Add ability to blocklist filepaths, ability to specify where gradio t…

…emp files are created (#4047)

* temporary file

* tests

* formatting

* rename

* added another test

* guide

* formatting

* changelog

* added custom gradio temp directory (#4053)

* added custom gradio temp directory

* Update 03_sharing-your-app.md

* rename test

* address review

* remove print

CHANGELOG.md

@@ -7,6 +7,8 @@
 ## New Features:
 
 - Add support for `visual-question-answering`, `document-question-answering`, and `image-to-text` using `gr.Interface.load("models/...")` and `gr.Interface.from_pipeline` by [@osanseviero](https://github.com/osanseviero) in [PR 3887](https://github.com/gradio-app/gradio/pull/3887)
+- Adds the ability to blocklist filepaths (and also improves the allowlist mechanism) by [@abidlabs](https://github.com/abidlabs) in [PR 4047](https://github.com/gradio-app/gradio/pull/4047).
+- Adds the ability to specify the upload directory via an environment variable by [@abidlabs](https://github.com/abidlabs) in [PR 4047](https://github.com/gradio-app/gradio/pull/4047).
 
 ## Bug Fixes:
 

gradio/blocks.py

@@ -692,7 +692,8 @@ def __init__(
         self.progress_tracking = None
         self.ssl_verify = True
 
-        self.file_directories = []
+        self.allowed_paths = []
+        self.blocked_paths = []
 
         if self.analytics_enabled:
             is_custom_theme = not any(
@@ -1588,6 +1589,8 @@ def launch(
         quiet: bool = False,
         show_api: bool = True,
         file_directories: List[str] | None = None,
+        allowed_paths: List[str] | None = None,
+        blocked_paths: List[str] | None = None,
         _frontend: bool = True,
     ) -> Tuple[FastAPI, str, str]:
         """
@@ -1618,7 +1621,9 @@ def launch(
             ssl_verify: If False, skips certificate validation which allows self-signed certificates to be used.
             quiet: If True, suppresses most print statements.
             show_api: If True, shows the api docs in the footer of the app. Default True. If the queue is enabled, then api_open parameter of .queue() will determine if the api docs are shown, independent of the value of show_api.
-            file_directories: List of directories that gradio is allowed to serve files from (in addition to the directory containing the gradio python file). Must be absolute paths. Warning: any files in these directories or its children are potentially accessible to all users of your app.
+            file_directories: This parameter has been renamed to `allowed_paths`. It will be removed in a future version.
+            allowed_paths: List of complete filepaths or parent directories that gradio is allowed to serve (in addition to the directory containing the gradio python file). Must be absolute paths. Warning: if you provide directories, any files in these directories or their subdirectories are accessible to all users of your app.
+            blocked_paths: List of complete filepaths or parent directories that gradio is not allowed to serve (i.e. users of your app are not allowed to access). Must be absolute paths. Warning: takes precedence over `allowed_paths` and all other directories exposed by Gradio by default.
         Returns:
             app: FastAPI app object that is running the demo
             local_url: Locally accessible link to the demo
@@ -1679,9 +1684,20 @@ def reverse(text):
             self.queue()
         self.show_api = self.api_open if self.enable_queue else show_api
 
-        self.file_directories = file_directories if file_directories is not None else []
-        if not isinstance(self.file_directories, list):
-            raise ValueError("file_directories must be a list of directories.")
+        if file_directories is not None:
+            warnings.warn(
+                "The `file_directories` parameter has been renamed to `allowed_paths`. Please use that instead.",
+                DeprecationWarning,
+            )
+            if allowed_paths is None:
+                allowed_paths = file_directories
+        self.allowed_paths = allowed_paths or []
+        self.blocked_paths = blocked_paths or []
+
+        if not isinstance(self.allowed_paths, list):
+            raise ValueError("`allowed_paths` must be a list of directories.")
+        if not isinstance(self.blocked_paths, list):
+            raise ValueError("`blocked_paths` must be a list of directories.")
 
