smssafe 0.0.1__tar.gz

smssafe-0.0.1/.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

smssafe-0.0.1/CHANGELOG.md

@@ -0,0 +1,30 @@
+# Changelog
+
+All notable changes to this project are documented here.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.0.1] - 2026-06-26
+
+### Added
+- Initial public release of `smssafe`.
+- `sanitize(text, *, drop_unknown=True) -> SanitizeResult` public API.
+- `SanitizeResult` frozen dataclass with full audit trail (`replacements`,
+  `remaining_unsafe`, `char_count`, `segments`, `encoding`, `is_clean`).
+- Deterministic 8-step GSM-7 sanitization pipeline (`smssafe.core`).
+- Homoglyph transliteration for Cyrillic, Greek, and full-width Latin lookalikes.
+- GSM-7 length and segment accounting (`smssafe.segments`), extended chars counted as 2.
+- Zero runtime dependencies; ships `py.typed`.
+- 689-case test suite.
+
+### Notes
+- **Tilde (`~`):** treated as the GSM-7 extended character it is (escape `0x3D`,
+  2 septets) and passed through unchanged, so `~5,000` ("approximately") is not
+  corrupted into `-5,000` ("negative"). Non-ASCII tilde lookalikes (`˜ ∼ ～`)
+  normalise to ASCII `~`.
+
+[Unreleased]: https://github.com/BRIQ-BLOCK/smssafe/compare/v0.0.1...HEAD
+[0.0.1]: https://github.com/BRIQ-BLOCK/smssafe/releases/tag/v0.0.1

smssafe-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 BRIQ 
+
+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.

smssafe-0.0.1/PKG-INFO

@@ -0,0 +1,129 @@
+Metadata-Version: 2.4
+Name: smssafe
+Version: 0.0.1
+Summary: Turn arbitrary text into guaranteed GSM-7 deliverable SMS — no UCS-2 fallback, deliverable on feature phones.
+Project-URL: Homepage, https://github.com/BRIQ-BLOCK/smssafe
+Project-URL: Repository, https://github.com/BRIQ-BLOCK/smssafe
+Project-URL: Changelog, https://github.com/BRIQ-BLOCK/smssafe/blob/main/CHANGELOG.md
+Project-URL: Issues, https://github.com/BRIQ-BLOCK/smssafe/issues
+Author-email: Eddie Gulay <groundhalt@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: a2p,encoding,gsm-7,gsm0338,sanitize,sms,transliterate,ucs2
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Communications :: Telephony
+Classifier: Topic :: Text Processing :: Filters
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Provides-Extra: dev
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: pytest>=7; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# smssafe
+
+[![CI](https://github.com/BRIQ-BLOCK/smssafe/actions/workflows/ci.yml/badge.svg)](https://github.com/BRIQ-BLOCK/smssafe/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/smssafe.svg)](https://pypi.org/project/smssafe/)
+[![Python](https://img.shields.io/pypi/pyversions/smssafe.svg)](https://pypi.org/project/smssafe/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+
+**Turn arbitrary text into guaranteed GSM-7 deliverable SMS — no UCS-2 fallback.**
+
+A single non-GSM-7 character (a smart quote, an em-dash, a stray emoji) forces an
+*entire* SMS into UCS-2 encoding: 70 characters per segment instead of 160, triple
+the cost, and silent delivery failure on feature/dumb phones that can't render it.
