unicode-segment 0.4.0__tar.gz

unicode_segment-0.4.0/LICENSE.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Lionel Rowe
+
+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.

unicode_segment-0.4.0/PKG-INFO

@@ -0,0 +1,79 @@
+Metadata-Version: 2.4
+Name: unicode-segment
+Version: 0.4.0
+Summary: Segment text with Unicode TR29-compliant segmenters.
+Author-email: Lionel Rowe <lionel.rowe@gmail.com>
+Maintainer-email: Lionel Rowe <lionel.rowe@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2025 Lionel Rowe
+        
+        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.
+        
+Project-URL: Homepage, https://github.com/lionel-rowe/unicode-segment
+Project-URL: Bug Reports, https://github.com/lionel-rowe/unicode-segment/issues
+Project-URL: Source, https://github.com/lionel-rowe/unicode-segment/
+Keywords: unicode,text-segmentation,segmenter,tr29,sentence,i18n
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.9
+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: Topic :: Text Processing
+Classifier: Topic :: Text Processing :: General
+Classifier: Topic :: Software Development :: Internationalization
+Classifier: Topic :: Software Development :: Localization
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: regex>=2025.11.3
+Dynamic: license-file
+
+# Unicode Segment
+
+Segment text with Unicode [TR29](https://www.unicode.org/reports/tr29/)-compliant segmenters.
+
+## Usage
+
+```py
+from unicode_segment import SentenceSegmenter
+
+text = """This, that, the other thing, etc. Another sentence... A, b, c, \
+etc., and more. D, e, f, etc. and more. One, i. e. two. Three, i. e., four. \
+Five, i.e. six. You have 4.2 messages. Property access: `a.b.c`."""
+
+segmenter = SentenceSegmenter()
+segments = segmenter.segment(text)
+
+assert list(segments) == [
+    (0, "This, that, the other thing, etc. "),
+    (34, "Another sentence... "),
+    (54, "A, b, c, etc., and more. "),
+    (79, "D, e, f, etc. and more. "),
+    (103, "One, i. e. two. "),
+    (119, "Three, i. e., four. "),
+    (139, "Five, i.e. six. "),
+    (155, "You have 4.2 messages. "),
+    (178, "Property access: `a.b.c`."),
+]
+```

unicode_segment-0.4.0/README.md

@@ -0,0 +1,28 @@
+# Unicode Segment
+
+Segment text with Unicode [TR29](https://www.unicode.org/reports/tr29/)-compliant segmenters.
+
+## Usage
+
+```py
+from unicode_segment import SentenceSegmenter
+
+text = """This, that, the other thing, etc. Another sentence... A, b, c, \
+etc., and more. D, e, f, etc. and more. One, i. e. two. Three, i. e., four. \
+Five, i.e. six. You have 4.2 messages. Property access: `a.b.c`."""
+
+segmenter = SentenceSegmenter()
+segments = segmenter.segment(text)
+
+assert list(segments) == [
+    (0, "This, that, the other thing, etc. "),
+    (34, "Another sentence... "),
+    (54, "A, b, c, etc., and more. "),
+    (79, "D, e, f, etc. and more. "),
+    (103, "One, i. e. two. "),
+    (119, "Three, i. e., four. "),
+    (139, "Five, i.e. six. "),
+    (155, "You have 4.2 messages. "),
+    (178, "Property access: `a.b.c`."),
+]
+```

unicode_segment-0.4.0/pyproject.toml

@@ -0,0 +1,47 @@
+[project]
+name = "unicode-segment"
+version = "0.4.0"
+description = "Segment text with Unicode TR29-compliant segmenters."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { file = "LICENSE.txt" }
+keywords = ["unicode", "text-segmentation", "segmenter", "tr29", "sentence", "i18n"]
+authors = [{ name = "Lionel Rowe", email = "lionel.rowe@gmail.com" }]
+maintainers = [{ name = "Lionel Rowe", email = "lionel.rowe@gmail.com" }]
+dependencies = [
+    "regex>=2025.11.3",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3.9",
+    "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",
+    "Topic :: Text Processing",
+    "Topic :: Text Processing :: General",
+    "Topic :: Software Development :: Internationalization",
+    "Topic :: Software Development :: Localization",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/lionel-rowe/unicode-segment"
+"Bug Reports" = "https://github.com/lionel-rowe/unicode-segment/issues"
+"Source" = "https://github.com/lionel-rowe/unicode-segment/"
+
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[dependency-groups]
+dev = [
+    "faker>=37.12.0",
+    "mypy>=1.18.2",
+    "pytest>=8.4.2",
+    "pytest-benchmark>=5.2.3",
+    "pytest-ruff>=0.5",
+    "types-regex>=2025.11.3.20251106",
+]

unicode_segment-0.4.0/setup.cfg

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

unicode_segment-0.4.0/src/unicode_segment/__init__.py

@@ -0,0 +1,3 @@
+from .sentence import SentenceSegmenter as SentenceSegmenter
+from .word import WordSegmenter as WordSegmenter
+from .grapheme import GraphemeSegmenter as GraphemeSegmenter