Refactor ghostscript error message deduplicating

src/ocrmypdf/_exec/ghostscript.py

@@ -42,6 +42,30 @@ COLOR_CONVERSION_STRATEGIES = frozenset(
 log = logging.getLogger(__name__)
 
 
+class DuplicateFilter(logging.Filter):
+    """Filter out duplicate log messages."""
+
+    def __init__(self, logger: logging.Logger):
+        self.last: logging.LogRecord | None = None
+        self.count = 0
+        self.logger = logger
+
+    def filter(self, record):
+        if self.last and record.msg == self.last.msg:
+            self.count += 1
+            return False
+        else:
+            if self.count >= 1:
+                rep_msg = f"(previous message repeated {self.count} times)"
+                self.count = 0  # Avoid infinite recursion
+                self.logger.log(self.last.levelno, rep_msg)
+            self.last = record
+            return True
+
+
+log.addFilter(DuplicateFilter(log))
+
+
 # Ghostscript executable - gswin32c is not supported
 GS = 'gswin64c' if os.name == 'nt' else 'gs'
 
@@ -252,14 +276,9 @@ def generate_pdfa(
         # If there is an error we log the whole stderr, except for filtering
         # duplicates.
         if _gs_error_reported(stderr):
-            last_part = None
-            repcount = 0
+            # Ghostscript outputs the pattern **** Error: ....  frequently.
+            # Occasionally the error message is spammed many times. We filter
+            # out duplicates of this message using the filter above. We use
+            # the **** pattern to split the stderr into parts.
             for part in stderr.split('****'):
-                if part != last_part:
-                    if repcount > 1:
-                        log.error(f"(previous error message repeated {repcount} times)")
-                        repcount = 0
-                    log.error(part)
-                else:
-                    repcount += 1
-                last_part = part
+                log.error(part)

tests/test_ghostscript.py

@@ -12,7 +12,7 @@ import pikepdf
 import pytest
 from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf._exec.ghostscript import rasterize_pdf
+from ocrmypdf._exec.ghostscript import DuplicateFilter, rasterize_pdf
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.helpers import Resolution
 
@@ -141,3 +141,41 @@ def test_rasterize_pdf_errors(resources, no_outpdf, caplog):
             )
         assert "this is an error" in caplog.text
         assert "invalid page image file" in caplog.text
+
+
+class TestDuplicateFilter:
+    @pytest.fixture(scope='class', autouse=True)
+    def duplicate_filter_logger(self):
+        logger = logging.getLogger(__name__)
+        logger.setLevel(logging.DEBUG)
+        logger.addFilter(DuplicateFilter(logger))
+        return logger
+
+    def test_filter_duplicate_messages(self, duplicate_filter_logger, caplog):
+        log = duplicate_filter_logger
+        log.error("test error message")
+        log.error("test error message")
+        log.error("test error message")
+        log.error("another error message")
+        log.error("another error message")
+        log.error("yet another error message")
+
+        assert len(caplog.records) == 5
+        assert caplog.records[0].msg == "test error message"
+        assert caplog.records[1].msg == "(previous message repeated 2 times)"
+        assert caplog.records[2].msg == "another error message"
+        assert caplog.records[3].msg == "(previous message repeated 1 times)"
+        assert caplog.records[4].msg == "yet another error message"
+
+    def test_filter_does_not_affect_unique_messages(
+        self, duplicate_filter_logger, caplog
+    ):
+        log = duplicate_filter_logger
+        log.error("test error message")
+        log.error("another error message")
+        log.error("yet another error message")
+
+        assert len(caplog.records) == 3
+        assert caplog.records[0].msg == "test error message"
+        assert caplog.records[1].msg == "another error message"
+        assert caplog.records[2].msg == "yet another error message"