Move optimize into a builtin plugin

src/ocrmypdf/_pipeline.py

@@ -35,7 +35,6 @@ from ocrmypdf.exceptions import (
 )
 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
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 
@@ -833,12 +832,18 @@ def metadata_fixup(working_file: Path, context: PdfContext):
 
 def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
     output_file = context.get_path('optimize.pdf')
-    save_settings = dict(
-        linearize=should_linearize(input_file, context),
-        **get_pdf_save_settings(context.options.output_type),
+    output_pdf = context.plugin_manager.hook.optimize_pdf(
+        input_pdf=input_file, output_pdf=output_file, context=context, executor=executor
     )
-    optimize(input_file, output_file, context, save_settings, executor)
-    return output_file
+
+    input_size = input_file.stat().st_size
+    output_size = output_file.stat().st_size
+    if output_size > 0:
+        ratio = input_size / output_size
+        savings = 1 - output_size / input_size
+        log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
+
+    return output_pdf
 
 
 def enumerate_compress_ranges(iterable):

src/ocrmypdf/builtin_plugins/optimize.py

@@ -0,0 +1,27 @@
+# © 2022 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Built-in plugin to implement PDF page optimization."""
+
+from pathlib import Path
+
+from ocrmypdf import PdfContext, hookimpl
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._pipeline import get_pdf_save_settings, should_linearize
+from ocrmypdf.optimize import optimize
+
+
+@hookimpl
+def optimize_pdf(
+    input_pdf: Path, output_pdf: Path, context: PdfContext, executor: Executor
+) -> Path:
+    save_settings = dict(
+        linearize=should_linearize(input_pdf, context),
+        **get_pdf_save_settings(context.options.output_type),
+    )
+    optimize(input_pdf, output_pdf, context, save_settings, executor)
+    return output_pdf

src/ocrmypdf/optimize.py

@@ -625,7 +625,7 @@ def optimize(
     context,
     save_settings,
     executor: Executor = DEFAULT_EXECUTOR,
-) -> None:
+) -> Path:
     options = context.options
     if options.optimize == 0:
         safe_symlink(input_file, output_file)
@@ -664,9 +664,7 @@ def optimize(
             f"Output file not created after optimizing. We probably ran "
             f"out of disk space in the temporary folder: {tempfile.gettempdir()}."
         )
-    ratio = input_size / output_size
     savings = 1 - output_size / input_size
-    log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
 
     if savings < 0:
         log.info(
@@ -680,6 +678,8 @@ def optimize(
     else:
         safe_symlink(target_file, output_file)
 
+    return output_file
+
 
 def main(infile, outfile, level, jobs=1):
     from shutil import copy  # pylint: disable=import-outside-toplevel

src/ocrmypdf/pluginspec.py

@@ -14,6 +14,7 @@ from typing import TYPE_CHECKING, AbstractSet, List, NamedTuple, Optional
 
 import pluggy
 
+from ocrmypdf import PdfContext
 from ocrmypdf._concurrent import Executor
 from ocrmypdf.helpers import Resolution
 
@@ -457,3 +458,33 @@ def generate_pdfa(
     See also:
         https://github.com/tqdm/tqdm
     """
+
+
+@hookspec(firstresult=True)
+def optimize_pdf(
+    input_pdf: Path, output_pdf: Path, context: PdfContext, executor: Executor
+) -> Path:
+    """Optimize a PDF after image, OCR and metadata processing.
+
+    If the input_pdf is a PDF/A, the plugin must only modify input_pdf in a way
+    that preserves the PDF/A status.
+
+    If the implementation fails to produce a smaller file than the input file, it
+    should return input_pdf instead.
+
+    Arguments:
+        input_pdf: The input PDF, which has OCR added.
+        output_pdf: The requested filename of the output PDF which should be created
+            by this optimization hook.
+        context: The current context.
+        executor: An initialized executor which may be used during optimization,
+            to distribute optimization tasks.
+
+    Returns:
+        Path: If optimization is successful, the hook should return ``output_file``.
+            If optimization does not produce a smaller file, the hook should return
+            ``input_file``.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """