Improve test to explicitly demonstrate case-insensitive handling of folder names like 'Inbox'

Co-authored-by: seanthegeek <44679+seanthegeek@users.noreply.github.com>

.github/workflows/python-tests.yml

@@ -30,7 +30,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
 
     steps:
     - uses: actions/checkout@v5

CHANGELOG.md

@@ -1,15 +1,5 @@
 # Changelog
 
-## 9.0.10
-
-- Support Python 3.14+
-
-## 9.0.9
-
-### Fixes
-
-- Validate that a string is base64-encoded before trying to base64 decode it. (PRs #648 and #649)
-
 ## 9.0.8
 
 ### Fixes

README.md

@@ -61,4 +61,4 @@ for RHEL or Debian.
 | 3.11    | ✅         | Actively maintained; supported until June 2028 (Debian 12) |
 | 3.12    | ✅         | Actively maintained; supported until May 2035 (RHEL 10)    |
 | 3.13    | ✅         | Actively maintained; supported until June 2030 (Debian 13) |
-| 3.14    | ✅         | Actively maintained                                        |
+| 3.14    | ❌         | Not currently supported due to [this imapclient bug](https://github.com/mjs/imapclient/issues/618)|

ci.ini

@@ -3,7 +3,6 @@ save_aggregate = True
 save_forensic = True
 save_smtp_tls = True
 debug = True
-offline = True
 
 [elasticsearch]
 hosts = http://localhost:9200

docs/source/example.ini

@@ -29,3 +29,14 @@ token_file = /etc/example/token.json
 include_spam_trash = True
 paginate_messages = True
 scopes = https://www.googleapis.com/auth/gmail.modify
+
+[msgraph]
+auth_method = ClientSecret
+client_id = 12345678-90ab-cdef-1234-567890abcdef
+client_secret = your-client-secret-here
+tenant_id = 12345678-90ab-cdef-1234-567890abcdef
+mailbox = dmarc-reports@example.com
+# Use standard folder names - they work across all locales
+# and avoid "Default folder Root not found" errors
+reports_folder = Inbox
+archive_folder = Archive

