ci: test on windows and mac

.github/workflows/benchmarks.yml

@@ -7,7 +7,11 @@ on:
 
 jobs:
   benchmark:
-    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+    runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python

.github/workflows/tests.yml

@@ -6,26 +6,48 @@ on:
     branches: [ "main" ]
 
 jobs:
-  test:
+  check:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-        with:
-          submodules: true
       - name: Set up Python
         uses: actions/setup-python@v5
-        with:
-          python-version: "3.9"
       - name: Install Hatch
         uses: pypa/hatch@install
       - name: Check types with mypy
         run: hatch run mypy --install-types --non-interactive playa
+  test:
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+      - name: Install Hatch
+        uses: pypa/hatch@install
       - name: Run tests
         run: hatch test --cover -py 3.9
-      - name: Install ghostscript
-        run: sudo apt update && sudo apt install ghostscript
+  thirdparty-test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: true
+      - name: Set up Python
+        uses: actions/setup-python@v5
+      - name: Install Hatch
+        uses: pypa/hatch@install
+      - name: Run pdf.js testsuite
+        run: |
+          hatch run pytest -k pdf.js
       - name: Run pdfplumber tests
         run: |
+          sudo apt update && sudo apt install ghostscript
           cd samples/3rdparty/pdfplumber
           python -m venv venv
           SETUPTOOLS_SCM_PRETEND_VERSION=0.2.5 venv/bin/pip install -e ../../..

benchmarks/parser.py

@@ -288,19 +288,19 @@ def bench_mmap():
 
     from playa.parser import Lexer
 
-    with tempfile.NamedTemporaryFile() as tf:
+    with tempfile.TemporaryFile(mode="w+b") as tf:
         runs = 100
-        with open(tf.name, "wb") as outfh:
-            outfh.write(DATA * runs)
-        with open(tf.name, "rb") as infh:
-            start = time.time()
-            mapping = mmap.mmap(infh.fileno(), 0, access=mmap.ACCESS_READ)
-            parser = Lexer(mapping)
-            _ = list(parser)
-            print(
-                "PLAYA Lexer (mmap): %fms / run"
-                % ((time.time() - start) / runs * 1000),
-            )
+        tf.write(DATA * runs)
+        tf.flush()
+        tf.seek(0, 0)
+        start = time.time()
+        mapping = mmap.mmap(tf.fileno(), 0, access=mmap.ACCESS_READ)
+        parser = Lexer(mapping)
+        _ = list(parser)
+        print(
+            "PLAYA Lexer (mmap): %fms / run"
+            % ((time.time() - start) / runs * 1000),
+        )
 
 
 def bench_playa():
@@ -341,21 +341,21 @@ def bench_pdfminer():
         "pdfminer.six Lexer (BytesIO): %fms / run"
         % ((time.time() - start) / runs * 1000),
     )
-    with tempfile.NamedTemporaryFile() as tf:
+    with tempfile.TemporaryFile(mode="w+b") as tf:
         runs = 100
-        with open(tf.name, "wb") as outfh:
-            outfh.write(DATA * runs)
-        with open(tf.name, "rb") as infh:
-            parser = PSBaseParser(infh)
-            while True:
-                try:
-                    _ = parser.nexttoken()
-                except PSEOF:
-                    break
-            print(
-                "pdfminer.six Lexer (BinaryIO): %fms / run"
-                % ((time.time() - start) / runs * 1000),
-            )
+        tf.write(DATA * runs)
+        tf.flush()
+        tf.seek(0, 0)
+        parser = PSBaseParser(tf)
+        while True:
+            try:
+                _ = parser.nexttoken()
+            except PSEOF:
+                break
+        print(
+            "pdfminer.six Lexer (BinaryIO): %fms / run"
+            % ((time.time() - start) / runs * 1000),
+        )
     runs = 20
     start = time.time()
     for _ in range(runs):

tests/data.py

@@ -20,7 +20,7 @@
     ALLPDFS.extend(PLUMBERS.glob("*.pdf"))
 PDFJS = TESTDIR / "3rdparty" / "pdf.js" / "test"
 try:
-    with open(PDFJS / "test_manifest.json") as infh:
+    with open(PDFJS / "test_manifest.json", encoding="utf-8") as infh:
         manifest = json.load(infh)
     for entry in manifest:
         path = PDFJS / entry["file"]