Merge branch 'release-4.3.3'

piskvorky · Jul 19, 2024 · e9ee434 · e9ee434
2 parents 30179c8 + ea7b162
commit e9ee434
Show file tree

Hide file tree

Showing 20 changed files with 157 additions and 83 deletions.
diff --git a/.github/workflows/build-docs.yml b/.github/workflows/build-docs.yml
@@ -18,9 +18,9 @@ jobs:
         shell: bash
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Setup up Python ${{ matrix.python }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           #
           # We use Py3.8 here for historical reasons.
@@ -55,12 +55,12 @@ jobs:
             git format-patch @^
             git bundle create prebuilt-docs-changes.bundle @^...@
             git reset --mixed @^
-            git diff --exit-code --stat @
+            git diff --stat @
           fi
 
       - name: Upload prebuilt docs changes
         if: always()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: prebuilt-docs-changes
           path: |

diff --git a/.github/workflows/build-wheels.yml b/.github/workflows/build-wheels.yml
@@ -15,28 +15,28 @@ jobs:
 
   build_wheels:
     needs: linters
-    name: Build wheels on ${{ matrix.os }}
+    name: Build ${{ matrix.os }}
     runs-on: ${{ matrix.os }}
     defaults:
       run:
         shell: bash
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04, windows-2019, macos-11]
+        os: [ubuntu-20.04, windows-2019, macos-12]
     steps:
 
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Set up QEMU
         if: runner.os == 'Linux'
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
         with:
           platforms: all
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.13.1
+        uses: pypa/cibuildwheel@v2.18.1
         env:
           CIBW_ARCHS_LINUX: x86_64 aarch64
           CIBW_ARCHS_MACOS: x86_64 arm64
@@ -49,49 +49,46 @@ jobs:
 
       - name: Upload wheels as artifacts
         if: always()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: wheels-${{ matrix.os }}
           path: wheelhouse/*.whl
 
   test:
-    name: Test wheel for ${{ matrix.os }} Python ${{ matrix.python }}
+    name: Test ${{ matrix.os }} Py${{ matrix.python }}
     needs: build_wheels
     strategy:
       fail-fast: false
       matrix:
         include:
-          - {python: '3.8', os: macos-11}
-          - {python: '3.9', os: macos-11}
-          - {python: '3.10', os: macos-11}
-          - {python: '3.11', os: macos-11}
+          - {python: '3.8', os: macos-12}
+          - {python: '3.9', os: macos-12}
+          - {python: '3.10', os: macos-12}
+          - {python: '3.11', os: macos-12}
+          - {python: '3.12', os: macos-12}
 
           - {python: '3.8', os: ubuntu-20.04}
           - {python: '3.9', os: ubuntu-20.04}
           - {python: '3.10', os: ubuntu-20.04}
           - {python: '3.11', os: ubuntu-20.04}
+          - {python: '3.12', os: ubuntu-20.04}
 
           - {python: '3.8', os: windows-2019}
           - {python: '3.9', os: windows-2019}
 
-          #
-          # We know that the Windows Py3.10 wheels are broken.  Don't test them,
-          # because it will fail the entire workflow.
-          #
-          # https://github.com/RaRe-Technologies/gensim/issues/3489
-          #
-          # - {python: '3.10', os: windows-2019}
+          - {python: '3.10', os: windows-2019}
           - {python: '3.11', os: windows-2019}
+          - {python: '3.12', os: windows-2019}
 
     runs-on: ${{ matrix.os }}
     steps:
       - name: Setup up Python ${{ matrix.python }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
 
       - name: Downloads build artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           path: artifacts/
 
@@ -101,6 +98,19 @@ jobs:
       - name: Install oldest-supported-numpy
         run: python -m pip install oldest-supported-numpy
 
+      #
+      # We know that the Windows Py3.10 wheels are broken: they won't work
+      # with older numpy versions.  We still want to test the wheel somehow,
+      # so we use a newer numpy version.
+      #
+      # https://github.com/RaRe-Technologies/gensim/issues/3489
+      #
+      - name: Install newest numpy (windows py3.10 only)
+        if: ${{ (matrix.os == 'windows-2019') && (matrix.python == '3.10') }}
+        run: |
+          python -m pip uninstall --yes oldest-supported-numpy
+          python -m pip install --upgrade numpy
+
       #
       # Avoid checking out the entire gensim repo to get just one file
       #
@@ -129,29 +139,34 @@ jobs:
     needs: build_wheels
     runs-on: ubuntu-latest
     steps:
-
-      - name: Install wheel uploading tool
-        run: python -m pip install wheelhouse-uploader
+      - run: python -m pip install awscli boto3
 
       - name: Downloads build artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           path: artifacts/
 
       - name: Check files
         run: tree artifacts/
 
-      - name: Move all wheels into one folder
-        run: mkdir wheelhouse ; find artifacts/ -name '*.whl' -exec mv -v {} wheelhouse/ \;
+      #
+      # Avoid checking out the entire gensim repo to get just one file
+      #
+      - name: Download installwheel.py
+        run: curl "https://raw.githubusercontent.com/RaRe-Technologies/gensim/develop/.github/workflows/update_index.py" --output update_index.py --silent
 
       - name: Upload wheels to s3://gensim-wheels
         #
         # Only do this if the credentials are set.
         # This means that PRs will still build wheels, but not upload them.
         # (PRs do not have access to secrets).
         #
-        if: ${{ env.WHEELHOUSE_UPLOADER_USERNAME && env.WHEELHOUSE_UPLOADER_SECRET }}
-        run: python -m wheelhouse_uploader upload --local-folder wheelhouse/ --no-ssl-check gensim-wheels --provider S3 --no-enable-cdn
+        if: ${{ env.AWS_ACCESS_KEY_ID && env.AWS_SECRET_ACCESS_KEY }}
+        run: |
+          find artifacts/ -name '*.whl' -print -exec aws s3 cp --no-progress {} s3://gensim-wheels/ \;
+          python update_index.py gensim-wheels "" > index.html
+          aws s3 cp --no-progress index.html s3://gensim-wheels/index.html
         env:
-          WHEELHOUSE_UPLOADER_USERNAME: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          WHEELHOUSE_UPLOADER_SECRET: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          AWS_REGION: us-east-1
+          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
diff --git a/.github/workflows/linters.yml b/.github/workflows/linters.yml
@@ -9,12 +9,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Setup up Python ${{ matrix.python }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python }}
+          python-version: 3.11
 
       - name: Update pip
         run: python -m pip install -U pip

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -26,9 +26,9 @@ jobs:
     needs: [linters]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Setup up Python ${{ matrix.python }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           #
           # We use Py3.8 here for historical reasons.
@@ -67,11 +67,13 @@ jobs:
           - {python: '3.9', os: ubuntu-20.04}
           - {python: '3.10', os: ubuntu-20.04}
           - {python: '3.11', os: ubuntu-20.04}
+          - {python: '3.12', os: ubuntu-20.04}
 
           - {python: '3.8', os: windows-2019}
           - {python: '3.9', os: windows-2019}
           - {python: '3.10', os: windows-2019}
           - {python: '3.11', os: windows-2019}
+          - {python: '3.12', os: windows-2019}
 
     #
     # Don't run this job unless the linters have succeeded.
@@ -81,9 +83,9 @@ jobs:
     needs: [linters]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Setup up Python ${{ matrix.python }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
       - name: Update pip
@@ -159,7 +161,7 @@ jobs:
 
       - name: Upload coverage to Codecov
         if: matrix.coverage == true
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
         with:
           fail_ci_if_error: true
           files: ./coverage.xml

diff --git a/.github/workflows/update_index.py b/.github/workflows/update_index.py
@@ -0,0 +1,29 @@
+"""Update index.html for the bucket listing
+
+http://gensim-wheels.s3-website-us-east-1.amazonaws.com/
+
+We do this ourselves as opposed to using wheelhouse_uploader because it's
+much faster this way (seconds as compared to nearly an hour).
+"""
+
+import sys
+import boto3
+
+
+def main():
+    bucket = sys.argv[1]
+    prefix = sys.argv[2]
+
+    client = boto3.client('s3')
+
+    print("<html><body><ul>")
+    paginator = client.get_paginator('list_objects_v2')
+    for page in paginator.paginate(Bucket=bucket, Delimiter='/', Prefix=prefix):
+        for content in page.get('Contents', []):
+            key = content['Key']
+            print(f"<li><a href='{key}'>{key}</a></li>")
+    print("</ul></body></html>")
+
+
+if __name__ == '__main__':
+    main()
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,26 @@
 Changes
 =======
+
+## 4.3.3, 2024-07-19
+
+### :star2: New Features
+
+### :red_circle: Bug fixes
+
+* Correct file argument name in KeyedVectors.save docstring (__[hammad7](https://github.com/hammad7)__, [#3532](https://github.com/piskvorky/gensim/pull/3532))
+* Import deprecated scipy.linalg.triu from numpy.triu instead (__[Luffy610](https://github.com/Luffy610)__, [#3524](https://github.com/piskvorky/gensim/pull/3524))
+
+### :books: Tutorial and doc improvements
+
+* Updated the broken Documentation Link on the README.md (__[wittyicon29](https://github.com/wittyicon29)__, [#3505](https://github.com/piskvorky/gensim/pull/3505))
+
+### :+1: Improvements
+
+* Add support for python3.12 wheels (__[YoungMind1](https://github.com/YoungMind1)__, [#3531](https://github.com/piskvorky/gensim/pull/3531))
+* Removed scipy from build-only dependencies (__[filip-komarzyniec](https://github.com/filip-komarzyniec)__, [#3538](https://github.com/piskvorky/gensim/pull/3538))
+* Use newer unittest.mock everwhere (__[a-detiste](https://github.com/a-detiste)__, [#3529](https://github.com/piskvorky/gensim/pull/3529))
+* Handle optional parameters without implicit bool cast (__[nk-fouque](https://github.com/nk-fouque)__, [#3502](https://github.com/piskvorky/gensim/pull/3502))
+
 ## 4.3.2, 2023-08-23
 