         self.validate_queue_settings()
 

gradio/components.py

@@ -9,6 +9,7 @@
 import json
 import math
 import operator
+import os
 import random
 import secrets
 import shutil
@@ -191,7 +192,9 @@ def __init__(
         **kwargs,
     ):
         self.temp_files: Set[str] = set()
-        self.DEFAULT_TEMP_DIR = tempfile.gettempdir()
+        self.DEFAULT_TEMP_DIR = os.environ.get("GRADIO_TEMP_DIR") or str(
+            Path(tempfile.gettempdir()) / "gradio"
+        )
 
         Component.__init__(
             self, elem_id=elem_id, elem_classes=elem_classes, visible=visible, **kwargs

gradio/routes.py

@@ -14,6 +14,7 @@
 from asyncio import TimeoutError as AsyncTimeOutError
 from collections import defaultdict
 from copy import deepcopy
+from pathlib import Path
 from typing import Any, Dict, List, Optional, Type
 from urllib.parse import urlparse
 
@@ -111,7 +112,9 @@ def __init__(self, **kwargs):
         self.lock = asyncio.Lock()
         self.queue_token = secrets.token_urlsafe(32)
         self.startup_events_triggered = False
-        self.uploaded_file_dir = str(utils.abspath(tempfile.mkdtemp()))
+        self.uploaded_file_dir = os.environ.get("GRADIO_TEMP_DIR") or str(
+            Path(tempfile.gettempdir()) / "gradio"
+        )
         super().__init__(**kwargs, docs_url=None, redoc_url=None)
 
     def configure_app(self, blocks: gradio.Blocks) -> None:
@@ -305,12 +308,21 @@ async def file(path_or_url: str, request: fastapi.Request):
                     url=path_or_url, status_code=status.HTTP_302_FOUND
                 )
             abs_path = utils.abspath(path_or_url)
+            in_blocklist = any(
+                (
+                    utils.is_in_or_equal(abs_path, blocked_path)
+                    for blocked_path in blocks.blocked_paths
+                )
+            )
+            if in_blocklist:
+                raise HTTPException(403, f"File not allowed: {path_or_url}.")
+
             in_app_dir = utils.abspath(app.cwd) in abs_path.parents
             created_by_app = str(abs_path) in set().union(*blocks.temp_file_sets)
             in_file_dir = any(
                 (
-                    utils.abspath(dir) in abs_path.parents
-                    for dir in blocks.file_directories
+                    utils.is_in_or_equal(abs_path, allowed_path)
+                    for allowed_path in blocks.allowed_paths
                 )
             )
             was_uploaded = utils.abspath(app.uploaded_file_dir) in abs_path.parents

gradio/utils.py

@@ -962,6 +962,19 @@ def abspath(path: str | Path) -> Path:
         return path.resolve()
 
 
+def is_in_or_equal(path_1: str | Path, path_2: str | Path):
+    """
+    True if path_1 is a descendant (i.e. located within) path_2 or if the paths are the
+    same, returns False otherwise.
+    Parameters:
+        path_1: str or Path (can be a file or directory)
+        path_2: str or Path (can be a file or directory)
+    """
+    return (abspath(path_2) in abspath(path_1).parents) or abspath(path_1) == abspath(
+        path_2
+    )
+
+
 def get_serializer_name(block: Block) -> str | None:
     if not hasattr(block, "serialize"):
         return None

guides/01_getting-started/03_sharing-your-app.md

@@ -198,8 +198,8 @@ In particular, Gradio apps grant users access to three kinds of files:
 
 * Files in the same folder (or a subdirectory) of where the Gradio script is launched from. For example, if the path to your gradio scripts is `/home/usr/scripts/project/app.py` and you launch it from `/home/usr/scripts/project/`, then users of your shared Gradio app will be able to access any files inside `/home/usr/scripts/project/`. This is needed so that you can easily reference these files in your Gradio app.
 
