confusable 0.1.0a1__tar.gz

confusable-0.1.0a1/LICENSE

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

confusable-0.1.0a1/LICENSES/Unicode-3.0.txt

@@ -0,0 +1,39 @@
+UNICODE LICENSE V3
+
+COPYRIGHT AND PERMISSION NOTICE
+
+Copyright © 1991-2026 Unicode, Inc.
+
+NOTICE TO USER: Carefully read the following legal agreement. BY
+DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING DATA FILES, AND/OR
+SOFTWARE, YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
+TERMS AND CONDITIONS OF THIS AGREEMENT. IF YOU DO NOT AGREE, DO NOT
+DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE THE DATA FILES OR SOFTWARE.
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of data files and any associated documentation (the "Data Files") or
+software and any associated documentation (the "Software") to deal in the
+Data Files or Software without restriction, including without limitation
+the rights to use, copy, modify, merge, publish, distribute, and/or sell
+copies of the Data Files or Software, and to permit persons to whom the
+Data Files or Software are furnished to do so, provided that either (a)
+this copyright and permission notice appear with all copies of the Data
+Files or Software, or (b) this copyright and permission notice appear in
+associated Documentation.
+
+THE DATA FILES AND SOFTWARE ARE 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 OF
+THIRD PARTY RIGHTS.
+
+IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE
+BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES,
+OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
+ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE DATA
+FILES OR SOFTWARE.
+
+Except as contained in this notice, the name of a copyright holder shall
+not be used in advertising or otherwise to promote the sale, use or other
+dealings in these Data Files or Software without prior written
+authorization of the copyright holder.

