etlplus 0.17.3__tar.gz → 0.17.4__tar.gz

{etlplus-0.17.3/etlplus.egg-info → etlplus-0.17.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.17.3
+Version: 0.17.4
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team

{etlplus-0.17.3 → etlplus-0.17.4/etlplus.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.17.3
+Version: 0.17.4
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team

{etlplus-0.17.3 → etlplus-0.17.4}/etlplus.egg-info/SOURCES.txt

@@ -229,6 +229,7 @@ tests/unit/database/test_u_database_ddl.py
 tests/unit/database/test_u_database_engine.py
 tests/unit/database/test_u_database_orm.py
 tests/unit/database/test_u_database_schema.py
+tests/unit/file/conftest.py
 tests/unit/file/test_u_file_core.py
 tests/unit/file/test_u_file_enums.py
 tests/unit/file/test_u_file_yaml.py

{etlplus-0.17.3 → etlplus-0.17.4}/tests/integration/conftest.py

@@ -1,7 +1,8 @@
 """
 :mod:`tests.integration.conftest` module.
 
-Configures pytest-based integration tests and provides shared fixtures.
+Define shared fixtures and helpers for pytest-based integration tests of
+:mod:`etlplus`.
 
 Notes
 -----

{etlplus-0.17.3 → etlplus-0.17.4}/tests/smoke/conftest.py

@@ -1,7 +1,12 @@
 """
 :mod:`tests.smoke.conftest` module.
 
-Shared fixtures for smoke tests.
+Define shared fixtures and helpers for pytest-based smoke tests of
+:mod:`etlplus`.
+
+Notes
+-----
+- Fixtures are designed for reuse and DRY test setup.
 """
 
 from __future__ import annotations

{etlplus-0.17.3 → etlplus-0.17.4}/tests/unit/api/conftest.py

@@ -1,13 +1,13 @@
 """
 :mod:`tests.unit.api.conftest` module.
 
-Configures pytest-based unit tests for and provides shared fixtures for
+Define shared fixtures and helpers for pytest-based unit tests of
 :mod:`etlplus.api`.
 
 Notes
 -----
-- Fixtures are designed for reuse and DRY test setup across API-focused
-    unit tests.
+- Fixtures are designed for reuse and DRY test setup across API-focused unit
+    tests.
 """
 
 from __future__ import annotations

{etlplus-0.17.3 → etlplus-0.17.4}/tests/unit/cli/conftest.py

@@ -1,8 +1,8 @@
 """
 :mod:`tests.unit.cli.conftest` module.
 
-Configures pytest-based unit tests and provides shared fixtures for
-:mod:`etlplus.cli` unit tests.
+Define shared fixtures and helpers for pytest-based unit tests of
+:mod:`etlplus.cli`.
 
 Notes
 -----

{etlplus-0.17.3 → etlplus-0.17.4}/tests/unit/conftest.py

@@ -1,7 +1,8 @@
 """
 :mod:`tests.unit.conftest` module.
 
-Configures pytest-based unit tests and provides shared fixtures.
+Define shared fixtures and helpers for pytest-based unit tests of
+:mod:`etlplus`.
 
