etlplus 0.10.4__py3-none-any.whl → 0.12.2__py3-none-any.whl

etlplus/file/enums.py

@@ -0,0 +1,238 @@
+"""
+:mod:`etlplus.file.enums` module.
+
+File-specific enums and helpers.
+"""
+
+from __future__ import annotations
+
+from pathlib import PurePath
+
+from ..enums import CoercibleStrEnum
+from ..types import StrStrMap
+
+# SECTION: EXPORTS ========================================================= #
+
+__all__ = [
+    'CompressionFormat',
+    'FileFormat',
+    'infer_file_format_and_compression',
+]
+
+
+# SECTION: ENUMS ============================================================ #
+
+
+class CompressionFormat(CoercibleStrEnum):
+    """Supported compression formats."""
+
+    # -- Constants -- #
+
+    GZ = 'gz'
+    ZIP = 'zip'
+
+    # -- Class Methods -- #
+
+    @classmethod
+    def aliases(cls) -> StrStrMap:
+        """
+        Return a mapping of common aliases for each enum member.
+
+        Returns
+        -------
+        StrStrMap
+            A mapping of alias names to their corresponding enum member names.
+        """
+        return {
+            # File extensions
+            '.gz': 'gz',
+            '.gzip': 'gz',
+            '.zip': 'zip',
+            # MIME types
+            'application/gzip': 'gz',
+            'application/x-gzip': 'gz',
+            'application/zip': 'zip',
+            'application/x-zip-compressed': 'zip',
+        }
+
+
+class FileFormat(CoercibleStrEnum):
+    """Supported file formats for extraction."""
+
+    # -- 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'
+
+    # -- Class Methods -- #
+
+    @classmethod
+    def aliases(cls) -> StrStrMap:
+        """
+        Return a mapping of common aliases for each enum member.
+
+        Returns
+        -------
+        StrStrMap
+            A mapping of alias names to their corresponding enum member names.
+        """
+        return {
+            # Common shorthand
+            'parq': 'parquet',
+            'yml': 'yaml',
+            # File extensions
+            '.avro': 'avro',
+            '.csv': 'csv',
+            '.feather': 'feather',
+            '.gz': 'gz',
+            '.json': 'json',
+            '.jsonl': 'ndjson',
+            '.ndjson': 'ndjson',
+            '.orc': 'orc',
+            '.parquet': 'parquet',
+            '.pq': 'parquet',
+            '.tsv': 'tsv',
+            '.txt': 'txt',
+            '.xls': 'xls',
+            '.xlsx': 'xlsx',
+            '.zip': 'zip',
+            '.xml': 'xml',
+            '.yaml': 'yaml',
+            '.yml': 'yaml',
+            # MIME types
+            'application/avro': 'avro',
+            'application/csv': 'csv',
+            'application/feather': 'feather',
+            'application/gzip': 'gz',
+            'application/json': 'json',
+            'application/jsonlines': 'ndjson',
+            'application/ndjson': 'ndjson',
+            'application/orc': 'orc',
+            'application/parquet': 'parquet',
+            'application/vnd.apache.avro': 'avro',
+            'application/vnd.apache.parquet': 'parquet',
+            'application/vnd.apache.arrow.file': 'feather',
+            'application/vnd.apache.orc': 'orc',
+            'application/vnd.ms-excel': 'xls',
+            (
+                'application/vnd.openxmlformats-'
+                'officedocument.spreadsheetml.sheet'
