etlplus 0.12.3__py3-none-any.whl → 0.12.10__py3-none-any.whl

etlplus/file/ini.py

@@ -0,0 +1,79 @@
+"""
+:mod:`etlplus.file.ini` module.
+
+Helpers for reading/writing initialization (INI) files.
+
+Notes
+-----
+- An INI file is a simple configuration file format that uses sections,
+    properties, and values.
+- Common cases:
+    - Sections are denoted by square brackets (e.g., ``[section]``).
+    - Properties are key-value pairs (e.g., ``key=value``).
+    - Comments are often indicated by semicolons (``;``) or hash symbols
+        (``#``).
+- Rule of thumb:
+    - If the file follows the INI 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 INI content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the INI file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the INI file.
+    """
+    return stub.read(path, format_name='INI')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to INI at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the INI file on disk.
+    data : JSONData
+        Data to write as INI. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the INI file.
+    """
+    return stub.write(path, data, format_name='INI')

etlplus/file/ion.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.ion` module.
+
+Helpers for reading/writing Amazon Ion (ION) files.
+
+Notes
+-----
+- An ION file is a richly-typed, self-describing data format developed by
+    Amazon, designed for efficient data interchange and storage.
+- Common cases:
+    - Data serialization for distributed systems.
+    - Interoperability between different programming languages.
+    - Handling of complex data types beyond standard JSON capabilities.
+- Rule of thumb:
+    - If the file follows the Amazon Ion 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 ION content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the ION file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the ION file.
+    """
+    return stub.read(path, format_name='ION')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to ION at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the ION file on disk.
+    data : JSONData
+        Data to write as ION. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the ION file.
+    """
+    return stub.write(path, data, format_name='ION')

etlplus/file/json.py

@@ -1,7 +1,19 @@
 """
 :mod:`etlplus.file.json` module.
 
-Helpers for reading/writing JSON files.
+Helpers for reading/writing JavaScript Object Notation (JSON) files.
+
+Notes
+-----
+- A JSON file is a widely used data interchange format that uses
+    human-readable text to represent structured data.
+- Common cases:
+    - Data interchange between web applications and servers.
+    - Configuration files for applications.
+    - Data storage for NoSQL databases.
+- Rule of thumb:
+    - If the file follows the JSON specification, use this module for
+        reading and writing.
 """
 
 from __future__ import annotations

etlplus/file/log.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.log` module.
+
+Helpers for reading/writing generic log (LOG) files.
+
+Notes
+-----
+- A LOG file is a plain text file that contains log messages generated by
+    applications or systems.
+- Common cases:
+    - Each line in the file represents a single log entry.
+    - Log entries may include timestamps, log levels, and messages.
+    - Formats may vary widely depending on the application generating the logs.
+- Rule of thumb:
+    - If the file is a generic log file, 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 LOG content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the LOG file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the LOG file.
+    """
+    return stub.read(path, format_name='LOG')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to LOG at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the LOG file on disk.
+    data : JSONData
+        Data to write as LOG. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the LOG file.
+    """
+    return stub.write(path, data, format_name='LOG')

etlplus/file/mdb.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.mdb` module.
+
+Helpers for reading/writing newer Microsoft Access database (MDB) files.
+
+Notes
+-----
+- An MDB file is a proprietary database file format used by Microsoft Access
+    2003 and earlier.
+- 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 MDB 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 CSV content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CSV file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the CSV file.
+    """
+    return stub.read(path, format_name='DAT')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to CSV at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CSV file on disk.
+    data : JSONData
+        Data to write as CSV. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the CSV file.
+    """
+    return stub.write(path, data, format_name='DAT')

etlplus/file/msgpack.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.msgpack` module.
+
+Helpers for reading/writing MessagePack (MSGPACK) files.
+
+Notes
+-----
+- A MsgPack file is a binary serialization format that is more compact than
+    JSON.
+- Common cases:
+    - Efficient data storage and transmission.
+    - Inter-process communication.
+    - Data serialization in performance-critical applications.
+- Rule of thumb:
+    - If the file follows the MsgPack 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 MsgPack content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the MsgPack file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the MsgPack file.
+    """
+    return stub.read(path, format_name='MSGPACK')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to MsgPack at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the MsgPack file on disk.
+    data : JSONData
+        Data to write as MsgPack. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the MsgPack file.
+    """
+    return stub.write(path, data, format_name='MSGPACK')

etlplus/file/ndjson.py

@@ -1,7 +1,18 @@
 """
 :mod:`etlplus.file.ndjson` module.
 
