etlplus 0.12.1__py3-none-any.whl → 0.12.10__py3-none-any.whl

etlplus/file/enums.py

@@ -61,21 +61,119 @@ class FileFormat(CoercibleStrEnum):
 
     # -- Constants -- #
 
-    AVRO = 'avro'
-    CSV = 'csv'
-    FEATHER = 'feather'
-    GZ = 'gz'
-    JSON = 'json'
-    NDJSON = 'ndjson'
-    ORC = 'orc'
-    PARQUET = 'parquet'
-    TSV = 'tsv'
-    TXT = 'txt'
-    XLS = 'xls'
-    XLSX = 'xlsx'
-    ZIP = 'zip'
-    XML = 'xml'
-    YAML = 'yaml'
+    # Stubbed / placeholder
+    STUB = 'stub'  # Placeholder format for tests & future connectors
+
+    # Tabular & delimited text
+    CSV = 'csv'  # Comma-Separated Values
+    DAT = 'dat'  # Generic data file, often delimited or fixed-width
+    FWF = 'fwf'  # Fixed-Width Formatted
+    PSV = 'psv'  # Pipe-Separated Values
+    TAB = 'tab'  # Often synonymous with TSV
+    TSV = 'tsv'  # Tab-Separated Values
+    TXT = 'txt'  # Plain text, often delimited or fixed-width
+
+    # Semi-structured text
+    CFG = 'cfg'  # Config-style key-value pairs
+    CONF = 'conf'  # Config-style key-value pairs
+    INI = 'ini'  # INI-style key-value pairs
+    JSON = 'json'  # JavaScript Object Notation
+    NDJSON = 'ndjson'  # Newline-Delimited JSON
+    PROPS = 'properties'  # Java-style key-value pairs
+    TOML = 'toml'  # Tom's Obvious Minimal Language
+    XML = 'xml'  # Extensible Markup Language
+    YAML = 'yaml'  # YAML Ain't Markup Language
+
+    # Columnar / analytics-friendly
+    ARROW = 'arrow'  # Apache Arrow IPC
+    FEATHER = 'feather'  # Apache Arrow Feather
+    ORC = 'orc'  # Optimized Row Columnar; common in Hadoop
+    PARQUET = 'parquet'  # Apache Parquet; common in Big Data
+
+    # Binary serialization & interchange
+    AVRO = 'avro'  # Apache Avro
+    BSON = 'bson'  # Binary JSON; common with MongoDB exports/dumps
+    CBOR = 'cbor'  # Concise Binary Object Representation
+    ION = 'ion'  # Amazon Ion
+    MSGPACK = 'msgpack'  # MessagePack
+    PB = 'pb'  # Protocol Buffers (Google Protobuf)
+    PBF = 'pbf'  # Protocolbuffer Binary Format; often for GIS data
+    PROTO = 'proto'  # Protocol Buffers schema; often in .pb / .bin
+
+    # Databases & embedded storage
+    ACCDB = 'accdb'  # Microsoft Access database file (newer format)
+    DUCKDB = 'duckdb'  # DuckDB database file
+    MDB = 'mdb'  # Microsoft Access database file (older format)
+    SQLITE = 'sqlite'  # SQLite database file
+
+    # Spreadsheets
+    NUMBERS = 'numbers'  # Apple Numbers spreadsheet
+    ODS = 'ods'  # OpenDocument Spreadsheet
+    WKS = 'wks'  # Lotus 1-2-3 spreadsheet
+    XLS = 'xls'  # Microsoft Excel (BIFF); read-only
+    XLSM = 'xlsm'  # Microsoft Excel Macro-Enabled (Open XML)
+    XLSX = 'xlsx'  # Microsoft Excel (Open XML)
+
+    # Statistical / scientific / numeric computing
+    DTA = 'dta'  # Stata data file
+    H5 = 'h5'  # Hierarchical Data Format
+    MAT = 'mat'  # MATLAB data file
+    NC = 'nc'  # NetCDF data file
+    RDA = 'rda'  # RData workspace/object bundle
+    RDS = 'rds'  # R data file
+    SAS7BDAT = 'sas7bdat'  # SAS data file
+    SAV = 'sav'  # SPSS data file
+    SYLK = 'sylk'  # Symbolic Link (SYmbolic LinK)
+    XPT = 'xpt'  # SAS Transport file
+    ZSAV = 'zsav'  # Compressed SPSS data file
+
+    # Time series and financial data
+    CAMT = 'camt'  # ISO 20022 Cash Management messages
+    FXT = 'fxt'  # Forex time series data
+    MT940 = 'mt940'  # SWIFT MT940 bank statement format
+    MT942 = 'mt942'  # SWIFT MT942 interim transaction report format
+    OFX = 'ofx'  # Open Financial Exchange
+    QFX = 'qfx'  # Quicken Financial Exchange
+    QIF = 'qif'  # Quicken Interchange Format
+    QQQ = 'qqq'  # QuantQuote historical data
+    TRR = 'trr'  # Trade and transaction reports
+    TSDB = 'tsdb'  # Time series database export
+
+    # Geospatial data
+    GEOJSON = 'geojson'  # GeoJSON
+    GEOTIFF = 'geotiff'  # GeoTIFF
+    GML = 'gml'  # Geography Markup Language
+    GPKG = 'gpkg'  # GeoPackage
+    GPX = 'gpx'  # GPS Exchange Format
+    KML = 'kml'  # Keyhole Markup Language
+    LAS = 'las'  # LiDAR Aerial Survey
+    LAZ = 'laz'  # LASzip (compressed LAS)
+    OSM = 'osm'  # OpenStreetMap XML Data
+    SHP = 'shp'  # ESRI Shapefile
+    WKB = 'wkb'  # Well-Known Binary
+    WKT = 'wkt'  # Well-Known Text
+
+    # Logs & event streams
+    EVT = 'evt'  # Windows Event Trace Log (pre-Vista)
+    EVTX = 'evtx'  # Windows Event Trace Log (Vista and later)
+    LOG = 'log'  # Generic log file
+    PCAP = 'pcap'  # Packet Capture file
+    PCAPPNG = 'pcapng'  # Packet Capture Next Generation file
+    SLOG = 'slog'  # Structured log file
+    W3CLOG = 'w3clog'  # W3C Extended Log File Format
+
+    # “Data archives” & packaging
+    _7Z = '7z'  # 7-Zip archive
+    GZ = 'gz'  # Gzip-compressed file
+    JAR = 'jar'  # Java archive
+    RAR = 'rar'  # RAR archive
+    SIT = 'sit'  # StuffIt archive
+    SITX = 'sitx'  # StuffIt X archive
+    TAR = 'tar'  # TAR archive
+    TGZ = 'tgz'  # Gzip-compressed TAR archive
+    ZIP = 'zip'  # ZIP archive
+
+    # Domain-specific & less common
 
