Merge branch 'feature/soft-error'

src/ocrmypdf/_exec/ghostscript.py

@@ -30,7 +30,7 @@ except AttributeError:
 
 log = logging.getLogger(__name__)
 
-# Most reliable what to get the bitness of Python interpreter, according to Python docs
+# Most reliable way to get the bitness of Python interpreter, according to Python docs
 _IS_64BIT = sys.maxsize > 2**32
 
 _GSWIN = None
@@ -63,6 +63,7 @@ def rasterize_pdf(
     page_dpi: Resolution | None = None,
     rotation: int | None = None,
     filter_vector: bool = False,
+    stop_on_error: bool = False,
 ):
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
     raster_dpi = raster_dpi.round(6)
@@ -83,6 +84,7 @@ def rasterize_pdf(
             f'-r{raster_dpi.x:f}x{raster_dpi.y:f}',
         ]
         + (['-dFILTERVECTOR'] if filter_vector else [])
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + [
             '-o',
             '-',
@@ -161,6 +163,7 @@ def generate_pdfa(
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
     progressbar_class=None,
+    stop_on_error: bool = False,
 ):
     # Ghostscript's compression is all or nothing. We can either force all images
     # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
@@ -193,6 +196,10 @@ def generate_pdfa(
         # https://bugs.ghostscript.com/show_bug.cgi?id=705187
         compression_args.append('-dNEWPDF=false')
 
+    if os.name == 'nt':
+        # Windows has lots of fatal "permission denied" errors
+        stop_on_error = False
+
     # nb no need to specify ProcessColorModel when ColorConversionStrategy
     # is set; see:
     # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -207,6 +214,7 @@ def generate_pdfa(
             "-dAutoRotatePages=/None",
             "-sColorConversionStrategy=" + strategy,
         ]
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + compression_args
         + [
             "-dJPEGQ=95",

src/ocrmypdf/_pipeline.py

@@ -343,6 +343,7 @@ def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
         page_dpi=page_dpi,
         rotation=0,
         filter_vector=False,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
     )
     return output_file
 
@@ -455,6 +456,7 @@ def rasterize(
         pageno=pageinfo.pageno + 1,
         rotation=correction,
         filter_vector=remove_vectors,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
     )
     return output_file
 
@@ -736,6 +738,7 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
             if options.progress_bar
             else None
         ),
+        stop_on_soft_error=not options.continue_on_soft_render_error,
     )
 
     return output_file

src/ocrmypdf/api.py

@@ -248,6 +248,7 @@ def ocr(  # noqa: ruff: disable=D417
     user_words: os.PathLike | None = None,
     user_patterns: os.PathLike | None = None,
     fast_web_view: float | None = None,
+    continue_on_soft_render_error: bool | None = None,
     plugins: Iterable[StrPath] | None = None,
     plugin_manager=None,
     keep_temporary_files: bool | None = None,

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -45,6 +45,7 @@ def rasterize_pdf_page(
     page_dpi,
     rotation,
     filter_vector,
+    stop_on_soft_error,
 ):
     """Rasterize a single page of a PDF file using Ghostscript."""
     ghostscript.rasterize_pdf(
@@ -56,6 +57,7 @@ def rasterize_pdf_page(
         page_dpi=page_dpi,
         rotation=rotation,
         filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file
 
@@ -69,6 +71,7 @@ def generate_pdfa(
     pdf_version,
     pdfa_part,
     progressbar_class,
+    stop_on_soft_error,
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
@@ -78,5 +81,6 @@ def generate_pdfa(
         pdf_version=pdf_version,
         pdfa_part=pdfa_part,
         progressbar_class=progressbar_class,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file

src/ocrmypdf/cli.py

@@ -420,6 +420,14 @@ Online documentation is located at:
         "which do not benefit. If the threshold is 0 it will be apply to all files. "
         "Set the threshold very high to disable.",
     )
+    advanced.add_argument(
+        '--continue-on-soft-render-error',
+        action='store_true',
+        help="Continue processing pages after a recoverable PDF rendering error. "
+        "A recoverable error is one that does not prevent the page from being "
+        "rendered, but may result in visual differences compared to the input "
+        "file. Missing fonts are a typical source of these errors.",
+    )
     advanced.add_argument(
         '--plugin',
         dest='plugins',

src/ocrmypdf/pluginspec.py

@@ -203,6 +203,7 @@ def rasterize_pdf_page(
     page_dpi: Resolution | None,
     rotation: int | None,
     filter_vector: bool,
+    stop_on_soft_error: bool,
 ) -> Path:
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
 
@@ -213,19 +214,26 @@ def rasterize_pdf_page(
     Args:
         input_file: The PDF to rasterize.
         output_file: The desired name of the rasterized image.
-        raster_device: Type of image to produce at output_file
-        raster_dpi: Resolution at which to rasterize page
-        pageno: Page number to rasterize (beginning at page 1)
-        page_dpi: Resolution, overriding output image DPI
-        rotation: Cardinal angle, clockwise, to rotate page
-        filter_vector: If True, remove vector graphics objects
+        raster_device: Type of image to produce at output_file.
+        raster_dpi: Resolution in dots per inch at which to rasterize page.
+        pageno: Page number to rasterize (beginning at page 1).
+        page_dpi: Resolution, overriding output image DPI.
+        rotation: Cardinal angle, clockwise, to rotate page.
+        filter_vector: If True, remove vector graphics objects.
+        stop_on_soft_error: If there is an "soft error" such that PDF page image
+            generation can proceed, but may visually differ from the original,
+            the implementer of this hook should raise a detailed exception. If
+            ``False``, continue processing and report by logging it. If the hook
+            cannot proceed, it should always raise an exception, regardless of
+            this setting. One "soft error" would be a missing font that is
+            required to properly rasterize the PDF.
+
     Returns:
         Path: output_file if successful
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
 
-
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -462,6 +470,7 @@ def generate_pdfa(
     pdf_version: str,
     pdfa_part: str,
     progressbar_class,
+    stop_on_soft_error: bool,
 ) -> Path:
     """Generate a PDF/A.
 
@@ -492,6 +501,12 @@ def generate_pdfa(
             and the name of the work units ("page"). Then ``instance.update()``
             will be called when a work unit is completed. If ``None``, no
             progress information is reported.
+        stop_on_soft_error: If there is an "soft error" such that PDF/A generation
+            can proceed and produce a valid PDF/A, but output may be invalid or
+            may not visually resemble the original, the implementer of this hook
+            should raise a detailed exception. If ``False``, continue processing
+            and report by logging it. If the hook cannot proceed, it should always
+            raise an exception, regardless of this setting.
 
     Returns:
         Path: If successful, the hook should return ``output_file``.

src/ocrmypdf/subprocess/__init__.py

@@ -118,8 +118,6 @@ def run_polling_stderr(
 def _fix_process_args(
     args: Args, env: OsEnviron | None, kwargs
 ) -> tuple[Args, OsEnviron, logging.Logger, bool]:
-    assert 'universal_newlines' not in kwargs, "Use text= instead of universal_newlines"
-
     if not env:
         env = os.environ