graphemeu 0.7.2__tar.gz

graphemeu-0.7.2/.github/workflows/python-app.yml

@@ -0,0 +1,37 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python package
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v2
+        with:
+          enable-cache: true
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
+      - name: Install the project
+        run: uv sync --all-extras --dev
+      - name: Lint with ruff
+        run: uvx ruff check .
+      - name: Format with ruff
+        run: uvx ruff format --check .
+      - name: Test with unittest
+        run: uv run --extra dev -m pytest

graphemeu-0.7.2/.gitignore

@@ -0,0 +1,61 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.cache
+nosetests.xml
+coverage.xml
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# OS X
+.DS_Store
+
+# Other
+.python-version
+.pytest_cache

graphemeu-0.7.2/.readthedocs.yaml

@@ -0,0 +1,31 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.12"
+    # You can also specify other tool versions:
+    # nodejs: "19"
+    # rust: "1.64"
+    # golang: "1.19"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally build your docs in additional formats such as PDF and ePub
+# formats:
+#    - pdf
+#    - epub
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+# python:
+#    install:
+#    - requirements: docs/requirements.txt

graphemeu-0.7.2/.vscode/launch.json

@@ -0,0 +1,15 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python Debugger: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal"
+        }
+    ]
+}

graphemeu-0.7.2/.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "python.analysis.typeCheckingMode": "basic"
+}

graphemeu-0.7.2/CHANGELOG.md

@@ -0,0 +1,51 @@
+## 0.7.2
+Fix bug #2 found by alwaysmpe.
+No API changes.
+
+## 0.7.1
+Fix bug #1 found by alwaysmpe.
+No API changes.
+
+## 0.7.0
+Added support for Unicode 16.
+Drops support for python 3.6. Now tested on python 3.7 - 3.12.
+No API changes.
+
+## 0.6.0
+Added support for Unicode 13.
+
+Drops support for python 3.4 & 3.5. Now tested on python 3.6 - 3.8.
+No API changes
+
+## 0.5.0
+Added support for Unicode 12.
+
+No API changes
+
+## 0.4.0
+Added support for Unicode 11.
+
+Added `grapheme.UNICODE_VERSION`.
+
+No other API changes
+
+## 0.3.0
+Added a few new functions:
+
+* `grapheme.safe_split_index`, which can find the highest grapheme boundary index in a given string without traversing the full grapheme sequence.
+* `grapheme.startswith`, which tests that a given string starts with the same grapheme sequence as a given prefix.
+* `grapheme.endswith`, which tests that a given string ends with the same grapheme sequence as a given suffix.
+
+## 0.2.1
+Performance improvements
+
+No new functionality, but noticably better performance.
+
+## 0.2.0
+* Adds `grapheme.contains`
+* Bugfix for empty strings
+
+## 0.1.0
+Initial release
+
+Basic support for getting graphemes, grapheme string lengths and grapheme based slicing.

graphemeu-0.7.2/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2017 The Python Packaging Authority (PyPA)
+Copyright (c) 2014 Mapbox
+Copyright (c) 2017 Alvin Lindstam
+Copyright (c) 2025 Timendum
+
+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.

