pangea-sdk 3.8.0__tar.gz → 3.8.0b2__tar.gz

{pangea_sdk-3.8.0 → pangea_sdk-3.8.0b2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pangea-sdk
-Version: 3.8.0
+Version: 3.8.0b2
 Summary: Pangea API SDK
 Home-page: https://pangea.cloud/docs/sdk/python/
 License: MIT
@@ -18,14 +18,13 @@ Classifier: Topic :: Software Development
 Classifier: Topic :: Software Development :: Libraries
 Requires-Dist: aiohttp (>=3.8.6,<4.0.0)
 Requires-Dist: asyncio (>=3.4.3,<4.0.0)
-Requires-Dist: cryptography (>=42.0.7,<43.0.0)
+Requires-Dist: cryptography (>=42.0.5,<43.0.0)
 Requires-Dist: deprecated (>=1.2.14,<2.0.0)
 Requires-Dist: google-crc32c (>=1.5.0,<2.0.0)
-Requires-Dist: pydantic (>=1.10.15,<2.0.0)
+Requires-Dist: pydantic (>=1.10.14,<2.0.0)
 Requires-Dist: python-dateutil (>=2.9.0,<3.0.0)
 Requires-Dist: requests (>=2.31.0,<3.0.0)
 Requires-Dist: requests-toolbelt (>=1.0.0,<2.0.0)
-Requires-Dist: typing-extensions (>=4.7.1,<5.0.0)
 Project-URL: Repository, https://github.com/pangeacyber/pangea-python/tree/main/packages/pangea-sdk
 Description-Content-Type: text/markdown
 
@@ -45,8 +44,6 @@ above.
 
 ## Installation
 
-#### GA releases
-
 Via pip:
 
 ```bash
@@ -59,32 +56,10 @@ Via poetry:
 $ poetry add pangea-sdk
 ```
 
-<a name="beta-releases"></a>
-
-#### Beta releases
-
-Pre-release versions may be available with the `b` (beta) denotation in the
-version number. These releases serve to preview beta services and APIs. Per
-Semantic Versioning, they are considered unstable and do not carry the same
-compatibility guarantees as stable releases. [Beta changelog](https://github.com/pangeacyber/pangea-python/blob/beta/CHANGELOG.md).
-
-Via pip:
-
-```bash
-$ pip3 install pangea-sdk==3.8.0b2
-```
-
-Via poetry:
-
-```bash
-$ poetry add pangea-sdk==3.8.0b2
-```
-
 ## Usage
 
 - [Documentation][]
-- [GA Examples][]
-- [Beta Examples][]
+- [Examples][]
 
 General usage would be to create a token for a service through the
 [Pangea Console][] and then construct an API client for that respective service.
@@ -143,6 +118,16 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+
+<a name="beta-releases"></a>
+
+## Beta releases
+
+Pre-release versions may be available with the `beta` denotation in the version
+number. These releases serve to preview beta services and APIs. Per Semantic
+Versioning, they are considered unstable and do not carry the same compatibility
+guarantees as stable releases.
+
 ## Secure Audit Log - Integrity Tools
 
 The Python Pangea SDK also includes some extra features to validate Audit Service log's integrity. Here we explain how to run them.
@@ -228,8 +213,7 @@ It accepts multiple file formats:
 
 
    [Documentation]: https://pangea.cloud/docs/sdk/python/
-   [GA Examples]: https://github.com/pangeacyber/pangea-python/tree/main/examples
-   [Beta Examples]: https://github.com/pangeacyber/pangea-python/tree/beta/examples
+   [Examples]: https://github.com/pangeacyber/pangea-python/tree/main/examples
    [Pangea Console]: https://console.pangea.cloud/
    [Slack]: https://pangea.cloud/join-slack/
    [Secure Audit Log]: https://pangea.cloud/docs/audit

{pangea_sdk-3.8.0 → pangea_sdk-3.8.0b2}/README.md

@@ -14,8 +14,6 @@ above.
 
