etlplus 0.11.2__tar.gz → 0.11.10__tar.gz

{etlplus-0.11.2/etlplus.egg-info → etlplus-0.11.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.11.2
+Version: 0.11.10
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team

{etlplus-0.11.2 → etlplus-0.11.10}/etlplus/cli/handlers.py

@@ -570,7 +570,7 @@ def transform_handler(
     data = transform(payload, cast(TransformOperations, operations_payload))
 
     if target and target != '-':
-        File.write_file(target, data, file_format=target_format)
+        File(target, file_format=target_format).write(data)
         print(f'Data transformed and saved to {target}')
         return 0
 

{etlplus-0.11.2 → etlplus-0.11.10}/etlplus/database/ddl.py

@@ -203,7 +203,7 @@ def load_table_spec(
         raise ValueError('Spec must be .json, .yml, or .yaml')
 
     try:
-        spec = File.read_file(spec_path)
+        spec = File(spec_path).read()
     except ImportError as e:
         if suffix in {'.yml', '.yaml'}:
             raise RuntimeError(

{etlplus-0.11.2 → etlplus-0.11.10}/etlplus/database/engine.py

@@ -113,7 +113,7 @@ def load_database_url_from_config(
     ValueError
         If no connection string/URL/DSN is found for the specified entry.
     """
-    cfg = File.read_file(Path(path))
+    cfg = File(Path(path)).read()
     if not isinstance(cfg, Mapping):
         raise TypeError('Database config must be a mapping')
 

{etlplus-0.11.2 → etlplus-0.11.10}/etlplus/database/schema.py

@@ -260,7 +260,7 @@ def load_table_specs(
     list[TableSpec]
         A list of TableSpec instances parsed from the YAML file.
     """
-    data = File.read_file(Path(path))
+    data = File(Path(path)).read()
     if not data:
         return []
 

{etlplus-0.11.2 → etlplus-0.11.10}/etlplus/file/__init__.py

@@ -9,7 +9,6 @@ from __future__ import annotations
 from .core import File
 from .enums import CompressionFormat
 from .enums import FileFormat
-from .enums import coerce_file_format
 from .enums import infer_file_format_and_compression
 
 # SECTION: EXPORTS ========================================================== #
@@ -22,6 +21,5 @@ __all__ = [
     'CompressionFormat',
     'FileFormat',
     # Functions
-    'coerce_file_format',
     'infer_file_format_and_compression',
 ]

etlplus-0.11.10/etlplus/file/avro.py

@@ -0,0 +1,59 @@
+"""
+:mod:`etlplus.file.avro` module.
+
+Stub helpers for AVRO read/write.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ..types import JSONData
+
+# SECTION: EXPORTS ========================================================== #
+
+
+def read(path: Path) -> JSONData:
+    """
+    Read AVRO content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the AVRO file on disk.
+
+    Returns
+    -------
+    JSONData
+        Parsed payload.
+
+    Raises
+    ------
+    NotImplementedError
+        AVRO :func:`read` is not implemented yet.
+    """
+    raise NotImplementedError('AVRO read is not implemented yet')
+
+
+def write(path: Path, data: JSONData) -> int:
+    """
+    Write ``data`` to AVRO at ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the AVRO file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+
+    Raises
+    ------
+    NotImplementedError
+        AVRO :func:`write` is not implemented yet.
+    """
+    raise NotImplementedError('AVRO write is not implemented yet')

{etlplus-0.11.2 → etlplus-0.11.10}/etlplus/file/core.py

@@ -11,11 +11,21 @@ from dataclasses import dataclass
 from pathlib import Path
 
 from ..types import JSONData
-from ..types import StrPath
+from . import avro
 from . import csv
+from . import feather
+from . import gz
 from . import json
+from . import ndjson
+from . import orc
+from . import parquet
+from . import tsv
+from . import txt
+from . import xls
+from . import xlsx
 from . import xml
 from . import yaml
+from . import zip
 from .enums import FileFormat
 from .enums import infer_file_format_and_compression
 
@@ -43,7 +53,15 @@ class File:
         Path to the file on disk.
     file_format : FileFormat | None, optional
         Explicit format. If omitted, the format is inferred from the file
-        extension (``.csv``, ``.json``, or ``.xml``).
+        extension (``.csv``, ``.json``, etc.).
+
+    Parameters
+    ----------
+    path : StrPath
+        Path to the file on disk.
+    file_format : FileFormat | str | None, optional
+        Explicit format. If omitted, the format is inferred from the file
+        extension (``.csv``, ``.json``, etc.).
     """
 
