minimindslab-filename-split 0.1.0__tar.gz

minimindslab_filename_split-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 MiniMindsLab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

minimindslab_filename_split-0.1.0/PKG-INFO

@@ -0,0 +1,72 @@
+Metadata-Version: 2.4
+Name: minimindslab-filename-split
+Version: 0.1.0
+Summary: Parse file names into base name and multi-part extension in a deterministic way, with optional support for known compound extensions like .tar.gz.
+Author: MiniMindsLab
+License: MIT
+Keywords: filename,extension,path,utilities
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# MiniMindsLab Filename Split
+
+A tiny, deterministic utility for splitting a filename into:
+
+- **stem** (base name)
+- **suffix** (extension), including optional handling of known compound extensions such as `.tar.gz`.
+
+## Features
+
+- Pure Python (standard library only)
+- Deterministic behavior
+- Correct handling for common edge cases like dotfiles
+
+## Usage
+
+```python
+from minimindslab_filename_split import split_filename
+
+print(split_filename("archive.tar.gz"))
+# ('archive', '.tar.gz')
+
+print(split_filename("report.csv"))
+# ('report', '.csv')
+
+print(split_filename(".env"))
+# ('.env', '')
+
+print(split_filename("notes"))
+# ('notes', '')
+```
+
+### Disabling compound extension handling
+
+```python
+from minimindslab_filename_split import split_filename
+
+print(split_filename("archive.tar.gz", allow_compound=False))
+# ('archive.tar', '.gz')
+```
+
+## API
+
+### `split_filename(filename: str, allow_compound: bool = True, compound_extensions: tuple[str, ...] | None = None) -> tuple[str, str]`
+
+Splits a filename into `(stem, suffix)`.
+
+- `allow_compound`: When `True`, known compound extensions are recognized.
+- `compound_extensions`: Optional custom compound extension list; each must start with `.`.
+
+## License
+
+MIT

minimindslab_filename_split-0.1.0/README.md

@@ -0,0 +1,52 @@
+# MiniMindsLab Filename Split
+
+A tiny, deterministic utility for splitting a filename into:
+
+- **stem** (base name)
+- **suffix** (extension), including optional handling of known compound extensions such as `.tar.gz`.
+
+## Features
+
+- Pure Python (standard library only)
+- Deterministic behavior
+- Correct handling for common edge cases like dotfiles
+
+## Usage
+
+```python
+from minimindslab_filename_split import split_filename
+
+print(split_filename("archive.tar.gz"))
+# ('archive', '.tar.gz')
+
+print(split_filename("report.csv"))
+# ('report', '.csv')
+
+print(split_filename(".env"))
+# ('.env', '')
+
+print(split_filename("notes"))
+# ('notes', '')
+```
+
+### Disabling compound extension handling
+
+```python
+from minimindslab_filename_split import split_filename
+
+print(split_filename("archive.tar.gz", allow_compound=False))
+# ('archive.tar', '.gz')
+```
+
+## API
+
+### `split_filename(filename: str, allow_compound: bool = True, compound_extensions: tuple[str, ...] | None = None) -> tuple[str, str]`
+
+Splits a filename into `(stem, suffix)`.
+
+- `allow_compound`: When `True`, known compound extensions are recognized.
+- `compound_extensions`: Optional custom compound extension list; each must start with `.`.
+
+## License
+
+MIT

minimindslab_filename_split-0.1.0/pyproject.toml

@@ -0,0 +1,32 @@
+[build-system]
+requires = ["setuptools>=77.0.3"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "minimindslab-filename-split"
+version = "0.1.0"
+description = "Parse file names into base name and multi-part extension in a deterministic way, with optional support for known compound extensions like .tar.gz."
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+dependencies = []
+authors = [
+  { name = "MiniMindsLab" }
+]
+keywords = ["filename", "extension", "path", "utilities"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Operating System :: OS Independent",
+  "Topic :: Software Development :: Libraries :: Python Modules"
+]
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]

minimindslab_filename_split-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

