Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Rearrange parsers #264

Merged
merged 8 commits into from
Sep 30, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 32 additions & 10 deletions poetry.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 3 additions & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,9 @@ pytest-xdist = "^3"
ruff = "^0"
sh = "^2"
"shandy-sqlfmt" = {version = "^0", extras=["shandy-sqlfmt[jinjafmt]"]}
types-PyYaml = "^6"
types-tabulate = "^0"
types-toml = "^0"

[tool.poetry.group.docs.dependencies]
mike = "^2"
Expand Down Expand Up @@ -154,7 +156,7 @@ exclude = [
"dist",
"node_modules",
"site-packages",
"src/dbt_bouncer/dbt_cloud",
"src/dbt_bouncer/artifact_parsers/dbt_cloud",
"venv",
]
line-length = 88
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -15,15 +15,15 @@

class CustomGranularity(BaseParserModel):
model_config = ConfigDict(
extra='forbid',
extra="forbid",
)
name: str
column_name: Optional[str] = None


class TimeSpine(BaseParserModel):
model_config = ConfigDict(
extra='forbid',
extra="forbid",
)
standard_granularity_column: str
custom_granularities: Optional[List[CustomGranularity]] = None
Expand Down
80 changes: 80 additions & 0 deletions src/dbt_bouncer/artifact_parsers/parsers_catalog.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,80 @@
# TODO Remove after this program no longer support Python 3.8.*
from __future__ import annotations

import logging
import warnings
from typing import TYPE_CHECKING, List

from pydantic import BaseModel

from dbt_bouncer.utils import clean_path_str

with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=UserWarning)
from dbt_artifacts_parser.parsers.catalog.catalog_v1 import (
CatalogTable, # noqa: TCH002
CatalogV1, # noqa: TCH002
)
if TYPE_CHECKING:
from pathlib import Path

from dbt_bouncer.artifact_parsers.parsers_manifest import DbtBouncerManifest


from dbt_bouncer.artifact_parsers.parsers_common import load_dbt_artifact


class DbtBouncerCatalogNode(BaseModel):
"""Model for all nodes in `catalog.json`."""

catalog_node: CatalogTable
original_file_path: str
unique_id: str


def parse_catalog(
artifact_dir: Path,
manifest_obj: "DbtBouncerManifest",
) -> tuple[List[DbtBouncerCatalogNode], List[DbtBouncerCatalogNode]]:
"""Parse the catalog.json artifact.
Returns:
List[DbtBouncerCatalogNode]: List of catalog nodes for the project.
List[DbtBouncerCatalogNode]: List of catalog nodes for the project sources.
"""
catalog_obj: CatalogV1 = load_dbt_artifact(
artifact_name="catalog.json",
dbt_artifacts_dir=artifact_dir,
)
project_catalog_nodes = [
DbtBouncerCatalogNode(
**{
"catalog_node": v,
"original_file_path": clean_path_str(
manifest_obj.manifest.nodes[k].original_file_path
),
"unique_id": k,
},
)
for k, v in catalog_obj.nodes.items()
if k.split(".")[-2] == manifest_obj.manifest.metadata.project_name
]
project_catalog_sources = [
DbtBouncerCatalogNode(
**{
"catalog_node": v,
"original_file_path": clean_path_str(
manifest_obj.manifest.sources[k].original_file_path
),
"unique_id": k,
},
)
for k, v in catalog_obj.sources.items()
if k.split(".")[1] == manifest_obj.manifest.metadata.project_name
]
logging.info(
f"Parsed `catalog.json`: {len(project_catalog_nodes)} nodes, {len(project_catalog_sources)} sources.",
)

return project_catalog_nodes, project_catalog_sources
Loading