     # -- Class Methods -- #
 
@@ -104,6 +202,7 @@ class FileFormat(CoercibleStrEnum):
             '.orc': 'orc',
             '.parquet': 'parquet',
             '.pq': 'parquet',
+            '.stub': 'stub',
             '.tsv': 'tsv',
             '.txt': 'txt',
             '.xls': 'xls',

etlplus/file/feather.py

@@ -1,18 +1,30 @@
 """
 :mod:`etlplus.file.feather` module.
 
-Helpers for reading/writing Feather files.
+Helpers for reading/writing Apache Arrow Feather (FEATHER) files.
+
+Notes
+-----
+- A FEATHER file is a binary file format designed for efficient
+    on-disk storage of data frames, built on top of Apache Arrow.
+- Common cases:
+    - Fast read/write operations for data frames.
+    - Interoperability between different data analysis tools.
+    - Storage of large datasets with efficient compression.
+- Rule of thumb:
+    - If the file follows the Apache Arrow Feather specification, use this
+        module for reading and writing.
 """
 
 from __future__ import annotations
 
 from pathlib import Path
-from typing import Any
 from typing import cast
 
 from ..types import JSONData
-from ..types import JSONDict
 from ..types import JSONList
+from ._imports import get_pandas
+from ._io import normalize_records
 
 # SECTION: EXPORTS ========================================================== #
 
@@ -23,51 +35,6 @@ __all__ = [
 ]
 
 
-# SECTION: INTERNAL CONSTANTS =============================================== #
-
-
-_PANDAS_CACHE: dict[str, Any] = {}
-
-
-# SECTION: INTERNAL FUNCTIONS =============================================== #
-
-
-def _get_pandas() -> Any:
-    """
-    Return the pandas module, importing it on first use.
-
-    Raises an informative ImportError if the optional dependency is missing.
-    """
-    mod = _PANDAS_CACHE.get('mod')
-    if mod is not None:  # pragma: no cover - tiny branch
-        return mod
-    try:
-        _pd = __import__('pandas')  # type: ignore[assignment]
-    except ImportError as e:  # pragma: no cover
-        raise ImportError(
-            'Feather support requires optional dependency "pandas".\n'
-            'Install with: pip install pandas',
-        ) from e
-    _PANDAS_CACHE['mod'] = _pd
-
-    return _pd
-
-
-def _normalize_records(data: JSONData) -> JSONList:
-    """
-    Normalize JSON payloads into a list of dictionaries.
-
-    Raises TypeError when payloads contain non-dict items.
-    """
-    if isinstance(data, list):
-        if not all(isinstance(item, dict) for item in data):
-            raise TypeError(
-                'Feather payloads must contain only objects (dicts)',
-            )
-        return cast(JSONList, data)
-    return [cast(JSONDict, data)]
-
-
 # SECTION: FUNCTIONS ======================================================== #
 
 
@@ -92,7 +59,7 @@ def read(
     ImportError
         When optional dependency "pyarrow" is missing.
     """
-    pandas = _get_pandas()
+    pandas = get_pandas('Feather')
     try:
         frame = pandas.read_feather(path)
     except ImportError as e:  # pragma: no cover
@@ -127,11 +94,11 @@ def write(
     ImportError
         When optional dependency "pyarrow" is missing.
     """
-    records = _normalize_records(data)
+    records = normalize_records(data, 'Feather')
     if not records:
         return 0
 
-    pandas = _get_pandas()
+    pandas = get_pandas('Feather')
     path.parent.mkdir(parents=True, exist_ok=True)
     frame = pandas.DataFrame.from_records(records)
     try:

etlplus/file/fwf.py

@@ -0,0 +1,77 @@
+"""
+:mod:`etlplus.file.fwf` module.
+
+Helpers for reading/writing Fixed-Width Fields (FWF) files.
+
+Notes
+-----
+- An FWF file is a text file format where each field has a fixed width.
+- Common cases:
+    - Data files from legacy systems.
+    - Reports with aligned columns.
+    - Data exchange in mainframe environments.
+- Rule of thumb:
+    - If the file follows the FWF 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 FWF content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the FWF file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the FWF file.
+    """
+    return stub.read(path, format_name='FWF')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to FWF file at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the FWF file on disk.
+    data : JSONData
+        Data to write as FWF file. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the FWF file.
+    """
+    return stub.write(path, data, format_name='FWF')

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')