graphemeu-0.7.2/PKG-INFO

@@ -0,0 +1,191 @@
+Metadata-Version: 2.4
+Name: graphemeu
+Version: 0.7.2
+Summary: Unicode grapheme helpers
+Project-URL: Homepage, https://github.com/timendum/grapheme
+Project-URL: Documentation, https://graphemeu.readthedocs.io/
+Author-email: Alvin Lindstam <alvin.lindstam@gmail.com>
+Maintainer: Timendum
+License: Copyright (c) 2017 The Python Packaging Authority (PyPA)
+        Copyright (c) 2014 Mapbox
+        Copyright (c) 2017 Alvin Lindstam
+        Copyright (c) 2025 Timendum
+        
+        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.
+License-File: LICENSE
+Keywords: grapheme,unicode
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python
+Requires-Python: >=3.7
+Provides-Extra: dev
+Requires-Dist: pytest; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: sphinx; extra == 'docs'
+Requires-Dist: sphinx-autobuild; extra == 'docs'
+Description-Content-Type: text/x-rst
+
+grapheme
+========
+
+A Python package for working with user perceived characters. More specifically,
+string manipulation and calculation functions for working with grapheme cluster
+groups (graphemes) as defined by the `Unicode Standard Annex #29 <http://unicode.org/reports/tr29/>`_.
+
+`documentation <https://graphemeu.readthedocs.io/>`_
+
+.. code-block:: console
+
+    pip install graphemeu
+
+Or similar.
+
+The currently supported version of Unicode: 16.0.0.
+
+This package is a fork of `grapheme <https://github.com/alvinlindstam/grapheme>`_ by Alvin Lindstam.
+
+What? Why?
+==========
+
+Unicode strings are made up of a series of unicode characters, but a unicode character does not
+always map to a user perceived character. Some human perceived characters are represented as two
+or more unicode characters.
+
+However, all built in python string functions and string methods work with single unicode characters
+without considering their connection to each other.
+
+.. code-block:: python
+
+    >>> string = 'u̲n̲d̲e̲r̲l̲i̲n̲e̲d̲'
+    >>> len(string)
+    20
+    >>> grapheme.length(string)
+    10
+    >>> string[:3]
+    'u̲n'
+    >>> grapheme.slice(string, 0, 3)
+    'u̲n̲d̲'
+
+This library implements the unicode default rules for extended grapheme clusters, and provides
+a set of functions for string manipulation based on graphemes.
+
+Documentation
+=============
+
+See `<https://graphemeu.readthedocs.io/en/latest/>`_.
+
+When should I consider graphemes instead of unicode characters?
+===============================================================
+
+You should consider working with graphemes over unicode code points when:
+
+* You wish to count characters as perceived by users.
+* You wish to split or truncate text at some user perceived lengths.
+* You wish to split or truncate text without risk of corrupting the characters.
+* Formatting text by length, such as creating text based tables in monospaced fonts
+
+You should work with normal python string functions when:
+
+* You wish to count or split by unicode codepoints for compliance with storage
+  limitations (such as database maximum length)
+* When working with systems that put limits on strings by unicode character
+  lengths
+* When you prioritize performance over correctness (see performance notes below)
+* When working with very long strings (see performance notes below)
+* If simplicity is more important than accuracy
+
+Performance
+===========
+
+Calculating graphemes require traversing the string and checking each character
+against a set of rules and the previous character(s). Because of this, all
+functions in this module will scale linearly to the string length.
+
+Whenever possible, they will only traverse the string for as long as needed and return
+early as soon as the requested output is generated. For example, the `grapheme.slice`
+function only has to traverse the string until the last requested grapheme is found, and
+does not care about the rest of the string.
+
+You should probably only use this package for testing/manipulating fairly short strings
+or with the beginning of long strings.
+
+When testing with a string of 10 000 ascii characters, and a 3.1 GHz processor, the execution
+time for some possible calls is roughly:
+
+================================================================  ==========================
+Code                                                              Approximate execution time
+================================================================  ==========================
+`len(long_ascii_string)`                                          3.0e-10 seconds
+`grapheme.length(long_ascii_string)`                              4.3e-05 seconds
+`grapheme.length(long_ascii_string, 500)`                         2.6e-06 seconds
+`long_ascii_string[0:100]`                                        1.3e-09 seconds
+`grapheme.slice(long_ascii_string, 0, 100)`                       6.3e-07 seconds
+`long_ascii_string[:100] in long_ascii_string`                    7.8e-09 seconds
+`grapheme.contains(long_ascii_string, long_ascii_string[:100])`   9.9e-07 seconds
+`long_ascii_string[-100:] in long_ascii_string`                   2.0e-08 seconds
+`grapheme.contains(long_ascii_string, long_ascii_string[-100:])`  6.9e-05 seconds
+================================================================  ==========================
+
+Execution times may improve in later releases, but calculating graphemes is and will continue
+to be notably slower than just counting unicode code points.
+
+Examples of grapheme cluster groups
+===================================
+
+This is not a complete list, but a some examples of when graphemes use multiple
+characters:
+
+* CR+LF
+* Hangul (korean)
+* Emoji with modifiers
+* Combining marks
+* Zero Width Join
+
+Development quick start
+=======================
+
+If you wish to contribute or edit this package, create a fork and clone it.
+
+Then install and run the tests.
+
+.. code-block:: console
+
+    uv run --extra dev -m pytest
+
+For the documentation, use:
+
+.. code-block:: console
+
+    uv run --extra docs sphinx-autobuild docs dist/www
+
+Unicode version upgrade
+-----------------------
+
+The library will issue a new release for each new unicode version.
+
+The steps necessary for this:
+
+1. Verify that there has been no material changes to the rulesets in Unicode
+   `Annex #29 <http://unicode.org/reports/tr29/>`_ (see modifications).
+2. Download the `data files <http://www.unicode.org/Public/>`_ from unicode into the unicode-data folder.
+   For the given version, some are in `ucd` and some are in `ucd/auxiliary`.
+3. Run `make process-data-files` to parse those files (will update the
+   `grapheme_break_property.json` and `derived_core_property.json` files).
+4. Update the unicode version in the documentation and in the source code.
+5. Bump the version.

