etlplus 0.9.0__py3-none-any.whl → 0.9.2__py3-none-any.whl

etlplus/file/parquet.py

@@ -0,0 +1,113 @@
+"""
+:mod:`etlplus.file.parquet` module.
+
+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
+
+from pathlib import Path
+from typing import cast
+
+from ..types import JSONData
+from ..types import JSONList
+from ._imports import get_pandas
+from ._io import normalize_records
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'read',
+    'write',
+]
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONList:
+    """
+    Read Parquet content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PARQUET file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the Parquet file.
+
+    Raises
+    ------
+    ImportError
+        If optional dependencies for Parquet support are missing.
+    """
+    pandas = get_pandas('Parquet')
+    try:
+        frame = pandas.read_parquet(path)
+    except ImportError as e:  # pragma: no cover
+        raise ImportError(
+            'Parquet support requires optional dependency '
+            '"pyarrow" or "fastparquet".\n'
+            'Install with: pip install pyarrow',
+        ) from e
+    return cast(JSONList, frame.to_dict(orient='records'))
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to Parquet at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PARQUET file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+
+    Raises
+    ------
+    ImportError
+        If optional dependencies for Parquet support are missing.
+    """
+    records = normalize_records(data, 'Parquet')
+    if not records:
+        return 0
+
+    pandas = get_pandas('Parquet')
+    path.parent.mkdir(parents=True, exist_ok=True)
+    frame = pandas.DataFrame.from_records(records)
+    try:
+        frame.to_parquet(path, index=False)
+    except ImportError as e:  # pragma: no cover
+        raise ImportError(
+            'Parquet support requires optional dependency '
+            '"pyarrow" or "fastparquet".\n'
+            'Install with: pip install pyarrow',
+        ) from e
+    return len(records)

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')

etlplus/file/properties.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.properties` module.
+
+Helpers for reading/writing properties (PROPERTIES) files.
+
+Notes
+-----
+- A PROPERTIES file is a properties file that typically uses key-value pairs,
+    often with a simple syntax.
+- Common cases:
+    - Java-style properties files with ``key=value`` pairs.
+    - INI-style files without sections.
+    - Custom formats specific to certain applications.
+- Rule of thumb:
+    - If the file follows a standard format like INI, 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 PROPERTIES content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PROPERTIES file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the PROPERTIES file.
+    """
+    return stub.read(path, format_name='PROPERTIES')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to PROPERTIES at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PROPERTIES file on disk.
+    data : JSONData
+        Data to write as PROPERTIES. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the PROPERTIES file.
+    """
+    return stub.write(path, data, format_name='PROPERTIES')

etlplus/file/proto.py

@@ -0,0 +1,77 @@
+"""
+:mod:`etlplus.file.proto` module.
+
+Helpers for reading/writing Protocol Buffers schema (PROTO) files.
+
+Notes
+-----
+- A PROTO file defines the structure of Protocol Buffers messages.
+- Common cases:
+    - Defining message formats for data interchange.
+    - Generating code for serialization/deserialization.
+    - Documenting data structures in distributed systems.
+- Rule of thumb:
+    - If the file follows the Protocol Buffers schema 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 PROTO content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PROTO file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the PROTO file.
+    """
+    return stub.read(path, format_name='PROTO')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to PROTO at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PROTO file on disk.
+    data : JSONData
+        Data to write as PROTO. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the PROTO file.
+    """
+    return stub.write(path, data, format_name='PROTO')

etlplus/file/psv.py

@@ -0,0 +1,79 @@
+"""
+:mod:`etlplus.file.psv` module.
+
+Helpers for reading/writing Pipe-Separated Values (PSV) files.
+
+Notes
+-----
+- A PSV file is a plain text file that uses the pipe character (`|`) 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 pipes
+        or special characters.
+- Rule of thumb:
+    - If the file follows the PSV 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 PSV content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PSV file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the PSV file.
+    """
+    return stub.read(path, format_name='PSV')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to PSV file at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the PSV file on disk.
+    data : JSONData
+        Data to write as PSV file. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the PSV file.
+    """
+    return stub.write(path, data, format_name='PSV')

etlplus/file/rda.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.rda` module.
+
+Helpers for reading/writing RData workspace/object bundle (RDA) files.
+
+Notes
+-----
+- A RDA file is a binary file format used by R to store workspace objects,
+    including data frames, lists, and other R objects.
+- Common cases:
+    - Storing R data objects for later use.
+    - Sharing R datasets between users.
+    - Loading R data into Python for analysis.
+- Rule of thumb:
+    - If the file follows the RDA 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 RDA content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the RDA file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the RDA file.
+    """
+    return stub.read(path, format_name='RDA')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to RDA file at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the RDA file on disk.
+    data : JSONData
+        Data to write as RDA file. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the RDA file.
+    """
+    return stub.write(path, data, format_name='RDA')

etlplus/file/rds.py

@@ -0,0 +1,78 @@
+"""
+:mod:`etlplus.file.rds` module.
+
+Helpers for reading/writing R (RDS) data files.
+
+Notes
+-----
+- An RDS file is a binary file format used by R to store a single R object,
+    such as a data frame, list, or vector.
+- Common cases:
+    - Storing R objects for later use.
+    - Sharing R data between users.
+    - Loading R data into Python for analysis.
+- Rule of thumb:
+    - If the file follows the RDS 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 RDS content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the RDS file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the RDS file.
+    """
+    return stub.read(path, format_name='RDS')
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to RDS file at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the RDS file on disk.
+    data : JSONData
+        Data to write as RDS file. Should be a list of dictionaries or a
+        single dictionary.
+
+    Returns
+    -------
+    int
+        The number of rows written to the RDS file.
+    """
+    return stub.write(path, data, format_name='RDS')