enable github ci actions pipeline (#11)

* enable github ci actions pipeline

* install wordnet data

Author: frascuchon

.github/workflows/ci.yml

@@ -0,0 +1,91 @@
+
+name: CI
+
+on:
+  push:
+    branches:
+      - 'master'
+    tags:
+      - 'v*'
+  pull_request:
+    branches:
+      - 'master'
+  release:
+    types: [published]
+
+jobs:
+  build:
+    name: Build python package
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout Code 🛎
+        uses: actions/checkout@v2
+      - name: Cache pip 👜
+        uses: actions/cache@v2
+        env:
+          # Increase this value to reset cache if setup.cfg has not changed
+          CACHE_NUMBER: 0
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ env.CACHE_NUMBER }}-${{ hashFiles('setup.cfg') }}
+      - name: Install package 🧊
+        run: pip install .[testing]
+      - name: Run tests 📈
+        run: |
+          python -m nltk.downloader wordnet
+          python -m nltk.downloader omw
+          pip install spacy~=2.0
+          python -m spacy download en_core_web_sm
+          python -m spacy download es_core_news_sm
+          pytest tests
+          pip install spacy~=3.0.0
+          python -m spacy download en_core_web_sm
+          python -m spacy download es_core_news_sm
+          pytest tests
+      - name: Build Package 🍟
+        run: |
+          pip install -U build
+          python -m build
+      - name: Upload package artifact
+        uses: actions/upload-artifact@v2
+        with:
+          name: python-package
+          path: dist
+
+  # This job will upload a Python Package using Twine when a release is created
+  # For more information see:
+  # https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+  deploy_release:
+    name: Deploy Release
+    runs-on: ubuntu-latest
+    if: ${{ github.event_name == 'release' }}
+    needs:
+      - build
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout Code 🛎
+        uses: actions/checkout@v2
+
+      - name: Download python package
+        uses: actions/download-artifact@v2
+        with:
+          name: python-package
+          path: dist
+      - name: Publish Package to TestPyPI 🥪
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          user: __token__
+          password: ${{ secrets.TEST_PYPI_API_TOKEN }}
+          repository_url: https://test.pypi.org/legacy/
+      - name: Test Installing 🍿
+        run: pip install --index-url https://test.pypi.org/simple --no-deps spacy-wordnet==${GITHUB_REF#refs/*/v}
+      - name: Publish Package to PyPI 🥩
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}

spacy_wordnet/wordnet_annotator.py

@@ -4,14 +4,21 @@
 
 from spacy_wordnet.wordnet_domains import Wordnet, load_wordnet_domains
 
-@Language.factory("spacy_wordnet", default_config={"lang": "en"})
-def wordnet_annotator(nlp, name, lang: str):
-	return WordnetAnnotator(lang=lang)
+try:
+
+    @Language.factory("spacy_wordnet", default_config={"lang": "en"})
+    def wordnet_annotator(nlp, name, lang: str):
+        return WordnetAnnotator(lang=lang)
+
+
+except AttributeError:
+    pass  # spacy 2.x
+
 
 class WordnetAnnotator(object):
-    __FIELD = 'wordnet'
+    __FIELD = "wordnet"
 
-    def __init__(self, lang: str = 'es'):
+    def __init__(self, lang: str = "es"):
         Token.set_extension(WordnetAnnotator.__FIELD, default=None, force=True)
         load_wordnet_domains()
         self.__lang = lang

tests/test_wordnet_annotator.py

@@ -11,32 +11,35 @@
 
 
 class WordnetAnnotatorTest(unittest.TestCase):
-
     def __init__(self, *args, **kwargs):
 
         super().__init__(*args, **kwargs)
 
-        self.nlp_en = spacy.load('en_core_web_sm')
-        self.nlp_es = spacy.load('es_core_news_sm')
+        self.nlp_en = spacy.load("en_core_web_sm")
+        self.nlp_es = spacy.load("es_core_news_sm")
 
-        # Add wordnet component
-        self.nlp_en.add_pipe("spacy_wordnet", config={'lang': self.nlp_en.lang})
-        self.nlp_es.add_pipe("spacy_wordnet", config={'lang': self.nlp_es.lang})
+        try:
+            # Add wordnet component
+            self.nlp_en.add_pipe("spacy_wordnet", config={"lang": self.nlp_en.lang})
+            self.nlp_es.add_pipe("spacy_wordnet", config={"lang": self.nlp_es.lang})
+        except TypeError:  # spacy 2.x
+            self.nlp_en.add_pipe(WordnetAnnotator(self.nlp_en.lang))
+            self.nlp_es.add_pipe(WordnetAnnotator(self.nlp_es.lang))
 
     def test_english_annotations(self):
 
-        token = self.nlp_en('contracts')[0]
+        token = self.nlp_en("contracts")[0]
 
         assert token._.wordnet.synsets()
         assert token._.wordnet.lemmas()
         assert token._.wordnet.wordnet_domains()
 
     def test_generate_variants_from_domain_list(self):
 
-        economy_domains = ['finance', 'banking']
+        economy_domains = ["finance", "banking"]
         enriched_sentence = []
 
-        sentence = self.nlp_en('I want to withdraw 5,000 euros')
+        sentence = self.nlp_en("I want to withdraw 5,000 euros")
 
         for token in sentence:
             synsets = token._.wordnet.wordnet_synsets_for_domain(economy_domains)
@@ -45,13 +48,15 @@ def test_generate_variants_from_domain_list(self):
                 lemmas_for_synset = []
                 for s in synsets:
                     lemmas_for_synset.extend(s.lemma_names())
-                enriched_sentence.append('({})'.format('|'.join(set(lemmas_for_synset))))
+                enriched_sentence.append(
+                    "({})".format("|".join(set(lemmas_for_synset)))
+                )
             else:
                 enriched_sentence.append(token.text)
-        print(' '.join(enriched_sentence))
+        print(" ".join(enriched_sentence))
 
     def test_spanish_annotations(self):
-        token = self.nlp_es('contratos')[0]
+        token = self.nlp_es("contratos")[0]
 
         assert token._.wordnet.synsets()
         assert token._.wordnet.lemmas()