updated to spacy v3:

- pipeline stage added by name
- declared entry_point to shorten set-up
- changed directory name to match package name

.gitignore

@@ -2,4 +2,143 @@ data/*
 .idea
 *.log
 .ipynb_checkpoints
-data_spacy_entity_linker
+data_spacy_entity_linker
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/

README.md

@@ -22,16 +22,12 @@ It also comes along with a number of disadvantages:
 ## Use
 ```python
 import spacy
-from spacyEntityLinker import EntityLinker
-
-#Initialize Entity Linker
-entityLinker = EntityLinker()
 
 #initialize language model
 nlp = spacy.load("en_core_web_sm")
 
-#add pipeline
-nlp.add_pipe(entityLinker, last=True, name="entityLinker")
+#add pipeline (declared through entry_points in setup.py)
+nlp.add_pipe("entityLinker", last=True)
 
 doc = nlp("I watched the Pirates of the Carribean last silvester")
 
@@ -135,7 +131,7 @@ To install the package run: <code>pip install spacy-entity-linker</code>
 
 Afterwards, the knowledge base (Wikidata) must be downloaded. This can be done by calling 
 
-<code>python -m spacyEntityLinker "download_knowledge_base"</code>
+<code>python -m spacy_entity_linker "download_knowledge_base"</code>
 
 This will download and extract a ~500mb file that contains a preprocessed version of Wikidata
 

requirements.txt

@@ -1 +1 @@
-spacy>=2.1.9
+-e .

setup.py

@@ -5,7 +5,6 @@
 
 # This file is part of fuzzywuzzy.
 
-from spacyEntityLinker import __version__
 import os
 
 try:
@@ -23,10 +22,10 @@ with open("README.md", "r") as fh:
 
 setup(
     name='spacy-entity-linker',
-    version=__version__,
+    version='0.0.6',
     author='Emanuel Gerber',
     author_email='[email protected]',
-    packages=['spacyEntityLinker'],
+    packages=['spacy_entity_linker'],
     url='https://github.com/egerber/spacy-entity-linker',
     license="MIT",
     classifiers=["Environment :: Console",
@@ -45,4 +44,11 @@ setup(
     long_description=long_description,
     long_description_content_type="text/markdown",
     zip_safe=True,
+    install_requires=[
+        'spacy>=3.0.0',
+        'numpy>=1.0.0'
+    ],
+    entry_points={
+        'spacy_factories': 'entityLinker = spacy_entity_linker.EntityLinker:EntityLinker'
+    }
 )

spacyEntityLinker/__init__.py

@@ -1,4 +0,0 @@
-from .EntityLinker import EntityLinker
-
-__version__ = '0.0.5'
-__all__ = [EntityLinker]

{spacyEntityLinker → spacy_entity_linker}/EntityCollection.py

@@ -1,5 +1,5 @@
 from collections import Counter, defaultdict
-from spacyEntityLinker.DatabaseConnection import get_wikidata_instance
+from .DatabaseConnection import get_wikidata_instance
 
 
 class EntityCollection:

{spacyEntityLinker → spacy_entity_linker}/EntityElement.py

@@ -1,5 +1,5 @@
-from spacyEntityLinker.DatabaseConnection import get_wikidata_instance
-from spacyEntityLinker.EntityCollection import EntityCollection
+from .DatabaseConnection import get_wikidata_instance
+from .EntityCollection import EntityCollection
 
 
 class EntityElement:

{spacyEntityLinker → spacy_entity_linker}/EntityLinker.py

@@ -1,12 +1,14 @@
-from spacyEntityLinker.EntityClassifier import EntityClassifier
-from spacyEntityLinker.EntityCollection import EntityCollection
-from spacyEntityLinker.TermCandidateExtractor import TermCandidateExtractor
 from spacy.tokens import Doc, Span
+from spacy.language import Language
 
+from .EntityClassifier import EntityClassifier
+from .EntityCollection import EntityCollection
+from .TermCandidateExtractor import TermCandidateExtractor
 
+@Language.factory('entityLinker')
 class EntityLinker:
 
-    def __init__(self):
+    def __init__(self, nlp, name):
         Doc.set_extension("linkedEntities", default=EntityCollection(), force=True)
         Span.set_extension("linkedEntities", default=None, force=True)
 

{spacyEntityLinker → spacy_entity_linker}/TermCandidate.py

@@ -1,6 +1,6 @@
-from spacyEntityLinker.EntityCandidates import EntityCandidates
-from spacyEntityLinker.EntityElement import EntityElement
-from spacyEntityLinker.DatabaseConnection import get_wikidata_instance
+from .EntityCandidates import EntityCandidates
+from .EntityElement import EntityElement
+from .DatabaseConnection import get_wikidata_instance
 
 
 class TermCandidate:

{spacyEntityLinker → spacy_entity_linker}/TermCandidateExtractor.py

@@ -1,4 +1,4 @@
-from spacyEntityLinker.TermCandidate import TermCandidate
+from .TermCandidate import TermCandidate
 
 
 class TermCandidateExtractor:

spacy_entity_linker/__init__.py

@@ -0,0 +1,11 @@
+try:  # Python 3.8
+    import importlib.metadata as importlib_metadata
+except ImportError:
+    import importlib_metadata  # noqa: F401
+
+from .EntityLinker import EntityLinker
+
+print(__name__)
+pkg_meta = importlib_metadata.metadata(__name__.split(".")[0])
+__version__ = pkg_meta["version"]
+__all__ = [EntityLinker]

tests/test_EntityLinker.py

@@ -1,6 +1,6 @@
 import unittest
 import spacy
-from spacyEntityLinker.EntityLinker import EntityLinker
+from spacy_entity_linker.EntityLinker import EntityLinker
 
 
 class TestEntityLinker(unittest.TestCase):
@@ -10,9 +10,8 @@ class TestEntityLinker(unittest.TestCase):
         self.nlp = spacy.load('en_core_web_sm')
 
     def test_initialization(self):
-        entityLinker = EntityLinker()
 
-        self.nlp.add_pipe(entityLinker, last=True, name="entityLinker")
+        self.nlp.add_pipe("entityLinker", last=True)
 
         doc = self.nlp(
             "Elon Musk was born in South Africa. Bill Gates and Steve Jobs come from in the United States")

tests/test_TermCandidateExtractor.py

@@ -1,6 +1,6 @@
 import unittest
 import spacy
-import spacyEntityLinker.TermCandidateExtractor
+import spacy_entity_linker.TermCandidateExtractor
 
 
 class TestCandidateExtractor(unittest.TestCase):