     # -- Attributes -- #
@@ -62,16 +80,10 @@ class File:
         extension is unknown, the attribute is left as ``None`` and will be
         validated later by :meth:`_ensure_format`.
         """
-        # Normalize incoming path (allow str in constructor) to Path.
-        if isinstance(self.path, str):
-            self.path = Path(self.path)
-
+        self.path = Path(self.path)
+        self.file_format = self._coerce_format(self.file_format)
         if self.file_format is None:
-            try:
-                self.file_format = self._guess_format()
-            except ValueError:
-                # Leave as None; _ensure_format() will raise on use if needed.
-                pass
+            self.file_format = self._maybe_guess_format()
 
     # -- Internal Instance Methods -- #
 
@@ -84,6 +96,28 @@ class File:
         if not self.path.exists():
             raise FileNotFoundError(f'File not found: {self.path}')
 
+    def _coerce_format(
+        self,
+        file_format: FileFormat | str | None,
+    ) -> FileFormat | None:
+        """
+        Normalize the file format input.
+
+        Parameters
+        ----------
+        file_format : FileFormat | str | None
+            File format specifier. Strings are coerced into
+            :class:`FileFormat`.
+
+        Returns
+        -------
+        FileFormat | None
+            A normalized file format, or ``None`` when unspecified.
+        """
+        if file_format is None or isinstance(file_format, FileFormat):
+            return file_format
+        return FileFormat.coerce(file_format)
+
     def _ensure_format(self) -> FileFormat:
         """
         Resolve the active format, guessing from extension if needed.
@@ -125,7 +159,22 @@ class File:
             f'Cannot infer file format from extension {self.path.suffix!r}',
         )
 
-    # -- Instance Methods (Generic API) -- #
+    def _maybe_guess_format(self) -> FileFormat | None:
+        """
+        Try to infer the format, returning ``None`` if it cannot be inferred.
+
+        Returns
+        -------
+        FileFormat | None
+            The inferred format, or ``None`` if inference fails.
+        """
+        try:
+            return self._guess_format()
+        except ValueError:
+            # Leave as None; _ensure_format() will raise on use if needed.
+            return None
+
+    # -- Instance Methods -- #
 
     def read(self) -> JSONData:
         """
@@ -144,14 +193,36 @@ class File:
         self._assert_exists()
         fmt = self._ensure_format()
         match fmt:
+            case FileFormat.AVRO:
+                return avro.read(self.path)
             case FileFormat.CSV:
                 return csv.read(self.path)
+            case FileFormat.FEATHER:
+                return feather.read(self.path)
+            case FileFormat.GZ:
+                return gz.read(self.path)
             case FileFormat.JSON:
                 return json.read(self.path)
+            case FileFormat.NDJSON:
+                return ndjson.read(self.path)
+            case FileFormat.ORC:
+                return orc.read(self.path)
+            case FileFormat.PARQUET:
+                return parquet.read(self.path)
+            case FileFormat.TSV:
+                return tsv.read(self.path)
+            case FileFormat.TXT:
+                return txt.read(self.path)
+            case FileFormat.XLS:
+                return xls.read(self.path)
+            case FileFormat.XLSX:
+                return xlsx.read(self.path)
             case FileFormat.XML:
                 return xml.read(self.path)
             case FileFormat.YAML:
                 return yaml.read(self.path)
+            case FileFormat.ZIP:
+                return zip.read(self.path)
         raise ValueError(f'Unsupported format: {fmt}')
 
