From 9a6150ae535221345a6f69e720bb3fa97440badd Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Sun, 27 Oct 2024 12:09:33 -0700
Subject: [PATCH] Refactor get_pdfinfo common code

---
 src/ocrmypdf/_pipelines/_common.py         | 13 +++++++++++++
 src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py | 12 ++----------
 src/ocrmypdf/_pipelines/ocr.py             | 13 ++-----------
 src/ocrmypdf/_pipelines/pdf_to_hocr.py     | 15 ++++-----------
 4 files changed, 21 insertions(+), 32 deletions(-)

diff --git a/src/ocrmypdf/_pipelines/_common.py b/src/ocrmypdf/_pipelines/_common.py
index 24077bdf..0044d0a4 100644
--- a/src/ocrmypdf/_pipelines/_common.py
+++ b/src/ocrmypdf/_pipelines/_common.py
@@ -33,6 +33,7 @@ from ocrmypdf._pipeline import (
     generate_postscript_stub,
     get_orientation_correction,
     get_pdf_save_settings,
+    get_pdfinfo,
     optimize_pdf,
     preprocess_clean,
     preprocess_deskew,
@@ -315,6 +316,18 @@ def setup_pipeline(
     return executor
 
 
+def do_get_pdfinfo(pdf, executor, options):
+    return get_pdfinfo(
+        pdf,
+        executor=executor,
+        detailed_analysis=options.redo_ocr,
+        progbar=options.progress_bar,
+        max_workers=options.jobs,
+        use_threads=options.use_threads,
+        check_pages=options.pages,
+    )
+
+
 def preprocess(
     page_context: PageContext,
     image: Path,
diff --git a/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py b/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
index 910915a0..c6fb5e38 100644
--- a/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
+++ b/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
@@ -19,11 +19,11 @@ from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
     copy_final,
-    get_pdfinfo,
     render_hocr_page,
 )
 from ocrmypdf._pipelines._common import (
     HOCRResult,
+    do_get_pdfinfo,
     manage_work_folder,
     postprocess,
     report_output_pdf,
@@ -117,15 +117,7 @@ def run_hocr_to_ocr_pdf_pipeline(
         origin_pdf = work_folder / 'origin.pdf'
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
         context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
         plugin_manager.hook.check_options(options=options)
         optimize_messages = exec_hocr_to_ocr_pdf(context, executor)
diff --git a/src/ocrmypdf/_pipelines/ocr.py b/src/ocrmypdf/_pipelines/ocr.py
index d6dc00a0..e742dce0 100644
--- a/src/ocrmypdf/_pipelines/ocr.py
+++ b/src/ocrmypdf/_pipelines/ocr.py
@@ -21,7 +21,6 @@ from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
     copy_final,
-    get_pdfinfo,
     is_ocr_required,
     merge_sidecars,
     ocr_engine_hocr,
@@ -33,6 +32,7 @@ from ocrmypdf._pipeline import (
 from ocrmypdf._pipelines._common import (
     PageResult,
     cli_exception_handler,
+    do_get_pdfinfo,
     manage_debug_log_handler,
     manage_work_folder,
     postprocess,
@@ -171,16 +171,7 @@ def _run_pipeline(
         )
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
-
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
         context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
 
         # Validate options are okay for this pdf
diff --git a/src/ocrmypdf/_pipelines/pdf_to_hocr.py b/src/ocrmypdf/_pipelines/pdf_to_hocr.py
index 7005d4ff..457d144c 100644
--- a/src/ocrmypdf/_pipelines/pdf_to_hocr.py
+++ b/src/ocrmypdf/_pipelines/pdf_to_hocr.py
@@ -17,13 +17,13 @@ import PIL
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
-    get_pdfinfo,
     is_ocr_required,
     ocr_engine_hocr,
     validate_pdfinfo_options,
 )
 from ocrmypdf._pipelines._common import (
     HOCRResult,
+    do_get_pdfinfo,
     manage_work_folder,
     process_page,
     set_thread_pageno,
@@ -94,18 +94,11 @@ def run_hocr_pipeline(
         work_folder=options.output_folder, retain=True, print_location=False
     ) as work_folder:
         executor = setup_pipeline(options, plugin_manager)
-        shutil.copy2(options.input_file, work_folder / 'origin.pdf')
+        origin_pdf = work_folder / 'origin.pdf'
+        shutil.copy2(options.input_file, origin_pdf)
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            options.input_file,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
         context = PdfContext(
             options, work_folder, options.input_file, pdfinfo, plugin_manager
         )