docs/source/index.md

@@ -61,7 +61,7 @@ for RHEL or Debian.
 | 3.11    | ✅         | Actively maintained; supported until June 2028 (Debian 12) |
 | 3.12    | ✅         | Actively maintained; supported until May 2035 (RHEL 10)    |
 | 3.13    | ✅         | Actively maintained; supported until June 2030 (Debian 13) |
-| 3.14    | ✅         | Actively maintained                                        |
+| 3.14    | ❌         | Not currently supported due to [this imapclient bug](https://github.com/mjs/imapclient/issues/618)|
 
 ```{toctree}
 :caption: 'Contents'

docs/source/usage.md

@@ -229,6 +229,18 @@ The full set of configuration options are:
     username, you must grant the app `Mail.ReadWrite.Shared`.
     :::
 
+    :::{tip}
+    When configuring folder names (e.g., `reports_folder`, `archive_folder`),
+    you can use standard folder names like `Inbox`, `Archive`, `Sent Items`, etc.
+    These will be automatically mapped to Microsoft Graph's well-known folder names,
+    which works reliably across different mailbox locales and avoids issues with
+    uninitialized or shared mailboxes. Supported folder names include:
+    - English: Inbox, Sent Items, Deleted Items, Drafts, Junk Email, Archive, Outbox
+    - German: Posteingang, Gesendete Elemente, Gelöschte Elemente, Entwürfe, Junk-E-Mail, Archiv
+    - French: Boîte de réception, Éléments envoyés, Éléments supprimés, Brouillons, Courrier indésirable, Archives
+    - Spanish: Bandeja de entrada, Elementos enviados, Elementos eliminados, Borradores, Correo no deseado
+    :::
+
     :::{warning}
     If you are using the `ClientSecret` auth method, you need to
     grant the `Mail.ReadWrite` (application) permission to the

parsedmarc/__init__.py

@@ -751,8 +751,8 @@ def parse_aggregate_report_xml(
         new_report_metadata["report_id"] = report_id
         date_range = report["report_metadata"]["date_range"]
 
-        begin_ts = int(date_range["begin"].split(".")[0])
-        end_ts = int(date_range["end"].split(".")[0])
+        begin_ts = int(date_range["begin"])
+        end_ts = int(date_range["end"])
         span_seconds = end_ts - begin_ts
 
         normalize_timespan = span_seconds > normalize_timespan_threshold_hours * 3600
@@ -892,11 +892,7 @@ def extract_report(content: Union[bytes, str, BinaryIO]) -> str:
     try:
         if isinstance(content, str):
             try:
-                file_object = BytesIO(
-                    b64decode(
-                        content.replace("\n", "").replace("\r", ""), validate=True
-                    )
-                )
+                file_object = BytesIO(b64decode(content))
             except binascii.Error:
                 return content
             header = file_object.read(6)

parsedmarc/constants.py

@@ -1,3 +1,3 @@
-__version__ = "9.0.10"
+__version__ = "9.0.8"
 
 USER_AGENT = f"parsedmarc/{__version__}"

parsedmarc/mail/graph.py

@@ -20,6 +20,59 @@ from msgraph.core import GraphClient
 from parsedmarc.log import logger
 from parsedmarc.mail.mailbox_connection import MailboxConnection
 
+# Mapping of common folder names to Microsoft Graph well-known folder names
+# This avoids the "Default folder Root not found" error on uninitialized mailboxes
+WELL_KNOWN_FOLDER_MAP = {
+    # English names
+    "inbox": "inbox",
+    "sent items": "sentitems",
+    "sent": "sentitems",
+    "sentitems": "sentitems",
+    "deleted items": "deleteditems",
+    "deleted": "deleteditems",
+    "deleteditems": "deleteditems",
+    "trash": "deleteditems",
+    "drafts": "drafts",
+    "junk email": "junkemail",
+    "junk": "junkemail",
+    "junkemail": "junkemail",
+    "spam": "junkemail",
+    "archive": "archive",
+    "outbox": "outbox",
+    "conversation history": "conversationhistory",
+    "conversationhistory": "conversationhistory",
+    # German names
+    "posteingang": "inbox",
+    "gesendete elemente": "sentitems",
+    "gesendet": "sentitems",
+    "gelöschte elemente": "deleteditems",
+    "gelöscht": "deleteditems",
+    "entwürfe": "drafts",
+    "junk-e-mail": "junkemail",
+    "archiv": "archive",
+    "postausgang": "outbox",
+    # French names
+    "boîte de réception": "inbox",
+    "éléments envoyés": "sentitems",
+    "envoyés": "sentitems",
+    "éléments supprimés": "deleteditems",
+    "supprimés": "deleteditems",
+    "brouillons": "drafts",
+    "courrier indésirable": "junkemail",
+    "archives": "archive",
+    "boîte d'envoi": "outbox",
+    # Spanish names
+    "bandeja de entrada": "inbox",
+    "elementos enviados": "sentitems",
+    "enviados": "sentitems",
+    "elementos eliminados": "deleteditems",
+    "eliminados": "deleteditems",
+    "borradores": "drafts",
+    "correo no deseado": "junkemail",
+    "archivar": "archive",
+    "bandeja de salida": "outbox",
+}
+
 
 class AuthMethod(Enum):
     DeviceCode = 1
@@ -130,6 +183,13 @@ class MSGraphConnection(MailboxConnection):
         self.mailbox_name = mailbox
 
     def create_folder(self, folder_name: str):
+        # Check if this is a well-known folder - they already exist and cannot be created
+        if "/" not in folder_name:
+            well_known_name = WELL_KNOWN_FOLDER_MAP.get(folder_name.lower())
+            if well_known_name:
+                logger.debug(f"Folder '{folder_name}' is a well-known folder, skipping creation")
+                return
+        
