rapidata 1.8.3__py3-none-any.whl → 2.44.4__py3-none-any.whl

rapidata/api_client/models/zip_entry_file_wrapper.py

@@ -0,0 +1,151 @@
+# coding: utf-8
+
+"""
+    Rapidata.Dataset
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
+
+    The version of the OpenAPI document: v1
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr, field_validator
+from typing import Any, ClassVar, Dict, List, Optional
+from rapidata.api_client.models.file_asset_metadata_value import FileAssetMetadataValue
+from typing import Optional, Set
+from typing_extensions import Self
+
+class ZipEntryFileWrapper(BaseModel):
+    """
+    ZipEntryFileWrapper
+    """ # noqa: E501
+    t: StrictStr = Field(description="Discriminator value for ZipEntryFileWrapper", alias="_t")
+    name: Optional[StrictStr] = None
+    content_length: Optional[StrictInt] = Field(default=None, alias="contentLength")
+    content_type: Optional[StrictStr] = Field(default=None, alias="contentType")
+    is_in_memory: Optional[StrictBool] = Field(default=None, alias="isInMemory")
+    metadata: Optional[Dict[str, FileAssetMetadataValue]] = None
+    creator_id: Optional[StrictStr] = Field(default=None, alias="creatorId")
+    creator_mail: Optional[StrictStr] = Field(default=None, alias="creatorMail")
+    __properties: ClassVar[List[str]] = ["_t", "name", "contentLength", "contentType", "isInMemory", "metadata", "creatorId", "creatorMail"]
+
+    @field_validator('t')
+    def t_validate_enum(cls, value):
+        """Validates the enum"""
+        if value not in set(['ZipEntryFileWrapper']):
+            raise ValueError("must be one of enum values ('ZipEntryFileWrapper')")
+        return value
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of ZipEntryFileWrapper from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        * OpenAPI `readOnly` fields are excluded.
+        * OpenAPI `readOnly` fields are excluded.
+        * OpenAPI `readOnly` fields are excluded.
+        * OpenAPI `readOnly` fields are excluded.
+        * OpenAPI `readOnly` fields are excluded.
+        """
+        excluded_fields: Set[str] = set([
+            "name",
+            "content_length",
+            "content_type",
+            "is_in_memory",
+            "metadata",
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        # override the default output from pydantic by calling `to_dict()` of each value in metadata (dict)
+        _field_dict = {}
+        if self.metadata:
+            for _key_metadata in self.metadata:
+                if self.metadata[_key_metadata]:
+                    _field_dict[_key_metadata] = self.metadata[_key_metadata].to_dict()
+            _dict['metadata'] = _field_dict
+        # set to None if content_length (nullable) is None
+        # and model_fields_set contains the field
+        if self.content_length is None and "content_length" in self.model_fields_set:
+            _dict['contentLength'] = None
+
+        # set to None if content_type (nullable) is None
+        # and model_fields_set contains the field
+        if self.content_type is None and "content_type" in self.model_fields_set:
+            _dict['contentType'] = None
+
+        # set to None if creator_id (nullable) is None
+        # and model_fields_set contains the field
+        if self.creator_id is None and "creator_id" in self.model_fields_set:
+            _dict['creatorId'] = None
+
+        # set to None if creator_mail (nullable) is None
+        # and model_fields_set contains the field
+        if self.creator_mail is None and "creator_mail" in self.model_fields_set:
+            _dict['creatorMail'] = None
+
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of ZipEntryFileWrapper from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "_t": obj.get("_t") if obj.get("_t") is not None else 'ZipEntryFileWrapper',
+            "name": obj.get("name"),
+            "contentLength": obj.get("contentLength"),
+            "contentType": obj.get("contentType"),
+            "isInMemory": obj.get("isInMemory"),
+            "metadata": dict(
+                (_k, FileAssetMetadataValue.from_dict(_v))
+                for _k, _v in obj["metadata"].items()
+            )
+            if obj.get("metadata") is not None
+            else None,
+            "creatorId": obj.get("creatorId"),
+            "creatorMail": obj.get("creatorMail")
+        })
+        return _obj
+
+

rapidata/api_client/rest.py

@@ -1,115 +1,97 @@
 # coding: utf-8
 
 """
-    Rapidata.Dataset
+Rapidata Asset API
 
-    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
+The API for the Rapidata Asset service
 
-    The version of the OpenAPI document: v1
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
+The version of the OpenAPI document: v1
+Generated by OpenAPI Generator (https://openapi-generator.tech)
 
-    Do not edit the class manually.
+Do not edit the class manually.
 """  # noqa: E501
 
-
 import io
 import json
 import re
-import ssl
+from typing import Dict, Optional
 