-* Temporary files created by Gradio. These are files that are created by Gradio as part of running your prediction function. For example, if your prediction function returns a video file, then Gradio will save that video to a temporary file and then send the path to the temporary file to the front end. 
+* Temporary files created by Gradio. These are files that are created by Gradio as part of running your prediction function. For example, if your prediction function returns a video file, then Gradio will save that video to a temporary file and then send the path to the temporary file to the front end. You can customize the location of temporary files created by Gradio by setting the environment variable GRADIO_TEMP_DIR to an absolute path, such as `/home/usr/scripts/project/temp/`.
 
-* Files that you explicitly allow via the `file_directories` parameter in `launch()`. In some cases, you may want to reference other files in your file system. The `file_directories` parameter allows you to pass in a list of additional directories you'd like to provide access to. (By default, there are no additional file directories).
+* Files that you explicitly allow via the `allowed_paths` parameter in `launch()`. This parameter  allows you to pass in a list of additional directories or exact filepaths you'd like to allow users to have access to. (By default, this parameter is an empty list).
 
-Users should NOT be able to access other arbitrary paths on the host.  
+Users should NOT be able to access other arbitrary paths on the host. Furthermore, as a security measure, you can also **block** specific files or directories from being able to be accessed by users. To do this, pass in a list of additional directories or exact filepaths to the `blocked_paths` parameter in `launch()`. This parameter takes precedence over the files that Gradio exposes by default or by the `allowed_paths`.

test/test_routes.py

@@ -3,6 +3,7 @@
 import os
 import sys
 import tempfile
+from pathlib import Path
 from unittest.mock import patch
 
 import numpy as np
@@ -54,7 +55,7 @@ def test_get_config_route(self, test_client):
         response = test_client.get("/config/")
         assert response.status_code == 200
 
-    def test_upload_route(self, test_client):
+    def test_upload_path(self, test_client):
         response = test_client.post(
             "/upload", files={"files": open("test/test_files/alphabet.txt", "r")}
         )
@@ -65,6 +66,25 @@ def test_upload_route(self, test_client):
         with open(file) as saved_file:
             assert saved_file.read() == "abcdefghijklmnopqrstuvwxyz"
 
+    def test_custom_upload_path(self):
+        os.environ["GRADIO_TEMP_DIR"] = str(Path(tempfile.gettempdir()) / "gradio-test")
+        io = Interface(lambda x: x + x, "text", "text")
+        app, _, _ = io.launch(prevent_thread_lock=True)
+        test_client = TestClient(app)
+        try:
+            response = test_client.post(
+                "/upload", files={"files": open("test/test_files/alphabet.txt", "r")}
+            )
+            assert response.status_code == 200
+            file = response.json()[0]
+            assert "alphabet" in file
+            assert file.startswith(str(Path(tempfile.gettempdir()) / "gradio-test"))
+            assert file.endswith(".txt")
+            with open(file) as saved_file:
+                assert saved_file.read() == "abcdefghijklmnopqrstuvwxyz"
+        finally:
+            os.environ["GRADIO_TEMP_DIR"] = ""
+
     def test_predict_route(self, test_client):
         response = test_client.post(
             "/api/predict/", json={"data": ["test"], "fn_index": 0}
@@ -192,28 +212,95 @@ def predict(input, history):
         output = dict(response.json())
         assert output["data"] == ["testtest", None]
 
-    def test_get_file_allowed_by_file_directories(self):
+    def test_get_allowed_paths(self):
         allowed_file = tempfile.NamedTemporaryFile(mode="w", delete=False)
         allowed_file.write(media_data.BASE64_IMAGE)
         allowed_file.flush()
 
