From f0ea093de867e5f099a4b5de2bfa24d788b79133 Mon Sep 17 00:00:00 2001
From: Nicholas Liu <nicholas.j.liu@gmail.com>
Date: Wed, 24 May 2023 22:26:17 -0700
Subject: [PATCH] Change Default GoogleDriveLoader Behavior to not Load Trashed
 Files (issue #5104) (#5220)

# Change Default GoogleDriveLoader Behavior to not Load Trashed Files
(issue #5104)

Fixes #5104

If the previous behavior of loading files that used to live in the
folder, but are now trashed, you can use the `load_trashed_files`
parameter:

```
loader = GoogleDriveLoader(
    folder_id="1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5",
    recursive=False,
    load_trashed_files=True
)
```

As not loading trashed files should be expected behavior, should we
1. even provide the `load_trashed_files` parameter?
2. add documentation? Feels most users will stick with default behavior

## Who can review?

Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:

DataLoaders
- @eyurtsev

Twitter: [@nicholasliu77](https://twitter.com/nicholasliu77)
---
 langchain/document_loaders/googledrive.py | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/langchain/document_loaders/googledrive.py b/langchain/document_loaders/googledrive.py
index 176191f7..dc00eb4a 100644
--- a/langchain/document_loaders/googledrive.py
+++ b/langchain/document_loaders/googledrive.py
@@ -31,6 +31,7 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
     file_ids: Optional[List[str]] = None
     recursive: bool = False
     file_types: Optional[Sequence[str]] = None
+    load_trashed_files: bool = False
 
     @root_validator
     def validate_inputs(cls, values: Dict[str, Any]) -> Dict[str, Any]:
@@ -215,8 +216,10 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
             _files = files
 
         returns = []
-        for file in _files:
-            if file["mimeType"] == "application/vnd.google-apps.document":
+        for file in files:
+            if file["trashed"] and not self.load_trashed_files:
+                continue
+            elif file["mimeType"] == "application/vnd.google-apps.document":
                 returns.append(self._load_document_from_id(file["id"]))  # type: ignore
             elif file["mimeType"] == "application/vnd.google-apps.spreadsheet":
                 returns.extend(self._load_sheet_from_id(file["id"]))  # type: ignore
@@ -224,7 +227,6 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
                 returns.extend(self._load_file_from_id(file["id"]))  # type: ignore
             else:
                 pass
-
         return returns
 
     def _fetch_files_recursive(
@@ -238,7 +240,7 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
                 pageSize=1000,
                 includeItemsFromAllDrives=True,
                 supportsAllDrives=True,
-                fields="nextPageToken, files(id, name, mimeType, parents)",
+                fields="nextPageToken, files(id, name, mimeType, parents, trashed)",
             )
             .execute()
         )