Merge pull request #1278 from dlt-hub/devel

master merge for 0.4.9 release

.github/workflows/test_common.yml

@@ -13,6 +13,7 @@ concurrency:
 
 env:
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
 jobs:
   get_docs_changes:

.github/workflows/test_dbt_cloud.yml

@@ -19,6 +19,7 @@ env:
   DBT_CLOUD__API_TOKEN: ${{ secrets.DBT_CLOUD__API_TOKEN }}
 
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
 jobs:
   get_docs_changes:

.github/workflows/test_dbt_runner.yml

@@ -16,6 +16,7 @@ env:
 
   DLT_SECRETS_TOML: ${{ secrets.DLT_SECRETS_TOML }}
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
 jobs:
   get_docs_changes:

.github/workflows/test_destination_athena.yml

@@ -19,7 +19,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
-  RUNTIME__DLTHUB_TELEMETRY_SEGMENT_WRITE_KEY: TLJiyRkGVZGCi2TtjClamXpFcxAA1rSB
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
   ACTIVE_DESTINATIONS: "[\"athena\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"
   EXCLUDED_DESTINATION_CONFIGURATIONS: "[\"athena-parquet-staging-iceberg\", \"athena-parquet-no-staging-iceberg\"]"

.github/workflows/test_destination_athena_iceberg.yml

@@ -19,7 +19,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
-  RUNTIME__DLTHUB_TELEMETRY_SEGMENT_WRITE_KEY: TLJiyRkGVZGCi2TtjClamXpFcxAA1rSB
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
   ACTIVE_DESTINATIONS: "[\"athena\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"
   EXCLUDED_DESTINATION_CONFIGURATIONS: "[\"athena-no-staging\", \"athena-parquet-no-staging\"]"

.github/workflows/test_destination_bigquery.yml

@@ -19,6 +19,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   ACTIVE_DESTINATIONS: "[\"bigquery\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"
@@ -70,12 +71,6 @@ jobs:
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
-      - run: |
-          poetry run pytest tests/load -m "essential"
-        name: Run essential tests Linux
-        if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
-
       - run: |
           poetry run pytest tests/load
         name: Run all tests Linux
-        if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_databricks.yml

@@ -19,6 +19,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   ACTIVE_DESTINATIONS: "[\"databricks\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"

.github/workflows/test_destination_dremio.yml

@@ -17,6 +17,7 @@ concurrency:
 env:
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   ACTIVE_DESTINATIONS: "[\"dremio\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"

.github/workflows/test_destination_mssql.yml

@@ -20,6 +20,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   ACTIVE_DESTINATIONS: "[\"mssql\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"

.github/workflows/test_destination_qdrant.yml

@@ -18,6 +18,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   ACTIVE_DESTINATIONS: "[\"qdrant\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"

.github/workflows/test_destination_snowflake.yml

@@ -19,6 +19,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   ACTIVE_DESTINATIONS: "[\"snowflake\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"

.github/workflows/test_destination_synapse.yml

@@ -18,6 +18,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://cf6086f7d263462088b9fb9f9947caee@o4505514867163136.ingest.sentry.io/4505516212682752
   RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   ACTIVE_DESTINATIONS: "[\"synapse\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"

.github/workflows/test_destinations.yml

@@ -25,7 +25,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
-  RUNTIME__DLTHUB_TELEMETRY_SEGMENT_WRITE_KEY: TLJiyRkGVZGCi2TtjClamXpFcxAA1rSB
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
   # Test redshift and filesystem with all buckets
   # postgres runs again here so we can test on mac/windows
   ACTIVE_DESTINATIONS: "[\"redshift\", \"postgres\", \"duckdb\", \"filesystem\", \"dummy\"]"

.github/workflows/test_doc_snippets.yml

@@ -17,7 +17,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
-  RUNTIME__DLTHUB_TELEMETRY_SEGMENT_WRITE_KEY: TLJiyRkGVZGCi2TtjClamXpFcxAA1rSB
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
   # Slack hook for chess in production example
   RUNTIME__SLACK_INCOMING_HOOK: ${{ secrets.RUNTIME__SLACK_INCOMING_HOOK }}