 ## Installation
 
-#### GA releases
-
 Via pip:
 
 ```bash
@@ -28,32 +26,10 @@ Via poetry:
 $ poetry add pangea-sdk
 ```
 
-<a name="beta-releases"></a>
-
-#### Beta releases
-
-Pre-release versions may be available with the `b` (beta) denotation in the
-version number. These releases serve to preview beta services and APIs. Per
-Semantic Versioning, they are considered unstable and do not carry the same
-compatibility guarantees as stable releases. [Beta changelog](https://github.com/pangeacyber/pangea-python/blob/beta/CHANGELOG.md).
-
-Via pip:
-
-```bash
-$ pip3 install pangea-sdk==3.8.0b2
-```
-
-Via poetry:
-
-```bash
-$ poetry add pangea-sdk==3.8.0b2
-```
-
 ## Usage
 
 - [Documentation][]
-- [GA Examples][]
-- [Beta Examples][]
+- [Examples][]
 
 General usage would be to create a token for a service through the
 [Pangea Console][] and then construct an API client for that respective service.
@@ -112,6 +88,16 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+
+<a name="beta-releases"></a>
+
+## Beta releases
+
+Pre-release versions may be available with the `beta` denotation in the version
+number. These releases serve to preview beta services and APIs. Per Semantic
+Versioning, they are considered unstable and do not carry the same compatibility
+guarantees as stable releases.
+
 ## Secure Audit Log - Integrity Tools
 
 The Python Pangea SDK also includes some extra features to validate Audit Service log's integrity. Here we explain how to run them.
@@ -197,8 +183,7 @@ It accepts multiple file formats:
 
 
    [Documentation]: https://pangea.cloud/docs/sdk/python/
-   [GA Examples]: https://github.com/pangeacyber/pangea-python/tree/main/examples
-   [Beta Examples]: https://github.com/pangeacyber/pangea-python/tree/beta/examples
+   [Examples]: https://github.com/pangeacyber/pangea-python/tree/main/examples
    [Pangea Console]: https://console.pangea.cloud/
    [Slack]: https://pangea.cloud/join-slack/
    [Secure Audit Log]: https://pangea.cloud/docs/audit

{pangea_sdk-3.8.0 → pangea_sdk-3.8.0b2}/pangea/__init__.py

@@ -1,6 +1,7 @@
-__version__ = "3.8.0"
+__version__ = "3.8.0beta2"
 
 from pangea.asyncio.request import PangeaRequestAsync
 from pangea.config import PangeaConfig
+from pangea.file_uploader import FileUploader
 from pangea.request import PangeaRequest
 from pangea.response import PangeaResponse

pangea_sdk-3.8.0b2/pangea/asyncio/__init__.py

@@ -0,0 +1 @@
+from .file_uploader import FileUploaderAsync

pangea_sdk-3.8.0b2/pangea/asyncio/file_uploader.py

@@ -0,0 +1,39 @@
+# Copyright 2022 Pangea Cyber Corporation
+# Author: Pangea Cyber Corporation
+import io
+import logging
+from typing import Dict, Optional
+
+from pangea.asyncio.request import PangeaRequestAsync
+from pangea.request import PangeaConfig
+from pangea.response import TransferMethod
+
+
+class FileUploaderAsync:
+    def __init__(self) -> None:
+        self.logger = logging.getLogger("pangea")
+        self._request: PangeaRequestAsync = PangeaRequestAsync(
+            config=PangeaConfig(),
+            token="",
+            service="FileUploader",
+            logger=self.logger,
+        )
+
+    async def upload_file(
+        self,
+        url: str,
+        file: io.BufferedReader,
+        transfer_method: TransferMethod = TransferMethod.PUT_URL,
+        file_details: Optional[Dict] = None,
+    ) -> None:
+        if transfer_method == TransferMethod.PUT_URL:
+            files = [("file", ("filename", file, "application/octet-stream"))]
+            await self._request.put_presigned_url(url=url, files=files)  # type: ignore[arg-type]
+        elif transfer_method == TransferMethod.POST_URL:
+            files = [("file", ("filename", file, "application/octet-stream"))]
+            await self._request.post_presigned_url(url=url, data=file_details, files=files)  # type: ignore[arg-type]
+        else:
+            raise ValueError(f"Transfer method not supported: {transfer_method}")
+
+    async def close(self) -> None:
+        await self._request.session.close()

