dagster-sigma 0.0.1__tar.gz

dagster_sigma-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "{}"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2023 Dagster Labs, Inc.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

dagster_sigma-0.0.1/MANIFEST.in

@@ -0,0 +1,3 @@
+include README.md
+include LICENSE
+include dagster_sigma/py.typed

dagster_sigma-0.0.1/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.1
+Name: dagster_sigma
+Version: 0.0.1
+Summary: Build assets representing Sigma dashboards.
+Home-page: https://github.com/dagster-io/dagster/tree/master/python_modules/libraries/dagster-sigma
+Author: Dagster Labs
+Author-email: hello@dagsterlabs.com
+License: Apache-2.0
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8,<3.13
+License-File: LICENSE
+Requires-Dist: dagster
+Requires-Dist: sqlglot

dagster_sigma-0.0.1/README.md

@@ -0,0 +1,3 @@
+# dagster-sigma
+
+Experimental package for integrating with [Sigma](https://sigmacomputing.com).

dagster_sigma-0.0.1/dagster_sigma/__init__.py

@@ -0,0 +1,16 @@
+from dagster._core.libraries import DagsterLibraryRegistry
+
+from dagster_sigma.resource import (
+    SigmaBaseUrl as SigmaBaseUrl,
+    SigmaOrganization as SigmaOrganization,
+)
+from dagster_sigma.translator import (
+    DagsterSigmaTranslator as DagsterSigmaTranslator,
+    SigmaDataset as SigmaDataset,
+    SigmaWorkbook as SigmaWorkbook,
+)
+
+# Move back to version.py and edit setup.py once we are ready to publish.
+__version__ = "0.0.1"
+
+DagsterLibraryRegistry.register("dagster-sigma", __version__)

