Fix Windows ghostscript path scanning

src/ocrmypdf/subprocess/_windows.py

@@ -103,12 +103,12 @@ def registry_path_tesseract(env=None) -> Iterator[Path]:
         log.warning(e)
 
 
-def _program_version_in_path_key(path: Path) -> tuple[str, Version | None]:
+def _gs_version_in_path_key(path: Path) -> tuple[str, Version | None]:
     """Key function for comparing Ghostscript and Tesseract paths.
 
     Ghostscript installs on Windows:
-        %PROGRAMFILES%/gs/gs9.56.1 -> ('gs', Version('9.56.1'))
-        %PROGRAMFILES%/gs/gs9.24 -> ('gs', Version('9.24'))
+        %PROGRAMFILES%/gs/gs9.56.1/bin -> ('gs', Version('9.56.1'))
+        %PROGRAMFILES%/gs/9.24/bin -> ('gs', Version('9.24'))
 
     Tesseract looks like:
         %PROGRAMFILES%/Tesseract-OCR -> ('Tesseract-OCR', None)
@@ -116,13 +116,12 @@ def _program_version_in_path_key(path: Path) -> tuple[str, Version | None]:
     Thus ensuring the resulting tuple will order the alternatives correctly,
     e.g. gs10.0 > gs9.99.
     """
-    match = re.match(r'([^0-9]+)(.*)', str(path.name))
+    match = re.search(r'gs[/\\]?([0-9.]+)[/\\]bin', str(path))
     if match:
         try:
-            program = match.group(1)
-            version_str = match.group(2)
+            version_str = match.group(1)
             version = Version(version_str)
-            return program, version
+            return 'gs', version
         except InvalidVersion:
             pass
     return path.name, None
@@ -145,7 +144,7 @@ def program_files_paths(env=None) -> Iterator[Path]:
     return iter(
         sorted(
             (p for p in path_walker()),
-            key=_program_version_in_path_key,
+            key=_gs_version_in_path_key,
             reverse=True,
         )
     )

tests/test_helpers.py

@@ -6,9 +6,11 @@ from __future__ import annotations
 import logging
 import multiprocessing
 import os
+from pathlib import Path
 from unittest.mock import MagicMock
 
 import pytest
+from packaging.version import Version
 
 from ocrmypdf import helpers
 
@@ -100,6 +102,17 @@ class TestFileIsWritable:
         assert not helpers.is_file_writable(pathmock)
 
 
+@pytest.mark.skipif(os.name != 'nt', reason="Windows test")
+def test_gs_install_locations():
+    # pylint: disable=import-outside-toplevel
+    from ocrmypdf.subprocess._windows import _gs_version_in_path_key
+
+    assert _gs_version_in_path_key(Path("C:\\Program Files\\gs\\gs9.52\\bin")) == (
+        'gs',
+        Version('9.52'),
+    )
+
+
 @pytest.mark.skipif(os.name != 'nt', reason="Windows test")
 def test_shim_paths(tmp_path):
     # pylint: disable=import-outside-toplevel
@@ -109,7 +122,7 @@ def test_shim_paths(tmp_path):
     progfiles.mkdir()
     (progfiles / 'tesseract-ocr').mkdir()
     (progfiles / 'gs' / '9.51' / 'bin').mkdir(parents=True)
-    (progfiles / 'gs' / '9.52' / 'bin').mkdir(parents=True)
+    (progfiles / 'gs' / 'gs9.52.3' / 'bin').mkdir(parents=True)
     syspath = tmp_path / 'bin'
     env = {'PROGRAMFILES': str(progfiles), 'PATH': str(syspath)}
 
@@ -117,7 +130,7 @@ def test_shim_paths(tmp_path):
     results = result_str.split(os.pathsep)
     assert results[0] == str(syspath), results
     assert results[-3].endswith('tesseract-ocr'), results
-    assert results[-2].endswith(os.path.join('gs', '9.52', 'bin')), results
+    assert results[-2].endswith(os.path.join('gs9.52.3', 'bin')), results
     assert results[-1].endswith(os.path.join('gs', '9.51', 'bin')), results