fix: use correct field name format for multipart file arrays

Author: stainless-app[bot]

src/cas_parser/_qs.py

@@ -2,17 +2,13 @@
 
 from typing import Any, List, Tuple, Union, Mapping, TypeVar
 from urllib.parse import parse_qs, urlencode
-from typing_extensions import Literal, get_args
+from typing_extensions import get_args
 
-from ._types import NotGiven, not_given
+from ._types import NotGiven, ArrayFormat, NestedFormat, not_given
 from ._utils import flatten
 
 _T = TypeVar("_T")
 
-
-ArrayFormat = Literal["comma", "repeat", "indices", "brackets"]
-NestedFormat = Literal["dots", "brackets"]
-
 PrimitiveData = Union[str, int, float, bool, None]
 # this should be Data = Union[PrimitiveData, "List[Data]", "Tuple[Data]", "Mapping[str, Data]"]
 # https://github.com/microsoft/pyright/issues/3555

src/cas_parser/_types.py

@@ -47,6 +47,9 @@
 ModelT = TypeVar("ModelT", bound=pydantic.BaseModel)
 _T = TypeVar("_T")
 
+ArrayFormat = Literal["comma", "repeat", "indices", "brackets"]
+NestedFormat = Literal["dots", "brackets"]
+
 
 # Approximates httpx internal ProxiesTypes and RequestFiles types
 # while adding support for `PathLike` instances

src/cas_parser/_utils/_utils.py

@@ -17,11 +17,11 @@
 )
 from pathlib import Path
 from datetime import date, datetime
-from typing_extensions import TypeGuard
+from typing_extensions import TypeGuard, get_args
 
 import sniffio
 
-from .._types import Omit, NotGiven, FileTypes, HeadersLike
+from .._types import Omit, NotGiven, FileTypes, ArrayFormat, HeadersLike
 
 _T = TypeVar("_T")
 _TupleT = TypeVar("_TupleT", bound=Tuple[object, ...])
@@ -40,25 +40,45 @@ def extract_files(
     query: Mapping[str, object],
     *,
     paths: Sequence[Sequence[str]],
+    array_format: ArrayFormat = "brackets",
 ) -> list[tuple[str, FileTypes]]:
     """Recursively extract files from the given dictionary based on specified paths.
 
     A path may look like this ['foo', 'files', '<array>', 'data'].
 
+    ``array_format`` controls how ``<array>`` segments contribute to the emitted
+    field name. Supported values: ``"brackets"`` (``foo[]``), ``"repeat"`` and
+    ``"comma"`` (``foo``), ``"indices"`` (``foo[0]``, ``foo[1]``).
+
     Note: this mutates the given dictionary.
     """
     files: list[tuple[str, FileTypes]] = []
     for path in paths:
-        files.extend(_extract_items(query, path, index=0, flattened_key=None))
+        files.extend(_extract_items(query, path, index=0, flattened_key=None, array_format=array_format))
     return files
 
 
+def _array_suffix(array_format: ArrayFormat, array_index: int) -> str:
+    if array_format == "brackets":
+        return "[]"
+    if array_format == "indices":
+        return f"[{array_index}]"
+    if array_format == "repeat" or array_format == "comma":
+        # Both repeat the bare field name for each file part; there is no
+        # meaningful way to comma-join binary parts.
+        return ""
+    raise NotImplementedError(
+        f"Unknown array_format value: {array_format}, choose from {', '.join(get_args(ArrayFormat))}"
+    )
+
+
 def _extract_items(
     obj: object,
     path: Sequence[str],
     *,
     index: int,
     flattened_key: str | None,
+    array_format: ArrayFormat,
 ) -> list[tuple[str, FileTypes]]:
     try:
         key = path[index]
@@ -75,9 +95,11 @@ def _extract_items(
 