graphemeu-0.7.2/README.rst

@@ -0,0 +1,148 @@
+grapheme
+========
+
+A Python package for working with user perceived characters. More specifically,
+string manipulation and calculation functions for working with grapheme cluster
+groups (graphemes) as defined by the `Unicode Standard Annex #29 <http://unicode.org/reports/tr29/>`_.
+
+`documentation <https://graphemeu.readthedocs.io/>`_
+
+.. code-block:: console
+
+    pip install graphemeu
+
+Or similar.
+
+The currently supported version of Unicode: 16.0.0.
+
+This package is a fork of `grapheme <https://github.com/alvinlindstam/grapheme>`_ by Alvin Lindstam.
+
+What? Why?
+==========
+
+Unicode strings are made up of a series of unicode characters, but a unicode character does not
+always map to a user perceived character. Some human perceived characters are represented as two
+or more unicode characters.
+
+However, all built in python string functions and string methods work with single unicode characters
+without considering their connection to each other.
+
+.. code-block:: python
+
+    >>> string = 'u̲n̲d̲e̲r̲l̲i̲n̲e̲d̲'
+    >>> len(string)
+    20
+    >>> grapheme.length(string)
+    10
+    >>> string[:3]
+    'u̲n'
+    >>> grapheme.slice(string, 0, 3)
+    'u̲n̲d̲'
+
+This library implements the unicode default rules for extended grapheme clusters, and provides
+a set of functions for string manipulation based on graphemes.
+
+Documentation
+=============
+
+See `<https://graphemeu.readthedocs.io/en/latest/>`_.
+
+When should I consider graphemes instead of unicode characters?
+===============================================================
+
+You should consider working with graphemes over unicode code points when:
+
+* You wish to count characters as perceived by users.
+* You wish to split or truncate text at some user perceived lengths.
+* You wish to split or truncate text without risk of corrupting the characters.
+* Formatting text by length, such as creating text based tables in monospaced fonts
+
+You should work with normal python string functions when:
+
+* You wish to count or split by unicode codepoints for compliance with storage
+  limitations (such as database maximum length)
+* When working with systems that put limits on strings by unicode character
+  lengths
+* When you prioritize performance over correctness (see performance notes below)
+* When working with very long strings (see performance notes below)
+* If simplicity is more important than accuracy
+
+Performance
+===========
+
+Calculating graphemes require traversing the string and checking each character
+against a set of rules and the previous character(s). Because of this, all
+functions in this module will scale linearly to the string length.
+
+Whenever possible, they will only traverse the string for as long as needed and return
+early as soon as the requested output is generated. For example, the `grapheme.slice`
+function only has to traverse the string until the last requested grapheme is found, and
+does not care about the rest of the string.
+
+You should probably only use this package for testing/manipulating fairly short strings
+or with the beginning of long strings.
+
+When testing with a string of 10 000 ascii characters, and a 3.1 GHz processor, the execution
+time for some possible calls is roughly:
+
+================================================================  ==========================
+Code                                                              Approximate execution time
+================================================================  ==========================
+`len(long_ascii_string)`                                          3.0e-10 seconds
+`grapheme.length(long_ascii_string)`                              4.3e-05 seconds
+`grapheme.length(long_ascii_string, 500)`                         2.6e-06 seconds
+`long_ascii_string[0:100]`                                        1.3e-09 seconds
+`grapheme.slice(long_ascii_string, 0, 100)`                       6.3e-07 seconds
+`long_ascii_string[:100] in long_ascii_string`                    7.8e-09 seconds
+`grapheme.contains(long_ascii_string, long_ascii_string[:100])`   9.9e-07 seconds
+`long_ascii_string[-100:] in long_ascii_string`                   2.0e-08 seconds
+`grapheme.contains(long_ascii_string, long_ascii_string[-100:])`  6.9e-05 seconds
+================================================================  ==========================
+
+Execution times may improve in later releases, but calculating graphemes is and will continue
+to be notably slower than just counting unicode code points.
+
+Examples of grapheme cluster groups
+===================================
+
+This is not a complete list, but a some examples of when graphemes use multiple
+characters:
+
+* CR+LF
+* Hangul (korean)
+* Emoji with modifiers
+* Combining marks
+* Zero Width Join
+
+Development quick start
+=======================
+
+If you wish to contribute or edit this package, create a fork and clone it.
+
+Then install and run the tests.
+
+.. code-block:: console
+
+    uv run --extra dev -m pytest
+
+For the documentation, use:
+
+.. code-block:: console
+
+    uv run --extra docs sphinx-autobuild docs dist/www
+
+Unicode version upgrade
+-----------------------
+
+The library will issue a new release for each new unicode version.
+
+The steps necessary for this:
+
+1. Verify that there has been no material changes to the rulesets in Unicode
+   `Annex #29 <http://unicode.org/reports/tr29/>`_ (see modifications).
+2. Download the `data files <http://www.unicode.org/Public/>`_ from unicode into the unicode-data folder.
+   For the given version, some are in `ucd` and some are in `ucd/auxiliary`.
+3. Run `make process-data-files` to parse those files (will update the
+   `grapheme_break_property.json` and `derived_core_property.json` files).
+4. Update the unicode version in the documentation and in the source code.
+5. Bump the version.

graphemeu-0.7.2/docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = python -msphinx
+SPHINXPROJ    = grapheme
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)