diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 60b11b0..ebba95f 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -1,12 +1,14 @@ name: CI on: push: - branches-ignore: - - 'generated' - - 'codegen/**' - - 'integrated/**' - - 'stl-preview-head/**' - - 'stl-preview-base/**' + branches: + - '**' + - '!integrated/**' + - '!stl-preview-head/**' + - '!stl-preview-base/**' + - '!generated' + - '!codegen/**' + - 'codegen/stl/**' pull_request: branches-ignore: - 'stl-preview-head/**' @@ -17,7 +19,7 @@ jobs: timeout-minutes: 10 name: lint runs-on: ${{ github.repository == 'stainless-sdks/zeroentropy-python' && 'depot-ubuntu-24.04' || 'ubuntu-latest' }} - if: github.event_name == 'push' || github.event.pull_request.head.repo.fork + if: (github.event_name == 'push' || github.event.pull_request.head.repo.fork) && (github.event_name != 'push' || github.event.head_commit.message != 'codegen metadata') steps: - uses: actions/checkout@v6 @@ -36,7 +38,7 @@ jobs: run: ./scripts/lint build: - if: github.event_name == 'push' || github.event.pull_request.head.repo.fork + if: (github.event_name == 'push' || github.event.pull_request.head.repo.fork) && (github.event_name != 'push' || github.event.head_commit.message != 'codegen metadata') timeout-minutes: 10 name: build permissions: @@ -61,14 +63,18 @@ jobs: run: rye build - name: Get GitHub OIDC Token - if: github.repository == 'stainless-sdks/zeroentropy-python' + if: |- + github.repository == 'stainless-sdks/zeroentropy-python' && + !startsWith(github.ref, 'refs/heads/stl/') id: github-oidc uses: actions/github-script@v8 with: script: core.setOutput('github_token', await core.getIDToken()); - name: Upload tarball - if: github.repository == 'stainless-sdks/zeroentropy-python' + if: |- + github.repository == 'stainless-sdks/zeroentropy-python' && + !startsWith(github.ref, 'refs/heads/stl/') env: URL: https://pkg.stainless.com/s AUTH: ${{ steps.github-oidc.outputs.github_token }} diff --git a/.gitignore b/.gitignore index 95ceb18..3824f4c 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,5 @@ .prism.log +.stdy.log _dev __pycache__ diff --git a/.release-please-manifest.json b/.release-please-manifest.json index ee49ac2..fd0ccba 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,3 +1,3 @@ { - ".": "0.1.0-alpha.11" + ".": "0.1.0-alpha.12" } \ No newline at end of file diff --git a/CHANGELOG.md b/CHANGELOG.md index 54812b2..60da096 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,48 @@ # Changelog +## 0.1.0-alpha.12 (2026-04-18) + +Full Changelog: [v0.1.0-alpha.11...v0.1.0-alpha.12](https://github.com/zeroentropy-ai/zeroentropy-python/compare/v0.1.0-alpha.11...v0.1.0-alpha.12) + +### Features + +* **internal:** implement indices array format for query and form serialization ([7afdedd](https://github.com/zeroentropy-ai/zeroentropy-python/commit/7afdedd66e2dff463aef37287e84596240d9ec3a)) + + +### Bug Fixes + +* **client:** preserve hardcoded query params when merging with user params ([bb86cc5](https://github.com/zeroentropy-ai/zeroentropy-python/commit/bb86cc51decf47d411f9959dee26996fd2ec501b)) +* **deps:** bump minimum typing-extensions version ([f4373a8](https://github.com/zeroentropy-ai/zeroentropy-python/commit/f4373a8d663cb8d2ca4212f77eade5269b518d1e)) +* ensure file data are only sent as 1 parameter ([ca9efb2](https://github.com/zeroentropy-ai/zeroentropy-python/commit/ca9efb2c1f815a83b97e922cbf361f0fedd1cbc5)) +* **pydantic:** do not pass `by_alias` unless set ([74ac1d3](https://github.com/zeroentropy-ai/zeroentropy-python/commit/74ac1d3f8dac62dc11de9550d88838d984301ca5)) +* sanitize endpoint path params ([a5a6035](https://github.com/zeroentropy-ai/zeroentropy-python/commit/a5a60354eabb5dce3a6a8c519311cd8590995179)) + + +### Performance Improvements + +* **client:** optimize file structure copying in multipart requests ([62638d4](https://github.com/zeroentropy-ai/zeroentropy-python/commit/62638d4e38f6dbe92abf136d98b105265eb3557f)) + + +### Chores + +* **ci:** skip lint on metadata-only changes ([ca93b8a](https://github.com/zeroentropy-ai/zeroentropy-python/commit/ca93b8ae56e0dddb8d49ecc21125c2a1751594c6)) +* **ci:** skip uploading artifacts on stainless-internal branches ([d6bb8a8](https://github.com/zeroentropy-ai/zeroentropy-python/commit/d6bb8a8306064729e4739209011106a6cc5e224f)) +* **internal:** tweak CI branches ([536468f](https://github.com/zeroentropy-ai/zeroentropy-python/commit/536468f4e298fb16e55818729b42fbc906a9d21f)) +* **internal:** update gitignore ([3009ce0](https://github.com/zeroentropy-ai/zeroentropy-python/commit/3009ce0201a8f99cb608182617796dc71e17a910)) +* **test:** do not count install time for mock server timeout ([ed8f79f](https://github.com/zeroentropy-ai/zeroentropy-python/commit/ed8f79f5b4c05cde5e12eb4c6a8137cc6b7dde74)) +* **tests:** bump steady to v0.19.4 ([814a31b](https://github.com/zeroentropy-ai/zeroentropy-python/commit/814a31b0de576a870d04e41ef0b52da726741311)) +* **tests:** bump steady to v0.19.5 ([f9bdfb4](https://github.com/zeroentropy-ai/zeroentropy-python/commit/f9bdfb48058be235113b6c19054a15e670d7c32b)) +* **tests:** bump steady to v0.19.6 ([9433bde](https://github.com/zeroentropy-ai/zeroentropy-python/commit/9433bde7d0d7953ad3f9a7327bf1468f30f6d600)) +* **tests:** bump steady to v0.19.7 ([e2ddebd](https://github.com/zeroentropy-ai/zeroentropy-python/commit/e2ddebd1af39af87aea48cc211b2b3520002f02c)) +* **tests:** bump steady to v0.20.1 ([4942675](https://github.com/zeroentropy-ai/zeroentropy-python/commit/494267565119547a125bc548f258bda341c1925c)) +* **tests:** bump steady to v0.20.2 ([73a8f04](https://github.com/zeroentropy-ai/zeroentropy-python/commit/73a8f04822fb42ddcbc63946b99801ca12c8e87e)) +* **tests:** bump steady to v0.22.1 ([9c3fcb6](https://github.com/zeroentropy-ai/zeroentropy-python/commit/9c3fcb69b97fdb396880759e5bea46f54e0dde99)) + + +### Refactors + +* **tests:** switch from prism to steady ([5465c72](https://github.com/zeroentropy-ai/zeroentropy-python/commit/5465c7207251fa90b2281a7429c2f0f078632b2e)) + ## 0.1.0-alpha.11 (2026-03-03) Full Changelog: [v0.1.0-alpha.10...v0.1.0-alpha.11](https://github.com/zeroentropy-ai/zeroentropy-python/compare/v0.1.0-alpha.10...v0.1.0-alpha.11) diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 7918a64..fd0d5fb 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -85,7 +85,7 @@ $ pip install ./path-to-wheel-file.whl ## Running tests -Most tests require you to [set up a mock server](https://github.com/stoplightio/prism) against the OpenAPI spec to run the tests. +Most tests require you to [set up a mock server](https://github.com/dgellow/steady) against the OpenAPI spec to run the tests. ```sh $ ./scripts/mock diff --git a/pyproject.toml b/pyproject.toml index 729d5d1..b9c4c44 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "zeroentropy" -version = "0.1.0-alpha.11" +version = "0.1.0-alpha.12" description = "The official Python library for the ZeroEntropy API" dynamic = ["readme"] license = "Apache-2.0" @@ -11,7 +11,7 @@ authors = [ dependencies = [ "httpx>=0.23.0, <1", "pydantic>=1.9.0, <3", - "typing-extensions>=4.10, <5", + "typing-extensions>=4.14, <5", "anyio>=3.5.0, <5", "distro>=1.7.0, <2", "sniffio", diff --git a/scripts/mock b/scripts/mock index 0b28f6e..feebe5e 100755 --- a/scripts/mock +++ b/scripts/mock @@ -19,23 +19,34 @@ fi echo "==> Starting mock server with URL ${URL}" -# Run prism mock on the given spec +# Run steady mock on the given spec if [ "$1" == "--daemon" ]; then - npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock "$URL" &> .prism.log & + # Pre-install the package so the download doesn't eat into the startup timeout + npm exec --package=@stdy/cli@0.22.1 -- steady --version - # Wait for server to come online + 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" - while ! grep -q "✖ fatal\|Prism is listening" ".prism.log" ; do + attempts=0 + while ! curl --silent --fail "http://127.0.0.1:4010/_x-steady/health" >/dev/null 2>&1; do + if ! kill -0 $! 