Remove duplicate thread local storage of page numbers

src/ocrmypdf/_pipelines/_common.py

@@ -10,13 +10,14 @@ import logging.handlers
 import os
 import shutil
 import sys
+import threading
 from collections.abc import Sequence
 from concurrent.futures.process import BrokenProcessPool
 from concurrent.futures.thread import BrokenThreadPool
 from contextlib import contextmanager
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, Callable, NamedTuple, cast
+from typing import Callable, NamedTuple, cast
 
 import PIL
 
@@ -39,7 +40,7 @@ from ocrmypdf._pipeline import (
     rasterize_preview,
     should_visible_page_image_use_jpg,
 )
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager, get_plugin_manager
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
 from ocrmypdf._validation import (
     report_output_file_size,
 )
@@ -53,11 +54,12 @@ from ocrmypdf.helpers import (
 from ocrmypdf.pdfa import file_claims_pdfa
 
 log = logging.getLogger(__name__)
+tls = threading.local()
+tls.pageno = None
 
-
-def set_logging_tls(tls):
+def _set_logging_tls(tls):
+    """Inject current page number (when available) into log records."""
     old_factory = logging.getLogRecordFactory()
-
     def wrapper(*args, **kwargs):
         record = old_factory(*args, **kwargs)
         if hasattr(tls, 'pageno'):
@@ -67,6 +69,14 @@ def set_logging_tls(tls):
     logging.setLogRecordFactory(wrapper)
 
 
+_set_logging_tls(tls)
+
+
+def set_thread_pageno(pageno:int):
+    """Set page number (1-based) that the current thread is processing."""
+    tls.pageno = pageno
+
+
 class PageResult(NamedTuple):
     """Result when a page is finished processing."""
 

src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py

@@ -10,8 +10,6 @@ from __future__ import annotations
 import argparse
 import logging
 import logging.handlers
-import shutil
-import threading
 from collections.abc import Sequence
 from functools import partial
 
@@ -24,14 +22,13 @@ from ocrmypdf._pipeline import (
     copy_final,
     get_pdfinfo,
     render_hocr_page,
-    validate_pdfinfo_options,
 )
 from ocrmypdf._pipelines._common import (
     HOCRResult,
     manage_work_folder,
     postprocess,
     report_output_pdf,
-    set_logging_tls,
+    set_thread_pageno,
     setup_pipeline,
     worker_init,
 )
@@ -41,12 +38,6 @@ from ocrmypdf.exceptions import ExitCode
 log = logging.getLogger(__name__)
 
 
-tls = threading.local()
-tls.pageno = None
-
-set_logging_tls(tls)
-
-
 def exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
     hocr_result = HOCRResult.from_json(page_context.get_path('hocr.json').read_text())
     hocr_result.textpdf = render_hocr_page(
@@ -68,7 +59,7 @@ def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[st
     def graft_page(result: HOCRResult, pbar):
         """After OCR is complete for a page, update the PDF."""
         try:
-            tls.pageno = result.pageno + 1
+            set_thread_pageno(result.pageno + 1)
             pbar.update()
             ocrgraft.graft_page(
                 pageno=result.pageno,
@@ -78,7 +69,7 @@ def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[st
             )
             pbar.update()
         finally:
-            tls.pageno = None
+            set_thread_pageno(None)
 
     executor(
         use_threads=options.use_threads,

src/ocrmypdf/_pipelines/ocr.py

@@ -40,7 +40,7 @@ from ocrmypdf._pipelines._common import (
     postprocess,
     process_page,
     report_output_pdf,
-    set_logging_tls,
+    set_thread_pageno,
     setup_pipeline,
     worker_init,
 )
@@ -54,12 +54,6 @@ from ocrmypdf.exceptions import ExitCode
 log = logging.getLogger(__name__)
 
 
-tls = threading.local()
-tls.pageno = None
-
-set_logging_tls(tls)
-
-
 def _image_to_ocr_text(
     page_context: PageContext, ocr_image_out: Path
 ) -> tuple[Path, Path]:
@@ -77,7 +71,7 @@ def _image_to_ocr_text(
 
 def exec_page_sync(page_context: PageContext) -> PageResult:
     """Execute a pipeline for a single page synchronously."""
-    tls.pageno = page_context.pageno + 1
+    set_thread_pageno(page_context.pageno + 1)
 
     if not is_ocr_required(page_context):
         return PageResult(pageno=page_context.pageno)
@@ -110,7 +104,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
     def update_page(result: PageResult, pbar):
         """After OCR is complete for a page, update the PDF."""
         try:
-            tls.pageno = result.pageno + 1
+            set_thread_pageno(result.pageno + 1)
             sidecars[result.pageno] = result.text
             pbar.update()
             ocrgraft.graft_page(
@@ -121,7 +115,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
             )
             pbar.update()
         finally:
-            tls.pageno = None
+            set_thread_pageno(None)
 
     executor(
         use_threads=options.use_threads,

src/ocrmypdf/_pipelines/pdf_to_hocr.py

@@ -28,7 +28,7 @@ from ocrmypdf._pipelines._common import (
     HOCRResult,
     manage_work_folder,
     process_page,
-    set_logging_tls,
+    set_thread_pageno,
     setup_pipeline,
     worker_init,
 )
@@ -39,15 +39,11 @@ from ocrmypdf._validation import (
 
 log = logging.getLogger(__name__)
 
-tls = threading.local()
-tls.pageno = None
-
-set_logging_tls(tls)
 
 
 def exec_page_hocr_sync(page_context: PageContext) -> HOCRResult:
     """Execute a pipeline for a single page hOCR."""
-    tls.pageno = page_context.pageno + 1
+    set_thread_pageno(page_context.pageno + 1)
 
     if not is_ocr_required(page_context):
         return HOCRResult(pageno=page_context.pageno)