         if is_list(obj):
             files: list[tuple[str, FileTypes]] = []
-            for entry in obj:
-                assert_is_file_content(entry, key=flattened_key + "[]" if flattened_key else "")
-                files.append((flattened_key + "[]", cast(FileTypes, entry)))
+            for array_index, entry in enumerate(obj):
+                suffix = _array_suffix(array_format, array_index)
+                emitted_key = (flattened_key + suffix) if flattened_key else suffix
+                assert_is_file_content(entry, key=emitted_key)
+                files.append((emitted_key, cast(FileTypes, entry)))
             return files
 
         assert_is_file_content(obj, key=flattened_key)
@@ -106,6 +128,7 @@ def _extract_items(
             path,
             index=index,
             flattened_key=flattened_key,
+            array_format=array_format,
         )
     elif is_list(obj):
         if key != "<array>":
@@ -117,9 +140,12 @@ def _extract_items(
                     item,
                     path,
                     index=index,
-                    flattened_key=flattened_key + "[]" if flattened_key is not None else "[]",
+                    flattened_key=(
+                        (flattened_key if flattened_key is not None else "") + _array_suffix(array_format, array_index)
+                    ),
+                    array_format=array_format,
                 )
-                for item in obj
+                for array_index, item in enumerate(obj)
             ]
         )
 

tests/test_extract_files.py

@@ -4,7 +4,7 @@
 
 import pytest
 
-from cas_parser._types import FileTypes
+from cas_parser._types import FileTypes, ArrayFormat
 from cas_parser._utils import extract_files
 
 
@@ -37,10 +37,7 @@ def test_multiple_files() -> None:
 
 def test_top_level_file_array() -> None:
     query = {"files": [b"file one", b"file two"], "title": "hello"}
-    assert extract_files(query, paths=[["files", "<array>"]]) == [
-        ("files[]", b"file one"),
-        ("files[]", b"file two"),
-    ]
+    assert extract_files(query, paths=[["files", "<array>"]]) == [("files[]", b"file one"), ("files[]", b"file two")]
     assert query == {"title": "hello"}
 
 
@@ -71,3 +68,24 @@ def test_ignores_incorrect_paths(
     expected: list[tuple[str, FileTypes]],
 ) -> None:
     assert extract_files(query, paths=paths) == expected
+
+
+@pytest.mark.parametrize(
+    "array_format,expected_top_level,expected_nested",
+    [
+        ("brackets", [("files[]", b"a"), ("files[]", b"b")], [("items[][file]", b"a"), ("items[][file]", b"b")]),
+        ("repeat", [("files", b"a"), ("files", b"b")], [("items[file]", b"a"), ("items[file]", b"b")]),
+        ("comma", [("files", b"a"), ("files", b"b")], [("items[file]", b"a"), ("items[file]", b"b")]),
+        ("indices", [("files[0]", b"a"), ("files[1]", b"b")], [("items[0][file]", b"a"), ("items[1][file]", b"b")]),
+    ],
+)
+def test_array_format_controls_file_field_names(
+    array_format: ArrayFormat,
+    expected_top_level: list[tuple[str, FileTypes]],
+    expected_nested: list[tuple[str, FileTypes]],
+) -> None:
+    top_level = {"files": [b"a", b"b"]}
+    assert extract_files(top_level, paths=[["files", "<array>"]], array_format=array_format) == expected_top_level
+
+    nested = {"items": [{"file": b"a"}, {"file": b"b"}]}
+    assert extract_files(nested, paths=[["items", "<array>", "file"]], array_format=array_format) == expected_nested

tests/test_files.py

@@ -131,7 +131,7 @@ def test_extract_files_does_not_mutate_original_nested_array_path(self) -> None:
         copied = deepcopy_with_paths(original, [["items", "<array>", "file"]])
         extracted = extract_files(copied, paths=[["items", "<array>", "file"]])
 
-        assert extracted == [("items[][file]", file1), ("items[][file]", file2)]
+        assert [entry for _, entry in extracted] == [file1, file2]
         assert original == {
             "items": [
                 {"file": file1, "extra": 1},