+            ): 'xlsx',
+            'application/x-avro': 'avro',
+            'application/x-csv': 'csv',
+            'application/x-feather': 'feather',
+            'application/x-orc': 'orc',
+            'application/x-ndjson': 'ndjson',
+            'application/x-parquet': 'parquet',
+            'application/x-yaml': 'yaml',
+            'application/xml': 'xml',
+            'application/zip': 'zip',
+            'text/csv': 'csv',
+            'text/plain': 'txt',
+            'text/tab-separated-values': 'tsv',
+            'text/tsv': 'tsv',
+            'text/xml': 'xml',
+            'text/yaml': 'yaml',
+        }
+
+
+# SECTION: INTERNAL CONSTANTS =============================================== #
+
+
+# Compression formats that are also file formats.
+_COMPRESSION_FILE_FORMATS: set[FileFormat] = {
+    FileFormat.GZ,
+    FileFormat.ZIP,
+}
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+# TODO: Convert to a method on FileFormat or CompressionFormat?
+def infer_file_format_and_compression(
+    value: object,
+    filename: object | None = None,
+) -> tuple[FileFormat | None, CompressionFormat | None]:
+    """
+    Infer data format and compression from a filename, extension, or MIME type.
+
+    Parameters
+    ----------
+    value : object
+        A filename, extension, MIME type, or existing enum member.
+    filename : object | None, optional
+        A filename to consult for extension-based inference (e.g. when
+        ``value`` is ``application/octet-stream``).
+
+    Returns
+    -------
+    tuple[FileFormat | None, CompressionFormat | None]
+        The inferred data format and compression, if any.
+    """
+    if isinstance(value, FileFormat):
+        if value in _COMPRESSION_FILE_FORMATS:
+            return None, CompressionFormat.coerce(value.value)
+        return value, None
+    if isinstance(value, CompressionFormat):
+        return None, value
+
+    text = str(value).strip()
+    if not text:
+        return None, None
+
+    normalized = text.casefold()
+    mime = normalized.split(';', 1)[0].strip()
+
+    is_octet_stream = mime == 'application/octet-stream'
+    compression = CompressionFormat.try_coerce(mime)
+    fmt = None if is_octet_stream else FileFormat.try_coerce(mime)
+
+    is_mime = mime.startswith(
+        (
+            'application/',
+            'text/',
+            'audio/',
+            'image/',
+            'video/',
+            'multipart/',
+        ),
+    )
+    suffix_source: object | None = filename if filename is not None else text
+    if is_mime and filename is None:
+        suffix_source = None
+
+    suffixes = (
+        PurePath(str(suffix_source)).suffixes
+        if suffix_source is not None
+        else []
+    )
+    if suffixes:
+        normalized_suffixes = [suffix.casefold() for suffix in suffixes]
+        compression = (
+            CompressionFormat.try_coerce(normalized_suffixes[-1])
+            or compression
+        )
+        if compression is not None:
+            normalized_suffixes = normalized_suffixes[:-1]
+        if normalized_suffixes:
+            fmt = FileFormat.try_coerce(normalized_suffixes[-1]) or fmt
+
+    if fmt in _COMPRESSION_FILE_FORMATS:
+        compression = compression or CompressionFormat.coerce(fmt.value)
+        fmt = None
+
+    return fmt, compression

etlplus/file/feather.py

@@ -0,0 +1,144 @@
+"""
+:mod:`etlplus.file.feather` module.
+
+Helpers for reading/writing Feather files.
+"""
+
+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
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'read',
+    'write',
+]
+
+
+# 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 ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONList:
+    """
+    Read Feather content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the Feather file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the Feather file.
+
+    Raises
+    ------
+    ImportError
+        When optional dependency "pyarrow" is missing.
+    """
+    pandas = _get_pandas()
+    try:
+        frame = pandas.read_feather(path)
+    except ImportError as e:  # pragma: no cover
+        raise ImportError(
+            'Feather support requires optional dependency "pyarrow".\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 Feather at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the Feather file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+
+    Raises
+    ------
+    ImportError
+        When optional dependency "pyarrow" is missing.
+    """
+    records = _normalize_records(data)
+    if not records:
+        return 0
+
+    pandas = _get_pandas()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    frame = pandas.DataFrame.from_records(records)
+    try:
+        frame.to_feather(path)
+    except ImportError as e:  # pragma: no cover
+        raise ImportError(
+            'Feather support requires optional dependency "pyarrow".\n'
+            'Install with: pip install pyarrow',
+        ) from e
+    return len(records)

etlplus/file/gz.py

@@ -0,0 +1,123 @@
+"""
+:mod:`etlplus.file.gz` module.
+
+Helpers for reading/writing GZ files.
+"""
+
+from __future__ import annotations
+
+import gzip
+import tempfile
+from pathlib import Path
+
+from ..types import JSONData
+from .enums import CompressionFormat
+from .enums import FileFormat
+from .enums import infer_file_format_and_compression
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'read',
+    'write',
+]
+
+
+# SECTION: INTERNAL FUNCTIONS =============================================== #
+
+
+def _resolve_format(
+    path: Path,
+) -> FileFormat:
+    """
+    Resolve the inner file format from a .gz filename.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the GZ file on disk.
+
+    Returns
+    -------
+    FileFormat
+        The inferred inner file format.
+
+    Raises
+    ------
+    ValueError
+        If the file format cannot be inferred from the filename.
+    """
+    fmt, compression = infer_file_format_and_compression(path)
+    if compression is not CompressionFormat.GZ:
+        raise ValueError(f'Not a gzip file: {path}')
+    if fmt is None:
+        raise ValueError(
+            f'Cannot infer file format from compressed file {path!r}',
+        )
+    return fmt
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONData:
+    """
+    Read GZ content from ``path`` and parse the inner payload.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the GZ file on disk.
+
+    Returns
+    -------
+    JSONData
+        Parsed payload.
+    """
+    fmt = _resolve_format(path)
+    with gzip.open(path, 'rb') as handle:
+        payload = handle.read()
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        tmp_path = Path(tmpdir) / f'payload.{fmt.value}'
+        tmp_path.write_bytes(payload)
+        from .core import File
+
+        return File(tmp_path, fmt).read()
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` to GZ at ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the GZ file on disk.
+    data : JSONData
+        Data to write.
+
+    Returns
+    -------
+    int
+        Number of records written.
+    """
+    fmt = _resolve_format(path)
+    with tempfile.TemporaryDirectory() as tmpdir:
+        tmp_path = Path(tmpdir) / f'payload.{fmt.value}'
+        from .core import File
+
+        count = File(tmp_path, fmt).write(data)
+        payload = tmp_path.read_bytes()
+
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with gzip.open(path, 'wb') as handle:
+        handle.write(payload)
+
+    return count

etlplus/file/json.py

@@ -0,0 +1,98 @@
+"""
+:mod:`etlplus.file.json` module.
+
+Helpers for reading/writing JSON files.
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import cast
+
+from ..types import JSONData
+from ..types import JSONDict
+from ..types import JSONList
+from ..utils import count_records
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'read',
+    'write',
+]
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONData:
+    """
+    Read JSON content from ``path``.
+
+    Validates that the JSON root is a dict or a list of dicts.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the JSON file on disk.
+
+    Returns
+    -------
+    JSONData
+        The structured data read from the JSON file.
+
+    Raises
+    ------
+    TypeError
+        If the JSON root is not an object or an array of objects.
+    """
+    with path.open('r', encoding='utf-8') as handle:
+        loaded = json.load(handle)
+
+    if isinstance(loaded, dict):
+        return cast(JSONDict, loaded)
+    if isinstance(loaded, list):
+        if all(isinstance(item, dict) for item in loaded):
+            return cast(JSONList, loaded)
+        raise TypeError(
+            'JSON array must contain only objects (dicts) when loading file',
+        )
+    raise TypeError(
+        'JSON root must be an object or an array of objects when loading file',
+    )
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write ``data`` as formatted JSON to ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the JSON file on disk.
+    data : JSONData
+        Data to serialize as JSON.
+
+    Returns
+    -------
+    int
+        The number of records written to the JSON file.
+    """
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open('w', encoding='utf-8') as handle:
+        json.dump(
+            data,
+            handle,
+            indent=2,
+            ensure_ascii=False,
+        )
+        handle.write('\n')
+
+    return count_records(data)

etlplus/file/ndjson.py

@@ -0,0 +1,109 @@
+"""
+:mod:`etlplus.file.ndjson` module.
+
+Helpers for reading/writing NDJSON files.
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import cast
+
+from ..types import JSONData
+from ..types import JSONDict
+from ..types import JSONList
+from ..utils import count_records
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'read',
+    'write',
+]
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONList:
+    """
+    Read NDJSON content from ``path``.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the NDJSON file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the NDJSON file.
+
+    Raises
+    ------
+    TypeError
+        If any line in the NDJSON file is not a JSON object (dict).
+    """
+    rows: JSONList = []
+    with path.open('r', encoding='utf-8') as handle:
+        for idx, line in enumerate(handle, start=1):
+            text = line.strip()
+            if not text:
+                continue
+            payload = json.loads(text)
+            if not isinstance(payload, dict):
+                raise TypeError(
+                    f'NDJSON lines must be objects (dicts) (line {idx})',
+                )
+            rows.append(cast(JSONDict, payload))
+    return rows
+
+
+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
+    ------
+    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)]
+
+    if not rows:
+        return 0
+
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open('w', encoding='utf-8') as handle:
+        for row in rows:
+            handle.write(json.dumps(row, ensure_ascii=False))
+            handle.write('\n')
+
+    return count_records(rows)