etlplus 0.12.5__tar.gz → 0.12.10__tar.gz

{etlplus-0.12.5/etlplus.egg-info → etlplus-0.12.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.12.5
+Version: 0.12.10
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team
@@ -68,6 +68,19 @@ package and command-line interface for data extraction, validation, transformati
   - [Features](#features)
   - [Installation](#installation)
   - [Quickstart](#quickstart)
+  - [Data Connectors](#data-connectors)
+    - [REST APIs (`api`)](#rest-apis-api)
+    - [Databases (`database`)](#databases-database)
+    - [Files (`file`)](#files-file)
+      - [Stubbed / Placeholder](#stubbed--placeholder)
+      - [Tabular \& Delimited Text](#tabular--delimited-text)
+      - [Semi-Structured Text](#semi-structured-text)
+      - [Columnar / Analytics-Friendly](#columnar--analytics-friendly)
+      - [Binary Serialization and Interchange](#binary-serialization-and-interchange)
+      - [Databases and Embedded Storage](#databases-and-embedded-storage)
+      - [Spreadsheets](#spreadsheets)
+      - [Data Archives](#data-archives)
+      - [Logs and Event Streams](#logs-and-event-streams)
   - [Usage](#usage)
     - [Command Line Interface](#command-line-interface)
       - [Argument Order and Required Options](#argument-order-and-required-options)
@@ -191,6 +204,111 @@ assert validate(filtered, rules)["valid"]
 load(filtered, "file", "temp/sample_output.json", file_format="json")
 ```
 
+## Data Connectors
+
+Data connectors abstract sources from which to extract data and targets to which to load data. They
+are differentiated by their types, each of which is represented in the subsections below.
+
+### REST APIs (`api`)
+
+ETLPlus can extract from REST APIs and load results via common HTTP methods. Supported operations
+include GET for extract and PATCH/POST/PUT for load.
+
+### Databases (`database`)
+
+Database connectors use connection strings for extraction and loading, and
+DDL can be rendered from table specs for migrations or schema checks.
+
+### Files (`file`)
+
+File formats are grouped as in `FileFormat`. Support is marked as:
+
+- **Y**: implemented (may require optional dependencies)
+- **N**: stubbed or not yet implemented
+
+#### Stubbed / Placeholder
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `stub` | N | Placeholder format for tests and future connectors. |
+
+#### Tabular & Delimited Text
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `csv` | Y | Comma-Separated Values |
+| `fwf` | N | Fixed-Width Fields |
+| `dat` | N | Generic data file, often delimited or fixed-width |
+| `psv` | N | Pipe-Separated Values |
+| `tab` | N | Often synonymous with TSV |
+| `tsv` | Y | Tab-Separated Values |
+| `txt` | Y | Plain text, often delimited or fixed-width |
+
+#### Semi-Structured Text
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `cfg` | N | Config-style key-value pairs |
+| `conf` | N | Config-style key-value pairs |
+| `ini` | N | Config-style key-value pairs |
+| `json` | Y | JavaScript Object Notation |
+| `ndjson` | Y | Newline-Delimited JSON |
+| `properties` | N | Java-style key-value pairs |
+| `toml` | N | Tom's Obvious Minimal Language |
+| `xml` | Y | Extensible Markup Language |
+| `yaml` | Y | YAML Ain't Markup Language |
+
+#### Columnar / Analytics-Friendly
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `arrow` | N | Apache Arrow IPC |
+| `feather` | Y | Apache Arrow Feather |
+| `orc` | Y | Optimized Row Columnar; common in Hadoop |
+| `parquet` | Y | Apache Parquet; common in Big Data |
+
+#### Binary Serialization and Interchange
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `avro` | Y | Apache Avro |
+| `bson` | N | Binary JSON; common with MongoDB exports/dumps |
+| `cbor` | N | Concise Binary Object Representation |
+| `ion` | N | Amazon Ion |
+| `msgpack` | N | MessagePack |
+| `pb` | N | Protocol Buffers (Google Protobuf) |
+| `pbf` | N | Protocolbuffer Binary Format; often for GIS data |
+| `proto` | N | Protocol Buffers schema; often in .pb / .bin |
+
+#### Databases and Embedded Storage
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `accdb` | N | Microsoft Access database file (newer format) |
+| `duckdb` | N | DuckDB database file |
+| `mdb` | N | Microsoft Access database file (older format) |
+| `sqlite` | N | SQLite database file |
+
+#### Spreadsheets
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `xls` | Y | Microsoft Excel (BIFF); read-only |
+| `xlsx` | Y | Microsoft Excel (Open XML) |
+
+#### Data Archives
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `gz` | Y | Gzip-compressed file |
+| `zip` | Y | ZIP archive |
+
+#### Logs and Event Streams
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `log` | N | Generic log file |
+
 ## Usage
 
 ### Command Line Interface

{etlplus-0.12.5 → etlplus-0.12.10}/README.md

@@ -18,6 +18,19 @@ package and command-line interface for data extraction, validation, transformati
   - [Features](#features)
   - [Installation](#installation)
   - [Quickstart](#quickstart)
+  - [Data Connectors](#data-connectors)
+    - [REST APIs (`api`)](#rest-apis-api)
+    - [Databases (`database`)](#databases-database)
+    - [Files (`file`)](#files-file)
+      - [Stubbed / Placeholder](#stubbed--placeholder)
+      - [Tabular \& Delimited Text](#tabular--delimited-text)
+      - [Semi-Structured Text](#semi-structured-text)
+      - [Columnar / Analytics-Friendly](#columnar--analytics-friendly)
+      - [Binary Serialization and Interchange](#binary-serialization-and-interchange)
+      - [Databases and Embedded Storage](#databases-and-embedded-storage)
+      - [Spreadsheets](#spreadsheets)
+      - [Data Archives](#data-archives)
+      - [Logs and Event Streams](#logs-and-event-streams)
   - [Usage](#usage)
     - [Command Line Interface](#command-line-interface)
       - [Argument Order and Required Options](#argument-order-and-required-options)
@@ -141,6 +154,111 @@ assert validate(filtered, rules)["valid"]
 load(filtered, "file", "temp/sample_output.json", file_format="json")
 ```
 