 Notes
 -----

etlplus-0.17.4/tests/unit/file/conftest.py

@@ -0,0 +1,112 @@
+"""
+:mod:`tests.unit.file.conftest` module.
+
+Define shared fixtures and helpers for pytest-based unit tests of
+:mod:`etlplus.file`.
+
+Notes
+-----
+- Fixtures are designed for reuse and DRY test setup across file-focused unit
+    tests.
+"""
+
+from __future__ import annotations
+
+import math
+import numbers
+
+import pytest
+
+from etlplus.types import JSONData
+from etlplus.types import JSONDict
+
+# SECTION: MARKERS ========================================================== #
+
+
+# Directory-level marker for unit tests.
+pytestmark = pytest.mark.unit
+
+
+# SECTION: HELPERS ========================================================== #
+
+
+def require_optional_modules(*modules: str) -> None:
+    """
+    Skip the test when optional dependencies are missing.
+
+    Parameters
+    ----------
+    *modules : str
+        Module names to verify via ``pytest.importorskip``.
+    """
+    for module in modules:
+        pytest.importorskip(module)
+
+
+def _coerce_numeric_value(value: object) -> object:
+    """Coerce numeric scalars into stable Python numeric types."""
+    if isinstance(value, numbers.Real):
+        try:
+            numeric = float(value)
+            if math.isnan(numeric):
+                return None
+        except (TypeError, ValueError):
+            return value
+        if numeric.is_integer():
+            return int(numeric)
+        return float(numeric)
+    return value
+
+
+def normalize_numeric_records(records: JSONData) -> JSONData:
+    """
+    Normalize numeric record values for deterministic comparisons.
+
+    Parameters
+    ----------
+    records : JSONData
+        Record payloads to normalize.
+
+    Returns
+    -------
+    JSONData
+        Normalized record payloads.
+    """
+    if isinstance(records, list):
+        normalized: list[JSONDict] = []
+        for row in records:
+            if not isinstance(row, dict):
+                normalized.append(row)
+                continue
+            cleaned: JSONDict = {}
+            for key, value in row.items():
+                cleaned[key] = _coerce_numeric_value(value)
+            normalized.append(cleaned)
+        return normalized
+    return records
+
+
+def normalize_xml_payload(payload: JSONData) -> JSONData:
+    """
+    Normalize XML payloads to list-based item structures when possible.
+
+    Parameters
+    ----------
+    payload : JSONData
+        XML payload to normalize.
+
+    Returns
+    -------
+    JSONData
+        Normalized XML payload.
+    """
+    if not isinstance(payload, dict):
+        return payload
+    root = payload.get('root')
+    if not isinstance(root, dict):
+        return payload
+    items = root.get('items')
+    if isinstance(items, dict):
+        root = {**root, 'items': [items]}
+        return {**payload, 'root': root}
+    return payload

{etlplus-0.17.3 → etlplus-0.17.4}/tests/unit/file/test_u_file_core.py

@@ -11,17 +11,24 @@ Notes
 
 from __future__ import annotations
 
-import math
-import numbers
+import sqlite3
+import zipfile
+from os import PathLike
 from pathlib import Path
+from pathlib import PurePath
 from typing import cast
 
 import pytest
 
 from etlplus.file import File
 from etlplus.file import FileFormat
+from etlplus.file import csv as csv_file
+from etlplus.file import json as json_file
+from etlplus.file import xml as xml_file
 from etlplus.types import JSONData
-from etlplus.types import JSONDict
+from tests.unit.file.conftest import normalize_numeric_records
+from tests.unit.file.conftest import normalize_xml_payload
+from tests.unit.file.conftest import require_optional_modules
 
 # SECTION: MARKERS ========================================================== #
 
@@ -299,64 +306,41 @@ FORMAT_CASES: list[FormatCase] = [
     ),
 ]
 
