Detect and warn about Tagged PDFs

src/ocrmypdf/_pipeline.py

@@ -33,6 +33,7 @@ from ocrmypdf.exceptions import (
     EncryptedPdfError,
     InputFileError,
     PriorOcrFoundError,
+    TaggedPDFError,
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
@@ -218,6 +219,16 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
                     "form and all filled form fields. The output PDF will be "
                     "'flattened' and will no longer be fillable."
                 )
+    if pdfinfo.is_tagged:
+        if options.force_ocr or options.skip_text or options.redo_ocr:
+            log.warning(
+                "This PDF is marked as a Tagged PDF. This often indicates "
+                "that the PDF was generated from an office document and does "
+                "not need OCR. PDF pages processed by OCRmyPDF may not be "
+                "tagged correctly."
+            )
+        else:
+            raise TaggedPDFError()
     context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
 
 

src/ocrmypdf/exceptions.py

@@ -108,10 +108,16 @@ class EncryptedPdfError(ExitCodeException):
     )
 
 
-class DigitalSignatureError(ExitCodeException):
+class TesseractConfigError(ExitCodeException):
+    """Tesseract config can't be parsed."""
+
+    exit_code = ExitCode.invalid_config
+    message = "Error occurred while parsing a Tesseract configuration file"
+
+
+class DigitalSignatureError(InputFileError):
     """PDF has a digital signature."""
 
-    exit_code = ExitCode.input_file
     message = dedent(
         """\
         Input PDF has a digital signature. OCR would alter the document,
@@ -120,8 +126,14 @@ class DigitalSignatureError(ExitCodeException):
     )
 
 
-class TesseractConfigError(ExitCodeException):
-    """Tesseract config can't be parsed."""
+class TaggedPDFError(InputFileError):
+    """PDF is tagged."""
 
-    exit_code = ExitCode.invalid_config
-    message = "Error occurred while parsing a Tesseract configuration file"
+    message = dedent(
+        """\
+        This PDF is marked as a Tagged PDF. This often indicates
+        that the PDF was generated from an office document and does
+        not need OCR. Use --force-ocr, --skip-text or --redo-ocr to
+        override this error.
+        """
+    )

src/ocrmypdf/pdfinfo/info.py

@@ -1038,7 +1038,11 @@ DEFAULT_EXECUTOR = SerialExecutor()
 
 
 class PdfInfo:
-    """Get summary information about a PDF."""
+    """Extract summary information about a PDF without retaining the PDF itself.
+
+    Crucially this lets us get the information in a pure Python format so that
+    it can be pickled and passed to a worker process.
+    """
 
     _has_acroform: bool = False
     _has_signature: bool = False
@@ -1078,6 +1082,9 @@ class PdfInfo:
                 elif Name.XFA in pdf.Root.AcroForm:
                     self._has_acroform = True
                 self._has_signature = bool(pdf.Root.AcroForm.get(Name.SigFlags, 0) & 1)
+            self._is_tagged = bool(
+                pdf.Root.get(Name.MarkInfo, {}).get(Name.Marked, False)
+            )
 
     @property
     def pages(self) -> Sequence[PageInfo | None]:
@@ -1105,6 +1112,11 @@ class PdfInfo:
         """Return True if the document annotations has a digital signature."""
         return self._has_signature
 
+    @property
+    def is_tagged(self) -> bool:
+        """Return True if the document catalog indicates this is a Tagged PDF."""
+        return self._is_tagged
+
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""

tests/test_tagged.py

@@ -0,0 +1,26 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import argparse
+
+import pytest
+
+import ocrmypdf
+
+
+def test_block_tagged(resources):
+    with pytest.raises(ocrmypdf.exceptions.TaggedPDFError):
+        ocrmypdf.ocr(resources / 'tagged.pdf', '_.pdf')
+
+
+def test_force_tagged_warns(resources, outpdf, caplog):
+    caplog.set_level('WARNING')
+    ocrmypdf.ocr(
+        resources / 'tagged.pdf',
+        outpdf,
+        force_ocr=True,
+        plugins=['tests/plugins/tesseract_noop.py'],
+    )
+    assert 'marked as a Tagged PDF' in caplog.text