minimindslab-header-normalize 0.1.0__tar.gz

minimindslab_header_normalize-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_header_normalize-0.1.0/PKG-INFO

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: minimindslab-header-normalize
+Version: 0.1.0
+Summary: Normalize text header names into stable machine-friendly field names.
+Author: MiniMindsLab
+License: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# MiniMindsLab Header Normalize
+
+Normalize messy text header labels into stable lowercase `snake_case` field names.
+
+## Features
+
+- Converts mixed case and separators to lowercase snake_case
+- Removes unsupported punctuation deterministically
+- Collapses repeated separators to a single underscore
+- Trims leading/trailing underscores
+- Pure Python (standard library only)
+
+## Installation
+
+```bash
+pip install minimindslab-header-normalize
+```
+
+## Usage
+
+```python
+from minimindslab_header_normalize import normalize_header
+
+print(normalize_header("  Customer Name "))          # customer_name
+print(normalize_header("Order-ID###"))              # order_id
+print(normalize_header("Total   Amount ($)"))       # total_amount
+print(normalize_header("___Already__snake___"))     # already_snake
+```
+
+## API
+
+### `normalize_header(value: str) -> str`
+
+Normalize a single header string to lowercase snake_case.
+
+Raises:
+- `TypeError` if `value` is not a string.

minimindslab_header_normalize-0.1.0/README.md

@@ -0,0 +1,37 @@
+# MiniMindsLab Header Normalize
+
+Normalize messy text header labels into stable lowercase `snake_case` field names.
+
+## Features
+
+- Converts mixed case and separators to lowercase snake_case
+- Removes unsupported punctuation deterministically
+- Collapses repeated separators to a single underscore
+- Trims leading/trailing underscores
+- Pure Python (standard library only)
+
+## Installation
+
+```bash
+pip install minimindslab-header-normalize
+```
+
+## Usage
+
+```python
+from minimindslab_header_normalize import normalize_header
+
+print(normalize_header("  Customer Name "))          # customer_name
+print(normalize_header("Order-ID###"))              # order_id
+print(normalize_header("Total   Amount ($)"))       # total_amount
+print(normalize_header("___Already__snake___"))     # already_snake
+```
+
+## API
+
+### `normalize_header(value: str) -> str`
+
+Normalize a single header string to lowercase snake_case.
+
+Raises:
+- `TypeError` if `value` is not a string.

minimindslab_header_normalize-0.1.0/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=77.0.3"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "minimindslab-header-normalize"
+version = "0.1.0"
+description = "Normalize text header names into stable machine-friendly field names."
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+authors = [
+  { name = "MiniMindsLab" }
+]
+dependencies = []
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]

minimindslab_header_normalize-0.1.0/setup.cfg

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

minimindslab_header_normalize-0.1.0/src/minimindslab_header_normalize/__init__.py

@@ -0,0 +1,47 @@
+"""MiniMindsLab Header Normalize.
+
+Utilities to normalize messy header names into stable lowercase snake_case.
+"""
+
+from __future__ import annotations
+
+import re
+
+__all__ = ["normalize_header"]
+
+_SEP_RE = re.compile(r"[^a-zA-Z0-9]+")
+_MULTI_UNDERSCORE_RE = re.compile(r"_+")
+
+
+def normalize_header(value: str) -> str:
+    """Normalize a header string into lowercase snake_case.
+
+    Rules:
+    - Convert non-alphanumeric runs into underscores.
+    - Collapse repeated underscores.
+    - Strip leading and trailing underscores.
+    - Lowercase final output.
+
+    Parameters
+    ----------
+    value:
+        Input header text.
+
+    Returns
+    -------
+    str
+        Normalized snake_case name. May be empty for inputs with no
+        alphanumeric characters.
+
+    Raises
+    ------
+    TypeError
+        If `value` is not a string.
+    """
+    if not isinstance(value, str):
+        raise TypeError("value must be a string")
+
+    normalized = _SEP_RE.sub("_", value)
+    normalized = _MULTI_UNDERSCORE_RE.sub("_", normalized)
+    normalized = normalized.strip("_")
+    return normalized.lower()

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

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: minimindslab-header-normalize
+Version: 0.1.0
+Summary: Normalize text header names into stable machine-friendly field names.
+Author: MiniMindsLab
+License: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# MiniMindsLab Header Normalize
+
+Normalize messy text header labels into stable lowercase `snake_case` field names.
+
+## Features
+
+- Converts mixed case and separators to lowercase snake_case
+- Removes unsupported punctuation deterministically
+- Collapses repeated separators to a single underscore
+- Trims leading/trailing underscores
+- Pure Python (standard library only)
+
+## Installation
+
+```bash
+pip install minimindslab-header-normalize
+```
+
+## Usage
+
+```python
+from minimindslab_header_normalize import normalize_header
+
+print(normalize_header("  Customer Name "))          # customer_name
+print(normalize_header("Order-ID###"))              # order_id
+print(normalize_header("Total   Amount ($)"))       # total_amount
+print(normalize_header("___Already__snake___"))     # already_snake
+```
+
+## API
+
+### `normalize_header(value: str) -> str`
+
+Normalize a single header string to lowercase snake_case.
+
+Raises:
+- `TypeError` if `value` is not a string.

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

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

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

@@ -0,0 +1 @@
+

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

@@ -0,0 +1 @@
+minimindslab_header_normalize

minimindslab_header_normalize-0.1.0/tests/test_normalize_header.py

@@ -0,0 +1,48 @@
+import pathlib
+import unittest
+
+from minimindslab_header_normalize import normalize_header
+
+
+class NormalizeHeaderTests(unittest.TestCase):
+    def test_mixed_case_spaces_punctuation_and_repeated_separators(self):
+        self.assertEqual(normalize_header(" First Name "), "first_name")
+        self.assertEqual(normalize_header("Order---ID"), "order_id")
+        self.assertEqual(normalize_header("TOTAL.amount"), "total_amount")
+        self.assertEqual(normalize_header("A__B   C"), "a_b_c")
+
+    def test_collapse_and_trim_underscores(self):
+        self.assertEqual(normalize_header("___alpha___beta___"), "alpha_beta")
+        self.assertEqual(normalize_header("__x__"), "x")
+
+    def test_preserve_alphanumeric_remove_other_punctuation(self):
+        self.assertEqual(normalize_header("Field#1 (v2)!"), "field_1_v2")
+        self.assertEqual(normalize_header("R2D2*&^%$Unit"), "r2d2_unit")
+
+    def test_empty_result_when_no_alphanumeric(self):
+        self.assertEqual(normalize_header("---***___"), "")
+
+    def test_type_error_for_non_string(self):
+        with self.assertRaises(TypeError):
+            normalize_header(None)  # type: ignore[arg-type]
+        with self.assertRaises(TypeError):
+            normalize_header(123)  # type: ignore[arg-type]
+
+    def test_security_no_forbidden_tokens_in_core_source(self):
+        forbidden = [
+            "sub" + "process",
+            "re" + "quests",
+            "ht" + "tpx",
+            "aio" + "http",
+            "urllib" + ".request",
+        ]
+        source_path = pathlib.Path(__file__).resolve().parents[1] / "src" / "minimindslab_header_normalize" / "__init__.py"
+        content = source_path.read_text(encoding="utf-8")
+        self.assertNotIn("ev" + "al(", content)
+        self.assertNotIn("ex" + "ec(", content)
+        for token in forbidden:
+            self.assertNotIn(token, content)
+
+
+if __name__ == "__main__":
+    unittest.main()