-
-def _coerce_numeric_value(
-    value: object,
-) -> object:
-    """Coerce numeric scalars into stable Python numeric types."""
-    if isinstance(value, numbers.Real):
-        try:
-            numeric = float(value)
-            if math.isnan(numeric):
-                return None
-        except (TypeError, ValueError):
-            return value
-        if numeric.is_integer():
-            return int(numeric)
-        return float(numeric)
-    return value
-
-
-def _normalize_numeric_records(
-    records: JSONData,
-) -> JSONData:
-    """Normalize numeric record values (e.g., floats to ints when integral)."""
-    if isinstance(records, list):
-        normalized: list[JSONDict] = []
-        for row in records:
-            if not isinstance(row, dict):
-                normalized.append(row)
-                continue
-            cleaned: JSONDict = {}
-            for key, value in row.items():
-                cleaned[key] = _coerce_numeric_value(value)
-            normalized.append(cleaned)
-        return normalized
-    return records
-
-
-def _normalize_xml_payload(
-    payload: JSONData,
-) -> JSONData:
-    """Normalize XML payloads to list-based item structures when possible."""
-    if not isinstance(payload, dict):
-        return payload
-    root = payload.get('root')
-    if not isinstance(root, dict):
-        return payload
-    items = root.get('items')
-    if isinstance(items, dict):
-        root = {**root, 'items': [items]}
-        return {**payload, 'root': root}
-    return payload
-
-
-def _require_modules(
-    modules: tuple[str, ...],
-) -> None:
-    """Skip the test when optional dependencies are missing."""
-    for module in modules:
-        pytest.importorskip(module)
+STUBBED_FORMATS: tuple[tuple[FileFormat, str], ...] = (
+    # Permanent stub as formality
+    (FileFormat.STUB, 'data.stub'),
+    # Temporary stubs until implemented
+    (FileFormat.ACCDB, 'data.accdb'),
+    (FileFormat.CFG, 'data.cfg'),
+    (FileFormat.CONF, 'data.conf'),
+    (FileFormat.ION, 'data.ion'),
+    (FileFormat.JINJA2, 'data.jinja2'),
+    (FileFormat.LOG, 'data.log'),
+    (FileFormat.MAT, 'data.mat'),
+    (FileFormat.MDB, 'data.mdb'),
+    # (FileFormat.MDF, 'data.mdf'),
+    (FileFormat.MUSTACHE, 'data.mustache'),
+    (FileFormat.PBF, 'data.pbf'),
+    # (FileFormat.RAW, 'data.raw'),
+    # (FileFormat.RTF, 'data.rtf'),
+    # (FileFormat.SDF, 'data.sdf'),
+    # (FileFormat.SLV, 'data.slv'),
+    (FileFormat.SYLK, 'data.sylk'),
+    # (FileFormat.VCF, 'data.vcf'),
+    (FileFormat.VM, 'data.vm'),
+    # (FileFormat.WSV, 'data.wsv'),
+    (FileFormat.ZSAV, 'data.zsav'),
+)
+
+
+class _DummyPath(PathLike[str]):
+    """Simple PathLike wrapper for StrPath tests."""
+
+    def __init__(self, path: str) -> None:
+        self._path = path
+
+    def __fspath__(self) -> str:
+        return self._path
 
 
 # SECTION: FIXTURES ========================================================= #
@@ -365,31 +349,7 @@ def _require_modules(
 @pytest.fixture(name='stubbed_formats')
 def stubbed_formats_fixture() -> list[tuple[FileFormat, str]]:
     """Return a list of stubbed file formats for testing."""
-    return [
-        # Permanent stub as formality
-        (FileFormat.STUB, 'data.stub'),
-        # Temporary stubs until implemented
-        (FileFormat.ACCDB, 'data.accdb'),
-        (FileFormat.CFG, 'data.cfg'),
-        (FileFormat.CONF, 'data.conf'),
-        (FileFormat.ION, 'data.ion'),
-        (FileFormat.JINJA2, 'data.jinja2'),
-        (FileFormat.LOG, 'data.log'),
-        (FileFormat.MAT, 'data.mat'),
-        (FileFormat.MDB, 'data.mdb'),
-        # (FileFormat.MDF, 'data.mdf'),
-        (FileFormat.MUSTACHE, 'data.mustache'),
-        (FileFormat.PBF, 'data.pbf'),
-        # (FileFormat.RAW, 'data.raw'),
-        # (FileFormat.RTF, 'data.rtf'),
-        # (FileFormat.SDF, 'data.sdf'),
-        # (FileFormat.SLV, 'data.slv'),
-        (FileFormat.SYLK, 'data.sylk'),
-        # (FileFormat.VCF, 'data.vcf'),
-        (FileFormat.VM, 'data.vm'),
-        # (FileFormat.WSV, 'data.wsv'),
-        (FileFormat.ZSAV, 'data.zsav'),
-    ]
+    return list(STUBBED_FORMATS)
 
 
 # SECTION: TESTS ============================================================ #
@@ -421,6 +381,40 @@ class TestFile:
             f.read()
         assert 'compressed file' in str(e.value)
 
+    def test_duckdb_read_fails_with_multiple_tables(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        Test DuckDB reader rejects multiple table databases.
+        """
+        duckdb = pytest.importorskip('duckdb')
+        path = tmp_path / 'multi.duckdb'
+        conn = duckdb.connect(str(path))
+        try:
+            conn.execute('CREATE TABLE one (id INTEGER)')
+            conn.execute('CREATE TABLE two (id INTEGER)')
+        finally:
+            conn.close()
+
+        with pytest.raises(ValueError, match='Multiple tables'):
+            File(path, FileFormat.DUCKDB).read()
+
+    def test_gz_round_trip_json(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        Test JSON round-trip inside a gzip archive.
+        """
+        path = tmp_path / 'data.json.gz'
+        payload = [{'name': 'Ada'}]
+
+        File(path, FileFormat.GZ).write(payload)
+        result = File(path, FileFormat.GZ).read()
+
+        assert result == payload
+
     @pytest.mark.parametrize(
         'filename,expected_format',
         [
@@ -541,7 +535,7 @@ class TestFile:
         requires: tuple[str, ...],
     ) -> None:
         """Test round-trip reads and writes across file formats."""
-        _require_modules(requires)
+        require_optional_modules(*requires)
         path = tmp_path / filename
 