-import urllib3
+import httpx
+from authlib.integrations.httpx_client import OAuth2Client
+from httpx import Timeout, ConnectError, Limits
 
 from rapidata.api_client.exceptions import ApiException, ApiValueError
 
-SUPPORTED_SOCKS_PROXIES = {"socks5", "socks5h", "socks4", "socks4a"}
-RESTResponseType = urllib3.HTTPResponse
-
-
-def is_socks_proxy_url(url):
-    if url is None:
-        return False
-    split_section = url.split("://")
-    if len(split_section) < 2:
-        return False
-    else:
-        return split_section[0].lower() in SUPPORTED_SOCKS_PROXIES
-
 
 class RESTResponse(io.IOBase):
 
-    def __init__(self, resp) -> None:
+    def __init__(self, resp: httpx.Response) -> None:
         self.response = resp
-        self.status = resp.status
-        self.reason = resp.reason
+        self.status = resp.status_code
+        self.reason = resp.reason_phrase
         self.data = None
 
     def read(self):
         if self.data is None:
-            self.data = self.response.data
+            self.data = self.response.content
         return self.data
 
-    def getheaders(self):
+    def getheaders(self) -> Dict[str, str]:
         """Returns a dictionary of the response headers."""
-        return self.response.headers
+        return dict(self.response.headers)
 
-    def getheader(self, name, default=None):
+    def getheader(self, name, default=None) -> Optional[str]:
         """Returns a given response header."""
         return self.response.headers.get(name, default)
 
 
-class RESTClientObject:
-
-    def __init__(self, configuration) -> None:
-        # urllib3.PoolManager will pass all kw parameters to connectionpool
-        # https://github.com/shazow/urllib3/blob/f9409436f83aeb79fbaf090181cd81b784f1b8ce/urllib3/poolmanager.py#L75  # noqa: E501
-        # https://github.com/shazow/urllib3/blob/f9409436f83aeb79fbaf090181cd81b784f1b8ce/urllib3/connectionpool.py#L680  # noqa: E501
-        # Custom SSL certificates and client certificates: http://urllib3.readthedocs.io/en/latest/advanced-usage.html  # noqa: E501
-
-        # cert_reqs
-        if configuration.verify_ssl:
-            cert_reqs = ssl.CERT_REQUIRED
-        else:
-            cert_reqs = ssl.CERT_NONE
-
-        pool_args = {
-            "cert_reqs": cert_reqs,
-            "ca_certs": configuration.ssl_ca_cert,
-            "cert_file": configuration.cert_file,
-            "key_file": configuration.key_file,
-        }
-        if configuration.assert_hostname is not None:
-            pool_args['assert_hostname'] = (
-                configuration.assert_hostname
-            )
-
-        if configuration.retries is not None:
-            pool_args['retries'] = configuration.retries
+RESTResponseType = RESTResponse
 
-        if configuration.tls_server_name:
-            pool_args['server_hostname'] = configuration.tls_server_name
 
+class RESTClientObject:
 
-        if configuration.socket_options is not None:
-            pool_args['socket_options'] = configuration.socket_options
+    def __init__(self, configuration) -> None:
+        self.configuration = configuration
 
-        if configuration.connection_pool_maxsize is not None:
-            pool_args['maxsize'] = configuration.connection_pool_maxsize
+        self.session: Optional[OAuth2Client] = None
 
-        # https pool manager
-        self.pool_manager: urllib3.PoolManager
+    def setup_oauth_client_credentials(
+        self, client_id: str, client_secret: str, token_endpoint: str, scope: str
+    ):
+        client_args = self._get_session_defaults()
+        self.session = OAuth2Client(
+            client_id=client_id,
+            client_secret=client_secret,
+            token_endpoint=token_endpoint,
+            scope=scope,
+            **client_args,
+        )
 
-        if configuration.proxy:
-            if is_socks_proxy_url(configuration.proxy):
-                from urllib3.contrib.socks import SOCKSProxyManager
-                pool_args["proxy_url"] = configuration.proxy
-                pool_args["headers"] = configuration.proxy_headers
-                self.pool_manager = SOCKSProxyManager(**pool_args)
+        try:
+            self.session.fetch_token()
+        except ConnectError as e:
+            if self._is_certificate_validation_error(e):
+                exit(self._get_ssl_verify_error_message())
             else:
-                pool_args["proxy_url"] = configuration.proxy
-                pool_args["proxy_headers"] = configuration.proxy_headers
-                self.pool_manager = urllib3.ProxyManager(**pool_args)
-        else:
-            self.pool_manager = urllib3.PoolManager(**pool_args)
+                raise
+
+    def setup_oauth_with_token(
+        self,
+        client_id: str | None,
+        client_secret: str | None,
+        token: dict,
+        token_endpoint: str,
+        leeway: int = 60,
+    ):
+        client_args = self._get_session_defaults()
+        self.session = OAuth2Client(
+            token=token,
+            token_endpoint=token_endpoint,
+            client_id=client_id,
+            client_secret=client_secret,
+            leeway=leeway,
+            **client_args,
+        )
 
     def request(
         self,
@@ -118,7 +100,7 @@ class RESTClientObject:
         headers=None,
         body=None,
         post_params=None,
-        _request_timeout=None
+        _request_timeout=None,
     ):
         """Perform requests.
 