.github/workflows/test_local_destinations.yml

@@ -20,7 +20,7 @@ env:
 
   RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
   RUNTIME__LOG_LEVEL: ERROR
-  RUNTIME__DLTHUB_TELEMETRY_SEGMENT_WRITE_KEY: TLJiyRkGVZGCi2TtjClamXpFcxAA1rSB
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
   ACTIVE_DESTINATIONS: "[\"duckdb\", \"postgres\", \"filesystem\", \"weaviate\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\", \"file\"]"
 

CONTRIBUTING.md

@@ -6,11 +6,12 @@ Thank you for considering contributing to **dlt**! We appreciate your help in ma
 
 1. [Getting Started](#getting-started)
 2. [Submitting Changes](#submitting-changes)
-3. [Linting](#linting)
-4. [Testing](#testing)
-5. [Local Development](#local-development)
-6. [Publishing (Maintainers Only)](#publishing-maintainers-only)
-7. [Resources](#resources)
+3. [Adding or updating core dependencies](#adding-or-updating-core-dependencies)
+4. [Linting](#linting)
+5. [Testing](#testing)
+6. [Local Development](#local-development)
+7. [Publishing (Maintainers Only)](#publishing-maintainers-only)
+8. [Resources](#resources)
 
 ## Before You Begin
 
@@ -62,6 +63,26 @@ only the `duckdb` and `postgres` are available to forks.
 
 In case you submit a new destination or make changes to a destination that require credentials (so Bigquery, Snowflake, buckets etc.) you **should contact us so we can add you as contributor**. Then you should make a PR directly to the `dlt` repo.
 
+## Adding or updating core dependencies
+
+Our objective is to maintain stability and compatibility of dlt across all environments.
+By following these guidelines, we can make sure that dlt stays secure, reliable and compatible.
+Please consider the following points carefully when proposing updates to dependencies.
+
+### Updating guidelines
+
+1. **Critical security or system integrity updates only:**
+   Major or minor version updates to dependencies should only be considered if there are critical security vulnerabilities or issues that impact the system's integrity. In such cases, updating is necessary to protect the system and the data it processes.
+
+2. **Using the '>=' operator:**
+   When specifying dependencies, please make sure to use the `>=` operator while also maintaining version minima. This approach ensures our project remains compatible with older systems and setups, mitigating potential unsolvable dependency conflicts.
+
+For example, if our project currently uses a package `example-package==1.2.3`, and a security update is
+released as `1.2.4`, instead of updating to `example-package==1.2.4`, we can set it to `example-package>=1.2.3,<2.0.0`. This permits the necessary security update and at the same time
+prevents the automatic jump to a potentially incompatible major version update in the future.
+The other important note on using possible version minimas is to prevent potential cases where package
+versions will not be resolvable.
+
 ## Linting
 
 `dlt` uses `mypy` and `flake8` with several plugins for linting.

README.md

@@ -113,4 +113,4 @@ The dlt project is quickly growing, and we're excited to have you join our commu
 
 ## License
 
-DLT is released under the [Apache 2.0 License](LICENSE.txt).
+`dlt` is released under the [Apache 2.0 License](LICENSE.txt).

dlt/cli/_dlt.py

@@ -5,7 +5,7 @@
 import click
 
 from dlt.version import __version__
-from dlt.common import json
+from dlt.common.json import json
 from dlt.common.schema import Schema
 from dlt.common.typing import DictStrAny
 from dlt.common.runners import Venv

dlt/cli/config_toml_writer.py

@@ -4,7 +4,7 @@
 from tomlkit.container import Container as TOMLContainer
 from collections.abc import Sequence as C_Sequence
 