+## Data Connectors
+
+Data connectors abstract sources from which to extract data and targets to which to load data. They
+are differentiated by their types, each of which is represented in the subsections below.
+
+### REST APIs (`api`)
+
+ETLPlus can extract from REST APIs and load results via common HTTP methods. Supported operations
+include GET for extract and PATCH/POST/PUT for load.
+
+### Databases (`database`)
+
+Database connectors use connection strings for extraction and loading, and
+DDL can be rendered from table specs for migrations or schema checks.
+
+### Files (`file`)
+
+File formats are grouped as in `FileFormat`. Support is marked as:
+
+- **Y**: implemented (may require optional dependencies)
+- **N**: stubbed or not yet implemented
+
+#### Stubbed / Placeholder
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `stub` | N | Placeholder format for tests and future connectors. |
+
+#### Tabular & Delimited Text
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `csv` | Y | Comma-Separated Values |
+| `fwf` | N | Fixed-Width Fields |
+| `dat` | N | Generic data file, often delimited or fixed-width |
+| `psv` | N | Pipe-Separated Values |
+| `tab` | N | Often synonymous with TSV |
+| `tsv` | Y | Tab-Separated Values |
+| `txt` | Y | Plain text, often delimited or fixed-width |
+
+#### Semi-Structured Text
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `cfg` | N | Config-style key-value pairs |
+| `conf` | N | Config-style key-value pairs |
+| `ini` | N | Config-style key-value pairs |
+| `json` | Y | JavaScript Object Notation |
+| `ndjson` | Y | Newline-Delimited JSON |
+| `properties` | N | Java-style key-value pairs |
+| `toml` | N | Tom's Obvious Minimal Language |
+| `xml` | Y | Extensible Markup Language |
+| `yaml` | Y | YAML Ain't Markup Language |
+
+#### Columnar / Analytics-Friendly
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `arrow` | N | Apache Arrow IPC |
+| `feather` | Y | Apache Arrow Feather |
+| `orc` | Y | Optimized Row Columnar; common in Hadoop |
+| `parquet` | Y | Apache Parquet; common in Big Data |
+
+#### Binary Serialization and Interchange
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `avro` | Y | Apache Avro |
+| `bson` | N | Binary JSON; common with MongoDB exports/dumps |
+| `cbor` | N | Concise Binary Object Representation |
+| `ion` | N | Amazon Ion |
+| `msgpack` | N | MessagePack |
+| `pb` | N | Protocol Buffers (Google Protobuf) |
+| `pbf` | N | Protocolbuffer Binary Format; often for GIS data |
+| `proto` | N | Protocol Buffers schema; often in .pb / .bin |
+
+#### Databases and Embedded Storage
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `accdb` | N | Microsoft Access database file (newer format) |
+| `duckdb` | N | DuckDB database file |
+| `mdb` | N | Microsoft Access database file (older format) |
+| `sqlite` | N | SQLite database file |
+
+#### Spreadsheets
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `xls` | Y | Microsoft Excel (BIFF); read-only |
+| `xlsx` | Y | Microsoft Excel (Open XML) |
+
+#### Data Archives
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `gz` | Y | Gzip-compressed file |
+| `zip` | Y | ZIP archive |
+
+#### Logs and Event Streams
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `log` | N | Generic log file |
+
 ## Usage
 
