Add argument to override digital signatures

src/ocrmypdf/_pipeline.py

@@ -197,9 +197,12 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
             "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
             "Designer and can only be read by Adobe Acrobat or Adobe Reader."
         )
-    if pdfinfo.has_acroform:
-        if pdfinfo.has_signature:
+    if pdfinfo.has_signature:
+        if options.invalidate_digital_signatures:
+            log.warning("All digital signatures will be invalidated")
+        else:
             raise DigitalSignatureError()
+    if pdfinfo.has_acroform:
         if options.redo_ocr:
             raise InputFileError(
                 "This PDF has a user fillable form. --redo-ocr is not "

src/ocrmypdf/cli.py

@@ -359,6 +359,13 @@ Online documentation is located at:
         help="Skip OCR on pages larger than the specified amount of megapixels, "
         "but include skipped pages in final output",
     )
+    ocrsettings.add_argument(
+        '--invalidate-digital-signatures',
+        action='store_true',
+        help="Normally, OCRmyPDF will refuse to OCR a PDF that has a digital "
+        "signature. This option allows OCR to proceed, but the digital signature "
+        "will be invalidated.",
+    )
 
     advanced = parser.add_argument_group(
         "Advanced", "Advanced options to control OCRmyPDF"

src/ocrmypdf/pdfinfo/info.py

@@ -954,6 +954,10 @@ DEFAULT_EXECUTOR = SerialExecutor()
 class PdfInfo:
     """Get summary information about a PDF."""
 
+    _has_acroform: bool = False
+    _has_signature: bool = False
+    _needs_rendering: bool = False
+
     def __init__(
         self,
         infile,
@@ -982,7 +986,6 @@ class PdfInfo:
                 detailed_analysis=detailed_analysis,
             )
             self._needs_rendering = pdf.Root.get(Name.NeedsRendering, False)
-            self._has_acroform = False
             if Name.AcroForm in pdf.Root:
                 if len(pdf.Root.AcroForm.get(Name.Fields, [])) > 0:
                     self._has_acroform = True