minimindslab_filename_split-0.1.0/src/minimindslab_filename_split/__init__.py

@@ -0,0 +1,71 @@
+"""MiniMindsLab Filename Split.
+
+Deterministically split filenames into stem and suffix, with optional
+support for known compound extensions.
+"""
+
+from __future__ import annotations
+
+from pathlib import PurePath
+
+__all__ = ["split_filename", "DEFAULT_COMPOUND_EXTENSIONS"]
+__version__ = "0.1.0"
+
+DEFAULT_COMPOUND_EXTENSIONS: tuple[str, ...] = (
+    ".tar.gz",
+    ".tar.bz2",
+    ".tar.xz",
+    ".tar.zst",
+)
+
+
+def split_filename(
+    filename: str,
+    allow_compound: bool = True,
+    compound_extensions: tuple[str, ...] | None = None,
+) -> tuple[str, str]:
+    """Split a filename into ``(stem, suffix)``.
+
+    Parameters
+    ----------
+    filename:
+        Input file name or path-like string. Only the final path segment is used.
+    allow_compound:
+        When True, recognizes known compound extensions (e.g. ``.tar.gz``).
+    compound_extensions:
+        Optional override for compound extension candidates. Each item must start
+        with ``.`` and contain at least one additional ``.``.
+
+    Returns
+    -------
+    tuple[str, str]
+        A 2-tuple of ``(stem, suffix)``.
+    """
+    if not isinstance(filename, str):
+        raise TypeError("filename must be a str")
+
+    name = PurePath(filename).name
+    if name == "":
+        return "", ""
+
+    if name.startswith(".") and name.count(".") == 1:
+        return name, ""
+
+    suffixes = PurePath(name).suffixes
+    if not suffixes:
+        return name, ""
+
+    if allow_compound:
+        candidates = compound_extensions or DEFAULT_COMPOUND_EXTENSIONS
+        for ext in candidates:
+            if not isinstance(ext, str) or not ext.startswith(".") or ext.count(".") < 2:
+                raise ValueError(
+                    "compound_extensions items must be strings starting with '.' and contain at least two dots"
+                )
+        for ext in sorted(candidates, key=len, reverse=True):
+            if name.lower().endswith(ext.lower()) and len(name) > len(ext):
+                return name[: -len(ext)], ext
+
+    suffix = suffixes[-1]
+    stem = name[: -len(suffix)] if suffix else name
+    return stem, suffix

minimindslab_filename_split-0.1.0/src/minimindslab_filename_split.egg-info/PKG-INFO

@@ -0,0 +1,72 @@
+Metadata-Version: 2.4
+Name: minimindslab-filename-split
+Version: 0.1.0
+Summary: Parse file names into base name and multi-part extension in a deterministic way, with optional support for known compound extensions like .tar.gz.
+Author: MiniMindsLab
+License: MIT
+Keywords: filename,extension,path,utilities
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# MiniMindsLab Filename Split
+
+A tiny, deterministic utility for splitting a filename into:
+
+- **stem** (base name)
+- **suffix** (extension), including optional handling of known compound extensions such as `.tar.gz`.
+
+## Features
+
+- Pure Python (standard library only)
+- Deterministic behavior
+- Correct handling for common edge cases like dotfiles
+
+## Usage
+
+```python
+from minimindslab_filename_split import split_filename
+
+print(split_filename("archive.tar.gz"))
+# ('archive', '.tar.gz')
+
+print(split_filename("report.csv"))
+# ('report', '.csv')
+
+print(split_filename(".env"))
+# ('.env', '')
+
+print(split_filename("notes"))
+# ('notes', '')
+```
+
+### Disabling compound extension handling
+
+```python
+from minimindslab_filename_split import split_filename
+
+print(split_filename("archive.tar.gz", allow_compound=False))
+# ('archive.tar', '.gz')
+```
+
+## API
+
+### `split_filename(filename: str, allow_compound: bool = True, compound_extensions: tuple[str, ...] | None = None) -> tuple[str, str]`
+
+Splits a filename into `(stem, suffix)`.
+
+- `allow_compound`: When `True`, known compound extensions are recognized.
+- `compound_extensions`: Optional custom compound extension list; each must start with `.`.
+
+## License
+
+MIT

