Use better img2pdf settings where possible while supporting old versions

Fixes #894

src/ocrmypdf/_pipeline.py

@@ -18,7 +18,7 @@ from typing import Dict, Iterable, Optional
 import img2pdf
 import pikepdf
 from pikepdf.models.metadata import encode_pdf_date
-from PIL import Image, ImageColor, ImageDraw
+from PIL import Image, ImageDraw
 
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._exec import unpaper
@@ -32,7 +32,7 @@ from ocrmypdf.exceptions import (
     PriorOcrFoundError,
     UnsupportedImageFormatError,
 )
-from ocrmypdf.helpers import Resolution, safe_symlink
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
 from ocrmypdf.optimize import optimize
 from ocrmypdf.pdfa import generate_pdfa_ps
@@ -98,8 +98,8 @@ def triage_image_file(input_file, output_file, options):
             img2pdf.convert(
                 os.fspath(input_file),
                 layout_fun=layout_fun,
-                with_pdfrw=False,
                 outputstream=outf,
+                **IMG2PDF_KWARGS,
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
@@ -612,7 +612,7 @@ def create_pdf_page_from_image(
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
+            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
         )
         log.debug('convert done')
 

src/ocrmypdf/helpers.py

@@ -19,10 +19,21 @@ from math import isclose, isfinite
 from pathlib import Path
 from typing import Any, Sequence
 
+import img2pdf
 import pikepdf
+from packaging.version import Version
 
 log = logging.getLogger(__name__)
 
+if Version(img2pdf.__version__) < Version('0.4.0'):
+    IMG2PDF_KWARGS = dict(without_pdfw=True)
+elif Version(img2pdf.__version__) < Version('0.4.3'):
+    IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf)
+else:
+    IMG2PDF_KWARGS = dict(
+        engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid
+    )
+
 
 class Resolution(namedtuple('Resolution', ('x', 'y'))):
     """The number of pixels per inch in each 2D direction.

src/ocrmypdf/optimize.py

@@ -41,7 +41,7 @@ from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf.exceptions import OutputFileAccessError
-from ocrmypdf.helpers import safe_symlink
+from ocrmypdf.helpers import IMG2PDF_KWARGS, safe_symlink
 
 log = logging.getLogger(__name__)
 
@@ -453,7 +453,7 @@ def transcode_jpegs(
 def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
     output = filename.with_suffix('.png.pdf')
     with output.open('wb') as f:
-        img2pdf.convert(fspath(filename), outputstream=f)
+        img2pdf.convert(fspath(filename), outputstream=f, **IMG2PDF_KWARGS)
 
     with Pdf.open(output) as pdf_image:
         foreign_image = next(iter(pdf_image.pages[0].images.values()))

tests/test_optimize.py

@@ -17,7 +17,7 @@ from PIL import Image, ImageDraw
 from ocrmypdf import optimize as opt
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._exec.ghostscript import rasterize_pdf
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 
 from .conftest import check_ocrmypdf
 
@@ -139,8 +139,8 @@ def test_multiple_pngs(resources, outdir):
         img2pdf.convert(
             fspath(resources / 'baiona_colormapped.png'),
             fspath(resources / 'baiona_gray.png'),
-            with_pdfrw=False,
             outputstream=inpdf,
+            **IMG2PDF_KWARGS,
         )
 
     def mockquant(input_file, output_file, *_args):

tests/test_pdfinfo.py

@@ -17,7 +17,7 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf import pdfinfo
 from ocrmypdf.exceptions import InputFileError
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 from ocrmypdf.pdfinfo import Colorspace, Encoding
 from ocrmypdf.pdfinfo.layout import PDFPage
 
@@ -67,9 +67,9 @@ def test_single_page_image(eight_by_eight, outpdf):
         img2pdf.convert(
             bio,
             producer="img2pdf",
-            with_pdfrw=False,
             layout_fun=layout_fun,
             outputstream=f,
+            **IMG2PDF_KWARGS,
         )
     info = pdfinfo.PdfInfo(outpdf)
 

tests/test_rotation.py

@@ -18,7 +18,7 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf._exec import ghostscript
 from ocrmypdf._plugin_manager import get_plugin_manager
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 from ocrmypdf.pdfinfo import PdfInfo
 
 from .conftest import check_ocrmypdf, run_ocrmypdf
@@ -230,6 +230,7 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
             memimg.read(),
             layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
             outputstream=mempdf,
+            **IMG2PDF_KWARGS,
         )
         mempdf.seek(0)
         pike = pikepdf.open(mempdf)