dagster_sigma-0.0.1/dagster_sigma/py.typed

@@ -0,0 +1 @@
+partial

dagster_sigma-0.0.1/dagster_sigma/resource.py

@@ -0,0 +1,295 @@
+from collections import defaultdict
+from enum import Enum
+from typing import Any, Dict, List, Mapping, Optional, Type
+
+import requests
+from dagster import ConfigurableResource
+from dagster._core.definitions.definitions_class import Definitions
+from dagster._core.definitions.definitions_loader import DefinitionsLoadContext, DefinitionsLoadType
+from dagster._serdes.serdes import deserialize_value, serialize_value
+from dagster._utils.cached_method import cached_method
+from pydantic import Field, PrivateAttr
+from sqlglot import exp, parse_one
+
+from dagster_sigma.translator import (
+    DagsterSigmaTranslator,
+    SigmaDataset,
+    SigmaOrganizationData,
+    SigmaWorkbook,
+    _inode_from_url,
+)
+
+SIGMA_PARTNER_ID_TAG = {"X-Sigma-Partner-Id": "dagster"}
+
+
+class SigmaBaseUrl(str, Enum):
+    """Enumeration of Sigma API base URLs for different cloud providers.
+
+    https://help.sigmacomputing.com/reference/get-started-sigma-api#identify-your-api-request-url
+    """
+
+    AWS_US = "https://aws-api.sigmacomputing.com"
+    AWS_CANADA = "https://api.ca.aws.sigmacomputing.com"
+    AWS_EUROPE = "https://api.eu.aws.sigmacomputing.com"
+    AWS_UK = "https://api.uk.aws.sigmacomputing.com"
+    AZURE_US = "https://api.us.azure.sigmacomputing.com"
+    GCP = "https://api.sigmacomputing.com"
+
+
+class SigmaOrganization(ConfigurableResource):
+    """Represents a workspace in Sigma and provides utilities
+    to interact with the Sigma API.
+    """
+
+    base_url: str = Field(
+        ...,
+        description=(
+            "Base URL for the cloud type of your Sigma organization, found under the Administration -> Account -> Site settings."
+            " See https://help.sigmacomputing.com/reference/get-started-sigma-api#identify-your-api-request-url for more information."
+        ),
+    )
+    client_id: str = Field(..., description="A client ID with access to the Sigma API.")
+    client_secret: str = Field(..., description="A client secret with access to the Sigma API.")
+
+    _api_token: Optional[str] = PrivateAttr(None)
+
+    def _fetch_api_token(self) -> str:
+        response = requests.post(
+            url=f"{self.base_url}/v2/auth/token",
+            headers={
+                "Accept": "application/json",
+                "Content-Type": "application/x-www-form-urlencoded",
+                **SIGMA_PARTNER_ID_TAG,
+            },
+            data={
+                "grant_type": "client_credentials",
+                "client_id": self.client_id,
+                "client_secret": self.client_secret,
+            },
+        )
+        response.raise_for_status()
+        return response.json()["access_token"]
+
+    @property
+    def api_token(self) -> str:
+        if self._api_token is None:
+            self._api_token = self._fetch_api_token()
+
+        return self._api_token
+
+    def fetch_json(self, endpoint: str, method: str = "GET") -> Dict[str, Any]:
+        response = requests.request(
+            method=method,
+            url=f"{self.base_url}/v2/{endpoint}",
+            headers={
+                "Accept": "application/json",
+                "Authorization": f"Bearer {self.api_token}",
+                **SIGMA_PARTNER_ID_TAG,
+            },
+        )
+        response.raise_for_status()
+        return response.json()
+
+    @cached_method
+    def fetch_workbooks(self) -> List[Dict[str, Any]]:
+        return self.fetch_json("workbooks")["entries"]
+
+    @cached_method
+    def fetch_datasets(self) -> List[Dict[str, Any]]:
+        return self.fetch_json("datasets")["entries"]
+
+    @cached_method
+    def fetch_pages_for_workbook(self, workbook_id: str) -> List[Dict[str, Any]]:
+        return self.fetch_json(f"workbooks/{workbook_id}/pages")["entries"]
+
+    @cached_method
+    def fetch_elements_for_page(self, workbook_id: str, page_id: str) -> List[Dict[str, Any]]:
+        return self.fetch_json(f"workbooks/{workbook_id}/pages/{page_id}/elements")["entries"]
+
+    @cached_method
+    def fetch_lineage_for_element(self, workbook_id: str, element_id: str) -> Dict[str, Any]:
+        return self.fetch_json(f"workbooks/{workbook_id}/lineage/elements/{element_id}")
+
+    @cached_method
+    def fetch_columns_for_element(self, workbook_id: str, element_id: str) -> List[Dict[str, Any]]:
+        return self.fetch_json(f"workbooks/{workbook_id}/elements/{element_id}/columns")["entries"]
+
+    @cached_method
+    def fetch_queries_for_workbook(self, workbook_id: str) -> List[Dict[str, Any]]:
+        return self.fetch_json(f"workbooks/{workbook_id}/queries")["entries"]
+
+    @cached_method
+    def fetch_dataset_upstreams_by_inode(self) -> Mapping[str, AbstractSet[str]]:
+        """Builds a mapping of dataset inodes to the upstream inputs they depend on.
+        Sigma does not expose this information directly, so we have to infer it from
+        the lineage of workbooks and the workbook queries.
+        """
+        deps_by_dataset_inode = defaultdict(set)
+
+        raw_workbooks = self.fetch_workbooks()
+
+        # We first figure out which tables/visualizations ("elements") in each workbook
+        # depend on which datasets.
+        for workbook in raw_workbooks:
+            queries = self.fetch_queries_for_workbook(workbook["workbookId"])
+            queries_by_element_id = defaultdict(list)
+            for query in queries:
+                queries_by_element_id[query["elementId"]].append(query)
+
+            pages = self.fetch_pages_for_workbook(workbook["workbookId"])
+
+            for page in pages:
+                elements = self.fetch_elements_for_page(workbook["workbookId"], page["pageId"])
+                for element in elements:
+                    # We extract the list of dataset dependencies from the lineage of each element
+                    # If there is a single dataset dependency, we can then know the queries for that element
+                    # are associated with that dataset
+                    lineage = self.fetch_lineage_for_element(
+                        workbook["workbookId"], element["elementId"]
+                    )
+                    dataset_dependencies = [
+                        dep
+                        for dep in lineage["dependencies"].values()
+                        if dep.get("type") == "dataset"
+                    ]
+                    if len(dataset_dependencies) != 1:
