Merge pull request #19 from CASParser/release-please--branches--main--changes--next

release: 1.8.0

Author: sameerkumar18

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "1.7.0"
+  ".": "1.8.0"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 21
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/cas-parser%2Fcas-parser-d9763d006969b49a1473851069fdfa429eb13133b64103a62963bb70ddb22305.yml
-openapi_spec_hash: 6aee689b7a759b12c85c088c15e29bc0
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/cas-parser%2Fcas-parser-e5c0c65637cdf3a6c4360b8193973b73a3d35ad1056ef607c3319ef03e591a55.yml
+openapi_spec_hash: 7515d1e5fe3130b9f5411f7aacbc8a64
 config_hash: 5509bb7a961ae2e79114b24c381606d4

CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## 1.8.0 (2026-04-19)
+
+Full Changelog: [v1.7.0...v1.8.0](https://github.com/CASParser/cas-parser-python/compare/v1.7.0...v1.8.0)
+
+### Features
+
+* **api:** api update ([78f7f97](https://github.com/CASParser/cas-parser-python/commit/78f7f97e1f17e44bc4443c43e92baf1888b2808a))
+* **api:** api update ([2e57117](https://github.com/CASParser/cas-parser-python/commit/2e571178acf86c879c727a43cff97ab4e05c1e2d))
+
+
+### Bug Fixes
+
+* **client:** preserve hardcoded query params when merging with user params ([3e5eea1](https://github.com/CASParser/cas-parser-python/commit/3e5eea1e92928bd98243022c607f6f15afa24d52))
+* ensure file data are only sent as 1 parameter ([4985a34](https://github.com/CASParser/cas-parser-python/commit/4985a349eee6f59007dfdf770c26deba75acc7dd))
+
+
+### Performance Improvements
+
+* **client:** optimize file structure copying in multipart requests ([1c854af](https://github.com/CASParser/cas-parser-python/commit/1c854af1baa2f1e702881692b65e9a85efffedd5))
+
 ## 1.7.0 (2026-03-27)
 
 Full Changelog: [v1.6.3...v1.7.0](https://github.com/CASParser/cas-parser-python/compare/v1.6.3...v1.7.0)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cas-parser-python"
-version = "1.7.0"
+version = "1.8.0"
 description = "The official Python library for the cas-parser API"
 dynamic = ["readme"]
 license = "Apache-2.0"

src/cas_parser/_base_client.py

@@ -558,6 +558,10 @@ 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("_", "-")}

src/cas_parser/_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": <content>}
+            }
+        }
+    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] == "<array>"]
+
+        # 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

src/cas_parser/_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,

src/cas_parser/_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 "<array>" traversal markers or end.
+            if all(p == "<array>" 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)

src/cas_parser/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "cas_parser"
-__version__ = "1.7.0"  # x-release-please-version
+__version__ = "1.8.0"  # x-release-please-version

src/cas_parser/resources/cams_kfintech.py

@@ -7,8 +7,9 @@
 import httpx
 
 from ..types import cams_kfintech_parse_params
+from .._files import deepcopy_with_paths
 from .._types import Body, Omit, Query, Headers, NotGiven, omit, not_given
-from .._utils import extract_files, maybe_transform, deepcopy_minimal, async_maybe_transform
+from .._utils import extract_files, maybe_transform, async_maybe_transform
 from .._compat import cached_property
 from .._resource import SyncAPIResource, AsyncAPIResource
 from .._response import (
@@ -78,12 +79,13 @@ def parse(
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
-        body = deepcopy_minimal(
+        body = deepcopy_with_paths(
             {
                 "password": password,
                 "pdf_file": pdf_file,
                 "pdf_url": pdf_url,
-            }
+            },
+            [["pdf_file"]],
         )
         files = extract_files(cast(Mapping[str, object], body), paths=[["pdf_file"]])
         if files:
@@ -157,12 +159,13 @@ async def parse(
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
-        body = deepcopy_minimal(
+        body = deepcopy_with_paths(
             {
                 "password": password,
                 "pdf_file": pdf_file,
                 "pdf_url": pdf_url,
-            }
+            },
+            [["pdf_file"]],
         )
         files = extract_files(cast(Mapping[str, object], body), paths=[["pdf_file"]])
         if files: