diff --git a/.release-please-manifest.json b/.release-please-manifest.json index c523ce1..c3c9552 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,3 +1,3 @@ { - ".": "1.8.0" + ".": "1.9.0" } \ No newline at end of file diff --git a/.stats.yml b/.stats.yml index bf21668..b1784cf 100644 --- a/.stats.yml +++ b/.stats.yml @@ -1,4 +1,4 @@ configured_endpoints: 21 -openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/browserbase%2Fbrowserbase-921d3c61c7aa06269f74bee63cee993597944f913429caa2aa2e00dd51fab60f.yml -openapi_spec_hash: d35b9613c41bf172fa2b28aceef10b39 +openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/browserbase%2Fbrowserbase-3683b291883198719787c333144da6650b6c287db400e0b21f54797f6e986a24.yml +openapi_spec_hash: 4da0b34a056487d20ed56a3b0b1c078e config_hash: cf04ecfb8dad5fbd8b85be25d6e9ec55 diff --git a/CHANGELOG.md b/CHANGELOG.md index 3a2dbc4..6b22527 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,29 @@ # Changelog +## 1.9.0 (2026-04-18) + +Full Changelog: [v1.8.0...v1.9.0](https://github.com/browserbase/sdk-python/compare/v1.8.0...v1.9.0) + +### Features + +* [CORE-1928][apps/api] Add `PENDING` as a valid session state ([4f1248d](https://github.com/browserbase/sdk-python/commit/4f1248dfb1bf79194f65854a6fcd6a0d53433ba1)) + + +### Bug Fixes + +* **client:** preserve hardcoded query params when merging with user params ([953fd3e](https://github.com/browserbase/sdk-python/commit/953fd3ecd54a7ffc2ee390eac67f2063df89b8e9)) +* ensure file data are only sent as 1 parameter ([a837357](https://github.com/browserbase/sdk-python/commit/a83735708037eec6cb4807e4220ca7452b5b6503)) + + +### Performance Improvements + +* **client:** optimize file structure copying in multipart requests ([4146f22](https://github.com/browserbase/sdk-python/commit/4146f22bb6c054e7491e4c10021dff3e9e2c8824)) + + +### Chores + +* **tests:** bump steady to v0.22.1 ([bafb680](https://github.com/browserbase/sdk-python/commit/bafb68055a4f36ef6b7d6a308606db9e8d33257b)) + ## 1.8.0 (2026-04-06) Full Changelog: [v1.7.0...v1.8.0](https://github.com/browserbase/sdk-python/compare/v1.7.0...v1.8.0) diff --git a/pyproject.toml b/pyproject.toml index e39927c..bc5e136 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "browserbase" -version = "1.8.0" +version = "1.9.0" description = "The official Python library for the Browserbase API" dynamic = ["readme"] license = "Apache-2.0" diff --git a/scripts/mock b/scripts/mock index 5cd7c15..feebe5e 100755 --- a/scripts/mock +++ b/scripts/mock @@ -22,9 +22,9 @@ echo "==> Starting mock server with URL ${URL}" # Run steady mock on the given spec if [ "$1" == "--daemon" ]; then # Pre-install the package so the download doesn't eat into the startup timeout - npm exec --package=@stdy/cli@0.20.2 -- steady --version + npm exec --package=@stdy/cli@0.22.1 -- steady --version - npm exec --package=@stdy/cli@0.20.2 -- steady --host 127.0.0.1 -p 4010 --validator-query-array-format=comma --validator-form-array-format=comma --validator-query-object-format=brackets --validator-form-object-format=brackets "$URL" &> .stdy.log & + npm exec --package=@stdy/cli@0.22.1 -- steady --host 127.0.0.1 -p 4010 --validator-query-array-format=comma --validator-form-array-format=comma --validator-query-object-format=brackets --validator-form-object-format=brackets "$URL" &> .stdy.log & # Wait for server to come online via health endpoint (max 30s) echo -n "Waiting for server" @@ -48,5 +48,5 @@ if [ "$1" == "--daemon" ]; then echo else - npm exec --package=@stdy/cli@0.20.2 -- steady --host 127.0.0.1 -p 4010 --validator-query-array-format=comma --validator-form-array-format=comma --validator-query-object-format=brackets --validator-form-object-format=brackets "$URL" + npm exec --package=@stdy/cli@0.22.1 -- steady --host 127.0.0.1 -p 4010 --validator-query-array-format=comma --validator-form-array-format=comma --validator-query-object-format=brackets --validator-form-object-format=brackets "$URL" fi