{pangea_sdk-3.8.0 → pangea_sdk-3.8.0b2}/pangea/asyncio/request.py

@@ -3,20 +3,18 @@
 
 import asyncio
 import json
+import os
 import time
 from typing import Dict, List, Optional, Tuple, Type, Union
 
 import aiohttp
 from aiohttp import FormData
-from typing_extensions import TypeVar
 
 import pangea.exceptions as pe
 from pangea.request import MultipartResponse, PangeaRequestBase
 from pangea.response import AttachedFile, PangeaResponse, PangeaResponseResult, ResponseStatus, TransferMethod
 from pangea.utils import default_encoder
 
-TResult = TypeVar("TResult", bound=PangeaResponseResult, default=PangeaResponseResult)
-
 
 class PangeaRequestAsync(PangeaRequestBase):
     """An object that makes direct calls to Pangea Service APIs.
@@ -30,12 +28,12 @@ class PangeaRequestAsync(PangeaRequestBase):
     async def post(
         self,
         endpoint: str,
-        result_class: Type[TResult],
+        result_class: Type[PangeaResponseResult],
         data: Union[str, Dict] = {},
         files: List[Tuple] = [],
         poll_result: bool = True,
         url: Optional[str] = None,
-    ) -> PangeaResponse[TResult]:
+    ) -> PangeaResponse:
         """Makes the POST call to a Pangea Service endpoint.
 
         Args:
@@ -93,7 +91,9 @@ class PangeaRequestAsync(PangeaRequestBase):
 
         return self._check_response(pangea_response)
 
-    async def get(self, path: str, result_class: Type[TResult], check_response: bool = True) -> PangeaResponse[TResult]:
+    async def get(
+        self, path: str, result_class: Type[PangeaResponseResult], check_response: bool = True
+    ) -> PangeaResponse[Type[PangeaResponseResult]]:
         """Makes the GET call to a Pangea Service endpoint.
 
         Args:
@@ -110,7 +110,7 @@ class PangeaRequestAsync(PangeaRequestBase):
 
         async with self.session.get(url, headers=self._headers()) as requests_response:
             await self._check_http_errors(requests_response)
-            pangea_response = PangeaResponse(
+            pangea_response = PangeaResponse(  # type: ignore[var-annotated]
                 requests_response, result_class=result_class, json=await requests_response.json()
             )
 
@@ -131,11 +131,11 @@ class PangeaRequestAsync(PangeaRequestBase):
             raise pe.ServiceTemporarilyUnavailable(await resp.json())
 
     async def poll_result_by_id(
-        self, request_id: str, result_class: Type[TResult], check_response: bool = True
-    ) -> PangeaResponse[TResult]:
+        self, request_id: str, result_class: Union[Type[PangeaResponseResult], Type[dict]], check_response: bool = True
+    ):
         path = self._get_poll_path(request_id)
         self.logger.debug(json.dumps({"service": self.service, "action": "poll_result_once", "url": path}))
-        return await self.get(path, result_class, check_response=check_response)
+        return await self.get(path, result_class, check_response=check_response)  # type: ignore[arg-type]
 
     async def poll_result_once(self, response: PangeaResponse, check_response: bool = True):
         request_id = response.request_id
@@ -180,6 +180,7 @@ class PangeaRequestAsync(PangeaRequestBase):
                     "service": self.service,
                     "action": "download_file",
                     "url": url,
+                    "filename": filename,
                     "status": "start",
                 }
             )
@@ -295,6 +296,9 @@ class PangeaRequestAsync(PangeaRequestBase):
             raise AttributeError("files attribute should have at least 1 file")
 
