Use test cache for test result images too.

anntzer · anntzer · commit 5ed01ab53588 · 2019-12-13T18:20:18.000+01:00
For image comparison tests in svg/pdf/ps formats, the result images are
converted to png for comparison.  Previously the conversion results were
cached for the baseline images, but not for the test-generated images
(because of non-deterministic svg/pdf/etc. results, due to
hash-salting, dict ordering, etc.).

Now that the test-generated images are generally deterministic, we can
enable the cache for baseline images as well.  This speeds up
`pytest -k '[svg]'` by ~30% (81s initially -&gt; 55s on a seeded cache) and
`pytest -k '[pdf]'` by ~10% (62s -&gt; 55s) (there are too few (e)ps image
comparison tests to see an effect).  Also add logging regarding the
cache which may help troubleshooting determinacy problems.

A simple cache eviction mechanism prevents the cache from growing
without bounds, limiting it to 2x the size of the baseline_images
directory.

This is a much simpler version of PR7764, which added more sophisticated
reporting of cache hits and misses and cache eviction.
diff --git a/lib/matplotlib/testing/compare.py b/lib/matplotlib/testing/compare.py
@@ -1,10 +1,11 @@
 """
 Provides a collection of utilities for comparing (image) results.
-
 """
 
 import atexit
+import functools
 import hashlib
+import logging
 import os
 from pathlib import Path
 import re
@@ -19,6 +20,8 @@
 import matplotlib as mpl
 from matplotlib.testing.exceptions import ImageComparisonFailure
 
+_log = logging.getLogger(__name__)
+
 __all__ = ['compare_images', 'comparable_formats']
 
 
@@ -281,21 +284,51 @@ def convert(filename, cache):
             cache_dir = None
 
         if cache_dir is not None:
+            _register_conversion_cache_cleaner_once()
             hash_value = get_file_hash(filename)
             new_ext = os.path.splitext(newname)[1]
             cached_file = os.path.join(cache_dir, hash_value + new_ext)
             if os.path.exists(cached_file):
+                _log.debug("For %s: reusing cached conversion.", filename)
                 shutil.copyfile(cached_file, newname)
                 return newname
 
+        _log.debug("For %s: converting to png.", filename)
         converter[extension](filename, newname)
 
         if cache_dir is not None:
+            _log.debug("For %s: caching conversion result.", filename)
             shutil.copyfile(newname, cached_file)
 
     return newname
 
 
+def _clean_conversion_cache():
+    # This will actually ignore mpl_toolkits baseline images, but they're
+    # relatively small.
+    baseline_images_size = sum(
+        path.stat().st_size
+        for path in Path(mpl.__file__).parent.glob("**/baseline_images/**/*"))
+    # 2x: one full copy of baselines, and one full copy of test results
+    # (actually an overestimate: we don't convert png baselines and results).
+    max_cache_size = 2 * baseline_images_size
+    # Reduce cache until it fits.
+    cache_stat = {
+        path: path.stat() for path in Path(get_cache_dir()).glob("*")}
+    cache_size = sum(stat.st_size for stat in cache_stat.values())
+    paths_by_atime = sorted(  # Oldest at the end.
+        cache_stat, key=lambda path: cache_stat[path].st_atime, reverse=True)
+    while cache_size > max_cache_size:
+        path = paths_by_atime.pop()
+        cache_size -= cache_stat[path].st_size
+        path.unlink()
+
+
+@functools.lru_cache()  # Ensure this is only registered once.
+def _register_conversion_cache_cleaner_once():
+    atexit.register(_clean_conversion_cache)
+
+
 def crop_to_same(actual_path, actual_image, expected_path, expected_image):
     # clip the images to the same size -- this is useful only when
     # comparing eps to pdf
@@ -382,7 +415,7 @@ def compare_images(expected, actual, tol, in_decorator=False):
         raise IOError('Baseline image %r does not exist.' % expected)
     extension = expected.split('.')[-1]
     if extension != 'png':
-        actual = convert(actual, cache=False)
+        actual = convert(actual, cache=True)
         expected = convert(expected, cache=True)
 
     # open the image files and remove the alpha channel (if it exists)