+
+`smssafe` sanitizes text **before** you send it — transliterating, replacing, or
+dropping every non-GSM-7 character while preserving as much meaning as possible.
+
+- ✅ **Zero dependencies** — pure Python standard library, 3.10+
+- ✅ **Fully typed** — ships `py.typed` (PEP 561)
+- ✅ Homoglyph-aware — Cyrillic/Greek/full-width lookalikes are *transliterated*, not dropped
+- ✅ Accurate segment & cost accounting (extended chars correctly counted as 2)
+- ✅ Deterministic, side-effect-free, full audit trail of every change
+
+## Install
+
+```bash
+pip install smssafe
+```
+
+## Usage
+
+```python
+from smssafe import sanitize
+
+result = sanitize("Hi — “there”, pay ~5,000 now… 🙂")
+
+result.sanitized          # 'Hi - "there", pay ~5,000 now...'
+result.encoding           # 'gsm7'
+result.char_count         # encoded length (extended chars count as 2)
+result.segments           # number of SMS parts
+result.replacements       # list[dict] — audit trail of every substitution
+result.remaining_unsafe   # list[str] — chars that could not be mapped (dropped)
+result.is_clean           # True if no changes were needed
+```
+
+### What it handles
+
+| Input | Output | Notes |
+|---|---|---|
+| `“ ” ‘ ’` smart quotes | `" '` | Word / Google Docs / AI output |
+| `– — …` dash & ellipsis | `- ...` | |
+| `• · ‣` bullets | `-` | |
+| Cyrillic `аеор`, Greek `Α`, full-width `Ａ１` | `aeop A A1` | lookalikes transliterated, not dropped |
+| `ÀÈÌÒÙ` uppercase accent traps | `AEIOU` | *not* in GSM-7 despite lowercase being valid |
+| `™ © ®` | `TM (c) (R)` | |
+| `₹ ₽ ₿` | `INR RUB BTC` | (`€ £ $ ¥` are kept — they're valid GSM-7) |
+| emoji, math-alphanumerics, non-BMP | _(stripped)_ | recorded in `remaining_unsafe` |
+| zero-width / BOM / exotic spaces | _(stripped / normalized)_ | |
+
+> **Tilde:** `~` is a GSM-7 extended character (escape `0x3D`, costs 2 septets), so
+> it passes through unchanged — `~5,000` stays `~5,000` rather than becoming a
+> misleading `-5,000`. Non-ASCII tilde lookalikes (`˜ ∼ ～`) normalise to `~`.
+
+### Drop vs. replace unknowns
+
+By default, characters with no safe mapping are dropped. Pass `drop_unknown=False`
+to replace them with `?` instead:
+
+```python
+sanitize("A中B", drop_unknown=False).sanitized   # 'A?B'
+```
+
+## How it works
+
+A deterministic 8-step pipeline (`smssafe.core`), each step independently testable:
+
+0. Strip non-BMP / surrogate codepoints (emoji, math-alphanumerics)
+1. Apply the homoglyph map (Cyrillic/Greek/full-width → Latin)
+2. Apply the explicit replacement map (quotes, dashes, currency, symbols…)
+3. NFD-normalize **per character** and strip diacritics for remaining accented chars
+4. Normalize whitespace (tabs, exotic/zero-width spaces)
+5. Collapse artifacts (runs of dashes/spaces)
+6. Final GSM-7 scan — drop or `?`-replace anything left
+7. Compute encoding, character count (extended = 2), and segment count
+
+## Development
+
+```bash
+git clone https://github.com/BRIQ-BLOCK/smssafe
+cd smssafe
+pip install -e ".[dev]"
+pytest            # 689 tests
+ruff check .
+mypy
+```
+
+## License
+
+MIT © Eddie Gulay