         response = await self.request_presigned_url(endpoint=endpoint, result_class=result_class, data=data)
+        if response.success:  # This should only happen when uploading a zero bytes file
+            return response.raw_response
+
         if response.accepted_result is None:
             raise pe.PangeaException("No accepted_result field when requesting presigned url")
         if response.accepted_result.post_url is None:
@@ -314,9 +318,8 @@ class PangeaRequestAsync(PangeaRequestBase):
     ) -> PangeaResponse:
         # Send request
         try:
-            # This should return 202 (AcceptedRequestException)
-            resp = await self.post(endpoint=endpoint, result_class=result_class, data=data, poll_result=False)
-            raise pe.PresignedURLException("Should return 202", resp)
+            # This should return 202 (AcceptedRequestException) at least zero size file is sent
+            return await self.post(endpoint=endpoint, result_class=result_class, data=data, poll_result=False)
         except pe.AcceptedRequestException as e:
             accepted_exception = e
         except Exception as e:
@@ -325,7 +328,9 @@ class PangeaRequestAsync(PangeaRequestBase):
         # Receive 202
         return await self._poll_presigned_url(accepted_exception.response)
 
-    async def _poll_presigned_url(self, response: PangeaResponse[TResult]) -> PangeaResponse[TResult]:
+    async def _poll_presigned_url(
+        self, response: PangeaResponse[Type[PangeaResponseResult]]
+    ) -> PangeaResponse[Type[PangeaResponseResult]]:
         if response.http_status != 202:
             raise AttributeError("Response should be 202")
 

{pangea_sdk-3.8.0 → pangea_sdk-3.8.0b2}/pangea/asyncio/services/__init__.py

@@ -1,8 +1,9 @@
 from .audit import AuditAsync
 from .authn import AuthNAsync
-from .authz import AuthZAsync
 from .embargo import EmbargoAsync
 from .file_scan import FileScanAsync
 from .intel import DomainIntelAsync, FileIntelAsync, IpIntelAsync, UrlIntelAsync, UserIntelAsync
 from .redact import RedactAsync
+from .share import ShareAsync
+from .sanitize import SanitizeAsync
 from .vault import VaultAsync

{pangea_sdk-3.8.0 → pangea_sdk-3.8.0b2}/pangea/asyncio/services/audit.py

@@ -1,14 +1,11 @@
 # Copyright 2022 Pangea Cyber Corporation
 # Author: Pangea Cyber Corporation
-from __future__ import annotations
-
 import datetime
-from typing import Any, Dict, List, Optional, Sequence, Union
+from typing import Any, Dict, List, Optional, Union
 
 import pangea.exceptions as pexc
 from pangea.asyncio.services.base import ServiceBaseAsync
-from pangea.config import PangeaConfig
-from pangea.response import PangeaResponse, PangeaResponseResult
+from pangea.response import PangeaResponse
 from pangea.services.audit.audit import AuditBase
 from pangea.services.audit.exceptions import AuditException
 from pangea.services.audit.models import (
@@ -16,7 +13,6 @@ from pangea.services.audit.models import (
     DownloadRequest,
     DownloadResult,
     Event,
-    ExportRequest,
     LogBulkResult,
     LogResult,
     PublishedRoot,
@@ -60,33 +56,14 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
 
     def __init__(
         self,
-        token: str,
-        config: PangeaConfig | None = None,
+        token,
+        config=None,
         private_key_file: str = "",
-        public_key_info: dict[str, str] = {},
-        tenant_id: str | None = None,
-        logger_name: str = "pangea",
-        config_id: str | None = None,
-    ) -> None:
-        """
-        Audit client
-
-        Initializes a new Audit client.
-
-        Args:
-            token: Pangea API token.
-            config: Configuration.
-            private_key_file: Private key filepath.
-            public_key_info: Public key information.
-            tenant_id: Tenant ID.
-            logger_name: Logger name.
-            config_id: Configuration ID.
-
-        Examples:
-             config = PangeaConfig(domain="pangea_domain")
-             audit = AuditAsync(token="pangea_token", config=config)
-        """
-
+        public_key_info: Dict[str, str] = {},
+        tenant_id: Optional[str] = None,
+        logger_name="pangea",
+        config_id: Optional[str] = None,
+    ):
         # FIXME: Temporary check to deprecate config_id from PangeaConfig.
         # Delete it when deprecate PangeaConfig.config_id
         if config_id and config is not None and config.config_id is not None:
@@ -295,7 +272,7 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
         end: Optional[Union[datetime.datetime, str]] = None,
         limit: Optional[int] = None,
         max_results: Optional[int] = None,
-        search_restriction: Optional[Dict[str, Sequence[str]]] = None,
+        search_restriction: Optional[dict] = None,
         verbose: Optional[bool] = None,
         verify_consistency: bool = False,
         verify_events: bool = True,
@@ -324,7 +301,7 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
             end (datetime, optional): An RFC-3339 formatted timestamp, or relative time adjustment from the current time.
             limit (int, optional): Optional[int] = None,
             max_results (int, optional): Maximum number of results to return.
-            search_restriction (Dict[str, Sequence[str]], optional): A list of keys to restrict the search results to. Useful for partitioning data available to the query string.
+            search_restriction (dict, optional): A list of keys to restrict the search results to. Useful for partitioning data available to the query string.
             verbose (bool, optional): If true, response include root and membership and consistency proofs.
             verify_consistency (bool): True to verify logs consistency
             verify_events (bool): True to verify hash events and signatures
@@ -370,7 +347,6 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
         id: str,
         limit: Optional[int] = 20,
         offset: Optional[int] = 0,
-        assert_search_restriction: Optional[Dict[str, Sequence[str]]] = None,
         verify_consistency: bool = False,
         verify_events: bool = True,
     ) -> PangeaResponse[SearchResultOutput]:
@@ -385,7 +361,6 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
             id (string): the id of a search action, found in `response.result.id`
             limit (integer, optional): the maximum number of results to return, default is 20
             offset (integer, optional): the position of the first result to return, default is 0
-            assert_search_restriction (Dict[str, Sequence[str]], optional): Assert the requested search results were queried with the exact same search restrictions, to ensure the results comply to the expected restrictions.
             verify_consistency (bool): True to verify logs consistency
             verify_events (bool): True to verify hash events and signatures
         Raises:
@@ -403,8 +378,7 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
             result_res: PangeaResponse[SearchResultsOutput] = audit.results(
                 id=search_res.result.id,
                 limit=10,
-                offset=0,
-                assert_search_restriction={'source': ["monitor"]})
+                offset=0)
         """
 
         if limit <= 0:  # type: ignore[operator]
@@ -417,7 +391,6 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
             id=id,
             limit=limit,
             offset=offset,
-            assert_search_restriction=assert_search_restriction,
         )
         response = await self.request.post("v1/results", SearchResultOutput, data=input.dict(exclude_none=True))
         if verify_consistency and response.result is not None:
@@ -425,107 +398,6 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
 
         return self.handle_results_response(response, verify_consistency, verify_events)
 
