gh-115809: Improve TimedRotatingFileHandler.getFilesToDelete() (GH-115812)

Improve algorithm for computing which rolled-over log files to delete
in logging.TimedRotatingFileHandler. It is now reliable for handlers
without namer and with arbitrary deterministic namer that leaves
the datetime part in the file name unmodified.

1 files changed, 24 insertions, 27 deletions

diff --git a/Lib/logging/handlers.py b/Lib/logging/handlers.py
index 6f0816b..cdb014b 100644
--- a/Lib/logging/handlers.py
+++ b/Lib/logging/handlers.py
@@ -232,19 +232,19 @@ class TimedRotatingFileHandler(BaseRotatingHandler):
         if self.when == 'S':
             self.interval = 1 # one second
             self.suffix = "%Y-%m-%d_%H-%M-%S"
-            self.extMatch = r"^\d{4}-\d{2}-\d{2}_\d{2}-\d{2}-\d{2}(\.\w+)?$"
+            extMatch = r"(?<!\d)\d{4}-\d{2}-\d{2}_\d{2}-\d{2}-\d{2}(?!\d)"
         elif self.when == 'M':
             self.interval = 60 # one minute
             self.suffix = "%Y-%m-%d_%H-%M"
-            self.extMatch = r"^\d{4}-\d{2}-\d{2}_\d{2}-\d{2}(\.\w+)?$"
+            extMatch = r"(?<!\d)\d{4}-\d{2}-\d{2}_\d{2}-\d{2}(?!\d)"
         elif self.when == 'H':
             self.interval = 60 * 60 # one hour
             self.suffix = "%Y-%m-%d_%H"
-            self.extMatch = r"^\d{4}-\d{2}-\d{2}_\d{2}(\.\w+)?$"
+            extMatch = r"(?<!\d)\d{4}-\d{2}-\d{2}_\d{2}(?!\d)"
         elif self.when == 'D' or self.when == 'MIDNIGHT':
             self.interval = 60 * 60 * 24 # one day
             self.suffix = "%Y-%m-%d"
-            self.extMatch = r"^\d{4}-\d{2}-\d{2}(\.\w+)?$"
+            extMatch = r"(?<!\d)\d{4}-\d{2}-\d{2}(?!\d)"
         elif self.when.startswith('W'):
             self.interval = 60 * 60 * 24 * 7 # one week
             if len(self.when) != 2:
@@ -253,11 +253,17 @@ class TimedRotatingFileHandler(BaseRotatingHandler):
                 raise ValueError("Invalid day specified for weekly rollover: %s" % self.when)
             self.dayOfWeek = int(self.when[1])
             self.suffix = "%Y-%m-%d"
-            self.extMatch = r"^\d{4}-\d{2}-\d{2}(\.\w+)?$"
+            extMatch = r"(?<!\d)\d{4}-\d{2}-\d{2}(?!\d)"
         else:
             raise ValueError("Invalid rollover interval specified: %s" % self.when)
 
-        self.extMatch = re.compile(self.extMatch, re.ASCII)
+        # extMatch is a pattern for matching a datetime suffix in a file name.
+        # After custom naming, it is no longer guaranteed to be separated by
+        # periods from other parts of the filename.  The lookup statements
+        # (?<!\d) and (?!\d) ensure that the datetime suffix (which itself
+        # starts and ends with digits) is not preceded or followed by digits.
+        # This reduces the number of false matches and improves performance.
+        self.extMatch = re.compile(extMatch, re.ASCII)
         self.interval = self.interval * interval # multiply by units requested
         # The following line added because the filename passed in could be a
         # path object (see Issue #27493), but self.baseFilename will be a string
@@ -376,31 +382,22 @@ class TimedRotatingFileHandler(BaseRotatingHandler):
             for fileName in fileNames:
                 if fileName[:plen] == prefix:
                     suffix = fileName[plen:]
-                    if self.extMatch.match(suffix):
+                    if self.extMatch.fullmatch(suffix):
                         result.append(os.path.join(dirName, fileName))
         else:
-            # See bpo-44753: Don't use the extension when computing the prefix.
-            n, e = os.path.splitext(baseName)
-            prefix = n + '.'
-            plen = len(prefix)
             for fileName in fileNames:
-                # Our files could be just about anything after custom naming, but
-                # likely candidates are of the form
-                # foo.log.DATETIME_SUFFIX or foo.DATETIME_SUFFIX.log
-                if (not fileName.startswith(baseName) and fileName.endswith(e) and
-                    len(fileName) > (plen + 1) and not fileName[plen+1].isdigit()):
-                    continue
+                # Our files could be just about anything after custom naming,
+                # but they should contain the datetime suffix.
+                # Try to find the datetime suffix in the file name and verify
+                # that the file name can be generated by this handler.
+                m = self.extMatch.search(fileName)
+                while m:
+                    dfn = self.namer(self.baseFilename + "." + m[0])
+                    if os.path.basename(dfn) == fileName:
+                        result.append(os.path.join(dirName, fileName))
+                        break
+                    m = self.extMatch.search(fileName, m.start() + 1)
 
-                if fileName[:plen] == prefix:
-                    suffix = fileName[plen:]
-                    # See bpo-45628: The date/time suffix could be anywhere in the
-                    # filename
-
-                    parts = suffix.split('.')
-                    for part in parts:
-                        if self.extMatch.match(part):
-                            result.append(os.path.join(dirName, fileName))
-                            break
         if len(result) < self.backupCount:
             result = []
         else: