etlplus 0.9.0__py3-none-any.whl → 0.10.4__py3-none-any.whl

etlplus/cli/commands.py

@@ -443,9 +443,9 @@ def extract_cmd(
         Source (JSON payload, file/folder path, URL/URI, or - for STDIN)
         from which to extract data. Default is ``-``.
     source_format : SourceFormatOption, optional
-        Source data format. Overrides the inferred format (``csv``, ``json``,
-        ``parquet``, ``xml``) based on filename extension or STDIN content.
-        Default is ``None``.
+        Data source format. Overrides the inferred format (``csv``, ``json``,
+        etc.) based on filename extension or STDIN content. Default is
+        ``None``.
     source_type : SourceTypeOption, optional
         Data source type. Overrides the inferred type (``api``, ``database``,
         ``file``, ``folder``) based on URI/URL schema. Default is ``None``.
@@ -523,15 +523,15 @@ def load_cmd(
     ctx : typer.Context
         The Typer context.
     source_format : SourceFormatOption, optional
-        Source data format. Overrides the inferred format (``csv``, ``json``,
-        ``parquet``, ``xml``) based on STDIN content. Default is ``None``.
+        Data source format. Overrides the inferred format (``csv``, ``json``,
+        etc.) based on filename extension or STDIN content. Default is
+        ``None``.
     target : TargetArg, optional
         Target (file/folder path, URL/URI, or - for STDOUT) into which to load
         data. Default is ``-``.
     target_format : TargetFormatOption, optional
-        Format of the target data. Overrides the inferred format (``csv``,
-        ``json``, ``parquet``, ``xml``) based on filename extension. Default is
-        ``None``.
+        Target data format. Overrides the inferred format (``csv``, ``json``,
+        etc.) based on filename extension. Default is ``None``.
     target_type : TargetTypeOption, optional
         Data target type. Overrides the inferred type (``api``, ``database``,
         ``file``, ``folder``) based on URI/URL schema. Default is ``None``.
@@ -760,9 +760,9 @@ def transform_cmd(
         Source (JSON payload, file/folder path, URL/URI, or - for STDIN) from
         which to extract data. Default is ``-``.
     source_format : SourceFormatOption, optional
-        Source data format. Overrides the inferred format (``csv``, ``json``,
-        ``parquet``, ``xml``) based on filename extension or STDIN content.
-        Default is ``None``.
+        Data source format. Overrides the inferred format (``csv``, ``json``,
+        etc.) based on filename extension or STDIN content. Default is
+        ``None``.
     source_type : SourceTypeOption, optional
         Data source type. Overrides the inferred type (``api``, ``database``,
         ``file``, ``folder``) based on URI/URL schema. Default is ``None``.
@@ -770,9 +770,8 @@ def transform_cmd(
         Target (file/folder path, URL/URI, or - for STDOUT) into which to load
         data. Default is ``-``.
     target_format : TargetFormatOption, optional
-        Format of the target data. Overrides the inferred format (``csv``,
-        ``json``, ``parquet``, ``xml``) based on filename extension. Default is
-        ``None``.
+        Target data format. Overrides the inferred format (``csv``, ``json``,
+        etc.) based on filename extension. Default is ``None``.
     target_type : TargetTypeOption, optional
         Data target type. Overrides the inferred type (``api``, ``database``,
         ``file``, ``folder``) based on URI/URL schema. Default is ``None``.
@@ -876,11 +875,12 @@ def validate_cmd(
     source : SourceArg
         Data source to validate (path, JSON payload, or - for STDIN).
     source_format : SourceFormatOption, optional
-        Format of the source. Overrides filename-based inference when provided.
-        Default is ``None``.
-    source_type : SourceTypeOption, optional
-        Override the inferred source type (file, database, api). Default is
+        Data source format. Overrides the inferred format (``csv``, ``json``,
+        etc.) based on filename extension or STDIN content. Default is
         ``None``.
+    source_type : SourceTypeOption, optional
+        Data source type. Overrides the inferred type (``api``, ``database``,
+        ``file``, ``folder``) based on URI/URL schema. Default is ``None``.
     output : OutputOption, optional
         Output file for validated output (- for STDOUT). Default is ``None``.
 

etlplus/enums.py

@@ -8,6 +8,7 @@ from __future__ import annotations
 
 import enum
 import operator as _op
+from pathlib import PurePath
 from statistics import fmean
 from typing import Self
 
