diff analyze_document/app.py @ 6:d15ccf5f1373

fix bug clean_text
author Dennis C. M. <dennis@denniscm.com>
date Mon, 05 Jun 2023 17:12:18 +0100
parents 9005b7590008
children bf19235a9636
line wrap: on
line diff
--- a/analyze_document/app.py	Mon Jun 05 12:48:47 2023 +0100
+++ b/analyze_document/app.py	Mon Jun 05 17:12:18 2023 +0100
@@ -15,7 +15,7 @@
 
     company_ticker = re.search('unprocessed/(.*)_', object_key).group(1)
     doc_type = re.search(f'unprocessed/{company_ticker}_(.*).pdf', object_key).group(1)
-    file_id = uuid.uuid4()
+    file_id = str(uuid.uuid4())
 
     data_dict = textract_client.analyze_document(
         Document={'S3Object': {'Bucket': bucket_name, 'Name': object_key}},