         sub_url = ""
         path_parts = folder_name.split("/")
         if len(path_parts) > 1:  # Folder is a subFolder
@@ -246,6 +306,12 @@ class MSGraphConnection(MailboxConnection):
                 parent_folder_id = folder_id
             return self._find_folder_id_with_parent(path_parts[-1], parent_folder_id)
         else:
+            # Check if this is a well-known folder name (case-insensitive)
+            well_known_name = WELL_KNOWN_FOLDER_MAP.get(folder_name.lower())
+            if well_known_name:
+                # Use well-known folder name directly to avoid querying uninitialized mailboxes
+                logger.debug(f"Using well-known folder name '{well_known_name}' for '{folder_name}'")
+                return well_known_name
             return self._find_folder_id_with_parent(folder_name, None)
 
     def _find_folder_id_with_parent(

pyproject.toml

@@ -29,7 +29,7 @@ classifiers = [
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3"
 ]
-requires-python = ">=3.9"
+requires-python = ">=3.9, <3.14"
 dependencies = [
     "azure-identity>=1.8.0",
     "azure-monitor-ingestion>=1.0.0",
@@ -48,7 +48,7 @@ dependencies = [
     "imapclient>=2.1.0",
     "kafka-python-ng>=2.2.2",
     "lxml>=4.4.0",
-    "mailsuite>=1.11.2",
+    "mailsuite>=1.11.1",
     "msgraph-core==0.2.2",
     "opensearch-py>=2.4.2,<=3.0.0",
     "publicsuffixlist>=0.10.0",

tests.py

@@ -12,9 +12,6 @@ from lxml import etree
 import parsedmarc
 import parsedmarc.utils
 
-# Detect if running in GitHub Actions to skip DNS lookups
-OFFLINE_MODE = os.environ.get("GITHUB_ACTIONS", "false").lower() == "true"
-
 
 def minify_xml(xml_string):
     parser = etree.XMLParser(remove_blank_text=True)
@@ -124,7 +121,7 @@ class Test(unittest.TestCase):
                 continue
             print("Testing {0}: ".format(sample_path), end="")
             parsed_report = parsedmarc.parse_report_file(
-                sample_path, always_use_local_files=True, offline=OFFLINE_MODE
+                sample_path, always_use_local_files=True
             )["report"]
             parsedmarc.parsed_aggregate_reports_to_csv(parsed_report)
             print("Passed!")
@@ -132,7 +129,7 @@ class Test(unittest.TestCase):
     def testEmptySample(self):
         """Test empty/unparasable report"""
         with self.assertRaises(parsedmarc.ParserError):
-            parsedmarc.parse_report_file("samples/empty.xml", offline=OFFLINE_MODE)
+            parsedmarc.parse_report_file("samples/empty.xml")
 
     def testForensicSamples(self):
         """Test sample forensic/ruf/failure DMARC reports"""
@@ -142,12 +139,8 @@ class Test(unittest.TestCase):
             print("Testing {0}: ".format(sample_path), end="")
             with open(sample_path) as sample_file:
                 sample_content = sample_file.read()
-                parsed_report = parsedmarc.parse_report_email(
-                    sample_content, offline=OFFLINE_MODE
-                )["report"]
-            parsed_report = parsedmarc.parse_report_file(
-                sample_path, offline=OFFLINE_MODE
-            )["report"]
+                parsed_report = parsedmarc.parse_report_email(sample_content)["report"]
+            parsed_report = parsedmarc.parse_report_file(sample_path)["report"]
             parsedmarc.parsed_forensic_reports_to_csv(parsed_report)
             print("Passed!")
 
@@ -159,12 +152,36 @@ class Test(unittest.TestCase):
             if os.path.isdir(sample_path):
                 continue
             print("Testing {0}: ".format(sample_path), end="")
-            parsed_report = parsedmarc.parse_report_file(
-                sample_path, offline=OFFLINE_MODE
-            )["report"]
+            parsed_report = parsedmarc.parse_report_file(sample_path)["report"]
             parsedmarc.parsed_smtp_tls_reports_to_csv(parsed_report)
             print("Passed!")
 
+    def testMSGraphWellKnownFolders(self):
+        """Test MSGraph well-known folder name mapping"""
+        from parsedmarc.mail.graph import WELL_KNOWN_FOLDER_MAP
+        
+        # Test English folder names
+        assert WELL_KNOWN_FOLDER_MAP.get("inbox") == "inbox"
+        assert WELL_KNOWN_FOLDER_MAP.get("sent items") == "sentitems"
+        assert WELL_KNOWN_FOLDER_MAP.get("deleted items") == "deleteditems"
+        assert WELL_KNOWN_FOLDER_MAP.get("archive") == "archive"
+        
+        # Test case insensitivity - simulating how the code actually uses it
+        # This is what happens when user config has "reports_folder = Inbox"
+        assert WELL_KNOWN_FOLDER_MAP.get("inbox") == "inbox"
+        assert WELL_KNOWN_FOLDER_MAP.get("Inbox".lower()) == "inbox"  # User's exact config
+        assert WELL_KNOWN_FOLDER_MAP.get("INBOX".lower()) == "inbox"
+        assert WELL_KNOWN_FOLDER_MAP.get("Archive".lower()) == "archive"
+        
+        # Test German folder names
+        assert WELL_KNOWN_FOLDER_MAP.get("posteingang") == "inbox"
+        assert WELL_KNOWN_FOLDER_MAP.get("Posteingang".lower()) == "inbox"  # Capitalized
+        assert WELL_KNOWN_FOLDER_MAP.get("archiv") == "archive"
+        
+        # Test that custom folders don't match
+        assert WELL_KNOWN_FOLDER_MAP.get("custom_folder") is None
+        assert WELL_KNOWN_FOLDER_MAP.get("my_reports") is None
+
 
 if __name__ == "__main__":
     unittest.main(verbosity=2)