@@ -135,15 +117,7 @@ class RESTClientObject:
                                  (connection, read) timeouts.
         """
         method = method.upper()
-        assert method in [
-            'GET',
-            'HEAD',
-            'DELETE',
-            'POST',
-            'PUT',
-            'PATCH',
-            'OPTIONS'
-        ]
+        assert method in ["GET", "HEAD", "DELETE", "POST", "PUT", "PATCH", "OPTIONS"]
 
         if post_params and body:
             raise ApiValueError(
@@ -153,105 +127,170 @@ class RESTClientObject:
         post_params = post_params or {}
         headers = headers or {}
 
+        if not self.session:
+            raise ApiValueError(
+                "OAuth2 session is not initialized. Please initialize it before making requests."
+            )
+
+        session = self.session
+
         timeout = None
         if _request_timeout:
             if isinstance(_request_timeout, (int, float)):
-                timeout = urllib3.Timeout(total=_request_timeout)
-            elif (
-                    isinstance(_request_timeout, tuple)
-                    and len(_request_timeout) == 2
-                ):
-                timeout = urllib3.Timeout(
-                    connect=_request_timeout[0],
-                    read=_request_timeout[1]
-                )
+                timeout = Timeout(timeout=_request_timeout)
+            elif isinstance(_request_timeout, tuple) and len(_request_timeout) == 2:
+                connect_timeout, read_timeout = _request_timeout
+                timeout = Timeout(timeout=connect_timeout, read=read_timeout)
 
         try:
-            # For `POST`, `PUT`, `PATCH`, `OPTIONS`, `DELETE`
-            if method in ['POST', 'PUT', 'PATCH', 'OPTIONS', 'DELETE']:
-
-                # no content type provided or payload is json
-                content_type = headers.get('Content-Type')
-                if (
-                    not content_type
-                    or re.search('json', content_type, re.IGNORECASE)
-                ):
+            if method in ["POST", "PUT", "PATCH", "OPTIONS", "DELETE"]:
+                content_type = headers.get("Content-Type")
+
+                if not content_type or re.search("json", content_type, re.IGNORECASE):
                     request_body = None
                     if body is not None:
                         request_body = json.dumps(body)
-                    r = self.pool_manager.request(
+                    r = session.request(
                         method,
                         url,
-                        body=request_body,
+                        content=request_body,
                         timeout=timeout,
                         headers=headers,
-                        preload_content=False
                     )
-                elif content_type == 'application/x-www-form-urlencoded':
-                    r = self.pool_manager.request(
-                        method,
-                        url,
-                        fields=post_params,
-                        encode_multipart=False,
-                        timeout=timeout,
-                        headers=headers,
-                        preload_content=False
+
+                elif content_type == "application/x-www-form-urlencoded":
+                    r = session.request(
+                        method, url, data=post_params, timeout=timeout, headers=headers
                     )
-                elif content_type == 'multipart/form-data':
-                    # must del headers['Content-Type'], or the correct
-                    # Content-Type which generated by urllib3 will be
-                    # overwritten.
-                    del headers['Content-Type']
-                    # Ensures that dict objects are serialized
-                    post_params = [(a, json.dumps(b)) if isinstance(b, dict) else (a,b) for a, b in post_params]
-                    r = self.pool_manager.request(
+
+                elif content_type == "multipart/form-data":
+                    del headers["Content-Type"]
+                    files = []
+                    data = {}
+
+                    for key, value in post_params:
+                        if isinstance(value, tuple) and len(value) >= 2:
+                            # This is a file tuple (filename, file_data, [content_type])
+                            filename, file_data = value[0], value[1]
+                            content_type = value[2] if len(value) > 2 else None
+                            files.append((key, (filename, file_data, content_type)))
+                        elif isinstance(value, dict):
+                            # JSON-serialize dictionary values
+                            if key in data:
+                                # If we already have this key, handle as needed
+                                # (convert to list or append to existing list)
+                                if not isinstance(data[key], list):
+                                    data[key] = [data[key]]
+                                data[key].append(json.dumps(value))
+                            else:
+                                data[key] = json.dumps(value)
+                        else:
+                            # Regular form data
+                            if key in data:
+                                if not isinstance(data[key], list):
+                                    data[key] = [data[key]]
+                                data[key].append(value)
+                            else:
+                                data[key] = value
+                    r = session.request(
                         method,
                         url,
-                        fields=post_params,
-                        encode_multipart=True,
+                        files=files,
+                        data=data,
                         timeout=timeout,
                         headers=headers,
-                        preload_content=False
                     )
-                # Pass a `string` parameter directly in the body to support
-                # other content types than JSON when `body` argument is
-                # provided in serialized form.
+
                 elif isinstance(body, str) or isinstance(body, bytes):
-                    r = self.pool_manager.request(
-                        method,
-                        url,
-                        body=body,
-                        timeout=timeout,
-                        headers=headers,
-                        preload_content=False
+                    r = session.request(
+                        method, url, content=body, timeout=timeout, headers=headers
                     )
-                elif headers['Content-Type'].startswith('text/') and isinstance(body, bool):
+
+                elif headers["Content-Type"].startswith("text/") and isinstance(
+                    body, bool
+                ):
                     request_body = "true" if body else "false"
-                    r = self.pool_manager.request(
+                    r = session.request(
                         method,
                         url,
-                        body=request_body,
-                        preload_content=False,
+                        content=request_body,
                         timeout=timeout,
-                        headers=headers)
+                        headers=headers,
+                    )
+
                 else:
-                    # Cannot generate the request from given parameters
-                    msg = """Cannot prepare a request message for provided
-                             arguments. Please check that your arguments match
-                             declared content type."""
+                    msg = """Cannot prepare a request message for provided arguments.
+                             Please check that your arguments match declared content type."""
                     raise ApiException(status=0, reason=msg)
-            # For `GET`, `HEAD`
+
             else:
-                r = self.pool_manager.request(
-                    method,
-                    url,
-                    fields={},
-                    timeout=timeout,
-                    headers=headers,
-                    preload_content=False
-                )
-        except urllib3.exceptions.SSLError as e:
+                r = session.request(method, url, timeout=timeout, headers=headers)
+
+        except httpx.HTTPError as e:
             msg = "\n".join([type(e).__name__, str(e)])
             raise ApiException(status=0, reason=msg)
 