diff --git a/scripts/test b/scripts/test index b8143aa..19acc91 100755 --- a/scripts/test +++ b/scripts/test @@ -43,7 +43,7 @@ elif ! steady_is_running ; then echo -e "To run the server, pass in the path or url of your OpenAPI" echo -e "spec to the steady command:" echo - echo -e " \$ ${YELLOW}npm exec --package=@stdy/cli@0.20.2 -- steady path/to/your.openapi.yml --host 127.0.0.1 -p 4010 --validator-query-array-format=comma --validator-form-array-format=comma --validator-query-object-format=brackets --validator-form-object-format=brackets${NC}" + echo -e " \$ ${YELLOW}npm exec --package=@stdy/cli@0.22.1 -- steady path/to/your.openapi.yml --host 127.0.0.1 -p 4010 --validator-query-array-format=comma --validator-form-array-format=comma --validator-query-object-format=brackets --validator-form-object-format=brackets${NC}" echo exit 1 diff --git a/src/browserbase/_base_client.py b/src/browserbase/_base_client.py index 5bc9823..bd88f59 100644 --- a/src/browserbase/_base_client.py +++ b/src/browserbase/_base_client.py @@ -540,6 +540,10 @@ def _build_request( files = cast(HttpxRequestFiles, ForceMultipartDict()) prepared_url = self._prepare_url(options.url) + # preserve hard-coded query params from the url + if params and prepared_url.query: + params = {**dict(prepared_url.params.items()), **params} + prepared_url = prepared_url.copy_with(raw_path=prepared_url.raw_path.split(b"?", 1)[0]) if "_" in prepared_url.host: # work around https://github.com/encode/httpx/discussions/2880 kwargs["extensions"] = {"sni_hostname": prepared_url.host.replace("_", "-")} diff --git a/src/browserbase/_files.py b/src/browserbase/_files.py index ff951be..83e91f6 100644 --- a/src/browserbase/_files.py +++ b/src/browserbase/_files.py @@ -3,8 +3,8 @@ import io import os import pathlib -from typing import overload -from typing_extensions import TypeGuard +from typing import Sequence, cast, overload +from typing_extensions import TypeVar, TypeGuard import anyio @@ -17,7 +17,9 @@ HttpxFileContent, HttpxRequestFiles, ) -from ._utils import is_tuple_t, is_mapping_t, is_sequence_t +from ._utils import is_list, is_mapping, is_tuple_t, is_mapping_t, is_sequence_t + +_T = TypeVar("_T") def is_base64_file_input(obj: object) -> TypeGuard[Base64FileInput]: @@ -121,3 +123,51 @@ async def async_read_file_content(file: FileContent) -> HttpxFileContent: return await anyio.Path(file).read_bytes() return file + + +def deepcopy_with_paths(item: _T, paths: Sequence[Sequence[str]]) -> _T: + """Copy only the containers along the given paths. + + Used to guard against mutation by extract_files without copying the entire structure. + Only dicts and lists that lie on a path are copied; everything else + is returned by reference. + + For example, given paths=[["foo", "files", "file"]] and the structure: + { + "foo": { + "bar": {"baz": {}}, + "files": {"file": } + } + } + The root dict, "foo", and "files" are copied (they lie on the path). + "bar" and "baz" are returned by reference (off the path). + """ + return _deepcopy_with_paths(item, paths, 0) + + +def _deepcopy_with_paths(item: _T, paths: Sequence[Sequence[str]], index: int) -> _T: + if not paths: + return item + if is_mapping(item): + key_to_paths: dict[str, list[Sequence[str]]] = {} + for path in paths: + if index < len(path): + key_to_paths.setdefault(path[index], []).append(path) + + # if no path continues through this mapping, it won't be mutated and copying it is redundant + if not key_to_paths: + return item + + result = dict(item) + for key, subpaths in key_to_paths.items(): + if key in result: + result[key] = _deepcopy_with_paths(result[key], subpaths, index + 1) + return cast(_T, result) + if is_list(item): + array_paths = [path for path in paths if index < len(path) and path[index] == ""] + + # if no path expects a list here, nothing will be mutated inside it - return by reference + if not array_paths: + return cast(_T, item) + return cast(_T, [_deepcopy_with_paths(entry, array_paths, index + 1) for entry in item]) + return item diff --git a/src/browserbase/_utils/__init__.py b/src/browserbase/_utils/__init__.py index 10cb66d..1c090e5 100644 --- a/src/browserbase/_utils/__init__.py +++ b/src/browserbase/_utils/__init__.py @@ -24,7 +24,6 @@ coerce_integer as coerce_integer, file_from_path as file_from_path, strip_not_given as strip_not_given, - deepcopy_minimal as deepcopy_minimal, get_async_library as get_async_library, maybe_coerce_float as maybe_coerce_float, get_required_header as get_required_header, diff --git a/src/browserbase/_utils/_utils.py b/src/browserbase/_utils/_utils.py index eec7f4a..771859f 100644 --- a/src/browserbase/_utils/_utils.py +++ b/src/browserbase/_utils/_utils.py @@ -86,8 +86,9 @@ def _extract_items( index += 1 if is_dict(obj): try: - # We are at the last entry in the path so we must remove the field - if (len(path)) == index: + # Remove the field if there are no more dict keys in the path, + # only "" traversal markers or end. + if all(p == "" for p in path[index:]): item = obj.pop(key) else: item = obj[key] @@ -176,21 +177,6 @@ def is_iterable(obj: object) -> TypeGuard[Iterable[object]]: return isinstance(obj, Iterable) -def deepcopy_minimal(item: _T) -> _T: - """Minimal reimplementation of copy.deepcopy() that will only copy certain object types: - - - mappings, e.g. `dict` - - list - - This is done for performance reasons. - """ - if is_mapping(item): - return cast(_T, {k: deepcopy_minimal(v) for k, v in item.items()}) - if is_list(item): - return cast(_T, [deepcopy_minimal(entry) for entry in item]) - return item - - # copied from https://github.com/Rapptz/RoboDanny def human_join(seq: Sequence[str], *, delim: str = ", ", final: str = "or") -> str: size = len(seq) diff --git a/src/browserbase/_version.py b/src/browserbase/_version.py index 10594de..eaa01ae 100644 --- a/src/browserbase/_version.py +++ b/src/browserbase/_version.py @@ -1,4 +1,4 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. __title__ = "browserbase" -__version__ = "1.8.0" # x-release-please-version +__version__ = "1.9.0" # x-release-please-version diff --git a/src/browserbase/resources/extensions.py b/src/browserbase/resources/extensions.py index 2d6fb1b..9325d6b 100644 --- a/src/browserbase/resources/extensions.py +++ b/src/browserbase/resources/extensions.py @@ -7,8 +7,9 @@ import httpx from ..types import extension_create_params +from .._files import deepcopy_with_paths from .._types import Body, Query, Headers, NoneType, NotGiven, FileTypes, not_given -from .._utils import extract_files, path_template, maybe_transform, deepcopy_minimal, async_maybe_transform +from .._utils import extract_files, path_template, maybe_transform, async_maybe_transform from .._compat import cached_property from .._resource import SyncAPIResource, AsyncAPIResource from .._response import ( @@ -66,7 +67,7 @@ def create( timeout: Override the client-level default timeout for this request, in seconds """ - body = deepcopy_minimal({"file": file}) + body = deepcopy_with_paths({"file": file}, [["file"]]) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) # It should be noted that the actual Content-Type header that will be # sent to the server will contain a `boundary` parameter, e.g. @@ -193,7 +194,7 @@ async def create( timeout: Override the client-level default timeout for this request, in seconds """ - body = deepcopy_minimal({"file": file}) + body = deepcopy_with_paths({"file": file}, [["file"]]) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) # It should be noted that the actual Content-Type header that will be # sent to the server will contain a `boundary` parameter, e.g. diff --git a/src/browserbase/resources/sessions/sessions.py b/src/browserbase/resources/sessions/sessions.py index 18bb0a7..ce3de98 100644 --- a/src/browserbase/resources/sessions/sessions.py +++ b/src/browserbase/resources/sessions/sessions.py @@ -255,7 +255,7 @@ def list( self, *, q: str | Omit = omit, - status: Literal["RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] | Omit = omit, + status: Literal["PENDING", "RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] | Omit = omit, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, @@ -527,7 +527,7 @@ async def list( self, *, q: str | Omit = omit, - status: Literal["RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] | Omit = omit, + status: Literal["PENDING", "RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] | Omit = omit, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, diff --git a/src/browserbase/resources/sessions/uploads.py b/src/browserbase/resources/sessions/uploads.py index 7c77602..f5d22d9 100644 --- a/src/browserbase/resources/sessions/uploads.py +++ b/src/browserbase/resources/sessions/uploads.py @@ -6,8 +6,9 @@ import httpx +from ..._files import deepcopy_with_paths from ..._types import Body, Query, Headers, NotGiven, FileTypes, not_given -from ..._utils import extract_files, path_template, maybe_transform, deepcopy_minimal, async_maybe_transform +from ..._utils import extract_files, path_template, maybe_transform, async_maybe_transform from ..._compat import cached_property from ..._resource import SyncAPIResource, AsyncAPIResource from ..._response import ( @@ -69,7 +70,7 @@ def create( """ if not id: raise ValueError(f"Expected a non-empty value for `id` but received {id!r}") - body = deepcopy_minimal({"file": file}) + body = deepcopy_with_paths({"file": file}, [["file"]]) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) # It should be noted that the actual Content-Type header that will be # sent to the server will contain a `boundary` parameter, e.g. @@ -132,7 +133,7 @@ async def create( """ if not id: raise ValueError(f"Expected a non-empty value for `id` but received {id!r}") - body = deepcopy_minimal({"file": file}) + body = deepcopy_with_paths({"file": file}, [["file"]]) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) # It should be noted that the actual Content-Type header that will be # sent to the server will contain a `boundary` parameter, e.g. diff --git a/src/browserbase/types/session.py b/src/browserbase/types/session.py index e983baa..eac6a81 100644 --- a/src/browserbase/types/session.py +++ b/src/browserbase/types/session.py @@ -32,7 +32,7 @@ class Session(BaseModel): started_at: datetime = FieldInfo(alias="startedAt") - status: Literal["RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] + status: Literal["PENDING", "RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] updated_at: datetime = FieldInfo(alias="updatedAt") diff --git a/src/browserbase/types/session_list_params.py b/src/browserbase/types/session_list_params.py index 54b0a05..c21b98e 100644 --- a/src/browserbase/types/session_list_params.py +++ b/src/browserbase/types/session_list_params.py @@ -16,4 +16,4 @@ class SessionListParams(TypedDict, total=False): for the schema of this query. """ - status: Literal["RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] + status: Literal["PENDING", "RUNNING", "ERROR", "TIMED_OUT", "COMPLETED"] diff --git a/tests/api_resources/test_sessions.py b/tests/api_resources/test_sessions.py index eb07d3f..78f99ce 100644 --- a/tests/api_resources/test_sessions.py +++ b/tests/api_resources/test_sessions.py @@ -189,7 +189,7 @@ def test_method_list(self, client: Browserbase) -> None: def test_method_list_with_all_params(self, client: Browserbase) -> None: session = client.sessions.list( q="q", - status="RUNNING", + status="PENDING", ) assert_matches_type(SessionListResponse, session, path=["response"]) @@ -423,7 +423,7 @@ async def test_method_list(self, async_client: AsyncBrowserbase) -> None: async def test_method_list_with_all_params(self, async_client: AsyncBrowserbase) -> None: session = await async_client.sessions.list( q="q", - status="RUNNING", + status="PENDING", ) assert_matches_type(SessionListResponse, session, path=["response"]) diff --git a/tests/test_client.py