minimindslab_filename_split-0.1.0/src/minimindslab_filename_split.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+LICENSE
+README.md
+pyproject.toml
+src/minimindslab_filename_split/__init__.py
+src/minimindslab_filename_split.egg-info/PKG-INFO
+src/minimindslab_filename_split.egg-info/SOURCES.txt
+src/minimindslab_filename_split.egg-info/dependency_links.txt
+src/minimindslab_filename_split.egg-info/top_level.txt
+tests/test_filename_split.py

minimindslab_filename_split-0.1.0/src/minimindslab_filename_split.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

minimindslab_filename_split-0.1.0/src/minimindslab_filename_split.egg-info/top_level.txt

@@ -0,0 +1 @@
+minimindslab_filename_split

minimindslab_filename_split-0.1.0/tests/test_filename_split.py

@@ -0,0 +1,79 @@
+import ast
+import pathlib
+import unittest
+
+from minimindslab_filename_split import split_filename
+
+
+class TestFilenameSplitAcceptance(unittest.TestCase):
+    def test_archive_tar_gz_compound_enabled(self):
+        self.assertEqual(split_filename("archive.tar.gz"), ("archive", ".tar.gz"))
+
+    def test_report_csv(self):
+        self.assertEqual(split_filename("report.csv"), ("report", ".csv"))
+
+    def test_dotenv(self):
+        self.assertEqual(split_filename(".env"), (".env", ""))
+
+    def test_no_extension(self):
+        self.assertEqual(split_filename("notes"), ("notes", ""))
+
+
+class TestFilenameSplitNegative(unittest.TestCase):
+    def test_type_error_non_string(self):
+        with self.assertRaises(TypeError):
+            split_filename(123)  # type: ignore[arg-type]
+
+    def test_invalid_compound_extension_definition(self):
+        with self.assertRaises(ValueError):
+            split_filename("archive.tar.gz", compound_extensions=("tar.gz",))
+
+    def test_compound_disabled(self):
+        self.assertEqual(
+            split_filename("archive.tar.gz", allow_compound=False),
+            ("archive.tar", ".gz"),
+        )
+
+
+class TestSecurityConstraints(unittest.TestCase):
+    def test_no_forbidden_calls_or_imports_in_core(self):
+        root = pathlib.Path(__file__).resolve().parents[1]
+        core_file = root / "src" / "minimindslab_filename_split" / "__init__.py"
+        source = core_file.read_text(encoding="utf-8")
+        tree = ast.parse(source)
+
+        forbidden_imports = {
+            "socket",
+        }
+        forbidden_calls = {"eval", "exec", "system"}
+
+        for node in ast.walk(tree):
+            if isinstance(node, ast.Import):
+                for alias in node.names:
+                    self.assertNotIn(alias.name, forbidden_imports)
+            elif isinstance(node, ast.ImportFrom):
+                module = node.module or ""
+                self.assertNotIn(module, forbidden_imports)
+            elif isinstance(node, ast.Call):
+                if isinstance(node.func, ast.Name):
+                    self.assertNotIn(node.func.id, forbidden_calls)
+                elif isinstance(node.func, ast.Attribute):
+                    self.assertFalse(
+                        node.func.attr == "system"
+                        and isinstance(node.func.value, ast.Name)
+                        and node.func.value.id == "os"
+                    )
+
+    def test_no_forbidden_tokens_in_repository_files(self):
+        root = pathlib.Path(__file__).resolve().parents[1]
+        forbidden_tokens = ["sub" + "process", "re" + "quests", "ht" + "tpx", "aio" + "http", "url" + "lib.request"]
+
+        for path in root.rglob("*.py"):
+            text = path.read_text(encoding="utf-8")
+            lowered = text.lower()
+            for token in forbidden_tokens:
+                self.assertNotIn(token, lowered)
+
+
+if __name__ == "__main__":
+    unittest.main()