From 5f45860de255adc72712032451577fd63e388d2a Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Mon, 26 Aug 2024 14:34:24 +0000
Subject: [PATCH] Bump nltk from 3.8.1 to 3.9.1 (#1993)

---
 docker/Dockerfile.baseimage |  5 ++++-
 poetry.lock                 | 10 +++++-----
 pyproject.toml              |  1 -
 tox.ini                     |  2 ++
 4 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/docker/Dockerfile.baseimage b/docker/Dockerfile.baseimage
index 44acef1022..0aaf8816ba 100644
--- a/docker/Dockerfile.baseimage
+++ b/docker/Dockerfile.baseimage
@@ -11,7 +11,7 @@
 #
 # Main repo for this image is here:
 # https://github.com/phusion/baseimage-docker
-FROM phusion/baseimage:jammy-1.0.1 As baseimage
+FROM phusion/baseimage:jammy-1.0.1 AS baseimage
 
 # Make sure base system is up to date
 RUN apt-get update && \
@@ -63,7 +63,10 @@ RUN python3 -m venv env && \
     . env/bin/activate && \
     pip install --upgrade pip && \
     poetry install --only main,pg --sync --no-root && \
+    # TODO: This can be removed once NLTK merges https://github.com/sloria/TextBlob/pull/469
+    python3 -m nltk.downloader punkt_tab && \
     python3 -m textblob.download_corpora lite && \
+    rm -rf /root/nltk_data/tokenizers/punkt && \
     mv /root/nltk_data /usr/lib/ && \
     find /usr/lib/nltk_data -name *.zip -delete && \
     rm -Rf /root/.cache && \
diff --git a/poetry.lock b/poetry.lock
index b3997b165e..ed5e44a8bf 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -2846,13 +2846,13 @@ files = [
 
 [[package]]
 name = "nltk"
-version = "3.8.1"
+version = "3.9.1"
 description = "Natural Language Toolkit"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "nltk-3.8.1-py3-none-any.whl", hash = "sha256:fd5c9109f976fa86bcadba8f91e47f5e9293bd034474752e92a520f81c93dda5"},
-    {file = "nltk-3.8.1.zip", hash = "sha256:1834da3d0682cba4f2cede2f9aad6b0fafb6461ba451db0efb6f9c39798d64d3"},
+    {file = "nltk-3.9.1-py3-none-any.whl", hash = "sha256:4fa26829c5b00715afe3061398a8989dc643b92ce7dd93fb4585a70930d168a1"},
+    {file = "nltk-3.9.1.tar.gz", hash = "sha256:87d127bd3de4bd89a4f81265e5fa59cb1b199b27440175370f7417d2bc7ae868"},
 ]
 
 [package.dependencies]
@@ -5124,4 +5124,4 @@ lxml = ">=3.8"
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<4"
-content-hash = "0733153c25bf8a37ba1661c2b13301ea3a4fbf79b851ab22fa4d703ee99ea33b"
+content-hash = "c601e5060bbc791f42c5e4ab9e91ab106f9f5c3ed6053f11d47c005e7f7c92d2"
diff --git a/pyproject.toml b/pyproject.toml
index f040c363c5..d0696bb349 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -246,7 +246,6 @@ lxml = {extras = ["html-clean"], version = "^5.2.1"}
 money = "1.3.0"
 multipledispatch = "^1.0"
 nameparser = "^1.1"  # nameparser is for author name manipulations
-nltk = "3.8.1"  # nltk is a textblob dependency.
 opensearch-dsl = "~1.0"
 opensearch-py = "~1.1"
 palace-webpub-manifest-parser = "^4.0.0"
diff --git a/tox.ini b/tox.ini
index b0b53b0811..51ab13f7ec 100644
--- a/tox.ini
+++ b/tox.ini
@@ -5,6 +5,8 @@ skipsdist = true
 [testenv]
 commands_pre =
     poetry install --without ci --sync -v
+    # TODO: This can be removed once NLTK merges https://github.com/sloria/TextBlob/pull/469
+    python -m nltk.downloader punkt_tab
     python -m textblob.download_corpora
 commands =
     pytest {posargs:tests}