strip-marks 1.0.0__tar.gz

strip_marks-1.0.0/LICENSE

@@ -0,0 +1,20 @@
+Copyright 2025 Jake W. Ireland <jakewilliami@icloud.com>
+
+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.

strip_marks-1.0.0/PKG-INFO

@@ -0,0 +1,55 @@
+Metadata-Version: 2.4
+Name: strip-marks
+Version: 1.0.0
+Summary: Small Python library to strip non-spacing marks (e.g., diacritics) from a string
+Author-email: "Jake W. Ireland" <jakewilliami@icloud.com>
+License: MIT
+Requires-Python: <4.0.0,>=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: ispunct>=1.0.0
+Dynamic: license-file
+
+# `strip_marks`
+
+A small Python library for stripping non-spacing marks (e.g., diacritics; accents) from a string.
+
+---
+
+## Quick Start
+
+```python
+from strip_marks import strip_marks
+
+assert strip_marks("şéàşöñ") == "season"
+assert strip_marks("kaderdenkesişenyollarinhikayesi.xyz") == "kaderdenkesisenyollarinhikayesi.xyz"
+
+def identity(x): return x
+assert strip_marks("hello world") == identity("hello world")
+```
+
+## Using `strip_marks` as a Library
+
+This package is published on PyPI.  You can install it with PIP:
+
+```commandline
+$ pip add strip_marks
+```
+
+Or, if using [UV](https://github.com/astral-sh/uv/) for dependency management:
+
+```commandline
+$ uv add strip-marks
+```
+
+## Notes on Internal Functionality
+
+This library also implements (and uses internally) functions adapted from the `utf8proc` C library to handle characters of multiple codepoints.  We also use bitwise functionality from our sister package, [`ispunct`](https://github.com/jakewilliami/ispunct-py).
+
+## Alternative Libraries
+
+This was written mostly as a proof of concept.  A more developed library with this functionality is [`unidecode`](https://pypi.org/project/Unidecode/).  A curious reader may also be interested in [`unihandecode`/`pykakasi`](https://pypi.org/project/pykakasi/) or [`text-unidecode`](https://pypi.org/project/text-unidecode/).
+
+## Citation
+
+If your research depends on `strip_marks`, please consider giving us a formal citation: [`citation.bib`](./citation.bib).

strip_marks-1.0.0/README.md

@@ -0,0 +1,43 @@
+# `strip_marks`
+
+A small Python library for stripping non-spacing marks (e.g., diacritics; accents) from a string.
+
+---
+
+## Quick Start
+
+```python
+from strip_marks import strip_marks
+
+assert strip_marks("şéàşöñ") == "season"
+assert strip_marks("kaderdenkesişenyollarinhikayesi.xyz") == "kaderdenkesisenyollarinhikayesi.xyz"
+
+def identity(x): return x
+assert strip_marks("hello world") == identity("hello world")
+```
+
+## Using `strip_marks` as a Library
+
+This package is published on PyPI.  You can install it with PIP:
+
+```commandline
+$ pip add strip_marks
+```
+
+Or, if using [UV](https://github.com/astral-sh/uv/) for dependency management:
+
+```commandline
+$ uv add strip-marks
+```
+
+## Notes on Internal Functionality
+
+This library also implements (and uses internally) functions adapted from the `utf8proc` C library to handle characters of multiple codepoints.  We also use bitwise functionality from our sister package, [`ispunct`](https://github.com/jakewilliami/ispunct-py).
+
+## Alternative Libraries
+
+This was written mostly as a proof of concept.  A more developed library with this functionality is [`unidecode`](https://pypi.org/project/Unidecode/).  A curious reader may also be interested in [`unihandecode`/`pykakasi`](https://pypi.org/project/pykakasi/) or [`text-unidecode`](https://pypi.org/project/text-unidecode/).
+
+## Citation
+
+If your research depends on `strip_marks`, please consider giving us a formal citation: [`citation.bib`](./citation.bib).