+                        continue
+
+                    inode = dataset_dependencies[0]["nodeId"]
+                    for query in queries_by_element_id[element["elementId"]]:
+                        # Use sqlglot to extract the tables used in each query and add them to the dataset's
+                        # list of dependencies
+                        table_deps = set(
+                            [
+                                f"{table.catalog}.{table.db}.{table.this}"
+                                for table in list(parse_one(query["sql"]).find_all(exp.Table))
+                                if table.catalog
+                            ]
+                        )
+
+                        deps_by_dataset_inode[inode] = deps_by_dataset_inode[inode].union(
+                            table_deps
+                        )
+
+        return deps_by_dataset_inode
+
+    @cached_method
+    def fetch_dataset_columns_by_inode(self) -> Mapping[str, AbstractSet[str]]:
+        """Builds a mapping of dataset inodes to the columns they contain. Note that
+        this is a partial list and will only include columns which are referenced in
+        workbooks, since Sigma does not expose a direct API for querying dataset columns.
+        """
+        columns_by_dataset_inode = defaultdict(set)
+
+        for workbook in self.fetch_workbooks():
+            pages = self.fetch_pages_for_workbook(workbook["workbookId"])
+            for page in pages:
+                elements = self.fetch_elements_for_page(workbook["workbookId"], page["pageId"])
+                for element in elements:
+                    # We can't query the list of columns in a dataset directly, so we have to build a partial
+                    # list from the columns which appear in any workbook.
+                    columns = self.fetch_columns_for_element(
+                        workbook["workbookId"], element["elementId"]
+                    )
+                    for column in columns:
+                        split = column["columnId"].split("/")
+                        if len(split) == 2:
+                            inode, column_name = split
+                        columns_by_dataset_inode[inode].add(column_name)
+
+        return columns_by_dataset_inode
+
+    @cached_method
+    def build_organization_data(self) -> SigmaOrganizationData:
+        """Retrieves all workbooks and datasets in the Sigma organization and builds a
+        SigmaOrganizationData object representing the organization's assets.
+        """
+        raw_workbooks = self.fetch_workbooks()
+
+        workbooks: List[SigmaWorkbook] = []
+        for workbook in raw_workbooks:
+            workbook_deps = set()
+            pages = self.fetch_pages_for_workbook(workbook["workbookId"])
+            for page in pages:
+                elements = self.fetch_elements_for_page(workbook["workbookId"], page["pageId"])
+                for element in elements:
+                    # We extract the list of dataset dependencies from the lineage of each workbook.
+                    lineage = self.fetch_lineage_for_element(
+                        workbook["workbookId"], element["elementId"]
+                    )
+                    for inode, item in lineage["dependencies"].items():
+                        if item.get("type") == "dataset":
+                            workbook_deps.add(item["nodeId"])
+
+            workbooks.append(SigmaWorkbook(properties=workbook, datasets=workbook_deps))
+
+        datasets: List[SigmaDataset] = []
+        deps_by_dataset_inode = self.fetch_dataset_upstreams_by_inode()
+        columns_by_dataset_inode = self.fetch_dataset_columns_by_inode()
+
+        for dataset in self.fetch_datasets():
+            inode = _inode_from_url(dataset["url"])
+            datasets.append(
+                SigmaDataset(
+                    properties=dataset,
+                    columns=columns_by_dataset_inode.get(inode, set()),
+                    inputs=deps_by_dataset_inode[inode],
+                )
+            )
+
+        return SigmaOrganizationData(workbooks=workbooks, datasets=datasets)
+
+    @property
+    def reconstruction_metadata_key(self) -> str:
+        return f"sigma_{self.client_id}"
+
+    def build_defs(
+        self,
+        context: DefinitionsLoadContext,
+        dagster_sigma_translator: Type[DagsterSigmaTranslator] = DagsterSigmaTranslator,
+    ) -> Definitions:
+        """Returns a Definitions object representing the Sigma content in the organization.
+
+        Args:
+            context (DefinitionsLoadContext): The context in which the definitions are being loaded.
+            dagster_sigma_translator (Type[DagsterSigmaTranslator]): The translator to use
+                to convert Sigma content into AssetSpecs. Defaults to DagsterSigmaTranslator.
+
+        Returns:
+            Definitions: The set of assets representing the Sigma content in the organization.
+        """
+        # Attempt to load cached data from the context.
+        if (
+            context.load_type == DefinitionsLoadType.RECONSTRUCTION
+            and self.reconstruction_metadata_key in context.reconstruction_metadata
+        ):
+            cached_data = context.reconstruction_metadata[self.reconstruction_metadata_key]
+            workbooks = [
+                deserialize_value(workbook, as_type=SigmaWorkbook)
+                for workbook in cached_data["workbooks"]
+            ]
+            datasets = [
+                deserialize_value(dataset, as_type=SigmaDataset)
+                for dataset in cached_data["datasets"]
+            ]
+        else:
+            organization_data = self.build_organization_data()
+            workbooks = organization_data.workbooks
+            datasets = organization_data.datasets
+            cached_data = {
+                "workbooks": [serialize_value(workbook) for workbook in workbooks],
+                "datasets": [serialize_value(dataset) for dataset in datasets],
+            }
+
+        org_data = SigmaOrganizationData(workbooks=workbooks, datasets=datasets)
+
+        translator = dagster_sigma_translator(context=org_data)
+
+        asset_specs = [
+            *[translator.get_workbook_spec(workbook) for workbook in org_data.workbooks],
+            *[translator.get_dataset_spec(dataset) for dataset in org_data.datasets],
+        ]
+
+        return Definitions(assets=asset_specs).with_reconstruction_metadata(
+            {self.reconstruction_metadata_key: cached_data}
+        )