-        app, _, _ = gr.Interface(lambda s: s.name, gr.File(), gr.File()).launch(
-            prevent_thread_lock=True,
-        )
+        io = gr.Interface(lambda s: s.name, gr.File(), gr.File())
+        app, _, _ = io.launch(prevent_thread_lock=True)
         client = TestClient(app)
-
         file_response = client.get(f"/file={allowed_file.name}")
         assert file_response.status_code == 403
+        io.close()
 
-        app, _, _ = gr.Interface(lambda s: s.name, gr.File(), gr.File()).launch(
+        io = gr.Interface(lambda s: s.name, gr.File(), gr.File())
+        app, _, _ = io.launch(
             prevent_thread_lock=True,
-            file_directories=[os.path.dirname(allowed_file.name)],
+            allowed_paths=[os.path.dirname(allowed_file.name)],
         )
         client = TestClient(app)
+        file_response = client.get(f"/file={allowed_file.name}")
+        assert file_response.status_code == 200
+        assert len(file_response.text) == len(media_data.BASE64_IMAGE)
+        io.close()
 
+        io = gr.Interface(lambda s: s.name, gr.File(), gr.File())
+        app, _, _ = io.launch(
+            prevent_thread_lock=True,
+            allowed_paths=[os.path.abspath(allowed_file.name)],
+        )
+        client = TestClient(app)
         file_response = client.get(f"/file={allowed_file.name}")
         assert file_response.status_code == 200
         assert len(file_response.text) == len(media_data.BASE64_IMAGE)
+        io.close()
+
+    def test_get_blocked_paths(self):
+        # Test that blocking a default Gradio file path works
+        with tempfile.NamedTemporaryFile(
+            dir=".", suffix=".jpg", delete=False
+        ) as tmp_file:
+            io = gr.Interface(lambda s: s.name, gr.File(), gr.File())
+            app, _, _ = io.launch(
+                prevent_thread_lock=True,
+            )
+            client = TestClient(app)
+            file_response = client.get(f"/file={tmp_file.name}")
+            assert file_response.status_code == 200
+        io.close()
+        os.remove(tmp_file.name)
+
+        with tempfile.NamedTemporaryFile(
+            dir=".", suffix=".jpg", delete=False
+        ) as tmp_file:
+            io = gr.Interface(lambda s: s.name, gr.File(), gr.File())
+            app, _, _ = io.launch(
+                prevent_thread_lock=True, blocked_paths=[os.path.abspath(tmp_file.name)]
+            )
+            client = TestClient(app)
+            file_response = client.get(f"/file={tmp_file.name}")
+            assert file_response.status_code == 403
+        io.close()
+        os.remove(tmp_file.name)
+
+        # Test that blocking a default Gradio directory works
+        with tempfile.NamedTemporaryFile(
+            dir=".", suffix=".jpg", delete=False
+        ) as tmp_file:
+            io = gr.Interface(lambda s: s.name, gr.File(), gr.File())
+            app, _, _ = io.launch(
+                prevent_thread_lock=True, blocked_paths=[os.path.abspath(tmp_file.name)]
+            )
+            client = TestClient(app)
+            file_response = client.get(f"/file={tmp_file.name}")
+            assert file_response.status_code == 403
+        io.close()
+        os.remove(tmp_file.name)
+
+        # Test that blocking a directory works even if it's also allowed
+        with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as tmp_file:
+            io = gr.Interface(lambda s: s.name, gr.File(), gr.File())
+            app, _, _ = io.launch(
+                prevent_thread_lock=True,
+                allowed_paths=[os.path.dirname(tmp_file.name)],
+                blocked_paths=[os.path.dirname(tmp_file.name)],
+            )
+            client = TestClient(app)
+            file_response = client.get(f"/file={tmp_file.name}")
+            assert file_response.status_code == 403
+        io.close()
+        os.remove(tmp_file.name)
 
     def test_get_file_created_by_app(self):
         app, _, _ = gr.Interface(lambda s: s.name, gr.File(), gr.File()).launch(