Convert generate_pdfa to plugin

src/ocrmypdf/_pipeline.py

@@ -688,9 +688,10 @@ def convert_to_pdfa(input_pdf, input_ps_stub, context):
         else:
             safe_symlink(input_pdf, fix_docinfo_file)
 
-    ghostscript.generate_pdfa(
+    context.plugin_manager.hook.generate_pdfa(
         pdf_version=input_pdfinfo.min_version,
-        pdf_pages=[fix_docinfo_file, input_ps_stub],
+        pdf_pages=[fix_docinfo_file],
+        pdfmark=input_ps_stub,
         output_file=output_file,
         compression=options.pdfa_image_compression,
         pdfa_part=options.output_type[-1],  # is pdfa-1, pdfa-2, or pdfa-3

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -69,14 +69,14 @@ def check_options(options):
 
 @hookimpl
 def rasterize_pdf_page(
-    input_file: Path,
-    output_file: Path,
-    raster_device: str,
-    raster_dpi: Resolution,
-    pageno: int,
-    page_dpi: Resolution = None,
-    rotation: int = None,
-    filter_vector: bool = False,
+    input_file,
+    output_file,
+    raster_device,
+    raster_dpi,
+    pageno,
+    page_dpi=None,
+    rotation=None,
+    filter_vector=False,
 ):
     return ghostscript.rasterize_pdf(
         input_file,
@@ -88,3 +88,14 @@ def rasterize_pdf_page(
         rotation=rotation,
         filter_vector=filter_vector,
     )
+
+
+@hookimpl
+def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdfa_part):
+    return ghostscript.generate_pdfa(
+        pdf_pages=[*pdf_pages, pdfmark],
+        output_file=output_file,
+        compression=compression,
+        pdf_version=pdf_version,
+        pdfa_part=pdfa_part,
+    )

src/ocrmypdf/exec/ghostscript.py

@@ -154,24 +154,6 @@ def generate_pdfa(
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
 ):
-    """Generate a PDF/A.
-
-    The pdf_pages, a list files, will be merged into output_file. One or more
-    PDF files may be merged. One of the files in this list must be a pdfmark
-    file that provides Ghostscript with details on how to perform the PDF/A
-    conversion. By default with we pick PDF/A-2b, but this works for 1 or 3.
-
-    compression can be 'jpeg', 'lossless', or an empty string. In 'jpeg',
-    Ghostscript is instructed to convert color and grayscale images to DCT
-    (JPEG encoding). In 'lossless' Ghostscript is told to convert images to
-    Flate (lossless/PNG). If the parameter is omitted Ghostscript is left to
-    make its own decisions about how to encode images; it appears to use a
-    heuristic to decide how to encode images. As of Ghostscript 9.25, we
-    support passthrough JPEG which allows Ghostscript to avoid transcoding
-    images entirely. (The feature was added in 9.23 but broken, and the 9.24
-    release of Ghostscript had regressions, so we don't support it until 9.25.)
-    """
-
     compression_args = []
     if compression == 'jpeg':
         compression_args = [

src/ocrmypdf/pluginspec.py

@@ -19,7 +19,7 @@ from abc import ABC, abstractstaticmethod
 from argparse import ArgumentParser, Namespace
 from collections import namedtuple
 from pathlib import Path
-from typing import AbstractSet, Optional
+from typing import AbstractSet, List, Optional
 
 import pluggy
 from PIL import Image
@@ -75,8 +75,8 @@ def rasterize_pdf_page(
     raster_device: str,
     raster_dpi: Resolution,
     pageno: int,
-    page_dpi: Resolution = None,
-    rotation: int = None,
+    page_dpi: Optional[Resolution] = None,
+    rotation: Optional[int] = None,
     filter_vector: bool = False,
 ) -> None:
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
@@ -162,3 +162,31 @@ class OcrEngine(ABC):
 @hookspec(firstresult=True)
 def get_ocr_engine() -> OcrEngine:
     pass
+
+
+@hookspec(firstresult=True)
+def generate_pdfa(
+    pdf_pages: List[Path],
+    pdfmark: Path,
+    output_file: Path,
+    compression: str,
+    pdf_version: str,
+    pdfa_part: str,
+):
+    """Generate a PDF/A.
+
+    The pdf_pages, a list of files, will be merged into output_file. One or more
+    PDF files may be merged. The pdfmark file is a PostScript.ps file that
+    provides Ghostscript with details on how to perform the PDF/A
+    conversion. By default with we pick PDF/A-2b, but this works for 1 or 3.
+
+    compression can be 'jpeg', 'lossless', or an empty string. In 'jpeg',
+    Ghostscript is instructed to convert color and grayscale images to DCT
+    (JPEG encoding). In 'lossless' Ghostscript is told to convert images to
+    Flate (lossless/PNG). If the parameter is omitted Ghostscript is left to
+    make its own decisions about how to encode images; it appears to use a
+    heuristic to decide how to encode images. As of Ghostscript 9.25, we
+    support passthrough JPEG which allows Ghostscript to avoid transcoding
+    images entirely. (The feature was added in 9.23 but broken, and the 9.24
+    release of Ghostscript had regressions, so we don't support it until 9.25.)
+    """