strip_marks-1.0.0/pyproject.toml

@@ -0,0 +1,48 @@
+[project]
+name = "strip-marks"
+version = "1.0.0"
+description = "Small Python library to strip non-spacing marks (e.g., diacritics) from a string"
+authors = [
+    { name = "Jake W. Ireland", email = "jakewilliami@icloud.com" },
+]
+readme = "README.md"
+requires-python = ">=3.11, <4.0.0"
+license = { text = "MIT" }
+dependencies = [
+    "ispunct>=1.0.0",
+]
+
+[dependency-groups]
+dev = [
+    "pip-audit>=2.9.0",
+    "pre-commit>=4.3.0",
+    "pytest==8.3.4",
+    "ruff>=0.12.8",
+]
+
+[tool.uv.sources]
+ispunct = { git = "https://github.com/jakewilliami/ispunct-py", tag = "v1.0.0" }
+
+[tool.pytest.ini_options]
+pythonpath = "src"
+
+[tool.ruff]
+# https://peps.python.org/pep-0008/#maximum-line-length
+line-length = 80
+
+[tool.ruff.lint]
+select = [
+    "E",    # pycodestyle
+    "F",    # Pyflakes
+    "UP",   # pyupgrade
+    "B",    # flake8-bugbear
+    "SIM",  # flake8-simplify
+    "I",    # isort
+]
+ignore = [
+    # "B008",  # docs.astral.sh/ruff/rules/function-call-in-default-argument/
+]
+fixable = ["ALL"]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]  # Unused imports

strip_marks-1.0.0/setup.cfg

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

strip_marks-1.0.0/src/strip_marks/__init__.py

@@ -0,0 +1 @@
+from strip_marks.strip_marks import strip_marks

strip_marks-1.0.0/src/strip_marks/strip_marks.py

@@ -0,0 +1,20 @@
+import unicodedata
+
+
+def strip_marks(s: str) -> str:
+    """
+    Strip non-spacing marks (e.g., accents) from input string.
+    """
+
+    # Base case: return input string is only made up of combining characters
+    if all(unicodedata.combining(c) for c in s):
+        return s
+
+    # Step 1: decompose input into normal form
+    s_norm = unicodedata.normalize("NFD", s)
+
+    # Step 2: keep only base characters
+    s_base = ''.join(ch for ch in s_norm if not unicodedata.combining(ch))
+
+    # Step 3: re-compose normalised form without base characters
+    return unicodedata.normalize("NFC", s_base)

strip_marks-1.0.0/src/strip_marks.egg-info/PKG-INFO

@@ -0,0 +1,55 @@
+Metadata-Version: 2.4
+Name: strip-marks
+Version: 1.0.0
+Summary: Small Python library to strip non-spacing marks (e.g., diacritics) from a string
+Author-email: "Jake W. Ireland" <jakewilliami@icloud.com>
+License: MIT
+Requires-Python: <4.0.0,>=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: ispunct>=1.0.0
+Dynamic: license-file
+
+# `strip_marks`
+
+A small Python library for stripping non-spacing marks (e.g., diacritics; accents) from a string.
+
+---
+
+## Quick Start
+
+```python
+from strip_marks import strip_marks
+
+assert strip_marks("şéàşöñ") == "season"
+assert strip_marks("kaderdenkesişenyollarinhikayesi.xyz") == "kaderdenkesisenyollarinhikayesi.xyz"
+
+def identity(x): return x
+assert strip_marks("hello world") == identity("hello world")
+```
+
+## Using `strip_marks` as a Library
+
+This package is published on PyPI.  You can install it with PIP:
+
+```commandline
+$ pip add strip_marks
+```
+
+Or, if using [UV](https://github.com/astral-sh/uv/) for dependency management:
+
+```commandline
+$ uv add strip-marks
+```
+
+## Notes on Internal Functionality
+
+This library also implements (and uses internally) functions adapted from the `utf8proc` C library to handle characters of multiple codepoints.  We also use bitwise functionality from our sister package, [`ispunct`](https://github.com/jakewilliami/ispunct-py).
+
+## Alternative Libraries
+
+This was written mostly as a proof of concept.  A more developed library with this functionality is [`unidecode`](https://pypi.org/project/Unidecode/).  A curious reader may also be interested in [`unihandecode`/`pykakasi`](https://pypi.org/project/pykakasi/) or [`text-unidecode`](https://pypi.org/project/text-unidecode/).
+
+## Citation
+
+If your research depends on `strip_marks`, please consider giving us a formal citation: [`citation.bib`](./citation.bib).

strip_marks-1.0.0/src/strip_marks.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+pyproject.toml
+src/strip_marks/__init__.py
+src/strip_marks/strip_marks.py
+src/strip_marks.egg-info/PKG-INFO
+src/strip_marks.egg-info/SOURCES.txt
+src/strip_marks.egg-info/dependency_links.txt
+src/strip_marks.egg-info/requires.txt
+src/strip_marks.egg-info/top_level.txt

strip_marks-1.0.0/src/strip_marks.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

strip_marks-1.0.0/src/strip_marks.egg-info/requires.txt

@@ -0,0 +1 @@
+ispunct>=1.0.0

strip_marks-1.0.0/src/strip_marks.egg-info/top_level.txt

@@ -0,0 +1 @@
+strip_marks