confusable-0.1.0a1/PKG-INFO

@@ -0,0 +1,203 @@
+Metadata-Version: 2.4
+Name: confusable
+Version: 0.1.0a1
+Summary: Unicode spoofing and confusable detection (UTS #39) in pure Python.
+Keywords: unicode,confusables,homoglyph,homograph,spoofing,uts39,identifier,security
+Author: Atilla Guzel
+Author-email: Atilla Guzel <33524244+atillaguzel@users.noreply.github.com>
+License-Expression: MIT
+License-File: LICENSE
+License-File: LICENSES/Unicode-3.0.txt
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+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: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Classifier: Topic :: Security
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Project-URL: Homepage, https://github.com/blip-box/confusable
+Project-URL: Repository, https://github.com/blip-box/confusable
+Project-URL: Issues, https://github.com/blip-box/confusable/issues
+Project-URL: Changelog, https://github.com/blip-box/confusable/releases
+Description-Content-Type: text/markdown
+
+# confusable
+
+Unicode spoofing and confusable detection for Python, following
+[Unicode Technical Standard #39](https://www.unicode.org/reports/tr39/). Pure Python,
+no runtime dependencies.
+
+> **Status: pre-alpha.** Look-alike detection (`skeleton`, `match`), mixed-script
+> detection, restriction levels, the identifier checks, the mixed-number and
+> combining-mark checks, invisible-character detection, grapheme clusters and the
+> compatibility module work and pass their tests. Nothing is on PyPI yet.
+
+## Usage
+
+```python
+import confusable
+
+confusable.skeleton("p\u0430ypal")  # 'paypal' (with CYRILLIC SMALL LETTER A)
+confusable.match("paypal", "p\u0430ypal")  # Match.MIXED_SCRIPT
+confusable.match("rn", "m")  # Match.SINGLE_SCRIPT
+confusable.match("paypal", "paypa1x")  # None: not confusable
+
+# The skeleton follows display order, so a right-to-left override is seen
+# the way a reader sees it:
+confusable.skeleton("invoice\u202egpj.exe")  # 'invoiceexe.jpg'
+```
+
+Restriction levels (UTS #39 section 5.2) rank how safely a string mixes scripts,
+from `ASCII_ONLY` to `UNRESTRICTED`, using the General Security Profile:
+
+```python
+confusable.restriction_level("caf\u00e9")  # RestrictionLevel.SINGLE_SCRIPT
+confusable.restriction_level("abc\u3042")  # HIGHLY_RESTRICTIVE: Latin with Japanese
+confusable.restriction_level(
+    "p\u0430ypal"
+)  # MINIMALLY_RESTRICTIVE: Latin with Cyrillic
+confusable.is_mixed_script("p\u0430ypal")  # True
+
+# Levels are ordered, most restrictive first:
+confusable.restriction_level(name) <= confusable.RestrictionLevel.HIGHLY_RESTRICTIVE
+```
+
+The identifier checks follow UTS #39's General Security Profile, under canonical
+equivalence, so the answer is the same however the text is encoded:
+
+```python
+confusable.is_allowed("paypal")  # True
+confusable.is_allowed("pay pal")  # False: a space is Restricted
+confusable.is_allowed("\u0114")  # True: U+0114 is Restricted, E + U+0306 is not
+confusable.identifier_types("\u200d")  # {IdentifierType.DEFAULT_IGNORABLE}
+confusable.isxidstart("_"), confusable.isxidcontinue("_")  # (False, True)
+
+# Persian, Malayalam and Sinhala need ZERO WIDTH (NON-)JOINER in some words. The
+# profile excludes both; joining_controls=True allows them only where UTS #39
+# section 3.1.1.1 says they change how the word looks:
+confusable.is_allowed("\u0dc1\u0dca\u200d\u0dbb\u0dd3", joining_controls=True)  # True
+confusable.is_allowed("pay\u200dpal", joining_controls=True)  # False
+```
+
+Three more checks from UTS #39 sections 5.3 and 5.4 catch digits from different
+number systems and combining marks that pile up or hide:
+
+```python
+confusable.has_mixed_numbers("1\u0661")  # True: ASCII and Arabic-Indic digits
+confusable.has_unlikely_marks("e\u0301\u0301")  # True: the same accent twice
+confusable.has_hidden_overlay("i\u0307")  # True: a dot above, lost in i's own dot
+```
+
+Invisible and control characters, for text that is not held to the identifier
+profile, such as display names and file names:
+
+```python
+confusable.find_invisible("pay\u200bpal")  # [(3, Invisible.DEFAULT_IGNORABLE)]: ZWSP
+confusable.find_invisible("invoice\u202egpj.exe")  # [(7, Invisible.BIDI_CONTROL)]
+confusable.find_invisible("hi\U000e0068\U000e0069")  # two Invisible.TAG: hidden "hi"
