSVggw7Ck,1486
|
54
54
|
datamule/sec/submissions/eftsquery.py,sha256=mSZon8rlW8dxma7M49ZW5V02Fn-ENOdt9TNO6elBrhE,27983
|
55
|
-
datamule/sec/submissions/monitor.py,sha256=
|
55
|
+
datamule/sec/submissions/monitor.py,sha256=6mE0NZFdPId69t4V53GwBb9sqtRN7HE54sU3WpU0bnY,11900
|
56
56
|
datamule/sec/submissions/streamer.py,sha256=Qydj40CmWB_wsPv2dibefRohmCokegG2pR7iZ9C3xLQ,11584
|
57
57
|
datamule/sec/submissions/textsearch.py,sha256=MKDXEz_VI_0ljl73_aw2lx4MVzJW5uDt8KxjvJBwPwM,5794
|
58
58
|
datamule/sec/xbrl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
@@ -66,7 +66,7 @@ datamule/seclibrary/downloader.py,sha256=3jEy67oiEg8BF20KcKCx2KC0UjHzhiepdu29TOa
|
|
66
66
|
datamule/seclibrary/query.py,sha256=qGuursTERRbOGfoDcYcpo4oWkW3PCBW6x1Qf1Puiak4,7352
|
67
67
|
datamule/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
68
68
|
datamule/utils/construct_submissions_data.py,sha256=aX7ZaAp3zXHLcv4TFk_rGwjb8r7yNDQDFVg4nPf60kM,5934
|
69
|
-
datamule-1.6.
|
70
|
-
datamule-1.6.
|
71
|
-
datamule-1.6.
|
72
|
-
datamule-1.6.
|
69
|
+
datamule-1.6.5.dist-info/METADATA,sha256=2Svo4CVhWzVDa9HFLOOwzIzgF84ItLQT-2BI6WR894s,524
|
70
|
+
datamule-1.6.5.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
|
71
|
+
datamule-1.6.5.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
|
72
|
+
datamule-1.6.5.dist-info/RECORD,,
|
File without changes
|
File without changes
|