feat: add punkt_tab to NLTK data downloads

Add punkt_tab to the list of NLTK downloads in Python 3.10, 3.11, and 3.12 Dockerfiles to support additional text processing capabilities.
hyperskill · Jan 17, 2025 · 7465ae5 · 7465ae5
1 parent c7df593
commit 7465ae5
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/epicbox-python/310/Dockerfile b/epicbox-python/310/Dockerfile
@@ -35,7 +35,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 COPY requirements.txt /tmp
 
 RUN pip install --no-cache-dir -r /tmp/requirements.txt \
-    && python -m nltk.downloader -d ${NLTK_DIR} averaged_perceptron_tagger brown gutenberg movie_reviews omw-1.4 punkt treebank word2vec_sample wordnet \
+    && python -m nltk.downloader -d ${NLTK_DIR} averaged_perceptron_tagger brown gutenberg movie_reviews omw-1.4 punkt punkt_tab treebank word2vec_sample wordnet \
     && wget -qO- https://download.cdn.yandex.net/mystem/mystem-3.1-linux-64bit.tar.gz | tar xvz -C ${MYSTEM_DIR} \
     && rm /tmp/requirements.txt
 

diff --git a/epicbox-python/311/Dockerfile b/epicbox-python/311/Dockerfile
@@ -36,7 +36,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 COPY requirements.txt /tmp
 
 RUN pip install --no-cache-dir -r /tmp/requirements.txt \
-    && python -m nltk.downloader -d ${NLTK_DIR} averaged_perceptron_tagger brown gutenberg movie_reviews omw-1.4 punkt treebank word2vec_sample wordnet \
+    && python -m nltk.downloader -d ${NLTK_DIR} averaged_perceptron_tagger brown gutenberg movie_reviews omw-1.4 punkt punkt_tab treebank word2vec_sample wordnet \
     && wget -qO- https://download.cdn.yandex.net/mystem/mystem-3.1-linux-64bit.tar.gz | tar xvz -C ${MYSTEM_DIR} \
     && rm /tmp/requirements.txt
 

diff --git a/epicbox-python/312/Dockerfile b/epicbox-python/312/Dockerfile
@@ -35,7 +35,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 COPY requirements.txt /tmp
 
 RUN pip install --no-cache-dir -r /tmp/requirements.txt \
-    && python -m nltk.downloader -d ${NLTK_DIR} averaged_perceptron_tagger brown gutenberg movie_reviews omw-1.4 punkt treebank word2vec_sample wordnet \
+    && python -m nltk.downloader -d ${NLTK_DIR} averaged_perceptron_tagger brown gutenberg movie_reviews omw-1.4 punkt punkt_tab treebank word2vec_sample wordnet \
     && wget -qO- https://download.cdn.yandex.net/mystem/mystem-3.1-linux-64bit.tar.gz | tar xvz -C ${MYSTEM_DIR} \
     && rm /tmp/requirements.txt