-Helpers for reading/writing NDJSON files.
+Helpers for reading/writing Newline Delimited JSON (NDJSON) files.
+
+Notes
+-----
+- An NDJSON file is a format where each line is a separate JSON object.
+- Common cases:
+    - Streaming JSON data.
+    - Log files with JSON entries.
+    - Large datasets that are processed line-by-line.
+- Rule of thumb:
+    - If the file follows the NDJSON specification, use this module for
+        reading and writing.
 """
 
 from __future__ import annotations
@@ -14,6 +25,7 @@ from ..types import JSONData
 from ..types import JSONDict
 from ..types import JSONList
 from ..utils import count_records
+from ._io import normalize_records
 
 # SECTION: EXPORTS ========================================================== #
 
@@ -81,21 +93,8 @@ def write(
     -------
     int
         Number of records written.
-
-    Raises
-    ------
-    TypeError
-        If ``data`` is a list containing non-dict items.
     """
-    rows: JSONList
-    if isinstance(data, list):
-        if not all(isinstance(item, dict) for item in data):
-            raise TypeError(
-                'NDJSON payloads must contain only objects (dicts)',
-            )
-        rows = cast(JSONList, data)
-    else:
-        rows = [cast(JSONDict, data)]
+    rows = normalize_records(data, 'NDJSON')
 
     if not rows:
         return 0

etlplus/file/orc.py

@@ -1,7 +1,19 @@
 """
 :mod:`etlplus.file.orc` module.
 
-Helpers for reading/writing ORC files.
+Helpers for reading/writing Optimized Row Columnar (ORC) files.
+
+Notes
+-----
+- An ORC file is a columnar storage file format optimized for Big Data
+    processing.
+- Common cases:
+    - Efficient storage and retrieval of large datasets.
+    - Integration with big data frameworks like Apache Hive and Apache Spark.
+    - Compression and performance optimization for analytical queries.
+- Rule of thumb:
+    - If the file follows the ORC specification, use this module for reading
+        and writing.
 """
 
 from __future__ import annotations
@@ -11,8 +23,8 @@ from typing import cast
 
 from ..types import JSONData
 from ..types import JSONList
+from ._imports import get_pandas
 from ._io import normalize_records
-from ._pandas import get_pandas
 
 # SECTION: EXPORTS ========================================================== #
 

etlplus/file/parquet.py

@@ -1,7 +1,19 @@
 """
 :mod:`etlplus.file.parquet` module.
 
-Helpers for reading/writing Parquet files.
+Helpers for reading/writing Apache Parquet (PARQUET) files.
+
+Notes
+-----
+- An Apache Parquet file is a columnar storage file format optimized for Big
+    Data processing.
+- Common cases:
+    - Efficient storage and retrieval of large datasets.
+    - Integration with big data frameworks like Apache Hive and Apache Spark.
+    - Compression and performance optimization for analytical queries.
+- Rule of thumb:
+    - If the file follows the Apache Parquet specification, use this module for
+        reading and writing.
 """
 
 from __future__ import annotations
@@ -11,8 +23,8 @@ from typing import cast
 
 from ..types import JSONData
 from ..types import JSONList
+from ._imports import get_pandas
 from ._io import normalize_records
-from ._pandas import get_pandas
 
 # SECTION: EXPORTS ========================================================== #
 

etlplus/file/pb.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.pb` module.
+
+Helpers for reading/writing Protocol Buffer (PB) files.
+
+Notes
+-----
+- PB (a.k.a. Protobuff) is a binary serialization format developed by Google
+    for structured data.
+- Common cases:
+    - Data interchange between services.
+    - Efficient storage of structured data.
+    - Communication in distributed systems.
+- Rule of thumb:
+    - If the file follows the Protocol Buffer 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 PB content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PB file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the PB file.
+    """
+    return stub.read(path, format_name='PB')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to PB at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PB file on disk.
+    data : JSONData
+        Data to write as PB. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the PB file.
+    """
+    return stub.write(path, data, format_name='PB')

etlplus/file/pbf.py

@@ -0,0 +1,77 @@
+"""
+:mod:`etlplus.file.pbf` module.
+
+Helpers for reading/writing Protocolbuffer Binary Format (PBF) files.
+
+Notes
+-----
+- PBF is a binary format used primarily for OpenStreetMap (OSM) data.
+- Common cases:
+    - Efficient storage of large OSM datasets.
+    - Fast data interchange for mapping applications.
+    - Compression of OSM data for reduced file size.
+- Rule of thumb:
+    - If the file follows the PBF 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 PBF content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PBF file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the PBF file.
+    """
+    return stub.read(path, format_name='PBF')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to PBF at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PBF file on disk.
+    data : JSONData
+        Data to write as PBF. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the PBF file.
+    """
+    return stub.write(path, data, format_name='PBF')