fix: report accurate UTF-8 hook line numbers

CHANGELOG.md

@@ -18,6 +18,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+ - UTF-8 pre-commit hook reports accurate line numbers for invalid byte sequences.
+   (https://github.com/gchq/coreax/issues/1251)
  - `KernelThinning.kt_half_recursive` now returns the correct partitions. (https://github.com/gchq/coreax/pull/1088)
 
 ### Changed

pre_commit_hooks/require_utf8.py

@@ -41,7 +41,6 @@
     THE SOFTWARE.
 """
 
-import itertools
 import sys
 
 
@@ -50,18 +49,14 @@ def main() -> None:
     failed = False
 
     for file_path in sys.argv[1:]:
-        with open(file_path, encoding="UTF-8") as rf:
-            for line_number in itertools.count(start=1):
+        with open(file_path, "rb") as rf:
+            for line_number, line in enumerate(rf, start=1):
                 try:
-                    line = rf.readline()
+                    line.decode("UTF-8")
                 except UnicodeDecodeError as error:
-                    line = ""  # avoid being unbound
                     print(f"{file_path}: line {line_number} {error!s}")
                     failed = True
 
-                if not line:
-                    break
-
     sys.exit(failed)
 
 

tests/unit/test_require_utf8.py

@@ -0,0 +1,55 @@
+# © Crown Copyright GCHQ
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Tests for the UTF-8 pre-commit hook."""
+
+import sys
+from contextlib import redirect_stdout
+from io import StringIO
+from pathlib import Path
+
+import pytest
+
+from pre_commit_hooks.require_utf8 import main
+
+
+def test_reports_actual_invalid_line_numbers(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    """Invalid byte sequences should be reported against their source lines."""
+    file_path = tmp_path / "invalid.txt"
+    file_path.write_bytes(b"first\nsecond\nthird \xff\nfourth\nfifth \xfe\n")
+    monkeypatch.setattr(sys, "argv", ["require_utf8.py", str(file_path)])
+
+    output_stream = StringIO()
+    with redirect_stdout(output_stream), pytest.raises(SystemExit) as exc_info:
+        main()
+
+    assert exc_info.value.code == 1
+    output = output_stream.getvalue()
+    assert f"{file_path}: line 3" in output
+    assert f"{file_path}: line 5" in output
+    assert f"{file_path}: line 1" not in output
+
+
+def test_valid_utf8_passes(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    """Valid UTF-8 should continue to pass the hook."""
+    file_path = tmp_path / "valid.txt"
+    file_path.write_text("first\nsecond café\n", encoding="UTF-8")
+    monkeypatch.setattr(sys, "argv", ["require_utf8.py", str(file_path)])
+
+    with pytest.raises(SystemExit) as exc_info:
+        main()
+
+    assert exc_info.value.code == 0