 ### Command Line Interface

etlplus-0.12.10/etlplus/file/_imports.py

@@ -0,0 +1,141 @@
+"""
+:mod:`etlplus.file._imports` module.
+
+Shared helpers for optional dependency imports.
+"""
+
+from __future__ import annotations
+
+from importlib import import_module
+from typing import Any
+
+# SECTION: INTERNAL CONSTANTS =============================================== #
+
+
+_MODULE_CACHE: dict[str, Any] = {}
+
+
+# SECTION: INTERNAL FUNCTIONS =============================================== #
+
+
+def _error_message(
+    module_name: str,
+    format_name: str,
+) -> str:
+    """
+    Build an import error message for an optional dependency.
+
+    Parameters
+    ----------
+    module_name : str
+        Module name to look up.
+    format_name : str
+        Human-readable format name for templated messages.
+
+    Returns
+    -------
+    str
+        Formatted error message.
+    """
+    return (
+        f'{format_name} support requires '
+        f'optional dependency "{module_name}".\n'
+        f'Install with: pip install {module_name}'
+    )
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def get_optional_module(
+    module_name: str,
+    *,
+    error_message: str,
+) -> Any:
+    """
+    Return an optional dependency module, caching on first import.
+
+    Parameters
+    ----------
+    module_name : str
+        Name of the module to import.
+    error_message : str
+        Error message to surface when the module is missing.
+
+    Returns
+    -------
+    Any
+        The imported module.
+
+    Raises
+    ------
+    ImportError
+        If the optional dependency is missing.
+    """
+    cached = _MODULE_CACHE.get(module_name)
+    if cached is not None:  # pragma: no cover - tiny branch
+        return cached
+    try:
+        module = import_module(module_name)
+    except ImportError as e:  # pragma: no cover
+        raise ImportError(error_message) from e
+    _MODULE_CACHE[module_name] = module
+    return module
+
+
+def get_fastavro() -> Any:
+    """
+    Return the fastavro module, importing it on first use.
+
+    Raises an informative ImportError if the optional dependency is missing.
+
+    Notes
+    -----
+    Prefer :func:`get_optional_module` for new call sites.
+    """
+    return get_optional_module(
+        'fastavro',
+        error_message=_error_message('fastavro', format_name='AVRO'),
+    )
+
+
+def get_pandas(
+    format_name: str,
+) -> Any:
+    """
+    Return the pandas module, importing it on first use.
+
+    Parameters
+    ----------
+    format_name : str
+        Human-readable format name for error messages.
+
+    Returns
+    -------
+    Any
+        The pandas module.
+
+    Notes
+    -----
+    Prefer :func:`get_optional_module` for new call sites.
+    """
+    return get_optional_module(
+        'pandas',
+        error_message=_error_message('pandas', format_name=format_name),
+    )
+
+
+def get_yaml() -> Any:
+    """
+    Return the PyYAML module, importing it on first use.
+
+    Raises an informative ImportError if the optional dependency is missing.
+
+    Notes
+    -----
+    Prefer :func:`get_optional_module` for new call sites.
+    """
+    return get_optional_module(
+        'yaml',
+        error_message=_error_message('PyYAML', format_name='YAML'),
+    )

{etlplus-0.12.5 → etlplus-0.12.10}/etlplus/file/_io.py

@@ -107,6 +107,7 @@ def write_delimited(path: Path, data: JSONData, *, delimiter: str) -> int:
         return 0
 
     fieldnames = sorted({key for row in rows for key in row})
+    path.parent.mkdir(parents=True, exist_ok=True)
     with path.open('w', encoding='utf-8', newline='') as handle:
         writer = csv.DictWriter(
             handle,