dagster_sigma-0.0.1/dagster_sigma/translator.py

@@ -0,0 +1,118 @@
+import re
+from typing import AbstractSet, Any, Dict, List
+
+from dagster import AssetKey, AssetSpec, MetadataValue, TableSchema
+from dagster._core.definitions.metadata.metadata_set import TableMetadataSet
+from dagster._core.definitions.metadata.table import TableColumn
+from dagster._core.definitions.tags import build_kind_tag
+from dagster._record import record
+from dagster._serdes.serdes import whitelist_for_serdes
+from dagster._utils.cached_method import cached_method
+from dagster._vendored.dateutil.parser import isoparse
+
+
+def _clean_asset_name(name: str) -> str:
+    """Cleans an input to be a valid Dagster asset name."""
+    return re.sub(r"[^A-Za-z0-9_]+", "_", name)
+
+
+def _inode_from_url(url: str) -> str:
+    """Builds a Sigma internal inode value from a Sigma URL."""
+    return f'inode-{url.split("/")[-1]}'
+
+
+@whitelist_for_serdes
+@record
+class SigmaWorkbook:
+    """Represents a Sigma workbook, a collection of visualizations and queries
+    for data exploration and analysis.
+
+    https://help.sigmacomputing.com/docs/workbooks
+    """
+
+    properties: Dict[str, Any]
+    datasets: AbstractSet[str]
+
+
+@whitelist_for_serdes
+@record
+class SigmaDataset:
+    """Represents a Sigma dataset, a centralized data definition which can
+    contain aggregations or other manipulations.
+
+    https://help.sigmacomputing.com/docs/datasets
+    """
+
+    properties: Dict[str, Any]
+    columns: AbstractSet[str]
+    inputs: AbstractSet[str]
+
+
+@record
+class SigmaOrganizationData:
+    workbooks: List[SigmaWorkbook]
+    datasets: List[SigmaDataset]
+
+    @cached_method
+    def get_datasets_by_inode(self) -> Dict[str, SigmaDataset]:
+        return {_inode_from_url(dataset.properties["url"]): dataset for dataset in self.datasets}
+
+
+class DagsterSigmaTranslator:
+    """Translator class which converts raw response data from the Sigma API into AssetSpecs.
+    Subclass this class to provide custom translation logic.
+    """
+
+    def __init__(self, context: SigmaOrganizationData):
+        self._context = context
+
+    @property
+    def organization_data(self) -> SigmaOrganizationData:
+        return self._context
+
+    def get_workbook_key(self, data: SigmaWorkbook) -> AssetKey:
+        return AssetKey(_clean_asset_name(data.properties["name"]))
+
+    def get_workbook_spec(self, data: SigmaWorkbook) -> AssetSpec:
+        metadata = {
+            "dagster_sigma/web_url": MetadataValue.url(data.properties["url"]),
+            "dagster_sigma/version": data.properties["latestVersion"],
+            "dagster_sigma/created_at": MetadataValue.timestamp(
+                isoparse(data.properties["createdAt"])
+            ),
+        }
+        datasets = [self._context.get_datasets_by_inode()[inode] for inode in data.datasets]
+        return AssetSpec(
+            key=self.get_workbook_key(data),
+            metadata=metadata,
+            tags={
+                **build_kind_tag("sigma"),
+            },
+            deps={self.get_dataset_key(dataset) for dataset in datasets},
+        )
+
+    def get_dataset_key(self, data: SigmaDataset) -> AssetKey:
+        return AssetKey(_clean_asset_name(data.properties["name"]))
+
+    def get_dataset_spec(self, data: SigmaDataset) -> AssetSpec:
+        metadata = {
+            "dagster_sigma/web_url": MetadataValue.url(data.properties["url"]),
+            "dagster_sigma/created_at": MetadataValue.timestamp(
+                isoparse(data.properties["createdAt"])
+            ),
+            **TableMetadataSet(
+                column_schema=TableSchema(
+                    columns=[TableColumn(name=column_name) for column_name in sorted(data.columns)]
+                )
+            ),
+        }
+
+        return AssetSpec(
+            key=self.get_dataset_key(data),
+            metadata=metadata,
+            tags={
+                **build_kind_tag("sigma"),
+            },
+            deps={AssetKey(input_name.lower().split(".")) for input_name in data.inputs},
+            description=data.properties.get("description"),
+        )