     def write(
@@ -183,105 +254,34 @@ class File:
         """
         fmt = self._ensure_format()
         match fmt:
+            case FileFormat.AVRO:
+                return avro.write(self.path, data)
             case FileFormat.CSV:
                 return csv.write(self.path, data)
+            case FileFormat.FEATHER:
+                return feather.write(self.path, data)
+            case FileFormat.GZ:
+                return gz.write(self.path, data)
             case FileFormat.JSON:
                 return json.write(self.path, data)
+            case FileFormat.NDJSON:
+                return ndjson.write(self.path, data)
+            case FileFormat.ORC:
+                return orc.write(self.path, data)
+            case FileFormat.PARQUET:
+                return parquet.write(self.path, data)
+            case FileFormat.TSV:
+                return tsv.write(self.path, data)
+            case FileFormat.TXT:
+                return txt.write(self.path, data)
+            case FileFormat.XLS:
+                return xls.write(self.path, data)
+            case FileFormat.XLSX:
+                return xlsx.write(self.path, data)
             case FileFormat.XML:
                 return xml.write(self.path, data, root_tag=root_tag)
             case FileFormat.YAML:
                 return yaml.write(self.path, data)
+            case FileFormat.ZIP:
+                return zip.write(self.path, data)
         raise ValueError(f'Unsupported format: {fmt}')
-
-    # -- Class Methods -- #
-
-    @classmethod
-    def from_path(
-        cls,
-        path: StrPath,
-        *,
-        file_format: FileFormat | str | None = None,
-    ) -> File:
-        """
-        Create a :class:`File` from any path-like and optional format.
-
-        Parameters
-        ----------
-        path : StrPath
-            Path to the file on disk.
-        file_format : FileFormat | str | None, optional
-            Explicit format. If omitted, the format is inferred from the file
-            extension (``.csv``, ``.json``, or ``.xml``).
-
-        Returns
-        -------
-        File
-            The constructed :class:`File` instance.
-        """
-        resolved = Path(path)
-        ff: FileFormat | None
-        if isinstance(file_format, str):
-            ff = FileFormat.coerce(file_format)
-        else:
-            ff = file_format
-
-        return cls(resolved, ff)
-
-    @classmethod
-    def read_file(
-        cls,
-        path: StrPath,
-        file_format: FileFormat | str | None = None,
-    ) -> JSONData:
-        """
-        Read structured data.
-
-        Parameters
-        ----------
-        path : StrPath
-            Path to the file on disk.
-        file_format : FileFormat | str | None, optional
-            Explicit format. If omitted, the format is inferred from the file
-            extension (``.csv``, ``.json``, or ``.xml``).
-
-        Returns
-        -------
-        JSONData
-            The structured data read from the file.
-        """
-        return cls.from_path(path, file_format=file_format).read()
-
-    @classmethod
-    def write_file(
-        cls,
-        path: StrPath,
-        data: JSONData,
-        file_format: FileFormat | str | None = None,
-        *,
-        root_tag: str = xml.DEFAULT_XML_ROOT,
-    ) -> int:
-        """
-        Write structured data and count written records.
-
-        Parameters
-        ----------
-        path : StrPath
-            Path to the file on disk.
-        data : JSONData
-            Data to write to the file.
-        file_format : FileFormat | str | None, optional
-            Explicit format. If omitted, the format is inferred from the file
-            extension (``.csv``, ``.json``, or ``.xml``).
-        root_tag : str, optional
-            Root tag name to use when writing XML files. Defaults to
-            ``'root'``.
-
-        Returns
-        -------
-        int
-            The number of records written to the file.
-        """
-        return cls.from_path(path, file_format=file_format).write(
-            data,
-            root_tag=root_tag,
-        )

{etlplus-0.11.2 → etlplus-0.11.10}/etlplus/file/enums.py

@@ -16,8 +16,6 @@ from ..types import StrStrMap
 __all__ = [
     'CompressionFormat',
     'FileFormat',
-    'coerce_compression_format',
-    'coerce_file_format',
     'infer_file_format_and_compression',
 ]
 
@@ -164,32 +162,6 @@ _COMPRESSION_FILE_FORMATS: set[FileFormat] = {
 # SECTION: FUNCTIONS ======================================================== #
 
