Adding catalogue number

app/helpers/process_file.py

@@ -26,6 +26,7 @@ def create_export_df(dwcs, ocrs, base_url):
     df.rename(columns={'index': 'filename'}, inplace=True)
     df = df.astype(str)
     df['id'] = df['filename'].str.extract(r'([^\.]+)')
+    df['catalogNumber'] = df['id']
     df['associatedMedia'] = base_url + df['filename']
     del df['filename']
     df['occurrenceRemarks'] = 'Record originally derived from Google Cloud Vision OCR using GPT-4-turbo'

app/helpers/prompt.txt

@@ -3,7 +3,6 @@ Important Note! Label OCR text contains rulers (i.e. incremental cm counts from
 First you correct any obvious OCR errors, and then you extract ONLY the following Darwin Core terms. Be sure to translate into English and when that's not possible convert from Cyrillic to latin alphabet:
 
     - scientificName: Full scientific name, not containing identification qualifications.
-    - catalogNumber: Unique identifier for the record in the dataset or collection.
     - recordNumber: Identifier given during recording, often linking field notes and Occurrence record.
     - recordedBy: List of people, groups, or organizations responsible for recording the original Occurrence.
     - year: Four-digit year of the Event.