diff --git a/docs/requests.md b/docs/requests.md
index 1e3cfc46c0..10a180bb2b 100644
--- a/docs/requests.md
+++ b/docs/requests.md
@@ -123,6 +123,7 @@ multidict, containing both file uploads and text input. File upload items are re
* `content_type`: A `str` with the content type (MIME type / media type) (e.g. `image/jpeg`).
* `file`: A `SpooledTemporaryFile` (a file-like object). This is the actual Python file that you can pass directly to other functions or libraries that expect a "file-like" object.
* `headers`: A `Headers` object. Often this will only be the `Content-Type` header, but if additional headers were included in the multipart field they will be included here. Note that these headers have no relationship with the headers in `Request.headers`.
+* `size`: An `int` with uploaded file's size in bytes. This value is calculated from request's contents, making it better choice to find uploaded file's size than `Content-Length` header. `None` if not set.
`UploadFile` has the following `async` methods. They all call the corresponding file methods underneath (using the internal `SpooledTemporaryFile`).
diff --git a/starlette/datastructures.py b/starlette/datastructures.py
index ab957f04c0..236f9fa433 100644
--- a/starlette/datastructures.py
+++ b/starlette/datastructures.py
@@ -438,11 +438,13 @@ def __init__(
self,
file: typing.BinaryIO,
*,
+ size: typing.Optional[int] = None,
filename: typing.Optional[str] = None,
headers: "typing.Optional[Headers]" = None,
) -> None:
self.filename = filename
self.file = file
+ self.size = size
self.headers = headers or Headers()
@property
@@ -456,6 +458,9 @@ def _in_memory(self) -> bool:
return not rolled_to_disk
async def write(self, data: bytes) -> None:
+ if self.size is not None:
+ self.size += len(data)
+
if self._in_memory:
self.file.write(data)
else:
diff --git a/starlette/formparsers.py b/starlette/formparsers.py
index 739befae86..eb76c6f10e 100644
--- a/starlette/formparsers.py
+++ b/starlette/formparsers.py
@@ -231,6 +231,7 @@ async def parse(self) -> FormData:
tempfile = SpooledTemporaryFile(max_size=self.max_file_size)
file = UploadFile(
file=tempfile, # type: ignore[arg-type]
+ size=0,
filename=filename,
headers=Headers(raw=item_headers),
)
diff --git a/tests/test_datastructures.py b/tests/test_datastructures.py
index e83f2be68d..b6e24ff703 100644
--- a/tests/test_datastructures.py
+++ b/tests/test_datastructures.py
@@ -293,10 +293,26 @@ def test_queryparams():
async def test_upload_file_file_input():
"""Test passing file/stream into the UploadFile constructor"""
stream = io.BytesIO(b"data")
+ file = UploadFile(filename="file", file=stream, size=4)
+ assert await file.read() == b"data"
+ assert file.size == 4
+ await file.write(b" and more data!")
+ assert await file.read() == b""
+ assert file.size == 19
+ await file.seek(0)
+ assert await file.read() == b"data and more data!"
+
+
+@pytest.mark.anyio
+async def test_upload_file_without_size():
+ """Test passing file/stream into the UploadFile constructor without size"""
+ stream = io.BytesIO(b"data")
file = UploadFile(filename="file", file=stream)
assert await file.read() == b"data"
+ assert file.size is None
await file.write(b" and more data!")
assert await file.read() == b""
+ assert file.size is None
await file.seek(0)
assert await file.read() == b"data and more data!"
@@ -310,22 +326,26 @@ async def test_uploadfile_rolling(max_size: int) -> None:
stream: BinaryIO = SpooledTemporaryFile( # type: ignore[assignment]
max_size=max_size
)
- file = UploadFile(filename="file", file=stream)
+ file = UploadFile(filename="file", file=stream, size=0)
assert await file.read() == b""
+ assert file.size == 0
await file.write(b"data")
assert await file.read() == b""
+ assert file.size == 4
await file.seek(0)
assert await file.read() == b"data"
await file.write(b" more")
assert await file.read() == b""
+ assert file.size == 9
await file.seek(0)
assert await file.read() == b"data more"
+ assert file.size == 9
await file.close()
def test_formdata():
stream = io.BytesIO(b"data")
- upload = UploadFile(filename="file", file=stream)
+ upload = UploadFile(filename="file", file=stream, size=4)
form = FormData([("a", "123"), ("a", "456"), ("b", upload)])
assert "a" in form
assert "A" not in form
diff --git a/tests/test_formparsers.py b/tests/test_formparsers.py
index 4792424abc..804ce8d26d 100644
--- a/tests/test_formparsers.py
+++ b/tests/test_formparsers.py
@@ -29,6 +29,7 @@ async def app(scope, receive, send):
content = await value.read()
output[key] = {
"filename": value.filename,
+ "size": value.size,
"content": content.decode(),
"content_type": value.content_type,
}
@@ -51,6 +52,7 @@ async def multi_items_app(scope, receive, send):
output[key].append(
{
"filename": value.filename,
+ "size": value.size,
"content": content.decode(),
"content_type": value.content_type,
}
@@ -71,6 +73,7 @@ async def app_with_headers(scope, receive, send):
content = await value.read()
output[key] = {
"filename": value.filename,
+ "size": value.size,
"content": content.decode(),
"content_type": value.content_type,
"headers": list(value.headers.items()),
@@ -112,6 +115,7 @@ def test_multipart_request_files(tmpdir, test_client_factory):
assert response.json() == {
"test": {
"filename": "test.txt",
+ "size": 14,
"content": "",
"content_type": "text/plain",
}
@@ -129,6 +133,7 @@ def test_multipart_request_files_with_content_type(tmpdir, test_client_factory):
assert response.json() == {
"test": {
"filename": "test.txt",
+ "size": 14,
"content": "",
"content_type": "text/plain",
}
@@ -152,11 +157,13 @@ def test_multipart_request_multiple_files(tmpdir, test_client_factory):
assert response.json() == {
"test1": {
"filename": "test1.txt",
+ "size": 15,
"content": "",
"content_type": "text/plain",
},
"test2": {
"filename": "test2.txt",
+ "size": 15,
"content": "",
"content_type": "text/plain",
},
@@ -185,6 +192,7 @@ def test_multipart_request_multiple_files_with_headers(tmpdir, test_client_facto
"test1": "",
"test2": {
"filename": "test2.txt",
+ "size": 15,
"content": "",
"content_type": "text/plain",
"headers": [
@@ -220,11 +228,13 @@ def test_multi_items(tmpdir, test_client_factory):
"abc",
{
"filename": "test1.txt",
+ "size": 15,
"content": "",
"content_type": "text/plain",
},
{
"filename": "test2.txt",
+ "size": 15,
"content": "",
"content_type": "text/plain",
},
@@ -261,6 +271,7 @@ def test_multipart_request_mixed_files_and_data(tmpdir, test_client_factory):
assert response.json() == {
"file": {
"filename": "file.txt",
+ "size": 14,
"content": "",
"content_type": "text/plain",
},
@@ -291,6 +302,7 @@ def test_multipart_request_with_charset_for_filename(tmpdir, test_client_factory
assert response.json() == {
"file": {
"filename": "文書.txt",
+ "size": 14,
"content": "",
"content_type": "text/plain",
}
@@ -318,6 +330,7 @@ def test_multipart_request_without_charset_for_filename(tmpdir, test_client_fact
assert response.json() == {
"file": {
"filename": "画像.jpg",
+ "size": 14,
"content": "",
"content_type": "image/jpeg",
}