 
-# TODO: Deprecate in favor of using the enum methods directly.
-def coerce_compression_format(
-    compression_format: CompressionFormat | str,
-) -> CompressionFormat:
-    """
-    Normalize textual compression format values to :class:`CompressionFormat`.
-
-    This thin wrapper is kept for backward compatibility; prefer
-    :meth:`CompressionFormat.coerce` going forward.
-    """
-    return CompressionFormat.coerce(compression_format)
-
-
-# TODO: Deprecate in favor of using the enum methods directly.
-def coerce_file_format(
-    file_format: FileFormat | str,
-) -> FileFormat:
-    """
-    Normalize textual file format values to :class:`FileFormat`.
-
-    This thin wrapper is kept for backward compatibility; prefer
-    :meth:`FileFormat.coerce` going forward.
-    """
-    return FileFormat.coerce(file_format)
-
-
 # TODO: Convert to a method on FileFormat or CompressionFormat?
 def infer_file_format_and_compression(
     value: object,

etlplus-0.11.10/etlplus/file/feather.py

@@ -0,0 +1,59 @@
+"""
+:mod:`etlplus.file.feather` module.
+
+Stub helpers for FEATHER read/write.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ..types import JSONData
+
+# SECTION: EXPORTS ========================================================== #
+
+
+def read(path: Path) -> JSONData:
+    """
+    Read FEATHER content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the FEATHER file on disk.
+
+    Returns
+    -------
+    JSONData
+        Parsed payload.
+
+    Raises
+    ------
+    NotImplementedError
+        FEATHER :func:`read` is not implemented yet.
+    """
+    raise NotImplementedError('FEATHER read is not implemented yet')
+
+
+def write(path: Path, data: JSONData) -> int:
+    """
+    Write ``data`` to FEATHER at ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the FEATHER file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+
+    Raises
+    ------
+    NotImplementedError
+        FEATHER :func:`write` is not implemented yet.
+    """
+    raise NotImplementedError('FEATHER write is not implemented yet')

etlplus-0.11.10/etlplus/file/gz.py

@@ -0,0 +1,59 @@
+"""
+:mod:`etlplus.file.gz` module.
+
+Stub helpers for GZ read/write.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ..types import JSONData
+
+# SECTION: EXPORTS ========================================================== #
+
+
+def read(path: Path) -> JSONData:
+    """
+    Read GZ content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the GZ file on disk.
+
+    Returns
+    -------
+    JSONData
+        Parsed payload.
+
+    Raises
+    ------
+    NotImplementedError
+        GZ :func:`read` is not implemented yet.
+    """
+    raise NotImplementedError('GZ read is not implemented yet')
+
+
+def write(path: Path, data: JSONData) -> int:
+    """
+    Write ``data`` to GZ at ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the GZ file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+
+    Raises
+    ------
+    NotImplementedError
+        GZ :func:`write` is not implemented yet.
+    """
+    raise NotImplementedError('GZ write is not implemented yet')

etlplus-0.11.10/etlplus/file/ndjson.py

@@ -0,0 +1,59 @@
+"""
+:mod:`etlplus.file.ndjson` module.
+
+Stub helpers for NDJSON read/write.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ..types import JSONData
+
+# SECTION: EXPORTS ========================================================== #
+
+
+def read(path: Path) -> JSONData:
+    """
+    Read NDJSON content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the NDJSON file on disk.
+
+    Returns
+    -------
+    JSONData
+        Parsed payload.
+
+    Raises
+    ------
+    NotImplementedError
+        NDJSON :func:`read` is not implemented yet.
+    """
+    raise NotImplementedError('NDJSON read is not implemented yet')
+
+
+def write(path: Path, data: JSONData) -> int:
+    """
+    Write ``data`` to NDJSON at ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the NDJSON file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+
+    Raises
+    ------
+    NotImplementedError
+        NDJSON :func:`write` is not implemented yet.
+    """
+    raise NotImplementedError('NDJSON write is not implemented yet')

etlplus-0.11.10/etlplus/file/orc.py

@@ -0,0 +1,59 @@
+"""
+:mod:`etlplus.file.orc` module.
+
+Stub helpers for ORC read/write.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ..types import JSONData
+
+# SECTION: EXPORTS ========================================================== #
+
+
+def read(path: Path) -> JSONData:
+    """
+    Read ORC content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the ORC file on disk.
+
+    Returns
+    -------
+    JSONData
+        Parsed payload.
+
+    Raises
+    ------
+    NotImplementedError
+        ORC :func:`read` is not implemented yet.
+    """
+    raise NotImplementedError('ORC read is not implemented yet')
+
+
+def write(path: Path, data: JSONData) -> int:
+    """
+    Write ``data`` to ORC at ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the ORC file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+
+    Raises
+    ------
+    NotImplementedError
+        ORC :func:`write` is not implemented yet.
+    """
+    raise NotImplementedError('ORC write is not implemented yet')