Refactor get_pdfinfo common code

This commit is contained in:
James R. Barlow
2024-10-27 12:09:33 -07:00
parent fec0948a13
commit 9a6150ae53
4 changed files with 21 additions and 32 deletions
+13
View File
@@ -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,
+2 -10
View File
@@ -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)
+2 -11
View File
@@ -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
+4 -11
View File
@@ -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
)