Support plugin invocation with API

tests/conftest.py

@@ -214,7 +214,7 @@ def no_outpdf(tmp_path):
 def check_ocrmypdf(input_file, output_file, *args, env=None):
     """Run ocrmypdf and confirmed that a valid file was created"""
 
-    options = cli.parser.parse_args(
+    options = cli.get_parser().parse_args(
         [str(input_file), str(output_file)]
         + [str(arg) for arg in args if arg is not None]
     )
@@ -222,7 +222,7 @@ def check_ocrmypdf(input_file, output_file, *args, env=None):
     if env:
         options.tesseract_env = env
         options.tesseract_env['_OCRMYPDF_TEST_INFILE'] = os.fspath(input_file)
-    result = api.run_pipeline(options, api=True)
+    result = api.run_pipeline(options, plugin_manager=None, api=True)
 
     assert result == 0
     assert os.path.exists(str(output_file)), "Output file not created"
@@ -238,7 +238,7 @@ def run_ocrmypdf_api(input_file, output_file, *args, env=None):
     Does not currently have a way to manipulate the PATH except for Tesseract.
     """
 
-    options = cli.parser.parse_args(
+    options = cli.get_parser().parse_args(
         [str(input_file), str(output_file)]
         + [str(arg) for arg in args if arg is not None]
     )
@@ -253,7 +253,7 @@ def run_ocrmypdf_api(input_file, output_file, *args, env=None):
     if options.tesseract_env:
         assert all(isinstance(v, (str, bytes)) for v in options.tesseract_env.values())
 
-    return api.run_pipeline(options, api=False)
+    return api.run_pipeline(options, plugin_manager=None, api=False)
 
 
 @pytest.helpers.register

tests/test_metadata.py

@@ -32,7 +32,7 @@ from pikepdf.models.metadata import decode_pdf_date
 
 from ocrmypdf._jobcontext import PDFContext
 from ocrmypdf._pipeline import convert_to_pdfa
-from ocrmypdf.cli import parser
+from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.pdfa import SRGB_ICC_PROFILE, file_claims_pdfa, generate_pdfa_ps
 from ocrmypdf.pdfinfo import PdfInfo
@@ -290,16 +290,15 @@ def test_kodak_toc(resources, outpdf, spoof_tesseract_noop):
 
 
 def test_metadata_fixup_warning(resources, outdir, caplog):
-    from ocrmypdf.__main__ import parser
     from ocrmypdf._pipeline import metadata_fixup
 
-    options = parser.parse_args(
+    options = get_parser().parse_args(
         args=['--output-type', 'pdfa-2', 'graph.pdf', 'out.pdf']
     )
 
     copyfile(resources / 'graph.pdf', outdir / 'graph.pdf')
 
-    context = PDFContext(options, outdir, outdir / 'graph.pdf', None)
+    context = PDFContext(options, outdir, outdir / 'graph.pdf', None, None)
     metadata_fixup(working_file=outdir / 'graph.pdf', context=context)
     for record in caplog.records:
         assert record.levelname != 'WARNING'
@@ -310,7 +309,7 @@ def test_metadata_fixup_warning(resources, outdir, caplog):
         meta['prism2:publicationName'] = 'OCRmyPDF Test'
     graph.save(outdir / 'graph_mod.pdf')
 
-    context = PDFContext(options, outdir, outdir / 'graph_mod.pdf', None)
+    context = PDFContext(options, outdir, outdir / 'graph_mod.pdf', None, None)
     metadata_fixup(working_file=outdir / 'graph.pdf', context=context)
     assert any(record.levelname == 'WARNING' for record in caplog.records)
 
@@ -326,11 +325,11 @@ def test_prevent_gs_invalid_xml(resources, outdir):
             Title=b'String with trailing nul\x00'
         )
 
-    options = parser.parse_args(
+    options = get_parser().parse_args(
         args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
     )
     pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
-    context = PDFContext(options, outdir, outdir / 'layers.rendered.pdf', pdfinfo)
+    context = PDFContext(options, outdir, outdir / 'layers.rendered.pdf', pdfinfo, None)
 
     convert_to_pdfa(
         str(outdir / 'layers.rendered.pdf'), str(outdir / 'pdfa.ps'), context
@@ -357,11 +356,11 @@ def test_malformed_docinfo(caplog, resources, outdir):
         pike.trailer.Info = pikepdf.Stream(pike, b"<xml></xml>")
         pike.save(outdir / 'layers.rendered.pdf', fix_metadata_version=False)
 
-    options = parser.parse_args(
+    options = get_parser().parse_args(
         args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
     )
     pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
-    context = PDFContext(options, outdir, outdir / 'layers.rendered.pdf', pdfinfo)
+    context = PDFContext(options, outdir, outdir / 'layers.rendered.pdf', pdfinfo, None)
 
     convert_to_pdfa(
         str(outdir / 'layers.rendered.pdf'), str(outdir / 'pdfa.ps'), context

tests/test_unpaper.py

@@ -21,7 +21,7 @@ from unittest.mock import patch
 import pytest
 
 from ocrmypdf._validation import check_options
-from ocrmypdf.cli import parser
+from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 from ocrmypdf.exec import unpaper
 
@@ -51,7 +51,7 @@ def spoof_unpaper_oldversion(tmp_path_factory):
 def test_no_unpaper(resources, no_outpdf):
     input_ = fspath(resources / "c02-22.pdf")
     output = fspath(no_outpdf)
-    options = parser.parse_args(args=["--clean", input_, output])
+    options = get_parser().parse_args(args=["--clean", input_, output])
 
     with patch("ocrmypdf.exec.unpaper.version") as mock_unpaper_version:
         mock_unpaper_version.side_effect = FileNotFoundError("unpaper")

tests/test_validation.py

@@ -23,6 +23,7 @@ import pytest
 
 import ocrmypdf._validation as vd
 from ocrmypdf.api import create_options
+from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.pdfinfo import PdfInfo
 
@@ -30,7 +31,9 @@ from ocrmypdf.pdfinfo import PdfInfo
 def make_opts(input_file='a.pdf', output_file='b.pdf', language='eng', **kwargs):
     if language is not None:
         kwargs['language'] = language
-    return create_options(input_file=input_file, output_file=output_file, **kwargs)
+    return create_options(
+        input_file=input_file, output_file=output_file, parser=get_parser(), **kwargs
+    )
 
 
 def test_hocr_notlatin_warning(caplog):