+confusable.has_invisible(
+    "\U0001f468\u200d\U0001f469\u200d\U0001f467"
+)  # False: an emoji
+```
+
+Grapheme clusters, the characters a reader sees, and truncation that never cuts
+one apart. A cluster can be any size, so pair a grapheme limit with a size limit:
+
+```python
+[
+    str(g) for g in confusable.iter_graphemes("e\u0301\U0001f1fa\U0001f1f8")
+]  # ['e' + accent, a flag]
+confusable.truncate(name, 32)  # at most 32 graphemes
+confusable.truncate(bio, 300, max_utf8_bytes=3000)  # and at most 3000 bytes
+```
+
+`skeleton(text, direction)` takes the paragraph direction text is shown in:
+`"ltr"` (the default, UTS #39's `skeleton`), `"rtl"`, `"auto"`, or `None` for
+UTS #39's `internalSkeleton`, which ignores display order. Skeletons are for
+comparison, not display, and change with the Unicode version
+(`confusable.unicode_version`), so recompute any you store when it changes.
+
+### Moving from confusable_homoglyphs
+
+`confusable.compat.homoglyphs` has the API of `confusable_homoglyphs` 3.3.1, so
+existing code switches by changing one import:
+
+```python
+from confusable.compat.homoglyphs import categories, confusables
+
+confusables.is_dangerous("p\u0430ypal")  # True
+```
+
+It returns what that package returns, with current Unicode data. It also finds
+Arabic and Hebrew look-alikes, which that package's data misses: its generator
+copies the invisible LEFT-TO-RIGHT MARKs that `confusables.txt` puts around
+right-to-left characters in its comments. For new code, prefer `match` and
+`restriction_level`, which follow UTS #39.
+
+## What it is for
+
+`confusable` decides whether user-supplied text is safe to accept as an identity: a
+username, display name, project name, slug or filename. Planned for v1:
+
+- **Look-alike detection** with the UTS #39 skeleton algorithm, so that `pаypal`
+  (with a Cyrillic `а`) and `paypal` compare as confusable.
+- **Restriction levels and mixed-script checks** from UTS #39 section 5, built on the
+  Unicode `Scripts` and `Script_Extensions` properties.
+- **Identifier status and type** from the UTS #39 General Security Profile.
+- **Mixed numbers and suspicious combining marks** from UTS #39 sections 5.3 and
+  5.4: digits from different decimal systems, repeated or stacked marks, and a dot
+  above hidden by the letter under it.
+- **Invisible and control characters**: default-ignorable code points, zero-width
+  characters, bidirectional controls, and Tag-block "ASCII smuggling", while still
+  accepting valid emoji tag sequences such as subdivision flags.
+- **UAX #31 identifier checks** equivalent to Python 3.15's `unicodedata.isxidstart()`
+  and `unicodedata.isxidcontinue()`, on Python 3.10 and later.
+- **Grapheme clusters**: iteration and truncation that never split a user-perceived
+  character, equivalent to Python 3.15's `unicodedata.iter_graphemes()`.
+- **A compatibility module**, `confusable.compat.homoglyphs`, with the same API as
+  `confusable_homoglyphs` 3.3.1, so existing code can switch by changing one import,
+  and that package's tests run against it.
+
+The Unicode data is pinned to a single Unicode version (18.0.0) and generated into the
+package, so installing needs no network access and no compiler.
+
+## Correctness
+
+A look-alike that slips through is a security bug, so the tests come first. Every
+operation is checked against two independent implementations of UTS #39, ICU and
+the Rust `unicode-security` crate, over every Unicode code point and a corpus of
+known attacks and generated strings. Both oracles run at the pinned Unicode
+version, and every place where they differ is explained by a specific rule. See
+[tools/oracles/README.md](tools/oracles/README.md).
+
+## Development
+
+```bash
+uv sync
+uv run pre-commit install
+uv run pytest
+uv run pre-commit run --all-files
+```
+
+[CHARTER.md](CHARTER.md) says what the project is for and the principles every
+change is held to. [AGENTS.md](AGENTS.md) has the conventions, for people and
+coding agents alike.
+
+## Security
+
+To report a vulnerability, see [SECURITY.md](.github/SECURITY.md).
+
+## License
+
+MIT. See [LICENSE](LICENSE). The Unicode data the package and its test fixtures are
+generated from is under the Unicode License v3; see
+[LICENSES/Unicode-3.0.txt](LICENSES/Unicode-3.0.txt).