-from dlt.common import pendulum
+from dlt.common.pendulum import pendulum
 from dlt.common.configuration.specs import (
     BaseConfiguration,
     is_base_configuration_inner_hint,

dlt/cli/pipeline_command.py

@@ -3,7 +3,7 @@
 import dlt
 from dlt.cli.exceptions import CliCommandException
 
-from dlt.common import json
+from dlt.common.json import json
 from dlt.common.pipeline import resource_state, get_dlt_pipelines_dir, TSourceState
 from dlt.common.destination.reference import TDestinationReferenceArg
 from dlt.common.runners import Venv

dlt/cli/utils.py

@@ -1,11 +1,8 @@
 import ast
 import os
-import tempfile
 from typing import Callable
 
-from dlt.common import git
 from dlt.common.reflection.utils import set_ast_parents
-from dlt.common.storages import FileStorage
 from dlt.common.typing import TFun
 from dlt.common.configuration import resolve_configuration
 from dlt.common.configuration.specs import RunConfiguration

dlt/common/configuration/providers/google_secrets.py

@@ -1,9 +1,8 @@
 import base64
 import string
 import re
-from typing import Tuple
 
-from dlt.common import json
+from dlt.common.json import json
 from dlt.common.configuration.specs import GcpServiceAccountCredentials
 from dlt.common.exceptions import MissingDependencyException
 from .toml import VaultTomlProvider

dlt/common/configuration/providers/toml.py

@@ -6,7 +6,7 @@
 from tomlkit.container import Container as TOMLContainer
 from typing import Any, Dict, Optional, Tuple, Type, Union
 
-from dlt.common import pendulum
+from dlt.common.pendulum import pendulum
 from dlt.common.configuration.paths import get_dlt_settings_dir, get_dlt_data_dir
 from dlt.common.configuration.utils import auto_cast
 from dlt.common.configuration.specs import known_sections

dlt/common/configuration/specs/azure_credentials.py

@@ -1,7 +1,6 @@
 from typing import Optional, Dict, Any
 
-from dlt.common import pendulum
-from dlt.common.exceptions import MissingDependencyException
+from dlt.common.pendulum import pendulum
 from dlt.common.typing import TSecretStrValue
 from dlt.common.configuration.specs import (
     CredentialsConfiguration,

dlt/common/configuration/specs/gcp_credentials.py

@@ -2,7 +2,8 @@
 import sys
 from typing import Any, ClassVar, Final, List, Tuple, Union, Dict
 
-from dlt.common import json, pendulum
+from dlt.common.json import json
+from dlt.common.pendulum import pendulum
 from dlt.common.configuration.specs.api_credentials import OAuth2Credentials
 from dlt.common.configuration.specs.exceptions import (
     InvalidGoogleNativeCredentialsType,

dlt/common/configuration/specs/run_configuration.py

@@ -16,6 +16,7 @@ class RunConfiguration(BaseConfiguration):
     slack_incoming_hook: Optional[TSecretStrValue] = None
     dlthub_telemetry: bool = True  # enable or disable dlthub telemetry
     dlthub_telemetry_segment_write_key: str = "a1F2gc6cNYw2plyAt02sZouZcsRjG7TD"
+    dlthub_telemetry_endpoint: str = "https://api.segment.io/v1/track"
     log_format: str = "{asctime}|[{levelname:<21}]|{process}|{thread}|{name}|{filename}|{funcName}:{lineno}|{message}"
     log_level: str = "WARNING"
     request_timeout: float = 60

dlt/common/configuration/utils.py

@@ -5,7 +5,7 @@
 from typing import Any, Dict, Mapping, NamedTuple, Optional, Tuple, Type, Sequence
 from collections.abc import Mapping as C_Mapping
 
