chore: remove Office constraint pin

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.15.2-dev5
+## 0.15.2-dev6
 
 ### Enhancements
 

requirements/deps/constraints.txt

@@ -15,9 +15,6 @@ certifi>=2023.7.22
 pyparsing<3.1.0
 scipy<1.11.4
 IPython<8.13
-# NOTE(alan) Pinned to avoid error that occurs with 2.4.3:
-# AttributeError: 'ResourcePath' object has no attribute 'collection'
-Office365-REST-Python-Client<2.4.3
 # NOTE(trevor) `unstructured-inference` is set in extra-pdf-image.in to allow
 # unstructured-inference to be upgraded when unstructured library is upgraded
 # https://github.com/Unstructured-IO/unstructured/issues/1458

requirements/extra-pdf-image.txt

@@ -148,7 +148,7 @@ pdfminer-six==20231228
     # via
     #   -r ./extra-pdf-image.in
     #   pdfplumber
-pdfplumber==0.11.2
+pdfplumber==0.11.3
     # via layoutparser
 pikepdf==9.1.0
     # via -r ./extra-pdf-image.in

requirements/ingest/onedrive.txt

@@ -33,10 +33,8 @@ msal==1.30.0
     # via
     #   -r ./ingest/onedrive.in
     #   office365-rest-python-client
-office365-rest-python-client==2.4.2
-    # via
-    #   -c ./ingest/../deps/constraints.txt
-    #   -r ./ingest/onedrive.in
+office365-rest-python-client==2.5.11
+    # via -r ./ingest/onedrive.in
 pycparser==2.22
     # via cffi
 pyjwt[crypto]==2.9.0
@@ -52,6 +50,10 @@ soupsieve==2.5
     # via
     #   -c ./ingest/../base.txt
     #   beautifulsoup4
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   office365-rest-python-client
 urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt

requirements/ingest/outlook.txt

@@ -27,10 +27,8 @@ msal==1.30.0
     # via
     #   -r ./ingest/outlook.in
     #   office365-rest-python-client
-office365-rest-python-client==2.4.2
-    # via
-    #   -c ./ingest/../deps/constraints.txt
-    #   -r ./ingest/outlook.in
+office365-rest-python-client==2.5.11
+    # via -r ./ingest/outlook.in
 pycparser==2.22
     # via cffi
 pyjwt[crypto]==2.9.0
@@ -42,6 +40,10 @@ requests==2.32.3
     #   -c ./ingest/../base.txt
     #   msal
     #   office365-rest-python-client
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   office365-rest-python-client
 urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt

requirements/ingest/sharepoint.txt

@@ -27,10 +27,8 @@ msal==1.30.0
     # via
     #   -r ./ingest/sharepoint.in
     #   office365-rest-python-client
-office365-rest-python-client==2.4.2
-    # via
-    #   -c ./ingest/../deps/constraints.txt
-    #   -r ./ingest/sharepoint.in
+office365-rest-python-client==2.5.11
+    # via -r ./ingest/sharepoint.in
 pycparser==2.22
     # via cffi
 pyjwt[crypto]==2.9.0
@@ -42,6 +40,10 @@ requests==2.32.3
     #   -c ./ingest/../base.txt
     #   msal
     #   office365-rest-python-client
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   office365-rest-python-client
 urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.15.2-dev5"  # pragma: no cover
+__version__ = "0.15.2-dev6"  # pragma: no cover

unstructured/ingest/v2/logger.py

@@ -22,8 +22,8 @@ def default_is_data_sensitive(k: str, v: Any) -> bool:
 
 
 def hide_sensitive_fields(
-    data: dict, is_sensitive_fn: Callable[[str, Any], bool] = default_is_data_sensitive
-) -> dict:
+    data: dict[str, Any], is_sensitive_fn: Callable[[str, Any], bool] = default_is_data_sensitive
+) -> dict[str, Any]:
     """
     Will recursively look through every k, v pair in this dict and any nested ones and run
     is_sensitive_fn to dynamically redact the value of the k, v pair. Will also check if
@@ -62,8 +62,7 @@ def redact_jsons(s: str) -> str:
     if "{" not in chars:
         return s
     i = 0
-    jsons = []
-    i = 0
+    jsons: list[str] = []
     while i < len(chars):
         char = chars[i]
         if char == "{":

unstructured/ingest/v2/processes/connectors/onedrive.py

@@ -89,10 +89,10 @@ class OnedriveIndexer(Indexer):
 
     def list_objects(self, folder, recursive) -> list["DriveItem"]:
         drive_items = folder.children.get().execute_query()
-        files = [d for d in drive_items if d.is_file]
+        files = [d for d in drive_items if d.file is not None]
         if not recursive:
             return files
-        folders = [d for d in drive_items if d.is_folder]
+        folders = [d for d in drive_items if d.is_folder is not None]
         for f in folders:
             files.extend(self.list_objects(f, recursive))
         return files
@@ -123,12 +123,12 @@ def drive_item_to_file_data(self, drive_item: "DriveItem") -> FileData:
         server_path = file_path + "/" + filename
         rel_path = server_path.replace(self.index_config.path, "").lstrip("/")
         date_modified_dt = (
-            parser.parse(drive_item.last_modified_datetime)
+            parser.parse(str(drive_item.last_modified_datetime))
             if drive_item.last_modified_datetime
             else None
         )
         date_created_at = (
-            parser.parse(drive_item.created_datetime) if drive_item.created_datetime else None
+            parser.parse(str(drive_item.created_datetime)) if drive_item.created_datetime else None
         )
         return FileData(
             identifier=drive_item.id,