@@ -19,16 +20,21 @@ from .types import StrStrMap
 
 
 __all__ = [
+    # Enums
     'AggregateName',
     'CoercibleStrEnum',
+    'CompressionFormat',
     'DataConnectorType',
     'FileFormat',
     'HttpMethod',
     'OperatorName',
     'PipelineStep',
+    # Functions
+    'coerce_compression_format',
     'coerce_data_connector_type',
     'coerce_file_format',
     'coerce_http_method',
+    'infer_file_format_and_compression',
 ]
 
 
@@ -172,6 +178,39 @@ class AggregateName(CoercibleStrEnum):
         return lambda xs, n: (fmean(xs) if xs else 0.0)
 
 
+class CompressionFormat(CoercibleStrEnum):
+    """Supported compression formats for data files."""
+
+    # -- 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 DataConnectorType(CoercibleStrEnum):
     """Supported data connector types."""
 
@@ -208,8 +247,19 @@ 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'
 
@@ -227,11 +277,61 @@ class FileFormat(CoercibleStrEnum):
         """
         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
-            'text/csv': 'csv',
+            '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',
         }
 
 
@@ -365,6 +465,13 @@ class PipelineStep(CoercibleStrEnum):
 # SECTION: INTERNAL CONSTANTS ============================================== #
 
 
+# Compression formats that are also file formats.
+_COMPRESSION_FILE_FORMATS: set[FileFormat] = {
+    FileFormat.GZ,
+    FileFormat.ZIP,
+}
+
+
 # Precomputed order index for PipelineStep; avoids recomputing on each access.
 _PIPELINE_ORDER_INDEX: dict[PipelineStep, int] = {
     PipelineStep.FILTER: 0,
@@ -402,6 +509,18 @@ def coerce_file_format(
     return FileFormat.coerce(file_format)
 
 
+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)
+
+
 def coerce_http_method(
     http_method: HttpMethod | str,
 ) -> HttpMethod:
@@ -412,3 +531,78 @@ def coerce_http_method(
     :meth:`HttpMethod.coerce` going forward.
     """
     return HttpMethod.coerce(http_method)
+
+
+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.py

@@ -16,6 +16,7 @@ from typing import Any
 from typing import cast
 
 from .enums import FileFormat
+from .enums import infer_file_format_and_compression
 from .types import JSONData
 from .types import JSONDict
 from .types import JSONList
@@ -33,15 +34,6 @@ __all__ = ['File']
 
 _DEFAULT_XML_ROOT = 'root'
 
-# Map common filename extensions to FileFormat (used for inference)
-_EXT_TO_FORMAT: dict[str, FileFormat] = {
-    'csv': FileFormat.CSV,
-    'json': FileFormat.JSON,
-    'xml': FileFormat.XML,
-    'yaml': FileFormat.YAML,
-    'yml': FileFormat.YAML,
-}
-
 # Optional YAML support (lazy-loaded to avoid hard dependency)
 # Cached access function to avoid global statements.
 _YAML_CACHE: dict[str, Any] = {}
@@ -246,14 +238,17 @@ class File:
         ValueError
             If the extension is unknown or unsupported.
         """
-        ext = self.path.suffix.lstrip('.').casefold()
-        try:
-            return _EXT_TO_FORMAT[ext]
-        except KeyError as e:
+        fmt, compression = infer_file_format_and_compression(self.path)
+        if fmt is not None:
+            return fmt
+        if compression is not None:
             raise ValueError(
-                'Cannot infer file format from '
-                f'extension {self.path.suffix!r}',
-            ) from e
+                'Cannot infer file format from compressed file '
+                f'{self.path!r} with compression {compression.value!r}',
+            )
+        raise ValueError(
+            f'Cannot infer file format from extension {self.path.suffix!r}',
+        )
 
     # -- Instance Methods (Generic API) -- #
 

{etlplus-0.9.0.dist-info → etlplus-0.10.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.9.0
+Version: 0.10.4
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team

