rename

lambdas/excel_ingestion/src/index.py

@@ -9,12 +9,12 @@
 
 def lambda_handler(event, context):
     """
-    Downloads the given docx file from S3, extracts the text content and saves it as a txt file in the same bucket, adjacent to the original docx file.
+    Downloads the given xlsx file from S3, extracts the text content and saves it as a csv file in the same bucket, adjacent to the original xlsx file.
     """
     try:
         print(event)
 
-        bucket, key = event['docx_s3_uri'].replace("s3://", "").split("/", 1)
+        bucket, key = event['xlsx_s3_uri'].replace("s3://", "").split("/", 1)
         print(f"File located at bucket: {bucket} and key: {key}")
 
         if os.path.splitext(key)[1][1:] != "xlsx":
@@ -29,15 +29,15 @@ def lambda_handler(event, context):
         df.to_csv(csv_file_path, index=False, sep='\t')
         base_path = Path(key).parent
         base_name = Path(key).stem
-        new_key = f"{base_path}/{base_name}_extracted_docx_content.csv"
+        new_key = f"{base_path}/{base_name}_extracted_xlsx_content.csv"
 
         with open(csv_file_path, "rb") as f:
             s3.upload_fileobj(f, bucket, new_key)
 
         return {
             'statusCode': 200,
             'body': 'xlsx text content extracted and saved',
-            'attachment_uri': f"s3://{bucket}/{new_key}"
+            'extracted_csv_uri': f"s3://{bucket}/{new_key}"
         }
 
     except Exception as e: