From a31f17bb9d44c961b01a3d7492162962c661ee5d Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Sat, 21 Oct 2023 01:34:41 -0700
Subject: [PATCH] Update comments and make worker functions private

---
 src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py | 10 ++++++----
 src/ocrmypdf/_pipelines/ocr.py             |  5 ++---
 src/ocrmypdf/_pipelines/pdf_to_hocr.py     |  5 +++--
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py b/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
index 7781b5a2..a0cd67dd 100644
--- a/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
+++ b/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
@@ -39,7 +39,8 @@ from ocrmypdf.exceptions import ExitCode
 log = logging.getLogger(__name__)
 
 
-def exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
+def _exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
+    """Process each page."""
     hocr_json = page_context.get_path('hocr.json')
     if not hocr_json.exists():
         # No hOCR file, so no OCR was performed on this page.
@@ -52,7 +53,7 @@ def exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
 
 
 def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Execute the OCR pipeline concurrently and output hOCR."""
+    """Convert hOCR files to OCR PDF."""
     # Run exec_page_sync on every page
     options = context.options
     max_workers = min(len(context.pdfinfo), options.jobs)
@@ -62,7 +63,7 @@ def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[st
     ocrgraft = OcrGrafter(context)
 
     def graft_page(result: HOCRResult, pbar: ProgressBar):
-        """After OCR is complete for a page, update the PDF."""
+        """Graft text only PDF on to main PDF's page."""
         try:
             set_thread_pageno(result.pageno + 1)
             pbar.update()
@@ -87,7 +88,7 @@ def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[st
             disable=not options.progress_bar,
         ),
         worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=exec_hocrtransform_sync,
+        task=_exec_hocrtransform_sync,
         task_arguments=context.get_page_context_args(),
         task_finished=graft_page,
     )
@@ -109,6 +110,7 @@ def run_hocr_to_ocr_pdf_pipeline(
     *,
     plugin_manager: OcrmypdfPluginManager,
 ) -> ExitCode:
+    """Run pipeline to convert hOCR to final output PDF."""
     with manage_work_folder(
         work_folder=options.work_folder, retain=True, print_location=False
     ) as work_folder:
diff --git a/src/ocrmypdf/_pipelines/ocr.py b/src/ocrmypdf/_pipelines/ocr.py
index 1b6fbc97..cb37bf0d 100644
--- a/src/ocrmypdf/_pipelines/ocr.py
+++ b/src/ocrmypdf/_pipelines/ocr.py
@@ -69,7 +69,7 @@ def _image_to_ocr_text(
     return ocr_out, text_out
 
 
-def exec_page_sync(page_context: PageContext) -> PageResult:
+def _exec_page_sync(page_context: PageContext) -> PageResult:
     """Execute a pipeline for a single page synchronously."""
     set_thread_pageno(page_context.pageno + 1)
 
@@ -92,7 +92,6 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
 
 def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
     """Execute the OCR pipeline concurrently."""
-    # Run exec_page_sync on every page
     options = context.options
     max_workers = min(len(context.pdfinfo), options.jobs)
     if max_workers > 1:
@@ -128,7 +127,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
             disable=not options.progress_bar,
         ),
         worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=exec_page_sync,
+        task=_exec_page_sync,
         task_arguments=context.get_page_context_args(),
         task_finished=update_page,
     )
diff --git a/src/ocrmypdf/_pipelines/pdf_to_hocr.py b/src/ocrmypdf/_pipelines/pdf_to_hocr.py
index 891878e6..fdc3b687 100644
--- a/src/ocrmypdf/_pipelines/pdf_to_hocr.py
+++ b/src/ocrmypdf/_pipelines/pdf_to_hocr.py
@@ -39,7 +39,7 @@ from ocrmypdf._validation import (
 log = logging.getLogger(__name__)
 
 
-def exec_page_hocr_sync(page_context: PageContext) -> HOCRResult:
+def _exec_page_hocr_sync(page_context: PageContext) -> HOCRResult:
     """Execute a pipeline for a single page hOCR."""
     set_thread_pageno(page_context.pageno + 1)
 
@@ -80,7 +80,7 @@ def exec_pdf_to_hocr(context: PdfContext, executor: Executor) -> None:
             disable=not options.progress_bar,
         ),
         worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=exec_page_hocr_sync,
+        task=_exec_page_hocr_sync,
         task_arguments=context.get_page_context_args(),
     )
 
@@ -90,6 +90,7 @@ def run_hocr_pipeline(
     *,
     plugin_manager: OcrmypdfPluginManager,
 ) -> None:
+    """Run pipeline to output hOCR."""
     with manage_work_folder(
         work_folder=options.output_folder, retain=True, print_location=False
     ) as work_folder: