etlplus 0.10.4__py3-none-any.whl → 0.11.1__py3-none-any.whl

etlplus/file/csv.py

@@ -0,0 +1,82 @@
+"""
+:mod:`etlplus.file.csv` module.
+
+CSV read/write helpers.
+"""
+
+from __future__ import annotations
+
+import csv
+from pathlib import Path
+from typing import cast
+
+from ..types import JSONData
+from ..types import JSONDict
+from ..types import JSONList
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONList:
+    """
+    Load CSV content as a list of dictionaries.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the CSV file on disk.
+
+    Returns
+    -------
+    JSONList
+        The list of dictionaries read from the CSV file.
+    """
+    with path.open('r', encoding='utf-8', newline='') as handle:
+        reader: csv.DictReader[str] = csv.DictReader(handle)
+        rows: JSONList = []
+        for row in reader:
+            if not any(row.values()):
+                continue
+            rows.append(cast(JSONDict, dict(row)))
+    return rows
+
+
+def write(
+    path: Path,
+    data: JSONData,
+) -> int:
+    """
+    Write CSV rows to ``path`` and return the number of rows.
+
+    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.
+    """
+    rows: list[JSONDict]
+    if isinstance(data, list):
+        rows = [row for row in data if isinstance(row, dict)]
+    else:
+        rows = [data]
+
+    if not rows:
+        return 0
+
+    fieldnames = sorted({key for row in rows for key in row})
+    with path.open('w', encoding='utf-8', newline='') as handle:
+        writer = csv.DictWriter(handle, fieldnames=fieldnames)
+        writer.writeheader()
+        for row in rows:
+            writer.writerow({field: row.get(field) for field in fieldnames})
+
+    return len(rows)

etlplus/file/enums.py

@@ -0,0 +1,266 @@
+"""
+: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',
+    'coerce_compression_format',
+    'coerce_file_format',
+    '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: 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,
+    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/json.py

@@ -0,0 +1,87 @@
+"""
+:mod:`etlplus.file.json` module.
+
+JSON read/write helpers.
+"""
+
+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: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONData:
+    """
+    Load and validate JSON payloads from ``path``.
+
+    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/xml.py

@@ -0,0 +1,165 @@
+"""
+:mod:`etlplus.file.xml` module.
+
+XML read/write helpers.
+"""
+
+from __future__ import annotations
+
+import xml.etree.ElementTree as ET
+from pathlib import Path
+from typing import Any
+
+from ..types import JSONData
+from ..types import JSONDict
+from ..utils import count_records
+
+# SECTION: CONSTANTS ======================================================== #
+
+
+DEFAULT_XML_ROOT = 'root'
+
+
+# SECTION: INTERNAL FUNCTIONS =============================================== #
+
+
+def _dict_to_element(
+    name: str,
+    payload: Any,
+) -> ET.Element:
+    """
+    Convert a dictionary-like payload into an XML element.
+
+    Parameters
+    ----------
+    name : str
+        Name of the XML element.
+    payload : Any
+        The data to include in the XML element.
+
+    Returns
+    -------
+    ET.Element
+        The constructed XML element.
+    """
+    element = ET.Element(name)
+
+    if isinstance(payload, dict):
+        text = payload.get('text')
+        if text is not None:
+            element.text = str(text)
+
+        for key, value in payload.items():
+            if key == 'text':
+                continue
+            if key.startswith('@'):
+                element.set(key[1:], str(value))
+                continue
+            if isinstance(value, list):
+                for item in value:
+                    element.append(_dict_to_element(key, item))
+            else:
+                element.append(_dict_to_element(key, value))
+    elif isinstance(payload, list):
+        for item in payload:
+            element.append(_dict_to_element('item', item))
+    elif payload is not None:
+        element.text = str(payload)
+
+    return element
+
+
+def _element_to_dict(
+    element: ET.Element,
+) -> JSONDict:
+    """
+    Convert an XML element into a nested dictionary.
+
+    Parameters
+    ----------
+    element : ET.Element
+        XML element to convert.
+
+    Returns
+    -------
+    JSONDict
+        Nested dictionary representation of the XML element.
+    """
+    result: JSONDict = {}
+    text = (element.text or '').strip()
+    if text:
+        result['text'] = text
+
+    for child in element:
+        child_data = _element_to_dict(child)
+        tag = child.tag
+        if tag in result:
+            existing = result[tag]
+            if isinstance(existing, list):
+                existing.append(child_data)
+            else:
+                result[tag] = [existing, child_data]
+        else:
+            result[tag] = child_data
+
+    for key, value in element.attrib.items():
+        if key in result:
+            result[f'@{key}'] = value
+        else:
+            result[key] = value
+    return result
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def read(
+    path: Path,
+) -> JSONDict:
+    """
+    Parse XML document at ``path`` into a nested dictionary.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the XML file on disk.
+
+    Returns
+    -------
+    JSONDict
+        Nested dictionary representation of the XML file.
+    """
+    tree = ET.parse(path)
+    root = tree.getroot()
+
+    return {root.tag: _element_to_dict(root)}
+
+
+def write(path: Path, data: JSONData, *, root_tag: str) -> int:
+    """
+    Write ``data`` as XML to ``path`` and return record count.
+
+    Parameters
+    ----------
+    path : Path
+        Path to the XML file on disk.
+    data : JSONData
+        Data to write as XML.
+    root_tag : str
+        Root tag name to use when writing XML files.
+
+    Returns
+    -------
+    int
+        The number of records written to the XML file.
+    """
+    if isinstance(data, dict) and len(data) == 1:
+        root_name, payload = next(iter(data.items()))
+        root_element = _dict_to_element(str(root_name), payload)
+    else:
+        root_element = _dict_to_element(root_tag, data)
+
+    tree = ET.ElementTree(root_element)
+    tree.write(path, encoding='utf-8', xml_declaration=True)
+
+    return count_records(data)