b/tests/test_client.py index 1d0d68b..95ae8e0 100644 --- a/tests/test_client.py +++ b/tests/test_client.py @@ -429,6 +429,30 @@ def test_default_query_option(self) -> None: client.close() + def test_hardcoded_query_params_in_url(self, client: Browserbase) -> None: + request = client._build_request(FinalRequestOptions(method="get", url="/foo?beta=true")) + url = httpx.URL(request.url) + assert dict(url.params) == {"beta": "true"} + + request = client._build_request( + FinalRequestOptions( + method="get", + url="/foo?beta=true", + params={"limit": "10", "page": "abc"}, + ) + ) + url = httpx.URL(request.url) + assert dict(url.params) == {"beta": "true", "limit": "10", "page": "abc"} + + request = client._build_request( + FinalRequestOptions( + method="get", + url="/files/a%2Fb?beta=true", + params={"limit": "10"}, + ) + ) + assert request.url.raw_path == b"/files/a%2Fb?beta=true&limit=10" + def test_request_extra_json(self, client: Browserbase) -> None: request = client._build_request( FinalRequestOptions( @@ -1330,6 +1354,30 @@ async def test_default_query_option(self) -> None: await client.close() + async def test_hardcoded_query_params_in_url(self, async_client: AsyncBrowserbase) -> None: + request = async_client._build_request(FinalRequestOptions(method="get", url="/foo?beta=true")) + url = httpx.URL(request.url) + assert dict(url.params) == {"beta": "true"} + + request = async_client._build_request( + FinalRequestOptions( + method="get", + url="/foo?beta=true", + params={"limit": "10", "page": "abc"}, + ) + ) + url = httpx.URL(request.url) + assert dict(url.params) == {"beta": "true", "limit": "10", "page": "abc"} + + request = async_client._build_request( + FinalRequestOptions( + method="get", + url="/files/a%2Fb?beta=true", + params={"limit": "10"}, + ) + ) + assert request.url.raw_path == b"/files/a%2Fb?beta=true&limit=10" + def test_request_extra_json(self, client: Browserbase) -> None: request = client._build_request( FinalRequestOptions( diff --git a/tests/test_deepcopy.py b/tests/test_deepcopy.py deleted file mode 100644 index a2a29e3..0000000 --- a/tests/test_deepcopy.py +++ /dev/null @@ -1,58 +0,0 @@ -from browserbase._utils import deepcopy_minimal - - -def assert_different_identities(obj1: object, obj2: object) -> None: - assert obj1 == obj2 - assert id(obj1) != id(obj2) - - -def test_simple_dict() -> None: - obj1 = {"foo": "bar"} - obj2 = deepcopy_minimal(obj1) - assert_different_identities(obj1, obj2) - - -def test_nested_dict() -> None: - obj1 = {"foo": {"bar": True}} - obj2 = deepcopy_minimal(obj1) - assert_different_identities(obj1, obj2) - assert_different_identities(obj1["foo"], obj2["foo"]) - - -def test_complex_nested_dict() -> None: - obj1 = {"foo": {"bar": [{"hello": "world"}]}} - obj2 = deepcopy_minimal(obj1) - assert_different_identities(obj1, obj2) - assert_different_identities(obj1["foo"], obj2["foo"]) - assert_different_identities(obj1["foo"]["bar"], obj2["foo"]["bar"]) - assert_different_identities(obj1["foo"]["bar"][0], obj2["foo"]["bar"][0]) - - -def test_simple_list() -> None: - obj1 = ["a", "b", "c"] - obj2 = deepcopy_minimal(obj1) - assert_different_identities(obj1, obj2) - - -def test_nested_list() -> None: - obj1 = ["a", [1, 2, 3]] - obj2 = deepcopy_minimal(obj1) - assert_different_identities(obj1, obj2) - assert_different_identities(obj1[1], obj2[1]) - - -class MyObject: ... - - -def test_ignores_other_types() -> None: - # custom classes - my_obj = MyObject() - obj1 = {"foo": my_obj} - obj2 = deepcopy_minimal(obj1) - assert_different_identities(obj1, obj2) - assert obj1["foo"] is my_obj - - # tuples - obj3 = ("a", "b") - obj4 = deepcopy_minimal(obj3) - assert obj3 is obj4 diff --git a/tests/test_extract_files.py b/tests/test_extract_files.py index 3c0fcb3..cd614d0 100644 --- a/tests/test_extract_files.py +++ b/tests/test_extract_files.py @@ -35,6 +35,15 @@ def test_multiple_files() -> None: assert query == {"documents": [{}, {}]} +def