etlplus 0.12.9__tar.gz → 0.12.10__tar.gz

{etlplus-0.12.9/etlplus.egg-info → etlplus-0.12.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.12.9
+Version: 0.12.10
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team
@@ -77,8 +77,10 @@ package and command-line interface for data extraction, validation, transformati
       - [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)
@@ -246,8 +248,13 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 
 | 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 |
 
@@ -255,6 +262,7 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 
 | 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 |
@@ -264,6 +272,22 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 | 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
 
@@ -279,6 +303,12 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 | `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-0.12.9 → etlplus-0.12.10}/README.md

@@ -27,8 +27,10 @@ package and command-line interface for data extraction, validation, transformati
       - [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)
@@ -196,8 +198,13 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 
 | 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 |
 
@@ -205,6 +212,7 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 
 | 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 |
@@ -214,6 +222,22 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 | 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
 
@@ -229,6 +253,12 @@ File formats are grouped as in `FileFormat`. Support is marked as:
 | `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/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-0.12.9 → 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

etlplus-0.12.10/etlplus/file/bson.py

@@ -0,0 +1,77 @@
+"""
+:mod:`etlplus.file.bson` module.
+
+Helpers for reading/writing Binary JSON (BSON) files.
+
+Notes
+-----
+- A BSON file is a binary-encoded serialization of JSON-like documents.
+- Common cases:
+    - Data storage in MongoDB.
+    - Efficient data interchange between systems.
+    - Handling of complex data types not supported in standard JSON.
+- Rule of thumb:
+    - If the file follows the BSON 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 BSON content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the BSON file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the BSON file.
+    """
+    return stub.read(path, format_name='BSON')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to BSON at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the BSON file on disk.
+    data : JSONData
+        Data to write as BSON. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the BSON file.
+    """
+    return stub.write(path, data, format_name='BSON')

etlplus-0.12.10/etlplus/file/cbor.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.cbor` module.
+
+Helpers for reading/writing Concise Binary Object Representation (CBOR) files.
+
+Notes
+-----
+- A CBOR file is a binary data format designed for small code size and message
+    size, suitable for constrained environments.
+- Common cases:
+    - IoT data interchange.
+    - Efficient data serialization.
+    - Storage of structured data in a compact binary form.
+- Rule of thumb:
+    - If the file follows the CBOR 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 CBOR content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CBOR file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the CBOR file.
+    """
+    return stub.read(path, format_name='CBOR')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to CBOR at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CBOR file on disk.
+    data : JSONData
+        Data to write as CBOR. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the CBOR file.
+    """
+    return stub.write(path, data, format_name='CBOR')

etlplus-0.12.10/etlplus/file/cfg.py

@@ -0,0 +1,79 @@
+"""
+:mod:`etlplus.file.cfg` module.
+
+Helpers for reading/writing config (CFG) files.
+
+Notes
+-----
+- A “CFG-formatted” file is a configuration file that may use various
+    syntaxes, such as INI, YAML, or custom formats.
+- Common cases:
+    - INI-style key-value pairs with sections (such as in Python ecosystems,
+        using ``configparser``).
+    - YAML-like structures with indentation.
+    - Custom formats specific to certain applications.
+- Rule of thumb:
+    - If the file follows a standard format like INI or YAML, consider using
+        dedicated parsers.
+"""
+
+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 CFG content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CFG file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the CFG file.
+    """
+    return stub.read(path, format_name='CFG')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to CFG file at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CFG file on disk.
+    data : JSONData
+        Data to write as CFG file. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the CFG file.
+    """
+    return stub.write(path, data, format_name='CFG')

etlplus-0.12.10/etlplus/file/conf.py

@@ -0,0 +1,80 @@
+"""
+:mod:`etlplus.file.conf` module.
+
+Helpers for reading/writing config (CONF) files.
+
+Notes
+-----
+- A “CONF-formatted” file is a configuration file that may use various
+    syntaxes, such as INI, YAML, or custom formats.
+- Common cases:
+    - INI-style key-value pairs with sections.
+    - YAML-like structures with indentation.
+    - Custom formats specific to certain applications (such as Unix-like
+        systems, where ``.conf`` is a strong convention for "This is a
+        configuration file").
+- Rule of thumb:
+    - If the file follows a standard format like INI or YAML, consider using
+        dedicated parsers.
+"""
+
+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 CONF content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CONF file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the CONF file.
+    """
+    return stub.read(path, format_name='CONF')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to CONF at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CONF file on disk.
+    data : JSONData
+        Data to write as CONF. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the CONF file.
+    """
+    return stub.write(path, data, format_name='CONF')

{etlplus-0.12.9 → etlplus-0.12.10}/etlplus/file/csv.py

@@ -1,7 +1,19 @@
 """
 :mod:`etlplus.file.csv` module.
 
-Helpers for reading/writing CSV files.
+Helpers for reading/writing Comma-Separated Values (CSV) files.
+
+Notes
+-----
+- A CSV file is a plain text file that uses commas to separate values.
+- Common cases:
+    - Each line in the file represents a single record.
+    - The first line often contains headers that define the column names.
+    - Values may be enclosed in quotes, especially if they contain commas
+        or special characters.
+- Rule of thumb:
+    - If the file follows the CSV specification, use this module for
+        reading and writing.
 """
 
 from __future__ import annotations

{etlplus-0.12.9 → etlplus-0.12.10}/etlplus/file/dat.py

@@ -1,7 +1,19 @@
 """
 :mod:`etlplus.file.dat` module.
 
-Helpers for reading/writing DAT (data) files.
+Helpers for reading/writing data (DAT) files.
+
+Notes
+-----
+- A “DAT-formatted” file is a generic data file that may use various
+    delimiters or fixed-width formats.
+- Common cases:
+    - Delimited text files (e.g., CSV, TSV).
+    - Fixed-width formatted files.
+    - Custom formats specific to certain applications.
+- Rule of thumb:
+    - If the file does not follow a specific standard format, use this module
+        for reading and writing.
 """
 
 from __future__ import annotations