Download punkt_tab required by nltk 3.9

NatLibFi · Aug 20, 2024 · fc80394 · fc80394
1 parent 9036913
commit fc80394
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/.github/workflows/cicd.yml b/.github/workflows/cicd.yml
@@ -101,7 +101,7 @@ jobs:
           # download the small English pretrained spaCy model needed by spacy analyzer
           poetry run python -m spacy download en_core_web_sm --upgrade-strategy only-if-needed
         fi
-        poetry run python -m nltk.downloader punkt
+        poetry run python -m nltk.downloader punkt_tab
     - name: Test with pytest
       run: |
         poetry run pytest --cov=./ --cov-report xml

diff --git a/Dockerfile b/Dockerfile
@@ -28,7 +28,7 @@ RUN echo "Installing dependencies for optional features: $optional_dependencies"
 	&& rm -rf /root/.cache/pypoetry  # No need for cache because of poetry.lock
 
 # Download nltk data
-RUN python -m nltk.downloader punkt -d /usr/share/nltk_data
+RUN python -m nltk.downloader punkt_tab -d /usr/share/nltk_data
 
 # Download spaCy models, if the optional feature was selected
 ARG spacy_models=en_core_web_sm