Merge branch 'nltk:develop' into hotfix-3072

Author: ekaf

.github/labeler.yml

@@ -1,49 +1,64 @@
 # https://github.com/actions/labeler
 CI:
-  - .github/workflows/*
-  - .github/labeler.yml
+  - changed-files:
+    - any-glob-to-any-file: [".github/workflows/*", ".github/labeler.yml"]
 
 classifier:
-  - nltk/classify/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/classify/**/*"
 
 cli:
-  - nltk/cli.py
+  - changed-files:
+    - any-glob-to-any-file: "nltk/cli.py"
 
 cluster:
-  - nltk/cluster/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/cluster/**/*"
 
 corpus:
-  - nltk/corpus/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/corpus/**/*"
 
 GUI:
-  - nltk/app/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/app/**/*"
 
 internals:
-  - nltk/internals.py
+  - changed-files:
+    - any-glob-to-any-file: "nltk/internals.py"
 
 language-model:
-  - nltk/lm/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/lm/**/*"
 
 metrics:
-  - nltk/metrics/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/metrics/**/*"
 
 parsing:
-  - nltk/parse/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/parse/**/*"
 
 sentiment:
-  - nltk/sentiment/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/sentiment/**/*"
 
 stem/lemma:
-  - nltk/stem/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/stem/**/*"
 
 tagger:
-  - nltk/tag/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/tag/**/*"
 
 tokenizer:
-  - nltk/tokenize/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/tokenize/**/*"
 
 twitter:
-  - nltk/twitter/**/*
+  - changed-files:
+    - any-glob-to-any-file: "nltk/twitter/**/*"
 
 wordnet:
-  - nltk/corpus/reader/wordnet.py
+  - changed-files:
+    - any-glob-to-any-file: "nltk/wordnet/**/*"

.github/workflows/ci.yaml

@@ -21,9 +21,13 @@ jobs:
     name: Run pre-commit
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v3
-      - uses: pre-commit/[email protected]
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.x' # run with latest python version
+      - run: |
+          pip install pre-commit
+          pre-commit run --all-files
 
   cache_nltk_data:
     name: Cache nltk_data
@@ -34,7 +38,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Cache nltk data
         uses: actions/cache@v3
@@ -56,7 +60,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Cache third party tools
         uses: actions/cache@v3
@@ -76,21 +80,21 @@ jobs:
     needs: [cache_nltk_data, cache_third_party]
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
         os: [ubuntu-latest, macos-latest, windows-latest]
       fail-fast: false
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup python
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
       - name: Set up JDK 16
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           distribution: 'zulu'
           java-version: '16'

.github/workflows/labeler.yml

@@ -9,7 +9,7 @@ jobs:
       pull-requests: write
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/labeler@v4
+    - uses: actions/labeler@v5
       with:
         repo-token: "${{ secrets.GITHUB_TOKEN }}"
         sync-labels: true

.pre-commit-config.yaml

@@ -1,19 +1,19 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.5.0
     hooks:
       - id: fix-byte-order-marker
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: requirements-txt-fixer
       - id: check-yaml
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.1.0
+    rev: v3.15.0
     hooks:
     - id: pyupgrade
-      args: ["--py37-plus"]
+      args: ["--py38-plus"]
   - repo: https://github.com/ambv/black
-    rev: 22.3.0
+    rev: 23.12.0
     hooks:
     - id: black
   - repo: local
@@ -27,4 +27,4 @@ repos:
         types_or: [cython, pyi, python]
         args: ['--filter-files']
         minimum_pre_commit_version: '2.9.2'
-        additional_dependencies: ['isort==5.10.1']
+        additional_dependencies: ['isort==5.13.2']

AUTHORS.md

@@ -110,6 +110,7 @@
 - Tom Lippincott
 - Peter Ljunglöf
 - Alex Louden
+- David Lukeš
 - Joseph Lynch
 - Nitin Madnani
 - Felipe Madrigal
@@ -127,6 +128,7 @@
 - David McClosky
 - Xinfan Meng
 - Dmitrijs Milajevs
+- Matt Miller
 - Margaret Mitchell
 - Tomonori Nagano
 - Jason Narad
@@ -296,6 +298,10 @@
 - M.K. Pawelkiewicz <https://github.com/hamiltonianflow>
 - Steven Thomas Smith <https://github.com/essandess>
 - Jan Lennartz <https://github.com/Madnex>
+- Tim Sockel <https://github.com/TiMauzi>
+- Akihiro Yamazaki <https://github.com/zakkie>
+- Ron Urbach <https://github.com/sharpblade4>
+- Vivek Kalyan <https://github.com/vivekkalyan>
 
 ## Others whose work we've taken and included in NLTK, but who didn't directly contribute it:
 

CITATION.cff

@@ -39,5 +39,9 @@ preferred-citation:
     - given-names: Edward
       family-names: Loper
   year: 2009
+  month: 6
+  url: "https://www.nltk.org/book/"
+  isbn: "9780596516499"
   publisher:
     name: "O'Reilly Media, Inc."
+    website: "https://www.oreilly.com/"