-    async def export(
-        self,
-        *,
-        format: DownloadFormat = DownloadFormat.CSV,
-        start: Optional[datetime.datetime] = None,
-        end: Optional[datetime.datetime] = None,
-        order: Optional[SearchOrder] = None,
-        order_by: Optional[str] = None,
-        verbose: bool = True,
-    ) -> PangeaResponse[PangeaResponseResult]:
-        """
-        Export from the audit log
-
-        Bulk export of data from the Secure Audit Log, with optional filtering.
-
-        OperationId: audit_post_v1_export
-
-        Args:
-            format: Format for the records.
-            start: The start of the time range to perform the search on.
-            end: The end of the time range to perform the search on. If omitted,
-                then all records up to the latest will be searched.
-            order: Specify the sort order of the response.
-            order_by: Name of column to sort the results by.
-            verbose: Whether or not to include the root hash of the tree and the
-                membership proof for each record.
-
-        Raises:
-            AuditException: If an audit based api exception happens
-            PangeaAPIException: If an API Error happens
-
-        Examples:
-            export_res = await audit.export(verbose=False)
-
-            # Export may take several dozens of minutes, so polling for the result
-            # should be done in a loop. That is omitted here for brevity's sake.
-            try:
-                await audit.poll_result(request_id=export_res.request_id)
-            except AcceptedRequestException:
-                # Retry later.
-
-            # Download the result when it's ready.
-            download_res = await audit.download_results(request_id=export_res.request_id)
-            download_res.result.dest_url
-            # => https://pangea-runtime.s3.amazonaws.com/audit/xxxxx/search_results_[...]
-        """
-        input = ExportRequest(
-            format=format,
-            start=start,
-            end=end,
-            order=order,
-            order_by=order_by,
-            verbose=verbose,
-        )
-        try:
-            return await self.request.post(
-                "v1/export", PangeaResponseResult, data=input.dict(exclude_none=True), poll_result=False
-            )
-        except pexc.AcceptedRequestException as e:
-            return e.response
-
-    async def log_stream(self, data: dict) -> PangeaResponse[PangeaResponseResult]:
-        """
-        Log streaming endpoint
-
-        This API allows 3rd party vendors (like Auth0) to stream events to this
-        endpoint where the structure of the payload varies across different
-        vendors.
-
-        OperationId: audit_post_v1_log_stream
-
-        Args:
-            data: Event data. The exact schema of this will vary by vendor.
-
-        Raises:
-            AuditException: If an audit based api exception happens
-            PangeaAPIException: If an API Error happens
-
-        Examples:
-            data = {
-                "logs": [
-                    {
-                        "log_id": "some log ID",
-                        "data": {
-                            "date": "2024-03-29T17:26:50.193Z",
-                            "type": "sapi",
-                            "description": "Create a log stream",
-                            "client_id": "some client ID",
-                            "ip": "127.0.0.1",
-                            "user_agent": "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0",
-                            "user_id": "some user ID",
-                        },
-                    }
-                    # ...
-                ]
-            }
-
-            response = await audit.log_stream(data)
-        """
-        return await self.request.post("v1/log_stream", PangeaResponseResult, data=data)
-
     async def root(self, tree_size: Optional[int] = None) -> PangeaResponse[RootResult]:
         """
         Tamperproof verification
@@ -551,10 +423,7 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
         return await self.request.post("v1/root", RootResult, data=input.dict(exclude_none=True))
 
     async def download_results(
-        self,
-        result_id: Optional[str] = None,
-        format: DownloadFormat = DownloadFormat.CSV,
-        request_id: Optional[str] = None,
+        self, result_id: str, format: Optional[DownloadFormat] = None
     ) -> PangeaResponse[DownloadResult]:
         """
         Download search results
@@ -566,7 +435,6 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
         Args:
             result_id: ID returned by the search API.
             format: Format for the records.
-            request_id: ID returned by the export API.
 
         Returns:
             URL where search results can be downloaded.
@@ -582,10 +450,7 @@ class AuditAsync(ServiceBaseAsync, AuditBase):
             )
         """
 
-        if request_id is None and result_id is None:
-            raise ValueError("must pass one of `request_id` or `result_id`")
-
-        input = DownloadRequest(request_id=request_id, result_id=result_id, format=format)
+        input = DownloadRequest(result_id=result_id, format=format)
         return await self.request.post("v1/download_results", DownloadResult, data=input.dict(exclude_none=True))
 
     async def update_published_roots(self, result: SearchResultOutput):