confusable-0.1.0a1/README.md

@@ -0,0 +1,171 @@
+# confusable
+
+Unicode spoofing and confusable detection for Python, following
+[Unicode Technical Standard #39](https://www.unicode.org/reports/tr39/). Pure Python,
+no runtime dependencies.
+
+> **Status: pre-alpha.** Look-alike detection (`skeleton`, `match`), mixed-script
+> detection, restriction levels, the identifier checks, the mixed-number and
+> combining-mark checks, invisible-character detection, grapheme clusters and the
+> compatibility module work and pass their tests. Nothing is on PyPI yet.
+
+## Usage
+
+```python
+import confusable
+
+confusable.skeleton("p\u0430ypal")  # 'paypal' (with CYRILLIC SMALL LETTER A)
+confusable.match("paypal", "p\u0430ypal")  # Match.MIXED_SCRIPT
+confusable.match("rn", "m")  # Match.SINGLE_SCRIPT
+confusable.match("paypal", "paypa1x")  # None: not confusable
+
+# The skeleton follows display order, so a right-to-left override is seen
+# the way a reader sees it:
+confusable.skeleton("invoice\u202egpj.exe")  # 'invoiceexe.jpg'
+```
+
+Restriction levels (UTS #39 section 5.2) rank how safely a string mixes scripts,
+from `ASCII_ONLY` to `UNRESTRICTED`, using the General Security Profile:
+
+```python
+confusable.restriction_level("caf\u00e9")  # RestrictionLevel.SINGLE_SCRIPT
+confusable.restriction_level("abc\u3042")  # HIGHLY_RESTRICTIVE: Latin with Japanese
+confusable.restriction_level(
+    "p\u0430ypal"
+)  # MINIMALLY_RESTRICTIVE: Latin with Cyrillic
+confusable.is_mixed_script("p\u0430ypal")  # True
+
+# Levels are ordered, most restrictive first:
+confusable.restriction_level(name) <= confusable.RestrictionLevel.HIGHLY_RESTRICTIVE
+```
+
+The identifier checks follow UTS #39's General Security Profile, under canonical
+equivalence, so the answer is the same however the text is encoded:
+
+```python
+confusable.is_allowed("paypal")  # True
+confusable.is_allowed("pay pal")  # False: a space is Restricted
+confusable.is_allowed("\u0114")  # True: U+0114 is Restricted, E + U+0306 is not
+confusable.identifier_types("\u200d")  # {IdentifierType.DEFAULT_IGNORABLE}
+confusable.isxidstart("_"), confusable.isxidcontinue("_")  # (False, True)
+
+# Persian, Malayalam and Sinhala need ZERO WIDTH (NON-)JOINER in some words. The
+# profile excludes both; joining_controls=True allows them only where UTS #39
+# section 3.1.1.1 says they change how the word looks:
+confusable.is_allowed("\u0dc1\u0dca\u200d\u0dbb\u0dd3", joining_controls=True)  # True
+confusable.is_allowed("pay\u200dpal", joining_controls=True)  # False
+```
+
+Three more checks from UTS #39 sections 5.3 and 5.4 catch digits from different
+number systems and combining marks that pile up or hide:
+
+```python
+confusable.has_mixed_numbers("1\u0661")  # True: ASCII and Arabic-Indic digits
+confusable.has_unlikely_marks("e\u0301\u0301")  # True: the same accent twice
+confusable.has_hidden_overlay("i\u0307")  # True: a dot above, lost in i's own dot
+```
+
+Invisible and control characters, for text that is not held to the identifier
+profile, such as display names and file names:
+
+```python
+confusable.find_invisible("pay\u200bpal")  # [(3, Invisible.DEFAULT_IGNORABLE)]: ZWSP
+confusable.find_invisible("invoice\u202egpj.exe")  # [(7, Invisible.BIDI_CONTROL)]
+confusable.find_invisible("hi\U000e0068\U000e0069")  # two Invisible.TAG: hidden "hi"
+confusable.has_invisible(
+    "\U0001f468\u200d\U0001f469\u200d\U0001f467"
+)  # False: an emoji
+```
+
+Grapheme clusters, the characters a reader sees, and truncation that never cuts
+one apart. A cluster can be any size, so pair a grapheme limit with a size limit:
+
+```python
+[
+    str(g) for g in confusable.iter_graphemes("e\u0301\U0001f1fa\U0001f1f8")
+]  # ['e' + accent, a flag]
+confusable.truncate(name, 32)  # at most 32 graphemes
+confusable.truncate(bio, 300, max_utf8_bytes=3000)  # and at most 3000 bytes
+```
+
+`skeleton(text, direction)` takes the paragraph direction text is shown in:
+`"ltr"` (the default, UTS #39's `skeleton`), `"rtl"`, `"auto"`, or `None` for
+UTS #39's `internalSkeleton`, which ignores display order. Skeletons are for
+comparison, not display, and change with the Unicode version
+(`confusable.unicode_version`), so recompute any you store when it changes.
+
+### Moving from confusable_homoglyphs
+
+`confusable.compat.homoglyphs` has the API of `confusable_homoglyphs` 3.3.1, so
+existing code switches by changing one import:
+
+```python
+from confusable.compat.homoglyphs import categories, confusables
+
+confusables.is_dangerous("p\u0430ypal")  # True
+```
+
+It returns what that package returns, with current Unicode data. It also finds
+Arabic and Hebrew look-alikes, which that package's data misses: its generator
+copies the invisible LEFT-TO-RIGHT MARKs that `confusables.txt` puts around
+right-to-left characters in its comments. For new code, prefer `match` and
+`restriction_level`, which follow UTS #39.
+
+## What it is for
+
+`confusable` decides whether user-supplied text is safe to accept as an identity: a
+username, display name, project name, slug or filename. Planned for v1:
+
+- **Look-alike detection** with the UTS #39 skeleton algorithm, so that `pаypal`
+  (with a Cyrillic `а`) and `paypal` compare as confusable.
+- **Restriction levels and mixed-script checks** from UTS #39 section 5, built on the
+  Unicode `Scripts` and `Script_Extensions` properties.
+- **Identifier status and type** from the UTS #39 General Security Profile.
+- **Mixed numbers and suspicious combining marks** from UTS #39 sections 5.3 and
+  5.4: digits from different decimal systems, repeated or stacked marks, and a dot
+  above hidden by the letter under it.
+- **Invisible and control characters**: default-ignorable code points, zero-width
+  characters, bidirectional controls, and Tag-block "ASCII smuggling", while still
+  accepting valid emoji tag sequences such as subdivision flags.
+- **UAX #31 identifier checks** equivalent to Python 3.15's `unicodedata.isxidstart()`
+  and `unicodedata.isxidcontinue()`, on Python 3.10 and later.
+- **Grapheme clusters**: iteration and truncation that never split a user-perceived
+  character, equivalent to Python 3.15's `unicodedata.iter_graphemes()`.
+- **A compatibility module**, `confusable.compat.homoglyphs`, with the same API as
+  `confusable_homoglyphs` 3.3.1, so existing code can switch by changing one import,
+  and that package's tests run against it.
+
+The Unicode data is pinned to a single Unicode version (18.0.0) and generated into the
+package, so installing needs no network access and no compiler.
+
+## Correctness
+
+A look-alike that slips through is a security bug, so the tests come first. Every
+operation is checked against two independent implementations of UTS #39, ICU and
+the Rust `unicode-security` crate, over every Unicode code point and a corpus of
+known attacks and generated strings. Both oracles run at the pinned Unicode
+version, and every place where they differ is explained by a specific rule. See
+[tools/oracles/README.md](tools/oracles/README.md).
+
+## Development
+
+```bash
+uv sync
+uv run pre-commit install
+uv run pytest
+uv run pre-commit run --all-files
+```
+
+[CHARTER.md](CHARTER.md) says what the project is for and the principles every
+change is held to. [AGENTS.md](AGENTS.md) has the conventions, for people and
+coding agents alike.
+
+## Security
+
+To report a vulnerability, see [SECURITY.md](.github/SECURITY.md).
+
+## License
+
+MIT. See [LICENSE](LICENSE). The Unicode data the package and its test fixtures are
+generated from is under the Unicode License v3; see
+[LICENSES/Unicode-3.0.txt](LICENSES/Unicode-3.0.txt).

