✨ 💫 sent char_span through with spaCy & regex & ♻️ Refactoring for more languages support

.coveragerc

@@ -0,0 +1,10 @@
+[report]
+exclude_lines =
+    pragma: no cover
+    def __repr__
+    if self.debug:
+    if settings.DEBUG
+    raise AssertionError
+    raise NotImplementedError
+    if 0:
+    if __name__ == .__main__.:

.github/workflows/python-package.yml

@@ -0,0 +1,50 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python package
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.5, 3.6, 3.7, 3.8]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
+      run: |
+        pip install flake8
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        pip install pytest
+        pip install pytest-cov
+        pytest --cov=pysbd tests/ --color yes --cov-report=xml --cov-report=html
+    - name: Upload coverage to Codecov
+      uses: codecov/[email protected]
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}
+        file: ./coverage.xml
+        flags: unittests
+        env_vars: OS,PYTHON
+        name: codecov-umbrella
+        fail_ci_if_error: true

CHANGELOG.md

@@ -1,46 +1,48 @@
-# v0.1.0
-
--   Initial Release
-
-# v0.1.1
-
--   English language support only
--   Support for oother languages - WIP
-
-# v0.1.2
+# v0.3.0rc
+-   ✨ 💫 sent `char_span` through with spaCy & regex approach - \#63
+-   ♻️ Refactoring to support multiple languages
+-   ✨ 💫Initial language support for - Hindi, Marathi, Chinese, Spanish
+-   ✅ Updated tests - more coverage & regression tests for issues
+-   👷👷🏻‍♀️ GitHub actions for CI-CD
+-   💚☂️ Add code coverage - coverage.py Add Codecov
+-   🐛 Fix incorrect text span & vanilla pysbd vs spacy output discrepancy - \#49, \#53, \#55 , \#59
+-   🐛 Fix `NUMBERED_REFERENCE_REGEX` for zero or one time - \#58
+-   🔐Fix security vulnerability bleach - \#62
 
--   🐛BugFix - IndexError of `scanlists` function
 
-# v0.1.3
-
--   🐛 Fix `lists_item_replacer` - \#29
--   🐛 Fix & ♻️refactor `replace_multi_period_abbreviations` - \#30
--   🐛 Fix `abbreviation_replacer` - \#31
--   ✅ Add regression tests for issues
-
-# v0.1.4
-
--   ✨ ✅ Handle intermittent punctuations - \#34
+# v0.2.3
+-   🐛 Performance improvement in `abbreviation_replacer`- \#50
 
-# v0.1.5
+# v0.2.2
+-   🐛 Fix unbalanced parenthesis - \#47
 
--   🐛 Handle text with only punctuations - \#36
--   🐛 Handle exclamation marks at EOL- \#37
+# v0.2.1
+-   ✨pySBD as a spaCy component through entrypoints
 
 # v0.2.0
-
 -   ✨Add `char_span` parameter (optional) to get sentence & its (start, end) char offsets from original text
 -   ✨pySBD as a spaCy component example
 -   🐛 Fix double question mark swallow bug - \#39
 
-# v0.2.1
+# v0.1.5
+-   🐛 Handle text with only punctuations - \#36
+-   🐛 Handle exclamation marks at EOL- \#37
 
--   ✨pySBD as a spaCy component through entrypoints
+# v0.1.4
+-   ✨ ✅ Handle intermittent punctuations - \#34
 
-# v0.2.2
+# v0.1.3
+-   🐛 Fix `lists_item_replacer` - \#29
+-   🐛 Fix & ♻️refactor `replace_multi_period_abbreviations` - \#30
+-   🐛 Fix `abbreviation_replacer` - \#31
+-   ✅ Add regression tests for issues
 
--   🐛 Fix unbalanced parenthesis - \#47
+# v0.1.2
+-   🐛BugFix - IndexError of `scanlists` function
 
-# v0.2.3
+# v0.1.1
+-   English language support only
+-   Support for oother languages - WIP
 
--   🐛 Performance improvement in `abbreviation_replacer`- \#50
+# v0.1.0
+-   Initial Release

Pipfile

@@ -4,14 +4,14 @@ url = "https://pypi.org/simple"
 verify_ssl = true
 
 [dev-packages]
-yapf = "*"
 ipython = "*"
 ipdb = "*"
 twine = "*"
+pytest = "*"
+pytest-cov = "*"
 
 [packages]
-pytest = "*"
-autopep8 = "*"
+spacy = "*"
 
 [requires]
 python_version = "3.6"