test_top_level_file_array() -> None: + query = {"files": [b"file one", b"file two"], "title": "hello"} + assert extract_files(query, paths=[["files", ""]]) == [ + ("files[]", b"file one"), + ("files[]", b"file two"), + ] + assert query == {"title": "hello"} + + @pytest.mark.parametrize( "query,paths,expected", [ diff --git a/tests/test_files.py b/tests/test_files.py index d8842d6..d1ccc25 100644 --- a/tests/test_files.py +++ b/tests/test_files.py @@ -4,7 +4,8 @@ import pytest from dirty_equals import IsDict, IsList, IsBytes, IsTuple -from browserbase._files import to_httpx_files, async_to_httpx_files +from browserbase._files import to_httpx_files, deepcopy_with_paths, async_to_httpx_files +from browserbase._utils import extract_files readme_path = Path(__file__).parent.parent.joinpath("README.md") @@ -49,3 +50,99 @@ def test_string_not_allowed() -> None: "file": "foo", # type: ignore } ) + + +def assert_different_identities(obj1: object, obj2: object) -> None: + assert obj1 == obj2 + assert obj1 is not obj2 + + +class TestDeepcopyWithPaths: + def test_copies_top_level_dict(self) -> None: + original = {"file": b"data", "other": "value"} + result = deepcopy_with_paths(original, [["file"]]) + assert_different_identities(result, original) + + def test_file_value_is_same_reference(self) -> None: + file_bytes = b"contents" + original = {"file": file_bytes} + result = deepcopy_with_paths(original, [["file"]]) + assert_different_identities(result, original) + assert result["file"] is file_bytes + + def test_list_popped_wholesale(self) -> None: + files = [b"f1", b"f2"] + original = {"files": files, "title": "t"} + result = deepcopy_with_paths(original, [["files", ""]]) + assert_different_identities(result, original) + result_files = result["files"] + assert isinstance(result_files, list) + assert_different_identities(result_files, files) + + def test_nested_array_path_copies_list_and_elements(self) -> None: + elem1 = {"file": b"f1", "extra": 1} + elem2 = {"file": b"f2", "extra": 2} + original = {"items": [elem1, elem2]} + result = deepcopy_with_paths(original, [["items", "", "file"]]) + assert_different_identities(result, original) + result_items = result["items"] + assert isinstance(result_items, list) + assert_different_identities(result_items, original["items"]) + assert_different_identities(result_items[0], elem1) + assert_different_identities(result_items[1], elem2) + + def test_empty_paths_returns_same_object(self) -> None: + original = {"foo": "bar"} + result = deepcopy_with_paths(original, []) + assert result is original + + def test_multiple_paths(self) -> None: + f1 = b"file1" + f2 = b"file2" + original = {"a": f1, "b": f2, "c": "unchanged"} + result = deepcopy_with_paths(original, [["a"], ["b"]]) + assert_different_identities(result, original) + assert result["a"] is f1 + assert result["b"] is f2 + assert result["c"] is original["c"] + + def test_extract_files_does_not_mutate_original_top_level(self) -> None: + file_bytes = b"contents" + original = {"file": file_bytes, "other": "value"} + + copied = deepcopy_with_paths(original, [["file"]]) + extracted = extract_files(copied, paths=[["file"]]) + + assert extracted == [("file", file_bytes)] + assert original == {"file": file_bytes, "other": "value"} + assert copied == {"other": "value"} + + def test_extract_files_does_not_mutate_original_nested_array_path(self) -> None: + file1 = b"f1" + file2 = b"f2" + original = { + "items": [ + {"file": file1, "extra": 1}, + {"file": file2, "extra": 2}, + ], + "title": "example", + } + + copied = deepcopy_with_paths(original, [["items", "", "file"]]) + extracted = extract_files(copied, paths=[["items", "", "file"]]) + + assert extracted == [("items[][file]", file1), ("items[][file]", file2)] + assert original == { + "items": [ + {"file": file1, "extra": 1}, + {"file": file2, "extra": 2}, + ], + "title": "example", + } + assert copied == { + "items": [ + {"extra": 1}, + {"extra": 2}, + ], + "title": "example", + }