dagster_sigma-0.0.1/dagster_sigma.egg-info/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.1
+Name: dagster_sigma
+Version: 0.0.1
+Summary: Build assets representing Sigma dashboards.
+Home-page: https://github.com/dagster-io/dagster/tree/master/python_modules/libraries/dagster-sigma
+Author: Dagster Labs
+Author-email: hello@dagsterlabs.com
+License: Apache-2.0
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8,<3.13
+License-File: LICENSE
+Requires-Dist: dagster
+Requires-Dist: sqlglot

dagster_sigma-0.0.1/dagster_sigma.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+MANIFEST.in
+README.md
+setup.cfg
+setup.py
+dagster_sigma/__init__.py
+dagster_sigma/py.typed
+dagster_sigma/resource.py
+dagster_sigma/translator.py
+dagster_sigma.egg-info/PKG-INFO
+dagster_sigma.egg-info/SOURCES.txt
+dagster_sigma.egg-info/dependency_links.txt
+dagster_sigma.egg-info/not-zip-safe
+dagster_sigma.egg-info/requires.txt
+dagster_sigma.egg-info/top_level.txt

dagster_sigma-0.0.1/dagster_sigma.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dagster_sigma-0.0.1/dagster_sigma.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

dagster_sigma-0.0.1/dagster_sigma.egg-info/requires.txt

@@ -0,0 +1,2 @@
+dagster
+sqlglot

dagster_sigma-0.0.1/dagster_sigma.egg-info/top_level.txt

@@ -0,0 +1 @@
+dagster_sigma

dagster_sigma-0.0.1/setup.cfg

@@ -0,0 +1,14 @@
+[metadata]
+license_files = LICENSE
+
+[check-manifest]
+ignore = 
+	.coveragerc
+	tox.ini
+	pytest.ini
+	dagster_sigma_tests/**
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

dagster_sigma-0.0.1/setup.py

@@ -0,0 +1,45 @@
+from setuptools import find_packages, setup
+
+
+def get_version() -> str:
+    return "0.0.1"
+    # Uncomment when ready to publish
+    # version: Dict[str, str] = {}
+    # with open(Path(__file__).parent / "dagster_sigma/version.py", encoding="utf8") as fp:
+    #     exec(fp.read(), version)
+
+    # return version["__version__"]
+
+
+ver = get_version()
+# dont pin dev installs to avoid pip dep resolver issues
+pin = ""
+setup(
+    name="dagster_sigma",
+    version=get_version(),
+    author="Dagster Labs",
+    author_email="hello@dagsterlabs.com",
+    license="Apache-2.0",
+    description="Build assets representing Sigma dashboards.",
+    url=(
+        "https://github.com/dagster-io/dagster/tree/master/python_modules/libraries/"
+        "dagster-sigma"
+    ),
+    classifiers=[
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "License :: OSI Approved :: Apache Software License",
+        "Operating System :: OS Independent",
+    ],
+    packages=find_packages(exclude=["dagster_sigma_tests*"]),
+    install_requires=[
+        f"dagster{pin}",
+        "sqlglot",
+    ],
+    include_package_data=True,
+    python_requires=">=3.8,<3.13",
+    zip_safe=False,
+)