CONTRIBUTING.md

@@ -77,7 +77,7 @@ Summary of our git branching model:
 - Do many small commits on that branch locally (`git add files-changed`,
   `git commit -m "Add some change"`);
 - Run the tests to make sure nothing breaks
-  (`tox -e py37` if you are on Python 3.7);
+  (`tox -e py312` if you are on Python 3.12);
 - Add your name to the `AUTHORS.md` file as a contributor;
 - Push to your fork on GitHub (with the name as your local branch:
   `git push origin branch-name`);
@@ -109,7 +109,7 @@ Summary of our git branching model:
 - Use [PEP8](https://www.python.org/dev/peps/pep-0008/);
 - Write tests for your new features (please see "Tests" topic below);
 - Always remember that [commented code is dead
-  code](https://www.codinghorror.com/blog/2008/07/coding-without-comments.html);
+  code](https://blog.codinghorror.com/coding-without-comments/);
 - Name identifiers (variables, classes, functions, module names) with readable
   names (`x` is always wrong);
 - When manipulating strings, we prefer either [f-string
@@ -169,7 +169,7 @@ The [`.github/workflows/ci.yaml`](https://github.com/nltk/nltk/blob/develop/.git
        - Otherwise, download all the data packages through `nltk.download('all')`.
 
   - The `test` job
-    - tests against supported Python versions (`3.7`, `3.8`, `3.9`).
+    - tests against supported Python versions (`3.8`, `3.9`, `3.10`, `3.11`, `3.12`).
     - tests on `ubuntu-latest` and `macos-latest`.
     - relies on the `cache_nltk_data` job to ensure that `nltk_data` is available.
     - performs these steps:
@@ -189,7 +189,7 @@ The [`.github/workflows/ci.yaml`](https://github.com/nltk/nltk/blob/develop/.git
 #### To test with `tox` locally
 
 First setup a new virtual environment, see https://docs.python-guide.org/dev/virtualenvs/
-Then run `tox -e py37`.
+Then run `tox -e py312`.
 
 For example, using `pipenv`:
 
@@ -198,7 +198,7 @@ git clone https://github.com/nltk/nltk.git
 cd nltk
 pipenv install -r pip-req.txt
 pipenv install tox
-tox -e py37
+tox -e py312
 ```
 
 

README.md

@@ -4,7 +4,7 @@
 
 NLTK -- the Natural Language Toolkit -- is a suite of open source Python
 modules, data sets, and tutorials supporting research and development in Natural
-Language Processing. NLTK requires Python version 3.7, 3.8, 3.9, 3.10 or 3.11.
+Language Processing. NLTK requires Python version 3.8, 3.9, 3.10, 3.11 or 3.12.
 
 For documentation, please visit [nltk.org](https://www.nltk.org/).
 

nltk/__init__.py

@@ -52,7 +52,7 @@
 # Description of the toolkit, keywords, and the project's primary URL.
 __longdescr__ = """\
 The Natural Language Toolkit (NLTK) is a Python package for
-natural language processing.  NLTK requires Python 3.7, 3.8, 3.9, 3.10 or 3.11."""
+natural language processing.  NLTK requires Python 3.8, 3.9, 3.10, 3.11 or 3.12."""
 __keywords__ = [
     "NLP",
     "CL",
@@ -84,11 +84,11 @@
     "Intended Audience :: Science/Research",
     "License :: OSI Approved :: Apache Software License",
     "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3.7",
     "Programming Language :: Python :: 3.8",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
     "Topic :: Scientific/Engineering",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Scientific/Engineering :: Human Machine Interfaces",

nltk/app/chunkparser_app.py

@@ -78,7 +78,7 @@ class RegexpChunkApp:
         "VBD": "Verb, past tense",
         "MD": "Modal",
         "NNS": "Noun, plural",
-        "NN": "Noun, singular or masps",
+        "NN": "Noun, singular or mass",
         "VBN": "Verb, past participle",
         "VBZ": "Verb,3rd ps. sing. present",
         "NNP": "Proper noun, singular",
@@ -713,7 +713,7 @@ def _eval_demon(self):
         if self.normalized_grammar != self._eval_normalized_grammar:
             # Check if we've seen this grammar already.  If so, then
             # just use the old evaluation values.
-            for (g, p, r, f) in self._history:
+            for g, p, r, f in self._history:
                 if self.normalized_grammar == self.normalize_grammar(g):
                     self._history.append((g, p, r, f))
                     self._history_index = len(self._history) - 1
@@ -850,7 +850,7 @@ def _init_widgets(self, top):
             ).grid(column=i * 2 + 1, row=0)
         self.helptabs[self.HELP[0][0]].configure(font=self._font)
         self.helpbox.tag_config("elide", elide=True)
-        for (tag, params) in self.HELP_AUTOTAG:
+        for tag, params in self.HELP_AUTOTAG:
             self.helpbox.tag_config("tag-%s" % tag, **params)
         self.show_help(self.HELP[0][0])
 
@@ -1047,7 +1047,7 @@ def show_trace(self, *e):
     def show_help(self, tab):
         self.helpbox["state"] = "normal"
         self.helpbox.delete("1.0", "end")
-        for (name, tabstops, text) in self.HELP:
+        for name, tabstops, text in self.HELP:
             if name == tab:
                 text = text.replace(
                     "<<TAGSET>>",
@@ -1066,7 +1066,7 @@ def show_help(self, tab):
                 self.helpbox.config(tabs=tabstops)
                 self.helpbox.insert("1.0", text + "\n" * 20)
                 C = "1.0 + %d chars"
-                for (tag, params) in self.HELP_AUTOTAG:
+                for tag, params in self.HELP_AUTOTAG:
                     pattern = f"(?s)(<{tag}>)(.*?)(</{tag}>)"
                     for m in re.finditer(pattern, text):
                         self.helpbox.tag_add("elide", C % m.start(1), C % m.end(1))