Add a test workflow; read CRLF files (0.5.2)

.github/workflows/tests.yml

@@ -0,0 +1,51 @@
+name: tests
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    name: ${{ matrix.os }} / Python ${{ matrix.python }} / ${{ matrix.numpy }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
+        numpy: ["numpy"]
+        include:
+          - os: ubuntu-latest
+            python: "3.12"
+            numpy: "numpy<2"
+          - os: macos-latest
+            python: "3.13"
+            numpy: "numpy"
+          - os: windows-latest
+            python: "3.13"
+            numpy: "numpy"
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python }}
+      # Install from the sdist, in an isolated build: this checks MANIFEST.in
+      # and the build requirements of pyproject.toml as well.
+      - name: Build the sdist
+        run: |
+          python -m pip install --upgrade pip build
+          python -m build --sdist --outdir dist
+      - name: Install the sdist
+        shell: bash
+        run: python -m pip install "${{ matrix.numpy }}" scipy pytest dist/*.tar.gz
+      # Run outside the checkout, so that the installed (compiled) module is
+      # the one imported.
+      - name: Test
+        working-directory: ${{ runner.temp }}
+        shell: bash
+        run: python -m pytest -q --import-mode=importlib "$GITHUB_WORKSPACE/tests"

setup.py

@@ -47,7 +47,7 @@
 
 setup(
     name = 'svmloader',
-    version = '0.5.1',
+    version = '0.5.2',
     description = DESCRIPTION,
     long_description = LONG_DESCRIPTION,
     long_description_content_type = 'text/markdown',

svmloader.pyx

@@ -69,7 +69,7 @@ cdef _load_svmfile(fp, dtype, ltype, bint zero_based, bint multilabels):
 
         # process the line
         last_idx = -1
-        while s[0] != '#' and s[0] != '\n' and s[0] != 0:
+        while s[0] != '#' and s[0] != '\n' and s[0] != '\r' and s[0] != 0:  # '\r': CRLF line ending
             # get index
             idx = strtol(s, &end, 10)
             if s == end:
@@ -225,7 +225,8 @@ cdef _save_svmfile(filename, mat, labels, bint zero_based,
     cdef Py_ssize_t i
     cdef Py_ssize_t j
     cdef Py_ssize_t offset = 0 if zero_based else 1
-    with open(filename, 'w') as fp:
+    # '\n' line endings on every platform, as libsvm files have
+    with open(filename, 'w', newline='\n') as fp:
         for i in range(indptr.shape[0] - 1):
             if labels is not None:
                 fp.write('%s ' % labels[i])

tests/test_svmloader.py

@@ -154,3 +154,22 @@ def test_load_compressed_file(tmp_path, suffix):
 
     np.testing.assert_array_equal(y_comp, y_plain)
     np.testing.assert_allclose(X_comp.toarray(), X_plain.toarray())
+
+
+def test_load_crlf_file(tmp_path):
+    path = tmp_path / "crlf.svm"
+    path.write_bytes(DATA.replace("\n", "\r\n").encode())
+
+    X, y = svmloader.load_svmfile(str(path), zero_based=False)
+
+    assert y.tolist() == [1, 0]
+    np.testing.assert_allclose(X.toarray(), [[0.5, 0.0, 2.0], [0.0, 1.0, 0.0]])
+
+
+def test_save_svmfile_writes_lf_line_endings(tmp_path):
+    X = sp.csr_matrix(np.array([[0.0, 1.5], [2.0, 0.0]]))
+    path = tmp_path / "out.svm"
+
+    svmloader.save_svmfile(str(path), X, np.array([1, 0]))
+
+    assert path.read_bytes() == b"1 2:1.5\n0 1:2\n"