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.

Sign up for GitHub

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

Support partial parsing when cache is disabled #1070

Merged
merged 4 commits into from
Jun 27, 2024
Merged

Support partial parsing when cache is disabled #1070

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
93a2239
Support partial parsing when cache is disabled
tatiana Jun 27, 2024
5dd59ed
Add missing file
tatiana Jun 27, 2024
58e1563
Fix test in CI
tatiana Jun 27, 2024
086c0ce
Fix broken unit test
tatiana Jun 27, 2024
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
25 changes: 16 additions & 9 deletions cosmos/dbt/graph.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -404,6 +404,10 @@ def load_via_dbt_ls_cache(self) -> bool:
logger.info(f"Cosmos performance: Cache miss for {self.dbt_ls_cache_key} - skipped")
return False

def should_use_partial_parse_cache(self) -> bool:
"""Identify if Cosmos should use/store dbt partial parse cache or not."""
return settings.enable_cache_partial_parse and settings.enable_cache and bool(self.cache_dir)

def load_via_dbt_ls_without_cache(self) -> None:
"""
This is the most accurate way of loading `dbt` projects and filtering them out, since it uses the `dbt` command
Expand All @@ -424,18 +428,21 @@ def load_via_dbt_ls_without_cache(self) -> None:
raise CosmosLoadDbtException("Unable to load project via dbt ls without a profile config.")

with tempfile.TemporaryDirectory() as tmpdir:
logger.debug(
f"Content of the dbt project dir {self.render_config.project_path}: `{os.listdir(self.render_config.project_path)}`"
)
logger.debug(f"Content of the dbt project dir {project_path}: `{os.listdir(project_path)}`")
tmpdir_path = Path(tmpdir)

create_symlinks(project_path, tmpdir_path, self.render_config.dbt_deps)

if self.project.partial_parse and self.cache_dir:
latest_partial_parse = cache._get_latest_partial_parse(project_path, self.cache_dir)
latest_partial_parse = None
if self.project.partial_parse:
if self.should_use_partial_parse_cache() and self.cache_dir:
latest_partial_parse = cache._get_latest_partial_parse(project_path, self.cache_dir)
else:
latest_partial_parse = get_partial_parse_path(project_path)

if latest_partial_parse is not None and latest_partial_parse.exists():
logger.info("Partial parse is enabled and the latest partial parse file is %s", latest_partial_parse)
if latest_partial_parse is not None:
cache._copy_partial_parse_to_project(latest_partial_parse, tmpdir_path)
cache._copy_partial_parse_to_project(latest_partial_parse, tmpdir_path)

with self.profile_config.ensure_profile(
use_mock_values=self.render_config.enable_mock_profile
Expand Down Expand Up @@ -470,9 +477,9 @@ def load_via_dbt_ls_without_cache(self) -> None:
self.nodes = nodes
self.filtered_nodes = nodes

if self.project.partial_parse and self.cache_dir:
if self.should_use_partial_parse_cache():
partial_parse_file = get_partial_parse_path(tmpdir_path)
if partial_parse_file.exists():
if partial_parse_file.exists() and self.cache_dir:
cache._update_partial_parse_cache(partial_parse_file, self.cache_dir)

def load_via_dbt_ls_file(self) -> None:
Expand Down
Loading
Loading