 ### :red_circle: Bug fixes

diff --git a/README.md b/README.md
@@ -49,13 +49,12 @@ on Wikipedia.
 Installation
 ------------
 
-This software depends on [NumPy and Scipy], two Python packages for
-scientific computing. You must have them installed prior to installing
-gensim.
-
-It is also recommended you install a fast BLAS library before installing
-NumPy. This is optional, but using an optimized BLAS such as MKL, [ATLAS] or
-[OpenBLAS] is known to improve performance by as much as an order of
+This software depends on [NumPy], a Python package for
+scientific computing. Please bear in mind that building NumPy from source
+(e.g. by installing gensim on a platform which lacks NumPy .whl distribution)
+is a non-trivial task involving [linking NumPy to a BLAS library].  
+It is recommended to provide a fast one (such as MKL, [ATLAS] or
+[OpenBLAS]) which can improve performance by as much as an order of
 magnitude. On OSX, NumPy picks up its vecLib BLAS automatically,
 so you don’t need to do anything special.
 
@@ -69,7 +68,9 @@ Or, if you have instead downloaded and unzipped the [source tar.gz]
 package:
 
 ```bash
-    python setup.py install
+    tar -xvzf gensim-X.X.X.tar.gz
+    cd gensim-X.X.X/
+    pip install .
 ```
 
 For alternative modes of installation, see the [documentation].
@@ -103,7 +104,7 @@ Documentation
   [QuickStart]: https://radimrehurek.com/gensim/auto_examples/core/run_core_concepts.html
   [Tutorials]: https://radimrehurek.com/gensim/auto_examples/
   [Official Documentation and Walkthrough]: https://radimrehurek.com/gensim/
-  [Official API Documentation]: https://radimrehurek.com/gensim/apiref.html
+  [Official API Documentation]: https://radimrehurek.com/gensim/auto_examples/index.html#documentation
 
 Support
 -------
@@ -172,8 +173,10 @@ BibTeX entry:
   [documentation and Jupyter Notebook tutorials]: https://github.com/RaRe-Technologies/gensim/#documentation
   [Vector Space Model]: https://en.wikipedia.org/wiki/Vector_space_model
   [unsupervised document analysis]: https://en.wikipedia.org/wiki/Latent_semantic_indexing
-  [NumPy and Scipy]: https://scipy.org/install/
+  [NumPy]: https://numpy.org/install/
+  [linking NumPy to a BLAS library]: https://numpy.org/devdocs/building/blas_lapack.html
   [ATLAS]: https://math-atlas.sourceforge.net/
   [OpenBLAS]: https://xianyi.github.io/OpenBLAS/
   [source tar.gz]: https://pypi.org/project/gensim/
   [documentation]: https://radimrehurek.com/gensim/#install
+
diff --git a/docs/src/auto_examples/core/run_core_concepts.ipynb b/docs/src/auto_examples/core/run_core_concepts.ipynb
@@ -195,7 +195,7 @@
       },
       "outputs": [],
       "source": [
-        "from gensim import similarities\n\nindex = similarities.SparseMatrixSimilarity(tfidf[bow_corpus], num_features=12)"
+        "from gensim import similarities\n\nindex = similarities.SparseMatrixSimilarity(tfidf[bow_corpus], num_features=max(tfidf.dfs) + 1)"
       ]
     },
     {
@@ -274,4 +274,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}
diff --git a/docs/src/check_gallery.py b/docs/src/check_gallery.py
@@ -63,7 +63,12 @@ def different(path1, path2):
     stale = '\n'.join(stale)
     print(f"""The gallery cache appears stale.
 
-Rebuild the documentation using the following commands from the gensim root subdirectory:
+Use Github Actions to rebuild the documentation.  See the following links for more info:
+
+    https://github.com/RaRe-Technologies/gensim/actions/workflows/build-docs.yml
+    https://github.com/RaRe-Technologies/gensim/wiki/Rebuilding-documentation
+
+Alternatively, rebuild the documentation locally using the following commands from the gensim root subdirectory:
 
     pip install -e .[docs]
     make -C docs/src html