etlplus-0.12.10/etlplus/file/accdb.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.accdb` module.
+
+Helpers for reading/writing newer Microsoft Access database (ACCDB) files.
+
+Notes
+-----
+- An ACCDB file is a proprietary database file format used by Microsoft Access
+    2007 and later.
+- Common cases:
+    - Storing relational data for small to medium-sized applications.
+    - Desktop database applications.
+    - Data management for non-enterprise solutions.
+- Rule of thumb:
+    - If the file follows the ACCDB specification, use this module for reading
+        and writing.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ..types import JSONData
+from ..types import JSONList
+from . import stub
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'read',
+    'write',
+]
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONList:
+    """
+    Read ACCDB content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the ACCDB file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the ACCDB file.
+    """
+    return stub.read(path, format_name='ACCDB')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to ACCDB at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the ACCDB file on disk.
+    data : JSONData
+        Data to write as ACCDB. Should be a list of dictionaries or a single
+        dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the ACCDB file.
+    """
+    return stub.write(path, data, format_name='ACCDB')

etlplus-0.12.10/etlplus/file/arrow.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.arrow` module.
+
+Helpers for reading/writing Apache Arrow (ARROW) files.
+
+Notes
+-----
+- An ARROW file is a binary file format designed for efficient
+    columnar data storage and processing.
+- Common cases:
+    - High-performance data analytics.
+    - Interoperability between different data processing systems.
+    - In-memory data representation for fast computations.
+- Rule of thumb:
+    - If the file follows the Apache Arrow specification, use this module for
+        reading and writing.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ..types import JSONData
+from ..types import JSONList
+from . import stub
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'read',
+    'write',
+]
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONList:
+    """
+    Read ARROW content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the Apache Arrow file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the Apache Arrow file.
+    """
+    return stub.read(path, format_name='ARROW')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to ARROW at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the ARROW file on disk.
+    data : JSONData
+        Data to write as ARROW. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the ARROW file.
+    """
+    return stub.write(path, data, format_name='ARROW')

{etlplus-0.12.5 → etlplus-0.12.10}/etlplus/file/avro.py

@@ -1,7 +1,19 @@
 """
 :mod:`etlplus.file.avro` module.
 
-Helpers for reading/writing Avro files.
+Helpers for reading/writing Apache Avro (AVRO) files.
+
+Notes
+-----
+- An AVRO file is a binary file format designed for efficient
+    on-disk storage of data, with a schema definition.
+- Common cases:
+    - Data serialization for distributed systems.
+    - Interoperability between different programming languages.
+    - Storage of large datasets with schema evolution support.
+- Rule of thumb:
+    - If the file follows the Apache Avro specification, use this module for
+        reading and writing.
 """
 
 from __future__ import annotations
@@ -10,6 +22,8 @@ from pathlib import Path
 from typing import Any
 from typing import cast
 
+from etlplus.file._imports import get_fastavro
+
 from ..types import JSONData
 from ..types import JSONDict
 from ..types import JSONList
@@ -27,9 +41,6 @@ __all__ = [
 # SECTION: INTERNAL CONSTANTS =============================================== #
 
 
-_FASTAVRO_CACHE: dict[str, Any] = {}
-
-
 _PRIMITIVE_TYPES: tuple[type, ...] = (
     bool,
     int,
@@ -43,27 +54,6 @@ _PRIMITIVE_TYPES: tuple[type, ...] = (
 # SECTION: INTERNAL FUNCTIONS =============================================== #
 
 
-def _get_fastavro() -> Any:
-    """
-    Return the fastavro module, importing it on first use.
-
-    Raises an informative ImportError if the optional dependency is missing.
-    """
-    mod = _FASTAVRO_CACHE.get('mod')
-    if mod is not None:  # pragma: no cover - tiny branch
-        return mod
-    try:
-        _fastavro = __import__('fastavro')  # type: ignore[assignment]
-    except ImportError as e:  # pragma: no cover
-        raise ImportError(
-            'AVRO support requires optional dependency "fastavro".\n'
-            'Install with: pip install fastavro',
-        ) from e
-    _FASTAVRO_CACHE['mod'] = _fastavro
-
-    return _fastavro
-
-
 def _infer_schema(records: JSONList) -> dict[str, Any]:
     """
     Infer a basic Avro schema from record payloads.
@@ -146,7 +136,7 @@ def read(
     JSONList
         The list of dictionaries read from the AVRO file.
     """
-    fastavro = _get_fastavro()
+    fastavro = get_fastavro()
     with path.open('rb') as handle:
         reader = fastavro.reader(handle)
         return [cast(JSONDict, record) for record in reader]
@@ -175,7 +165,7 @@ def write(
     if not records:
         return 0
 
-    fastavro = _get_fastavro()
+    fastavro = get_fastavro()
     schema = _infer_schema(records)
     parsed_schema = fastavro.parse_schema(schema)