         File(path, file_format).write(payload)
@@ -553,12 +547,57 @@ class TestFile:
             raise
 
         if file_format is FileFormat.XML:
-            result = _normalize_xml_payload(result)
-            expected = _normalize_xml_payload(expected)
+            result = normalize_xml_payload(result)
+            expected = normalize_xml_payload(expected)
         if file_format is FileFormat.XLS:
-            result = _normalize_numeric_records(result)
+            result = normalize_numeric_records(result)
         assert result == expected
 
+    def test_sqlite_read_fails_with_multiple_tables(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        Test SQLite reader rejects multiple table databases.
+        """
+        path = tmp_path / 'multi.sqlite'
+        conn = sqlite3.connect(path)
+        try:
+            conn.execute('CREATE TABLE one (id INTEGER)')
+            conn.execute('CREATE TABLE two (id INTEGER)')
+            conn.commit()
+        finally:
+            conn.close()
+
+        with pytest.raises(ValueError, match='Multiple tables'):
+            File(path, FileFormat.SQLITE).read()
+
+    def test_strpath_support_for_module_helpers(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        Test module helpers accept ``StrPath`` inputs.
+
+        Uses ``str`` and ``PathLike`` inputs to validate normalization.
+        """
+        csv_path = tmp_path / 'data.csv'
+        json_path = tmp_path / 'data.json'
+        xml_path = tmp_path / 'data.xml'
+
+        csv_file.write(str(csv_path), [{'name': 'Ada'}])
+        assert csv_file.read(str(csv_path)) == [{'name': 'Ada'}]
+
+        json_file.write(_DummyPath(str(json_path)), {'name': 'Ada'})
+        assert json_file.read(_DummyPath(str(json_path))) == {'name': 'Ada'}
+
+        xml_file.write(
+            PurePath(xml_path),
+            {'root': {'text': 'hello'}},
+            root_tag='root',
+        )
+        assert xml_file.read(PurePath(xml_path)) == {'root': {'text': 'hello'}}
+
     def test_stub_formats_raise_on_read(
         self,
         tmp_path: Path,
@@ -680,3 +719,39 @@ class TestFile:
         text = path.read_text(encoding='utf-8')
         assert text.startswith('<?xml')
         assert '<records>' in text
+
+    def test_xml_round_trip_with_attributes(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        Test XML read/write preserves attribute fields.
+        """
+        path = tmp_path / 'attrs.xml'
+        payload: JSONData = {
+            'root': {
+                '@id': '42',
+                'item': {'@lang': 'en', 'text': 'Hello'},
+            },
+        }
+
+        File(path, FileFormat.XML).write(payload)
+        result = File(path, FileFormat.XML).read()
+
+        assert result == payload
+
+    def test_zip_multi_file_read(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        Test ZIP files with multiple entries return a dict payload.
+        """
+        path = tmp_path / 'bundle.zip'
+        with zipfile.ZipFile(path, 'w') as archive:
+            archive.writestr('a.json', '{"a": 1}')
+            archive.writestr('b.json', '{"b": 2}')
+
+        result = File(path, FileFormat.ZIP).read()
+
+        assert result == {'a.json': {'a': 1}, 'b.json': {'b': 2}}

{etlplus-0.17.3 → etlplus-0.17.4}/tests/unit/file/test_u_file_yaml.py

@@ -6,7 +6,7 @@ Unit tests for :mod:`etlplus.file.yaml`.
 Notes
 -----
 - Uses ``tmp_path`` for filesystem isolation.
-- Exercises JSON detection and defers errors for unknown extensions.
+- Exercises YAML read/write helpers with a stubbed PyYAML module.
 """
 
 from __future__ import annotations