-from dlt.common import json
+from dlt.common.json import json
 from dlt.common.typing import AnyType, TAny
 from dlt.common.data_types import coerce_value, py_type_to_sc_type
 from dlt.common.configuration.providers import EnvironProvider
@@ -122,8 +122,6 @@ def log_traces(
     default_value: Any,
     traces: Sequence[LookupTrace],
 ) -> None:
-    from dlt.common import logger
-
     # if logger.is_logging() and logger.log_level() == "DEBUG" and config:
     #     logger.debug(f"Field {key} with type {hint} in {type(config).__name__} {'NOT RESOLVED' if value is None else 'RESOLVED'}")
     # print(f"Field {key} with type {hint} in {type(config).__name__} {'NOT RESOLVED' if value is None else 'RESOLVED'}")

dlt/common/data_types/type_helpers.py

@@ -3,13 +3,13 @@
 import dataclasses
 import datetime  # noqa: I251
 from collections.abc import Mapping as C_Mapping, Sequence as C_Sequence
-from typing import Any, Type, Literal, Union, cast
+from typing import Any, Type, Union
 from enum import Enum
 
-from dlt.common import pendulum, json, Decimal, Wei
 from dlt.common.json import custom_pua_remove, json
 from dlt.common.json._simplejson import custom_encode as json_custom_encode
-from dlt.common.arithmetics import InvalidOperation
+from dlt.common.wei import Wei
+from dlt.common.arithmetics import InvalidOperation, Decimal
 from dlt.common.data_types.typing import TDataType
 from dlt.common.time import (
     ensure_pendulum_datetime,

dlt/common/data_writers/__init__.py

@@ -3,6 +3,9 @@
     DataWriterMetrics,
     TDataItemFormat,
     FileWriterSpec,
+    resolve_best_writer_spec,
+    get_best_writer_spec,
+    is_native_writer,
 )
 from dlt.common.data_writers.buffered import BufferedDataWriter, new_file_id
 from dlt.common.data_writers.escape import (
@@ -14,6 +17,9 @@
 __all__ = [
     "DataWriter",
     "FileWriterSpec",
+    "resolve_best_writer_spec",
+    "get_best_writer_spec",
+    "is_native_writer",
     "DataWriterMetrics",
     "TDataItemFormat",
     "BufferedDataWriter",

dlt/common/data_writers/buffered.py

@@ -47,9 +47,7 @@ def __init__(
         self.writer_spec = writer_spec
         if self.writer_spec.requires_destination_capabilities and not _caps:
             raise DestinationCapabilitiesRequired(self.writer_spec.file_format)
-        self.writer_cls = DataWriter.class_factory(
-            writer_spec.file_format, writer_spec.data_item_format
-        )
+        self.writer_cls = DataWriter.writer_class_from_spec(writer_spec)
         self._supports_schema_changes = self.writer_spec.supports_schema_changes
         self._caps = _caps
         # validate if template has correct placeholders

dlt/common/data_writers/escape.py

@@ -4,6 +4,8 @@
 from datetime import date, datetime, time  # noqa: I251
 
 from dlt.common.json import json
+from dlt.common.pendulum import pendulum
+from dlt.common.time import reduce_pendulum_datetime_precision
 
 # use regex to escape characters in single pass
 SQL_ESCAPE_DICT = {"'": "''", "\\": "\\\\", "\n": "\\n", "\r": "\\r"}
@@ -152,3 +154,25 @@ def escape_databricks_literal(v: Any) -> Any:
         return "NULL"
 
     return str(v)
+
+
+def format_datetime_literal(v: pendulum.DateTime, precision: int = 6, no_tz: bool = False) -> str:
+    """Converts `v` to ISO string, optionally without timezone spec (in UTC) and with given `precision`"""
+    if no_tz:
+        v = v.in_timezone(tz="UTC").replace(tzinfo=None)
+    v = reduce_pendulum_datetime_precision(v, precision)
+    # yet another precision translation
+    timespec: str = "microseconds"
+    if precision < 6:
+        timespec = "milliseconds"
+    elif precision < 3:
+        timespec = "seconds"
+    return "'" + v.isoformat(sep=" ", timespec=timespec) + "'"
+
+
+def format_bigquery_datetime_literal(
+    v: pendulum.DateTime, precision: int = 6, no_tz: bool = False
+) -> str:
+    """Returns BigQuery-adjusted datetime literal by prefixing required `TIMESTAMP` indicator."""
+    # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#timestamp_literals
+    return "TIMESTAMP " + format_datetime_literal(v, precision, no_tz)