Merge pull request #2158 from dlt-hub/devel

master merge for 1.5.0 release

.github/workflows/test_destination_athena.yml

@@ -67,7 +67,7 @@ jobs:
 
       - name: Install dependencies
         # if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction -E athena --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E athena --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_athena_iceberg.yml

@@ -67,7 +67,7 @@ jobs:
 
       - name: Install dependencies
         # if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction -E athena --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E athena --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_bigquery.yml

@@ -66,7 +66,7 @@ jobs:
 
       - name: Install dependencies
         # if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction -E bigquery --with providers -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E bigquery --with providers -E parquet --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_clickhouse.yml

@@ -61,7 +61,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-gcp
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E clickhouse --with providers -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E clickhouse --with providers -E parquet --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_databricks.yml

@@ -64,7 +64,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-gcp
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E databricks -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E databricks -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_dremio.yml

@@ -65,7 +65,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-gcp
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline,ibis
 
       - run: |
           poetry run pytest tests/load --ignore tests/load/sources

.github/workflows/test_destination_motherduck.yml

@@ -64,7 +64,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-motherduck
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E motherduck -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E motherduck -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_mssql.yml

@@ -69,7 +69,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-gcp
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E mssql -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E mssql -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_snowflake.yml

@@ -64,7 +64,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-gcp
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E snowflake -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E snowflake -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destination_synapse.yml

@@ -67,7 +67,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-gcp
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E synapse -E parquet --with sentry-sdk --with pipeline
+        run: poetry install --no-interaction -E synapse -E parquet --with sentry-sdk --with pipeline,ibis
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_destinations.yml

@@ -77,8 +77,10 @@ jobs:
       #     key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-redshift
 
       - name: Install dependencies
-        # if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction -E redshift -E postgis -E postgres -E gs -E s3 -E az -E parquet -E duckdb -E cli -E filesystem --with sentry-sdk --with pipeline -E deltalake
+        run: poetry install --no-interaction -E redshift -E postgis -E postgres -E gs -E s3 -E az -E parquet -E duckdb -E cli -E filesystem --with sentry-sdk --with pipeline,ibis -E deltalake -E pyiceberg
+
+      - name: Upgrade sqlalchemy
+        run: poetry run pip install sqlalchemy==2.0.18  # minimum version required by `pyiceberg`
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

.github/workflows/test_local_destinations.yml

@@ -95,7 +95,10 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-local-destinations
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E postgres -E postgis -E duckdb -E parquet -E filesystem -E cli -E weaviate -E qdrant -E sftp --with sentry-sdk --with pipeline -E deltalake
+        run: poetry install --no-interaction -E postgres -E postgis -E duckdb -E parquet -E filesystem -E cli -E weaviate -E qdrant -E sftp --with sentry-sdk --with pipeline,ibis -E deltalake -E pyiceberg
+
+      - name: Upgrade sqlalchemy
+        run: poetry run pip install sqlalchemy==2.0.18  # minimum version required by `pyiceberg`
 
       - name: Start SFTP server
         run: docker compose -f "tests/load/filesystem_sftp/docker-compose.yml" up -d

.github/workflows/test_sqlalchemy_destinations.yml

@@ -86,7 +86,7 @@ jobs:
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-local-destinations
 
       - name: Install dependencies
-        run: poetry install --no-interaction -E parquet -E filesystem -E sqlalchemy -E cli --with sentry-sdk --with pipeline && poetry run pip install mysqlclient && poetry run pip install "sqlalchemy==${{ matrix.sqlalchemy }}"
+        run: poetry install --no-interaction -E parquet -E filesystem -E sqlalchemy -E cli --with sentry-sdk --with pipeline,ibis && poetry run pip install mysqlclient && poetry run pip install "sqlalchemy==${{ matrix.sqlalchemy }}"
 
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml

Makefile

@@ -44,7 +44,7 @@ has-poetry:
 	poetry --version
 
 dev: has-poetry
-	poetry install --all-extras --with docs,providers,pipeline,sources,sentry-sdk,airflow
+	poetry install --all-extras --with docs,providers,pipeline,sources,sentry-sdk
 
 lint:
 	./tools/check-package.sh
@@ -63,7 +63,6 @@ format:
 lint-snippets:
 	cd docs/tools && poetry run python check_embedded_snippets.py full
 