2>/dev/null; then + echo + cat .stdy.log + exit 1 + fi + attempts=$((attempts + 1)) + if [ "$attempts" -ge 300 ]; then + echo + echo "Timed out waiting for Steady server to start" + cat .stdy.log + exit 1 + fi echo -n "." sleep 0.1 done - if grep -q "✖ fatal" ".prism.log"; then - cat .prism.log - exit 1 - fi - echo else - npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock "$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 "$URL" fi diff --git a/scripts/test b/scripts/test index dbeda2d..19acc91 100755 --- a/scripts/test +++ b/scripts/test @@ -9,8 +9,8 @@ GREEN='\033[0;32m' YELLOW='\033[0;33m' NC='\033[0m' # No Color -function prism_is_running() { - curl --silent "http://localhost:4010" >/dev/null 2>&1 +function steady_is_running() { + curl --silent "http://127.0.0.1:4010/_x-steady/health" >/dev/null 2>&1 } kill_server_on_port() { @@ -25,7 +25,7 @@ function is_overriding_api_base_url() { [ -n "$TEST_API_BASE_URL" ] } -if ! is_overriding_api_base_url && ! prism_is_running ; then +if ! is_overriding_api_base_url && ! steady_is_running ; then # When we exit this script, make sure to kill the background mock server process trap 'kill_server_on_port 4010' EXIT @@ -36,19 +36,19 @@ fi if is_overriding_api_base_url ; then echo -e "${GREEN}✔ Running tests against ${TEST_API_BASE_URL}${NC}" echo -elif ! prism_is_running ; then - echo -e "${RED}ERROR:${NC} The test suite will not run without a mock Prism server" +elif ! steady_is_running ; then + echo -e "${RED}ERROR:${NC} The test suite will not run without a mock Steady server" echo -e "running against your OpenAPI spec." echo echo -e "To run the server, pass in the path or url of your OpenAPI" - echo -e "spec to the prism command:" + echo -e "spec to the steady command:" echo - echo -e " \$ ${YELLOW}npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock path/to/your.openapi.yml${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 else - echo -e "${GREEN}✔ Mock prism server is running with your OpenAPI spec${NC}" + echo -e "${GREEN}✔ Mock steady server is running with your OpenAPI spec${NC}" echo fi diff --git a/src/zeroentropy/_base_client.py b/src/zeroentropy/_base_client.py index ddeaa86..e79904f 100644 --- a/src/zeroentropy/_base_client.py +++ b/src/zeroentropy/_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/zeroentropy/_compat.py b/src/zeroentropy/_compat.py index 786ff42..e6690a4 100644 --- a/src/zeroentropy/_compat.py +++ b/src/zeroentropy/_compat.py @@ -2,7 +2,7 @@ from typing import TYPE_CHECKING, Any, Union, Generic, TypeVar, Callable, cast, overload from datetime import date, datetime -from typing_extensions import Self, Literal +from typing_extensions import Self, Literal, TypedDict import pydantic from pydantic.fields import FieldInfo @@ -131,6 +131,10 @@ def model_json(model: pydantic.BaseModel, *, indent: int | None = None) -> str: return model.model_dump_json(indent=indent) +class _ModelDumpKwargs(TypedDict, total=False): + by_alias: bool + + def model_dump( model: pydantic.BaseModel, *, @@ -142,6 +146,9 @@ def model_dump( by_alias: bool | None = None, ) -> dict[str, Any]: if (not PYDANTIC_V1) or hasattr(model, "model_dump"): + kwargs: _ModelDumpKwargs = {} + if by_alias is not None: + kwargs["by_alias"] = by_alias return model.model_dump( mode=mode, exclude=exclude, @@ -149,7 +156,7 @@ def model_dump( exclude_defaults=exclude_defaults, # warnings are not supported in Pydantic v1 warnings=True if PYDANTIC_V1 else warnings, - by_alias=by_alias, + **kwargs, ) return cast( "dict[str, Any]", diff --git a/src/zeroentropy/_files.py b/src/zeroentropy/_files.py index cc14c14..0fdce17 100644 --- a/src/zeroentropy/_files.py +++ b/src/zeroentropy/_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/zeroentropy/_qs.py b/src/zeroentropy/_qs.py index ada6fd3..de8c99b 100644 --- a/src/zeroentropy/_qs.py +++ b/src/zeroentropy/_qs.py @@ -101,7 +101,10 @@ def _stringify_item( items.extend(self._stringify_item(key, item, opts)) return items elif array_format == "indices": - raise NotImplementedError("The array indices format is not supported yet") + items = [] + for i, item in enumerate(value): + items.extend(self._stringify_item(f"{key}[{i}]", item, opts)) + return items elif array_format == "brackets": items = [] key = key + "[]" diff --git a/src/zeroentropy/_utils/__init__.py b/src/zeroentropy/_utils/__init__.py index dc64e29..1c090e5 100644 --- a/src/zeroentropy/_utils/__init__.py +++ b/src/zeroentropy/_utils/__init__.py @@ -1,3 +1,4 @@ +from ._path import path_template as path_template from ._sync import asyncify as asyncify from ._proxy import LazyProxy as LazyProxy from ._utils import ( @@ -23,7 +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/zeroentropy/_utils/_path.py b/src/zeroentropy/_utils/_path.py new file mode 100644 index 0000000..4d6e1e4 --- /dev/null +++ b/src/zeroentropy/_utils/_path.py @@ -0,0 +1,127 @@ +from __future__ import annotations + +import re +from typing import ( + Any, + Mapping, + Callable, +) +from urllib.parse import quote + +# Matches '.' or '..' where each dot is either literal or percent-encoded (%2e / %2E). +_DOT_SEGMENT_RE = re.compile(r"^(?:\.|%2[eE]){1,2}$") + +_PLACEHOLDER_RE = re.compile(r"\{(\w+)\}") + + +def _quote_path_segment_part(value: str) -> str: + """Percent-encode `value` for use in a URI path segment. + + Considers characters not in `pchar` set from RFC 3986 §3.3 to be unsafe. + https://datatracker.ietf.org/doc/html/rfc3986#section-3.3 + """ + # quote() already treats unreserved characters (letters, digits, and -._~) + # as safe, so we only need to add sub-delims, ':', and '@'. + # Notably, unlike the default `safe` for quote(), / is unsafe and must be quoted. + return quote(value, safe="!$&'()*+,;=:@") + + +def _quote_query_part(value: str) -> str: + """Percent-encode `value` for use in a URI query string. + + Considers &, = and characters not in `query` set from RFC 3986 §3.4 to be unsafe. + https://datatracker.ietf.org/doc/html/rfc3986#section-3.4 + """ + return quote(value, safe="!$'()*+,;:@/?") + + +def _quote_fragment_part(value: str) -> str: + """Percent-encode `value` for use in a URI fragment. + + Considers characters not in `fragment` set from RFC 3986 §3.5 to be unsafe. + https://datatracker.ietf.org/doc/html/rfc3986#section-3.5 + """ + return quote(value, safe="!$&'()*+,;=:@/?") + + +def _interpolate( + template: str, + values: Mapping[str, Any], + quoter: Callable[[str], str], +) -> str: + """Replace {name} placeholders in `template`, quoting each value with `quoter`. + + Placeholder names are looked up in `values`. + + Raises: + KeyError: If a placeholder is not found in `values`. + """ + # re.split with a capturing group returns alternating + # [text, name, text, name, ..., text] elements. + parts = _PLACEHOLDER_RE.split(template) + + for i in range(1, len(parts), 2): + name = parts[i] + if name not in values: + raise KeyError(f"a value for placeholder {{{name}}} was not provided") + val = values[name] + if val is None: + parts[i] = "null" + elif isinstance(val, bool): + parts[i] = "true" if val else "false" + else: + parts[i] = quoter(str(values[name])) + + return "".join(parts) + + +def path_template(template: str, /, **kwargs: Any) -> str: + """Interpolate {name} placeholders in `template` from keyword arguments. + + Args: + template: The template string containing {name} placeholders. + **kwargs: Keyword arguments to interpolate into the template. + + Returns: + The template with placeholders interpolated and percent-encoded. + + Safe characters for percent-encoding are dependent on the URI component. + Placeholders in path and fragment portions are percent-encoded where the `segment` + and `fragment` sets from RFC 3986 respectively are considered safe. + Placeholders in the query portion are percent-encoded where the `query` set from + RFC 3986 §3.3 is considered safe except for = and & characters. + + Raises: + KeyError: If a placeholder is not found in `kwargs`. + ValueError: If resulting path contains /./ or /../ segments (including percent-encoded dot-segments). + """ + # Split the template into path, query, and fragment portions. + fragment_template: str | None = None + query_template: str | None = None + + rest = template + if "#" in rest: + rest, fragment_template = rest.split("#", 1) + if "?" in rest: + rest, query_template = rest.split("?", 1) + path_template = rest + + # Interpolate each portion with the appropriate quoting rules. + path_result = _interpolate(path_template, kwargs, _quote_path_segment_part) + + # Reject dot-segments (. and ..) in the final assembled path. The check + # runs after interpolation so that adjacent placeholders or a mix of static + # text and placeholders that together form a dot-segment are caught. + # Also reject percent-encoded dot-segments to protect against incorrectly + # implemented normalization in servers/proxies. + for segment in path_result.split("/"): + if _DOT_SEGMENT_RE.match(segment): + raise ValueError(f"Constructed path {path_result!r} contains dot-segment {segment!r} which is not allowed") + + result = path_result + if query_template is not None: + result += "?" + _interpolate(query_template, kwargs, _quote_query_part) + if fragment_template is not None: + result += "#" + _interpolate(fragment_template, kwargs, _quote_fragment_part) + + return result diff --git a/src/zeroentropy/_utils/_utils.py b/src/zeroentropy/_utils/_utils.py index eec7f4a..771859f 100644 --- a/src/zeroentropy/_utils/_utils.py +++ b/src/zeroentropy/_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/zeroentropy/_version.py b/src/zeroentropy/_version.py index 5361556..933f906 100644 --- a/src/zeroentropy/_version.py +++ b/src/zeroentropy/_version.py @@ -1,4 +1,4 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. __title__ = "zeroentropy" -__version__ = "0.1.0-alpha.11" # x-release-please-version +__version__ = "0.1.0-alpha.12" # x-release-please-version diff --git a/tests/test_client.py b/tests/test_client.py index 6582560..00abf52 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: ZeroEntropy) -> 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: ZeroEntropy) -> 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: AsyncZeroEntropy) -> 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: ZeroEntropy) -> None: request = client._build_request( FinalRequestOptions( diff --git a/tests/test_deepcopy.py b/tests/test_deepcopy.py deleted file mode 100644 index 8300d0e..0000000 --- a/tests/test_deepcopy.py +++ /dev/null @@ -1,58 +0,0 @@ -from zeroentropy._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 aedd4be..9ab1830 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 84448cb..1da7ff2 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 zeroentropy._files import to_httpx_files, async_to_httpx_files +from zeroentropy._files import to_httpx_files, deepcopy_with_paths, async_to_httpx_files +from zeroentropy._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", + } diff --git a/tests/test_utils/test_path.py b/tests/test_utils/test_path.py new file mode 100644 index 0000000..c5d6b2a --- /dev/null +++ b/tests/test_utils/test_path.py @@ -0,0 +1,89 @@ +from __future__ import annotations + +from typing import Any + +import pytest + +from zeroentropy._utils._path import path_template + + +@pytest.mark.parametrize( + "template, kwargs, expected", + [ + ("/v1/{id}", dict(id="abc"), "/v1/abc"), + ("/v1/{a}/{b}", dict(a="x", b="y"), "/v1/x/y"), + ("/v1/{a}{b}/path/{c}?val={d}#{e}", dict(a="x", b="y", c="z", d="u", e="v"), "/v1/xy/path/z?val=u#v"), + ("/{w}/{w}", dict(w="echo"), "/echo/echo"), + ("/v1/static", {}, "/v1/static"), + ("", {}, ""), + ("/v1/?q={n}&count=10", dict(n=42), "/v1/?q=42&count=10"), + ("/v1/{v}", dict(v=None), "/v1/null"), + ("/v1/{v}", dict(v=True), "/v1/true"), + ("/v1/{v}", dict(v=False), "/v1/false"), + ("/v1/{v}", dict(v=".hidden"), "/v1/.hidden"), # dot prefix ok + ("/v1/{v}", dict(v="file.txt"), "/v1/file.txt"), # dot in middle ok + ("/v1/{v}", dict(v="..."), "/v1/..."), # triple dot ok + ("/v1/{a}{b}", dict(a=".", b="txt"), "/v1/.txt"), # dot var combining with adjacent to be ok + ("/items?q={v}#{f}", dict(v=".", f=".."), "/items?q=.#.."), # dots in query/fragment are fine + ( + "/v1/{a}?query={b}", + dict(a="../../other/endpoint", b="a&bad=true"), + "/v1/..%2F..%2Fother%2Fendpoint?query=a%26bad%3Dtrue", + ), + ("/v1/{val}", dict(val="a/b/c"), "/v1/a%2Fb%2Fc"), + ("/v1/{val}", dict(val="a/b/c?query=value"), "/v1/a%2Fb%2Fc%3Fquery=value"), + ("/v1/{val}", dict(val="a/b/c?query=value&bad=true"), "/v1/a%2Fb%2Fc%3Fquery=value&bad=true"), + ("/v1/{val}", dict(val="%20"), "/v1/%2520"), # escapes escape sequences in input + # Query: slash and ? are safe, # is not + ("/items?q={v}", dict(v="a/b"), "/items?q=a/b"), + ("/items?q={v}", dict(v="a?b"), "/items?q=a?b"), + ("/items?q={v}", dict(v="a#b"), "/items?q=a%23b"), + ("/items?q={v}", dict(v="a b"), "/items?q=a%20b"), + # Fragment: slash and ? are safe + ("/docs#{v}", dict(v="a/b"), "/docs#a/b"), + ("/docs#{v}", dict(v="a?b"), "/docs#a?b"), + # Path: slash, ? and # are all encoded + ("/v1/{v}", dict(v="a/b"), "/v1/a%2Fb"), + ("/v1/{v}", dict(v="a?b"), "/v1/a%3Fb"), + ("/v1/{v}", dict(v="a#b"), "/v1/a%23b"), + # same var encoded differently by component + ( + "/v1/{v}?q={v}#{v}", + dict(v="a/b?c#d"), + "/v1/a%2Fb%3Fc%23d?q=a/b?c%23d#a/b?c%23d", + ), + ("/v1/{val}", dict(val="x?admin=true"), "/v1/x%3Fadmin=true"), # query injection + ("/v1/{val}", dict(val="x#admin"), "/v1/x%23admin"), # fragment injection + ], +) +def test_interpolation(template: str, kwargs: dict[str, Any], expected: str) -> None: + assert path_template(template, **kwargs) == expected + + +def test_missing_kwarg_raises_key_error() -> None: + with pytest.raises(KeyError, match="org_id"): + path_template("/v1/{org_id}") + + +@pytest.mark.parametrize( + "template, kwargs", + [ + ("{a}/path", dict(a=".")), + ("{a}/path", dict(a="..")), + ("/v1/{a}", dict(a=".")), + ("/v1/{a}", dict(a="..")), + ("/v1/{a}/path", dict(a=".")), + ("/v1/{a}/path", dict(a="..")), + ("/v1/{a}{b}", dict(a=".", b=".")), # adjacent vars → ".." + ("/v1/{a}.", dict(a=".")), # var + static → ".." + ("/v1/{a}{b}", dict(a="", b=".")), # empty + dot → "." + ("/v1/%2e/{x}", dict(x="ok")), # encoded dot in static text + ("/v1/%2e./{x}", dict(x="ok")), # mixed encoded ".." in static + ("/v1/.%2E/{x}", dict(x="ok")), # mixed encoded ".." in static + ("/v1/{v}?q=1", dict(v="..")), + ("/v1/{v}#frag", dict(v="..")), + ], +) +def test_dot_segment_rejected(template: str, kwargs: dict[str, Any]) -> None: + with pytest.raises(ValueError, match="dot-segment"): + path_template(template, **kwargs)