update

scripts/post_consume.py

@@ -0,0 +1,94 @@
+#!/usr/bin/env python3
+
+import os
+import re
+from datetime import datetime
+from helper import Config
+from helper import PaperlessAPI
+
+
+
+
+# need to have this manually as setlocale() won't work in Paperless docker setup
+MONTH_NAMES = [
+    "0-Index",
+    "Januar",
+    "Februar",
+    "März",
+    "April",
+    "Mai",
+    "Juni",
+    "Juli",
+    "August",
+    "September",
+    "Oktober",
+    "November",
+    "Dezember"
+]
+
+#""
+# expand the string by the provided parts, but only if the input string doesn't contain those parts yet.
+#
+def expand_by_non_existing_parts(title, parts=[]) -> str:
+    if len(parts) == 0:
+        return title
+    
+    for part in parts:
+        if str(part) not in title:
+            title += " " + str(part)
+
+    return title
+
+
+if __name__ == "__main__":
+    cfg = Config()
+
+    print("START POST CONSUME")
+    print(cfg)
+
+    api = PaperlessAPI(cfg.get_paperless_api_url(), cfg.get_auth_token())
+
+    document_id = os.environ["DOCUMENT_ID"]
+    document = api.get_document_by_id(document_id)
+    orig_filename = document["original_file_name"]
+
+    title = document["title"]
+
+    pattern = re.compile(r'^(\d{8})(\s\W\s|\s)(.*)')
+    findings = pattern.match(title)    
+    if findings:
+        extracted_new_title = findings.group(3)
+        print(f'Extracted title="{extracted_new_title}"')
+        
+        # should add Month Year suffix to title?
+        if cfg.expand_title_by_date():
+            print("add suffix")
+            date_string = findings.group(1)
+            print(f"title date string={date_string}")
+            d=datetime.strptime(date_string, "%Y%m%d")
+
+            print(f"parsed date={d}")
+            suffix = f'{MONTH_NAMES[d.month]} {d.year}'
+            print(f"created suffix={suffix}")
+            extracted_new_title = expand_by_non_existing_parts(extracted_new_title, [MONTH_NAMES[d.month], d.year])
+
+        tag_id = api.get_tag_id_by_name(cfg.get_notify_tag())
+        print(tag_id)
+        if tag_id is None:
+            data = {"title": extracted_new_title}
+        else:
+            document["tags"].append(tag_id)
+            data = {"title": extracted_new_title, "tags": document["tags"]}
+
+        response = api.patch_document(document_id, data)
+
+        print(f'Status Code = {response.status_code}')
+        response.raise_for_status()
+    else:
+        print("Nothing changed")
+
+    
+    print("END POST CONSUME")
+
+
+