-
 lint-and-test-snippets: lint-snippets
 	poetry run mypy --config-file mypy.ini docs/website docs/tools --exclude docs/tools/lint_setup --exclude docs/website/docs_processed
 	poetry run flake8 --max-line-length=200 docs/website docs/tools --exclude docs/website/.dlt-repo
@@ -82,7 +81,7 @@ lint-security:
 	poetry run bandit -r dlt/ -n 3 -l
 
 test:
-	(set -a && . tests/.env && poetry run pytest tests)
+	poetry run pytest tests
 
 test-load-local:
 	DESTINATION__POSTGRES__CREDENTIALS=postgresql://loader:loader@localhost:5432/dlt_data DESTINATION__DUCKDB__CREDENTIALS=duckdb:///_storage/test_quack.duckdb  poetry run pytest tests -k '(postgres or duckdb)'

dlt/__init__.py

@@ -42,7 +42,6 @@
 )
 from dlt.pipeline import progress
 from dlt import destinations
-from dlt.destinations.dataset import dataset as _dataset
 
 pipeline = _pipeline
 current = _current
@@ -80,7 +79,6 @@
     "TCredentials",
     "sources",
     "destinations",
-    "_dataset",
 ]
 
 # verify that no injection context was created

dlt/cli/command_wrappers.py

@@ -43,14 +43,14 @@ def init_command_wrapper(
     destination_type: str,
     repo_location: str,
     branch: str,
-    omit_core_sources: bool = False,
+    eject_source: bool = False,
 ) -> None:
     init_command(
         source_name,
         destination_type,
         repo_location,
         branch,
-        omit_core_sources,
+        eject_source,
     )
 
 

dlt/cli/init_command.py

@@ -157,7 +157,7 @@ def _list_core_sources() -> Dict[str, SourceConfiguration]:
     sources: Dict[str, SourceConfiguration] = {}
     for source_name in files_ops.get_sources_names(core_sources_storage, source_type="core"):
         sources[source_name] = files_ops.get_core_source_configuration(
-            core_sources_storage, source_name
+            core_sources_storage, source_name, eject_source=False
         )
     return sources
 
@@ -295,7 +295,7 @@ def init_command(
     destination_type: str,
     repo_location: str,
     branch: str = None,
-    omit_core_sources: bool = False,
+    eject_source: bool = False,
 ) -> None:
     # try to import the destination and get config spec
     destination_reference = Destination.from_reference(destination_type)
@@ -310,13 +310,9 @@ def init_command(
 
     # discover type of source
     source_type: files_ops.TSourceType = "template"
-    if (
-        source_name in files_ops.get_sources_names(core_sources_storage, source_type="core")
-    ) and not omit_core_sources:
+    if source_name in files_ops.get_sources_names(core_sources_storage, source_type="core"):
         source_type = "core"
     else:
-        if omit_core_sources:
-            fmt.echo("Omitting dlt core sources.")
         verified_sources_storage = _clone_and_get_verified_sources_storage(repo_location, branch)
         if source_name in files_ops.get_sources_names(
             verified_sources_storage, source_type="verified"
@@ -380,7 +376,7 @@ def init_command(
     else:
         if source_type == "core":
             source_configuration = files_ops.get_core_source_configuration(
-                core_sources_storage, source_name
+                core_sources_storage, source_name, eject_source
             )
             from importlib.metadata import Distribution
 
@@ -392,6 +388,9 @@ def init_command(
 
             if canonical_source_name in extras:
                 source_configuration.requirements.update_dlt_extras(canonical_source_name)
+
+            #  create remote modified index to copy files when ejecting
+            remote_modified = {file_name: None for file_name in source_configuration.files}
         else:
             if not is_valid_schema_name(source_name):
                 raise InvalidSchemaName(source_name)
@@ -536,11 +535,17 @@ def init_command(
                 "Creating a new pipeline with the dlt core source %s (%s)"
                 % (fmt.bold(source_name), source_configuration.doc)
             )
-            fmt.echo(
-                "NOTE: Beginning with dlt 1.0.0, the source %s will no longer be copied from the"
-                " verified sources repo but imported from dlt.sources. You can provide the"
-                " --omit-core-sources flag to revert to the old behavior." % (fmt.bold(source_name))
-            )
+            if eject_source:
+                fmt.echo(
+                    "NOTE: Source code of %s will be ejected. Remember to modify the pipeline "
+                    "example script to import the ejected source." % (fmt.bold(source_name))
+                )
+            else:
+                fmt.echo(
+                    "NOTE: Beginning with dlt 1.0.0, the source %s will no longer be copied from"
+                    " the verified sources repo but imported from dlt.sources. You can provide the"
+                    " --eject flag to revert to the old behavior." % (fmt.bold(source_name))
+                )
         elif source_configuration.source_type == "verified":
             fmt.echo(
                 "Creating and configuring a new pipeline with the verified source %s (%s)"

dlt/cli/pipeline_files.py

@@ -226,19 +226,39 @@ def get_template_configuration(
     )
 