{etlplus-0.9.0.dist-info → etlplus-0.10.4.dist-info}/RECORD

@@ -1,9 +1,9 @@
 etlplus/__init__.py,sha256=M2gScnyir6WOMAh_EuoQIiAzdcTls0_5hbd_Q6of8I0,1021
 etlplus/__main__.py,sha256=btoROneNiigyfBU7BSzPKZ1R9gzBMpxcpsbPwmuHwTM,479
 etlplus/__version__.py,sha256=1E0GMK_yUWCMQFKxXjTvyMwofi0qT2k4CDNiHWiymWE,327
-etlplus/enums.py,sha256=V_j18Ud2BCXpFsBk2pZGrvCVrvAMJ7uja1z9fppFGso,10175
+etlplus/enums.py,sha256=8hzprOLyeCCzlHaXpG4VfgmxPSEdlZeOnHLFzBneKNs,15969
 etlplus/extract.py,sha256=f44JdHhNTACxgn44USx05paKTwq7LQY-V4wANCW9hVM,6173
-etlplus/file.py,sha256=RxIAsGDN4f_vNA2B5-ct88JNd_ISAyYbooIRE5DstS8,17972
+etlplus/file.py,sha256=B-zebTrIFDKaaKzA9Fq5-L0JwDNYa2T--_6veR3N03s,17939
 etlplus/load.py,sha256=R_y0_vtsEo1bwxWVQu2bfhB5ZIJoIoWu2ycCdvY4RnE,8737
 etlplus/mixins.py,sha256=ifGpHwWv7U00yqGf-kN93vJax2IiK4jaGtTsPsO3Oak,1350
 etlplus/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -31,7 +31,7 @@ etlplus/api/rate_limiting/__init__.py,sha256=ZySB1dZettEDnWvI1EHf_TZ9L08M_kKsNR-
 etlplus/api/rate_limiting/config.py,sha256=2b4wIynblN-1EyMqI4aXa71SljzSjXYh5N1Nngr3jOg,9406
 etlplus/api/rate_limiting/rate_limiter.py,sha256=Uxozqd_Ej5Lsj-M-mLT2WexChgWh7x35_YP10yqYPQA,7159
 etlplus/cli/__init__.py,sha256=J97-Rv931IL1_b4AXnB7Fbbd7HKnHBpx18NQfC_kE6c,299
-etlplus/cli/commands.py,sha256=_nias9eSMZoTBiicXDNEkWLYfzd4-CcO2j_xPPxghls,24632
+etlplus/cli/commands.py,sha256=BK2qmFsser6AXOgEvpiadrYMIiwviAzqkSxMlBhRXRw,24670
 etlplus/cli/constants.py,sha256=KIZj7J2tNf5mJbkqAdZmu5FXYW2FQmxwgeOKWc3-3Hg,1944
 etlplus/cli/handlers.py,sha256=K0GazvrPgocJ-63HZqF0xhyJk8TB1Gcj-eIbWltXKRU,17759
 etlplus/cli/io.py,sha256=7sldiZz4-Geomge5IO_XYykXPa6UiORfUWzLCdQePG8,7846
@@ -57,9 +57,9 @@ etlplus/templates/ddl.sql.j2,sha256=s8fMWvcb4eaJVXkifuib1aQPljtZ8buuyB_uA-ZdU3Q,
 etlplus/templates/view.sql.j2,sha256=Iy8DHfhq5yyvrUKDxqp_aHIEXY4Tm6j4wT7YDEFWAhk,2180
 etlplus/validation/__init__.py,sha256=Pe5Xg1_EA4uiNZGYu5WTF3j7odjmyxnAJ8rcioaplSQ,1254
 etlplus/validation/utils.py,sha256=Mtqg449VIke0ziy_wd2r6yrwJzQkA1iulZC87FzXMjo,10201
-etlplus-0.9.0.dist-info/licenses/LICENSE,sha256=MuNO63i6kWmgnV2pbP2SLqP54mk1BGmu7CmbtxMmT-U,1069
-etlplus-0.9.0.dist-info/METADATA,sha256=ynMgjG7Wv_xkP0fBaAOj3-rpUgJHwZ7UOzCxoU8CBeE,21035
-etlplus-0.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-etlplus-0.9.0.dist-info/entry_points.txt,sha256=6w-2-jzuPa55spzK34h-UKh2JTEShh38adFRONNP9QE,45
-etlplus-0.9.0.dist-info/top_level.txt,sha256=aWWF-udn_sLGuHTM6W6MLh99ArS9ROkUWO8Mi8y1_2U,8
-etlplus-0.9.0.dist-info/RECORD,,
+etlplus-0.10.4.dist-info/licenses/LICENSE,sha256=MuNO63i6kWmgnV2pbP2SLqP54mk1BGmu7CmbtxMmT-U,1069
+etlplus-0.10.4.dist-info/METADATA,sha256=M_lQUZ5o-JaD1KuZk_t0LeHbaOj_SdqqaJQSbDCW-zY,21036
+etlplus-0.10.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+etlplus-0.10.4.dist-info/entry_points.txt,sha256=6w-2-jzuPa55spzK34h-UKh2JTEShh38adFRONNP9QE,45
+etlplus-0.10.4.dist-info/top_level.txt,sha256=aWWF-udn_sLGuHTM6W6MLh99ArS9ROkUWO8Mi8y1_2U,8
+etlplus-0.10.4.dist-info/RECORD,,