confusable-0.1.0a1/pyproject.toml

@@ -0,0 +1,137 @@
+[project]
+name = "confusable"
+version = "0.1.0a1"
+description = "Unicode spoofing and confusable detection (UTS #39) in pure Python."
+readme = "README.md"
+license = "MIT"
+license-files = [
+    "LICENSE",
+    "LICENSES/Unicode-3.0.txt",
+]
+requires-python = ">=3.10"
+dependencies = []
+keywords = [
+    "unicode",
+    "confusables",
+    "homoglyph",
+    "homograph",
+    "spoofing",
+    "uts39",
+    "identifier",
+    "security",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: 3.15",
+    "Topic :: Security",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Text Processing :: Linguistic",
+    "Typing :: Typed",
+]
+
+[[project.authors]]
+name = "Atilla Guzel"
+email = "33524244+atillaguzel@users.noreply.github.com"
+
+[project.urls]
+Homepage = "https://github.com/blip-box/confusable"
+Repository = "https://github.com/blip-box/confusable"
+Issues = "https://github.com/blip-box/confusable/issues"
+Changelog = "https://github.com/blip-box/confusable/releases"
+
+[build-system]
+requires = ["uv_build>=0.12.24,<0.14.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+test = [
+    "hypothesis>=6.168.5",
+    "pytest>=9.1.1",
+]
+lint = [
+    { include-group = "test" },
+    "mypy>=2.4.0",
+    "pre-commit>=4.6.2",
+    "virtualenv>=21.14.13",
+]
+
+[tool.uv]
+default-groups = [
+    "test",
+    "lint",
+]
+required-version = ">=0.13.4"
+
+[tool.pytest.ini_options]
+minversion = "9.0"
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--strict-config",
+    "--import-mode=importlib",
+]
+testpaths = ["tests"]
+pythonpath = ["."]
+xfail_strict = true
+filterwarnings = ["error"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+warn_unreachable = true
+files = [
+    "src",
+    "tests",
+    "tools",
+]
+exclude = [
+    "^tools/oracles/rust/(vendor|target)/",
+    '^tools/oracles/icu/\.build/',
+    '^tools/oracles/homoglyphs/\.build/',
+    '^tools/\.cache/',
+]
+
+[tool.ruff]
+line-length = 88
+extend-exclude = ["src/confusable/_data/"]
+force-exclude = true
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "F",
+    "W",
+    "D",
+    "I",
+    "UP",
+    "N",
+    "B",
+    "PT",
+    "RUF",
+    "PLE25",
+]
+ignore = [
+    "D203",
+    "D213",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = [
+    "D",
+    "RUF001",
+    "RUF002",
+    "RUF003",
+]
+"tools/**" = ["D1"]
+
+[tool.ruff.format]
+docstring-code-format = true