 
+def _get_source_files(sources_storage: FileStorage, source_name: str) -> List[str]:
+    """Get all files that belong to source `source_name`"""
+    files: List[str] = []
+    for root, subdirs, _files in os.walk(sources_storage.make_full_path(source_name)):
+        # filter unwanted files
+        for subdir in list(subdirs):
+            if any(fnmatch.fnmatch(subdir, ignore) for ignore in IGNORE_FILES):
+                subdirs.remove(subdir)
+        rel_root = sources_storage.to_relative_path(root)
+        files.extend(
+            [
+                os.path.join(rel_root, file)
+                for file in _files
+                if all(not fnmatch.fnmatch(file, ignore) for ignore in IGNORE_FILES)
+            ]
+        )
+    return files
+
+
 def get_core_source_configuration(
-    sources_storage: FileStorage, source_name: str
+    sources_storage: FileStorage, source_name: str, eject_source: bool
 ) -> SourceConfiguration:
     src_pipeline_file = CORE_SOURCE_TEMPLATE_MODULE_NAME + "/" + source_name + PIPELINE_FILE_SUFFIX
     dest_pipeline_file = source_name + PIPELINE_FILE_SUFFIX
+    files: List[str] = _get_source_files(sources_storage, source_name) if eject_source else []
 
     return SourceConfiguration(
         "core",
         "dlt.sources." + source_name,
         sources_storage,
         src_pipeline_file,
         dest_pipeline_file,
-        [".gitignore"],
+        files,
         SourceRequirements([]),
         _get_docstring_for_module(sources_storage, source_name),
         False,
@@ -259,21 +279,7 @@ def get_verified_source_configuration(
             f"Pipeline example script {example_script} could not be found in the repository",
             source_name,
         )
-    # get all files recursively
-    files: List[str] = []
-    for root, subdirs, _files in os.walk(sources_storage.make_full_path(source_name)):
-        # filter unwanted files
-        for subdir in list(subdirs):
-            if any(fnmatch.fnmatch(subdir, ignore) for ignore in IGNORE_FILES):
-                subdirs.remove(subdir)
-        rel_root = sources_storage.to_relative_path(root)
-        files.extend(
-            [
-                os.path.join(rel_root, file)
-                for file in _files
-                if all(not fnmatch.fnmatch(file, ignore) for ignore in IGNORE_FILES)
-            ]
-        )
+    files = _get_source_files(sources_storage, source_name)
     # read requirements
     requirements_path = os.path.join(source_name, utils.REQUIREMENTS_TXT)
     if sources_storage.has_file(requirements_path):

dlt/cli/plugins.py

@@ -84,14 +84,10 @@ def configure_parser(self, parser: argparse.ArgumentParser) -> None:
         )
 
         parser.add_argument(
-            "--omit-core-sources",
+            "--eject",
             default=False,
             action="store_true",
-            help=(
-                "When present, will not create the new pipeline with a core source of the given"
-                " name but will take a source of this name from the default or provided"
-                " location."
-            ),
+            help="Ejects the source code of the core source like sql_database",
         )
 
     def execute(self, args: argparse.Namespace) -> None:
@@ -107,7 +103,7 @@ def execute(self, args: argparse.Namespace) -> None:
                     args.destination,
                     args.location,
                     args.branch,
-                    args.omit_core_sources,
+                    args.eject,
                 )
 
 

dlt/cli/source_detection.py

@@ -29,8 +29,7 @@ def find_call_arguments_to_replace(
                     if not isinstance(dn_node, ast.Constant) or not isinstance(dn_node.value, str):
                         raise CliCommandInnerException(
                             "init",
-                            f"The pipeline script {init_script_name} must pass the {t_arg_name} as"
-                            f" string to '{arg_name}' function in line {dn_node.lineno}",
+                            f"The pipeline script {init_script_name} must pass the {t_arg_name} as string to '{arg_name}' function in line {dn_node.lineno}",  # type: ignore[attr-defined]
                         )
                     else:
                         transformed_nodes.append((dn_node, ast.Constant(value=t_value, kind=None)))

dlt/common/configuration/providers/toml.py

@@ -124,6 +124,12 @@ def _read_google_colab_secrets(self, name: str, file_name: str) -> tomlkit.TOMLD
         """Try to load the toml from google colab userdata object"""
         try:
             from google.colab import userdata
+            from dlt.common.runtime.exec_info import is_notebook
+
+            # make sure we work in interactive mode (get_ipython() is available)
+            # when dlt cli is run, userdata is available but without a kernel
+            if not is_notebook():
+                return None
 
             try:
                 return tomlkit.loads(userdata.get(file_name))