smssafe-0.0.1/README.md

@@ -0,0 +1,98 @@
+# smssafe
+
+[![CI](https://github.com/BRIQ-BLOCK/smssafe/actions/workflows/ci.yml/badge.svg)](https://github.com/BRIQ-BLOCK/smssafe/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/smssafe.svg)](https://pypi.org/project/smssafe/)
+[![Python](https://img.shields.io/pypi/pyversions/smssafe.svg)](https://pypi.org/project/smssafe/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+
+**Turn arbitrary text into guaranteed GSM-7 deliverable SMS — no UCS-2 fallback.**
+
+A single non-GSM-7 character (a smart quote, an em-dash, a stray emoji) forces an
+*entire* SMS into UCS-2 encoding: 70 characters per segment instead of 160, triple
+the cost, and silent delivery failure on feature/dumb phones that can't render it.
+
+`smssafe` sanitizes text **before** you send it — transliterating, replacing, or
+dropping every non-GSM-7 character while preserving as much meaning as possible.
+
+- ✅ **Zero dependencies** — pure Python standard library, 3.10+
+- ✅ **Fully typed** — ships `py.typed` (PEP 561)
+- ✅ Homoglyph-aware — Cyrillic/Greek/full-width lookalikes are *transliterated*, not dropped
+- ✅ Accurate segment & cost accounting (extended chars correctly counted as 2)
+- ✅ Deterministic, side-effect-free, full audit trail of every change
+
+## Install
+
+```bash
+pip install smssafe
+```
+
+## Usage
+
+```python
+from smssafe import sanitize
+
+result = sanitize("Hi — “there”, pay ~5,000 now… 🙂")
+
+result.sanitized          # 'Hi - "there", pay ~5,000 now...'
+result.encoding           # 'gsm7'
+result.char_count         # encoded length (extended chars count as 2)
+result.segments           # number of SMS parts
+result.replacements       # list[dict] — audit trail of every substitution
+result.remaining_unsafe   # list[str] — chars that could not be mapped (dropped)
+result.is_clean           # True if no changes were needed
+```
+
+### What it handles
+
+| Input | Output | Notes |
+|---|---|---|
+| `“ ” ‘ ’` smart quotes | `" '` | Word / Google Docs / AI output |
+| `– — …` dash & ellipsis | `- ...` | |
+| `• · ‣` bullets | `-` | |
+| Cyrillic `аеор`, Greek `Α`, full-width `Ａ１` | `aeop A A1` | lookalikes transliterated, not dropped |
+| `ÀÈÌÒÙ` uppercase accent traps | `AEIOU` | *not* in GSM-7 despite lowercase being valid |
+| `™ © ®` | `TM (c) (R)` | |
+| `₹ ₽ ₿` | `INR RUB BTC` | (`€ £ $ ¥` are kept — they're valid GSM-7) |
+| emoji, math-alphanumerics, non-BMP | _(stripped)_ | recorded in `remaining_unsafe` |
+| zero-width / BOM / exotic spaces | _(stripped / normalized)_ | |
+
+> **Tilde:** `~` is a GSM-7 extended character (escape `0x3D`, costs 2 septets), so
+> it passes through unchanged — `~5,000` stays `~5,000` rather than becoming a
+> misleading `-5,000`. Non-ASCII tilde lookalikes (`˜ ∼ ～`) normalise to `~`.
+
+### Drop vs. replace unknowns
+
+By default, characters with no safe mapping are dropped. Pass `drop_unknown=False`
+to replace them with `?` instead:
+
+```python
+sanitize("A中B", drop_unknown=False).sanitized   # 'A?B'
+```
+
+## How it works
+
+A deterministic 8-step pipeline (`smssafe.core`), each step independently testable:
+
+0. Strip non-BMP / surrogate codepoints (emoji, math-alphanumerics)
+1. Apply the homoglyph map (Cyrillic/Greek/full-width → Latin)
+2. Apply the explicit replacement map (quotes, dashes, currency, symbols…)
+3. NFD-normalize **per character** and strip diacritics for remaining accented chars
+4. Normalize whitespace (tabs, exotic/zero-width spaces)
+5. Collapse artifacts (runs of dashes/spaces)
+6. Final GSM-7 scan — drop or `?`-replace anything left
+7. Compute encoding, character count (extended = 2), and segment count
+
+## Development
+
+```bash
+git clone https://github.com/BRIQ-BLOCK/smssafe
+cd smssafe
+pip install -e ".[dev]"
+pytest            # 689 tests
+ruff check .
+mypy
+```
+
+## License
+
+MIT © Eddie Gulay

smssafe-0.0.1/pyproject.toml

@@ -0,0 +1,75 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "smssafe"
+description = "Turn arbitrary text into guaranteed GSM-7 deliverable SMS — no UCS-2 fallback, deliverable on feature phones."
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [{ name = "Eddie Gulay", email = "groundhalt@gmail.com" }]
+keywords = ["sms", "gsm-7", "gsm0338", "encoding", "sanitize", "a2p", "ucs2", "transliterate"]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Intended Audience :: Developers",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Communications :: Telephony",
+  "Topic :: Text Processing :: Filters",
+  "Typing :: Typed",
+]
+dynamic = ["version"]
+dependencies = []
+
+[project.optional-dependencies]
+dev = ["pytest>=7", "pytest-cov", "ruff", "mypy"]
+
+[project.urls]
+Homepage = "https://github.com/BRIQ-BLOCK/smssafe"
+Repository = "https://github.com/BRIQ-BLOCK/smssafe"
+Changelog = "https://github.com/BRIQ-BLOCK/smssafe/blob/main/CHANGELOG.md"
+Issues = "https://github.com/BRIQ-BLOCK/smssafe/issues"
+
+# Optional CLI — uncomment after adding src/smssafe/__main__.py
+# [project.scripts]
+# smssafe = "smssafe.__main__:main"
+
+[tool.hatch.version]
+path = "src/smssafe/__init__.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/smssafe"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/smssafe", "tests", "README.md", "CHANGELOG.md", "LICENSE"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+addopts = "-q"
+
+[tool.coverage.run]
+source = ["smssafe"]
+branch = true
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "C4", "SIM"]
+
+[tool.ruff.lint.per-file-ignores]
+# Test docstrings spell out the invariant under test; long lines are fine there.
+"tests/**" = ["E501"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+files = ["src/smssafe"]

smssafe-0.0.1/src/smssafe/__init__.py

@@ -0,0 +1,15 @@
+"""smssafe -- turn arbitrary text into guaranteed GSM-7 deliverable SMS.
+
+Public API:
+    from smssafe import sanitize, SanitizeResult
+    result = sanitize("Hi — “there”")
+    result.sanitized   # -> 'Hi - "there"'
+
+Stdlib only. No third-party imports. Python 3.10+.
+"""
+
+from .core import SanitizeResult, sanitize
+
+__all__ = ["sanitize", "SanitizeResult"]
+
+__version__ = "0.0.1"