+        except ConnectError as e:
+            if self._is_certificate_validation_error(e):
+                exit(self._get_ssl_verify_error_message())
+            else:
+                raise
+
         return RESTResponse(r)
+
+    def _get_session_defaults(self):
+        # Set connection pool limits to support high concurrency uploads
+        # Default httpx limits (max_connections=100, max_keepalive_connections=20)
+        # are too restrictive for parallel upload scenarios
+        limits = Limits(max_connections=200, max_keepalive_connections=200)
+
+        client_kwargs = {
+            "verify": (
+                self.configuration.ssl_ca_cert
+                if self.configuration.ssl_ca_cert
+                else self.configuration.verify_ssl
+            ),
+            "limits": limits,
+        }
+
+        if self.configuration.proxy:
+            client_kwargs["proxy"] = self.configuration.proxy
+
+            existing_headers = client_kwargs.pop("headers")
+            if self.configuration.proxy_headers:
+                for key, value in self.configuration.proxy_headers.items():
+                    existing_headers[key] = value
+            client_kwargs["headers"] = existing_headers
+
+        if self.configuration.retries is not None:
+            transport = httpx.HTTPTransport(
+                retries=self.configuration.retries, limits=limits
+            )
+            client_kwargs["transport"] = transport
+
+        return client_kwargs
+
+    @staticmethod
+    def _is_certificate_validation_error(error: ConnectError) -> bool:
+        """
+        Check if the error is related to certificate validation.
+        """
+        return error.args[0].startswith("[SSL: CERTIFICATE_VERIFY_FAILED]")
+
+    @staticmethod
+    def _get_ssl_verify_error_message() -> str:
+        return """
+        We encountered an issue while trying to verify the SSL certificate.
+        This often happens on macOS when using the default Python installation provided by Apple,
+        which lacks the required certificates to perform secure HTTPS requests.
+        To resolve this, please perform the following steps:
+        1. Make sure you are using the latest version of the Rapidata Package: `pip install --upgrade rapidata`
+        2. If you are using the default Python installation from Apple, consider switching to a different Python distribution, such as Homebrew or pyenv.
+        3. If you prefer to continue using the default Python, you can run the following command in your terminal:
+           `/Applications/Python\\ 3.1*/Install\\ Certificates.command`
+        
+        For more details on this issue, please refer to the following link:
+        https://stackoverflow.com/questions/42098126/mac-osx-python-ssl-sslerror-ssl-certificate-verify-failed-certificate-verify
+        
+        If the issue persists, please reach out to us at 'info@rapidata.ai', we're happy to help you.
+        """